diff options
446 files changed, 21954 insertions, 10926 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/Documentation/devicetree/bindings/net/amlogic,g12a-mdio-mux.yaml b/Documentation/devicetree/bindings/net/amlogic,g12a-mdio-mux.yaml new file mode 100644 index 000000000000..ec5c038ce6a0 --- /dev/null +++ b/Documentation/devicetree/bindings/net/amlogic,g12a-mdio-mux.yaml @@ -0,0 +1,80 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/amlogic,g12a-mdio-mux.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MDIO bus multiplexer/glue of Amlogic G12a SoC family + +description: + This is a special case of a MDIO bus multiplexer. It allows to choose between + the internal mdio bus leading to the embedded 10/100 PHY or the external + MDIO bus. + +maintainers: + - Neil Armstrong <neil.armstrong@linaro.org> + +allOf: + - $ref: mdio-mux.yaml# + +properties: + compatible: + const: amlogic,g12a-mdio-mux + + reg: + maxItems: 1 + + clocks: + items: + - description: peripheral clock + - description: platform crytal + - description: SoC 50MHz MPLL + + clock-names: + items: + - const: pclk + - const: clkin0 + - const: clkin1 + +required: + - compatible + - reg + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + #include <dt-bindings/interrupt-controller/arm-gic.h> + mdio-multiplexer@4c000 { + compatible = "amlogic,g12a-mdio-mux"; + reg = <0x4c000 0xa4>; + clocks = <&clkc_eth_phy>, <&xtal>, <&clkc_mpll>; + clock-names = "pclk", "clkin0", "clkin1"; + mdio-parent-bus = <&mdio0>; + #address-cells = <1>; + #size-cells = <0>; + + mdio@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + }; + + mdio@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@8 { + compatible = "ethernet-phy-id0180.3301", + "ethernet-phy-ieee802.3-c22"; + interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; + reg = <8>; + max-speed = <100>; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/net/dsa/arrow,xrs700x.yaml b/Documentation/devicetree/bindings/net/dsa/arrow,xrs700x.yaml index 2a6d126606ca..9565a7402146 100644 --- a/Documentation/devicetree/bindings/net/dsa/arrow,xrs700x.yaml +++ b/Documentation/devicetree/bindings/net/dsa/arrow,xrs700x.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Arrow SpeedChips XRS7000 Series Switch allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports maintainers: - George McCollister <george.mccollister@gmail.com> diff --git a/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml b/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml index 1219b830b1a4..5bef4128d175 100644 --- a/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml +++ b/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml @@ -66,7 +66,7 @@ required: - reg allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml b/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml index d159ac78cec1..eed16e216fb6 100644 --- a/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml +++ b/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml @@ -85,11 +85,16 @@ properties: ports: type: object - properties: - brcm,use-bcm-hdr: - description: if present, indicates that the switch port has Broadcom - tags enabled (per-packet metadata) - type: boolean + patternProperties: + '^port@[0-9a-f]$': + $ref: dsa-port.yaml# + unevaluatedProperties: false + + properties: + brcm,use-bcm-hdr: + description: if present, indicates that the switch port has Broadcom + tags enabled (per-packet metadata) + type: boolean required: - reg diff --git a/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml b/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml index b173fceb8998..480120469953 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml +++ b/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml @@ -4,18 +4,19 @@ $id: http://devicetree.org/schemas/net/dsa/dsa-port.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Ethernet Switch port +title: Generic DSA Switch Port maintainers: - Andrew Lunn <andrew@lunn.ch> - Florian Fainelli <f.fainelli@gmail.com> - - Vivien Didelot <vivien.didelot@gmail.com> + - Vladimir Oltean <olteanv@gmail.com> description: - Ethernet switch port Description + A DSA switch port is a component of a switch that manages one MAC, and can + pass Ethernet frames. It can act as a stanadard Ethernet switch port, or have + DSA-specific functionality. -allOf: - - $ref: /schemas/net/ethernet-controller.yaml# +$ref: /schemas/net/ethernet-switch-port.yaml# properties: reg: @@ -58,25 +59,6 @@ properties: - rtl8_4t - seville - phy-handle: true - - phy-mode: true - - fixed-link: true - - mac-address: true - - sfp: true - - managed: true - - rx-internal-delay-ps: true - - tx-internal-delay-ps: true - -required: - - reg - # CPU and DSA ports must have phylink-compatible link descriptions if: oneOf: diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml index 5469ae8a4389..8d971813bab6 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml +++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml @@ -9,7 +9,7 @@ title: Ethernet Switch maintainers: - Andrew Lunn <andrew@lunn.ch> - Florian Fainelli <f.fainelli@gmail.com> - - Vivien Didelot <vivien.didelot@gmail.com> + - Vladimir Oltean <olteanv@gmail.com> description: This binding represents Ethernet Switches which have a dedicated CPU @@ -18,10 +18,9 @@ description: select: false -properties: - $nodename: - pattern: "^(ethernet-)?switch(@.*)?$" +$ref: /schemas/net/ethernet-switch.yaml# +properties: dsa,member: minItems: 2 maxItems: 2 @@ -32,30 +31,28 @@ properties: (single device hanging off a CPU port) must not specify this property $ref: /schemas/types.yaml#/definitions/uint32-array -patternProperties: - "^(ethernet-)?ports$": - type: object - properties: - '#address-cells': - const: 1 - '#size-cells': - const: 0 +additionalProperties: true + +$defs: + ethernet-ports: + description: A DSA switch without any extra port properties + $ref: '#/' patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?ports$": type: object - description: Ethernet switch ports - - $ref: dsa-port.yaml# - - unevaluatedProperties: false - -oneOf: - - required: - - ports - - required: - - ethernet-ports - -additionalProperties: true + additionalProperties: false + + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^(ethernet-)?port@[0-9]+$": + description: Ethernet switch ports + $ref: dsa-port.yaml# + unevaluatedProperties: false ... diff --git a/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml b/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml index 447589b01e8e..4021b054f684 100644 --- a/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Hirschmann Hellcreek TSN Switch allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports maintainers: - Andrew Lunn <andrew@lunn.ch> diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml index f2e9ff3f580b..08667bff74a5 100644 --- a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml +++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml @@ -157,9 +157,6 @@ patternProperties: patternProperties: "^(ethernet-)?port@[0-9]+$": type: object - description: Ethernet switch ports - - unevaluatedProperties: false properties: reg: @@ -168,7 +165,6 @@ patternProperties: for user ports. allOf: - - $ref: dsa-port.yaml# - if: required: [ ethernet ] then: @@ -238,7 +234,7 @@ $defs: - sgmii allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports - if: required: - mediatek,mcm diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 4da75b1f9533..a4b53434c85c 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -11,7 +11,7 @@ maintainers: - Woojung Huh <Woojung.Huh@microchip.com> allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports - $ref: /schemas/spi/spi-peripheral-props.yaml# properties: diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml index b34de303966b..8d7e878b84dc 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml @@ -10,7 +10,7 @@ maintainers: - UNGLinuxDriver@microchip.com allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports properties: compatible: diff --git a/Documentation/devicetree/bindings/net/dsa/mscc,ocelot.yaml b/Documentation/devicetree/bindings/net/dsa/mscc,ocelot.yaml index 347a0e1b3d3f..fe02d05196e4 100644 --- a/Documentation/devicetree/bindings/net/dsa/mscc,ocelot.yaml +++ b/Documentation/devicetree/bindings/net/dsa/mscc,ocelot.yaml @@ -78,7 +78,7 @@ required: - reg allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index df98a16e4e75..9a64ed658745 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -13,7 +13,7 @@ description: depends on the SPI bus master driver. allOf: - - $ref: "dsa.yaml#" + - $ref: dsa.yaml#/$defs/ethernet-ports - $ref: /schemas/spi/spi-peripheral-props.yaml# maintainers: diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.yaml b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml index 978162df51f7..389892592aac 100644 --- a/Documentation/devicetree/bindings/net/dsa/qca8k.yaml +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml @@ -66,15 +66,11 @@ properties: With the legacy mapping the reg corresponding to the internal mdio is the switch reg with an offset of -1. +$ref: "dsa.yaml#" + patternProperties: "^(ethernet-)?ports$": type: object - properties: - '#address-cells': - const: 1 - '#size-cells': - const: 0 - patternProperties: "^(ethernet-)?port@[0-6]$": type: object @@ -116,7 +112,7 @@ required: - compatible - reg -additionalProperties: true +unevaluatedProperties: false examples: - | @@ -148,8 +144,6 @@ examples: switch@10 { compatible = "qca,qca8337"; - #address-cells = <1>; - #size-cells = <0>; reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; reg = <0x10>; @@ -209,8 +203,6 @@ examples: switch@10 { compatible = "qca,qca8337"; - #address-cells = <1>; - #size-cells = <0>; reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; reg = <0x10>; diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml index 1a7d45a8ad66..cfd69c2604ea 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Realtek switches for unmanaged switches allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports maintainers: - Linus Walleij <linus.walleij@linaro.org> diff --git a/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml b/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml index 0a0d62b6c00e..833d2f68daa1 100644 --- a/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml +++ b/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml @@ -14,7 +14,7 @@ description: | handles 4 ports + 1 CPU management port. allOf: - - $ref: dsa.yaml# + - $ref: dsa.yaml#/$defs/ethernet-ports properties: compatible: diff --git a/Documentation/devicetree/bindings/net/ethernet-switch-port.yaml b/Documentation/devicetree/bindings/net/ethernet-switch-port.yaml new file mode 100644 index 000000000000..d5cf7e40e3c3 --- /dev/null +++ b/Documentation/devicetree/bindings/net/ethernet-switch-port.yaml @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/ethernet-switch-port.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Generic Ethernet Switch Port + +maintainers: + - Andrew Lunn <andrew@lunn.ch> + - Florian Fainelli <f.fainelli@gmail.com> + - Vladimir Oltean <olteanv@gmail.com> + +description: + An Ethernet switch port is a component of a switch that manages one MAC, and + can pass Ethernet frames. + +$ref: ethernet-controller.yaml# + +properties: + reg: + description: Port number + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/net/ethernet-switch.yaml b/Documentation/devicetree/bindings/net/ethernet-switch.yaml new file mode 100644 index 000000000000..a04f8ef744aa --- /dev/null +++ b/Documentation/devicetree/bindings/net/ethernet-switch.yaml @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/ethernet-switch.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Generic Ethernet Switch + +maintainers: + - Andrew Lunn <andrew@lunn.ch> + - Florian Fainelli <f.fainelli@gmail.com> + - Vladimir Oltean <olteanv@gmail.com> + +description: + Ethernet switches are multi-port Ethernet controllers. Each port has + its own number and is represented as its own Ethernet controller. + The minimum required functionality is to pass packets to software. + They may or may not be able to forward packets automonously between + ports. + +select: false + +properties: + $nodename: + pattern: "^(ethernet-)?switch(@.*)?$" + +patternProperties: + "^(ethernet-)?ports$": + type: object + unevaluatedProperties: false + + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^(ethernet-)?port@[0-9]+$": + type: object + description: Ethernet switch ports + +oneOf: + - required: + - ports + - required: + - ethernet-ports + +additionalProperties: true + +$defs: + base: + description: An ethernet switch without any extra port properties + $ref: '#/' + + patternProperties: + "^(ethernet-)?port@[0-9]+$": + description: Ethernet switch ports + $ref: ethernet-switch-port.yaml# + unevaluatedProperties: false + +... diff --git a/Documentation/devicetree/bindings/net/fsl,fec.yaml b/Documentation/devicetree/bindings/net/fsl,fec.yaml index 77e5f32cb62f..e6f2045f05de 100644 --- a/Documentation/devicetree/bindings/net/fsl,fec.yaml +++ b/Documentation/devicetree/bindings/net/fsl,fec.yaml @@ -51,6 +51,7 @@ properties: - fsl,imx8mm-fec - fsl,imx8mn-fec - fsl,imx8mp-fec + - fsl,imx93-fec - const: fsl,imx8mq-fec - const: fsl,imx6sx-fec - items: diff --git a/Documentation/devicetree/bindings/net/maxlinear,gpy2xx.yaml b/Documentation/devicetree/bindings/net/maxlinear,gpy2xx.yaml new file mode 100644 index 000000000000..d71fa9de2b64 --- /dev/null +++ b/Documentation/devicetree/bindings/net/maxlinear,gpy2xx.yaml @@ -0,0 +1,47 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/maxlinear,gpy2xx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MaxLinear GPY2xx PHY + +maintainers: + - Andrew Lunn <andrew@lunn.ch> + - Michael Walle <michael@walle.cc> + +allOf: + - $ref: ethernet-phy.yaml# + +properties: + maxlinear,use-broken-interrupts: + description: | + Interrupts are broken on some GPY2xx PHYs in that they keep the + interrupt line asserted even after the interrupt status register is + cleared. Thus it is blocking the interrupt line which is usually bad + for shared lines. By default interrupts are disabled for this PHY and + polling mode is used. If one can live with the consequences, this + property can be used to enable interrupt handling. + + Affected PHYs (as far as known) are GPY215B and GPY215C. + type: boolean + +dependencies: + maxlinear,use-broken-interrupts: [ interrupts ] + +unevaluatedProperties: false + +examples: + - | + ethernet { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@0 { + reg = <0>; + interrupts-extended = <&intc 0>; + maxlinear,use-broken-interrupts; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/net/mdio-mux-meson-g12a.txt b/Documentation/devicetree/bindings/net/mdio-mux-meson-g12a.txt deleted file mode 100644 index 3a96cbed9294..000000000000 --- a/Documentation/devicetree/bindings/net/mdio-mux-meson-g12a.txt +++ /dev/null @@ -1,48 +0,0 @@ -Properties for the MDIO bus multiplexer/glue of Amlogic G12a SoC family. - -This is a special case of a MDIO bus multiplexer. It allows to choose between -the internal mdio bus leading to the embedded 10/100 PHY or the external -MDIO bus. - -Required properties in addition to the generic multiplexer properties: -- compatible : amlogic,g12a-mdio-mux -- reg: physical address and length of the multiplexer/glue registers -- clocks: list of clock phandle, one for each entry clock-names. -- clock-names: should contain the following: - * "pclk" : peripheral clock. - * "clkin0" : platform crytal - * "clkin1" : SoC 50MHz MPLL - -Example : - -mdio_mux: mdio-multiplexer@4c000 { - compatible = "amlogic,g12a-mdio-mux"; - reg = <0x0 0x4c000 0x0 0xa4>; - clocks = <&clkc CLKID_ETH_PHY>, - <&xtal>, - <&clkc CLKID_MPLL_5OM>; - clock-names = "pclk", "clkin0", "clkin1"; - mdio-parent-bus = <&mdio0>; - #address-cells = <1>; - #size-cells = <0>; - - ext_mdio: mdio@0 { - reg = <0>; - #address-cells = <1>; - #size-cells = <0>; - }; - - int_mdio: mdio@1 { - reg = <1>; - #address-cells = <1>; - #size-cells = <0>; - - internal_ephy: ethernet-phy@8 { - compatible = "ethernet-phy-id0180.3301", - "ethernet-phy-ieee802.3-c22"; - interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; - reg = <8>; - max-speed = <100>; - }; - }; -}; diff --git a/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml b/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml index ee0a504bdb24..5ffe831e59e4 100644 --- a/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml +++ b/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml @@ -18,10 +18,9 @@ description: | packets using CPU. Additionally, PTP is supported as well as FDMA for faster packet extraction/injection. -properties: - $nodename: - pattern: "^switch@[0-9a-f]+$" +$ref: ethernet-switch.yaml# +properties: compatible: const: mscc,vsc7514-switch @@ -100,35 +99,11 @@ properties: patternProperties: "^port@[0-9a-f]+$": - type: object - description: Ethernet ports handled by the switch - $ref: ethernet-controller.yaml# + $ref: ethernet-switch-port.yaml# unevaluatedProperties: false - properties: - reg: - description: Switch port number - - phy-handle: true - - phy-mode: true - - fixed-link: true - - mac-address: true - - required: - - reg - - phy-mode - - oneOf: - - required: - - phy-handle - - required: - - fixed-link - required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml index 04df496af7e6..63409cbff5ad 100644 --- a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml +++ b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/net/nxp,dwmac-imx.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: NXP i.MX8 DWMAC glue layer +title: NXP i.MX8/9 DWMAC glue layer maintainers: - Clark Wang <xiaoning.wang@nxp.com> @@ -19,6 +19,7 @@ select: enum: - nxp,imx8mp-dwmac-eqos - nxp,imx8dxl-dwmac-eqos + - nxp,imx93-dwmac-eqos required: - compatible @@ -32,6 +33,7 @@ properties: - enum: - nxp,imx8mp-dwmac-eqos - nxp,imx8dxl-dwmac-eqos + - nxp,imx93-dwmac-eqos - const: snps,dwmac-5.10a clocks: diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml index 42fb72b6909d..04936632fcbb 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml @@ -49,11 +49,11 @@ properties: - rockchip,rk3368-gmac - rockchip,rk3399-gmac - rockchip,rv1108-gmac - - rockchip,rv1126-gmac - items: - enum: - rockchip,rk3568-gmac - rockchip,rk3588-gmac + - rockchip,rv1126-gmac - const: snps,dwmac-4.20a clocks: diff --git a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml index 821974815dec..900063411a20 100644 --- a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml +++ b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml @@ -57,6 +57,7 @@ properties: - ti,am654-cpsw-nuss - ti,j7200-cpswxg-nuss - ti,j721e-cpsw-nuss + - ti,j721e-cpswxg-nuss - ti,am642-cpsw-nuss reg: @@ -111,7 +112,7 @@ properties: const: 0 patternProperties: - "^port@[1-4]$": + "^port@[1-8]$": type: object description: CPSWxG NUSS external ports @@ -121,7 +122,7 @@ properties: properties: reg: minimum: 1 - maximum: 4 + maximum: 8 description: CPSW port number phys: @@ -186,12 +187,36 @@ allOf: properties: compatible: contains: - const: ti,j7200-cpswxg-nuss + const: ti,j721e-cpswxg-nuss then: properties: ethernet-ports: patternProperties: - "^port@[3-4]$": false + "^port@[5-8]$": false + "^port@[1-4]$": + properties: + reg: + minimum: 1 + maximum: 4 + + - if: + not: + properties: + compatible: + contains: + enum: + - ti,j721e-cpswxg-nuss + - ti,j7200-cpswxg-nuss + then: + properties: + ethernet-ports: + patternProperties: + "^port@[3-8]$": false + "^port@[1-2]$": + properties: + reg: + minimum: 1 + maximum: 2 additionalProperties: false diff --git a/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml b/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml index 6230f576134b..3e910d3b24a0 100644 --- a/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml +++ b/Documentation/devicetree/bindings/net/ti,k3-am654-cpts.yaml @@ -93,6 +93,14 @@ properties: description: Number of timestamp Generator function outputs (TS_GENFx) + ti,pps: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 2 + maxItems: 2 + description: | + The pair of HWx_TS_PUSH input and TS_GENFy output indexes used for + PPS events generation. Platform/board specific. + refclk-mux: type: object additionalProperties: false diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 70ffb3780621..161766b1de50 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -775,6 +775,8 @@ patternProperties: description: MaxBotix Inc. "^maxim,.*": description: Maxim Integrated Products + "^maxlinear,.*": + description: MaxLinear Inc. "^mbvl,.*": description: Mobiveil Inc. "^mcube,.*": diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index dc2e60ced927..1aa029d08cb1 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -901,15 +901,17 @@ To enable/disable UDP Segmentation Offload, issue the following command:: # ethtool -K <ethX> tx-udp-segmentation [off|on] + GNSS module ----------- -Allows user to read messages from the GNSS module and write supported commands. -If the module is physically present, driver creates 2 TTYs for each supported -device in /dev, ttyGNSS_<device>:<function>_0 and _1. First one (_0) is RW and -the second one is RO. -The protocol of write commands is dependent on the GNSS module as the driver -writes raw bytes from the TTY to the GNSS i2c. Please refer to the module -documentation for details. +Requires kernel compiled with CONFIG_GNSS=y or CONFIG_GNSS=m. +Allows user to read messages from the GNSS hardware module and write supported +commands. If the module is physically present, a GNSS device is spawned: +``/dev/gnss<id>``. +The protocol of write command is dependent on the GNSS hardware module as the +driver writes raw bytes by the GNSS object to the receiver through i2c. Please +refer to the hardware GNSS module documentation for configuration details. + Performance Optimization ======================== diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index f10f8eb44255..d345f5df248e 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1004,6 +1004,9 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval ``ETHTOOL_A_COALESCE_USE_CQE_TX`` bool timer reset mode, Tx ``ETHTOOL_A_COALESCE_USE_CQE_RX`` bool timer reset mode, Rx + ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx + ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx + ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1022,6 +1025,17 @@ each packet event resets the timer. In this mode timer is used to force the interrupt if queue goes idle, while busy queues depend on the packet limit to trigger interrupts. +Tx aggregation consists of copying frames into a contiguous buffer so that they +can be submitted as a single IO operation. ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` +describes the maximum size in bytes for the submitted buffer. +``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` describes the maximum number of frames +that can be aggregated into a single buffer. +``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` describes the amount of time in usecs, +counted since the first packet arrival in an aggregated block, after which the +block should be sent. +This feature is mainly of interest for specific USB devices which does not cope +well with frequent small-sized URBs transmissions. + COALESCE_SET ============ @@ -1055,6 +1069,9 @@ Request contents: ``ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL`` u32 rate sampling interval ``ETHTOOL_A_COALESCE_USE_CQE_TX`` bool timer reset mode, Tx ``ETHTOOL_A_COALESCE_USE_CQE_RX`` bool timer reset mode, Rx + ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx + ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx + ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. @@ -1716,6 +1733,141 @@ being used. Current supported options are toeplitz, xor or crc32. ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte indicates queue number. +PLCA_GET_CFG +============ + +Gets the IEEE 802.3cg-2019 Clause 148 Physical Layer Collision Avoidance +(PLCA) Reconciliation Sublayer (RS) attributes. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PLCA_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ============================= + ``ETHTOOL_A_PLCA_HEADER`` nested reply header + ``ETHTOOL_A_PLCA_VERSION`` u16 Supported PLCA management + interface standard/version + ``ETHTOOL_A_PLCA_ENABLED`` u8 PLCA Admin State + ``ETHTOOL_A_PLCA_NODE_ID`` u32 PLCA unique local node ID + ``ETHTOOL_A_PLCA_NODE_CNT`` u32 Number of PLCA nodes on the + network, including the + coordinator + ``ETHTOOL_A_PLCA_TO_TMR`` u32 Transmit Opportunity Timer + value in bit-times (BT) + ``ETHTOOL_A_PLCA_BURST_CNT`` u32 Number of additional packets + the node is allowed to send + within a single TO + ``ETHTOOL_A_PLCA_BURST_TMR`` u32 Time to wait for the MAC to + transmit a new frame before + terminating the burst + ====================================== ====== ============================= + +When set, the optional ``ETHTOOL_A_PLCA_VERSION`` attribute indicates which +standard and version the PLCA management interface complies to. When not set, +the interface is vendor-specific and (possibly) supplied by the driver. +The OPEN Alliance SIG specifies a standard register map for 10BASE-T1S PHYs +embedding the PLCA Reconcialiation Sublayer. See "10BASE-T1S PLCA Management +Registers" at https://www.opensig.org/about/specifications/. + +When set, the optional ``ETHTOOL_A_PLCA_ENABLED`` attribute indicates the +administrative state of the PLCA RS. When not set, the node operates in "plain" +CSMA/CD mode. This option is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.1 +aPLCAAdminState / 30.16.1.2.1 acPLCAAdminControl. + +When set, the optional ``ETHTOOL_A_PLCA_NODE_ID`` attribute indicates the +configured local node ID of the PHY. This ID determines which transmit +opportunity (TO) is reserved for the node to transmit into. This option is +corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.4 aPLCALocalNodeID. The valid +range for this attribute is [0 .. 255] where 255 means "not configured". + +When set, the optional ``ETHTOOL_A_PLCA_NODE_CNT`` attribute indicates the +configured maximum number of PLCA nodes on the mixing-segment. This number +determines the total number of transmit opportunities generated during a +PLCA cycle. This attribute is relevant only for the PLCA coordinator, which is +the node with aPLCALocalNodeID set to 0. Follower nodes ignore this setting. +This option is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.3 +aPLCANodeCount. The valid range for this attribute is [1 .. 255]. + +When set, the optional ``ETHTOOL_A_PLCA_TO_TMR`` attribute indicates the +configured value of the transmit opportunity timer in bit-times. This value +must be set equal across all nodes sharing the medium for PLCA to work +correctly. This option is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.5 +aPLCATransmitOpportunityTimer. The valid range for this attribute is +[0 .. 255]. + +When set, the optional ``ETHTOOL_A_PLCA_BURST_CNT`` attribute indicates the +configured number of extra packets that the node is allowed to send during a +single transmit opportunity. By default, this attribute is 0, meaning that +the node can only send a sigle frame per TO. When greater than 0, the PLCA RS +keeps the TO after any transmission, waiting for the MAC to send a new frame +for up to aPLCABurstTimer BTs. This can only happen a number of times per PLCA +cycle up to the value of this parameter. After that, the burst is over and the +normal counting of TOs resumes. This option is corresponding to +``IEEE 802.3cg-2019`` 30.16.1.1.6 aPLCAMaxBurstCount. The valid range for this +attribute is [0 .. 255]. + +When set, the optional ``ETHTOOL_A_PLCA_BURST_TMR`` attribute indicates how +many bit-times the PLCA RS waits for the MAC to initiate a new transmission +when aPLCAMaxBurstCount is greater than 0. If the MAC fails to send a new +frame within this time, the burst ends and the counting of TOs resumes. +Otherwise, the new frame is sent as part of the current burst. This option +is corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.7 aPLCABurstTimer. The +valid range for this attribute is [0 .. 255]. Although, the value should be +set greater than the Inter-Frame-Gap (IFG) time of the MAC (plus some margin) +for PLCA burst mode to work as intended. + +PLCA_SET_CFG +============ + +Sets PLCA RS parameters. + +Request contents: + + ====================================== ====== ============================= + ``ETHTOOL_A_PLCA_HEADER`` nested request header + ``ETHTOOL_A_PLCA_ENABLED`` u8 PLCA Admin State + ``ETHTOOL_A_PLCA_NODE_ID`` u8 PLCA unique local node ID + ``ETHTOOL_A_PLCA_NODE_CNT`` u8 Number of PLCA nodes on the + netkork, including the + coordinator + ``ETHTOOL_A_PLCA_TO_TMR`` u8 Transmit Opportunity Timer + value in bit-times (BT) + ``ETHTOOL_A_PLCA_BURST_CNT`` u8 Number of additional packets + the node is allowed to send + within a single TO + ``ETHTOOL_A_PLCA_BURST_TMR`` u8 Time to wait for the MAC to + transmit a new frame before + terminating the burst + ====================================== ====== ============================= + +For a description of each attribute, see ``PLCA_GET_CFG``. + +PLCA_GET_STATUS +=============== + +Gets PLCA RS status information. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_PLCA_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ============================= + ``ETHTOOL_A_PLCA_HEADER`` nested reply header + ``ETHTOOL_A_PLCA_STATUS`` u8 PLCA RS operational status + ====================================== ====== ============================= + +When set, the ``ETHTOOL_A_PLCA_STATUS`` attribute indicates whether the node is +detecting the presence of the BEACON on the network. This flag is +corresponding to ``IEEE 802.3cg-2019`` 30.16.1.1.2 aPLCAStatus. + Request translation =================== @@ -1817,4 +1969,7 @@ are netlink only. n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` n/a ``ETHTOOL_MSG_MODULE_GET`` n/a ``ETHTOOL_MSG_MODULE_SET`` + n/a ``ETHTOOL_MSG_PLCA_GET_CFG`` + n/a ``ETHTOOL_MSG_PLCA_SET_CFG`` + n/a ``ETHTOOL_MSG_PLCA_GET_STATUS`` =================================== ===================================== diff --git a/MAINTAINERS b/MAINTAINERS index f8ef124a941b..f9a459661b6b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6098,7 +6098,7 @@ S: Supported F: Documentation/networking/devlink F: include/net/devlink.h F: include/uapi/linux/devlink.h -F: net/core/devlink.c +F: net/devlink/ DH ELECTRONICS IMX6 DHCOM/DHCOR BOARD SUPPORT M: Christoph Niedermaier <cniedermaier@dh-electronics.com> @@ -13709,6 +13709,7 @@ S: Maintained F: Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml F: Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml F: drivers/net/dsa/microchip/* +F: include/linux/dsa/ksz_common.h F: include/linux/platform_data/microchip-ksz.h F: net/dsa/tag_ksz.c @@ -14541,6 +14542,8 @@ M: Florian Fainelli <f.fainelli@gmail.com> M: Vladimir Oltean <olteanv@gmail.com> S: Maintained F: Documentation/devicetree/bindings/net/dsa/ +F: Documentation/devicetree/bindings/net/ethernet-switch-port.yaml +F: Documentation/devicetree/bindings/net/ethernet-switch.yaml F: drivers/net/dsa/ F: include/linux/dsa/ F: include/linux/platform_data/dsa.h @@ -15584,6 +15587,13 @@ L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/boot/dts/ralink/omega2p.dts +ONSEMI ETHERNET PHY DRIVERS +M: Piergiorgio Beruto <piergiorgio.beruto@gmail.com> +L: netdev@vger.kernel.org +S: Supported +W: http://www.onsemi.com +F: drivers/net/phy/ncn* + OP-TEE DRIVER M: Jens Wiklander <jens.wiklander@linaro.org> L: op-tee@lists.trustedfirmware.org @@ -16629,6 +16639,13 @@ S: Maintained F: Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml F: drivers/iio/chemical/pms7003.c +PLCA RECONCILIATION SUBLAYER (IEEE802.3 Clause 148) +M: Piergiorgio Beruto <piergiorgio.beruto@gmail.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/phy/mdio-open-alliance.h +F: net/ethtool/plca.c + PLDMFW LIBRARY M: Jacob Keller <jacob.e.keller@intel.com> S: Maintained @@ -20788,7 +20805,7 @@ M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Yehezkel Bernat <YehezkelShB@gmail.com> L: netdev@vger.kernel.org S: Maintained -F: drivers/net/thunderbolt.c +F: drivers/net/thunderbolt/ THUNDERX GPIO DRIVER M: Robert Richter <rric@kernel.org> diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index 69786c326db0..91b196c49be1 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -35,6 +35,46 @@ status = "okay"; }; +&eqos { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_eqos>; + phy-mode = "rgmii-id"; + phy-handle = <ðphy1>; + status = "okay"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <5000000>; + + ethphy1: ethernet-phy@1 { + reg = <1>; + eee-broken-1000t; + }; + }; +}; + +&fec { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_fec>; + phy-mode = "rgmii-id"; + phy-handle = <ðphy2>; + fsl,magic-packet; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <5000000>; + + ethphy2: ethernet-phy@2 { + reg = <2>; + eee-broken-1000t; + }; + }; +}; + &lpuart1 { /* console */ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1>; @@ -65,6 +105,44 @@ }; &iomuxc { + pinctrl_eqos: eqosgrp { + fsl,pins = < + MX93_PAD_ENET1_MDC__ENET_QOS_MDC 0x57e + MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO 0x57e + MX93_PAD_ENET1_RD0__ENET_QOS_RGMII_RD0 0x57e + MX93_PAD_ENET1_RD1__ENET_QOS_RGMII_RD1 0x57e + MX93_PAD_ENET1_RD2__ENET_QOS_RGMII_RD2 0x57e + MX93_PAD_ENET1_RD3__ENET_QOS_RGMII_RD3 0x57e + MX93_PAD_ENET1_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK 0x5fe + MX93_PAD_ENET1_RX_CTL__ENET_QOS_RGMII_RX_CTL 0x57e + MX93_PAD_ENET1_TD0__ENET_QOS_RGMII_TD0 0x57e + MX93_PAD_ENET1_TD1__ENET_QOS_RGMII_TD1 0x57e + MX93_PAD_ENET1_TD2__ENET_QOS_RGMII_TD2 0x57e + MX93_PAD_ENET1_TD3__ENET_QOS_RGMII_TD3 0x57e + MX93_PAD_ENET1_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK 0x5fe + MX93_PAD_ENET1_TX_CTL__ENET_QOS_RGMII_TX_CTL 0x57e + >; + }; + + pinctrl_fec: fecgrp { + fsl,pins = < + MX93_PAD_ENET2_MDC__ENET1_MDC 0x57e + MX93_PAD_ENET2_MDIO__ENET1_MDIO 0x57e + MX93_PAD_ENET2_RD0__ENET1_RGMII_RD0 0x57e + MX93_PAD_ENET2_RD1__ENET1_RGMII_RD1 0x57e + MX93_PAD_ENET2_RD2__ENET1_RGMII_RD2 0x57e + MX93_PAD_ENET2_RD3__ENET1_RGMII_RD3 0x57e + MX93_PAD_ENET2_RXC__ENET1_RGMII_RXC 0x5fe + MX93_PAD_ENET2_RX_CTL__ENET1_RGMII_RX_CTL 0x57e + MX93_PAD_ENET2_TD0__ENET1_RGMII_TD0 0x57e + MX93_PAD_ENET2_TD1__ENET1_RGMII_TD1 0x57e + MX93_PAD_ENET2_TD2__ENET1_RGMII_TD2 0x57e + MX93_PAD_ENET2_TD3__ENET1_RGMII_TD3 0x57e + MX93_PAD_ENET2_TXC__ENET1_RGMII_TXC 0x5fe + MX93_PAD_ENET2_TX_CTL__ENET1_RGMII_TX_CTL 0x57e + >; + }; + pinctrl_uart1: uart1grp { fsl,pins = < MX93_PAD_UART1_RXD__LPUART1_RX 0x31e diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 5d79663b3b84..22dd2ee70be7 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -536,6 +536,54 @@ status = "disabled"; }; + eqos: ethernet@428a0000 { + compatible = "nxp,imx93-dwmac-eqos", "snps,dwmac-5.10a"; + reg = <0x428a0000 0x10000>; + interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "eth_wake_irq", "macirq"; + clocks = <&clk IMX93_CLK_ENET_QOS_GATE>, + <&clk IMX93_CLK_ENET_QOS_GATE>, + <&clk IMX93_CLK_ENET_TIMER2>, + <&clk IMX93_CLK_ENET>, + <&clk IMX93_CLK_ENET_QOS_GATE>; + clock-names = "stmmaceth", "pclk", "ptp_ref", "tx", "mem"; + assigned-clocks = <&clk IMX93_CLK_ENET_TIMER2>, + <&clk IMX93_CLK_ENET>; + assigned-clock-parents = <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>, + <&clk IMX93_CLK_SYS_PLL_PFD0_DIV2>; + assigned-clock-rates = <100000000>, <250000000>; + intf_mode = <&wakeupmix_gpr 0x28>; + clk_csr = <0>; + status = "disabled"; + }; + + fec: ethernet@42890000 { + compatible = "fsl,imx93-fec", "fsl,imx8mq-fec", "fsl,imx6sx-fec"; + reg = <0x42890000 0x10000>; + interrupts = <GIC_SPI 179 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk IMX93_CLK_ENET1_GATE>, + <&clk IMX93_CLK_ENET1_GATE>, + <&clk IMX93_CLK_ENET_TIMER1>, + <&clk IMX93_CLK_ENET_REF>, + <&clk IMX93_CLK_ENET_REF_PHY>; + clock-names = "ipg", "ahb", "ptp", + "enet_clk_ref", "enet_out"; + assigned-clocks = <&clk IMX93_CLK_ENET_TIMER1>, + <&clk IMX93_CLK_ENET_REF>, + <&clk IMX93_CLK_ENET_REF_PHY>; + assigned-clock-parents = <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>, + <&clk IMX93_CLK_SYS_PLL_PFD0_DIV2>, + <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>; + assigned-clock-rates = <100000000>, <250000000>, <50000000>; + fsl,num-tx-queues = <3>; + fsl,num-rx-queues = <3>; + status = "disabled"; + }; + usdhc3: mmc@428b0000 { compatible = "fsl,imx93-usdhc", "fsl,imx8mm-usdhc"; reg = <0x428b0000 0x10000>; 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/drivers/base/regmap/regmap-mdio.c b/drivers/base/regmap/regmap-mdio.c index f7293040a2b1..6aa6a2409478 100644 --- a/drivers/base/regmap/regmap-mdio.c +++ b/drivers/base/regmap/regmap-mdio.c @@ -10,31 +10,21 @@ /* Clause-45 mask includes the device type (5 bit) and actual register number (16 bit) */ #define REGNUM_C45_MASK GENMASK(20, 0) -static int regmap_mdio_read(struct mdio_device *mdio_dev, u32 reg, unsigned int *val) +static int regmap_mdio_c22_read(void *context, unsigned int reg, unsigned int *val) { + struct mdio_device *mdio_dev = context; int ret; + if (unlikely(reg & ~REGNUM_C22_MASK)) + return -ENXIO; + ret = mdiodev_read(mdio_dev, reg); if (ret < 0) return ret; *val = ret & REGVAL_MASK; - return 0; -} - -static int regmap_mdio_write(struct mdio_device *mdio_dev, u32 reg, unsigned int val) -{ - return mdiodev_write(mdio_dev, reg, val); -} - -static int regmap_mdio_c22_read(void *context, unsigned int reg, unsigned int *val) -{ - struct mdio_device *mdio_dev = context; - - if (unlikely(reg & ~REGNUM_C22_MASK)) - return -ENXIO; - return regmap_mdio_read(mdio_dev, reg, val); + return 0; } static int regmap_mdio_c22_write(void *context, unsigned int reg, unsigned int val) @@ -55,21 +45,36 @@ static const struct regmap_bus regmap_mdio_c22_bus = { static int regmap_mdio_c45_read(void *context, unsigned int reg, unsigned int *val) { struct mdio_device *mdio_dev = context; + unsigned int devad; + int ret; if (unlikely(reg & ~REGNUM_C45_MASK)) return -ENXIO; - return regmap_mdio_read(mdio_dev, MII_ADDR_C45 | reg, val); + devad = reg >> REGMAP_MDIO_C45_DEVAD_SHIFT; + reg = reg & REGMAP_MDIO_C45_REGNUM_MASK; + + ret = mdiodev_c45_read(mdio_dev, devad, reg); + if (ret < 0) + return ret; + + *val = ret & REGVAL_MASK; + + return 0; } static int regmap_mdio_c45_write(void *context, unsigned int reg, unsigned int val) { struct mdio_device *mdio_dev = context; + unsigned int devad; if (unlikely(reg & ~REGNUM_C45_MASK)) return -ENXIO; - return regmap_mdio_write(mdio_dev, MII_ADDR_C45 | reg, val); + devad = reg >> REGMAP_MDIO_C45_DEVAD_SHIFT; + reg = reg & REGMAP_MDIO_C45_REGNUM_MASK; + + return mdiodev_c45_write(mdio_dev, devad, reg, val); } static const struct regmap_bus regmap_mdio_c45_bus = { diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 4dd777cc0c89..d6037a328669 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -442,18 +442,7 @@ EXPORT_SYMBOL_GPL(i2c_acpi_find_adapter_by_handle); static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) { - struct device *dev; - struct i2c_client *client; - - dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); - if (!dev) - return NULL; - - client = i2c_verify_client(dev); - if (!client) - put_device(dev); - - return client; + return i2c_find_device_by_fwnode(acpi_fwnode_handle(adev)); } static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value, diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 087e480b624c..b47e255fc6f1 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1012,6 +1012,35 @@ void i2c_unregister_device(struct i2c_client *client) } EXPORT_SYMBOL_GPL(i2c_unregister_device); +/** + * i2c_find_device_by_fwnode() - find an i2c_client for the fwnode + * @fwnode: &struct fwnode_handle corresponding to the &struct i2c_client + * + * Look up and return the &struct i2c_client corresponding to the @fwnode. + * If no client can be found, or @fwnode is NULL, this returns NULL. + * + * The user must call put_device(&client->dev) once done with the i2c client. + */ +struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode) +{ + struct i2c_client *client; + struct device *dev; + + if (!fwnode) + return NULL; + + dev = bus_find_device_by_fwnode(&i2c_bus_type, fwnode); + if (!dev) + return NULL; + + client = i2c_verify_client(dev); + if (!client) + put_device(dev); + + return client; +} +EXPORT_SYMBOL(i2c_find_device_by_fwnode); + static const struct i2c_device_id dummy_id[] = { { "dummy", 0 }, @@ -1761,6 +1790,75 @@ int devm_i2c_add_adapter(struct device *dev, struct i2c_adapter *adapter) } EXPORT_SYMBOL_GPL(devm_i2c_add_adapter); +static int i2c_dev_or_parent_fwnode_match(struct device *dev, const void *data) +{ + if (dev_fwnode(dev) == data) + return 1; + + if (dev->parent && dev_fwnode(dev->parent) == data) + return 1; + + return 0; +} + +/** + * i2c_find_adapter_by_fwnode() - find an i2c_adapter for the fwnode + * @fwnode: &struct fwnode_handle corresponding to the &struct i2c_adapter + * + * Look up and return the &struct i2c_adapter corresponding to the @fwnode. + * If no adapter can be found, or @fwnode is NULL, this returns NULL. + * + * The user must call put_device(&adapter->dev) once done with the i2c adapter. + */ +struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + struct i2c_adapter *adapter; + struct device *dev; + + if (!fwnode) + return NULL; + + dev = bus_find_device(&i2c_bus_type, NULL, fwnode, + i2c_dev_or_parent_fwnode_match); + if (!dev) + return NULL; + + adapter = i2c_verify_adapter(dev); + if (!adapter) + put_device(dev); + + return adapter; +} +EXPORT_SYMBOL(i2c_find_adapter_by_fwnode); + +/** + * i2c_get_adapter_by_fwnode() - find an i2c_adapter for the fwnode + * @fwnode: &struct fwnode_handle corresponding to the &struct i2c_adapter + * + * Look up and return the &struct i2c_adapter corresponding to the @fwnode, + * and increment the adapter module's use count. If no adapter can be found, + * or @fwnode is NULL, this returns NULL. + * + * The user must call i2c_put_adapter(adapter) once done with the i2c adapter. + * Note that this is different from i2c_find_adapter_by_node(). + */ +struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + struct i2c_adapter *adapter; + + adapter = i2c_find_adapter_by_fwnode(fwnode); + if (!adapter) + return NULL; + + if (!try_module_get(adapter->owner)) { + put_device(&adapter->dev); + adapter = NULL; + } + + return adapter; +} +EXPORT_SYMBOL(i2c_get_adapter_by_fwnode); + static void i2c_parse_timing(struct device *dev, char *prop_name, u32 *cur_val_p, u32 def_val, bool use_def) { diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index 3ed74aa4b44b..bce6b796e04c 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -113,72 +113,6 @@ void of_i2c_register_devices(struct i2c_adapter *adap) of_node_put(bus); } -static int of_dev_or_parent_node_match(struct device *dev, const void *data) -{ - if (dev->of_node == data) - return 1; - - if (dev->parent) - return dev->parent->of_node == data; - - return 0; -} - -/* must call put_device() when done with returned i2c_client device */ -struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) -{ - struct device *dev; - struct i2c_client *client; - - dev = bus_find_device_by_of_node(&i2c_bus_type, node); - if (!dev) - return NULL; - - client = i2c_verify_client(dev); - if (!client) - put_device(dev); - - return client; -} -EXPORT_SYMBOL(of_find_i2c_device_by_node); - -/* must call put_device() when done with returned i2c_adapter device */ -struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) -{ - struct device *dev; - struct i2c_adapter *adapter; - - dev = bus_find_device(&i2c_bus_type, NULL, node, - of_dev_or_parent_node_match); - if (!dev) - return NULL; - - adapter = i2c_verify_adapter(dev); - if (!adapter) - put_device(dev); - - return adapter; -} -EXPORT_SYMBOL(of_find_i2c_adapter_by_node); - -/* must call i2c_put_adapter() when done with returned i2c_adapter device */ -struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node) -{ - struct i2c_adapter *adapter; - - adapter = of_find_i2c_adapter_by_node(node); - if (!adapter) - return NULL; - - if (!try_module_get(adapter->owner)) { - put_device(&adapter->dev); - adapter = NULL; - } - - return adapter; -} -EXPORT_SYMBOL(of_get_i2c_adapter_by_node); - static const struct of_device_id* i2c_of_match_device_sysfs(const struct of_device_id *matches, struct i2c_client *client) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 9e63b8c43f3e..950a09f021dd 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -583,18 +583,7 @@ config FUJITSU_ES This driver provides support for Extended Socket network device on Extended Partitioning of FUJITSU PRIMEQUEST 2000 E2 series. -config USB4_NET - tristate "Networking over USB4 and Thunderbolt cables" - depends on USB4 && INET - help - Select this if you want to create network between two computers - over a USB4 and Thunderbolt cables. The driver supports Apple - ThunderboltIP protocol and allows communication with any host - supporting the same protocol including Windows and macOS. - - To compile this driver a module, choose M here. The module will be - called thunderbolt-net. - +source "drivers/net/thunderbolt/Kconfig" source "drivers/net/hyperv/Kconfig" config NETDEVSIM diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 6ce076462dbf..e26f98f897c5 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -84,8 +84,6 @@ obj-$(CONFIG_HYPERV_NET) += hyperv/ obj-$(CONFIG_NTB_NETDEV) += ntb_netdev.o obj-$(CONFIG_FUJITSU_ES) += fjes/ - -thunderbolt-net-y += thunderbolt.o -obj-$(CONFIG_USB4_NET) += thunderbolt-net.o +obj-$(CONFIG_USB4_NET) += thunderbolt/ obj-$(CONFIG_NETDEVSIM) += netdevsim/ obj-$(CONFIG_NET_FAILOVER) += net_failover.o diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 2e270b479143..cbe831875347 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -15,6 +15,9 @@ #include "lan9303.h" +/* For the LAN9303 and LAN9354, only port 0 is an XMII port. */ +#define IS_PORT_XMII(port) ((port) == 0) + #define LAN9303_NUM_PORTS 3 /* 13.2 System Control and Status Registers @@ -50,6 +53,9 @@ #define LAN9303_MANUAL_FC_1 0x68 #define LAN9303_MANUAL_FC_2 0x69 #define LAN9303_MANUAL_FC_0 0x6a +# define LAN9303_BP_EN BIT(6) +# define LAN9303_RX_FC_EN BIT(2) +# define LAN9303_TX_FC_EN BIT(1) #define LAN9303_SWITCH_CSR_DATA 0x6b #define LAN9303_SWITCH_CSR_CMD 0x6c #define LAN9303_SWITCH_CSR_CMD_BUSY BIT(31) @@ -225,6 +231,13 @@ const struct regmap_access_table lan9303_register_set = { }; EXPORT_SYMBOL(lan9303_register_set); +/* Flow Control registers indexed by port number */ +static unsigned int flow_ctl_reg[] = { + LAN9303_MANUAL_FC_0, + LAN9303_MANUAL_FC_1, + LAN9303_MANUAL_FC_2 +}; + static int lan9303_read(struct regmap *regmap, unsigned int offset, u32 *reg) { int ret, i; @@ -902,6 +915,7 @@ static int lan9303_setup(struct dsa_switch *ds) { struct lan9303 *chip = ds->priv; int ret; + u32 reg; /* Make sure that port 0 is the cpu port */ if (!dsa_is_cpu_port(ds, 0)) { @@ -909,6 +923,17 @@ static int lan9303_setup(struct dsa_switch *ds) return -EINVAL; } + /* Virtual Phy: Remove Turbo 200Mbit mode */ + ret = lan9303_read(chip->regmap, LAN9303_VIRT_SPECIAL_CTRL, ®); + if (ret) + return (ret); + + /* Clear the TURBO Mode bit if it was set. */ + if (reg & LAN9303_VIRT_SPECIAL_TURBO) { + reg &= ~LAN9303_VIRT_SPECIAL_TURBO; + regmap_write(chip->regmap, LAN9303_VIRT_SPECIAL_CTRL, reg); + } + ret = lan9303_setup_tagging(chip); if (ret) dev_err(chip->dev, "failed to setup port tagging %d\n", ret); @@ -1049,42 +1074,6 @@ static int lan9303_phy_write(struct dsa_switch *ds, int phy, int regnum, return chip->ops->phy_write(chip, phy, regnum, val); } -static void lan9303_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) -{ - struct lan9303 *chip = ds->priv; - int ctl; - - if (!phy_is_pseudo_fixed_link(phydev)) - return; - - ctl = lan9303_phy_read(ds, port, MII_BMCR); - - ctl &= ~BMCR_ANENABLE; - - if (phydev->speed == SPEED_100) - ctl |= BMCR_SPEED100; - else if (phydev->speed == SPEED_10) - ctl &= ~BMCR_SPEED100; - else - dev_err(ds->dev, "unsupported speed: %d\n", phydev->speed); - - if (phydev->duplex == DUPLEX_FULL) - ctl |= BMCR_FULLDPLX; - else - ctl &= ~BMCR_FULLDPLX; - - lan9303_phy_write(ds, port, MII_BMCR, ctl); - - if (port == chip->phy_addr_base) { - /* Virtual Phy: Remove Turbo 200Mbit mode */ - lan9303_read(chip->regmap, LAN9303_VIRT_SPECIAL_CTRL, &ctl); - - ctl &= ~LAN9303_VIRT_SPECIAL_TURBO; - regmap_write(chip->regmap, LAN9303_VIRT_SPECIAL_CTRL, ctl); - } -} - static int lan9303_port_enable(struct dsa_switch *ds, int port, struct phy_device *phy) { @@ -1281,26 +1270,96 @@ static int lan9303_port_mdb_del(struct dsa_switch *ds, int port, return 0; } +static void lan9303_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(%d) entered.", __func__, port); + + config->mac_capabilities = MAC_10 | MAC_100 | MAC_ASYM_PAUSE | + MAC_SYM_PAUSE; + + if (port == 0) { + __set_bit(PHY_INTERFACE_MODE_RMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_MII, + config->supported_interfaces); + } else { + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + /* Compatibility for phylib's default interface type when the + * phy-mode property is absent + */ + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); + } + + /* This driver does not make use of the speed, duplex, pause or the + * advertisement in its mac_config, so it is safe to mark this driver + * as non-legacy. + */ + config->legacy_pre_march2020 = false; +} + +static void lan9303_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev, int speed, + int duplex, bool tx_pause, + bool rx_pause) +{ + struct lan9303 *chip = ds->priv; + u32 ctl; + u32 reg; + + /* On this device, we are only interested in doing something here if + * this is the xMII port. All other ports are 10/100 phys using MDIO + * to control there link settings. + */ + if (!IS_PORT_XMII(port)) + return; + + /* Disable auto-negotiation and force the speed/duplex settings. */ + ctl = lan9303_phy_read(ds, port, MII_BMCR); + ctl &= ~(BMCR_ANENABLE | BMCR_SPEED100 | BMCR_FULLDPLX); + if (speed == SPEED_100) + ctl |= BMCR_SPEED100; + if (duplex == DUPLEX_FULL) + ctl |= BMCR_FULLDPLX; + lan9303_phy_write(ds, port, MII_BMCR, ctl); + + /* Force the flow control settings. */ + lan9303_read(chip->regmap, flow_ctl_reg[port], ®); + reg &= ~(LAN9303_BP_EN | LAN9303_RX_FC_EN | LAN9303_TX_FC_EN); + if (rx_pause) + reg |= (LAN9303_RX_FC_EN | LAN9303_BP_EN); + if (tx_pause) + reg |= LAN9303_TX_FC_EN; + regmap_write(chip->regmap, flow_ctl_reg[port], reg); +} + static const struct dsa_switch_ops lan9303_switch_ops = { - .get_tag_protocol = lan9303_get_tag_protocol, - .setup = lan9303_setup, - .get_strings = lan9303_get_strings, - .phy_read = lan9303_phy_read, - .phy_write = lan9303_phy_write, - .adjust_link = lan9303_adjust_link, - .get_ethtool_stats = lan9303_get_ethtool_stats, - .get_sset_count = lan9303_get_sset_count, - .port_enable = lan9303_port_enable, - .port_disable = lan9303_port_disable, - .port_bridge_join = lan9303_port_bridge_join, - .port_bridge_leave = lan9303_port_bridge_leave, - .port_stp_state_set = lan9303_port_stp_state_set, - .port_fast_age = lan9303_port_fast_age, - .port_fdb_add = lan9303_port_fdb_add, - .port_fdb_del = lan9303_port_fdb_del, - .port_fdb_dump = lan9303_port_fdb_dump, - .port_mdb_add = lan9303_port_mdb_add, - .port_mdb_del = lan9303_port_mdb_del, + .get_tag_protocol = lan9303_get_tag_protocol, + .setup = lan9303_setup, + .get_strings = lan9303_get_strings, + .phy_read = lan9303_phy_read, + .phy_write = lan9303_phy_write, + .phylink_get_caps = lan9303_phylink_get_caps, + .phylink_mac_link_up = lan9303_phylink_mac_link_up, + .get_ethtool_stats = lan9303_get_ethtool_stats, + .get_sset_count = lan9303_get_sset_count, + .port_enable = lan9303_port_enable, + .port_disable = lan9303_port_disable, + .port_bridge_join = lan9303_port_bridge_join, + .port_bridge_leave = lan9303_port_bridge_leave, + .port_stp_state_set = lan9303_port_stp_state_set, + .port_fast_age = lan9303_port_fast_age, + .port_fdb_add = lan9303_port_fdb_add, + .port_fdb_del = lan9303_port_fdb_del, + .port_fdb_dump = lan9303_port_fdb_dump, + .port_mdb_add = lan9303_port_mdb_add, + .port_mdb_del = lan9303_port_mdb_del, }; static int lan9303_register_switch(struct lan9303 *chip) diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig index 913f83ef013c..0546c573668a 100644 --- a/drivers/net/dsa/microchip/Kconfig +++ b/drivers/net/dsa/microchip/Kconfig @@ -11,6 +11,7 @@ menuconfig NET_DSA_MICROCHIP_KSZ_COMMON config NET_DSA_MICROCHIP_KSZ9477_I2C tristate "KSZ series I2C connected switch driver" depends on NET_DSA_MICROCHIP_KSZ_COMMON && I2C + depends on PTP_1588_CLOCK_OPTIONAL select REGMAP_I2C help Select to enable support for registering switches configured through I2C. @@ -18,10 +19,20 @@ config NET_DSA_MICROCHIP_KSZ9477_I2C config NET_DSA_MICROCHIP_KSZ_SPI tristate "KSZ series SPI connected switch driver" depends on NET_DSA_MICROCHIP_KSZ_COMMON && SPI + depends on PTP_1588_CLOCK_OPTIONAL select REGMAP_SPI help Select to enable support for registering switches configured through SPI. +config NET_DSA_MICROCHIP_KSZ_PTP + bool "Support for the PTP clock on the KSZ9563/LAN937x Ethernet Switch" + depends on NET_DSA_MICROCHIP_KSZ_COMMON && PTP_1588_CLOCK + help + Select to enable support for timestamping & PTP clock manipulation in + KSZ8563/KSZ9563/LAN937x series of switches. KSZ9563/KSZ8563 supports + only one step timestamping. LAN937x switch supports both one step and + two step timestamping. + config NET_DSA_MICROCHIP_KSZ8863_SMI tristate "KSZ series SMI connected switch driver" depends on NET_DSA_MICROCHIP_KSZ_COMMON diff --git a/drivers/net/dsa/microchip/Makefile b/drivers/net/dsa/microchip/Makefile index 28873559efc2..48360cc9fc68 100644 --- a/drivers/net/dsa/microchip/Makefile +++ b/drivers/net/dsa/microchip/Makefile @@ -4,6 +4,11 @@ ksz_switch-objs := ksz_common.o ksz_switch-objs += ksz9477.o ksz_switch-objs += ksz8795.o ksz_switch-objs += lan937x_main.o + +ifdef CONFIG_NET_DSA_MICROCHIP_KSZ_PTP +ksz_switch-objs += ksz_ptp.o +endif + obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477_I2C) += ksz9477_i2c.o obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ_SPI) += ksz_spi.o obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ8863_SMI) += ksz8863_smi.o diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 9b20c2ee6d62..5e1e5bd555d2 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -6,6 +6,7 @@ */ #include <linux/delay.h> +#include <linux/dsa/ksz_common.h> #include <linux/export.h> #include <linux/gpio/consumer.h> #include <linux/kernel.h> @@ -25,6 +26,7 @@ #include <net/switchdev.h> #include "ksz_common.h" +#include "ksz_ptp.h" #include "ksz8.h" #include "ksz9477.h" #include "lan937x.h" @@ -2099,13 +2101,23 @@ static int ksz_setup(struct dsa_switch *ds) ret = ksz_pirq_setup(dev, dp->index); if (ret) goto out_girq; + + ret = ksz_ptp_irq_setup(ds, dp->index); + if (ret) + goto out_pirq; } } + ret = ksz_ptp_clock_register(ds); + if (ret) { + dev_err(dev->dev, "Failed to register PTP clock: %d\n", ret); + goto out_ptpirq; + } + ret = ksz_mdio_register(dev); if (ret < 0) { dev_err(dev->dev, "failed to register the mdio"); - goto out_pirq; + goto out_ptp_clock_unregister; } /* start switch */ @@ -2114,6 +2126,12 @@ static int ksz_setup(struct dsa_switch *ds) return 0; +out_ptp_clock_unregister: + ksz_ptp_clock_unregister(ds); +out_ptpirq: + if (dev->irq > 0) + dsa_switch_for_each_user_port(dp, dev->ds) + ksz_ptp_irq_free(ds, dp->index); out_pirq: if (dev->irq > 0) dsa_switch_for_each_user_port(dp, dev->ds) @@ -2130,9 +2148,14 @@ static void ksz_teardown(struct dsa_switch *ds) struct ksz_device *dev = ds->priv; struct dsa_port *dp; + ksz_ptp_clock_unregister(ds); + if (dev->irq > 0) { - dsa_switch_for_each_user_port(dp, dev->ds) + dsa_switch_for_each_user_port(dp, dev->ds) { + ksz_ptp_irq_free(ds, dp->index); + ksz_irq_free(&dev->ports[dp->index].pirq); + } ksz_irq_free(&dev->girq); } @@ -2517,6 +2540,17 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, return proto; } +static int ksz_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) +{ + struct ksz_tagger_data *tagger_data; + + tagger_data = ksz_tagger_data(ds); + tagger_data->xmit_work_fn = ksz_port_deferred_xmit; + + return 0; +} + static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port, bool flag, struct netlink_ext_ack *extack) { @@ -2932,6 +2966,7 @@ static int ksz_switch_detect(struct ksz_device *dev) static const struct dsa_switch_ops ksz_switch_ops = { .get_tag_protocol = ksz_get_tag_protocol, + .connect_tag_protocol = ksz_connect_tag_protocol, .get_phy_flags = ksz_get_phy_flags, .setup = ksz_setup, .teardown = ksz_teardown, @@ -2966,6 +3001,11 @@ static const struct dsa_switch_ops ksz_switch_ops = { .get_pause_stats = ksz_get_pause_stats, .port_change_mtu = ksz_change_mtu, .port_max_mtu = ksz_max_mtu, + .get_ts_info = ksz_get_ts_info, + .port_hwtstamp_get = ksz_hwtstamp_get, + .port_hwtstamp_set = ksz_hwtstamp_set, + .port_txtstamp = ksz_port_txtstamp, + .port_rxtstamp = ksz_port_rxtstamp, }; struct ksz_device *ksz_switch_alloc(struct device *base, void *priv) diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 055d61ff3fb8..7260528e5c57 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -15,9 +15,12 @@ #include <net/dsa.h> #include <linux/irq.h> +#include "ksz_ptp.h" + #define KSZ_MAX_NUM_PORTS 8 struct ksz_device; +struct ksz_port; struct vlan_table { u32 table[3]; @@ -81,6 +84,14 @@ struct ksz_irq { struct ksz_device *dev; }; +struct ksz_ptp_irq { + struct ksz_port *port; + u16 ts_reg; + bool ts_en; + char name[16]; + int num; +}; + struct ksz_port { bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ bool learning; @@ -100,6 +111,15 @@ struct ksz_port { struct ksz_device *ksz_dev; struct ksz_irq pirq; u8 num; +#if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_PTP) + struct hwtstamp_config tstamp_config; + bool hwts_tx_en; + bool hwts_rx_en; + struct ksz_irq ptpirq; + struct ksz_ptp_irq ptpmsg_irq[3]; + ktime_t tstamp_msg; + struct completion tstamp_msg_comp; +#endif }; struct ksz_device { @@ -140,6 +160,7 @@ struct ksz_device { u16 port_mask; struct mutex lock_irq; /* IRQ Access */ struct ksz_irq girq; + struct ksz_ptp_data ptp_data; }; /* List of supported models */ @@ -443,6 +464,32 @@ static inline int ksz_write32(struct ksz_device *dev, u32 reg, u32 value) return ret; } +static inline int ksz_rmw16(struct ksz_device *dev, u32 reg, u16 mask, + u16 value) +{ + int ret; + + ret = regmap_update_bits(dev->regmap[1], reg, mask, value); + if (ret) + dev_err(dev->dev, "can't rmw 16bit reg 0x%x: %pe\n", reg, + ERR_PTR(ret)); + + return ret; +} + +static inline int ksz_rmw32(struct ksz_device *dev, u32 reg, u32 mask, + u32 value) +{ + int ret; + + ret = regmap_update_bits(dev->regmap[2], reg, mask, value); + if (ret) + dev_err(dev->dev, "can't rmw 32bit reg 0x%x: %pe\n", reg, + ERR_PTR(ret)); + + return ret; +} + static inline int ksz_write64(struct ksz_device *dev, u32 reg, u64 value) { u32 val[2]; @@ -591,6 +638,7 @@ static inline int is_lan937x(struct ksz_device *dev) #define REG_PORT_INT_MASK 0x001F #define PORT_SRC_PHY_INT 1 +#define PORT_SRC_PTP_INT 2 #define KSZ8795_HUGE_PACKET_SIZE 2000 #define KSZ8863_HUGE_PACKET_SIZE 1916 diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c new file mode 100644 index 000000000000..4e22a695a64c --- /dev/null +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -0,0 +1,1201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Microchip KSZ PTP Implementation + * + * Copyright (C) 2020 ARRI Lighting + * Copyright (C) 2022 Microchip Technology Inc. + */ + +#include <linux/dsa/ksz_common.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/ptp_classify.h> +#include <linux/ptp_clock_kernel.h> + +#include "ksz_common.h" +#include "ksz_ptp.h" +#include "ksz_ptp_reg.h" + +#define ptp_caps_to_data(d) container_of((d), struct ksz_ptp_data, caps) +#define ptp_data_to_ksz_dev(d) container_of((d), struct ksz_device, ptp_data) +#define work_to_xmit_work(w) \ + container_of((w), struct ksz_deferred_xmit_work, work) + +/* Sub-nanoseconds-adj,max * sub-nanoseconds / 40ns * 1ns + * = (2^30-1) * (2 ^ 32) / 40 ns * 1 ns = 6249999 + */ +#define KSZ_MAX_DRIFT_CORR 6249999 +#define KSZ_MAX_PULSE_WIDTH 125000000LL + +#define KSZ_PTP_INC_NS 40ULL /* HW clock is incremented every 40 ns (by 40) */ +#define KSZ_PTP_SUBNS_BITS 32 + +#define KSZ_PTP_INT_START 13 + +static int ksz_ptp_tou_gpio(struct ksz_device *dev) +{ + int ret; + + if (!is_lan937x(dev)) + return 0; + + ret = ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, GPIO_OUT, + GPIO_OUT); + if (ret) + return ret; + + ret = ksz_rmw32(dev, REG_SW_GLOBAL_LED_OVR__4, LED_OVR_1 | LED_OVR_2, + LED_OVR_1 | LED_OVR_2); + if (ret) + return ret; + + return ksz_rmw32(dev, REG_SW_GLOBAL_LED_SRC__4, + LED_SRC_PTP_GPIO_1 | LED_SRC_PTP_GPIO_2, + LED_SRC_PTP_GPIO_1 | LED_SRC_PTP_GPIO_2); +} + +static int ksz_ptp_tou_reset(struct ksz_device *dev, u8 unit) +{ + u32 data; + int ret; + + /* Reset trigger unit (clears TRIGGER_EN, but not GPIOSTATx) */ + ret = ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, TRIG_RESET, TRIG_RESET); + + data = FIELD_PREP(TRIG_DONE_M, BIT(unit)); + ret = ksz_write32(dev, REG_PTP_TRIG_STATUS__4, data); + if (ret) + return ret; + + data = FIELD_PREP(TRIG_INT_M, BIT(unit)); + ret = ksz_write32(dev, REG_PTP_INT_STATUS__4, data); + if (ret) + return ret; + + /* Clear reset and set GPIO direction */ + return ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, (TRIG_RESET | TRIG_ENABLE), + 0); +} + +static int ksz_ptp_tou_pulse_verify(u64 pulse_ns) +{ + u32 data; + + if (pulse_ns & 0x3) + return -EINVAL; + + data = (pulse_ns / 8); + if (!FIELD_FIT(TRIG_PULSE_WIDTH_M, data)) + return -ERANGE; + + return 0; +} + +static int ksz_ptp_tou_target_time_set(struct ksz_device *dev, + struct timespec64 const *ts) +{ + int ret; + + /* Hardware has only 32 bit */ + if ((ts->tv_sec & 0xffffffff) != ts->tv_sec) + return -EINVAL; + + ret = ksz_write32(dev, REG_TRIG_TARGET_NANOSEC, ts->tv_nsec); + if (ret) + return ret; + + ret = ksz_write32(dev, REG_TRIG_TARGET_SEC, ts->tv_sec); + if (ret) + return ret; + + return 0; +} + +static int ksz_ptp_tou_start(struct ksz_device *dev, u8 unit) +{ + u32 data; + int ret; + + ret = ksz_rmw32(dev, REG_PTP_CTRL_STAT__4, TRIG_ENABLE, TRIG_ENABLE); + if (ret) + return ret; + + /* Check error flag: + * - the ACTIVE flag is NOT cleared an error! + */ + ret = ksz_read32(dev, REG_PTP_TRIG_STATUS__4, &data); + if (ret) + return ret; + + if (FIELD_GET(TRIG_ERROR_M, data) & (1 << unit)) { + dev_err(dev->dev, "%s: Trigger unit%d error!\n", __func__, + unit); + ret = -EIO; + /* Unit will be reset on next access */ + return ret; + } + + return 0; +} + +static int ksz_ptp_configure_perout(struct ksz_device *dev, + u32 cycle_width_ns, u32 pulse_width_ns, + struct timespec64 const *target_time, + u8 index) +{ + u32 data; + int ret; + + data = FIELD_PREP(TRIG_NOTIFY, 1) | + FIELD_PREP(TRIG_GPO_M, index) | + FIELD_PREP(TRIG_PATTERN_M, TRIG_POS_PERIOD); + ret = ksz_write32(dev, REG_TRIG_CTRL__4, data); + if (ret) + return ret; + + ret = ksz_write32(dev, REG_TRIG_CYCLE_WIDTH, cycle_width_ns); + if (ret) + return ret; + + /* Set cycle count 0 - Infinite */ + ret = ksz_rmw32(dev, REG_TRIG_CYCLE_CNT, TRIG_CYCLE_CNT_M, 0); + if (ret) + return ret; + + data = (pulse_width_ns / 8); + ret = ksz_write32(dev, REG_TRIG_PULSE_WIDTH__4, data); + if (ret) + return ret; + + ret = ksz_ptp_tou_target_time_set(dev, target_time); + if (ret) + return ret; + + return 0; +} + +static int ksz_ptp_enable_perout(struct ksz_device *dev, + struct ptp_perout_request const *request, + int on) +{ + struct ksz_ptp_data *ptp_data = &dev->ptp_data; + u64 req_pulse_width_ns; + u64 cycle_width_ns; + u64 pulse_width_ns; + int pin = 0; + u32 data32; + int ret; + + if (request->flags & ~PTP_PEROUT_DUTY_CYCLE) + return -EOPNOTSUPP; + + if (ptp_data->tou_mode != KSZ_PTP_TOU_PEROUT && + ptp_data->tou_mode != KSZ_PTP_TOU_IDLE) + return -EBUSY; + + pin = ptp_find_pin(ptp_data->clock, PTP_PF_PEROUT, request->index); + if (pin < 0) + return -EINVAL; + + data32 = FIELD_PREP(PTP_GPIO_INDEX, pin) | + FIELD_PREP(PTP_TOU_INDEX, request->index); + ret = ksz_rmw32(dev, REG_PTP_UNIT_INDEX__4, + PTP_GPIO_INDEX | PTP_TOU_INDEX, data32); + if (ret) + return ret; + + ret = ksz_ptp_tou_reset(dev, request->index); + if (ret) + return ret; + + if (!on) { + ptp_data->tou_mode = KSZ_PTP_TOU_IDLE; + return 0; + } + + ptp_data->perout_target_time_first.tv_sec = request->start.sec; + ptp_data->perout_target_time_first.tv_nsec = request->start.nsec; + + ptp_data->perout_period.tv_sec = request->period.sec; + ptp_data->perout_period.tv_nsec = request->period.nsec; + + cycle_width_ns = timespec64_to_ns(&ptp_data->perout_period); + if ((cycle_width_ns & TRIG_CYCLE_WIDTH_M) != cycle_width_ns) + return -EINVAL; + + if (request->flags & PTP_PEROUT_DUTY_CYCLE) { + pulse_width_ns = request->on.sec * NSEC_PER_SEC + + request->on.nsec; + } else { + /* Use a duty cycle of 50%. Maximum pulse width supported by the + * hardware is a little bit more than 125 ms. + */ + req_pulse_width_ns = (request->period.sec * NSEC_PER_SEC + + request->period.nsec) / 2; + pulse_width_ns = min_t(u64, req_pulse_width_ns, + KSZ_MAX_PULSE_WIDTH); + } + + ret = ksz_ptp_tou_pulse_verify(pulse_width_ns); + if (ret) + return ret; + + ret = ksz_ptp_configure_perout(dev, cycle_width_ns, pulse_width_ns, + &ptp_data->perout_target_time_first, + pin); + if (ret) + return ret; + + ret = ksz_ptp_tou_gpio(dev); + if (ret) + return ret; + + ret = ksz_ptp_tou_start(dev, request->index); + if (ret) + return ret; + + ptp_data->tou_mode = KSZ_PTP_TOU_PEROUT; + + return 0; +} + +static int ksz_ptp_enable_mode(struct ksz_device *dev) +{ + struct ksz_tagger_data *tagger_data = ksz_tagger_data(dev->ds); + struct ksz_ptp_data *ptp_data = &dev->ptp_data; + struct ksz_port *prt; + struct dsa_port *dp; + bool tag_en = false; + int ret; + + dsa_switch_for_each_user_port(dp, dev->ds) { + prt = &dev->ports[dp->index]; + if (prt->hwts_tx_en || prt->hwts_rx_en) { + tag_en = true; + break; + } + } + + if (tag_en) { + ret = ptp_schedule_worker(ptp_data->clock, 0); + if (ret) + return ret; + } else { + ptp_cancel_worker_sync(ptp_data->clock); + } + + tagger_data->hwtstamp_set_state(dev->ds, tag_en); + + return ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_ENABLE, + tag_en ? PTP_ENABLE : 0); +} + +/* The function is return back the capability of timestamping feature when + * requested through ethtool -T <interface> utility + */ +int ksz_get_ts_info(struct dsa_switch *ds, int port, struct ethtool_ts_info *ts) +{ + struct ksz_device *dev = ds->priv; + struct ksz_ptp_data *ptp_data; + + ptp_data = &dev->ptp_data; + + if (!ptp_data->clock) + return -ENODEV; + + ts->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + ts->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ONESTEP_P2P); + + if (is_lan937x(dev)) + ts->tx_types |= BIT(HWTSTAMP_TX_ON); + + ts->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + + ts->phc_index = ptp_clock_index(ptp_data->clock); + + return 0; +} + +int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr) +{ + struct ksz_device *dev = ds->priv; + struct hwtstamp_config *config; + struct ksz_port *prt; + + prt = &dev->ports[port]; + config = &prt->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +static int ksz_set_hwtstamp_config(struct ksz_device *dev, + struct ksz_port *prt, + struct hwtstamp_config *config) +{ + int ret; + + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + prt->ptpmsg_irq[KSZ_SYNC_MSG].ts_en = false; + prt->ptpmsg_irq[KSZ_XDREQ_MSG].ts_en = false; + prt->ptpmsg_irq[KSZ_PDRES_MSG].ts_en = false; + prt->hwts_tx_en = false; + break; + case HWTSTAMP_TX_ONESTEP_P2P: + prt->ptpmsg_irq[KSZ_SYNC_MSG].ts_en = false; + prt->ptpmsg_irq[KSZ_XDREQ_MSG].ts_en = true; + prt->ptpmsg_irq[KSZ_PDRES_MSG].ts_en = false; + prt->hwts_tx_en = true; + + ret = ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_1STEP, PTP_1STEP); + if (ret) + return ret; + + break; + case HWTSTAMP_TX_ON: + if (!is_lan937x(dev)) + return -ERANGE; + + prt->ptpmsg_irq[KSZ_SYNC_MSG].ts_en = true; + prt->ptpmsg_irq[KSZ_XDREQ_MSG].ts_en = true; + prt->ptpmsg_irq[KSZ_PDRES_MSG].ts_en = true; + prt->hwts_tx_en = true; + + ret = ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_1STEP, 0); + if (ret) + return ret; + + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + prt->hwts_rx_en = false; + break; + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; + prt->hwts_rx_en = true; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + prt->hwts_rx_en = true; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + prt->hwts_rx_en = true; + break; + default: + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + return ksz_ptp_enable_mode(dev); +} + +int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) +{ + struct ksz_device *dev = ds->priv; + struct hwtstamp_config config; + struct ksz_port *prt; + int ret; + + prt = &dev->ports[port]; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + ret = ksz_set_hwtstamp_config(dev, prt, &config); + if (ret) + return ret; + + memcpy(&prt->tstamp_config, &config, sizeof(config)); + + if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) + return -EFAULT; + + return 0; +} + +static ktime_t ksz_tstamp_reconstruct(struct ksz_device *dev, ktime_t tstamp) +{ + struct timespec64 ptp_clock_time; + struct ksz_ptp_data *ptp_data; + struct timespec64 diff; + struct timespec64 ts; + + ptp_data = &dev->ptp_data; + ts = ktime_to_timespec64(tstamp); + + spin_lock_bh(&ptp_data->clock_lock); + ptp_clock_time = ptp_data->clock_time; + spin_unlock_bh(&ptp_data->clock_lock); + + /* calculate full time from partial time stamp */ + ts.tv_sec = (ptp_clock_time.tv_sec & ~3) | ts.tv_sec; + + /* find nearest possible point in time */ + diff = timespec64_sub(ts, ptp_clock_time); + if (diff.tv_sec > 2) + ts.tv_sec -= 4; + else if (diff.tv_sec < -2) + ts.tv_sec += 4; + + return timespec64_to_ktime(ts); +} + +bool ksz_port_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb, + unsigned int type) +{ + struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); + struct ksz_device *dev = ds->priv; + struct ptp_header *ptp_hdr; + struct ksz_port *prt; + u8 ptp_msg_type; + ktime_t tstamp; + s64 correction; + + prt = &dev->ports[port]; + + tstamp = KSZ_SKB_CB(skb)->tstamp; + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ksz_tstamp_reconstruct(dev, tstamp); + + if (prt->tstamp_config.tx_type != HWTSTAMP_TX_ONESTEP_P2P) + goto out; + + ptp_hdr = ptp_parse_header(skb, type); + if (!ptp_hdr) + goto out; + + ptp_msg_type = ptp_get_msgtype(ptp_hdr, type); + if (ptp_msg_type != PTP_MSGTYPE_PDELAY_REQ) + goto out; + + /* Only subtract the partial time stamp from the correction field. When + * the hardware adds the egress time stamp to the correction field of + * the PDelay_Resp message on tx, also only the partial time stamp will + * be added. + */ + correction = (s64)get_unaligned_be64(&ptp_hdr->correction); + correction -= ktime_to_ns(tstamp) << 16; + + ptp_header_update_correction(skb, type, ptp_hdr, correction); + +out: + return false; +} + +void ksz_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) +{ + struct ksz_device *dev = ds->priv; + struct ptp_header *hdr; + struct sk_buff *clone; + struct ksz_port *prt; + unsigned int type; + u8 ptp_msg_type; + + prt = &dev->ports[port]; + + if (!prt->hwts_tx_en) + return; + + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return; + + hdr = ptp_parse_header(skb, type); + if (!hdr) + return; + + ptp_msg_type = ptp_get_msgtype(hdr, type); + + switch (ptp_msg_type) { + case PTP_MSGTYPE_SYNC: + if (prt->tstamp_config.tx_type == HWTSTAMP_TX_ONESTEP_P2P) + return; + break; + case PTP_MSGTYPE_PDELAY_REQ: + break; + case PTP_MSGTYPE_PDELAY_RESP: + if (prt->tstamp_config.tx_type == HWTSTAMP_TX_ONESTEP_P2P) { + KSZ_SKB_CB(skb)->ptp_type = type; + KSZ_SKB_CB(skb)->update_correction = true; + return; + } + break; + + default: + return; + } + + clone = skb_clone_sk(skb); + if (!clone) + return; + + /* caching the value to be used in tag_ksz.c */ + KSZ_SKB_CB(skb)->clone = clone; +} + +static void ksz_ptp_txtstamp_skb(struct ksz_device *dev, + struct ksz_port *prt, struct sk_buff *skb) +{ + struct skb_shared_hwtstamps hwtstamps = {}; + int ret; + + /* timeout must include DSA master to transmit data, tstamp latency, + * IRQ latency and time for reading the time stamp. + */ + ret = wait_for_completion_timeout(&prt->tstamp_msg_comp, + msecs_to_jiffies(100)); + if (!ret) + return; + + hwtstamps.hwtstamp = prt->tstamp_msg; + skb_complete_tx_timestamp(skb, &hwtstamps); +} + +void ksz_port_deferred_xmit(struct kthread_work *work) +{ + struct ksz_deferred_xmit_work *xmit_work = work_to_xmit_work(work); + struct sk_buff *clone, *skb = xmit_work->skb; + struct dsa_switch *ds = xmit_work->dp->ds; + struct ksz_device *dev = ds->priv; + struct ksz_port *prt; + + prt = &dev->ports[xmit_work->dp->index]; + + clone = KSZ_SKB_CB(skb)->clone; + + skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS; + + reinit_completion(&prt->tstamp_msg_comp); + + dsa_enqueue_skb(skb, skb->dev); + + ksz_ptp_txtstamp_skb(dev, prt, clone); + + kfree(xmit_work); +} + +static int _ksz_ptp_gettime(struct ksz_device *dev, struct timespec64 *ts) +{ + u32 nanoseconds; + u32 seconds; + u8 phase; + int ret; + + /* Copy current PTP clock into shadow registers and read */ + ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_READ_TIME, PTP_READ_TIME); + if (ret) + return ret; + + ret = ksz_read8(dev, REG_PTP_RTC_SUB_NANOSEC__2, &phase); + if (ret) + return ret; + + ret = ksz_read32(dev, REG_PTP_RTC_NANOSEC, &nanoseconds); + if (ret) + return ret; + + ret = ksz_read32(dev, REG_PTP_RTC_SEC, &seconds); + if (ret) + return ret; + + ts->tv_sec = seconds; + ts->tv_nsec = nanoseconds + phase * 8; + + return 0; +} + +static int ksz_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp); + struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data); + int ret; + + mutex_lock(&ptp_data->lock); + ret = _ksz_ptp_gettime(dev, ts); + mutex_unlock(&ptp_data->lock); + + return ret; +} + +static int ksz_ptp_restart_perout(struct ksz_device *dev) +{ + struct ksz_ptp_data *ptp_data = &dev->ptp_data; + s64 now_ns, first_ns, period_ns, next_ns; + struct ptp_perout_request request; + struct timespec64 next; + struct timespec64 now; + unsigned int count; + int ret; + + dev_info(dev->dev, "Restarting periodic output signal\n"); + + ret = _ksz_ptp_gettime(dev, &now); + if (ret) + return ret; + + now_ns = timespec64_to_ns(&now); + first_ns = timespec64_to_ns(&ptp_data->perout_target_time_first); + + /* Calculate next perout event based on start time and period */ + period_ns = timespec64_to_ns(&ptp_data->perout_period); + + if (first_ns < now_ns) { + count = div_u64(now_ns - first_ns, period_ns); + next_ns = first_ns + count * period_ns; + } else { + next_ns = first_ns; + } + + /* Ensure 100 ms guard time prior next event */ + while (next_ns < now_ns + 100000000) + next_ns += period_ns; + + /* Restart periodic output signal */ + next = ns_to_timespec64(next_ns); + request.start.sec = next.tv_sec; + request.start.nsec = next.tv_nsec; + request.period.sec = ptp_data->perout_period.tv_sec; + request.period.nsec = ptp_data->perout_period.tv_nsec; + request.index = 0; + request.flags = 0; + + return ksz_ptp_enable_perout(dev, &request, 1); +} + +static int ksz_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp); + struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data); + int ret; + + mutex_lock(&ptp_data->lock); + + /* Write to shadow registers and Load PTP clock */ + ret = ksz_write16(dev, REG_PTP_RTC_SUB_NANOSEC__2, PTP_RTC_0NS); + if (ret) + goto unlock; + + ret = ksz_write32(dev, REG_PTP_RTC_NANOSEC, ts->tv_nsec); + if (ret) + goto unlock; + + ret = ksz_write32(dev, REG_PTP_RTC_SEC, ts->tv_sec); + if (ret) + goto unlock; + + ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_LOAD_TIME, PTP_LOAD_TIME); + if (ret) + goto unlock; + + switch (ptp_data->tou_mode) { + case KSZ_PTP_TOU_IDLE: + break; + + case KSZ_PTP_TOU_PEROUT: + ret = ksz_ptp_restart_perout(dev); + if (ret) + goto unlock; + + break; + } + + spin_lock_bh(&ptp_data->clock_lock); + ptp_data->clock_time = *ts; + spin_unlock_bh(&ptp_data->clock_lock); + +unlock: + mutex_unlock(&ptp_data->lock); + + return ret; +} + +static int ksz_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp); + struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data); + u64 base, adj; + bool negative; + u32 data32; + int ret; + + mutex_lock(&ptp_data->lock); + + if (scaled_ppm) { + base = KSZ_PTP_INC_NS << KSZ_PTP_SUBNS_BITS; + negative = diff_by_scaled_ppm(base, scaled_ppm, &adj); + + data32 = (u32)adj; + data32 &= PTP_SUBNANOSEC_M; + if (!negative) + data32 |= PTP_RATE_DIR; + + ret = ksz_write32(dev, REG_PTP_SUBNANOSEC_RATE, data32); + if (ret) + goto unlock; + + ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_CLK_ADJ_ENABLE, + PTP_CLK_ADJ_ENABLE); + if (ret) + goto unlock; + } else { + ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_CLK_ADJ_ENABLE, 0); + if (ret) + goto unlock; + } + +unlock: + mutex_unlock(&ptp_data->lock); + return ret; +} + +static int ksz_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp); + struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data); + struct timespec64 delta64 = ns_to_timespec64(delta); + s32 sec, nsec; + u16 data16; + int ret; + + mutex_lock(&ptp_data->lock); + + /* do not use ns_to_timespec64(), + * both sec and nsec are subtracted by hw + */ + sec = div_s64_rem(delta, NSEC_PER_SEC, &nsec); + + ret = ksz_write32(dev, REG_PTP_RTC_NANOSEC, abs(nsec)); + if (ret) + goto unlock; + + ret = ksz_write32(dev, REG_PTP_RTC_SEC, abs(sec)); + if (ret) + goto unlock; + + ret = ksz_read16(dev, REG_PTP_CLK_CTRL, &data16); + if (ret) + goto unlock; + + data16 |= PTP_STEP_ADJ; + + /* PTP_STEP_DIR -- 0: subtract, 1: add */ + if (delta < 0) + data16 &= ~PTP_STEP_DIR; + else + data16 |= PTP_STEP_DIR; + + ret = ksz_write16(dev, REG_PTP_CLK_CTRL, data16); + if (ret) + goto unlock; + + switch (ptp_data->tou_mode) { + case KSZ_PTP_TOU_IDLE: + break; + + case KSZ_PTP_TOU_PEROUT: + ret = ksz_ptp_restart_perout(dev); + if (ret) + goto unlock; + + break; + } + + spin_lock_bh(&ptp_data->clock_lock); + ptp_data->clock_time = timespec64_add(ptp_data->clock_time, delta64); + spin_unlock_bh(&ptp_data->clock_lock); + +unlock: + mutex_unlock(&ptp_data->lock); + return ret; +} + +static int ksz_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *req, int on) +{ + struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp); + struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data); + int ret; + + switch (req->type) { + case PTP_CLK_REQ_PEROUT: + mutex_lock(&ptp_data->lock); + ret = ksz_ptp_enable_perout(dev, &req->perout, on); + mutex_unlock(&ptp_data->lock); + break; + default: + return -EOPNOTSUPP; + } + + return ret; +} + +static int ksz_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + int ret = 0; + + switch (func) { + case PTP_PF_NONE: + case PTP_PF_PEROUT: + break; + default: + ret = -1; + break; + } + + return ret; +} + +/* Function is pointer to the do_aux_work in the ptp_clock capability */ +static long ksz_ptp_do_aux_work(struct ptp_clock_info *ptp) +{ + struct ksz_ptp_data *ptp_data = ptp_caps_to_data(ptp); + struct ksz_device *dev = ptp_data_to_ksz_dev(ptp_data); + struct timespec64 ts; + int ret; + + mutex_lock(&ptp_data->lock); + ret = _ksz_ptp_gettime(dev, &ts); + if (ret) + goto out; + + spin_lock_bh(&ptp_data->clock_lock); + ptp_data->clock_time = ts; + spin_unlock_bh(&ptp_data->clock_lock); + +out: + mutex_unlock(&ptp_data->lock); + + return HZ; /* reschedule in 1 second */ +} + +static int ksz_ptp_start_clock(struct ksz_device *dev) +{ + struct ksz_ptp_data *ptp_data = &dev->ptp_data; + int ret; + + ret = ksz_rmw16(dev, REG_PTP_CLK_CTRL, PTP_CLK_ENABLE, PTP_CLK_ENABLE); + if (ret) + return ret; + + ptp_data->clock_time.tv_sec = 0; + ptp_data->clock_time.tv_nsec = 0; + + return 0; +} + +int ksz_ptp_clock_register(struct dsa_switch *ds) +{ + struct ksz_device *dev = ds->priv; + struct ksz_ptp_data *ptp_data; + int ret; + u8 i; + + ptp_data = &dev->ptp_data; + mutex_init(&ptp_data->lock); + spin_lock_init(&ptp_data->clock_lock); + + ptp_data->caps.owner = THIS_MODULE; + snprintf(ptp_data->caps.name, 16, "Microchip Clock"); + ptp_data->caps.max_adj = KSZ_MAX_DRIFT_CORR; + ptp_data->caps.gettime64 = ksz_ptp_gettime; + ptp_data->caps.settime64 = ksz_ptp_settime; + ptp_data->caps.adjfine = ksz_ptp_adjfine; + ptp_data->caps.adjtime = ksz_ptp_adjtime; + ptp_data->caps.do_aux_work = ksz_ptp_do_aux_work; + ptp_data->caps.enable = ksz_ptp_enable; + ptp_data->caps.verify = ksz_ptp_verify_pin; + ptp_data->caps.n_pins = KSZ_PTP_N_GPIO; + ptp_data->caps.n_per_out = 3; + + ret = ksz_ptp_start_clock(dev); + if (ret) + return ret; + + for (i = 0; i < KSZ_PTP_N_GPIO; i++) { + struct ptp_pin_desc *ptp_pin = &ptp_data->pin_config[i]; + + snprintf(ptp_pin->name, + sizeof(ptp_pin->name), "ksz_ptp_pin_%02d", i); + ptp_pin->index = i; + ptp_pin->func = PTP_PF_NONE; + } + + ptp_data->caps.pin_config = ptp_data->pin_config; + + /* Currently only P2P mode is supported. When 802_1AS bit is set, it + * forwards all PTP packets to host port and none to other ports. + */ + ret = ksz_rmw16(dev, REG_PTP_MSG_CONF1, PTP_TC_P2P | PTP_802_1AS, + PTP_TC_P2P | PTP_802_1AS); + if (ret) + return ret; + + ptp_data->clock = ptp_clock_register(&ptp_data->caps, dev->dev); + if (IS_ERR_OR_NULL(ptp_data->clock)) + return PTR_ERR(ptp_data->clock); + + return 0; +} + +void ksz_ptp_clock_unregister(struct dsa_switch *ds) +{ + struct ksz_device *dev = ds->priv; + struct ksz_ptp_data *ptp_data; + + ptp_data = &dev->ptp_data; + + if (ptp_data->clock) + ptp_clock_unregister(ptp_data->clock); +} + +static irqreturn_t ksz_ptp_msg_thread_fn(int irq, void *dev_id) +{ + struct ksz_ptp_irq *ptpmsg_irq = dev_id; + struct ksz_device *dev; + struct ksz_port *port; + u32 tstamp_raw; + ktime_t tstamp; + int ret; + + port = ptpmsg_irq->port; + dev = port->ksz_dev; + + if (ptpmsg_irq->ts_en) { + ret = ksz_read32(dev, ptpmsg_irq->ts_reg, &tstamp_raw); + if (ret) + return IRQ_NONE; + + tstamp = ksz_decode_tstamp(tstamp_raw); + + port->tstamp_msg = ksz_tstamp_reconstruct(dev, tstamp); + + complete(&port->tstamp_msg_comp); + } + + return IRQ_HANDLED; +} + +static irqreturn_t ksz_ptp_irq_thread_fn(int irq, void *dev_id) +{ + struct ksz_irq *ptpirq = dev_id; + unsigned int nhandled = 0; + struct ksz_device *dev; + unsigned int sub_irq; + u16 data; + int ret; + u8 n; + + dev = ptpirq->dev; + + ret = ksz_read16(dev, ptpirq->reg_status, &data); + if (ret) + goto out; + + /* Clear the interrupts W1C */ + ret = ksz_write16(dev, ptpirq->reg_status, data); + if (ret) + return IRQ_NONE; + + for (n = 0; n < ptpirq->nirqs; ++n) { + if (data & BIT(n + KSZ_PTP_INT_START)) { + sub_irq = irq_find_mapping(ptpirq->domain, n); + handle_nested_irq(sub_irq); + ++nhandled; + } + } + +out: + return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); +} + +static void ksz_ptp_irq_mask(struct irq_data *d) +{ + struct ksz_irq *kirq = irq_data_get_irq_chip_data(d); + + kirq->masked &= ~BIT(d->hwirq + KSZ_PTP_INT_START); +} + +static void ksz_ptp_irq_unmask(struct irq_data *d) +{ + struct ksz_irq *kirq = irq_data_get_irq_chip_data(d); + + kirq->masked |= BIT(d->hwirq + KSZ_PTP_INT_START); +} + +static void ksz_ptp_irq_bus_lock(struct irq_data *d) +{ + struct ksz_irq *kirq = irq_data_get_irq_chip_data(d); + + mutex_lock(&kirq->dev->lock_irq); +} + +static void ksz_ptp_irq_bus_sync_unlock(struct irq_data *d) +{ + struct ksz_irq *kirq = irq_data_get_irq_chip_data(d); + struct ksz_device *dev = kirq->dev; + int ret; + + ret = ksz_write16(dev, kirq->reg_mask, kirq->masked); + if (ret) + dev_err(dev->dev, "failed to change IRQ mask\n"); + + mutex_unlock(&dev->lock_irq); +} + +static const struct irq_chip ksz_ptp_irq_chip = { + .name = "ksz-irq", + .irq_mask = ksz_ptp_irq_mask, + .irq_unmask = ksz_ptp_irq_unmask, + .irq_bus_lock = ksz_ptp_irq_bus_lock, + .irq_bus_sync_unlock = ksz_ptp_irq_bus_sync_unlock, +}; + +static int ksz_ptp_irq_domain_map(struct irq_domain *d, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, d->host_data); + irq_set_chip_and_handler(irq, &ksz_ptp_irq_chip, handle_level_irq); + irq_set_noprobe(irq); + + return 0; +} + +static const struct irq_domain_ops ksz_ptp_irq_domain_ops = { + .map = ksz_ptp_irq_domain_map, + .xlate = irq_domain_xlate_twocell, +}; + +static void ksz_ptp_msg_irq_free(struct ksz_port *port, u8 n) +{ + struct ksz_ptp_irq *ptpmsg_irq; + + ptpmsg_irq = &port->ptpmsg_irq[n]; + + free_irq(ptpmsg_irq->num, ptpmsg_irq); + irq_dispose_mapping(ptpmsg_irq->num); +} + +static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) +{ + u16 ts_reg[] = {REG_PTP_PORT_PDRESP_TS, REG_PTP_PORT_XDELAY_TS, + REG_PTP_PORT_SYNC_TS}; + static const char * const name[] = {"pdresp-msg", "xdreq-msg", + "sync-msg"}; + const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops; + struct ksz_ptp_irq *ptpmsg_irq; + + ptpmsg_irq = &port->ptpmsg_irq[n]; + + ptpmsg_irq->port = port; + ptpmsg_irq->ts_reg = ops->get_port_addr(port->num, ts_reg[n]); + + snprintf(ptpmsg_irq->name, sizeof(ptpmsg_irq->name), name[n]); + + ptpmsg_irq->num = irq_find_mapping(port->ptpirq.domain, n); + if (ptpmsg_irq->num < 0) + return ptpmsg_irq->num; + + return request_threaded_irq(ptpmsg_irq->num, NULL, + ksz_ptp_msg_thread_fn, IRQF_ONESHOT, + ptpmsg_irq->name, ptpmsg_irq); +} + +int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) +{ + struct ksz_device *dev = ds->priv; + const struct ksz_dev_ops *ops = dev->dev_ops; + struct ksz_port *port = &dev->ports[p]; + struct ksz_irq *ptpirq = &port->ptpirq; + int irq; + int ret; + + ptpirq->dev = dev; + ptpirq->masked = 0; + ptpirq->nirqs = 3; + ptpirq->reg_mask = ops->get_port_addr(p, REG_PTP_PORT_TX_INT_ENABLE__2); + ptpirq->reg_status = ops->get_port_addr(p, + REG_PTP_PORT_TX_INT_STATUS__2); + snprintf(ptpirq->name, sizeof(ptpirq->name), "ptp-irq-%d", p); + + init_completion(&port->tstamp_msg_comp); + + ptpirq->domain = irq_domain_add_linear(dev->dev->of_node, ptpirq->nirqs, + &ksz_ptp_irq_domain_ops, ptpirq); + if (!ptpirq->domain) + return -ENOMEM; + + for (irq = 0; irq < ptpirq->nirqs; irq++) + irq_create_mapping(ptpirq->domain, irq); + + ptpirq->irq_num = irq_find_mapping(port->pirq.domain, PORT_SRC_PTP_INT); + if (ptpirq->irq_num < 0) { + ret = ptpirq->irq_num; + goto out; + } + + ret = request_threaded_irq(ptpirq->irq_num, NULL, ksz_ptp_irq_thread_fn, + IRQF_ONESHOT, ptpirq->name, ptpirq); + if (ret) + goto out; + + for (irq = 0; irq < ptpirq->nirqs; irq++) { + ret = ksz_ptp_msg_irq_setup(port, irq); + if (ret) + goto out_ptp_msg; + } + + return 0; + +out_ptp_msg: + free_irq(ptpirq->irq_num, ptpirq); + while (irq--) + free_irq(port->ptpmsg_irq[irq].num, &port->ptpmsg_irq[irq]); +out: + for (irq = 0; irq < ptpirq->nirqs; irq++) + irq_dispose_mapping(port->ptpmsg_irq[irq].num); + + irq_domain_remove(ptpirq->domain); + + return ret; +} + +void ksz_ptp_irq_free(struct dsa_switch *ds, u8 p) +{ + struct ksz_device *dev = ds->priv; + struct ksz_port *port = &dev->ports[p]; + struct ksz_irq *ptpirq = &port->ptpirq; + u8 n; + + for (n = 0; n < ptpirq->nirqs; n++) + ksz_ptp_msg_irq_free(port, n); + + free_irq(ptpirq->irq_num, ptpirq); + irq_dispose_mapping(ptpirq->irq_num); + + irq_domain_remove(ptpirq->domain); +} + +MODULE_AUTHOR("Christian Eggers <ceggers@arri.de>"); +MODULE_AUTHOR("Arun Ramadoss <arun.ramadoss@microchip.com>"); +MODULE_DESCRIPTION("PTP support for KSZ switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/microchip/ksz_ptp.h b/drivers/net/dsa/microchip/ksz_ptp.h new file mode 100644 index 000000000000..0ca8ca4f804e --- /dev/null +++ b/drivers/net/dsa/microchip/ksz_ptp.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Microchip KSZ PTP Implementation + * + * Copyright (C) 2020 ARRI Lighting + * Copyright (C) 2022 Microchip Technology Inc. + */ + +#ifndef _NET_DSA_DRIVERS_KSZ_PTP_H +#define _NET_DSA_DRIVERS_KSZ_PTP_H + +#if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_PTP) + +#include <linux/ptp_clock_kernel.h> + +#define KSZ_PTP_N_GPIO 2 + +enum ksz_ptp_tou_mode { + KSZ_PTP_TOU_IDLE, + KSZ_PTP_TOU_PEROUT, +}; + +struct ksz_ptp_data { + struct ptp_clock_info caps; + struct ptp_clock *clock; + struct ptp_pin_desc pin_config[KSZ_PTP_N_GPIO]; + /* Serializes all operations on the PTP hardware clock */ + struct mutex lock; + /* lock for accessing the clock_time */ + spinlock_t clock_lock; + struct timespec64 clock_time; + enum ksz_ptp_tou_mode tou_mode; + struct timespec64 perout_target_time_first; /* start of first pulse */ + struct timespec64 perout_period; +}; + +int ksz_ptp_clock_register(struct dsa_switch *ds); + +void ksz_ptp_clock_unregister(struct dsa_switch *ds); + +int ksz_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *ts); +int ksz_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr); +int ksz_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr); +void ksz_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +void ksz_port_deferred_xmit(struct kthread_work *work); +bool ksz_port_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb, + unsigned int type); +int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p); +void ksz_ptp_irq_free(struct dsa_switch *ds, u8 p); + +#else + +struct ksz_ptp_data { + /* Serializes all operations on the PTP hardware clock */ + struct mutex lock; +}; + +static inline int ksz_ptp_clock_register(struct dsa_switch *ds) +{ + return 0; +} + +static inline void ksz_ptp_clock_unregister(struct dsa_switch *ds) { } + +static inline int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) +{ + return 0; +} + +static inline void ksz_ptp_irq_free(struct dsa_switch *ds, u8 p) {} + +#define ksz_get_ts_info NULL + +#define ksz_hwtstamp_get NULL + +#define ksz_hwtstamp_set NULL + +#define ksz_port_rxtstamp NULL + +#define ksz_port_txtstamp NULL + +#define ksz_port_deferred_xmit NULL + +#endif /* End of CONFIG_NET_DSA_MICROCHIP_KSZ_PTP */ + +#endif diff --git a/drivers/net/dsa/microchip/ksz_ptp_reg.h b/drivers/net/dsa/microchip/ksz_ptp_reg.h new file mode 100644 index 000000000000..d71e85510cda --- /dev/null +++ b/drivers/net/dsa/microchip/ksz_ptp_reg.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Microchip KSZ PTP register definitions + * Copyright (C) 2022 Microchip Technology Inc. + */ + +#ifndef __KSZ_PTP_REGS_H +#define __KSZ_PTP_REGS_H + +#define REG_SW_GLOBAL_LED_OVR__4 0x0120 +#define LED_OVR_2 BIT(1) +#define LED_OVR_1 BIT(0) + +#define REG_SW_GLOBAL_LED_SRC__4 0x0128 +#define LED_SRC_PTP_GPIO_1 BIT(3) +#define LED_SRC_PTP_GPIO_2 BIT(2) + +/* 5 - PTP Clock */ +#define REG_PTP_CLK_CTRL 0x0500 + +#define PTP_STEP_ADJ BIT(6) +#define PTP_STEP_DIR BIT(5) +#define PTP_READ_TIME BIT(4) +#define PTP_LOAD_TIME BIT(3) +#define PTP_CLK_ADJ_ENABLE BIT(2) +#define PTP_CLK_ENABLE BIT(1) +#define PTP_CLK_RESET BIT(0) + +#define REG_PTP_RTC_SUB_NANOSEC__2 0x0502 + +#define PTP_RTC_SUB_NANOSEC_M 0x0007 +#define PTP_RTC_0NS 0x00 + +#define REG_PTP_RTC_NANOSEC 0x0504 + +#define REG_PTP_RTC_SEC 0x0508 + +#define REG_PTP_SUBNANOSEC_RATE 0x050C + +#define PTP_SUBNANOSEC_M 0x3FFFFFFF +#define PTP_RATE_DIR BIT(31) +#define PTP_TMP_RATE_ENABLE BIT(30) + +#define REG_PTP_SUBNANOSEC_RATE_L 0x050E + +#define REG_PTP_RATE_DURATION 0x0510 +#define REG_PTP_RATE_DURATION_H 0x0510 +#define REG_PTP_RATE_DURATION_L 0x0512 + +#define REG_PTP_MSG_CONF1 0x0514 + +#define PTP_802_1AS BIT(7) +#define PTP_ENABLE BIT(6) +#define PTP_ETH_ENABLE BIT(5) +#define PTP_IPV4_UDP_ENABLE BIT(4) +#define PTP_IPV6_UDP_ENABLE BIT(3) +#define PTP_TC_P2P BIT(2) +#define PTP_MASTER BIT(1) +#define PTP_1STEP BIT(0) + +#define REG_PTP_UNIT_INDEX__4 0x0520 + +#define PTP_GPIO_INDEX GENMASK(19, 16) +#define PTP_TSI_INDEX BIT(8) +#define PTP_TOU_INDEX GENMASK(1, 0) + +#define REG_PTP_TRIG_STATUS__4 0x0524 + +#define TRIG_ERROR_M GENMASK(18, 16) +#define TRIG_DONE_M GENMASK(2, 0) + +#define REG_PTP_INT_STATUS__4 0x0528 + +#define TRIG_INT_M GENMASK(18, 16) +#define TS_INT_M GENMASK(1, 0) + +#define REG_PTP_CTRL_STAT__4 0x052C + +#define GPIO_IN BIT(7) +#define GPIO_OUT BIT(6) +#define TS_INT_ENABLE BIT(5) +#define TRIG_ACTIVE BIT(4) +#define TRIG_ENABLE BIT(3) +#define TRIG_RESET BIT(2) +#define TS_ENABLE BIT(1) +#define TS_RESET BIT(0) + +#define REG_TRIG_TARGET_NANOSEC 0x0530 +#define REG_TRIG_TARGET_SEC 0x0534 + +#define REG_TRIG_CTRL__4 0x0538 + +#define TRIG_CASCADE_ENABLE BIT(31) +#define TRIG_CASCADE_TAIL BIT(30) +#define TRIG_CASCADE_UPS_M GENMASK(29, 26) +#define TRIG_NOW BIT(25) +#define TRIG_NOTIFY BIT(24) +#define TRIG_EDGE BIT(23) +#define TRIG_PATTERN_M GENMASK(22, 20) +#define TRIG_NEG_EDGE 0 +#define TRIG_POS_EDGE 1 +#define TRIG_NEG_PULSE 2 +#define TRIG_POS_PULSE 3 +#define TRIG_NEG_PERIOD 4 +#define TRIG_POS_PERIOD 5 +#define TRIG_REG_OUTPUT 6 +#define TRIG_GPO_M GENMASK(19, 16) +#define TRIG_CASCADE_ITERATE_CNT_M GENMASK(15, 0) + +#define REG_TRIG_CYCLE_WIDTH 0x053C +#define TRIG_CYCLE_WIDTH_M GENMASK(31, 0) + +#define REG_TRIG_CYCLE_CNT 0x0540 + +#define TRIG_CYCLE_CNT_M GENMASK(31, 16) +#define TRIG_BIT_PATTERN_M GENMASK(15, 0) + +#define REG_TRIG_ITERATE_TIME 0x0544 + +#define REG_TRIG_PULSE_WIDTH__4 0x0548 + +#define TRIG_PULSE_WIDTH_M GENMASK(23, 0) + +/* Port PTP Register */ +#define REG_PTP_PORT_RX_DELAY__2 0x0C00 +#define REG_PTP_PORT_TX_DELAY__2 0x0C02 +#define REG_PTP_PORT_ASYM_DELAY__2 0x0C04 + +#define REG_PTP_PORT_XDELAY_TS 0x0C08 +#define REG_PTP_PORT_SYNC_TS 0x0C0C +#define REG_PTP_PORT_PDRESP_TS 0x0C10 + +#define REG_PTP_PORT_TX_INT_STATUS__2 0x0C14 +#define REG_PTP_PORT_TX_INT_ENABLE__2 0x0C16 + +#define PTP_PORT_SYNC_INT BIT(15) +#define PTP_PORT_XDELAY_REQ_INT BIT(14) +#define PTP_PORT_PDELAY_RESP_INT BIT(13) +#define KSZ_SYNC_MSG 2 +#define KSZ_XDREQ_MSG 1 +#define KSZ_PDRES_MSG 0 + +#endif diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 908fa89444c9..616b21c90d05 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -608,17 +608,29 @@ mt7530_mib_reset(struct dsa_switch *ds) mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_ACTIVATE); } -static int mt7530_phy_read(struct mt7530_priv *priv, int port, int regnum) +static int mt7530_phy_read_c22(struct mt7530_priv *priv, int port, int regnum) { return mdiobus_read_nested(priv->bus, port, regnum); } -static int mt7530_phy_write(struct mt7530_priv *priv, int port, int regnum, - u16 val) +static int mt7530_phy_write_c22(struct mt7530_priv *priv, int port, int regnum, + u16 val) { return mdiobus_write_nested(priv->bus, port, regnum, val); } +static int mt7530_phy_read_c45(struct mt7530_priv *priv, int port, + int devad, int regnum) +{ + return mdiobus_c45_read_nested(priv->bus, port, devad, regnum); +} + +static int mt7530_phy_write_c45(struct mt7530_priv *priv, int port, int devad, + int regnum, u16 val) +{ + return mdiobus_c45_write_nested(priv->bus, port, devad, regnum, val); +} + static int mt7531_ind_c45_phy_read(struct mt7530_priv *priv, int port, int devad, int regnum) @@ -670,7 +682,7 @@ out: static int mt7531_ind_c45_phy_write(struct mt7530_priv *priv, int port, int devad, - int regnum, u32 data) + int regnum, u16 data) { struct mii_bus *bus = priv->bus; struct mt7530_dummy_poll p; @@ -793,55 +805,36 @@ out: } static int -mt7531_ind_phy_read(struct mt7530_priv *priv, int port, int regnum) +mt753x_phy_read_c22(struct mii_bus *bus, int port, int regnum) { - int devad; - int ret; - - if (regnum & MII_ADDR_C45) { - devad = (regnum >> MII_DEVADDR_C45_SHIFT) & 0x1f; - ret = mt7531_ind_c45_phy_read(priv, port, devad, - regnum & MII_REGADDR_C45_MASK); - } else { - ret = mt7531_ind_c22_phy_read(priv, port, regnum); - } + struct mt7530_priv *priv = bus->priv; - return ret; + return priv->info->phy_read_c22(priv, port, regnum); } static int -mt7531_ind_phy_write(struct mt7530_priv *priv, int port, int regnum, - u16 data) +mt753x_phy_read_c45(struct mii_bus *bus, int port, int devad, int regnum) { - int devad; - int ret; - - if (regnum & MII_ADDR_C45) { - devad = (regnum >> MII_DEVADDR_C45_SHIFT) & 0x1f; - ret = mt7531_ind_c45_phy_write(priv, port, devad, - regnum & MII_REGADDR_C45_MASK, - data); - } else { - ret = mt7531_ind_c22_phy_write(priv, port, regnum, data); - } + struct mt7530_priv *priv = bus->priv; - return ret; + return priv->info->phy_read_c45(priv, port, devad, regnum); } static int -mt753x_phy_read(struct mii_bus *bus, int port, int regnum) +mt753x_phy_write_c22(struct mii_bus *bus, int port, int regnum, u16 val) { struct mt7530_priv *priv = bus->priv; - return priv->info->phy_read(priv, port, regnum); + return priv->info->phy_write_c22(priv, port, regnum, val); } static int -mt753x_phy_write(struct mii_bus *bus, int port, int regnum, u16 val) +mt753x_phy_write_c45(struct mii_bus *bus, int port, int devad, int regnum, + u16 val) { struct mt7530_priv *priv = bus->priv; - return priv->info->phy_write(priv, port, regnum, val); + return priv->info->phy_write_c45(priv, port, devad, regnum, val); } static void @@ -2086,8 +2079,10 @@ mt7530_setup_mdio(struct mt7530_priv *priv) bus->priv = priv; bus->name = KBUILD_MODNAME "-mii"; snprintf(bus->id, MII_BUS_ID_SIZE, KBUILD_MODNAME "-%d", idx++); - bus->read = mt753x_phy_read; - bus->write = mt753x_phy_write; + bus->read = mt753x_phy_read_c22; + bus->write = mt753x_phy_write_c22; + bus->read_c45 = mt753x_phy_read_c45; + bus->write_c45 = mt753x_phy_write_c45; bus->parent = dev; bus->phy_mask = ~ds->phys_mii_mask; @@ -3182,8 +3177,10 @@ static const struct mt753x_info mt753x_table[] = { .id = ID_MT7621, .pcs_ops = &mt7530_pcs_ops, .sw_setup = mt7530_setup, - .phy_read = mt7530_phy_read, - .phy_write = mt7530_phy_write, + .phy_read_c22 = mt7530_phy_read_c22, + .phy_write_c22 = mt7530_phy_write_c22, + .phy_read_c45 = mt7530_phy_read_c45, + .phy_write_c45 = mt7530_phy_write_c45, .pad_setup = mt7530_pad_clk_setup, .mac_port_get_caps = mt7530_mac_port_get_caps, .mac_port_config = mt7530_mac_config, @@ -3192,8 +3189,10 @@ static const struct mt753x_info mt753x_table[] = { .id = ID_MT7530, .pcs_ops = &mt7530_pcs_ops, .sw_setup = mt7530_setup, - .phy_read = mt7530_phy_read, - .phy_write = mt7530_phy_write, + .phy_read_c22 = mt7530_phy_read_c22, + .phy_write_c22 = mt7530_phy_write_c22, + .phy_read_c45 = mt7530_phy_read_c45, + .phy_write_c45 = mt7530_phy_write_c45, .pad_setup = mt7530_pad_clk_setup, .mac_port_get_caps = mt7530_mac_port_get_caps, .mac_port_config = mt7530_mac_config, @@ -3202,8 +3201,10 @@ static const struct mt753x_info mt753x_table[] = { .id = ID_MT7531, .pcs_ops = &mt7531_pcs_ops, .sw_setup = mt7531_setup, - .phy_read = mt7531_ind_phy_read, - .phy_write = mt7531_ind_phy_write, + .phy_read_c22 = mt7531_ind_c22_phy_read, + .phy_write_c22 = mt7531_ind_c22_phy_write, + .phy_read_c45 = mt7531_ind_c45_phy_read, + .phy_write_c45 = mt7531_ind_c45_phy_write, .pad_setup = mt7531_pad_setup, .cpu_port_config = mt7531_cpu_port_config, .mac_port_get_caps = mt7531_mac_port_get_caps, @@ -3263,7 +3264,7 @@ mt7530_probe(struct mdio_device *mdiodev) * properly. */ if (!priv->info->sw_setup || !priv->info->pad_setup || - !priv->info->phy_read || !priv->info->phy_write || + !priv->info->phy_read_c22 || !priv->info->phy_write_c22 || !priv->info->mac_port_get_caps || !priv->info->mac_port_config) return -EINVAL; diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index e8d966435350..6b2fc6290ea8 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -750,8 +750,10 @@ struct mt753x_pcs { /* struct mt753x_info - This is the main data structure for holding the specific * part for each supported device * @sw_setup: Holding the handler to a device initialization - * @phy_read: Holding the way reading PHY port - * @phy_write: Holding the way writing PHY port + * @phy_read_c22: Holding the way reading PHY port using C22 + * @phy_write_c22: Holding the way writing PHY port using C22 + * @phy_read_c45: Holding the way reading PHY port using C45 + * @phy_write_c45: Holding the way writing PHY port using C45 * @pad_setup: Holding the way setting up the bus pad for a certain * MAC port * @phy_mode_supported: Check if the PHY type is being supported on a certain @@ -767,8 +769,13 @@ struct mt753x_info { const struct phylink_pcs_ops *pcs_ops; int (*sw_setup)(struct dsa_switch *ds); - int (*phy_read)(struct mt7530_priv *priv, int port, int regnum); - int (*phy_write)(struct mt7530_priv *priv, int port, int regnum, u16 val); + int (*phy_read_c22)(struct mt7530_priv *priv, int port, int regnum); + int (*phy_write_c22)(struct mt7530_priv *priv, int port, int regnum, + u16 val); + int (*phy_read_c45)(struct mt7530_priv *priv, int port, int devad, + int regnum); + int (*phy_write_c45)(struct mt7530_priv *priv, int port, int devad, + int regnum, u16 val); int (*pad_setup)(struct dsa_switch *ds, phy_interface_t interface); int (*cpu_port_config)(struct dsa_switch *ds, int port); void (*mac_port_get_caps)(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile index 49bf358b9c4f..1409e691ab77 100644 --- a/drivers/net/dsa/mv88e6xxx/Makefile +++ b/drivers/net/dsa/mv88e6xxx/Makefile @@ -15,6 +15,7 @@ mv88e6xxx-objs += port_hidden.o mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += ptp.o mv88e6xxx-objs += serdes.o mv88e6xxx-objs += smi.o +mv88e6xxx-objs += switchdev.o mv88e6xxx-objs += trace.o # for tracing framework to find trace.h diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 242b8b325504..0a5d6c7bb128 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1728,11 +1728,11 @@ static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid, return err; } -static int mv88e6xxx_vtu_walk(struct mv88e6xxx_chip *chip, - int (*cb)(struct mv88e6xxx_chip *chip, - const struct mv88e6xxx_vtu_entry *entry, - void *priv), - void *priv) +int mv88e6xxx_vtu_walk(struct mv88e6xxx_chip *chip, + int (*cb)(struct mv88e6xxx_chip *chip, + const struct mv88e6xxx_vtu_entry *entry, + void *priv), + void *priv) { struct mv88e6xxx_vtu_entry entry = { .vid = mv88e6xxx_max_vid(chip), @@ -3884,6 +3884,24 @@ static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg) return err ? err : val; } +static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad, + int reg) +{ + struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; + struct mv88e6xxx_chip *chip = mdio_bus->chip; + u16 val; + int err; + + if (!chip->info->ops->phy_read_c45) + return -EOPNOTSUPP; + + mv88e6xxx_reg_lock(chip); + err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val); + mv88e6xxx_reg_unlock(chip); + + return err ? err : val; +} + static int mv88e6xxx_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) { struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; @@ -3900,6 +3918,23 @@ static int mv88e6xxx_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) return err; } +static int mv88e6xxx_mdio_write_c45(struct mii_bus *bus, int phy, int devad, + int reg, u16 val) +{ + struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; + struct mv88e6xxx_chip *chip = mdio_bus->chip; + int err; + + if (!chip->info->ops->phy_write_c45) + return -EOPNOTSUPP; + + mv88e6xxx_reg_lock(chip); + err = chip->info->ops->phy_write_c45(chip, bus, phy, devad, reg, val); + mv88e6xxx_reg_unlock(chip); + + return err; +} + static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, struct device_node *np, bool external) @@ -3938,6 +3973,8 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, bus->read = mv88e6xxx_mdio_read; bus->write = mv88e6xxx_mdio_write; + bus->read_c45 = mv88e6xxx_mdio_read_c45; + bus->write_c45 = mv88e6xxx_mdio_write_c45; bus->parent = chip->dev; if (!external) { @@ -4149,8 +4186,10 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6185_port_sync_link, .port_set_speed_duplex = mv88e6185_port_set_speed_duplex, @@ -4198,8 +4237,10 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_speed_duplex = mv88e6185_port_set_speed_duplex, @@ -4279,8 +4320,10 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -4343,8 +4386,10 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_speed_duplex = mv88e6185_port_set_speed_duplex, @@ -4426,8 +4471,10 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -4472,8 +4519,10 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -4527,8 +4576,10 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -4573,8 +4624,10 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -4673,8 +4726,10 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -4736,8 +4791,10 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -4799,8 +4856,10 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -4862,8 +4921,10 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -4925,8 +4986,10 @@ static const struct mv88e6xxx_ops mv88e6250_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -4964,8 +5027,10 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -5017,7 +5082,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, - .ptp_ops = &mv88e6352_ptp_ops, + .ptp_ops = &mv88e6390_ptp_ops, .phylink_get_caps = mv88e6390_phylink_get_caps, }; @@ -5029,8 +5094,10 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay, @@ -5074,8 +5141,10 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay, @@ -5117,8 +5186,10 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -5183,8 +5254,10 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -5227,8 +5300,10 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .ip_pri_map = mv88e6085_g1_ip_pri_map, .irl_init_all = mv88e6352_g2_irl_init_all, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -5275,8 +5350,10 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom16, .set_eeprom = mv88e6xxx_g2_set_eeprom16, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, @@ -5340,8 +5417,10 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -5391,7 +5470,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .serdes_irq_status = mv88e6390_serdes_irq_status, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, - .ptp_ops = &mv88e6352_ptp_ops, + .ptp_ops = &mv88e6390_ptp_ops, .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, @@ -5407,8 +5486,10 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -5462,7 +5543,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, - .ptp_ops = &mv88e6352_ptp_ops, + .ptp_ops = &mv88e6390_ptp_ops, .phylink_get_caps = mv88e6390x_phylink_get_caps, }; @@ -5473,8 +5554,10 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = { .get_eeprom = mv88e6xxx_g2_get_eeprom8, .set_eeprom = mv88e6xxx_g2_set_eeprom8, .set_switch_mac = mv88e6xxx_g2_set_switch_mac, - .phy_read = mv88e6xxx_g2_smi_phy_read, - .phy_write = mv88e6xxx_g2_smi_phy_write, + .phy_read = mv88e6xxx_g2_smi_phy_read_c22, + .phy_write = mv88e6xxx_g2_smi_phy_write_c22, + .phy_read_c45 = mv88e6xxx_g2_smi_phy_read_c45, + .phy_write_c45 = mv88e6xxx_g2_smi_phy_write_c45, .port_set_link = mv88e6xxx_port_set_link, .port_sync_link = mv88e6xxx_port_sync_link, .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay, @@ -6526,7 +6609,7 @@ static int mv88e6xxx_port_pre_bridge_flags(struct dsa_switch *ds, int port, const struct mv88e6xxx_ops *ops; if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | - BR_BCAST_FLOOD | BR_PORT_LOCKED)) + BR_BCAST_FLOOD | BR_PORT_LOCKED | BR_PORT_MAB)) return -EINVAL; ops = chip->info->ops; @@ -6545,7 +6628,7 @@ static int mv88e6xxx_port_bridge_flags(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack) { struct mv88e6xxx_chip *chip = ds->priv; - int err = -EOPNOTSUPP; + int err = 0; mv88e6xxx_reg_lock(chip); @@ -6584,6 +6667,12 @@ static int mv88e6xxx_port_bridge_flags(struct dsa_switch *ds, int port, goto out; } + if (flags.mask & BR_PORT_MAB) { + bool mab = !!(flags.val & BR_PORT_MAB); + + mv88e6xxx_port_set_mab(chip, port, mab); + } + if (flags.mask & BR_PORT_LOCKED) { bool locked = !!(flags.val & BR_PORT_LOCKED); diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index e693154cf803..da6e1339f809 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -280,6 +280,9 @@ struct mv88e6xxx_port { unsigned int serdes_irq; char serdes_irq_name[64]; struct devlink_region *region; + + /* MacAuth Bypass control flag */ + bool mab; }; enum mv88e6xxx_region_id { @@ -451,6 +454,13 @@ struct mv88e6xxx_ops { struct mii_bus *bus, int addr, int reg, u16 val); + int (*phy_read_c45)(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int devad, int reg, u16 *val); + int (*phy_write_c45)(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int devad, int reg, u16 val); + /* Priority Override Table operations */ int (*pot_clear)(struct mv88e6xxx_chip *chip); @@ -705,6 +715,7 @@ struct mv88e6xxx_ptp_ops { int (*port_disable)(struct mv88e6xxx_chip *chip, int port); int (*global_enable)(struct mv88e6xxx_chip *chip); int (*global_disable)(struct mv88e6xxx_chip *chip); + int (*set_ptp_cpu_port)(struct mv88e6xxx_chip *chip, int port); int n_ext_ts; int arr0_sts_reg; int arr1_sts_reg; @@ -784,6 +795,12 @@ static inline bool mv88e6xxx_is_invalid_port(struct mv88e6xxx_chip *chip, int po return (chip->info->invalid_port_mask & BIT(port)) != 0; } +static inline void mv88e6xxx_port_set_mab(struct mv88e6xxx_chip *chip, + int port, bool mab) +{ + chip->ports[port].mab = mab; +} + int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, @@ -802,6 +819,12 @@ static inline void mv88e6xxx_reg_unlock(struct mv88e6xxx_chip *chip) mutex_unlock(&chip->reg_lock); } +int mv88e6xxx_vtu_walk(struct mv88e6xxx_chip *chip, + int (*cb)(struct mv88e6xxx_chip *chip, + const struct mv88e6xxx_vtu_entry *entry, + void *priv), + void *priv); + int mv88e6xxx_fid_map(struct mv88e6xxx_chip *chip, unsigned long *bitmap); #endif /* _MV88E6XXX_CHIP_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 5848112036b0..2fa55a643591 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -403,6 +403,18 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port) return mv88e6390_g1_monitor_write(chip, ptr, port); } +int mv88e6390_g1_set_ptp_cpu_port(struct mv88e6xxx_chip *chip, int port) +{ + u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_PTP_CPU_DEST; + + /* Use the default high priority for PTP frames sent to + * the CPU. + */ + port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI; + + return mv88e6390_g1_monitor_write(chip, ptr, port); +} + int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip) { u16 ptr; diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 65958b2a0d3a..c99ddd117fe6 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -214,6 +214,7 @@ #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST 0x2000 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST 0x2100 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST 0x3000 +#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_PTP_CPU_DEST 0x3200 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI 0x00e0 #define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK 0x00ff @@ -303,6 +304,7 @@ int mv88e6390_g1_set_egress_port(struct mv88e6xxx_chip *chip, int port); int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); +int mv88e6390_g1_set_ptp_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); int mv88e6085_g1_ip_pri_map(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 61ae2d61e25c..ce3b3690c3c0 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -12,6 +12,7 @@ #include "chip.h" #include "global1.h" +#include "switchdev.h" #include "trace.h" /* Offset 0x01: ATU FID Register */ @@ -409,23 +410,25 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) err = mv88e6xxx_g1_read_atu_violation(chip); if (err) - goto out; + goto out_unlock; err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_ATU_OP, &val); if (err) - goto out; + goto out_unlock; err = mv88e6xxx_g1_atu_fid_read(chip, &fid); if (err) - goto out; + goto out_unlock; err = mv88e6xxx_g1_atu_data_read(chip, &entry); if (err) - goto out; + goto out_unlock; err = mv88e6xxx_g1_atu_mac_read(chip, &entry); if (err) - goto out; + goto out_unlock; + + mv88e6xxx_reg_unlock(chip); spid = entry.state; @@ -441,6 +444,13 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) entry.portvec, entry.mac, fid); chip->ports[spid].atu_miss_violation++; + + if (fid != MV88E6XXX_FID_STANDALONE && chip->ports[spid].mab) { + err = mv88e6xxx_handle_miss_violation(chip, spid, + &entry, fid); + if (err) + goto out; + } } if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) { @@ -449,13 +459,13 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) fid); chip->ports[spid].atu_full_violation++; } - mv88e6xxx_reg_unlock(chip); return IRQ_HANDLED; -out: +out_unlock: mv88e6xxx_reg_unlock(chip); +out: dev_err(chip->dev, "ATU problem: error %d while handling interrupt\n", err); return IRQ_HANDLED; diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index fa65ecd9cb85..ed3b2f88e783 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -739,20 +739,18 @@ static int mv88e6xxx_g2_smi_phy_read_data_c45(struct mv88e6xxx_chip *chip, return mv88e6xxx_g2_read(chip, MV88E6XXX_G2_SMI_PHY_DATA, data); } -static int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, - bool external, int port, int reg, - u16 *data) +static int _mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, + bool external, int port, int devad, + int reg, u16 *data) { - int dev = (reg >> 16) & 0x1f; - int addr = reg & 0xffff; int err; - err = mv88e6xxx_g2_smi_phy_write_addr_c45(chip, external, port, dev, - addr); + err = mv88e6xxx_g2_smi_phy_write_addr_c45(chip, external, port, devad, + reg); if (err) return err; - return mv88e6xxx_g2_smi_phy_read_data_c45(chip, external, port, dev, + return mv88e6xxx_g2_smi_phy_read_data_c45(chip, external, port, devad, data); } @@ -771,51 +769,65 @@ static int mv88e6xxx_g2_smi_phy_write_data_c45(struct mv88e6xxx_chip *chip, return mv88e6xxx_g2_smi_phy_access_c45(chip, external, op, port, dev); } -static int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, - bool external, int port, int reg, - u16 data) +static int _mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, + bool external, int port, int devad, + int reg, u16 data) { - int dev = (reg >> 16) & 0x1f; - int addr = reg & 0xffff; int err; - err = mv88e6xxx_g2_smi_phy_write_addr_c45(chip, external, port, dev, - addr); + err = mv88e6xxx_g2_smi_phy_write_addr_c45(chip, external, port, devad, + reg); if (err) return err; - return mv88e6xxx_g2_smi_phy_write_data_c45(chip, external, port, dev, + return mv88e6xxx_g2_smi_phy_write_data_c45(chip, external, port, devad, data); } -int mv88e6xxx_g2_smi_phy_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus, - int addr, int reg, u16 *val) +int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int reg, u16 *val) { struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; bool external = mdio_bus->external; - if (reg & MII_ADDR_C45) - return mv88e6xxx_g2_smi_phy_read_c45(chip, external, addr, reg, - val); - return mv88e6xxx_g2_smi_phy_read_data_c22(chip, external, addr, reg, val); } -int mv88e6xxx_g2_smi_phy_write(struct mv88e6xxx_chip *chip, struct mii_bus *bus, - int addr, int reg, u16 val) +int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, int addr, int devad, + int reg, u16 *val) { struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; bool external = mdio_bus->external; - if (reg & MII_ADDR_C45) - return mv88e6xxx_g2_smi_phy_write_c45(chip, external, addr, reg, - val); + return _mv88e6xxx_g2_smi_phy_read_c45(chip, external, addr, devad, reg, + val); +} + +int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, int addr, int reg, + u16 val) +{ + struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; + bool external = mdio_bus->external; return mv88e6xxx_g2_smi_phy_write_data_c22(chip, external, addr, reg, val); } +int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, int addr, int devad, + int reg, u16 val) +{ + struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; + bool external = mdio_bus->external; + + return _mv88e6xxx_g2_smi_phy_write_c45(chip, external, addr, devad, reg, + val); +} + /* Offset 0x1B: Watchdog Control */ static int mv88e6097_watchdog_action(struct mv88e6xxx_chip *chip, int irq) { diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index 7536b8b0ad01..e973114d6890 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -314,12 +314,18 @@ int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, int reg, int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); -int mv88e6xxx_g2_smi_phy_read(struct mv88e6xxx_chip *chip, - struct mii_bus *bus, - int addr, int reg, u16 *val); -int mv88e6xxx_g2_smi_phy_write(struct mv88e6xxx_chip *chip, - struct mii_bus *bus, - int addr, int reg, u16 val); +int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int reg, u16 *val); +int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int reg, u16 val); +int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int devad, int reg, u16 *val); +int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, + struct mii_bus *bus, + int addr, int devad, int reg, u16 val); int mv88e6xxx_g2_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6xxx_g2_get_eeprom8(struct mv88e6xxx_chip *chip, diff --git a/drivers/net/dsa/mv88e6xxx/phy.c b/drivers/net/dsa/mv88e6xxx/phy.c index 252b5b3a3efe..8bb88b3d900d 100644 --- a/drivers/net/dsa/mv88e6xxx/phy.c +++ b/drivers/net/dsa/mv88e6xxx/phy.c @@ -55,6 +55,38 @@ int mv88e6xxx_phy_write(struct mv88e6xxx_chip *chip, int phy, int reg, u16 val) return chip->info->ops->phy_write(chip, bus, addr, reg, val); } +int mv88e6xxx_phy_read_c45(struct mv88e6xxx_chip *chip, int phy, int devad, + int reg, u16 *val) +{ + int addr = phy; /* PHY devices addresses start at 0x0 */ + struct mii_bus *bus; + + bus = mv88e6xxx_default_mdio_bus(chip); + if (!bus) + return -EOPNOTSUPP; + + if (!chip->info->ops->phy_read_c45) + return -EOPNOTSUPP; + + return chip->info->ops->phy_read_c45(chip, bus, addr, devad, reg, val); +} + +int mv88e6xxx_phy_write_c45(struct mv88e6xxx_chip *chip, int phy, int devad, + int reg, u16 val) +{ + int addr = phy; /* PHY devices addresses start at 0x0 */ + struct mii_bus *bus; + + bus = mv88e6xxx_default_mdio_bus(chip); + if (!bus) + return -EOPNOTSUPP; + + if (!chip->info->ops->phy_write_c45) + return -EOPNOTSUPP; + + return chip->info->ops->phy_write_c45(chip, bus, addr, devad, reg, val); +} + static int mv88e6xxx_phy_page_get(struct mv88e6xxx_chip *chip, int phy, u8 page) { return mv88e6xxx_phy_write(chip, phy, MV88E6XXX_PHY_PAGE, page); diff --git a/drivers/net/dsa/mv88e6xxx/phy.h b/drivers/net/dsa/mv88e6xxx/phy.h index 05ea0d546969..5f47722364cc 100644 --- a/drivers/net/dsa/mv88e6xxx/phy.h +++ b/drivers/net/dsa/mv88e6xxx/phy.h @@ -28,6 +28,10 @@ int mv88e6xxx_phy_read(struct mv88e6xxx_chip *chip, int phy, int reg, u16 *val); int mv88e6xxx_phy_write(struct mv88e6xxx_chip *chip, int phy, int reg, u16 val); +int mv88e6xxx_phy_read_c45(struct mv88e6xxx_chip *chip, int phy, int devad, + int reg, u16 *val); +int mv88e6xxx_phy_write_c45(struct mv88e6xxx_chip *chip, int phy, int devad, + int reg, u16 val); int mv88e6xxx_phy_page_read(struct mv88e6xxx_chip *chip, int phy, u8 page, int reg, u16 *val); int mv88e6xxx_phy_page_write(struct mv88e6xxx_chip *chip, int phy, diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c index d838c174dc0d..ea17231dc34e 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.c +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -11,6 +11,7 @@ */ #include "chip.h" +#include "global1.h" #include "global2.h" #include "hwtstamp.h" #include "ptp.h" @@ -419,6 +420,34 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = { .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, }; +const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = { + .clock_read = mv88e6352_ptp_clock_read, + .ptp_enable = mv88e6352_ptp_enable, + .ptp_verify = mv88e6352_ptp_verify, + .event_work = mv88e6352_tai_event_work, + .port_enable = mv88e6352_hwtstamp_port_enable, + .port_disable = mv88e6352_hwtstamp_port_disable, + .set_ptp_cpu_port = mv88e6390_g1_set_ptp_cpu_port, + .n_ext_ts = 1, + .arr0_sts_reg = MV88E6XXX_PORT_PTP_ARR0_STS, + .arr1_sts_reg = MV88E6XXX_PORT_PTP_ARR1_STS, + .dep_sts_reg = MV88E6XXX_PORT_PTP_DEP_STS, + .rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), + .cc_shift = MV88E6XXX_CC_SHIFT, + .cc_mult = MV88E6XXX_CC_MULT, + .cc_mult_num = MV88E6XXX_CC_MULT_NUM, + .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, +}; + static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc) { struct mv88e6xxx_chip *chip = cc_to_chip(cc); @@ -491,6 +520,23 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) chip->ptp_clock_info.verify = ptp_ops->ptp_verify; chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work; + if (ptp_ops->set_ptp_cpu_port) { + struct dsa_port *dp; + int upstream = 0; + int err; + + dsa_switch_for_each_user_port(dp, chip->ds) { + upstream = dsa_upstream_port(chip->ds, dp->index); + break; + } + + err = ptp_ops->set_ptp_cpu_port(chip, upstream); + if (err) { + dev_err(chip->dev, "Failed to set PTP CPU destination port!\n"); + return err; + } + } + chip->ptp_clock = ptp_clock_register(&chip->ptp_clock_info, chip->dev); if (IS_ERR(chip->ptp_clock)) return PTR_ERR(chip->ptp_clock); diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h index 269d5d16a466..6c4d09adc93c 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.h +++ b/drivers/net/dsa/mv88e6xxx/ptp.h @@ -151,6 +151,7 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip); extern const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops; extern const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops; extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops; +extern const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops; #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */ @@ -171,6 +172,7 @@ static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip) static const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {}; static const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {}; static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {}; +static const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {}; #endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */ diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index d94150d8f3f4..72faec8f44dc 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -36,17 +36,13 @@ static int mv88e6352_serdes_write(struct mv88e6xxx_chip *chip, int reg, static int mv88e6390_serdes_read(struct mv88e6xxx_chip *chip, int lane, int device, int reg, u16 *val) { - int reg_c45 = MII_ADDR_C45 | device << 16 | reg; - - return mv88e6xxx_phy_read(chip, lane, reg_c45, val); + return mv88e6xxx_phy_read_c45(chip, lane, device, reg, val); } static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip, int lane, int device, int reg, u16 val) { - int reg_c45 = MII_ADDR_C45 | device << 16 | reg; - - return mv88e6xxx_phy_write(chip, lane, reg_c45, val); + return mv88e6xxx_phy_write_c45(chip, lane, device, reg, val); } static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, diff --git a/drivers/net/dsa/mv88e6xxx/switchdev.c b/drivers/net/dsa/mv88e6xxx/switchdev.c new file mode 100644 index 000000000000..4c346a884fb2 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/switchdev.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * switchdev.c + * + * Authors: + * Hans J. Schultz <netdev@kapio-technology.com> + * + */ + +#include <net/switchdev.h> +#include "chip.h" +#include "global1.h" +#include "switchdev.h" + +struct mv88e6xxx_fid_search_ctx { + u16 fid_search; + u16 vid_found; +}; + +static int __mv88e6xxx_find_vid(struct mv88e6xxx_chip *chip, + const struct mv88e6xxx_vtu_entry *entry, + void *priv) +{ + struct mv88e6xxx_fid_search_ctx *ctx = priv; + + if (ctx->fid_search == entry->fid) { + ctx->vid_found = entry->vid; + return 1; + } + + return 0; +} + +static int mv88e6xxx_find_vid(struct mv88e6xxx_chip *chip, u16 fid, u16 *vid) +{ + struct mv88e6xxx_fid_search_ctx ctx; + int err; + + ctx.fid_search = fid; + mv88e6xxx_reg_lock(chip); + err = mv88e6xxx_vtu_walk(chip, __mv88e6xxx_find_vid, &ctx); + mv88e6xxx_reg_unlock(chip); + if (err < 0) + return err; + if (err == 1) + *vid = ctx.vid_found; + else + return -ENOENT; + + return 0; +} + +int mv88e6xxx_handle_miss_violation(struct mv88e6xxx_chip *chip, int port, + struct mv88e6xxx_atu_entry *entry, u16 fid) +{ + struct switchdev_notifier_fdb_info info = { + .addr = entry->mac, + .locked = true, + }; + struct net_device *brport; + struct dsa_port *dp; + u16 vid; + int err; + + err = mv88e6xxx_find_vid(chip, fid, &vid); + if (err) + return err; + + info.vid = vid; + dp = dsa_to_port(chip->ds, port); + + rtnl_lock(); + brport = dsa_port_to_bridge_port(dp); + if (!brport) { + rtnl_unlock(); + return -ENODEV; + } + err = call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, + brport, &info.info, NULL); + rtnl_unlock(); + + return err; +} diff --git a/drivers/net/dsa/mv88e6xxx/switchdev.h b/drivers/net/dsa/mv88e6xxx/switchdev.h new file mode 100644 index 000000000000..62214f9d62b0 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/switchdev.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * + * switchdev.h + * + * Authors: + * Hans J. Schultz <netdev@kapio-technology.com> + * + */ + +#ifndef _MV88E6XXX_SWITCHDEV_H_ +#define _MV88E6XXX_SWITCHDEV_H_ + +#include "chip.h" + +int mv88e6xxx_handle_miss_violation(struct mv88e6xxx_chip *chip, int port, + struct mv88e6xxx_atu_entry *entry, + u16 fid); + +#endif /* _MV88E6XXX_SWITCHDEV_H_ */ diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 01ac70fd7ddf..cbcc457499f3 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -954,8 +954,10 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) return -ENOMEM; bus->name = "VSC9959 internal MDIO bus"; - bus->read = enetc_mdio_read; - bus->write = enetc_mdio_write; + bus->read = enetc_mdio_read_c22; + bus->write = enetc_mdio_write_c22; + bus->read_c45 = enetc_mdio_read_c45; + bus->write_c45 = enetc_mdio_write_c45; bus->parent = dev; mdio_priv = bus->priv; mdio_priv->hw = hw; diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 9ba2ec2b966d..fb1549a5fe32 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -149,8 +149,10 @@ struct sja1105_info { bool (*rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); void (*txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); int (*clocking_setup)(struct sja1105_private *priv); - int (*pcs_mdio_read)(struct mii_bus *bus, int phy, int reg); - int (*pcs_mdio_write)(struct mii_bus *bus, int phy, int reg, u16 val); + int (*pcs_mdio_read_c45)(struct mii_bus *bus, int phy, int mmd, + int reg); + int (*pcs_mdio_write_c45)(struct mii_bus *bus, int phy, int mmd, + int reg, u16 val); int (*disable_microcontroller)(struct sja1105_private *priv); const char *name; bool supports_mii[SJA1105_MAX_NUM_PORTS]; @@ -303,10 +305,12 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv); /* From sja1105_mdio.c */ int sja1105_mdiobus_register(struct dsa_switch *ds); void sja1105_mdiobus_unregister(struct dsa_switch *ds); -int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg); -int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val); -int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg); -int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val); +int sja1105_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg); +int sja1105_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int mmd, int reg, + u16 val); +int sja1110_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg); +int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int mmd, int reg, + u16 val); /* From sja1105_devlink.c */ int sja1105_devlink_setup(struct dsa_switch *ds); diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 4059fcc8c832..2fcb601cb4eb 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -7,20 +7,15 @@ #define SJA1110_PCS_BANK_REG SJA1110_SPI_ADDR(0x3fc) -int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) +int sja1105_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg) { struct sja1105_mdio_private *mdio_priv = bus->priv; struct sja1105_private *priv = mdio_priv->priv; u64 addr; u32 tmp; - u16 mmd; int rc; - if (!(reg & MII_ADDR_C45)) - return -EINVAL; - - mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; - addr = (mmd << 16) | (reg & GENMASK(15, 0)); + addr = (mmd << 16) | reg; if (mmd != MDIO_MMD_VEND1 && mmd != MDIO_MMD_VEND2) return 0xffff; @@ -37,19 +32,15 @@ int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) return tmp & 0xffff; } -int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) +int sja1105_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int mmd, + int reg, u16 val) { struct sja1105_mdio_private *mdio_priv = bus->priv; struct sja1105_private *priv = mdio_priv->priv; u64 addr; u32 tmp; - u16 mmd; - - if (!(reg & MII_ADDR_C45)) - return -EINVAL; - mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; - addr = (mmd << 16) | (reg & GENMASK(15, 0)); + addr = (mmd << 16) | reg; tmp = val; if (mmd != MDIO_MMD_VEND1 && mmd != MDIO_MMD_VEND2) @@ -58,7 +49,7 @@ int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) return sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); } -int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) +int sja1110_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg) { struct sja1105_mdio_private *mdio_priv = bus->priv; struct sja1105_private *priv = mdio_priv->priv; @@ -66,17 +57,12 @@ int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) int offset, bank; u64 addr; u32 tmp; - u16 mmd; int rc; - if (!(reg & MII_ADDR_C45)) - return -EINVAL; - if (regs->pcs_base[phy] == SJA1105_RSV_ADDR) return -ENODEV; - mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; - addr = (mmd << 16) | (reg & GENMASK(15, 0)); + addr = (mmd << 16) | reg; if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID1) return NXP_SJA1110_XPCS_ID >> 16; @@ -108,7 +94,8 @@ int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) return tmp & 0xffff; } -int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) +int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int reg, int mmd, + u16 val) { struct sja1105_mdio_private *mdio_priv = bus->priv; struct sja1105_private *priv = mdio_priv->priv; @@ -116,17 +103,12 @@ int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) int offset, bank; u64 addr; u32 tmp; - u16 mmd; int rc; - if (!(reg & MII_ADDR_C45)) - return -EINVAL; - if (regs->pcs_base[phy] == SJA1105_RSV_ADDR) return -ENODEV; - mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; - addr = (mmd << 16) | (reg & GENMASK(15, 0)); + addr = (mmd << 16) | reg; bank = addr >> 8; offset = addr & GENMASK(7, 0); @@ -167,7 +149,7 @@ static u64 sja1105_base_t1_encode_addr(struct sja1105_private *priv, return regs->mdio_100base_t1 | (phy << 7) | (op << 5) | (xad << 0); } -static int sja1105_base_t1_mdio_read(struct mii_bus *bus, int phy, int reg) +static int sja1105_base_t1_mdio_read_c22(struct mii_bus *bus, int phy, int reg) { struct sja1105_mdio_private *mdio_priv = bus->priv; struct sja1105_private *priv = mdio_priv->priv; @@ -175,30 +157,31 @@ static int sja1105_base_t1_mdio_read(struct mii_bus *bus, int phy, int reg) u32 tmp; int rc; - if (reg & MII_ADDR_C45) { - u16 mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; - - addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR, - mmd); + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f); - tmp = reg & MII_REGADDR_C45_MASK; + rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL); + if (rc < 0) + return rc; - rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); - if (rc < 0) - return rc; + return tmp & 0xffff; +} - addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA, - mmd); +static int sja1105_base_t1_mdio_read_c45(struct mii_bus *bus, int phy, + int mmd, int reg) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + u64 addr; + u32 tmp; + int rc; - rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL); - if (rc < 0) - return rc; + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR, mmd); - return tmp & 0xffff; - } + rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, ®, NULL); + if (rc < 0) + return rc; - /* Clause 22 read */ - addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f); + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA, mmd); rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL); if (rc < 0) @@ -207,41 +190,37 @@ static int sja1105_base_t1_mdio_read(struct mii_bus *bus, int phy, int reg) return tmp & 0xffff; } -static int sja1105_base_t1_mdio_write(struct mii_bus *bus, int phy, int reg, - u16 val) +static int sja1105_base_t1_mdio_write_c22(struct mii_bus *bus, int phy, int reg, + u16 val) { struct sja1105_mdio_private *mdio_priv = bus->priv; struct sja1105_private *priv = mdio_priv->priv; u64 addr; u32 tmp; - int rc; - - if (reg & MII_ADDR_C45) { - u16 mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; - addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR, - mmd); - - tmp = reg & MII_REGADDR_C45_MASK; + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f); - rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); - if (rc < 0) - return rc; + tmp = val & 0xffff; - addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA, - mmd); + return sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); +} - tmp = val & 0xffff; +static int sja1105_base_t1_mdio_write_c45(struct mii_bus *bus, int phy, + int mmd, int reg, u16 val) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + u64 addr; + u32 tmp; + int rc; - rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); - if (rc < 0) - return rc; + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR, mmd); - return 0; - } + rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, ®, NULL); + if (rc < 0) + return rc; - /* Clause 22 write */ - addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f); + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA, mmd); tmp = val & 0xffff; @@ -360,8 +339,10 @@ static int sja1105_mdiobus_base_t1_register(struct sja1105_private *priv, bus->name = "SJA1110 100base-T1 MDIO bus"; snprintf(bus->id, MII_BUS_ID_SIZE, "%s-base-t1", dev_name(priv->ds->dev)); - bus->read = sja1105_base_t1_mdio_read; - bus->write = sja1105_base_t1_mdio_write; + bus->read = sja1105_base_t1_mdio_read_c22; + bus->write = sja1105_base_t1_mdio_write_c22; + bus->read_c45 = sja1105_base_t1_mdio_read_c45; + bus->write_c45 = sja1105_base_t1_mdio_write_c45; bus->parent = priv->ds->dev; mdio_priv = bus->priv; mdio_priv->priv = priv; @@ -398,7 +379,7 @@ static int sja1105_mdiobus_pcs_register(struct sja1105_private *priv) int rc = 0; int port; - if (!priv->info->pcs_mdio_read || !priv->info->pcs_mdio_write) + if (!priv->info->pcs_mdio_read_c45 || !priv->info->pcs_mdio_write_c45) return 0; bus = mdiobus_alloc_size(sizeof(*mdio_priv)); @@ -408,8 +389,8 @@ static int sja1105_mdiobus_pcs_register(struct sja1105_private *priv) bus->name = "SJA1105 PCS MDIO bus"; snprintf(bus->id, MII_BUS_ID_SIZE, "%s-pcs", dev_name(ds->dev)); - bus->read = priv->info->pcs_mdio_read; - bus->write = priv->info->pcs_mdio_write; + bus->read_c45 = priv->info->pcs_mdio_read_c45; + bus->write_c45 = priv->info->pcs_mdio_write_c45; bus->parent = ds->dev; /* There is no PHY on this MDIO bus => mask out all PHY addresses * from auto probing. diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index d3c9ad6d39d4..5ce29c8057a4 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -719,8 +719,8 @@ const struct sja1105_info sja1105r_info = { .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, - .pcs_mdio_read = sja1105_pcs_mdio_read, - .pcs_mdio_write = sja1105_pcs_mdio_write, + .pcs_mdio_read_c45 = sja1105_pcs_mdio_read_c45, + .pcs_mdio_write_c45 = sja1105_pcs_mdio_write_c45, .regs = &sja1105pqrs_regs, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -756,8 +756,8 @@ const struct sja1105_info sja1105s_info = { .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, - .pcs_mdio_read = sja1105_pcs_mdio_read, - .pcs_mdio_write = sja1105_pcs_mdio_write, + .pcs_mdio_read_c45 = sja1105_pcs_mdio_read_c45, + .pcs_mdio_write_c45 = sja1105_pcs_mdio_write_c45, .port_speed = { [SJA1105_SPEED_AUTO] = 0, [SJA1105_SPEED_10MBPS] = 3, @@ -794,8 +794,8 @@ const struct sja1105_info sja1110a_info = { .rxtstamp = sja1110_rxtstamp, .txtstamp = sja1110_txtstamp, .disable_microcontroller = sja1110_disable_microcontroller, - .pcs_mdio_read = sja1110_pcs_mdio_read, - .pcs_mdio_write = sja1110_pcs_mdio_write, + .pcs_mdio_read_c45 = sja1110_pcs_mdio_read_c45, + .pcs_mdio_write_c45 = sja1110_pcs_mdio_write_c45, .port_speed = { [SJA1105_SPEED_AUTO] = 0, [SJA1105_SPEED_10MBPS] = 4, @@ -844,8 +844,8 @@ const struct sja1105_info sja1110b_info = { .rxtstamp = sja1110_rxtstamp, .txtstamp = sja1110_txtstamp, .disable_microcontroller = sja1110_disable_microcontroller, - .pcs_mdio_read = sja1110_pcs_mdio_read, - .pcs_mdio_write = sja1110_pcs_mdio_write, + .pcs_mdio_read_c45 = sja1110_pcs_mdio_read_c45, + .pcs_mdio_write_c45 = sja1110_pcs_mdio_write_c45, .port_speed = { [SJA1105_SPEED_AUTO] = 0, [SJA1105_SPEED_10MBPS] = 4, @@ -894,8 +894,8 @@ const struct sja1105_info sja1110c_info = { .rxtstamp = sja1110_rxtstamp, .txtstamp = sja1110_txtstamp, .disable_microcontroller = sja1110_disable_microcontroller, - .pcs_mdio_read = sja1110_pcs_mdio_read, - .pcs_mdio_write = sja1110_pcs_mdio_write, + .pcs_mdio_read_c45 = sja1110_pcs_mdio_read_c45, + .pcs_mdio_write_c45 = sja1110_pcs_mdio_write_c45, .port_speed = { [SJA1105_SPEED_AUTO] = 0, [SJA1105_SPEED_10MBPS] = 4, @@ -944,8 +944,8 @@ const struct sja1105_info sja1110d_info = { .rxtstamp = sja1110_rxtstamp, .txtstamp = sja1110_txtstamp, .disable_microcontroller = sja1110_disable_microcontroller, - .pcs_mdio_read = sja1110_pcs_mdio_read, - .pcs_mdio_write = sja1110_pcs_mdio_write, + .pcs_mdio_read_c45 = sja1110_pcs_mdio_read_c45, + .pcs_mdio_write_c45 = sja1110_pcs_mdio_write_c45, .port_speed = { [SJA1105_SPEED_AUTO] = 0, [SJA1105_SPEED_10MBPS] = 4, diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 0805f249fff2..25f55756681d 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -523,7 +523,6 @@ static int adin1110_register_mdiobus(struct adin1110_priv *priv, mii_bus->priv = priv; mii_bus->parent = dev; mii_bus->phy_mask = ~((u32)GENMASK(2, 0)); - mii_bus->probe_capabilities = MDIOBUS_C22; snprintf(mii_bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); ret = devm_mdiobus_register(dev, mii_bus); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 466273b22f0a..3fd9728f817f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -1699,20 +1699,21 @@ do { \ } while (0) /* Macros for building, reading or writing register values or bits - * using MDIO. Different from above because of the use of standardized - * Linux include values. No shifting is performed with the bit - * operations, everything works on mask values. + * using MDIO. */ + +#define XGBE_ADDR_C45 BIT(30) + #define XMDIO_READ(_pdata, _mmd, _reg) \ ((_pdata)->hw_if.read_mmd_regs((_pdata), 0, \ - MII_ADDR_C45 | (_mmd << 16) | ((_reg) & 0xffff))) + XGBE_ADDR_C45 | (_mmd << 16) | ((_reg) & 0xffff))) #define XMDIO_READ_BITS(_pdata, _mmd, _reg, _mask) \ (XMDIO_READ((_pdata), _mmd, _reg) & _mask) #define XMDIO_WRITE(_pdata, _mmd, _reg, _val) \ ((_pdata)->hw_if.write_mmd_regs((_pdata), 0, \ - MII_ADDR_C45 | (_mmd << 16) | ((_reg) & 0xffff), (_val))) + XGBE_ADDR_C45 | (_mmd << 16) | ((_reg) & 0xffff), (_val))) #define XMDIO_WRITE_BITS(_pdata, _mmd, _reg, _mask, _val) \ do { \ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 4030d619e84f..f393228d41c7 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -814,6 +814,9 @@ static int xgbe_set_speed(struct xgbe_prv_data *pdata, int speed) unsigned int ss; switch (speed) { + case SPEED_10: + ss = 0x07; + break; case SPEED_1000: ss = 0x03; break; @@ -1154,8 +1157,8 @@ static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad, unsigned int mmd_address, index, offset; int mmd_data; - if (mmd_reg & MII_ADDR_C45) - mmd_address = mmd_reg & ~MII_ADDR_C45; + if (mmd_reg & XGBE_ADDR_C45) + mmd_address = mmd_reg & ~XGBE_ADDR_C45; else mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff); @@ -1186,8 +1189,8 @@ static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad, unsigned long flags; unsigned int mmd_address, index, offset; - if (mmd_reg & MII_ADDR_C45) - mmd_address = mmd_reg & ~MII_ADDR_C45; + if (mmd_reg & XGBE_ADDR_C45) + mmd_address = mmd_reg & ~XGBE_ADDR_C45; else mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff); @@ -1217,8 +1220,8 @@ static int xgbe_read_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad, unsigned int mmd_address; int mmd_data; - if (mmd_reg & MII_ADDR_C45) - mmd_address = mmd_reg & ~MII_ADDR_C45; + if (mmd_reg & XGBE_ADDR_C45) + mmd_address = mmd_reg & ~XGBE_ADDR_C45; else mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff); @@ -1245,8 +1248,8 @@ static void xgbe_write_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad, unsigned int mmd_address; unsigned long flags; - if (mmd_reg & MII_ADDR_C45) - mmd_address = mmd_reg & ~MII_ADDR_C45; + if (mmd_reg & XGBE_ADDR_C45) + mmd_address = mmd_reg & ~XGBE_ADDR_C45; else mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff); @@ -1291,11 +1294,20 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad, } } -static unsigned int xgbe_create_mdio_sca(int port, int reg) +static unsigned int xgbe_create_mdio_sca_c22(int port, int reg) { - unsigned int mdio_sca, da; + unsigned int mdio_sca; + + mdio_sca = 0; + XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, RA, reg); + XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, PA, port); - da = (reg & MII_ADDR_C45) ? reg >> 16 : 0; + return mdio_sca; +} + +static unsigned int xgbe_create_mdio_sca_c45(int port, unsigned int da, int reg) +{ + unsigned int mdio_sca; mdio_sca = 0; XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, RA, reg); @@ -1305,14 +1317,13 @@ static unsigned int xgbe_create_mdio_sca(int port, int reg) return mdio_sca; } -static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr, - int reg, u16 val) +static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, + unsigned int mdio_sca, u16 val) { - unsigned int mdio_sca, mdio_sccd; + unsigned int mdio_sccd; reinit_completion(&pdata->mdio_complete); - mdio_sca = xgbe_create_mdio_sca(addr, reg); XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca); mdio_sccd = 0; @@ -1329,14 +1340,33 @@ static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr, return 0; } -static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr, - int reg) +static int xgbe_write_ext_mii_regs_c22(struct xgbe_prv_data *pdata, int addr, + int reg, u16 val) { - unsigned int mdio_sca, mdio_sccd; + unsigned int mdio_sca; + + mdio_sca = xgbe_create_mdio_sca_c22(addr, reg); + + return xgbe_write_ext_mii_regs(pdata, mdio_sca, val); +} + +static int xgbe_write_ext_mii_regs_c45(struct xgbe_prv_data *pdata, int addr, + int devad, int reg, u16 val) +{ + unsigned int mdio_sca; + + mdio_sca = xgbe_create_mdio_sca_c45(addr, devad, reg); + + return xgbe_write_ext_mii_regs(pdata, mdio_sca, val); +} + +static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, + unsigned int mdio_sca) +{ + unsigned int mdio_sccd; reinit_completion(&pdata->mdio_complete); - mdio_sca = xgbe_create_mdio_sca(addr, reg); XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca); mdio_sccd = 0; @@ -1352,6 +1382,26 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr, return XGMAC_IOREAD_BITS(pdata, MAC_MDIOSCCDR, DATA); } +static int xgbe_read_ext_mii_regs_c22(struct xgbe_prv_data *pdata, int addr, + int reg) +{ + unsigned int mdio_sca; + + mdio_sca = xgbe_create_mdio_sca_c22(addr, reg); + + return xgbe_read_ext_mii_regs(pdata, mdio_sca); +} + +static int xgbe_read_ext_mii_regs_c45(struct xgbe_prv_data *pdata, int addr, + int devad, int reg) +{ + unsigned int mdio_sca; + + mdio_sca = xgbe_create_mdio_sca_c45(addr, devad, reg); + + return xgbe_read_ext_mii_regs(pdata, mdio_sca); +} + static int xgbe_set_ext_mii_mode(struct xgbe_prv_data *pdata, unsigned int port, enum xgbe_mdio_mode mode) { @@ -3565,8 +3615,10 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if) hw_if->set_speed = xgbe_set_speed; hw_if->set_ext_mii_mode = xgbe_set_ext_mii_mode; - hw_if->read_ext_mii_regs = xgbe_read_ext_mii_regs; - hw_if->write_ext_mii_regs = xgbe_write_ext_mii_regs; + hw_if->read_ext_mii_regs_c22 = xgbe_read_ext_mii_regs_c22; + hw_if->write_ext_mii_regs_c22 = xgbe_write_ext_mii_regs_c22; + hw_if->read_ext_mii_regs_c45 = xgbe_read_ext_mii_regs_c45; + hw_if->write_ext_mii_regs_c45 = xgbe_write_ext_mii_regs_c45; hw_if->set_gpio = xgbe_set_gpio; hw_if->clr_gpio = xgbe_clr_gpio; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 43fdd111235a..33a9574e9e04 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -274,6 +274,15 @@ static void xgbe_sgmii_1000_mode(struct xgbe_prv_data *pdata) pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_SGMII_1000); } +static void xgbe_sgmii_10_mode(struct xgbe_prv_data *pdata) +{ + /* Set MAC to 10M speed */ + pdata->hw_if.set_speed(pdata, SPEED_10); + + /* Call PHY implementation support to complete rate change */ + pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_SGMII_10); +} + static void xgbe_sgmii_100_mode(struct xgbe_prv_data *pdata) { /* Set MAC to 1G speed */ @@ -306,6 +315,9 @@ static void xgbe_change_mode(struct xgbe_prv_data *pdata, case XGBE_MODE_KR: xgbe_kr_mode(pdata); break; + case XGBE_MODE_SGMII_10: + xgbe_sgmii_10_mode(pdata); + break; case XGBE_MODE_SGMII_100: xgbe_sgmii_100_mode(pdata); break; @@ -1077,6 +1089,8 @@ static const char *xgbe_phy_fc_string(struct xgbe_prv_data *pdata) static const char *xgbe_phy_speed_string(int speed) { switch (speed) { + case SPEED_10: + return "10Mbps"; case SPEED_100: return "100Mbps"; case SPEED_1000: @@ -1164,6 +1178,7 @@ static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata) case XGBE_MODE_KX_1000: case XGBE_MODE_KX_2500: case XGBE_MODE_KR: + case XGBE_MODE_SGMII_10: case XGBE_MODE_SGMII_100: case XGBE_MODE_SGMII_1000: case XGBE_MODE_X: @@ -1225,6 +1240,8 @@ static int __xgbe_phy_config_aneg(struct xgbe_prv_data *pdata, bool set_mode) xgbe_set_mode(pdata, XGBE_MODE_SGMII_1000); } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_100)) { xgbe_set_mode(pdata, XGBE_MODE_SGMII_100); + } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_10)) { + xgbe_set_mode(pdata, XGBE_MODE_SGMII_10); } else { enable_irq(pdata->an_irq); ret = -EINVAL; @@ -1325,6 +1342,9 @@ static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) mode = xgbe_phy_status_aneg(pdata); switch (mode) { + case XGBE_MODE_SGMII_10: + pdata->phy.speed = SPEED_10; + break; case XGBE_MODE_SGMII_100: pdata->phy.speed = SPEED_100; break; @@ -1467,6 +1487,8 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) xgbe_sgmii_1000_mode(pdata); } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_100)) { xgbe_sgmii_100_mode(pdata); + } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_10)) { + xgbe_sgmii_10_mode(pdata); } else { ret = -EINVAL; goto err_irq; @@ -1564,6 +1586,8 @@ static int xgbe_phy_best_advertised_speed(struct xgbe_prv_data *pdata) return SPEED_1000; else if (XGBE_ADV(lks, 100baseT_Full)) return SPEED_100; + else if (XGBE_ADV(lks, 10baseT_Full)) + return SPEED_10; return SPEED_UNKNOWN; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index c731a04731f8..f4683d53e58c 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -124,6 +124,7 @@ #include "xgbe.h" #include "xgbe-common.h" +#define XGBE_PHY_PORT_SPEED_10 BIT(0) #define XGBE_PHY_PORT_SPEED_100 BIT(1) #define XGBE_PHY_PORT_SPEED_1000 BIT(2) #define XGBE_PHY_PORT_SPEED_2500 BIT(3) @@ -599,20 +600,27 @@ static int xgbe_phy_get_comm_ownership(struct xgbe_prv_data *pdata) return -ETIMEDOUT; } -static int xgbe_phy_mdio_mii_write(struct xgbe_prv_data *pdata, int addr, - int reg, u16 val) +static int xgbe_phy_mdio_mii_write_c22(struct xgbe_prv_data *pdata, int addr, + int reg, u16 val) { struct xgbe_phy_data *phy_data = pdata->phy_data; - if (reg & MII_ADDR_C45) { - if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL45) - return -ENOTSUPP; - } else { - if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL22) - return -ENOTSUPP; - } + if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL22) + return -EOPNOTSUPP; - return pdata->hw_if.write_ext_mii_regs(pdata, addr, reg, val); + return pdata->hw_if.write_ext_mii_regs_c22(pdata, addr, reg, val); +} + +static int xgbe_phy_mdio_mii_write_c45(struct xgbe_prv_data *pdata, int addr, + int devad, int reg, u16 val) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL45) + return -EOPNOTSUPP; + + return pdata->hw_if.write_ext_mii_regs_c45(pdata, addr, devad, + reg, val); } static int xgbe_phy_i2c_mii_write(struct xgbe_prv_data *pdata, int reg, u16 val) @@ -637,7 +645,8 @@ static int xgbe_phy_i2c_mii_write(struct xgbe_prv_data *pdata, int reg, u16 val) return ret; } -static int xgbe_phy_mii_write(struct mii_bus *mii, int addr, int reg, u16 val) +static int xgbe_phy_mii_write_c22(struct mii_bus *mii, int addr, int reg, + u16 val) { struct xgbe_prv_data *pdata = mii->priv; struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -650,29 +659,58 @@ static int xgbe_phy_mii_write(struct mii_bus *mii, int addr, int reg, u16 val) if (phy_data->conn_type == XGBE_CONN_TYPE_SFP) ret = xgbe_phy_i2c_mii_write(pdata, reg, val); else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO) - ret = xgbe_phy_mdio_mii_write(pdata, addr, reg, val); + ret = xgbe_phy_mdio_mii_write_c22(pdata, addr, reg, val); else - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; xgbe_phy_put_comm_ownership(pdata); return ret; } -static int xgbe_phy_mdio_mii_read(struct xgbe_prv_data *pdata, int addr, - int reg) +static int xgbe_phy_mii_write_c45(struct mii_bus *mii, int addr, int devad, + int reg, u16 val) { + struct xgbe_prv_data *pdata = mii->priv; struct xgbe_phy_data *phy_data = pdata->phy_data; + int ret; - if (reg & MII_ADDR_C45) { - if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL45) - return -ENOTSUPP; - } else { - if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL22) - return -ENOTSUPP; - } + ret = xgbe_phy_get_comm_ownership(pdata); + if (ret) + return ret; - return pdata->hw_if.read_ext_mii_regs(pdata, addr, reg); + if (phy_data->conn_type == XGBE_CONN_TYPE_SFP) + ret = -EOPNOTSUPP; + else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO) + ret = xgbe_phy_mdio_mii_write_c45(pdata, addr, devad, reg, val); + else + ret = -EOPNOTSUPP; + + xgbe_phy_put_comm_ownership(pdata); + + return ret; +} + +static int xgbe_phy_mdio_mii_read_c22(struct xgbe_prv_data *pdata, int addr, + int reg) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL22) + return -EOPNOTSUPP; + + return pdata->hw_if.read_ext_mii_regs_c22(pdata, addr, reg); +} + +static int xgbe_phy_mdio_mii_read_c45(struct xgbe_prv_data *pdata, int addr, + int devad, int reg) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL45) + return -EOPNOTSUPP; + + return pdata->hw_if.read_ext_mii_regs_c45(pdata, addr, devad, reg); } static int xgbe_phy_i2c_mii_read(struct xgbe_prv_data *pdata, int reg) @@ -697,7 +735,7 @@ static int xgbe_phy_i2c_mii_read(struct xgbe_prv_data *pdata, int reg) return ret; } -static int xgbe_phy_mii_read(struct mii_bus *mii, int addr, int reg) +static int xgbe_phy_mii_read_c22(struct mii_bus *mii, int addr, int reg) { struct xgbe_prv_data *pdata = mii->priv; struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -710,7 +748,30 @@ static int xgbe_phy_mii_read(struct mii_bus *mii, int addr, int reg) if (phy_data->conn_type == XGBE_CONN_TYPE_SFP) ret = xgbe_phy_i2c_mii_read(pdata, reg); else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO) - ret = xgbe_phy_mdio_mii_read(pdata, addr, reg); + ret = xgbe_phy_mdio_mii_read_c22(pdata, addr, reg); + else + ret = -EOPNOTSUPP; + + xgbe_phy_put_comm_ownership(pdata); + + return ret; +} + +static int xgbe_phy_mii_read_c45(struct mii_bus *mii, int addr, int devad, + int reg) +{ + struct xgbe_prv_data *pdata = mii->priv; + struct xgbe_phy_data *phy_data = pdata->phy_data; + int ret; + + ret = xgbe_phy_get_comm_ownership(pdata); + if (ret) + return ret; + + if (phy_data->conn_type == XGBE_CONN_TYPE_SFP) + ret = -EOPNOTSUPP; + else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO) + ret = xgbe_phy_mdio_mii_read_c45(pdata, addr, devad, reg); else ret = -ENOTSUPP; @@ -759,6 +820,8 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) XGBE_SET_SUP(lks, Pause); XGBE_SET_SUP(lks, Asym_Pause); if (phy_data->sfp_base == XGBE_SFP_BASE_1000_T) { + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) + XGBE_SET_SUP(lks, 10baseT_Full); if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) XGBE_SET_SUP(lks, 100baseT_Full); if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) @@ -1542,6 +1605,16 @@ static enum xgbe_mode xgbe_phy_an37_sgmii_outcome(struct xgbe_prv_data *pdata) xgbe_phy_phydev_flowctrl(pdata); switch (pdata->an_status & XGBE_SGMII_AN_LINK_SPEED) { + case XGBE_SGMII_AN_LINK_SPEED_10: + if (pdata->an_status & XGBE_SGMII_AN_LINK_DUPLEX) { + XGBE_SET_LP_ADV(lks, 10baseT_Full); + mode = XGBE_MODE_SGMII_10; + } else { + /* Half-duplex not supported */ + XGBE_SET_LP_ADV(lks, 10baseT_Half); + mode = XGBE_MODE_UNKNOWN; + } + break; case XGBE_SGMII_AN_LINK_SPEED_100: if (pdata->an_status & XGBE_SGMII_AN_LINK_DUPLEX) { XGBE_SET_LP_ADV(lks, 100baseT_Full); @@ -1658,7 +1731,10 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) switch (phy_data->sfp_base) { case XGBE_SFP_BASE_1000_T: if (phy_data->phydev && - (phy_data->phydev->speed == SPEED_100)) + (phy_data->phydev->speed == SPEED_10)) + mode = XGBE_MODE_SGMII_10; + else if (phy_data->phydev && + (phy_data->phydev->speed == SPEED_100)) mode = XGBE_MODE_SGMII_100; else mode = XGBE_MODE_SGMII_1000; @@ -1673,7 +1749,10 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) break; default: if (phy_data->phydev && - (phy_data->phydev->speed == SPEED_100)) + (phy_data->phydev->speed == SPEED_10)) + mode = XGBE_MODE_SGMII_10; + else if (phy_data->phydev && + (phy_data->phydev->speed == SPEED_100)) mode = XGBE_MODE_SGMII_100; else mode = XGBE_MODE_SGMII_1000; @@ -1910,8 +1989,8 @@ static int xgbe_phy_set_redrv_mode_mdio(struct xgbe_prv_data *pdata, redrv_reg = XGBE_PHY_REDRV_MODE_REG + (phy_data->redrv_lane * 0x1000); redrv_val = (u16)mode; - return pdata->hw_if.write_ext_mii_regs(pdata, phy_data->redrv_addr, - redrv_reg, redrv_val); + return pdata->hw_if.write_ext_mii_regs_c22(pdata, phy_data->redrv_addr, + redrv_reg, redrv_val); } static int xgbe_phy_set_redrv_mode_i2c(struct xgbe_prv_data *pdata, @@ -2127,6 +2206,20 @@ static void xgbe_phy_sgmii_100_mode(struct xgbe_prv_data *pdata) netif_dbg(pdata, link, pdata->netdev, "100MbE SGMII mode set\n"); } +static void xgbe_phy_sgmii_10_mode(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + xgbe_phy_set_redrv_mode(pdata); + + /* 10M/SGMII */ + xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_1G, XGBE_MB_SUBCMD_10MBITS); + + phy_data->cur_mode = XGBE_MODE_SGMII_10; + + netif_dbg(pdata, link, pdata->netdev, "10MbE SGMII mode set\n"); +} + static void xgbe_phy_kr_mode(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -2185,6 +2278,7 @@ static enum xgbe_mode xgbe_phy_switch_baset_mode(struct xgbe_prv_data *pdata) return xgbe_phy_cur_mode(pdata); switch (xgbe_phy_cur_mode(pdata)) { + case XGBE_MODE_SGMII_10: case XGBE_MODE_SGMII_100: case XGBE_MODE_SGMII_1000: return XGBE_MODE_KR; @@ -2252,6 +2346,8 @@ static enum xgbe_mode xgbe_phy_get_baset_mode(struct xgbe_phy_data *phy_data, int speed) { switch (speed) { + case SPEED_10: + return XGBE_MODE_SGMII_10; case SPEED_100: return XGBE_MODE_SGMII_100; case SPEED_1000: @@ -2269,6 +2365,8 @@ static enum xgbe_mode xgbe_phy_get_sfp_mode(struct xgbe_phy_data *phy_data, int speed) { switch (speed) { + case SPEED_10: + return XGBE_MODE_SGMII_10; case SPEED_100: return XGBE_MODE_SGMII_100; case SPEED_1000: @@ -2343,6 +2441,9 @@ static void xgbe_phy_set_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) case XGBE_MODE_KR: xgbe_phy_kr_mode(pdata); break; + case XGBE_MODE_SGMII_10: + xgbe_phy_sgmii_10_mode(pdata); + break; case XGBE_MODE_SGMII_100: xgbe_phy_sgmii_100_mode(pdata); break; @@ -2399,6 +2500,9 @@ static bool xgbe_phy_use_baset_mode(struct xgbe_prv_data *pdata, struct ethtool_link_ksettings *lks = &pdata->phy.lks; switch (mode) { + case XGBE_MODE_SGMII_10: + return xgbe_phy_check_mode(pdata, mode, + XGBE_ADV(lks, 10baseT_Full)); case XGBE_MODE_SGMII_100: return xgbe_phy_check_mode(pdata, mode, XGBE_ADV(lks, 100baseT_Full)); @@ -2428,6 +2532,11 @@ static bool xgbe_phy_use_sfp_mode(struct xgbe_prv_data *pdata, return false; return xgbe_phy_check_mode(pdata, mode, XGBE_ADV(lks, 1000baseX_Full)); + case XGBE_MODE_SGMII_10: + if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T) + return false; + return xgbe_phy_check_mode(pdata, mode, + XGBE_ADV(lks, 10baseT_Full)); case XGBE_MODE_SGMII_100: if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T) return false; @@ -2520,10 +2629,17 @@ static bool xgbe_phy_valid_speed_basex_mode(struct xgbe_phy_data *phy_data, } } -static bool xgbe_phy_valid_speed_baset_mode(struct xgbe_phy_data *phy_data, +static bool xgbe_phy_valid_speed_baset_mode(struct xgbe_prv_data *pdata, int speed) { + struct xgbe_phy_data *phy_data = pdata->phy_data; + unsigned int ver; + switch (speed) { + case SPEED_10: + /* Supported in ver >= 30H */ + ver = XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER); + return (ver >= 0x30) ? true : false; case SPEED_100: case SPEED_1000: return true; @@ -2536,10 +2652,17 @@ static bool xgbe_phy_valid_speed_baset_mode(struct xgbe_phy_data *phy_data, } } -static bool xgbe_phy_valid_speed_sfp_mode(struct xgbe_phy_data *phy_data, +static bool xgbe_phy_valid_speed_sfp_mode(struct xgbe_prv_data *pdata, int speed) { + struct xgbe_phy_data *phy_data = pdata->phy_data; + unsigned int ver; + switch (speed) { + case SPEED_10: + /* Supported in ver >= 30H */ + ver = XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER); + return (ver >= 0x30) && (phy_data->sfp_speed == XGBE_SFP_SPEED_100_1000); case SPEED_100: return (phy_data->sfp_speed == XGBE_SFP_SPEED_100_1000); case SPEED_1000: @@ -2586,12 +2709,12 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed) case XGBE_PORT_MODE_1000BASE_T: case XGBE_PORT_MODE_NBASE_T: case XGBE_PORT_MODE_10GBASE_T: - return xgbe_phy_valid_speed_baset_mode(phy_data, speed); + return xgbe_phy_valid_speed_baset_mode(pdata, speed); case XGBE_PORT_MODE_1000BASE_X: case XGBE_PORT_MODE_10GBASE_R: return xgbe_phy_valid_speed_basex_mode(phy_data, speed); case XGBE_PORT_MODE_SFP: - return xgbe_phy_valid_speed_sfp_mode(phy_data, speed); + return xgbe_phy_valid_speed_sfp_mode(pdata, speed); default: return false; } @@ -2862,6 +2985,12 @@ static int xgbe_phy_mdio_reset_setup(struct xgbe_prv_data *pdata) static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; + unsigned int ver; + + /* 10 Mbps speed is not supported in ver < 30H */ + ver = XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER); + if (ver < 0x30 && (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10)) + return true; switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: @@ -2875,7 +3004,8 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) return false; break; case XGBE_PORT_MODE_1000BASE_T: - if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || + if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) || + (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000)) return false; break; @@ -2884,13 +3014,15 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) return false; break; case XGBE_PORT_MODE_NBASE_T: - if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || + if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) || + (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500)) return false; break; case XGBE_PORT_MODE_10GBASE_T: - if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || + if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) || + (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)) return false; @@ -2900,7 +3032,8 @@ static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata) return false; break; case XGBE_PORT_MODE_SFP: - if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || + if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) || + (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) || (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)) return false; @@ -3269,6 +3402,10 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) XGBE_SET_SUP(lks, Pause); XGBE_SET_SUP(lks, Asym_Pause); XGBE_SET_SUP(lks, TP); + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) { + XGBE_SET_SUP(lks, 10baseT_Full); + phy_data->start_mode = XGBE_MODE_SGMII_10; + } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { XGBE_SET_SUP(lks, 100baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_100; @@ -3299,6 +3436,10 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) XGBE_SET_SUP(lks, Pause); XGBE_SET_SUP(lks, Asym_Pause); XGBE_SET_SUP(lks, TP); + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) { + XGBE_SET_SUP(lks, 10baseT_Full); + phy_data->start_mode = XGBE_MODE_SGMII_10; + } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { XGBE_SET_SUP(lks, 100baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_100; @@ -3321,6 +3462,10 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) XGBE_SET_SUP(lks, Pause); XGBE_SET_SUP(lks, Asym_Pause); XGBE_SET_SUP(lks, TP); + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) { + XGBE_SET_SUP(lks, 10baseT_Full); + phy_data->start_mode = XGBE_MODE_SGMII_10; + } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { XGBE_SET_SUP(lks, 100baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_100; @@ -3361,6 +3506,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) XGBE_SET_SUP(lks, Asym_Pause); XGBE_SET_SUP(lks, TP); XGBE_SET_SUP(lks, FIBRE); + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10) + phy_data->start_mode = XGBE_MODE_SGMII_10; if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) phy_data->start_mode = XGBE_MODE_SGMII_100; if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) @@ -3415,8 +3562,10 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) mii->priv = pdata; mii->name = "amd-xgbe-mii"; - mii->read = xgbe_phy_mii_read; - mii->write = xgbe_phy_mii_write; + mii->read = xgbe_phy_mii_read_c22; + mii->write = xgbe_phy_mii_write_c22; + mii->read_c45 = xgbe_phy_mii_read_c45; + mii->write_c45 = xgbe_phy_mii_write_c45; mii->parent = pdata->dev; mii->phy_mask = ~0; snprintf(mii->id, sizeof(mii->id), "%s", dev_name(pdata->dev)); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 7a41367c437d..16e73df3e9b9 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -294,6 +294,7 @@ #define XGBE_SGMII_AN_LINK_STATUS BIT(1) #define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3)) +#define XGBE_SGMII_AN_LINK_SPEED_10 0x00 #define XGBE_SGMII_AN_LINK_SPEED_100 0x04 #define XGBE_SGMII_AN_LINK_SPEED_1000 0x08 #define XGBE_SGMII_AN_LINK_DUPLEX BIT(4) @@ -595,6 +596,7 @@ enum xgbe_mode { XGBE_MODE_KX_2500, XGBE_MODE_KR, XGBE_MODE_X, + XGBE_MODE_SGMII_10, XGBE_MODE_SGMII_100, XGBE_MODE_SGMII_1000, XGBE_MODE_SFI, @@ -774,8 +776,11 @@ struct xgbe_hw_if { int (*set_ext_mii_mode)(struct xgbe_prv_data *, unsigned int, enum xgbe_mdio_mode); - int (*read_ext_mii_regs)(struct xgbe_prv_data *, int, int); - int (*write_ext_mii_regs)(struct xgbe_prv_data *, int, int, u16); + int (*read_ext_mii_regs_c22)(struct xgbe_prv_data *, int, int); + int (*write_ext_mii_regs_c22)(struct xgbe_prv_data *, int, int, u16); + int (*read_ext_mii_regs_c45)(struct xgbe_prv_data *, int, int, int); + int (*write_ext_mii_regs_c45)(struct xgbe_prv_data *, int, int, int, + u16); int (*set_gpio)(struct xgbe_prv_data *, unsigned int); int (*clr_gpio)(struct xgbe_prv_data *, unsigned int); diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index d30d11872719..306393f8eeca 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1905,7 +1905,6 @@ static void alx_remove(struct pci_dev *pdev) free_netdev(alx->dev); } -#ifdef CONFIG_PM_SLEEP static int alx_suspend(struct device *dev) { struct alx_priv *alx = dev_get_drvdata(dev); @@ -1951,12 +1950,7 @@ unlock: return err; } -static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); -#define ALX_PM_OPS (&alx_pm_ops) -#else -#define ALX_PM_OPS NULL -#endif - +static DEFINE_SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); static pci_ers_result_t alx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state) @@ -2055,7 +2049,7 @@ static struct pci_driver alx_driver = { .probe = alx_probe, .remove = alx_remove, .err_handler = &alx_err_handlers, - .driver.pm = ALX_PM_OPS, + .driver.pm = pm_sleep_ptr(&alx_pm_ops), }; module_pci_driver(alx_driver); diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 9c410f93a103..14dfec4db8f9 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -768,8 +768,6 @@ #define gem_readl_n(port, reg, idx) (port)->macb_reg_readl((port), GEM_##reg + idx * 4) #define gem_writel_n(port, reg, idx, value) (port)->macb_reg_writel((port), GEM_##reg + idx * 4, (value)) -#define PTP_TS_BUFFER_SIZE 128 /* must be power of 2 */ - /* Conditional GEM/MACB macros. These perform the operation to the correct * register dependent on whether the device is a GEM or a MACB. For registers * and bitfields that are common across both devices, use macb_{read,write}l @@ -819,11 +817,6 @@ struct macb_dma_desc_ptp { u32 ts_1; u32 ts_2; }; - -struct gem_tx_ts { - struct sk_buff *skb; - struct macb_dma_desc_ptp desc_ptp; -}; #endif /* DMA descriptor bitfields */ @@ -1224,12 +1217,6 @@ struct macb_queue { void *rx_buffers; struct napi_struct napi_rx; struct queue_stats stats; - -#ifdef CONFIG_MACB_USE_HWSTAMP - struct work_struct tx_ts_task; - unsigned int tx_ts_head, tx_ts_tail; - struct gem_tx_ts tx_timestamps[PTP_TS_BUFFER_SIZE]; -#endif }; struct ethtool_rx_fs_item { @@ -1340,14 +1327,14 @@ enum macb_bd_control { void gem_ptp_init(struct net_device *ndev); void gem_ptp_remove(struct net_device *ndev); -int gem_ptp_txstamp(struct macb_queue *queue, struct sk_buff *skb, struct macb_dma_desc *des); +void gem_ptp_txstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc); void gem_ptp_rxstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc); -static inline int gem_ptp_do_txstamp(struct macb_queue *queue, struct sk_buff *skb, struct macb_dma_desc *desc) +static inline void gem_ptp_do_txstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) { - if (queue->bp->tstamp_config.tx_type == TSTAMP_DISABLED) - return -ENOTSUPP; + if (bp->tstamp_config.tx_type == TSTAMP_DISABLED) + return; - return gem_ptp_txstamp(queue, skb, desc); + gem_ptp_txstamp(bp, skb, desc); } static inline void gem_ptp_do_rxstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) @@ -1363,11 +1350,7 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd); static inline void gem_ptp_init(struct net_device *ndev) { } static inline void gem_ptp_remove(struct net_device *ndev) { } -static inline int gem_ptp_do_txstamp(struct macb_queue *queue, struct sk_buff *skb, struct macb_dma_desc *desc) -{ - return -1; -} - +static inline void gem_ptp_do_txstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) { } static inline void gem_ptp_do_rxstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) { } #endif diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 72e42820713d..41964fd02452 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -334,7 +334,7 @@ static int macb_mdio_wait_for_idle(struct macb *bp) 1, MACB_MDIO_TIMEOUT); } -static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum) +static int macb_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum) { struct macb *bp = bus->priv; int status; @@ -347,35 +347,62 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum) if (status < 0) goto mdio_read_exit; - if (regnum & MII_ADDR_C45) { - macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) - | MACB_BF(RW, MACB_MAN_C45_ADDR) - | MACB_BF(PHYA, mii_id) - | MACB_BF(REGA, (regnum >> 16) & 0x1F) - | MACB_BF(DATA, regnum & 0xFFFF) - | MACB_BF(CODE, MACB_MAN_C45_CODE))); - - status = macb_mdio_wait_for_idle(bp); - if (status < 0) - goto mdio_read_exit; - - macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) - | MACB_BF(RW, MACB_MAN_C45_READ) - | MACB_BF(PHYA, mii_id) - | MACB_BF(REGA, (regnum >> 16) & 0x1F) - | MACB_BF(CODE, MACB_MAN_C45_CODE))); - } else { - macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF) - | MACB_BF(RW, MACB_MAN_C22_READ) - | MACB_BF(PHYA, mii_id) - | MACB_BF(REGA, regnum) - | MACB_BF(CODE, MACB_MAN_C22_CODE))); + macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF) + | MACB_BF(RW, MACB_MAN_C22_READ) + | MACB_BF(PHYA, mii_id) + | MACB_BF(REGA, regnum) + | MACB_BF(CODE, MACB_MAN_C22_CODE))); + + status = macb_mdio_wait_for_idle(bp); + if (status < 0) + goto mdio_read_exit; + + status = MACB_BFEXT(DATA, macb_readl(bp, MAN)); + +mdio_read_exit: + pm_runtime_mark_last_busy(&bp->pdev->dev); + pm_runtime_put_autosuspend(&bp->pdev->dev); +mdio_pm_exit: + return status; +} + +static int macb_mdio_read_c45(struct mii_bus *bus, int mii_id, int devad, + int regnum) +{ + struct macb *bp = bus->priv; + int status; + + status = pm_runtime_get_sync(&bp->pdev->dev); + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); + goto mdio_pm_exit; } status = macb_mdio_wait_for_idle(bp); if (status < 0) goto mdio_read_exit; + macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) + | MACB_BF(RW, MACB_MAN_C45_ADDR) + | MACB_BF(PHYA, mii_id) + | MACB_BF(REGA, devad & 0x1F) + | MACB_BF(DATA, regnum & 0xFFFF) + | MACB_BF(CODE, MACB_MAN_C45_CODE))); + + status = macb_mdio_wait_for_idle(bp); + if (status < 0) + goto mdio_read_exit; + + macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) + | MACB_BF(RW, MACB_MAN_C45_READ) + | MACB_BF(PHYA, mii_id) + | MACB_BF(REGA, devad & 0x1F) + | MACB_BF(CODE, MACB_MAN_C45_CODE))); + + status = macb_mdio_wait_for_idle(bp); + if (status < 0) + goto mdio_read_exit; + status = MACB_BFEXT(DATA, macb_readl(bp, MAN)); mdio_read_exit: @@ -385,8 +412,8 @@ mdio_pm_exit: return status; } -static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum, - u16 value) +static int macb_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum, + u16 value) { struct macb *bp = bus->priv; int status; @@ -399,37 +426,63 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum, if (status < 0) goto mdio_write_exit; - if (regnum & MII_ADDR_C45) { - macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) - | MACB_BF(RW, MACB_MAN_C45_ADDR) - | MACB_BF(PHYA, mii_id) - | MACB_BF(REGA, (regnum >> 16) & 0x1F) - | MACB_BF(DATA, regnum & 0xFFFF) - | MACB_BF(CODE, MACB_MAN_C45_CODE))); - - status = macb_mdio_wait_for_idle(bp); - if (status < 0) - goto mdio_write_exit; - - macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) - | MACB_BF(RW, MACB_MAN_C45_WRITE) - | MACB_BF(PHYA, mii_id) - | MACB_BF(REGA, (regnum >> 16) & 0x1F) - | MACB_BF(CODE, MACB_MAN_C45_CODE) - | MACB_BF(DATA, value))); - } else { - macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF) - | MACB_BF(RW, MACB_MAN_C22_WRITE) - | MACB_BF(PHYA, mii_id) - | MACB_BF(REGA, regnum) - | MACB_BF(CODE, MACB_MAN_C22_CODE) - | MACB_BF(DATA, value))); + macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C22_SOF) + | MACB_BF(RW, MACB_MAN_C22_WRITE) + | MACB_BF(PHYA, mii_id) + | MACB_BF(REGA, regnum) + | MACB_BF(CODE, MACB_MAN_C22_CODE) + | MACB_BF(DATA, value))); + + status = macb_mdio_wait_for_idle(bp); + if (status < 0) + goto mdio_write_exit; + +mdio_write_exit: + pm_runtime_mark_last_busy(&bp->pdev->dev); + pm_runtime_put_autosuspend(&bp->pdev->dev); +mdio_pm_exit: + return status; +} + +static int macb_mdio_write_c45(struct mii_bus *bus, int mii_id, + int devad, int regnum, + u16 value) +{ + struct macb *bp = bus->priv; + int status; + + status = pm_runtime_get_sync(&bp->pdev->dev); + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); + goto mdio_pm_exit; } status = macb_mdio_wait_for_idle(bp); if (status < 0) goto mdio_write_exit; + macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) + | MACB_BF(RW, MACB_MAN_C45_ADDR) + | MACB_BF(PHYA, mii_id) + | MACB_BF(REGA, devad & 0x1F) + | MACB_BF(DATA, regnum & 0xFFFF) + | MACB_BF(CODE, MACB_MAN_C45_CODE))); + + status = macb_mdio_wait_for_idle(bp); + if (status < 0) + goto mdio_write_exit; + + macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_C45_SOF) + | MACB_BF(RW, MACB_MAN_C45_WRITE) + | MACB_BF(PHYA, mii_id) + | MACB_BF(REGA, devad & 0x1F) + | MACB_BF(CODE, MACB_MAN_C45_CODE) + | MACB_BF(DATA, value))); + + status = macb_mdio_wait_for_idle(bp); + if (status < 0) + goto mdio_write_exit; + mdio_write_exit: pm_runtime_mark_last_busy(&bp->pdev->dev); pm_runtime_put_autosuspend(&bp->pdev->dev); @@ -902,8 +955,10 @@ static int macb_mii_init(struct macb *bp) } bp->mii_bus->name = "MACB_mii_bus"; - bp->mii_bus->read = &macb_mdio_read; - bp->mii_bus->write = &macb_mdio_write; + bp->mii_bus->read = &macb_mdio_read_c22; + bp->mii_bus->write = &macb_mdio_write_c22; + bp->mii_bus->read_c45 = &macb_mdio_read_c45; + bp->mii_bus->write_c45 = &macb_mdio_write_c45; snprintf(bp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", bp->pdev->name, bp->pdev->id); bp->mii_bus->priv = bp; @@ -1191,13 +1246,9 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) /* First, update TX stats if needed */ if (skb) { if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - !ptp_one_step_sync(skb) && - gem_ptp_do_txstamp(queue, skb, desc) == 0) { - /* skb now belongs to timestamp buffer - * and will be removed later - */ - tx_skb->skb = NULL; - } + !ptp_one_step_sync(skb)) + gem_ptp_do_txstamp(bp, skb, desc); + netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n", macb_tx_ring_wrap(bp, tail), skb->data); @@ -2253,6 +2304,12 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } +#ifdef CONFIG_MACB_USE_HWSTAMP + if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + (bp->hw_dma_cap & HW_DMA_CAP_PTP)) + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; +#endif + is_lso = (skb_shinfo(skb)->gso_size != 0); if (is_lso) { diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index e6cb20aaa76a..f962a95068a0 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -292,79 +292,39 @@ void gem_ptp_rxstamp(struct macb *bp, struct sk_buff *skb, } } -static void gem_tstamp_tx(struct macb *bp, struct sk_buff *skb, - struct macb_dma_desc_ptp *desc_ptp) +void gem_ptp_txstamp(struct macb *bp, struct sk_buff *skb, + struct macb_dma_desc *desc) { struct skb_shared_hwtstamps shhwtstamps; - struct timespec64 ts; - - gem_hw_timestamp(bp, desc_ptp->ts_1, desc_ptp->ts_2, &ts); - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); - skb_tstamp_tx(skb, &shhwtstamps); -} - -int gem_ptp_txstamp(struct macb_queue *queue, struct sk_buff *skb, - struct macb_dma_desc *desc) -{ - unsigned long tail = READ_ONCE(queue->tx_ts_tail); - unsigned long head = queue->tx_ts_head; struct macb_dma_desc_ptp *desc_ptp; - struct gem_tx_ts *tx_timestamp; - - if (!GEM_BFEXT(DMA_TXVALID, desc->ctrl)) - return -EINVAL; + struct timespec64 ts; - if (CIRC_SPACE(head, tail, PTP_TS_BUFFER_SIZE) == 0) - return -ENOMEM; + if (!GEM_BFEXT(DMA_TXVALID, desc->ctrl)) { + dev_warn_ratelimited(&bp->pdev->dev, + "Timestamp not set in TX BD as expected\n"); + return; + } - desc_ptp = macb_ptp_desc(queue->bp, desc); + desc_ptp = macb_ptp_desc(bp, desc); /* Unlikely but check */ - if (!desc_ptp) - return -EINVAL; - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - tx_timestamp = &queue->tx_timestamps[head]; - tx_timestamp->skb = skb; + if (!desc_ptp) { + dev_warn_ratelimited(&bp->pdev->dev, + "Timestamp not supported in BD\n"); + return; + } + /* ensure ts_1/ts_2 is loaded after ctrl (TX_USED check) */ dma_rmb(); - tx_timestamp->desc_ptp.ts_1 = desc_ptp->ts_1; - tx_timestamp->desc_ptp.ts_2 = desc_ptp->ts_2; - /* move head */ - smp_store_release(&queue->tx_ts_head, - (head + 1) & (PTP_TS_BUFFER_SIZE - 1)); - - schedule_work(&queue->tx_ts_task); - return 0; -} + gem_hw_timestamp(bp, desc_ptp->ts_1, desc_ptp->ts_2, &ts); -static void gem_tx_timestamp_flush(struct work_struct *work) -{ - struct macb_queue *queue = - container_of(work, struct macb_queue, tx_ts_task); - unsigned long head, tail; - struct gem_tx_ts *tx_ts; - - /* take current head */ - head = smp_load_acquire(&queue->tx_ts_head); - tail = queue->tx_ts_tail; - - while (CIRC_CNT(head, tail, PTP_TS_BUFFER_SIZE)) { - tx_ts = &queue->tx_timestamps[tail]; - gem_tstamp_tx(queue->bp, tx_ts->skb, &tx_ts->desc_ptp); - /* cleanup */ - dev_kfree_skb_any(tx_ts->skb); - /* remove old tail */ - smp_store_release(&queue->tx_ts_tail, - (tail + 1) & (PTP_TS_BUFFER_SIZE - 1)); - tail = queue->tx_ts_tail; - } + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb, &shhwtstamps); } void gem_ptp_init(struct net_device *dev) { struct macb *bp = netdev_priv(dev); - struct macb_queue *queue; - unsigned int q; bp->ptp_clock_info = gem_ptp_caps_template; @@ -384,11 +344,6 @@ void gem_ptp_init(struct net_device *dev) } spin_lock_init(&bp->tsu_clk_lock); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - queue->tx_ts_head = 0; - queue->tx_ts_tail = 0; - INIT_WORK(&queue->tx_ts_task, gem_tx_timestamp_flush); - } gem_ptp_init_tsu(bp); diff --git a/drivers/net/ethernet/engleder/Makefile b/drivers/net/ethernet/engleder/Makefile index b6e3b16623de..b98135f65eb7 100644 --- a/drivers/net/ethernet/engleder/Makefile +++ b/drivers/net/ethernet/engleder/Makefile @@ -6,5 +6,5 @@ obj-$(CONFIG_TSNEP) += tsnep.o tsnep-objs := tsnep_main.o tsnep_ethtool.o tsnep_ptp.o tsnep_tc.o \ - tsnep_rxnfc.o $(tsnep-y) + tsnep_rxnfc.o tsnep_xdp.o tsnep-$(CONFIG_TSNEP_SELFTESTS) += tsnep_selftests.o diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h index f93ba48bac3f..058c2bcf31a7 100644 --- a/drivers/net/ethernet/engleder/tsnep.h +++ b/drivers/net/ethernet/engleder/tsnep.h @@ -65,7 +65,11 @@ struct tsnep_tx_entry { u32 properties; - struct sk_buff *skb; + u32 type; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; size_t len; DEFINE_DMA_UNMAP_ADDR(dma); }; @@ -78,8 +82,6 @@ struct tsnep_tx { void *page[TSNEP_RING_PAGE_COUNT]; dma_addr_t page_dma[TSNEP_RING_PAGE_COUNT]; - /* TX ring lock */ - spinlock_t lock; struct tsnep_tx_entry entry[TSNEP_RING_SIZE]; int write; int read; @@ -107,6 +109,7 @@ struct tsnep_rx { struct tsnep_adapter *adapter; void __iomem *addr; int queue_index; + int tx_queue_index; void *page[TSNEP_RING_PAGE_COUNT]; dma_addr_t page_dma[TSNEP_RING_PAGE_COUNT]; @@ -123,6 +126,8 @@ struct tsnep_rx { u32 dropped; u32 multicast; u32 alloc_failed; + + struct xdp_rxq_info xdp_rxq; }; struct tsnep_queue { @@ -172,6 +177,8 @@ struct tsnep_adapter { int rxnfc_count; int rxnfc_max; + struct bpf_prog *xdp_prog; + int num_tx_queues; struct tsnep_tx tx[TSNEP_MAX_QUEUES]; int num_rx_queues; @@ -204,6 +211,9 @@ int tsnep_rxnfc_add_rule(struct tsnep_adapter *adapter, int tsnep_rxnfc_del_rule(struct tsnep_adapter *adapter, struct ethtool_rxnfc *cmd); +int tsnep_xdp_setup_prog(struct tsnep_adapter *adapter, struct bpf_prog *prog, + struct netlink_ext_ack *extack); + #if IS_ENABLED(CONFIG_TSNEP_SELFTESTS) int tsnep_ethtool_get_test_count(void); void tsnep_ethtool_get_test_strings(u8 *data); diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index bf0190e1d2ea..5a909c1c11bc 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -26,9 +26,11 @@ #include <linux/etherdevice.h> #include <linux/phy.h> #include <linux/iopoll.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> -#define TSNEP_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -#define TSNEP_HEADROOM ALIGN(TSNEP_SKB_PAD, 4) +#define TSNEP_RX_OFFSET (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN) +#define TSNEP_HEADROOM ALIGN(TSNEP_RX_OFFSET, 4) #define TSNEP_MAX_RX_BUF_SIZE (PAGE_SIZE - TSNEP_HEADROOM - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) @@ -43,6 +45,14 @@ #define TSNEP_COALESCE_USECS_MAX ((ECM_INT_DELAY_MASK >> ECM_INT_DELAY_SHIFT) * \ ECM_INT_DELAY_BASE_US + ECM_INT_DELAY_BASE_US - 1) +#define TSNEP_TX_TYPE_SKB BIT(0) +#define TSNEP_TX_TYPE_SKB_FRAG BIT(1) +#define TSNEP_TX_TYPE_XDP_TX BIT(2) +#define TSNEP_TX_TYPE_XDP_NDO BIT(3) + +#define TSNEP_XDP_TX BIT(0) +#define TSNEP_XDP_REDIRECT BIT(1) + static void tsnep_enable_irq(struct tsnep_adapter *adapter, u32 mask) { iowrite32(mask, adapter->addr + ECM_INT_ENABLE); @@ -306,10 +316,12 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length, struct tsnep_tx_entry *entry = &tx->entry[index]; entry->properties = 0; + /* xdpf is union with skb */ if (entry->skb) { entry->properties = length & TSNEP_DESC_LENGTH_MASK; entry->properties |= TSNEP_DESC_INTERRUPT_FLAG; - if (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) + if ((entry->type & TSNEP_TX_TYPE_SKB) && + (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS)) entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG; /* toggle user flag to prevent false acknowledge @@ -378,15 +390,19 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count) for (i = 0; i < count; i++) { entry = &tx->entry[(tx->write + i) % TSNEP_RING_SIZE]; - if (i == 0) { + if (!i) { len = skb_headlen(skb); dma = dma_map_single(dmadev, skb->data, len, DMA_TO_DEVICE); + + entry->type = TSNEP_TX_TYPE_SKB; } else { len = skb_frag_size(&skb_shinfo(skb)->frags[i - 1]); dma = skb_frag_dma_map(dmadev, &skb_shinfo(skb)->frags[i - 1], 0, len, DMA_TO_DEVICE); + + entry->type = TSNEP_TX_TYPE_SKB_FRAG; } if (dma_mapping_error(dmadev, dma)) return -ENOMEM; @@ -413,12 +429,13 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count) entry = &tx->entry[(index + i) % TSNEP_RING_SIZE]; if (entry->len) { - if (i == 0) + if (entry->type & TSNEP_TX_TYPE_SKB) dma_unmap_single(dmadev, dma_unmap_addr(entry, dma), dma_unmap_len(entry, len), DMA_TO_DEVICE); - else + else if (entry->type & + (TSNEP_TX_TYPE_SKB_FRAG | TSNEP_TX_TYPE_XDP_NDO)) dma_unmap_page(dmadev, dma_unmap_addr(entry, dma), dma_unmap_len(entry, len), @@ -434,7 +451,6 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count) static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, struct tsnep_tx *tx) { - unsigned long flags; int count = 1; struct tsnep_tx_entry *entry; int length; @@ -444,16 +460,12 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, if (skb_shinfo(skb)->nr_frags > 0) count += skb_shinfo(skb)->nr_frags; - spin_lock_irqsave(&tx->lock, flags); - if (tsnep_tx_desc_available(tx) < count) { /* ring full, shall not happen because queue is stopped if full * below */ netif_stop_queue(tx->adapter->netdev); - spin_unlock_irqrestore(&tx->lock, flags); - return NETDEV_TX_BUSY; } @@ -468,10 +480,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, tx->dropped++; - spin_unlock_irqrestore(&tx->lock, flags); - - netdev_err(tx->adapter->netdev, "TX DMA map failed\n"); - return NETDEV_TX_OK; } length = retval; @@ -481,7 +489,7 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, for (i = 0; i < count; i++) tsnep_tx_activate(tx, (tx->write + i) % TSNEP_RING_SIZE, length, - i == (count - 1)); + i == count - 1); tx->write = (tx->write + count) % TSNEP_RING_SIZE; skb_tx_timestamp(skb); @@ -496,20 +504,146 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, netif_stop_queue(tx->adapter->netdev); } - spin_unlock_irqrestore(&tx->lock, flags); - return NETDEV_TX_OK; } +static int tsnep_xdp_tx_map(struct xdp_frame *xdpf, struct tsnep_tx *tx, + struct skb_shared_info *shinfo, int count, u32 type) +{ + struct device *dmadev = tx->adapter->dmadev; + struct tsnep_tx_entry *entry; + struct page *page; + skb_frag_t *frag; + unsigned int len; + int map_len = 0; + dma_addr_t dma; + void *data; + int i; + + frag = NULL; + len = xdpf->len; + for (i = 0; i < count; i++) { + entry = &tx->entry[(tx->write + i) % TSNEP_RING_SIZE]; + if (type & TSNEP_TX_TYPE_XDP_NDO) { + data = unlikely(frag) ? skb_frag_address(frag) : + xdpf->data; + dma = dma_map_single(dmadev, data, len, DMA_TO_DEVICE); + if (dma_mapping_error(dmadev, dma)) + return -ENOMEM; + + entry->type = TSNEP_TX_TYPE_XDP_NDO; + } else { + page = unlikely(frag) ? skb_frag_page(frag) : + virt_to_page(xdpf->data); + dma = page_pool_get_dma_addr(page); + if (unlikely(frag)) + dma += skb_frag_off(frag); + else + dma += sizeof(*xdpf) + xdpf->headroom; + dma_sync_single_for_device(dmadev, dma, len, + DMA_BIDIRECTIONAL); + + entry->type = TSNEP_TX_TYPE_XDP_TX; + } + + entry->len = len; + dma_unmap_addr_set(entry, dma, dma); + + entry->desc->tx = __cpu_to_le64(dma); + + map_len += len; + + if (i + 1 < count) { + frag = &shinfo->frags[i]; + len = skb_frag_size(frag); + } + } + + return map_len; +} + +/* This function requires __netif_tx_lock is held by the caller. */ +static bool tsnep_xdp_xmit_frame_ring(struct xdp_frame *xdpf, + struct tsnep_tx *tx, u32 type) +{ + struct skb_shared_info *shinfo = xdp_get_shared_info_from_frame(xdpf); + struct tsnep_tx_entry *entry; + int count, length, retval, i; + + count = 1; + if (unlikely(xdp_frame_has_frags(xdpf))) + count += shinfo->nr_frags; + + /* ensure that TX ring is not filled up by XDP, always MAX_SKB_FRAGS + * will be available for normal TX path and queue is stopped there if + * necessary + */ + if (tsnep_tx_desc_available(tx) < (MAX_SKB_FRAGS + 1 + count)) + return false; + + entry = &tx->entry[tx->write]; + entry->xdpf = xdpf; + + retval = tsnep_xdp_tx_map(xdpf, tx, shinfo, count, type); + if (retval < 0) { + tsnep_tx_unmap(tx, tx->write, count); + entry->xdpf = NULL; + + tx->dropped++; + + return false; + } + length = retval; + + for (i = 0; i < count; i++) + tsnep_tx_activate(tx, (tx->write + i) % TSNEP_RING_SIZE, length, + i == count - 1); + tx->write = (tx->write + count) % TSNEP_RING_SIZE; + + /* descriptor properties shall be valid before hardware is notified */ + dma_wmb(); + + return true; +} + +static void tsnep_xdp_xmit_flush(struct tsnep_tx *tx) +{ + iowrite32(TSNEP_CONTROL_TX_ENABLE, tx->addr + TSNEP_CONTROL); +} + +static bool tsnep_xdp_xmit_back(struct tsnep_adapter *adapter, + struct xdp_buff *xdp, + struct netdev_queue *tx_nq, struct tsnep_tx *tx) +{ + struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); + bool xmit; + + if (unlikely(!xdpf)) + return false; + + __netif_tx_lock(tx_nq, smp_processor_id()); + + xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, TSNEP_TX_TYPE_XDP_TX); + + /* Avoid transmit queue timeout since we share it with the slow path */ + if (xmit) + txq_trans_cond_update(tx_nq); + + __netif_tx_unlock(tx_nq); + + return xmit; +} + static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) { - unsigned long flags; - int budget = 128; struct tsnep_tx_entry *entry; - int count; + struct netdev_queue *nq; + int budget = 128; int length; + int count; - spin_lock_irqsave(&tx->lock, flags); + nq = netdev_get_tx_queue(tx->adapter->netdev, tx->queue_index); + __netif_tx_lock(nq, smp_processor_id()); do { if (tx->read == tx->write) @@ -527,12 +661,17 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) dma_rmb(); count = 1; - if (skb_shinfo(entry->skb)->nr_frags > 0) + if ((entry->type & TSNEP_TX_TYPE_SKB) && + skb_shinfo(entry->skb)->nr_frags > 0) count += skb_shinfo(entry->skb)->nr_frags; + else if (!(entry->type & TSNEP_TX_TYPE_SKB) && + xdp_frame_has_frags(entry->xdpf)) + count += xdp_get_shared_info_from_frame(entry->xdpf)->nr_frags; length = tsnep_tx_unmap(tx, tx->read, count); - if ((skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) && + if ((entry->type & TSNEP_TX_TYPE_SKB) && + (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) && (__le32_to_cpu(entry->desc_wb->properties) & TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) { struct skb_shared_hwtstamps hwtstamps; @@ -552,7 +691,11 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) skb_tstamp_tx(entry->skb, &hwtstamps); } - napi_consume_skb(entry->skb, budget); + if (entry->type & TSNEP_TX_TYPE_SKB) + napi_consume_skb(entry->skb, napi_budget); + else + xdp_return_frame_rx_napi(entry->xdpf); + /* xdpf is union with skb */ entry->skb = NULL; tx->read = (tx->read + count) % TSNEP_RING_SIZE; @@ -568,18 +711,19 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) netif_wake_queue(tx->adapter->netdev); } - spin_unlock_irqrestore(&tx->lock, flags); + __netif_tx_unlock(nq); - return (budget != 0); + return budget != 0; } static bool tsnep_tx_pending(struct tsnep_tx *tx) { - unsigned long flags; struct tsnep_tx_entry *entry; + struct netdev_queue *nq; bool pending = false; - spin_lock_irqsave(&tx->lock, flags); + nq = netdev_get_tx_queue(tx->adapter->netdev, tx->queue_index); + __netif_tx_lock(nq, smp_processor_id()); if (tx->read != tx->write) { entry = &tx->entry[tx->read]; @@ -589,7 +733,7 @@ static bool tsnep_tx_pending(struct tsnep_tx *tx) pending = true; } - spin_unlock_irqrestore(&tx->lock, flags); + __netif_tx_unlock(nq); return pending; } @@ -615,8 +759,6 @@ static int tsnep_tx_open(struct tsnep_adapter *adapter, void __iomem *addr, tx->owner_counter = 1; tx->increment_owner_counter = TSNEP_RING_SIZE - 1; - spin_lock_init(&tx->lock); - return 0; } @@ -692,9 +834,9 @@ static int tsnep_rx_ring_init(struct tsnep_rx *rx) pp_params.pool_size = TSNEP_RING_SIZE; pp_params.nid = dev_to_node(dmadev); pp_params.dev = dmadev; - pp_params.dma_dir = DMA_FROM_DEVICE; + pp_params.dma_dir = DMA_BIDIRECTIONAL; pp_params.max_len = TSNEP_MAX_RX_BUF_SIZE; - pp_params.offset = TSNEP_SKB_PAD; + pp_params.offset = TSNEP_RX_OFFSET; rx->page_pool = page_pool_create(&pp_params); if (IS_ERR(rx->page_pool)) { retval = PTR_ERR(rx->page_pool); @@ -729,7 +871,7 @@ static void tsnep_rx_set_page(struct tsnep_rx *rx, struct tsnep_rx_entry *entry, entry->page = page; entry->len = TSNEP_MAX_RX_BUF_SIZE; entry->dma = page_pool_get_dma_addr(entry->page); - entry->desc->rx = __cpu_to_le64(entry->dma + TSNEP_SKB_PAD); + entry->desc->rx = __cpu_to_le64(entry->dma + TSNEP_RX_OFFSET); } static int tsnep_rx_alloc_buffer(struct tsnep_rx *rx, int index) @@ -823,6 +965,62 @@ static int tsnep_rx_refill(struct tsnep_rx *rx, int count, bool reuse) return i; } +static bool tsnep_xdp_run_prog(struct tsnep_rx *rx, struct bpf_prog *prog, + struct xdp_buff *xdp, int *status, + struct netdev_queue *tx_nq, struct tsnep_tx *tx) +{ + unsigned int length; + unsigned int sync; + u32 act; + + length = xdp->data_end - xdp->data_hard_start - XDP_PACKET_HEADROOM; + + act = bpf_prog_run_xdp(prog, xdp); + + /* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */ + sync = xdp->data_end - xdp->data_hard_start - XDP_PACKET_HEADROOM; + sync = max(sync, length); + + switch (act) { + case XDP_PASS: + return false; + case XDP_TX: + if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx)) + goto out_failure; + *status |= TSNEP_XDP_TX; + return true; + case XDP_REDIRECT: + if (xdp_do_redirect(rx->adapter->netdev, xdp, prog) < 0) + goto out_failure; + *status |= TSNEP_XDP_REDIRECT; + return true; + default: + bpf_warn_invalid_xdp_action(rx->adapter->netdev, prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx->adapter->netdev, prog, act); + fallthrough; + case XDP_DROP: + page_pool_put_page(rx->page_pool, virt_to_head_page(xdp->data), + sync, true); + return true; + } +} + +static void tsnep_finalize_xdp(struct tsnep_adapter *adapter, int status, + struct netdev_queue *tx_nq, struct tsnep_tx *tx) +{ + if (status & TSNEP_XDP_TX) { + __netif_tx_lock(tx_nq, smp_processor_id()); + tsnep_xdp_xmit_flush(tx); + __netif_tx_unlock(tx_nq); + } + + if (status & TSNEP_XDP_REDIRECT) + xdp_do_flush(); +} + static struct sk_buff *tsnep_build_skb(struct tsnep_rx *rx, struct page *page, int length) { @@ -833,14 +1031,14 @@ static struct sk_buff *tsnep_build_skb(struct tsnep_rx *rx, struct page *page, return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, TSNEP_SKB_PAD + TSNEP_RX_INLINE_METADATA_SIZE); - __skb_put(skb, length - TSNEP_RX_INLINE_METADATA_SIZE - ETH_FCS_LEN); + skb_reserve(skb, TSNEP_RX_OFFSET + TSNEP_RX_INLINE_METADATA_SIZE); + __skb_put(skb, length - ETH_FCS_LEN); if (rx->adapter->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL) { struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); struct tsnep_rx_inline *rx_inline = (struct tsnep_rx_inline *)(page_address(page) + - TSNEP_SKB_PAD); + TSNEP_RX_OFFSET); skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV; @@ -858,15 +1056,28 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, int budget) { struct device *dmadev = rx->adapter->dmadev; - int desc_available; - int done = 0; enum dma_data_direction dma_dir; struct tsnep_rx_entry *entry; + struct netdev_queue *tx_nq; + struct bpf_prog *prog; + struct xdp_buff xdp; struct sk_buff *skb; + struct tsnep_tx *tx; + int desc_available; + int xdp_status = 0; + int done = 0; int length; desc_available = tsnep_rx_desc_available(rx); dma_dir = page_pool_get_dma_dir(rx->page_pool); + prog = READ_ONCE(rx->adapter->xdp_prog); + if (prog) { + tx_nq = netdev_get_tx_queue(rx->adapter->netdev, + rx->tx_queue_index); + tx = &rx->adapter->tx[rx->tx_queue_index]; + + xdp_init_buff(&xdp, PAGE_SIZE, &rx->xdp_rxq); + } while (likely(done < budget) && (rx->read != rx->write)) { entry = &rx->entry[rx->read]; @@ -900,21 +1111,47 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, */ dma_rmb(); - prefetch(page_address(entry->page) + TSNEP_SKB_PAD); + prefetch(page_address(entry->page) + TSNEP_RX_OFFSET); length = __le32_to_cpu(entry->desc_wb->properties) & TSNEP_DESC_LENGTH_MASK; - dma_sync_single_range_for_cpu(dmadev, entry->dma, TSNEP_SKB_PAD, - length, dma_dir); + dma_sync_single_range_for_cpu(dmadev, entry->dma, + TSNEP_RX_OFFSET, length, dma_dir); + + /* RX metadata with timestamps is in front of actual data, + * subtract metadata size to get length of actual data and + * consider metadata size as offset of actual data during RX + * processing + */ + length -= TSNEP_RX_INLINE_METADATA_SIZE; rx->read = (rx->read + 1) % TSNEP_RING_SIZE; desc_available++; + if (prog) { + bool consume; + + xdp_prepare_buff(&xdp, page_address(entry->page), + XDP_PACKET_HEADROOM + TSNEP_RX_INLINE_METADATA_SIZE, + length, false); + + consume = tsnep_xdp_run_prog(rx, prog, &xdp, + &xdp_status, tx_nq, tx); + if (consume) { + rx->packets++; + rx->bytes += length; + + entry->page = NULL; + + continue; + } + } + skb = tsnep_build_skb(rx, entry->page, length); if (skb) { page_pool_release_page(rx->page_pool, entry->page); rx->packets++; - rx->bytes += length - TSNEP_RX_INLINE_METADATA_SIZE; + rx->bytes += length; if (skb->pkt_type == PACKET_MULTICAST) rx->multicast++; @@ -927,6 +1164,9 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, entry->page = NULL; } + if (xdp_status) + tsnep_finalize_xdp(rx->adapter, xdp_status, tx_nq, tx); + if (desc_available) tsnep_rx_refill(rx, desc_available, false); @@ -1083,17 +1323,73 @@ static void tsnep_free_irq(struct tsnep_queue *queue, bool first) memset(queue->name, 0, sizeof(queue->name)); } +static void tsnep_queue_close(struct tsnep_queue *queue, bool first) +{ + struct tsnep_rx *rx = queue->rx; + + tsnep_free_irq(queue, first); + + if (rx && xdp_rxq_info_is_reg(&rx->xdp_rxq)) + xdp_rxq_info_unreg(&rx->xdp_rxq); + + netif_napi_del(&queue->napi); +} + +static int tsnep_queue_open(struct tsnep_adapter *adapter, + struct tsnep_queue *queue, bool first) +{ + struct tsnep_rx *rx = queue->rx; + struct tsnep_tx *tx = queue->tx; + int retval; + + queue->adapter = adapter; + + netif_napi_add(adapter->netdev, &queue->napi, tsnep_poll); + + if (rx) { + /* choose TX queue for XDP_TX */ + if (tx) + rx->tx_queue_index = tx->queue_index; + else if (rx->queue_index < adapter->num_tx_queues) + rx->tx_queue_index = rx->queue_index; + else + rx->tx_queue_index = 0; + + retval = xdp_rxq_info_reg(&rx->xdp_rxq, adapter->netdev, + rx->queue_index, queue->napi.napi_id); + if (retval) + goto failed; + retval = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, + MEM_TYPE_PAGE_POOL, + rx->page_pool); + if (retval) + goto failed; + } + + retval = tsnep_request_irq(queue, first); + if (retval) { + netif_err(adapter, drv, adapter->netdev, + "can't get assigned irq %d.\n", queue->irq); + goto failed; + } + + return 0; + +failed: + tsnep_queue_close(queue, first); + + return retval; +} + static int tsnep_netdev_open(struct net_device *netdev) { struct tsnep_adapter *adapter = netdev_priv(netdev); - int i; - void __iomem *addr; int tx_queue_index = 0; int rx_queue_index = 0; - int retval; + void __iomem *addr; + int i, retval; for (i = 0; i < adapter->num_queues; i++) { - adapter->queue[i].adapter = adapter; if (adapter->queue[i].tx) { addr = adapter->addr + TSNEP_QUEUE(tx_queue_index); retval = tsnep_tx_open(adapter, addr, tx_queue_index, @@ -1104,21 +1400,16 @@ static int tsnep_netdev_open(struct net_device *netdev) } if (adapter->queue[i].rx) { addr = adapter->addr + TSNEP_QUEUE(rx_queue_index); - retval = tsnep_rx_open(adapter, addr, - rx_queue_index, + retval = tsnep_rx_open(adapter, addr, rx_queue_index, adapter->queue[i].rx); if (retval) goto failed; rx_queue_index++; } - retval = tsnep_request_irq(&adapter->queue[i], i == 0); - if (retval) { - netif_err(adapter, drv, adapter->netdev, - "can't get assigned irq %d.\n", - adapter->queue[i].irq); + retval = tsnep_queue_open(adapter, &adapter->queue[i], i == 0); + if (retval) goto failed; - } } retval = netif_set_real_num_tx_queues(adapter->netdev, @@ -1136,8 +1427,6 @@ static int tsnep_netdev_open(struct net_device *netdev) goto phy_failed; for (i = 0; i < adapter->num_queues; i++) { - netif_napi_add(adapter->netdev, &adapter->queue[i].napi, - tsnep_poll); napi_enable(&adapter->queue[i].napi); tsnep_enable_irq(adapter, adapter->queue[i].irq_mask); @@ -1147,10 +1436,9 @@ static int tsnep_netdev_open(struct net_device *netdev) phy_failed: tsnep_disable_irq(adapter, ECM_INT_LINK); - tsnep_phy_close(adapter); failed: for (i = 0; i < adapter->num_queues; i++) { - tsnep_free_irq(&adapter->queue[i], i == 0); + tsnep_queue_close(&adapter->queue[i], i == 0); if (adapter->queue[i].rx) tsnep_rx_close(adapter->queue[i].rx); @@ -1172,9 +1460,8 @@ static int tsnep_netdev_close(struct net_device *netdev) tsnep_disable_irq(adapter, adapter->queue[i].irq_mask); napi_disable(&adapter->queue[i].napi); - netif_napi_del(&adapter->queue[i].napi); - tsnep_free_irq(&adapter->queue[i], i == 0); + tsnep_queue_close(&adapter->queue[i], i == 0); if (adapter->queue[i].rx) tsnep_rx_close(adapter->queue[i].rx); @@ -1327,6 +1614,67 @@ static ktime_t tsnep_netdev_get_tstamp(struct net_device *netdev, return ns_to_ktime(timestamp); } +static int tsnep_netdev_bpf(struct net_device *dev, struct netdev_bpf *bpf) +{ + struct tsnep_adapter *adapter = netdev_priv(dev); + + switch (bpf->command) { + case XDP_SETUP_PROG: + return tsnep_xdp_setup_prog(adapter, bpf->prog, bpf->extack); + default: + return -EOPNOTSUPP; + } +} + +static struct tsnep_tx *tsnep_xdp_get_tx(struct tsnep_adapter *adapter, u32 cpu) +{ + if (cpu >= TSNEP_MAX_QUEUES) + cpu &= TSNEP_MAX_QUEUES - 1; + + while (cpu >= adapter->num_tx_queues) + cpu -= adapter->num_tx_queues; + + return &adapter->tx[cpu]; +} + +static int tsnep_netdev_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **xdp, u32 flags) +{ + struct tsnep_adapter *adapter = netdev_priv(dev); + u32 cpu = smp_processor_id(); + struct netdev_queue *nq; + struct tsnep_tx *tx; + int nxmit; + bool xmit; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + tx = tsnep_xdp_get_tx(adapter, cpu); + nq = netdev_get_tx_queue(adapter->netdev, tx->queue_index); + + __netif_tx_lock(nq, cpu); + + for (nxmit = 0; nxmit < n; nxmit++) { + xmit = tsnep_xdp_xmit_frame_ring(xdp[nxmit], tx, + TSNEP_TX_TYPE_XDP_NDO); + if (!xmit) + break; + + /* avoid transmit queue timeout since we share it with the slow + * path + */ + txq_trans_cond_update(nq); + } + + if (flags & XDP_XMIT_FLUSH) + tsnep_xdp_xmit_flush(tx); + + __netif_tx_unlock(nq); + + return nxmit; +} + static const struct net_device_ops tsnep_netdev_ops = { .ndo_open = tsnep_netdev_open, .ndo_stop = tsnep_netdev_close, @@ -1338,6 +1686,8 @@ static const struct net_device_ops tsnep_netdev_ops = { .ndo_set_features = tsnep_netdev_set_features, .ndo_get_tstamp = tsnep_netdev_get_tstamp, .ndo_setup_tc = tsnep_tc_setup, + .ndo_bpf = tsnep_netdev_bpf, + .ndo_xdp_xmit = tsnep_netdev_xdp_xmit, }; static int tsnep_mac_init(struct tsnep_adapter *adapter) diff --git a/drivers/net/ethernet/engleder/tsnep_xdp.c b/drivers/net/ethernet/engleder/tsnep_xdp.c new file mode 100644 index 000000000000..4d14cb1fd772 --- /dev/null +++ b/drivers/net/ethernet/engleder/tsnep_xdp.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2022 Gerhard Engleder <gerhard@engleder-embedded.com> */ + +#include <linux/if_vlan.h> +#include <net/xdp_sock_drv.h> + +#include "tsnep.h" + +int tsnep_xdp_setup_prog(struct tsnep_adapter *adapter, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ + struct bpf_prog *old_prog; + + old_prog = xchg(&adapter->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index 6c8c78018ce6..139fe66f8bcd 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -182,6 +182,12 @@ static int ftmac100_start_hw(struct ftmac100 *priv) if (netdev->mtu > ETH_DATA_LEN) maccr |= FTMAC100_MACCR_RX_FTL; + /* Add other bits as needed */ + if (netdev->flags & IFF_PROMISC) + maccr |= FTMAC100_MACCR_RCV_ALL; + if (netdev->flags & IFF_ALLMULTI) + maccr |= FTMAC100_MACCR_RX_MULTIPKT; + iowrite32(maccr, priv->base + FTMAC100_OFFSET_MACCR); return 0; } diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index cdc0ff89388a..6f6d07324d3b 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config FSL_ENETC tristate "ENETC PF driver" - depends on PCI && PCI_MSI + depends on PCI_MSI select FSL_ENETC_IERB select FSL_ENETC_MDIO select PHYLINK @@ -16,7 +16,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" - depends on PCI && PCI_MSI + depends on PCI_MSI select FSL_ENETC_MDIO select PHYLINK select DIMLIB diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index e96449eedfb5..b227e17e7b02 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1305,6 +1305,10 @@ static int enetc_xdp_frame_to_xdp_tx_swbd(struct enetc_bdr *tx_ring, xdp_tx_swbd->xdp_frame = NULL; n++; + + if (!xdp_frame_has_frags(xdp_frame)) + goto out; + xdp_tx_swbd = &xdp_tx_arr[n]; shinfo = xdp_get_shared_info_from_frame(xdp_frame); @@ -1334,7 +1338,7 @@ static int enetc_xdp_frame_to_xdp_tx_swbd(struct enetc_bdr *tx_ring, n++; xdp_tx_swbd = &xdp_tx_arr[n]; } - +out: xdp_tx_arr[n - 1].is_eof = true; xdp_tx_arr[n - 1].xdp_frame = xdp_frame; @@ -1390,16 +1394,12 @@ static void enetc_map_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, { struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size); void *hard_start = page_address(rx_swbd->page) + rx_swbd->page_offset; - struct skb_shared_info *shinfo; /* To be used for XDP_TX */ rx_swbd->len = size; xdp_prepare_buff(xdp_buff, hard_start - rx_ring->buffer_offset, rx_ring->buffer_offset, size, false); - - shinfo = xdp_get_shared_info_from_buff(xdp_buff); - shinfo->nr_frags = 0; } static void enetc_add_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, @@ -1407,11 +1407,23 @@ static void enetc_add_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, { struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp_buff); struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size); - skb_frag_t *frag = &shinfo->frags[shinfo->nr_frags]; + skb_frag_t *frag; /* To be used for XDP_TX */ rx_swbd->len = size; + if (!xdp_buff_has_frags(xdp_buff)) { + xdp_buff_set_frags_flag(xdp_buff); + shinfo->xdp_frags_size = size; + shinfo->nr_frags = 0; + } else { + shinfo->xdp_frags_size += size; + } + + if (page_is_pfmemalloc(rx_swbd->page)) + xdp_buff_set_frag_pfmemalloc(xdp_buff); + + frag = &shinfo->frags[shinfo->nr_frags]; skb_frag_off_set(frag, rx_swbd->page_offset); skb_frag_size_set(frag, size); __skb_frag_set_page(frag, rx_swbd->page); @@ -1584,20 +1596,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, } break; case XDP_REDIRECT: - /* xdp_return_frame does not support S/G in the sense - * that it leaks the fragments (__xdp_return should not - * call page_frag_free only for the initial buffer). - * Until XDP_REDIRECT gains support for S/G let's keep - * the code structure in place, but dead. We drop the - * S/G frames ourselves to avoid memory leaks which - * would otherwise leave the kernel OOM. - */ - if (unlikely(cleaned_cnt - orig_cleaned_cnt != 1)) { - enetc_xdp_drop(rx_ring, orig_i, i); - rx_ring->stats.xdp_redirect_sg++; - break; - } - err = xdp_do_redirect(rx_ring->ndev, &xdp_buff, prog); if (unlikely(err)) { enetc_xdp_drop(rx_ring, orig_i, i); @@ -1717,200 +1715,255 @@ void enetc_get_si_caps(struct enetc_si *si) si->hw_features |= ENETC_SI_F_PSFP; } -static int enetc_dma_alloc_bdr(struct enetc_bdr *r, size_t bd_size) +static int enetc_dma_alloc_bdr(struct enetc_bdr_resource *res) { - r->bd_base = dma_alloc_coherent(r->dev, r->bd_count * bd_size, - &r->bd_dma_base, GFP_KERNEL); - if (!r->bd_base) + size_t bd_base_size = res->bd_count * res->bd_size; + + res->bd_base = dma_alloc_coherent(res->dev, bd_base_size, + &res->bd_dma_base, GFP_KERNEL); + if (!res->bd_base) return -ENOMEM; /* h/w requires 128B alignment */ - if (!IS_ALIGNED(r->bd_dma_base, 128)) { - dma_free_coherent(r->dev, r->bd_count * bd_size, r->bd_base, - r->bd_dma_base); + if (!IS_ALIGNED(res->bd_dma_base, 128)) { + dma_free_coherent(res->dev, bd_base_size, res->bd_base, + res->bd_dma_base); return -EINVAL; } return 0; } -static int enetc_alloc_txbdr(struct enetc_bdr *txr) +static void enetc_dma_free_bdr(const struct enetc_bdr_resource *res) +{ + size_t bd_base_size = res->bd_count * res->bd_size; + + dma_free_coherent(res->dev, bd_base_size, res->bd_base, + res->bd_dma_base); +} + +static int enetc_alloc_tx_resource(struct enetc_bdr_resource *res, + struct device *dev, size_t bd_count) { int err; - txr->tx_swbd = vzalloc(txr->bd_count * sizeof(struct enetc_tx_swbd)); - if (!txr->tx_swbd) + res->dev = dev; + res->bd_count = bd_count; + res->bd_size = sizeof(union enetc_tx_bd); + + res->tx_swbd = vzalloc(bd_count * sizeof(*res->tx_swbd)); + if (!res->tx_swbd) return -ENOMEM; - err = enetc_dma_alloc_bdr(txr, sizeof(union enetc_tx_bd)); + err = enetc_dma_alloc_bdr(res); if (err) goto err_alloc_bdr; - txr->tso_headers = dma_alloc_coherent(txr->dev, - txr->bd_count * TSO_HEADER_SIZE, - &txr->tso_headers_dma, + res->tso_headers = dma_alloc_coherent(dev, bd_count * TSO_HEADER_SIZE, + &res->tso_headers_dma, GFP_KERNEL); - if (!txr->tso_headers) { + if (!res->tso_headers) { err = -ENOMEM; goto err_alloc_tso; } - txr->next_to_clean = 0; - txr->next_to_use = 0; - return 0; err_alloc_tso: - dma_free_coherent(txr->dev, txr->bd_count * sizeof(union enetc_tx_bd), - txr->bd_base, txr->bd_dma_base); - txr->bd_base = NULL; + enetc_dma_free_bdr(res); err_alloc_bdr: - vfree(txr->tx_swbd); - txr->tx_swbd = NULL; + vfree(res->tx_swbd); + res->tx_swbd = NULL; return err; } -static void enetc_free_txbdr(struct enetc_bdr *txr) +static void enetc_free_tx_resource(const struct enetc_bdr_resource *res) { - int size, i; - - for (i = 0; i < txr->bd_count; i++) - enetc_free_tx_frame(txr, &txr->tx_swbd[i]); - - size = txr->bd_count * sizeof(union enetc_tx_bd); - - dma_free_coherent(txr->dev, txr->bd_count * TSO_HEADER_SIZE, - txr->tso_headers, txr->tso_headers_dma); - txr->tso_headers = NULL; - - dma_free_coherent(txr->dev, size, txr->bd_base, txr->bd_dma_base); - txr->bd_base = NULL; - - vfree(txr->tx_swbd); - txr->tx_swbd = NULL; + dma_free_coherent(res->dev, res->bd_count * TSO_HEADER_SIZE, + res->tso_headers, res->tso_headers_dma); + enetc_dma_free_bdr(res); + vfree(res->tx_swbd); } -static int enetc_alloc_tx_resources(struct enetc_ndev_priv *priv) +static struct enetc_bdr_resource * +enetc_alloc_tx_resources(struct enetc_ndev_priv *priv) { + struct enetc_bdr_resource *tx_res; int i, err; + tx_res = kcalloc(priv->num_tx_rings, sizeof(*tx_res), GFP_KERNEL); + if (!tx_res) + return ERR_PTR(-ENOMEM); + for (i = 0; i < priv->num_tx_rings; i++) { - err = enetc_alloc_txbdr(priv->tx_ring[i]); + struct enetc_bdr *tx_ring = priv->tx_ring[i]; + err = enetc_alloc_tx_resource(&tx_res[i], tx_ring->dev, + tx_ring->bd_count); if (err) goto fail; } - return 0; + return tx_res; fail: while (i-- > 0) - enetc_free_txbdr(priv->tx_ring[i]); + enetc_free_tx_resource(&tx_res[i]); - return err; + kfree(tx_res); + + return ERR_PTR(err); } -static void enetc_free_tx_resources(struct enetc_ndev_priv *priv) +static void enetc_free_tx_resources(const struct enetc_bdr_resource *tx_res, + size_t num_resources) { - int i; + size_t i; - for (i = 0; i < priv->num_tx_rings; i++) - enetc_free_txbdr(priv->tx_ring[i]); + for (i = 0; i < num_resources; i++) + enetc_free_tx_resource(&tx_res[i]); + + kfree(tx_res); } -static int enetc_alloc_rxbdr(struct enetc_bdr *rxr, bool extended) +static int enetc_alloc_rx_resource(struct enetc_bdr_resource *res, + struct device *dev, size_t bd_count, + bool extended) { - size_t size = sizeof(union enetc_rx_bd); int err; - rxr->rx_swbd = vzalloc(rxr->bd_count * sizeof(struct enetc_rx_swbd)); - if (!rxr->rx_swbd) - return -ENOMEM; - + res->dev = dev; + res->bd_count = bd_count; + res->bd_size = sizeof(union enetc_rx_bd); if (extended) - size *= 2; + res->bd_size *= 2; + + res->rx_swbd = vzalloc(bd_count * sizeof(struct enetc_rx_swbd)); + if (!res->rx_swbd) + return -ENOMEM; - err = enetc_dma_alloc_bdr(rxr, size); + err = enetc_dma_alloc_bdr(res); if (err) { - vfree(rxr->rx_swbd); + vfree(res->rx_swbd); return err; } - rxr->next_to_clean = 0; - rxr->next_to_use = 0; - rxr->next_to_alloc = 0; - rxr->ext_en = extended; - return 0; } -static void enetc_free_rxbdr(struct enetc_bdr *rxr) +static void enetc_free_rx_resource(const struct enetc_bdr_resource *res) { - int size; - - size = rxr->bd_count * sizeof(union enetc_rx_bd); - - dma_free_coherent(rxr->dev, size, rxr->bd_base, rxr->bd_dma_base); - rxr->bd_base = NULL; - - vfree(rxr->rx_swbd); - rxr->rx_swbd = NULL; + enetc_dma_free_bdr(res); + vfree(res->rx_swbd); } -static int enetc_alloc_rx_resources(struct enetc_ndev_priv *priv) +static struct enetc_bdr_resource * +enetc_alloc_rx_resources(struct enetc_ndev_priv *priv, bool extended) { - bool extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); + struct enetc_bdr_resource *rx_res; int i, err; + rx_res = kcalloc(priv->num_rx_rings, sizeof(*rx_res), GFP_KERNEL); + if (!rx_res) + return ERR_PTR(-ENOMEM); + for (i = 0; i < priv->num_rx_rings; i++) { - err = enetc_alloc_rxbdr(priv->rx_ring[i], extended); + struct enetc_bdr *rx_ring = priv->rx_ring[i]; + err = enetc_alloc_rx_resource(&rx_res[i], rx_ring->dev, + rx_ring->bd_count, extended); if (err) goto fail; } - return 0; + return rx_res; fail: while (i-- > 0) - enetc_free_rxbdr(priv->rx_ring[i]); + enetc_free_rx_resource(&rx_res[i]); - return err; + kfree(rx_res); + + return ERR_PTR(err); } -static void enetc_free_rx_resources(struct enetc_ndev_priv *priv) +static void enetc_free_rx_resources(const struct enetc_bdr_resource *rx_res, + size_t num_resources) +{ + size_t i; + + for (i = 0; i < num_resources; i++) + enetc_free_rx_resource(&rx_res[i]); + + kfree(rx_res); +} + +static void enetc_assign_tx_resource(struct enetc_bdr *tx_ring, + const struct enetc_bdr_resource *res) +{ + tx_ring->bd_base = res ? res->bd_base : NULL; + tx_ring->bd_dma_base = res ? res->bd_dma_base : 0; + tx_ring->tx_swbd = res ? res->tx_swbd : NULL; + tx_ring->tso_headers = res ? res->tso_headers : NULL; + tx_ring->tso_headers_dma = res ? res->tso_headers_dma : 0; +} + +static void enetc_assign_rx_resource(struct enetc_bdr *rx_ring, + const struct enetc_bdr_resource *res) +{ + rx_ring->bd_base = res ? res->bd_base : NULL; + rx_ring->bd_dma_base = res ? res->bd_dma_base : 0; + rx_ring->rx_swbd = res ? res->rx_swbd : NULL; +} + +static void enetc_assign_tx_resources(struct enetc_ndev_priv *priv, + const struct enetc_bdr_resource *res) { int i; - for (i = 0; i < priv->num_rx_rings; i++) - enetc_free_rxbdr(priv->rx_ring[i]); + if (priv->tx_res) + enetc_free_tx_resources(priv->tx_res, priv->num_tx_rings); + + for (i = 0; i < priv->num_tx_rings; i++) { + enetc_assign_tx_resource(priv->tx_ring[i], + res ? &res[i] : NULL); + } + + priv->tx_res = res; } -static void enetc_free_tx_ring(struct enetc_bdr *tx_ring) +static void enetc_assign_rx_resources(struct enetc_ndev_priv *priv, + const struct enetc_bdr_resource *res) { int i; - if (!tx_ring->tx_swbd) - return; + if (priv->rx_res) + enetc_free_rx_resources(priv->rx_res, priv->num_rx_rings); + + for (i = 0; i < priv->num_rx_rings; i++) { + enetc_assign_rx_resource(priv->rx_ring[i], + res ? &res[i] : NULL); + } + + priv->rx_res = res; +} + +static void enetc_free_tx_ring(struct enetc_bdr *tx_ring) +{ + int i; for (i = 0; i < tx_ring->bd_count; i++) { struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i]; enetc_free_tx_frame(tx_ring, tx_swbd); } - - tx_ring->next_to_clean = 0; - tx_ring->next_to_use = 0; } static void enetc_free_rx_ring(struct enetc_bdr *rx_ring) { int i; - if (!rx_ring->rx_swbd) - return; - for (i = 0; i < rx_ring->bd_count; i++) { struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[i]; @@ -1922,10 +1975,6 @@ static void enetc_free_rx_ring(struct enetc_bdr *rx_ring) __free_page(rx_swbd->page); rx_swbd->page = NULL; } - - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; - rx_ring->next_to_alloc = 0; } static void enetc_free_rxtx_rings(struct enetc_ndev_priv *priv) @@ -2039,7 +2088,7 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1); - tbmr = ENETC_TBMR_EN | ENETC_TBMR_SET_PRIO(tx_ring->prio); + tbmr = ENETC_TBMR_SET_PRIO(tx_ring->prio); if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) tbmr |= ENETC_TBMR_VIH; @@ -2051,10 +2100,11 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) tx_ring->idr = hw->reg + ENETC_SITXIDR; } -static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) +static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring, + bool extended) { int idx = rx_ring->index; - u32 rbmr; + u32 rbmr = 0; enetc_rxbdr_wr(hw, idx, ENETC_RBBAR0, lower_32_bits(rx_ring->bd_dma_base)); @@ -2081,8 +2131,7 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) /* enable Rx ints by setting pkt thr to 1 */ enetc_rxbdr_wr(hw, idx, ENETC_RBICR0, ENETC_RBICR0_ICEN | 0x1); - rbmr = ENETC_RBMR_EN; - + rx_ring->ext_en = extended; if (rx_ring->ext_en) rbmr |= ENETC_RBMR_BDS; @@ -2092,15 +2141,18 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->rcir = hw->reg + ENETC_BDR(RX, idx, ENETC_RBCIR); rx_ring->idr = hw->reg + ENETC_SIRXIDR; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + rx_ring->next_to_alloc = 0; + enetc_lock_mdio(); enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); enetc_unlock_mdio(); - /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); } -static void enetc_setup_bdrs(struct enetc_ndev_priv *priv) +static void enetc_setup_bdrs(struct enetc_ndev_priv *priv, bool extended) { struct enetc_hw *hw = &priv->si->hw; int i; @@ -2109,10 +2161,42 @@ static void enetc_setup_bdrs(struct enetc_ndev_priv *priv) enetc_setup_txbdr(hw, priv->tx_ring[i]); for (i = 0; i < priv->num_rx_rings; i++) - enetc_setup_rxbdr(hw, priv->rx_ring[i]); + enetc_setup_rxbdr(hw, priv->rx_ring[i], extended); } -static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) +static void enetc_enable_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) +{ + int idx = tx_ring->index; + u32 tbmr; + + tbmr = enetc_txbdr_rd(hw, idx, ENETC_TBMR); + tbmr |= ENETC_TBMR_EN; + enetc_txbdr_wr(hw, idx, ENETC_TBMR, tbmr); +} + +static void enetc_enable_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) +{ + int idx = rx_ring->index; + u32 rbmr; + + rbmr = enetc_rxbdr_rd(hw, idx, ENETC_RBMR); + rbmr |= ENETC_RBMR_EN; + enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); +} + +static void enetc_enable_bdrs(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + enetc_enable_txbdr(hw, priv->tx_ring[i]); + + for (i = 0; i < priv->num_rx_rings; i++) + enetc_enable_rxbdr(hw, priv->rx_ring[i]); +} + +static void enetc_disable_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) { int idx = rx_ring->index; @@ -2120,13 +2204,30 @@ static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) enetc_rxbdr_wr(hw, idx, ENETC_RBMR, 0); } -static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) +static void enetc_disable_txbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) { - int delay = 8, timeout = 100; - int idx = tx_ring->index; + int idx = rx_ring->index; /* disable EN bit on ring */ enetc_txbdr_wr(hw, idx, ENETC_TBMR, 0); +} + +static void enetc_disable_bdrs(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + enetc_disable_txbdr(hw, priv->tx_ring[i]); + + for (i = 0; i < priv->num_rx_rings; i++) + enetc_disable_rxbdr(hw, priv->rx_ring[i]); +} + +static void enetc_wait_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) +{ + int delay = 8, timeout = 100; + int idx = tx_ring->index; /* wait for busy to clear */ while (delay < timeout && @@ -2140,18 +2241,13 @@ static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) idx); } -static void enetc_clear_bdrs(struct enetc_ndev_priv *priv) +static void enetc_wait_bdrs(struct enetc_ndev_priv *priv) { struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_clear_txbdr(hw, priv->tx_ring[i]); - - for (i = 0; i < priv->num_rx_rings; i++) - enetc_clear_rxbdr(hw, priv->rx_ring[i]); - - udelay(1); + enetc_wait_txbdr(hw, priv->tx_ring[i]); } static int enetc_setup_irqs(struct enetc_ndev_priv *priv) @@ -2267,8 +2363,11 @@ static int enetc_phylink_connect(struct net_device *ndev) struct ethtool_eee edata; int err; - if (!priv->phylink) - return 0; /* phy-less mode */ + if (!priv->phylink) { + /* phy-less mode */ + netif_carrier_on(ndev); + return 0; + } err = phylink_of_phy_connect(priv->phylink, priv->dev->of_node, 0); if (err) { @@ -2280,6 +2379,8 @@ static int enetc_phylink_connect(struct net_device *ndev) memset(&edata, 0, sizeof(struct ethtool_eee)); phylink_ethtool_set_eee(priv->phylink, &edata); + phylink_start(priv->phylink); + return 0; } @@ -2321,10 +2422,7 @@ void enetc_start(struct net_device *ndev) enable_irq(irq); } - if (priv->phylink) - phylink_start(priv->phylink); - else - netif_carrier_on(ndev); + enetc_enable_bdrs(priv); netif_tx_start_all_queues(ndev); } @@ -2332,9 +2430,13 @@ void enetc_start(struct net_device *ndev) int enetc_open(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_bdr_resource *tx_res, *rx_res; int num_stack_tx_queues; + bool extended; int err; + extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); + err = enetc_setup_irqs(priv); if (err) return err; @@ -2343,13 +2445,17 @@ int enetc_open(struct net_device *ndev) if (err) goto err_phy_connect; - err = enetc_alloc_tx_resources(priv); - if (err) + tx_res = enetc_alloc_tx_resources(priv); + if (IS_ERR(tx_res)) { + err = PTR_ERR(tx_res); goto err_alloc_tx; + } - err = enetc_alloc_rx_resources(priv); - if (err) + rx_res = enetc_alloc_rx_resources(priv, extended); + if (IS_ERR(rx_res)) { + err = PTR_ERR(rx_res); goto err_alloc_rx; + } num_stack_tx_queues = enetc_num_stack_tx_queues(priv); @@ -2362,15 +2468,17 @@ int enetc_open(struct net_device *ndev) goto err_set_queues; enetc_tx_onestep_tstamp_init(priv); - enetc_setup_bdrs(priv); + enetc_assign_tx_resources(priv, tx_res); + enetc_assign_rx_resources(priv, rx_res); + enetc_setup_bdrs(priv, extended); enetc_start(ndev); return 0; err_set_queues: - enetc_free_rx_resources(priv); + enetc_free_rx_resources(rx_res, priv->num_rx_rings); err_alloc_rx: - enetc_free_tx_resources(priv); + enetc_free_tx_resources(tx_res, priv->num_tx_rings); err_alloc_tx: if (priv->phylink) phylink_disconnect_phy(priv->phylink); @@ -2387,6 +2495,8 @@ void enetc_stop(struct net_device *ndev) netif_tx_stop_all_queues(ndev); + enetc_disable_bdrs(priv); + for (i = 0; i < priv->bdr_int_num; i++) { int irq = pci_irq_vector(priv->si->pdev, ENETC_BDR_INT_BASE_IDX + i); @@ -2396,10 +2506,7 @@ void enetc_stop(struct net_device *ndev) napi_disable(&priv->int_vector[i]->napi); } - if (priv->phylink) - phylink_stop(priv->phylink); - else - netif_carrier_off(ndev); + enetc_wait_bdrs(priv); enetc_clear_interrupts(priv); } @@ -2409,18 +2516,76 @@ int enetc_close(struct net_device *ndev) struct enetc_ndev_priv *priv = netdev_priv(ndev); enetc_stop(ndev); - enetc_clear_bdrs(priv); - if (priv->phylink) + if (priv->phylink) { + phylink_stop(priv->phylink); phylink_disconnect_phy(priv->phylink); + } else { + netif_carrier_off(ndev); + } + enetc_free_rxtx_rings(priv); - enetc_free_rx_resources(priv); - enetc_free_tx_resources(priv); + + /* Avoids dangling pointers and also frees old resources */ + enetc_assign_rx_resources(priv, NULL); + enetc_assign_tx_resources(priv, NULL); + enetc_free_irqs(priv); return 0; } +static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, + int (*cb)(struct enetc_ndev_priv *priv, void *ctx), + void *ctx) +{ + struct enetc_bdr_resource *tx_res, *rx_res; + int err; + + ASSERT_RTNL(); + + /* If the interface is down, run the callback right away, + * without reconfiguration. + */ + if (!netif_running(priv->ndev)) { + if (cb) + cb(priv, ctx); + + return 0; + } + + tx_res = enetc_alloc_tx_resources(priv); + if (IS_ERR(tx_res)) { + err = PTR_ERR(tx_res); + goto out; + } + + rx_res = enetc_alloc_rx_resources(priv, extended); + if (IS_ERR(rx_res)) { + err = PTR_ERR(rx_res); + goto out_free_tx_res; + } + + enetc_stop(priv->ndev); + enetc_free_rxtx_rings(priv); + + /* Interface is down, run optional callback now */ + if (cb) + cb(priv, ctx); + + enetc_assign_tx_resources(priv, tx_res); + enetc_assign_rx_resources(priv, rx_res); + enetc_setup_bdrs(priv, extended); + enetc_start(priv->ndev); + + return 0; + +out_free_tx_res: + enetc_free_tx_resources(tx_res, priv->num_tx_rings); +out: + return err; +} + int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) { struct enetc_ndev_priv *priv = netdev_priv(ndev); @@ -2478,21 +2643,11 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) return 0; } -static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog, - struct netlink_ext_ack *extack) +static int enetc_reconfigure_xdp_cb(struct enetc_ndev_priv *priv, void *ctx) { - struct enetc_ndev_priv *priv = netdev_priv(dev); - struct bpf_prog *old_prog; - bool is_up; + struct bpf_prog *old_prog, *prog = ctx; int i; - /* The buffer layout is changing, so we need to drain the old - * RX buffers and seed new ones. - */ - is_up = netif_running(dev); - if (is_up) - dev_close(dev); - old_prog = xchg(&priv->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); @@ -2508,17 +2663,28 @@ static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog, rx_ring->buffer_offset = ENETC_RXB_PAD; } - if (is_up) - return dev_open(dev, extack); - return 0; } -int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp) +static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog, + struct netlink_ext_ack *extack) { - switch (xdp->command) { + struct enetc_ndev_priv *priv = netdev_priv(ndev); + bool extended; + + extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); + + /* The buffer layout is changing, so we need to drain the old + * RX buffers and seed new ones. + */ + return enetc_reconfigure(priv, extended, enetc_reconfigure_xdp_cb, prog); +} + +int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf) +{ + switch (bpf->command) { case XDP_SETUP_PROG: - return enetc_setup_xdp_prog(dev, xdp->prog, xdp->extack); + return enetc_setup_xdp_prog(ndev, bpf->prog, bpf->extack); default: return -EINVAL; } @@ -2613,43 +2779,47 @@ void enetc_set_features(struct net_device *ndev, netdev_features_t features) static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + int err, new_offloads = priv->active_offloads; struct hwtstamp_config config; - int ao; if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; switch (config.tx_type) { case HWTSTAMP_TX_OFF: - priv->active_offloads &= ~ENETC_F_TX_TSTAMP_MASK; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; break; case HWTSTAMP_TX_ON: - priv->active_offloads &= ~ENETC_F_TX_TSTAMP_MASK; - priv->active_offloads |= ENETC_F_TX_TSTAMP; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; + new_offloads |= ENETC_F_TX_TSTAMP; break; case HWTSTAMP_TX_ONESTEP_SYNC: - priv->active_offloads &= ~ENETC_F_TX_TSTAMP_MASK; - priv->active_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; + new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP; break; default: return -ERANGE; } - ao = priv->active_offloads; switch (config.rx_filter) { case HWTSTAMP_FILTER_NONE: - priv->active_offloads &= ~ENETC_F_RX_TSTAMP; + new_offloads &= ~ENETC_F_RX_TSTAMP; break; default: - priv->active_offloads |= ENETC_F_RX_TSTAMP; + new_offloads |= ENETC_F_RX_TSTAMP; config.rx_filter = HWTSTAMP_FILTER_ALL; } - if (netif_running(ndev) && ao != priv->active_offloads) { - enetc_close(ndev); - enetc_open(ndev); + if ((new_offloads ^ priv->active_offloads) & ENETC_F_RX_TSTAMP) { + bool extended = !!(new_offloads & ENETC_F_RX_TSTAMP); + + err = enetc_reconfigure(priv, extended, NULL, NULL); + if (err) + return err; } + priv->active_offloads = new_offloads; + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index c6d8cc15c270..6a87aa972e1e 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -70,7 +70,6 @@ struct enetc_ring_stats { unsigned int xdp_tx_drops; unsigned int xdp_redirect; unsigned int xdp_redirect_failures; - unsigned int xdp_redirect_sg; unsigned int recycles; unsigned int recycle_failures; unsigned int win_drop; @@ -86,6 +85,23 @@ struct enetc_xdp_data { #define ENETC_TX_RING_DEFAULT_SIZE 2048 #define ENETC_DEFAULT_TX_WORK (ENETC_TX_RING_DEFAULT_SIZE / 2) +struct enetc_bdr_resource { + /* Input arguments saved for teardown */ + struct device *dev; /* for DMA mapping */ + size_t bd_count; + size_t bd_size; + + /* Resource proper */ + void *bd_base; /* points to Rx or Tx BD ring */ + dma_addr_t bd_dma_base; + union { + struct enetc_tx_swbd *tx_swbd; + struct enetc_rx_swbd *rx_swbd; + }; + char *tso_headers; + dma_addr_t tso_headers_dma; +}; + struct enetc_bdr { struct device *dev; /* for DMA mapping */ struct net_device *ndev; @@ -345,6 +361,8 @@ struct enetc_ndev_priv { struct enetc_bdr **xdp_tx_ring; struct enetc_bdr *tx_ring[16]; struct enetc_bdr *rx_ring[16]; + const struct enetc_bdr_resource *tx_res; + const struct enetc_bdr_resource *rx_res; struct enetc_cls_rule *cls_rules; @@ -397,7 +415,7 @@ struct net_device_stats *enetc_get_stats(struct net_device *ndev); void enetc_set_features(struct net_device *ndev, netdev_features_t features); int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd); int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data); -int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp); +int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf); int enetc_xdp_xmit(struct net_device *ndev, int num_frames, struct xdp_frame **frames, u32 flags); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index c8369e3752b0..d45f305eb03c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -197,7 +197,6 @@ static const char rx_ring_stats[][ETH_GSTRING_LEN] = { "Rx ring %2d recycle failures", "Rx ring %2d redirects", "Rx ring %2d redirect failures", - "Rx ring %2d redirect S/G", }; static const char tx_ring_stats[][ETH_GSTRING_LEN] = { @@ -291,7 +290,6 @@ static void enetc_get_ethtool_stats(struct net_device *ndev, data[o++] = priv->rx_ring[i]->stats.recycle_failures; data[o++] = priv->rx_ring[i]->stats.xdp_redirect; data[o++] = priv->rx_ring[i]->stats.xdp_redirect_failures; - data[o++] = priv->rx_ring[i]->stats.xdp_redirect_sg; } if (!enetc_si_is_pf(priv->si)) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c index 1c8f5cc6dec4..998aaa394e9c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c @@ -55,7 +55,8 @@ static int enetc_mdio_wait_complete(struct enetc_mdio_priv *mdio_priv) is_busy, !is_busy, 10, 10 * 1000); } -int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) +int enetc_mdio_write_c22(struct mii_bus *bus, int phy_id, int regnum, + u16 value) { struct enetc_mdio_priv *mdio_priv = bus->priv; u32 mdio_ctl, mdio_cfg; @@ -63,14 +64,39 @@ int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) int ret; mdio_cfg = ENETC_EMDIO_CFG; - if (regnum & MII_ADDR_C45) { - dev_addr = (regnum >> 16) & 0x1f; - mdio_cfg |= MDIO_CFG_ENC45; - } else { - /* clause 22 (ie 1G) */ - dev_addr = regnum & 0x1f; - mdio_cfg &= ~MDIO_CFG_ENC45; - } + dev_addr = regnum & 0x1f; + mdio_cfg &= ~MDIO_CFG_ENC45; + + enetc_mdio_wr(mdio_priv, ENETC_MDIO_CFG, mdio_cfg); + + ret = enetc_mdio_wait_complete(mdio_priv); + if (ret) + return ret; + + /* set port and dev addr */ + mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); + enetc_mdio_wr(mdio_priv, ENETC_MDIO_CTL, mdio_ctl); + + /* write the value */ + enetc_mdio_wr(mdio_priv, ENETC_MDIO_DATA, value); + + ret = enetc_mdio_wait_complete(mdio_priv); + if (ret) + return ret; + + return 0; +} +EXPORT_SYMBOL_GPL(enetc_mdio_write_c22); + +int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id, int dev_addr, + int regnum, u16 value) +{ + struct enetc_mdio_priv *mdio_priv = bus->priv; + u32 mdio_ctl, mdio_cfg; + int ret; + + mdio_cfg = ENETC_EMDIO_CFG; + mdio_cfg |= MDIO_CFG_ENC45; enetc_mdio_wr(mdio_priv, ENETC_MDIO_CFG, mdio_cfg); @@ -83,13 +109,11 @@ int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) enetc_mdio_wr(mdio_priv, ENETC_MDIO_CTL, mdio_ctl); /* set the register address */ - if (regnum & MII_ADDR_C45) { - enetc_mdio_wr(mdio_priv, ENETC_MDIO_ADDR, regnum & 0xffff); + enetc_mdio_wr(mdio_priv, ENETC_MDIO_ADDR, regnum & 0xffff); - ret = enetc_mdio_wait_complete(mdio_priv); - if (ret) - return ret; - } + ret = enetc_mdio_wait_complete(mdio_priv); + if (ret) + return ret; /* write the value */ enetc_mdio_wr(mdio_priv, ENETC_MDIO_DATA, value); @@ -100,9 +124,9 @@ int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) return 0; } -EXPORT_SYMBOL_GPL(enetc_mdio_write); +EXPORT_SYMBOL_GPL(enetc_mdio_write_c45); -int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +int enetc_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum) { struct enetc_mdio_priv *mdio_priv = bus->priv; u32 mdio_ctl, mdio_cfg; @@ -110,14 +134,51 @@ int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) int ret; mdio_cfg = ENETC_EMDIO_CFG; - if (regnum & MII_ADDR_C45) { - dev_addr = (regnum >> 16) & 0x1f; - mdio_cfg |= MDIO_CFG_ENC45; - } else { - dev_addr = regnum & 0x1f; - mdio_cfg &= ~MDIO_CFG_ENC45; + dev_addr = regnum & 0x1f; + mdio_cfg &= ~MDIO_CFG_ENC45; + + enetc_mdio_wr(mdio_priv, ENETC_MDIO_CFG, mdio_cfg); + + ret = enetc_mdio_wait_complete(mdio_priv); + if (ret) + return ret; + + /* set port and device addr */ + mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); + enetc_mdio_wr(mdio_priv, ENETC_MDIO_CTL, mdio_ctl); + + /* initiate the read */ + enetc_mdio_wr(mdio_priv, ENETC_MDIO_CTL, mdio_ctl | MDIO_CTL_READ); + + ret = enetc_mdio_wait_complete(mdio_priv); + if (ret) + return ret; + + /* return all Fs if nothing was there */ + if (enetc_mdio_rd(mdio_priv, ENETC_MDIO_CFG) & MDIO_CFG_RD_ER) { + dev_dbg(&bus->dev, + "Error while reading PHY%d reg at %d.%d\n", + phy_id, dev_addr, regnum); + return 0xffff; } + value = enetc_mdio_rd(mdio_priv, ENETC_MDIO_DATA) & 0xffff; + + return value; +} +EXPORT_SYMBOL_GPL(enetc_mdio_read_c22); + +int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id, int dev_addr, + int regnum) +{ + struct enetc_mdio_priv *mdio_priv = bus->priv; + u32 mdio_ctl, mdio_cfg; + u16 value; + int ret; + + mdio_cfg = ENETC_EMDIO_CFG; + mdio_cfg |= MDIO_CFG_ENC45; + enetc_mdio_wr(mdio_priv, ENETC_MDIO_CFG, mdio_cfg); ret = enetc_mdio_wait_complete(mdio_priv); @@ -129,13 +190,11 @@ int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) enetc_mdio_wr(mdio_priv, ENETC_MDIO_CTL, mdio_ctl); /* set the register address */ - if (regnum & MII_ADDR_C45) { - enetc_mdio_wr(mdio_priv, ENETC_MDIO_ADDR, regnum & 0xffff); + enetc_mdio_wr(mdio_priv, ENETC_MDIO_ADDR, regnum & 0xffff); - ret = enetc_mdio_wait_complete(mdio_priv); - if (ret) - return ret; - } + ret = enetc_mdio_wait_complete(mdio_priv); + if (ret) + return ret; /* initiate the read */ enetc_mdio_wr(mdio_priv, ENETC_MDIO_CTL, mdio_ctl | MDIO_CTL_READ); @@ -156,7 +215,7 @@ int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) return value; } -EXPORT_SYMBOL_GPL(enetc_mdio_read); +EXPORT_SYMBOL_GPL(enetc_mdio_read_c45); struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c index dafb26f81f95..a1b595bd7993 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -39,8 +39,10 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev, } bus->name = ENETC_MDIO_BUS_NAME; - bus->read = enetc_mdio_read; - bus->write = enetc_mdio_write; + bus->read = enetc_mdio_read_c22; + bus->write = enetc_mdio_write_c22; + bus->read_c45 = enetc_mdio_read_c45; + bus->write_c45 = enetc_mdio_write_c45; bus->parent = dev; mdio_priv = bus->priv; mdio_priv->hw = hw; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 9f6c4f5c0a6c..bc012deedab4 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -848,8 +848,10 @@ static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) return -ENOMEM; bus->name = "Freescale ENETC MDIO Bus"; - bus->read = enetc_mdio_read; - bus->write = enetc_mdio_write; + bus->read = enetc_mdio_read_c22; + bus->write = enetc_mdio_write_c22; + bus->read_c45 = enetc_mdio_read_c45; + bus->write_c45 = enetc_mdio_write_c45; bus->parent = dev; mdio_priv = bus->priv; mdio_priv->hw = &pf->si->hw; @@ -885,8 +887,10 @@ static int enetc_imdio_create(struct enetc_pf *pf) return -ENOMEM; bus->name = "Freescale ENETC internal MDIO Bus"; - bus->read = enetc_mdio_read; - bus->write = enetc_mdio_write; + bus->read = enetc_mdio_read_c22; + bus->write = enetc_mdio_write_c22; + bus->read_c45 = enetc_mdio_read_c45; + bus->write_c45 = enetc_mdio_write_c45; bus->parent = dev; bus->phy_mask = ~0; mdio_priv = bus->priv; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 644f3c963730..e6238e53940d 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1987,47 +1987,74 @@ static int fec_enet_mdio_wait(struct fec_enet_private *fep) return ret; } -static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) +static int fec_enet_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum) { struct fec_enet_private *fep = bus->priv; struct device *dev = &fep->pdev->dev; int ret = 0, frame_start, frame_addr, frame_op; - bool is_c45 = !!(regnum & MII_ADDR_C45); ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; - if (is_c45) { - frame_start = FEC_MMFR_ST_C45; + /* C22 read */ + frame_op = FEC_MMFR_OP_READ; + frame_start = FEC_MMFR_ST; + frame_addr = regnum; - /* write address */ - frame_addr = (regnum >> 16); - writel(frame_start | FEC_MMFR_OP_ADDR_WRITE | - FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | - FEC_MMFR_TA | (regnum & 0xFFFF), - fep->hwp + FEC_MII_DATA); + /* start a read op */ + writel(frame_start | frame_op | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | + FEC_MMFR_TA, fep->hwp + FEC_MII_DATA); - /* wait for end of transfer */ - ret = fec_enet_mdio_wait(fep); - if (ret) { - netdev_err(fep->netdev, "MDIO address write timeout\n"); - goto out; - } + /* wait for end of transfer */ + ret = fec_enet_mdio_wait(fep); + if (ret) { + netdev_err(fep->netdev, "MDIO read timeout\n"); + goto out; + } - frame_op = FEC_MMFR_OP_READ_C45; + ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); - } else { - /* C22 read */ - frame_op = FEC_MMFR_OP_READ; - frame_start = FEC_MMFR_ST; - frame_addr = regnum; +out: + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; +} + +static int fec_enet_mdio_read_c45(struct mii_bus *bus, int mii_id, + int devad, int regnum) +{ + struct fec_enet_private *fep = bus->priv; + struct device *dev = &fep->pdev->dev; + int ret = 0, frame_start, frame_op; + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) + return ret; + + frame_start = FEC_MMFR_ST_C45; + + /* write address */ + writel(frame_start | FEC_MMFR_OP_ADDR_WRITE | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(devad) | + FEC_MMFR_TA | (regnum & 0xFFFF), + fep->hwp + FEC_MII_DATA); + + /* wait for end of transfer */ + ret = fec_enet_mdio_wait(fep); + if (ret) { + netdev_err(fep->netdev, "MDIO address write timeout\n"); + goto out; } + frame_op = FEC_MMFR_OP_READ_C45; + /* start a read op */ writel(frame_start | frame_op | - FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | - FEC_MMFR_TA, fep->hwp + FEC_MII_DATA); + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(devad) | + FEC_MMFR_TA, fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ ret = fec_enet_mdio_wait(fep); @@ -2045,45 +2072,69 @@ out: return ret; } -static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, - u16 value) +static int fec_enet_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum, + u16 value) { struct fec_enet_private *fep = bus->priv; struct device *dev = &fep->pdev->dev; int ret, frame_start, frame_addr; - bool is_c45 = !!(regnum & MII_ADDR_C45); ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; - if (is_c45) { - frame_start = FEC_MMFR_ST_C45; + /* C22 write */ + frame_start = FEC_MMFR_ST; + frame_addr = regnum; - /* write address */ - frame_addr = (regnum >> 16); - writel(frame_start | FEC_MMFR_OP_ADDR_WRITE | - FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | - FEC_MMFR_TA | (regnum & 0xFFFF), - fep->hwp + FEC_MII_DATA); + /* start a write op */ + writel(frame_start | FEC_MMFR_OP_WRITE | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | + FEC_MMFR_TA | FEC_MMFR_DATA(value), + fep->hwp + FEC_MII_DATA); - /* wait for end of transfer */ - ret = fec_enet_mdio_wait(fep); - if (ret) { - netdev_err(fep->netdev, "MDIO address write timeout\n"); - goto out; - } - } else { - /* C22 write */ - frame_start = FEC_MMFR_ST; - frame_addr = regnum; + /* wait for end of transfer */ + ret = fec_enet_mdio_wait(fep); + if (ret) + netdev_err(fep->netdev, "MDIO write timeout\n"); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; +} + +static int fec_enet_mdio_write_c45(struct mii_bus *bus, int mii_id, + int devad, int regnum, u16 value) +{ + struct fec_enet_private *fep = bus->priv; + struct device *dev = &fep->pdev->dev; + int ret, frame_start; + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) + return ret; + + frame_start = FEC_MMFR_ST_C45; + + /* write address */ + writel(frame_start | FEC_MMFR_OP_ADDR_WRITE | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(devad) | + FEC_MMFR_TA | (regnum & 0xFFFF), + fep->hwp + FEC_MII_DATA); + + /* wait for end of transfer */ + ret = fec_enet_mdio_wait(fep); + if (ret) { + netdev_err(fep->netdev, "MDIO address write timeout\n"); + goto out; } /* start a write op */ writel(frame_start | FEC_MMFR_OP_WRITE | - FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | - FEC_MMFR_TA | FEC_MMFR_DATA(value), - fep->hwp + FEC_MII_DATA); + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(devad) | + FEC_MMFR_TA | FEC_MMFR_DATA(value), + fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ ret = fec_enet_mdio_wait(fep); @@ -2381,8 +2432,10 @@ static int fec_enet_mii_init(struct platform_device *pdev) } fep->mii_bus->name = "fec_enet_mii_bus"; - fep->mii_bus->read = fec_enet_mdio_read; - fep->mii_bus->write = fec_enet_mdio_write; + fep->mii_bus->read = fec_enet_mdio_read_c22; + fep->mii_bus->write = fec_enet_mdio_write_c22; + fep->mii_bus->read_c45 = fec_enet_mdio_read_c45; + fep->mii_bus->write_c45 = fec_enet_mdio_write_c45; snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", pdev->name, fep->dev_id + 1); fep->mii_bus->priv = fep; diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index d7d39a58cd80..a13b4ba4d6e1 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -128,30 +128,49 @@ static int xgmac_wait_until_done(struct device *dev, return 0; } -/* - * Write value to the PHY for this device to the register at regnum,waiting - * until the write is done before it returns. All PHY configuration has to be - * done through the TSEC1 MIIM regs. - */ -static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) +static int xgmac_mdio_write_c22(struct mii_bus *bus, int phy_id, int regnum, + u16 value) { struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; struct tgec_mdio_controller __iomem *regs = priv->mdio_base; - uint16_t dev_addr; + bool endian = priv->is_little_endian; + u16 dev_addr = regnum & 0x1f; u32 mdio_ctl, mdio_stat; int ret; + + mdio_stat = xgmac_read32(®s->mdio_stat, endian); + mdio_stat &= ~MDIO_STAT_ENC; + xgmac_write32(mdio_stat, ®s->mdio_stat, endian); + + ret = xgmac_wait_until_free(&bus->dev, regs, endian); + if (ret) + return ret; + + /* Set the port and dev addr */ + mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); + xgmac_write32(mdio_ctl, ®s->mdio_ctl, endian); + + /* Write the value to the register */ + xgmac_write32(MDIO_DATA(value), ®s->mdio_data, endian); + + ret = xgmac_wait_until_done(&bus->dev, regs, endian); + if (ret) + return ret; + + return 0; +} + +static int xgmac_mdio_write_c45(struct mii_bus *bus, int phy_id, int dev_addr, + int regnum, u16 value) +{ + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; bool endian = priv->is_little_endian; + u32 mdio_ctl, mdio_stat; + int ret; mdio_stat = xgmac_read32(®s->mdio_stat, endian); - if (regnum & MII_ADDR_C45) { - /* Clause 45 (ie 10G) */ - dev_addr = (regnum >> 16) & 0x1f; - mdio_stat |= MDIO_STAT_ENC; - } else { - /* Clause 22 (ie 1G) */ - dev_addr = regnum & 0x1f; - mdio_stat &= ~MDIO_STAT_ENC; - } + mdio_stat |= MDIO_STAT_ENC; xgmac_write32(mdio_stat, ®s->mdio_stat, endian); @@ -164,13 +183,11 @@ static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 val xgmac_write32(mdio_ctl, ®s->mdio_ctl, endian); /* Set the register address */ - if (regnum & MII_ADDR_C45) { - xgmac_write32(regnum & 0xffff, ®s->mdio_addr, endian); + xgmac_write32(regnum & 0xffff, ®s->mdio_addr, endian); - ret = xgmac_wait_until_free(&bus->dev, regs, endian); - if (ret) - return ret; - } + ret = xgmac_wait_until_free(&bus->dev, regs, endian); + if (ret) + return ret; /* Write the value to the register */ xgmac_write32(MDIO_DATA(value), ®s->mdio_data, endian); @@ -182,31 +199,82 @@ static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 val return 0; } -/* - * Reads from register regnum in the PHY for device dev, returning the value. +/* Reads from register regnum in the PHY for device dev, returning the value. * Clears miimcom first. All PHY configuration has to be done through the * TSEC1 MIIM regs. */ -static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +static int xgmac_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum) { struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; struct tgec_mdio_controller __iomem *regs = priv->mdio_base; + bool endian = priv->is_little_endian; + u16 dev_addr = regnum & 0x1f; unsigned long flags; - uint16_t dev_addr; uint32_t mdio_stat; uint32_t mdio_ctl; int ret; - bool endian = priv->is_little_endian; mdio_stat = xgmac_read32(®s->mdio_stat, endian); - if (regnum & MII_ADDR_C45) { - dev_addr = (regnum >> 16) & 0x1f; - mdio_stat |= MDIO_STAT_ENC; + mdio_stat &= ~MDIO_STAT_ENC; + xgmac_write32(mdio_stat, ®s->mdio_stat, endian); + + ret = xgmac_wait_until_free(&bus->dev, regs, endian); + if (ret) + return ret; + + /* Set the Port and Device Addrs */ + mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); + xgmac_write32(mdio_ctl, ®s->mdio_ctl, endian); + + if (priv->has_a009885) + /* Once the operation completes, i.e. MDIO_STAT_BSY clears, we + * must read back the data register within 16 MDC cycles. + */ + local_irq_save(flags); + + /* Initiate the read */ + xgmac_write32(mdio_ctl | MDIO_CTL_READ, ®s->mdio_ctl, endian); + + ret = xgmac_wait_until_done(&bus->dev, regs, endian); + if (ret) + goto irq_restore; + + /* Return all Fs if nothing was there */ + if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) && + !priv->has_a011043) { + dev_dbg(&bus->dev, + "Error while reading PHY%d reg at %d.%d\n", + phy_id, dev_addr, regnum); + ret = 0xffff; } else { - dev_addr = regnum & 0x1f; - mdio_stat &= ~MDIO_STAT_ENC; + ret = xgmac_read32(®s->mdio_data, endian) & 0xffff; + dev_dbg(&bus->dev, "read %04x\n", ret); } +irq_restore: + if (priv->has_a009885) + local_irq_restore(flags); + + return ret; +} + +/* Reads from register regnum in the PHY for device dev, returning the value. + * Clears miimcom first. All PHY configuration has to be done through the + * TSEC1 MIIM regs. + */ +static int xgmac_mdio_read_c45(struct mii_bus *bus, int phy_id, int dev_addr, + int regnum) +{ + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; + bool endian = priv->is_little_endian; + u32 mdio_stat, mdio_ctl; + unsigned long flags; + int ret; + + mdio_stat = xgmac_read32(®s->mdio_stat, endian); + mdio_stat |= MDIO_STAT_ENC; + xgmac_write32(mdio_stat, ®s->mdio_stat, endian); ret = xgmac_wait_until_free(&bus->dev, regs, endian); @@ -218,13 +286,11 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) xgmac_write32(mdio_ctl, ®s->mdio_ctl, endian); /* Set the register address */ - if (regnum & MII_ADDR_C45) { - xgmac_write32(regnum & 0xffff, ®s->mdio_addr, endian); + xgmac_write32(regnum & 0xffff, ®s->mdio_addr, endian); - ret = xgmac_wait_until_free(&bus->dev, regs, endian); - if (ret) - return ret; - } + ret = xgmac_wait_until_free(&bus->dev, regs, endian); + if (ret) + return ret; if (priv->has_a009885) /* Once the operation completes, i.e. MDIO_STAT_BSY clears, we @@ -326,10 +392,11 @@ static int xgmac_mdio_probe(struct platform_device *pdev) return -ENOMEM; bus->name = "Freescale XGMAC MDIO Bus"; - bus->read = xgmac_mdio_read; - bus->write = xgmac_mdio_write; + bus->read = xgmac_mdio_read_c22; + bus->write = xgmac_mdio_write_c22; + bus->read_c45 = xgmac_mdio_read_c45; + bus->write_c45 = xgmac_mdio_write_c45; bus->parent = &pdev->dev; - bus->probe_capabilities = MDIOBUS_C22_C45; snprintf(bus->id, MII_BUS_ID_SIZE, "%pa", &res->start); priv = bus->priv; diff --git a/drivers/net/ethernet/fungible/funeth/Kconfig b/drivers/net/ethernet/fungible/funeth/Kconfig index c72ad9386400..e742e7663449 100644 --- a/drivers/net/ethernet/fungible/funeth/Kconfig +++ b/drivers/net/ethernet/fungible/funeth/Kconfig @@ -5,7 +5,7 @@ config FUN_ETH tristate "Fungible Ethernet device driver" - depends on PCI && PCI_MSI + depends on PCI_MSI depends on TLS && TLS_DEVICE || TLS_DEVICE=n select NET_DEVLINK select FUN_CORE diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 740850b64aff..5df19c604d09 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -554,11 +554,11 @@ static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb) argv4.package.count = 1; argv4.package.elements = &obj_args; - obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), - &hns_dsaf_acpi_dsm_guid, 0, - HNS_OP_GET_PORT_TYPE_FUNC, &argv4); - - if (!obj || obj->type != ACPI_TYPE_INTEGER) + obj = acpi_evaluate_dsm_typed(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, + HNS_OP_GET_PORT_TYPE_FUNC, &argv4, + ACPI_TYPE_INTEGER); + if (!obj) return phy_if; phy_if = obj->integer.value ? @@ -601,11 +601,11 @@ static int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt) argv4.package.count = 1; argv4.package.elements = &obj_args; - obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), - &hns_dsaf_acpi_dsm_guid, 0, - HNS_OP_GET_SFP_STAT_FUNC, &argv4); - - if (!obj || obj->type != ACPI_TYPE_INTEGER) + obj = acpi_evaluate_dsm_typed(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, + HNS_OP_GET_SFP_STAT_FUNC, &argv4, + ACPI_TYPE_INTEGER); + if (!obj) return -ENODEV; *sfp_prsnt = obj->integer.value; diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index c2ae1b4f9a5f..9232caaf0bdc 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -206,7 +206,7 @@ static void hns_mdio_cmd_write(struct hns_mdio_device *mdio_dev, } /** - * hns_mdio_write - access phy register + * hns_mdio_write_c22 - access phy register * @bus: mdio bus * @phy_id: phy id * @regnum: register num @@ -214,21 +214,19 @@ static void hns_mdio_cmd_write(struct hns_mdio_device *mdio_dev, * * Return 0 on success, negative on failure */ -static int hns_mdio_write(struct mii_bus *bus, - int phy_id, int regnum, u16 data) +static int hns_mdio_write_c22(struct mii_bus *bus, + int phy_id, int regnum, u16 data) { - int ret; struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; - u8 devad = ((regnum >> 16) & 0x1f); - u8 is_c45 = !!(regnum & MII_ADDR_C45); u16 reg = (u16)(regnum & 0xffff); - u8 op; u16 cmd_reg_cfg; + int ret; + u8 op; dev_dbg(&bus->dev, "mdio write %s,base is %p\n", bus->id, mdio_dev->vbase); - dev_dbg(&bus->dev, "phy id=%d, is_c45=%d, devad=%d, reg=%#x, write data=%d\n", - phy_id, is_c45, devad, reg, data); + dev_dbg(&bus->dev, "phy id=%d, reg=%#x, write data=%d\n", + phy_id, reg, data); /* wait for ready */ ret = hns_mdio_wait_ready(bus); @@ -237,58 +235,91 @@ static int hns_mdio_write(struct mii_bus *bus, return ret; } - if (!is_c45) { - cmd_reg_cfg = reg; - op = MDIO_C22_WRITE; - } else { - /* config the cmd-reg to write addr*/ - MDIO_SET_REG_FIELD(mdio_dev, MDIO_ADDR_REG, MDIO_ADDR_DATA_M, - MDIO_ADDR_DATA_S, reg); + cmd_reg_cfg = reg; + op = MDIO_C22_WRITE; - hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_WRITE_ADDR, phy_id, devad); + MDIO_SET_REG_FIELD(mdio_dev, MDIO_WDATA_REG, MDIO_WDATA_DATA_M, + MDIO_WDATA_DATA_S, data); - /* check for read or write opt is finished */ - ret = hns_mdio_wait_ready(bus); - if (ret) { - dev_err(&bus->dev, "MDIO bus is busy\n"); - return ret; - } + hns_mdio_cmd_write(mdio_dev, false, op, phy_id, cmd_reg_cfg); + + return 0; +} + +/** + * hns_mdio_write_c45 - access phy register + * @bus: mdio bus + * @phy_id: phy id + * @devad: device address to read + * @regnum: register num + * @data: register value + * + * Return 0 on success, negative on failure + */ +static int hns_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad, + int regnum, u16 data) +{ + struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; + u16 reg = (u16)(regnum & 0xffff); + u16 cmd_reg_cfg; + int ret; + u8 op; + + dev_dbg(&bus->dev, "mdio write %s,base is %p\n", + bus->id, mdio_dev->vbase); + dev_dbg(&bus->dev, "phy id=%d, devad=%d, reg=%#x, write data=%d\n", + phy_id, devad, reg, data); + + /* wait for ready */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + /* config the cmd-reg to write addr*/ + MDIO_SET_REG_FIELD(mdio_dev, MDIO_ADDR_REG, MDIO_ADDR_DATA_M, + MDIO_ADDR_DATA_S, reg); - /* config the data needed writing */ - cmd_reg_cfg = devad; - op = MDIO_C45_WRITE_DATA; + hns_mdio_cmd_write(mdio_dev, true, MDIO_C45_WRITE_ADDR, phy_id, devad); + + /* check for read or write opt is finished */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; } + /* config the data needed writing */ + cmd_reg_cfg = devad; + op = MDIO_C45_WRITE_DATA; + MDIO_SET_REG_FIELD(mdio_dev, MDIO_WDATA_REG, MDIO_WDATA_DATA_M, MDIO_WDATA_DATA_S, data); - hns_mdio_cmd_write(mdio_dev, is_c45, op, phy_id, cmd_reg_cfg); + hns_mdio_cmd_write(mdio_dev, true, op, phy_id, cmd_reg_cfg); return 0; } /** - * hns_mdio_read - access phy register + * hns_mdio_read_c22 - access phy register * @bus: mdio bus * @phy_id: phy id * @regnum: register num * * Return phy register value */ -static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +static int hns_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum) { - int ret; - u16 reg_val; - u8 devad = ((regnum >> 16) & 0x1f); - u8 is_c45 = !!(regnum & MII_ADDR_C45); - u16 reg = (u16)(regnum & 0xffff); struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; + u16 reg = (u16)(regnum & 0xffff); + u16 reg_val; + int ret; dev_dbg(&bus->dev, "mdio read %s,base is %p\n", bus->id, mdio_dev->vbase); - dev_dbg(&bus->dev, "phy id=%d, is_c45=%d, devad=%d, reg=%#x!\n", - phy_id, is_c45, devad, reg); + dev_dbg(&bus->dev, "phy id=%d, reg=%#x!\n", phy_id, reg); /* Step 1: wait for ready */ ret = hns_mdio_wait_ready(bus); @@ -297,29 +328,74 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) return ret; } - if (!is_c45) { - hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C22_READ, phy_id, reg); - } else { - MDIO_SET_REG_FIELD(mdio_dev, MDIO_ADDR_REG, MDIO_ADDR_DATA_M, - MDIO_ADDR_DATA_S, reg); + hns_mdio_cmd_write(mdio_dev, false, MDIO_C22_READ, phy_id, reg); - /* Step 2; config the cmd-reg to write addr*/ - hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_WRITE_ADDR, phy_id, devad); + /* Step 2: waiting for MDIO_COMMAND_REG 's mdio_start==0,*/ + /* check for read or write opt is finished */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } - /* Step 3: check for read or write opt is finished */ - ret = hns_mdio_wait_ready(bus); - if (ret) { - dev_err(&bus->dev, "MDIO bus is busy\n"); - return ret; - } + reg_val = MDIO_GET_REG_BIT(mdio_dev, MDIO_STA_REG, MDIO_STATE_STA_B); + if (reg_val) { + dev_err(&bus->dev, " ERROR! MDIO Read failed!\n"); + return -EBUSY; + } - hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_READ, phy_id, devad); + /* Step 3; get out data*/ + reg_val = (u16)MDIO_GET_REG_FIELD(mdio_dev, MDIO_RDATA_REG, + MDIO_RDATA_DATA_M, MDIO_RDATA_DATA_S); + + return reg_val; +} + +/** + * hns_mdio_read_c45 - access phy register + * @bus: mdio bus + * @phy_id: phy id + * @devad: device address to read + * @regnum: register num + * + * Return phy register value + */ +static int hns_mdio_read_c45(struct mii_bus *bus, int phy_id, int devad, + int regnum) +{ + struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; + u16 reg = (u16)(regnum & 0xffff); + u16 reg_val; + int ret; + + dev_dbg(&bus->dev, "mdio read %s,base is %p\n", + bus->id, mdio_dev->vbase); + dev_dbg(&bus->dev, "phy id=%d, devad=%d, reg=%#x!\n", + phy_id, devad, reg); + + /* Step 1: wait for ready */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + MDIO_SET_REG_FIELD(mdio_dev, MDIO_ADDR_REG, MDIO_ADDR_DATA_M, + MDIO_ADDR_DATA_S, reg); + + /* Step 2; config the cmd-reg to write addr*/ + hns_mdio_cmd_write(mdio_dev, true, MDIO_C45_WRITE_ADDR, phy_id, devad); + + /* Step 3: check for read or write opt is finished */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; } - /* Step 5: waiting for MDIO_COMMAND_REG's mdio_start==0,*/ + hns_mdio_cmd_write(mdio_dev, true, MDIO_C45_READ, phy_id, devad); + + /* Step 5: waiting for MDIO_COMMAND_REG 's mdio_start==0,*/ /* check for read or write opt is finished */ ret = hns_mdio_wait_ready(bus); if (ret) { @@ -438,8 +514,10 @@ static int hns_mdio_probe(struct platform_device *pdev) } new_bus->name = MDIO_BUS_NAME; - new_bus->read = hns_mdio_read; - new_bus->write = hns_mdio_write; + new_bus->read = hns_mdio_read_c22; + new_bus->write = hns_mdio_write_c22; + new_bus->read_c45 = hns_mdio_read_c45; + new_bus->write_c45 = hns_mdio_write_c45; new_bus->reset = hns_mdio_reset; new_bus->priv = mdio_dev; new_bus->parent = &pdev->dev; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 3facb55b7161..a3c84bf05e44 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -337,6 +337,9 @@ config ICE_HWTS the PTP clock driver precise cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE). +config ICE_GNSS + def_bool GNSS = y || GNSS = ICE + config FM10K tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support" default n diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 59e82d131d88..721f86fd5802 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -110,9 +110,9 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = { static int e1000_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { + u32 speed, supported, advertising, lp_advertising, lpa_t; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 speed, supported, advertising; if (hw->phy.media_type == e1000_media_type_copper) { supported = (SUPPORTED_10baseT_Half | @@ -120,7 +120,9 @@ static int e1000_get_link_ksettings(struct net_device *netdev, SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | SUPPORTED_1000baseT_Full | + SUPPORTED_Asym_Pause | SUPPORTED_Autoneg | + SUPPORTED_Pause | SUPPORTED_TP); if (hw->phy.type == e1000_phy_ife) supported &= ~SUPPORTED_1000baseT_Full; @@ -192,10 +194,16 @@ static int e1000_get_link_ksettings(struct net_device *netdev, if (hw->phy.media_type != e1000_media_type_copper) cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; + lpa_t = mii_stat1000_to_ethtool_lpa_t(adapter->phy_regs.stat1000); + lp_advertising = lpa_t | + mii_lpa_to_ethtool_lpa_t(adapter->phy_regs.lpa); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, supported); ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, advertising); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising, + lp_advertising); return 0; } diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 060b263348ce..08c3d477dd6f 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -2,6 +2,7 @@ /* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "e1000.h" +#include <linux/ethtool.h> static s32 e1000_wait_autoneg(struct e1000_hw *hw); static s32 e1000_access_phy_wakeup_reg_bm(struct e1000_hw *hw, u32 offset, @@ -1011,6 +1012,8 @@ static s32 e1000_phy_setup_autoneg(struct e1000_hw *hw) */ mii_autoneg_adv_reg &= ~(ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP); + phy->autoneg_advertised &= + ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); break; case e1000_fc_rx_pause: /* Rx Flow control is enabled, and Tx Flow control is @@ -1024,6 +1027,8 @@ static s32 e1000_phy_setup_autoneg(struct e1000_hw *hw) */ mii_autoneg_adv_reg |= (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP); + phy->autoneg_advertised |= + (ADVERTISED_Pause | ADVERTISED_Asym_Pause); break; case e1000_fc_tx_pause: /* Tx Flow control is enabled, and Rx Flow control is @@ -1031,6 +1036,8 @@ static s32 e1000_phy_setup_autoneg(struct e1000_hw *hw) */ mii_autoneg_adv_reg |= ADVERTISE_PAUSE_ASYM; mii_autoneg_adv_reg &= ~ADVERTISE_PAUSE_CAP; + phy->autoneg_advertised |= ADVERTISED_Asym_Pause; + phy->autoneg_advertised &= ~ADVERTISED_Pause; break; case e1000_fc_full: /* Flow control (both Rx and Tx) is enabled by a software @@ -1038,6 +1045,8 @@ static s32 e1000_phy_setup_autoneg(struct e1000_hw *hw) */ mii_autoneg_adv_reg |= (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP); + phy->autoneg_advertised |= + (ADVERTISED_Pause | ADVERTISED_Asym_Pause); break; default: e_dbg("Flow control param set incorrectly\n"); diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 9183d480b70b..f269952d207d 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -28,6 +28,7 @@ ice-y := ice_main.o \ ice_flow.o \ ice_idc.o \ ice_devlink.o \ + ice_ddp.o \ ice_fw_update.o \ ice_lag.o \ ice_ethtool.o \ @@ -42,8 +43,8 @@ ice-$(CONFIG_PCI_IOV) += \ ice_vf_vsi_vlan_ops.o \ ice_vf_lib.o ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o -ice-$(CONFIG_TTY) += ice_gnss.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o +ice-$(CONFIG_ICE_GNSS) += ice_gnss.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2f0b604abc5e..ae93ae488bc2 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -39,6 +39,7 @@ #include <linux/avf/virtchnl.h> #include <linux/cpu_rmap.h> #include <linux/dim.h> +#include <linux/gnss.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_gact.h> @@ -565,9 +566,8 @@ struct ice_pf { struct mutex adev_mutex; /* lock to protect aux device access */ u32 msg_enable; struct ice_ptp ptp; - struct tty_driver *ice_gnss_tty_driver; - struct tty_port *gnss_tty_port[ICE_GNSS_TTY_MINOR_DEVICES]; - struct gnss_serial *gnss_serial[ICE_GNSS_TTY_MINOR_DEVICES]; + struct gnss_serial *gnss_serial; + struct gnss_device *gnss_dev; u16 num_rdma_msix; /* Total MSIX vectors for RDMA driver */ u16 rdma_base_vector; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 958c1e435232..838d9b274d68 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1659,14 +1659,24 @@ struct ice_aqc_lldp_get_mib { #define ICE_AQ_LLDP_TX_ACTIVE 0 #define ICE_AQ_LLDP_TX_SUSPENDED 1 #define ICE_AQ_LLDP_TX_FLUSHED 3 +/* DCBX mode */ +#define ICE_AQ_LLDP_DCBX_M GENMASK(7, 6) +#define ICE_AQ_LLDP_DCBX_NA 0 +#define ICE_AQ_LLDP_DCBX_CEE 1 +#define ICE_AQ_LLDP_DCBX_IEEE 2 + + u8 state; +#define ICE_AQ_LLDP_MIB_CHANGE_STATE_M BIT(0) +#define ICE_AQ_LLDP_MIB_CHANGE_EXECUTED 0 +#define ICE_AQ_LLDP_MIB_CHANGE_PENDING 1 + /* The following bytes are reserved for the Get LLDP MIB command (0x0A00) * and in the LLDP MIB Change Event (0x0A01). They are valid for the * Get LLDP MIB (0x0A00) response only. */ - u8 reserved1; __le16 local_len; __le16 remote_len; - u8 reserved2[2]; + u8 reserved[2]; __le32 addr_high; __le32 addr_low; }; @@ -1677,6 +1687,9 @@ struct ice_aqc_lldp_set_mib_change { u8 command; #define ICE_AQ_LLDP_MIB_UPDATE_ENABLE 0x0 #define ICE_AQ_LLDP_MIB_UPDATE_DIS 0x1 +#define ICE_AQ_LLDP_MIB_PENDING_M BIT(1) +#define ICE_AQ_LLDP_MIB_PENDING_DISABLE 0 +#define ICE_AQ_LLDP_MIB_PENDING_ENABLE 1 u8 reserved[15]; }; @@ -2329,6 +2342,7 @@ enum ice_adminq_opc { ice_aqc_opc_lldp_set_local_mib = 0x0A08, ice_aqc_opc_lldp_stop_start_specific_agent = 0x0A09, ice_aqc_opc_lldp_filter_ctrl = 0x0A0A, + ice_aqc_opc_lldp_execute_pending_mib = 0x0A0B, /* RSS commands */ ice_aqc_opc_set_rss_key = 0x0B02, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index d02b55b6aa9c..f5842ff42bc7 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5504,6 +5504,19 @@ ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) } /** + * ice_lldp_execute_pending_mib - execute LLDP pending MIB request + * @hw: pointer to HW struct + */ +int ice_lldp_execute_pending_mib(struct ice_hw *hw) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_execute_pending_mib); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** * ice_fw_supports_report_dflt_cfg * @hw: pointer to the hardware structure * diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 4c6a0b5c9304..98aa8d124730 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -122,7 +122,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update); int ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, - enum ice_fc_mode fc); + enum ice_fc_mode req_mode); bool ice_phy_caps_equals_cfg(struct ice_aqc_get_phy_caps_data *caps, struct ice_aqc_set_phy_cfg_data *cfg); @@ -221,6 +221,7 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw); int ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add); +int ice_lldp_execute_pending_mib(struct ice_hw *hw); int ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, u16 bus_addr, __le16 addr, u8 params, u8 *data, diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 6be02f9b0b8c..776c1ff6e265 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -73,6 +73,9 @@ ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update, if (!ena_update) cmd->command |= ICE_AQ_LLDP_MIB_UPDATE_DIS; + else + cmd->command |= FIELD_PREP(ICE_AQ_LLDP_MIB_PENDING_M, + ICE_AQ_LLDP_MIB_PENDING_ENABLE); return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } @@ -964,6 +967,42 @@ int ice_get_dcb_cfg(struct ice_port_info *pi) } /** + * ice_get_dcb_cfg_from_mib_change + * @pi: port information structure + * @event: pointer to the admin queue receive event + * + * Set DCB configuration from received MIB Change event + */ +void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi, + struct ice_rq_event_info *event) +{ + struct ice_dcbx_cfg *dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg; + struct ice_aqc_lldp_get_mib *mib; + u8 change_type, dcbx_mode; + + mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw; + + change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type); + if (change_type == ICE_AQ_LLDP_MIB_REMOTE) + dcbx_cfg = &pi->qos_cfg.remote_dcbx_cfg; + + dcbx_mode = FIELD_GET(ICE_AQ_LLDP_DCBX_M, mib->type); + + switch (dcbx_mode) { + case ICE_AQ_LLDP_DCBX_IEEE: + dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_IEEE; + ice_lldp_to_dcb_cfg(event->msg_buf, dcbx_cfg); + break; + + case ICE_AQ_LLDP_DCBX_CEE: + pi->qos_cfg.desired_dcbx_cfg = pi->qos_cfg.local_dcbx_cfg; + ice_cee_to_dcb_cfg((struct ice_aqc_get_cee_dcb_cfg_resp *) + event->msg_buf, pi); + break; + } +} + +/** * ice_init_dcb * @hw: pointer to the HW struct * @enable_mib_change: enable MIB change event diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h index 6abf28a14291..be34650a77d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb.h @@ -144,6 +144,8 @@ ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype, struct ice_dcbx_cfg *dcbcfg); int ice_get_dcb_cfg(struct ice_port_info *pi); int ice_set_dcb_cfg(struct ice_port_info *pi); +void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi, + struct ice_rq_event_info *event); int ice_init_dcb(struct ice_hw *hw, bool enable_mib_change); int ice_query_port_ets(struct ice_port_info *pi, diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 4f24d441c35e..a97b137e21c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -859,7 +859,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) if (err) goto dcb_init_err; - return err; + return 0; dcb_init_err: dev_err(dev, "DCB init failed\n"); @@ -944,6 +944,16 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, } /** + * ice_dcb_is_mib_change_pending - Check if MIB change is pending + * @state: MIB change state + */ +static bool ice_dcb_is_mib_change_pending(u8 state) +{ + return ICE_AQ_LLDP_MIB_CHANGE_PENDING == + FIELD_GET(ICE_AQ_LLDP_MIB_CHANGE_STATE_M, state); +} + +/** * ice_dcb_process_lldp_set_mib_change - Process MIB change * @pf: ptr to ice_pf * @event: pointer to the admin queue receive event @@ -956,6 +966,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct device *dev = ice_pf_to_dev(pf); struct ice_aqc_lldp_get_mib *mib; struct ice_dcbx_cfg tmp_dcbx_cfg; + bool pending_handled = true; bool need_reconfig = false; struct ice_port_info *pi; u8 mib_type; @@ -972,41 +983,58 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, pi = pf->hw.port_info; mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw; + /* Ignore if event is not for Nearest Bridge */ - mib_type = ((mib->type >> ICE_AQ_LLDP_BRID_TYPE_S) & - ICE_AQ_LLDP_BRID_TYPE_M); + mib_type = FIELD_GET(ICE_AQ_LLDP_BRID_TYPE_M, mib->type); dev_dbg(dev, "LLDP event MIB bridge type 0x%x\n", mib_type); if (mib_type != ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID) return; + /* A pending change event contains accurate config information, and + * the FW setting has not been updaed yet, so detect if change is + * pending to determine where to pull config information from + * (FW vs event) + */ + if (ice_dcb_is_mib_change_pending(mib->state)) + pending_handled = false; + /* Check MIB Type and return if event for Remote MIB update */ - mib_type = mib->type & ICE_AQ_LLDP_MIB_TYPE_M; + mib_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type); dev_dbg(dev, "LLDP event mib type %s\n", mib_type ? "remote" : "local"); if (mib_type == ICE_AQ_LLDP_MIB_REMOTE) { /* Update the remote cached instance and return */ - ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE, - ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, - &pi->qos_cfg.remote_dcbx_cfg); - if (ret) { - dev_err(dev, "Failed to get remote DCB config\n"); - return; + if (!pending_handled) { + ice_get_dcb_cfg_from_mib_change(pi, event); + } else { + ret = + ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE, + ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, + &pi->qos_cfg.remote_dcbx_cfg); + if (ret) + dev_dbg(dev, "Failed to get remote DCB config\n"); } + return; } + /* That a DCB change has happened is now determined */ mutex_lock(&pf->tc_mutex); /* store the old configuration */ - tmp_dcbx_cfg = pf->hw.port_info->qos_cfg.local_dcbx_cfg; + tmp_dcbx_cfg = pi->qos_cfg.local_dcbx_cfg; /* Reset the old DCBX configuration data */ memset(&pi->qos_cfg.local_dcbx_cfg, 0, sizeof(pi->qos_cfg.local_dcbx_cfg)); /* Get updated DCBX data from firmware */ - ret = ice_get_dcb_cfg(pf->hw.port_info); - if (ret) { - dev_err(dev, "Failed to get DCB config\n"); - goto out; + if (!pending_handled) { + ice_get_dcb_cfg_from_mib_change(pi, event); + } else { + ret = ice_get_dcb_cfg(pi); + if (ret) { + dev_err(dev, "Failed to get DCB config\n"); + goto out; + } } /* No change detected in DCBX configs */ @@ -1033,11 +1061,17 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, clear_bit(ICE_FLAG_DCB_ENA, pf->flags); } + /* Send Execute Pending MIB Change event if it is a Pending event */ + if (!pending_handled) { + ice_lldp_execute_pending_mib(&pf->hw); + pending_handled = true; + } + rtnl_lock(); /* disable VSIs affected by DCB changes */ ice_dcb_ena_dis_vsi(pf, false, true); - ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); + ret = ice_query_port_ets(pi, &buf, sizeof(buf), NULL); if (ret) { dev_err(dev, "Query Port ETS failed\n"); goto unlock_rtnl; @@ -1052,4 +1086,8 @@ unlock_rtnl: rtnl_unlock(); out: mutex_unlock(&pf->tc_mutex); + + /* Send Execute Pending MIB Change event if it is a Pending event */ + if (!pending_handled) + ice_lldp_execute_pending_mib(&pf->hw); } diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c new file mode 100644 index 000000000000..d71ed210f9c4 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -0,0 +1,1897 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Intel Corporation. */ + +#include "ice_common.h" +#include "ice.h" +#include "ice_ddp.h" + +/* For supporting double VLAN mode, it is necessary to enable or disable certain + * boost tcam entries. The metadata labels names that match the following + * prefixes will be saved to allow enabling double VLAN mode. + */ +#define ICE_DVM_PRE "BOOST_MAC_VLAN_DVM" /* enable these entries */ +#define ICE_SVM_PRE "BOOST_MAC_VLAN_SVM" /* disable these entries */ + +/* To support tunneling entries by PF, the package will append the PF number to + * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc. + */ +#define ICE_TNL_PRE "TNL_" +static const struct ice_tunnel_type_scan tnls[] = { + { TNL_VXLAN, "TNL_VXLAN_PF" }, + { TNL_GENEVE, "TNL_GENEVE_PF" }, + { TNL_LAST, "" } +}; + +/** + * ice_verify_pkg - verify package + * @pkg: pointer to the package buffer + * @len: size of the package buffer + * + * Verifies various attributes of the package file, including length, format + * version, and the requirement of at least one segment. + */ +enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +{ + u32 seg_count; + u32 i; + + if (len < struct_size(pkg, seg_offset, 1)) + return ICE_DDP_PKG_INVALID_FILE; + + if (pkg->pkg_format_ver.major != ICE_PKG_FMT_VER_MAJ || + pkg->pkg_format_ver.minor != ICE_PKG_FMT_VER_MNR || + pkg->pkg_format_ver.update != ICE_PKG_FMT_VER_UPD || + pkg->pkg_format_ver.draft != ICE_PKG_FMT_VER_DFT) + return ICE_DDP_PKG_INVALID_FILE; + + /* pkg must have at least one segment */ + seg_count = le32_to_cpu(pkg->seg_count); + if (seg_count < 1) + return ICE_DDP_PKG_INVALID_FILE; + + /* make sure segment array fits in package length */ + if (len < struct_size(pkg, seg_offset, seg_count)) + return ICE_DDP_PKG_INVALID_FILE; + + /* all segments must fit within length */ + for (i = 0; i < seg_count; i++) { + u32 off = le32_to_cpu(pkg->seg_offset[i]); + struct ice_generic_seg_hdr *seg; + + /* segment header must fit */ + if (len < off + sizeof(*seg)) + return ICE_DDP_PKG_INVALID_FILE; + + seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off); + + /* segment body must fit */ + if (len < off + le32_to_cpu(seg->seg_size)) + return ICE_DDP_PKG_INVALID_FILE; + } + + return ICE_DDP_PKG_SUCCESS; +} + +/** + * ice_free_seg - free package segment pointer + * @hw: pointer to the hardware structure + * + * Frees the package segment pointer in the proper manner, depending on if the + * segment was allocated or just the passed in pointer was stored. + */ +void ice_free_seg(struct ice_hw *hw) +{ + if (hw->pkg_copy) { + devm_kfree(ice_hw_to_dev(hw), hw->pkg_copy); + hw->pkg_copy = NULL; + hw->pkg_size = 0; + } + hw->seg = NULL; +} + +/** + * ice_chk_pkg_version - check package version for compatibility with driver + * @pkg_ver: pointer to a version structure to check + * + * Check to make sure that the package about to be downloaded is compatible with + * the driver. To be compatible, the major and minor components of the package + * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR + * definitions. + */ +static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) +{ + if (pkg_ver->major > ICE_PKG_SUPP_VER_MAJ || + (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ && + pkg_ver->minor > ICE_PKG_SUPP_VER_MNR)) + return ICE_DDP_PKG_FILE_VERSION_TOO_HIGH; + else if (pkg_ver->major < ICE_PKG_SUPP_VER_MAJ || + (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ && + pkg_ver->minor < ICE_PKG_SUPP_VER_MNR)) + return ICE_DDP_PKG_FILE_VERSION_TOO_LOW; + + return ICE_DDP_PKG_SUCCESS; +} + +/** + * ice_pkg_val_buf + * @buf: pointer to the ice buffer + * + * This helper function validates a buffer's header. + */ +struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) +{ + struct ice_buf_hdr *hdr; + u16 section_count; + u16 data_end; + + hdr = (struct ice_buf_hdr *)buf->buf; + /* verify data */ + section_count = le16_to_cpu(hdr->section_count); + if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT) + return NULL; + + data_end = le16_to_cpu(hdr->data_end); + if (data_end < ICE_MIN_S_DATA_END || data_end > ICE_MAX_S_DATA_END) + return NULL; + + return hdr; +} + +/** + * ice_find_buf_table + * @ice_seg: pointer to the ice segment + * + * Returns the address of the buffer table within the ice segment. + */ +static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg) +{ + struct ice_nvm_table *nvms = (struct ice_nvm_table *) + (ice_seg->device_table + le32_to_cpu(ice_seg->device_table_count)); + + return (__force struct ice_buf_table *)(nvms->vers + + le32_to_cpu(nvms->table_count)); +} + +/** + * ice_pkg_enum_buf + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * + * This function will enumerate all the buffers in the ice segment. The first + * call is made with the ice_seg parameter non-NULL; on subsequent calls, + * ice_seg is set to NULL which continues the enumeration. When the function + * returns a NULL pointer, then the end of the buffers has been reached, or an + * unexpected value has been detected (for example an invalid section count or + * an invalid buffer end value). + */ +static struct ice_buf_hdr *ice_pkg_enum_buf(struct ice_seg *ice_seg, + struct ice_pkg_enum *state) +{ + if (ice_seg) { + state->buf_table = ice_find_buf_table(ice_seg); + if (!state->buf_table) + return NULL; + + state->buf_idx = 0; + return ice_pkg_val_buf(state->buf_table->buf_array); + } + + if (++state->buf_idx < le32_to_cpu(state->buf_table->buf_count)) + return ice_pkg_val_buf(state->buf_table->buf_array + + state->buf_idx); + else + return NULL; +} + +/** + * ice_pkg_advance_sect + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * + * This helper function will advance the section within the ice segment, + * also advancing the buffer if needed. + */ +static bool ice_pkg_advance_sect(struct ice_seg *ice_seg, + struct ice_pkg_enum *state) +{ + if (!ice_seg && !state->buf) + return false; + + if (!ice_seg && state->buf) + if (++state->sect_idx < le16_to_cpu(state->buf->section_count)) + return true; + + state->buf = ice_pkg_enum_buf(ice_seg, state); + if (!state->buf) + return false; + + /* start of new buffer, reset section index */ + state->sect_idx = 0; + return true; +} + +/** + * ice_pkg_enum_section + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * @sect_type: section type to enumerate + * + * This function will enumerate all the sections of a particular type in the + * ice segment. The first call is made with the ice_seg parameter non-NULL; + * on subsequent calls, ice_seg is set to NULL which continues the enumeration. + * When the function returns a NULL pointer, then the end of the matching + * sections has been reached. + */ +void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, + u32 sect_type) +{ + u16 offset, size; + + if (ice_seg) + state->type = sect_type; + + if (!ice_pkg_advance_sect(ice_seg, state)) + return NULL; + + /* scan for next matching section */ + while (state->buf->section_entry[state->sect_idx].type != + cpu_to_le32(state->type)) + if (!ice_pkg_advance_sect(NULL, state)) + return NULL; + + /* validate section */ + offset = le16_to_cpu(state->buf->section_entry[state->sect_idx].offset); + if (offset < ICE_MIN_S_OFF || offset > ICE_MAX_S_OFF) + return NULL; + + size = le16_to_cpu(state->buf->section_entry[state->sect_idx].size); + if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) + return NULL; + + /* make sure the section fits in the buffer */ + if (offset + size > ICE_PKG_BUF_SIZE) + return NULL; + + state->sect_type = + le32_to_cpu(state->buf->section_entry[state->sect_idx].type); + + /* calc pointer to this section */ + state->sect = + ((u8 *)state->buf) + + le16_to_cpu(state->buf->section_entry[state->sect_idx].offset); + + return state->sect; +} + +/** + * ice_pkg_enum_entry + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * @sect_type: section type to enumerate + * @offset: pointer to variable that receives the offset in the table (optional) + * @handler: function that handles access to the entries into the section type + * + * This function will enumerate all the entries in particular section type in + * the ice segment. The first call is made with the ice_seg parameter non-NULL; + * on subsequent calls, ice_seg is set to NULL which continues the enumeration. + * When the function returns a NULL pointer, then the end of the entries has + * been reached. + * + * Since each section may have a different header and entry size, the handler + * function is needed to determine the number and location entries in each + * section. + * + * The offset parameter is optional, but should be used for sections that + * contain an offset for each section table. For such cases, the section handler + * function must return the appropriate offset + index to give the absolution + * offset for each entry. For example, if the base for a section's header + * indicates a base offset of 10, and the index for the entry is 2, then + * section handler function should set the offset to 10 + 2 = 12. + */ +static void *ice_pkg_enum_entry(struct ice_seg *ice_seg, + struct ice_pkg_enum *state, u32 sect_type, + u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)) +{ + void *entry; + + if (ice_seg) { + if (!handler) + return NULL; + + if (!ice_pkg_enum_section(ice_seg, state, sect_type)) + return NULL; + + state->entry_idx = 0; + state->handler = handler; + } else { + state->entry_idx++; + } + + if (!state->handler) + return NULL; + + /* get entry */ + entry = state->handler(state->sect_type, state->sect, state->entry_idx, + offset); + if (!entry) { + /* end of a section, look for another section of this type */ + if (!ice_pkg_enum_section(NULL, state, 0)) + return NULL; + + state->entry_idx = 0; + entry = state->handler(state->sect_type, state->sect, + state->entry_idx, offset); + } + + return entry; +} + +/** + * ice_sw_fv_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the field vector entry to be returned + * @offset: ptr to variable that receives the offset in the field vector table + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * This function treats the given section as of type ice_sw_fv_section and + * enumerates offset field. "offset" is an index into the field vector table. + */ +static void *ice_sw_fv_handler(u32 sect_type, void *section, u32 index, + u32 *offset) +{ + struct ice_sw_fv_section *fv_section = section; + + if (!section || sect_type != ICE_SID_FLD_VEC_SW) + return NULL; + if (index >= le16_to_cpu(fv_section->count)) + return NULL; + if (offset) + /* "index" passed in to this function is relative to a given + * 4k block. To get to the true index into the field vector + * table need to add the relative index to the base_offset + * field of this section + */ + *offset = le16_to_cpu(fv_section->base_offset) + index; + return fv_section->fv + index; +} + +/** + * ice_get_prof_index_max - get the max profile index for used profile + * @hw: pointer to the HW struct + * + * Calling this function will get the max profile index for used profile + * and store the index number in struct ice_switch_info *switch_info + * in HW for following use. + */ +static int ice_get_prof_index_max(struct ice_hw *hw) +{ + u16 prof_index = 0, j, max_prof_index = 0; + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + bool flag = false; + struct ice_fv *fv; + u32 offset; + + memset(&state, 0, sizeof(state)); + + if (!hw->seg) + return -EINVAL; + + ice_seg = hw->seg; + + do { + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + if (!fv) + break; + ice_seg = NULL; + + /* in the profile that not be used, the prot_id is set to 0xff + * and the off is set to 0x1ff for all the field vectors. + */ + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv->ew[j].prot_id != ICE_PROT_INVALID || + fv->ew[j].off != ICE_FV_OFFSET_INVAL) + flag = true; + if (flag && prof_index > max_prof_index) + max_prof_index = prof_index; + + prof_index++; + flag = false; + } while (fv); + + hw->switch_info->max_used_prof_index = max_prof_index; + + return 0; +} + +/** + * ice_get_ddp_pkg_state - get DDP pkg state after download + * @hw: pointer to the HW struct + * @already_loaded: indicates if pkg was already loaded onto the device + */ +static enum ice_ddp_state ice_get_ddp_pkg_state(struct ice_hw *hw, + bool already_loaded) +{ + if (hw->pkg_ver.major == hw->active_pkg_ver.major && + hw->pkg_ver.minor == hw->active_pkg_ver.minor && + hw->pkg_ver.update == hw->active_pkg_ver.update && + hw->pkg_ver.draft == hw->active_pkg_ver.draft && + !memcmp(hw->pkg_name, hw->active_pkg_name, sizeof(hw->pkg_name))) { + if (already_loaded) + return ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED; + else + return ICE_DDP_PKG_SUCCESS; + } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ || + hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) { + return ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED; + } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && + hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) { + return ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED; + } else { + return ICE_DDP_PKG_ERR; + } +} + +/** + * ice_init_pkg_regs - initialize additional package registers + * @hw: pointer to the hardware structure + */ +static void ice_init_pkg_regs(struct ice_hw *hw) +{ +#define ICE_SW_BLK_INP_MASK_L 0xFFFFFFFF +#define ICE_SW_BLK_INP_MASK_H 0x0000FFFF +#define ICE_SW_BLK_IDX 0 + + /* setup Switch block input mask, which is 48-bits in two parts */ + wr32(hw, GL_PREEXT_L2_PMASK0(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_L); + wr32(hw, GL_PREEXT_L2_PMASK1(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_H); +} + +/** + * ice_marker_ptype_tcam_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the Marker PType TCAM entry to be returned + * @offset: pointer to receive absolute offset, always 0 for ptype TCAM sections + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * Handles enumeration of individual Marker PType TCAM entries. + */ +static void *ice_marker_ptype_tcam_handler(u32 sect_type, void *section, + u32 index, u32 *offset) +{ + struct ice_marker_ptype_tcam_section *marker_ptype; + + if (sect_type != ICE_SID_RXPARSER_MARKER_PTYPE) + return NULL; + + if (index > ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF) + return NULL; + + if (offset) + *offset = 0; + + marker_ptype = section; + if (index >= le16_to_cpu(marker_ptype->count)) + return NULL; + + return marker_ptype->tcam + index; +} + +/** + * ice_add_dvm_hint + * @hw: pointer to the HW structure + * @val: value of the boost entry + * @enable: true if entry needs to be enabled, or false if needs to be disabled + */ +static void ice_add_dvm_hint(struct ice_hw *hw, u16 val, bool enable) +{ + if (hw->dvm_upd.count < ICE_DVM_MAX_ENTRIES) { + hw->dvm_upd.tbl[hw->dvm_upd.count].boost_addr = val; + hw->dvm_upd.tbl[hw->dvm_upd.count].enable = enable; + hw->dvm_upd.count++; + } +} + +/** + * ice_add_tunnel_hint + * @hw: pointer to the HW structure + * @label_name: label text + * @val: value of the tunnel port boost entry + */ +static void ice_add_tunnel_hint(struct ice_hw *hw, char *label_name, u16 val) +{ + if (hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) { + u16 i; + + for (i = 0; tnls[i].type != TNL_LAST; i++) { + size_t len = strlen(tnls[i].label_prefix); + + /* Look for matching label start, before continuing */ + if (strncmp(label_name, tnls[i].label_prefix, len)) + continue; + + /* Make sure this label matches our PF. Note that the PF + * character ('0' - '7') will be located where our + * prefix string's null terminator is located. + */ + if ((label_name[len] - '0') == hw->pf_id) { + hw->tnl.tbl[hw->tnl.count].type = tnls[i].type; + hw->tnl.tbl[hw->tnl.count].valid = false; + hw->tnl.tbl[hw->tnl.count].boost_addr = val; + hw->tnl.tbl[hw->tnl.count].port = 0; + hw->tnl.count++; + break; + } + } + } +} + +/** + * ice_label_enum_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the label entry to be returned + * @offset: pointer to receive absolute offset, always zero for label sections + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * Handles enumeration of individual label entries. + */ +static void *ice_label_enum_handler(u32 __always_unused sect_type, + void *section, u32 index, u32 *offset) +{ + struct ice_label_section *labels; + + if (!section) + return NULL; + + if (index > ICE_MAX_LABELS_IN_BUF) + return NULL; + + if (offset) + *offset = 0; + + labels = section; + if (index >= le16_to_cpu(labels->count)) + return NULL; + + return labels->label + index; +} + +/** + * ice_enum_labels + * @ice_seg: pointer to the ice segment (NULL on subsequent calls) + * @type: the section type that will contain the label (0 on subsequent calls) + * @state: ice_pkg_enum structure that will hold the state of the enumeration + * @value: pointer to a value that will return the label's value if found + * + * Enumerates a list of labels in the package. The caller will call + * ice_enum_labels(ice_seg, type, ...) to start the enumeration, then call + * ice_enum_labels(NULL, 0, ...) to continue. When the function returns a NULL + * the end of the list has been reached. + */ +static char *ice_enum_labels(struct ice_seg *ice_seg, u32 type, + struct ice_pkg_enum *state, u16 *value) +{ + struct ice_label *label; + + /* Check for valid label section on first call */ + if (type && !(type >= ICE_SID_LBL_FIRST && type <= ICE_SID_LBL_LAST)) + return NULL; + + label = ice_pkg_enum_entry(ice_seg, state, type, NULL, + ice_label_enum_handler); + if (!label) + return NULL; + + *value = le16_to_cpu(label->value); + return label->name; +} + +/** + * ice_boost_tcam_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the boost TCAM entry to be returned + * @offset: pointer to receive absolute offset, always 0 for boost TCAM sections + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * Handles enumeration of individual boost TCAM entries. + */ +static void *ice_boost_tcam_handler(u32 sect_type, void *section, u32 index, + u32 *offset) +{ + struct ice_boost_tcam_section *boost; + + if (!section) + return NULL; + + if (sect_type != ICE_SID_RXPARSER_BOOST_TCAM) + return NULL; + + if (index > ICE_MAX_BST_TCAMS_IN_BUF) + return NULL; + + if (offset) + *offset = 0; + + boost = section; + if (index >= le16_to_cpu(boost->count)) + return NULL; + + return boost->tcam + index; +} + +/** + * ice_find_boost_entry + * @ice_seg: pointer to the ice segment (non-NULL) + * @addr: Boost TCAM address of entry to search for + * @entry: returns pointer to the entry + * + * Finds a particular Boost TCAM entry and returns a pointer to that entry + * if it is found. The ice_seg parameter must not be NULL since the first call + * to ice_pkg_enum_entry requires a pointer to an actual ice_segment structure. + */ +static int ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr, + struct ice_boost_tcam_entry **entry) +{ + struct ice_boost_tcam_entry *tcam; + struct ice_pkg_enum state; + + memset(&state, 0, sizeof(state)); + + if (!ice_seg) + return -EINVAL; + + do { + tcam = ice_pkg_enum_entry(ice_seg, &state, + ICE_SID_RXPARSER_BOOST_TCAM, NULL, + ice_boost_tcam_handler); + if (tcam && le16_to_cpu(tcam->addr) == addr) { + *entry = tcam; + return 0; + } + + ice_seg = NULL; + } while (tcam); + + *entry = NULL; + return -EIO; +} + +/** + * ice_is_init_pkg_successful - check if DDP init was successful + * @state: state of the DDP pkg after download + */ +bool ice_is_init_pkg_successful(enum ice_ddp_state state) +{ + switch (state) { + case ICE_DDP_PKG_SUCCESS: + case ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED: + case ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED: + return true; + default: + return false; + } +} + +/** + * ice_pkg_buf_alloc + * @hw: pointer to the HW structure + * + * Allocates a package buffer and returns a pointer to the buffer header. + * Note: all package contents must be in Little Endian form. + */ +struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw) +{ + struct ice_buf_build *bld; + struct ice_buf_hdr *buf; + + bld = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*bld), GFP_KERNEL); + if (!bld) + return NULL; + + buf = (struct ice_buf_hdr *)bld; + buf->data_end = + cpu_to_le16(offsetof(struct ice_buf_hdr, section_entry)); + return bld; +} + +static bool ice_is_gtp_u_profile(u16 prof_idx) +{ + return (prof_idx >= ICE_PROFID_IPV6_GTPU_TEID && + prof_idx <= ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER) || + prof_idx == ICE_PROFID_IPV4_GTPU_TEID; +} + +static bool ice_is_gtp_c_profile(u16 prof_idx) +{ + switch (prof_idx) { + case ICE_PROFID_IPV4_GTPC_TEID: + case ICE_PROFID_IPV4_GTPC_NO_TEID: + case ICE_PROFID_IPV6_GTPC_TEID: + case ICE_PROFID_IPV6_GTPC_NO_TEID: + return true; + default: + return false; + } +} + +/** + * ice_get_sw_prof_type - determine switch profile type + * @hw: pointer to the HW structure + * @fv: pointer to the switch field vector + * @prof_idx: profile index to check + */ +static enum ice_prof_type ice_get_sw_prof_type(struct ice_hw *hw, + struct ice_fv *fv, u32 prof_idx) +{ + u16 i; + + if (ice_is_gtp_c_profile(prof_idx)) + return ICE_PROF_TUN_GTPC; + + if (ice_is_gtp_u_profile(prof_idx)) + return ICE_PROF_TUN_GTPU; + + for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) { + /* UDP tunnel will have UDP_OF protocol ID and VNI offset */ + if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF && + fv->ew[i].off == ICE_VNI_OFFSET) + return ICE_PROF_TUN_UDP; + + /* GRE tunnel will have GRE protocol */ + if (fv->ew[i].prot_id == (u8)ICE_PROT_GRE_OF) + return ICE_PROF_TUN_GRE; + } + + return ICE_PROF_NON_TUN; +} + +/** + * ice_get_sw_fv_bitmap - Get switch field vector bitmap based on profile type + * @hw: pointer to hardware structure + * @req_profs: type of profiles requested + * @bm: pointer to memory for returning the bitmap of field vectors + */ +void ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, + unsigned long *bm) +{ + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + + if (req_profs == ICE_PROF_ALL) { + bitmap_set(bm, 0, ICE_MAX_NUM_PROFILES); + return; + } + + memset(&state, 0, sizeof(state)); + bitmap_zero(bm, ICE_MAX_NUM_PROFILES); + ice_seg = hw->seg; + do { + enum ice_prof_type prof_type; + u32 offset; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + ice_seg = NULL; + + if (fv) { + /* Determine field vector type */ + prof_type = ice_get_sw_prof_type(hw, fv, offset); + + if (req_profs & prof_type) + set_bit((u16)offset, bm); + } + } while (fv); +} + +/** + * ice_get_sw_fv_list + * @hw: pointer to the HW structure + * @lkups: list of protocol types + * @bm: bitmap of field vectors to consider + * @fv_list: Head of a list + * + * Finds all the field vector entries from switch block that contain + * a given protocol ID and offset and returns a list of structures of type + * "ice_sw_fv_list_entry". Every structure in the list has a field vector + * definition and profile ID information + * NOTE: The caller of the function is responsible for freeing the memory + * allocated for every list entry. + */ +int ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups, + unsigned long *bm, struct list_head *fv_list) +{ + struct ice_sw_fv_list_entry *fvl; + struct ice_sw_fv_list_entry *tmp; + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + u32 offset; + + memset(&state, 0, sizeof(state)); + + if (!lkups->n_val_words || !hw->seg) + return -EINVAL; + + ice_seg = hw->seg; + do { + u16 i; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + if (!fv) + break; + ice_seg = NULL; + + /* If field vector is not in the bitmap list, then skip this + * profile. + */ + if (!test_bit((u16)offset, bm)) + continue; + + for (i = 0; i < lkups->n_val_words; i++) { + int j; + + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv->ew[j].prot_id == + lkups->fv_words[i].prot_id && + fv->ew[j].off == lkups->fv_words[i].off) + break; + if (j >= hw->blk[ICE_BLK_SW].es.fvw) + break; + if (i + 1 == lkups->n_val_words) { + fvl = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*fvl), GFP_KERNEL); + if (!fvl) + goto err; + fvl->fv_ptr = fv; + fvl->profile_id = offset; + list_add(&fvl->list_entry, fv_list); + break; + } + } + } while (fv); + if (list_empty(fv_list)) { + dev_warn(ice_hw_to_dev(hw), + "Required profiles not found in currently loaded DDP package"); + return -EIO; + } + + return 0; + +err: + list_for_each_entry_safe(fvl, tmp, fv_list, list_entry) { + list_del(&fvl->list_entry); + devm_kfree(ice_hw_to_dev(hw), fvl); + } + + return -ENOMEM; +} + +/** + * ice_init_prof_result_bm - Initialize the profile result index bitmap + * @hw: pointer to hardware structure + */ +void ice_init_prof_result_bm(struct ice_hw *hw) +{ + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + + memset(&state, 0, sizeof(state)); + + if (!hw->seg) + return; + + ice_seg = hw->seg; + do { + u32 off; + u16 i; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &off, ice_sw_fv_handler); + ice_seg = NULL; + if (!fv) + break; + + bitmap_zero(hw->switch_info->prof_res_bm[off], + ICE_MAX_FV_WORDS); + + /* Determine empty field vector indices, these can be + * used for recipe results. Skip index 0, since it is + * always used for Switch ID. + */ + for (i = 1; i < ICE_MAX_FV_WORDS; i++) + if (fv->ew[i].prot_id == ICE_PROT_INVALID && + fv->ew[i].off == ICE_FV_OFFSET_INVAL) + set_bit(i, hw->switch_info->prof_res_bm[off]); + } while (fv); +} + +/** + * ice_pkg_buf_free + * @hw: pointer to the HW structure + * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) + * + * Frees a package buffer + */ +void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) +{ + devm_kfree(ice_hw_to_dev(hw), bld); +} + +/** + * ice_pkg_buf_reserve_section + * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) + * @count: the number of sections to reserve + * + * Reserves one or more section table entries in a package buffer. This routine + * can be called multiple times as long as they are made before calling + * ice_pkg_buf_alloc_section(). Once ice_pkg_buf_alloc_section() + * is called once, the number of sections that can be allocated will not be able + * to be increased; not using all reserved sections is fine, but this will + * result in some wasted space in the buffer. + * Note: all package contents must be in Little Endian form. + */ +int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count) +{ + struct ice_buf_hdr *buf; + u16 section_count; + u16 data_end; + + if (!bld) + return -EINVAL; + + buf = (struct ice_buf_hdr *)&bld->buf; + + /* already an active section, can't increase table size */ + section_count = le16_to_cpu(buf->section_count); + if (section_count > 0) + return -EIO; + + if (bld->reserved_section_table_entries + count > ICE_MAX_S_COUNT) + return -EIO; + bld->reserved_section_table_entries += count; + + data_end = le16_to_cpu(buf->data_end) + + flex_array_size(buf, section_entry, count); + buf->data_end = cpu_to_le16(data_end); + + return 0; +} + +/** + * ice_pkg_buf_alloc_section + * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) + * @type: the section type value + * @size: the size of the section to reserve (in bytes) + * + * Reserves memory in the buffer for a section's content and updates the + * buffers' status accordingly. This routine returns a pointer to the first + * byte of the section start within the buffer, which is used to fill in the + * section contents. + * Note: all package contents must be in Little Endian form. + */ +void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size) +{ + struct ice_buf_hdr *buf; + u16 sect_count; + u16 data_end; + + if (!bld || !type || !size) + return NULL; + + buf = (struct ice_buf_hdr *)&bld->buf; + + /* check for enough space left in buffer */ + data_end = le16_to_cpu(buf->data_end); + + /* section start must align on 4 byte boundary */ + data_end = ALIGN(data_end, 4); + + if ((data_end + size) > ICE_MAX_S_DATA_END) + return NULL; + + /* check for more available section table entries */ + sect_count = le16_to_cpu(buf->section_count); + if (sect_count < bld->reserved_section_table_entries) { + void *section_ptr = ((u8 *)buf) + data_end; + + buf->section_entry[sect_count].offset = cpu_to_le16(data_end); + buf->section_entry[sect_count].size = cpu_to_le16(size); + buf->section_entry[sect_count].type = cpu_to_le32(type); + + data_end += size; + buf->data_end = cpu_to_le16(data_end); + + buf->section_count = cpu_to_le16(sect_count + 1); + return section_ptr; + } + + /* no free section table entries */ + return NULL; +} + +/** + * ice_pkg_buf_alloc_single_section + * @hw: pointer to the HW structure + * @type: the section type value + * @size: the size of the section to reserve (in bytes) + * @section: returns pointer to the section + * + * Allocates a package buffer with a single section. + * Note: all package contents must be in Little Endian form. + */ +struct ice_buf_build *ice_pkg_buf_alloc_single_section(struct ice_hw *hw, + u32 type, u16 size, + void **section) +{ + struct ice_buf_build *buf; + + if (!section) + return NULL; + + buf = ice_pkg_buf_alloc(hw); + if (!buf) + return NULL; + + if (ice_pkg_buf_reserve_section(buf, 1)) + goto ice_pkg_buf_alloc_single_section_err; + + *section = ice_pkg_buf_alloc_section(buf, type, size); + if (!*section) + goto ice_pkg_buf_alloc_single_section_err; + + return buf; + +ice_pkg_buf_alloc_single_section_err: + ice_pkg_buf_free(hw, buf); + return NULL; +} + +/** + * ice_pkg_buf_get_active_sections + * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) + * + * Returns the number of active sections. Before using the package buffer + * in an update package command, the caller should make sure that there is at + * least one active section - otherwise, the buffer is not legal and should + * not be used. + * Note: all package contents must be in Little Endian form. + */ +u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld) +{ + struct ice_buf_hdr *buf; + + if (!bld) + return 0; + + buf = (struct ice_buf_hdr *)&bld->buf; + return le16_to_cpu(buf->section_count); +} + +/** + * ice_pkg_buf + * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) + * + * Return a pointer to the buffer's header + */ +struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) +{ + if (!bld) + return NULL; + + return &bld->buf; +} + +static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err) +{ + switch (aq_err) { + case ICE_AQ_RC_ENOSEC: + case ICE_AQ_RC_EBADSIG: + return ICE_DDP_PKG_FILE_SIGNATURE_INVALID; + case ICE_AQ_RC_ESVN: + return ICE_DDP_PKG_FILE_REVISION_TOO_LOW; + case ICE_AQ_RC_EBADMAN: + case ICE_AQ_RC_EBADBUF: + return ICE_DDP_PKG_LOAD_ERROR; + default: + return ICE_DDP_PKG_ERR; + } +} + +/** + * ice_acquire_global_cfg_lock + * @hw: pointer to the HW structure + * @access: access type (read or write) + * + * This function will request ownership of the global config lock for reading + * or writing of the package. When attempting to obtain write access, the + * caller must check for the following two return values: + * + * 0 - Means the caller has acquired the global config lock + * and can perform writing of the package. + * -EALREADY - Indicates another driver has already written the + * package or has found that no update was necessary; in + * this case, the caller can just skip performing any + * update of the package. + */ +static int ice_acquire_global_cfg_lock(struct ice_hw *hw, + enum ice_aq_res_access_type access) +{ + int status; + + status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access, + ICE_GLOBAL_CFG_LOCK_TIMEOUT); + + if (!status) + mutex_lock(&ice_global_cfg_lock_sw); + else if (status == -EALREADY) + ice_debug(hw, ICE_DBG_PKG, + "Global config lock: No work to do\n"); + + return status; +} + +/** + * ice_release_global_cfg_lock + * @hw: pointer to the HW structure + * + * This function will release the global config lock. + */ +static void ice_release_global_cfg_lock(struct ice_hw *hw) +{ + mutex_unlock(&ice_global_cfg_lock_sw); + ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID); +} + +/** + * ice_dwnld_cfg_bufs + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains global config lock and downloads the package configuration buffers + * to the firmware. Metadata buffers are skipped, and the first metadata buffer + * found indicates that the rest of the buffers are all metadata buffers. + */ +static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, + struct ice_buf *bufs, u32 count) +{ + enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; + struct ice_buf_hdr *bh; + enum ice_aq_err err; + u32 offset, info, i; + int status; + + if (!bufs || !count) + return ICE_DDP_PKG_ERR; + + /* If the first buffer's first section has its metadata bit set + * then there are no buffers to be downloaded, and the operation is + * considered a success. + */ + bh = (struct ice_buf_hdr *)bufs; + if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + return ICE_DDP_PKG_SUCCESS; + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == -EALREADY) + return ICE_DDP_PKG_ALREADY_LOADED; + return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); + } + + for (i = 0; i < count; i++) { + bool last = ((i + 1) == count); + + if (!last) { + /* check next buffer for metadata flag */ + bh = (struct ice_buf_hdr *)(bufs + i + 1); + + /* A set metadata flag in the next buffer will signal + * that the current buffer will be the last buffer + * downloaded + */ + if (le16_to_cpu(bh->section_count)) + if (le32_to_cpu(bh->section_entry[0].type) & + ICE_METADATA_BUF) + last = true; + } + + bh = (struct ice_buf_hdr *)(bufs + i); + + status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, + &offset, &info, NULL); + + /* Save AQ status from download package */ + if (status) { + ice_debug(hw, ICE_DBG_PKG, + "Pkg download failed: err %d off %d inf %d\n", + status, offset, info); + err = hw->adminq.sq_last_status; + state = ice_map_aq_err_to_ddp_state(err); + break; + } + + if (last) + break; + } + + if (!status) { + status = ice_set_vlan_mode(hw); + if (status) + ice_debug(hw, ICE_DBG_PKG, + "Failed to set VLAN mode: err %d\n", status); + } + + ice_release_global_cfg_lock(hw); + + return state; +} + +/** + * ice_aq_get_pkg_info_list + * @hw: pointer to the hardware structure + * @pkg_info: the buffer which will receive the information list + * @buf_size: the size of the pkg_info information buffer + * @cd: pointer to command details structure or NULL + * + * Get Package Info List (0x0C43) + */ +static int ice_aq_get_pkg_info_list(struct ice_hw *hw, + struct ice_aqc_get_pkg_info_resp *pkg_info, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); + + return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); +} + +/** + * ice_download_pkg + * @hw: pointer to the hardware structure + * @ice_seg: pointer to the segment of the package to be downloaded + * + * Handles the download of a complete package. + */ +static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, + struct ice_seg *ice_seg) +{ + struct ice_buf_table *ice_buf_tbl; + int status; + + ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", + ice_seg->hdr.seg_format_ver.major, + ice_seg->hdr.seg_format_ver.minor, + ice_seg->hdr.seg_format_ver.update, + ice_seg->hdr.seg_format_ver.draft); + + ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n", + le32_to_cpu(ice_seg->hdr.seg_type), + le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id); + + ice_buf_tbl = ice_find_buf_table(ice_seg); + + ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", + le32_to_cpu(ice_buf_tbl->buf_count)); + + status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); + + ice_post_pkg_dwnld_vlan_mode_cfg(hw); + + return status; +} + +/** + * ice_aq_download_pkg + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer to transfer + * @buf_size: the size of the package buffer + * @last_buf: last buffer indicator + * @error_offset: returns error offset + * @error_info: returns error information + * @cd: pointer to command details structure or NULL + * + * Download Package (0x0C40) + */ +int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) +{ + struct ice_aqc_download_pkg *cmd; + struct ice_aq_desc desc; + int status; + + if (error_offset) + *error_offset = 0; + if (error_info) + *error_info = 0; + + cmd = &desc.params.download_pkg; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (last_buf) + cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + + status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + if (status == -EIO) { + /* Read error from buffer only when the FW returned an error */ + struct ice_aqc_download_pkg_resp *resp; + + resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * ice_aq_upload_section + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer which will receive the section + * @buf_size: the size of the package buffer + * @cd: pointer to command details structure or NULL + * + * Upload Section (0x0C41) + */ +int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); +} + +/** + * ice_aq_update_pkg + * @hw: pointer to the hardware structure + * @pkg_buf: the package cmd buffer + * @buf_size: the size of the package cmd buffer + * @last_buf: last buffer indicator + * @error_offset: returns error offset + * @error_info: returns error information + * @cd: pointer to command details structure or NULL + * + * Update Package (0x0C42) + */ +static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) +{ + struct ice_aqc_download_pkg *cmd; + struct ice_aq_desc desc; + int status; + + if (error_offset) + *error_offset = 0; + if (error_info) + *error_info = 0; + + cmd = &desc.params.download_pkg; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (last_buf) + cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + + status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + if (status == -EIO) { + /* Read error from buffer only when the FW returned an error */ + struct ice_aqc_download_pkg_resp *resp; + + resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * ice_update_pkg_no_lock + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + */ +int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + int status = 0; + u32 i; + + for (i = 0; i < count; i++) { + struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i); + bool last = ((i + 1) == count); + u32 offset, info; + + status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end), + last, &offset, &info, NULL); + + if (status) { + ice_debug(hw, ICE_DBG_PKG, + "Update pkg failed: err %d off %d inf %d\n", + status, offset, info); + break; + } + } + + return status; +} + +/** + * ice_update_pkg + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains change lock and updates package. + */ +int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + int status; + + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + return status; + + status = ice_update_pkg_no_lock(hw, bufs, count); + + ice_release_change_lock(hw); + + return status; +} + +/** + * ice_find_seg_in_pkg + * @hw: pointer to the hardware structure + * @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK) + * @pkg_hdr: pointer to the package header to be searched + * + * This function searches a package file for a particular segment type. On + * success it returns a pointer to the segment header, otherwise it will + * return NULL. + */ +struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, + struct ice_pkg_hdr *pkg_hdr) +{ + u32 i; + + ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n", + pkg_hdr->pkg_format_ver.major, pkg_hdr->pkg_format_ver.minor, + pkg_hdr->pkg_format_ver.update, + pkg_hdr->pkg_format_ver.draft); + + /* Search all package segments for the requested segment type */ + for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { + struct ice_generic_seg_hdr *seg; + + seg = (struct ice_generic_seg_hdr + *)((u8 *)pkg_hdr + + le32_to_cpu(pkg_hdr->seg_offset[i])); + + if (le32_to_cpu(seg->seg_type) == seg_type) + return seg; + } + + return NULL; +} + +/** + * ice_init_pkg_info + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to the driver's package hdr + * + * Saves off the package details into the HW structure. + */ +static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, + struct ice_pkg_hdr *pkg_hdr) +{ + struct ice_generic_seg_hdr *seg_hdr; + + if (!pkg_hdr) + return ICE_DDP_PKG_ERR; + + seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); + if (seg_hdr) { + struct ice_meta_sect *meta; + struct ice_pkg_enum state; + + memset(&state, 0, sizeof(state)); + + /* Get package information from the Metadata Section */ + meta = ice_pkg_enum_section((struct ice_seg *)seg_hdr, &state, + ICE_SID_METADATA); + if (!meta) { + ice_debug(hw, ICE_DBG_INIT, + "Did not find ice metadata section in package\n"); + return ICE_DDP_PKG_INVALID_FILE; + } + + hw->pkg_ver = meta->ver; + memcpy(hw->pkg_name, meta->name, sizeof(meta->name)); + + ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n", + meta->ver.major, meta->ver.minor, meta->ver.update, + meta->ver.draft, meta->name); + + hw->ice_seg_fmt_ver = seg_hdr->seg_format_ver; + memcpy(hw->ice_seg_id, seg_hdr->seg_id, sizeof(hw->ice_seg_id)); + + ice_debug(hw, ICE_DBG_PKG, "Ice Seg: %d.%d.%d.%d, %s\n", + seg_hdr->seg_format_ver.major, + seg_hdr->seg_format_ver.minor, + seg_hdr->seg_format_ver.update, + seg_hdr->seg_format_ver.draft, seg_hdr->seg_id); + } else { + ice_debug(hw, ICE_DBG_INIT, + "Did not find ice segment in driver package\n"); + return ICE_DDP_PKG_INVALID_FILE; + } + + return ICE_DDP_PKG_SUCCESS; +} + +/** + * ice_get_pkg_info + * @hw: pointer to the hardware structure + * + * Store details of the package currently loaded in HW into the HW structure. + */ +static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) +{ + enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; + struct ice_aqc_get_pkg_info_resp *pkg_info; + u16 size; + u32 i; + + size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT); + pkg_info = kzalloc(size, GFP_KERNEL); + if (!pkg_info) + return ICE_DDP_PKG_ERR; + + if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) { + state = ICE_DDP_PKG_ERR; + goto init_pkg_free_alloc; + } + + for (i = 0; i < le32_to_cpu(pkg_info->count); i++) { +#define ICE_PKG_FLAG_COUNT 4 + char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 }; + u8 place = 0; + + if (pkg_info->pkg_info[i].is_active) { + flags[place++] = 'A'; + hw->active_pkg_ver = pkg_info->pkg_info[i].ver; + hw->active_track_id = + le32_to_cpu(pkg_info->pkg_info[i].track_id); + memcpy(hw->active_pkg_name, pkg_info->pkg_info[i].name, + sizeof(pkg_info->pkg_info[i].name)); + hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm; + } + if (pkg_info->pkg_info[i].is_active_at_boot) + flags[place++] = 'B'; + if (pkg_info->pkg_info[i].is_modified) + flags[place++] = 'M'; + if (pkg_info->pkg_info[i].is_in_nvm) + flags[place++] = 'N'; + + ice_debug(hw, ICE_DBG_PKG, "Pkg[%d]: %d.%d.%d.%d,%s,%s\n", i, + pkg_info->pkg_info[i].ver.major, + pkg_info->pkg_info[i].ver.minor, + pkg_info->pkg_info[i].ver.update, + pkg_info->pkg_info[i].ver.draft, + pkg_info->pkg_info[i].name, flags); + } + +init_pkg_free_alloc: + kfree(pkg_info); + + return state; +} + +/** + * ice_chk_pkg_compat + * @hw: pointer to the hardware structure + * @ospkg: pointer to the package hdr + * @seg: pointer to the package segment hdr + * + * This function checks the package version compatibility with driver and NVM + */ +static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, + struct ice_pkg_hdr *ospkg, + struct ice_seg **seg) +{ + struct ice_aqc_get_pkg_info_resp *pkg; + enum ice_ddp_state state; + u16 size; + u32 i; + + /* Check package version compatibility */ + state = ice_chk_pkg_version(&hw->pkg_ver); + if (state) { + ice_debug(hw, ICE_DBG_INIT, "Package version check failed.\n"); + return state; + } + + /* find ICE segment in given package */ + *seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, + ospkg); + if (!*seg) { + ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n"); + return ICE_DDP_PKG_INVALID_FILE; + } + + /* Check if FW is compatible with the OS package */ + size = struct_size(pkg, pkg_info, ICE_PKG_CNT); + pkg = kzalloc(size, GFP_KERNEL); + if (!pkg) + return ICE_DDP_PKG_ERR; + + if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) { + state = ICE_DDP_PKG_LOAD_ERROR; + goto fw_ddp_compat_free_alloc; + } + + for (i = 0; i < le32_to_cpu(pkg->count); i++) { + /* loop till we find the NVM package */ + if (!pkg->pkg_info[i].is_in_nvm) + continue; + if ((*seg)->hdr.seg_format_ver.major != + pkg->pkg_info[i].ver.major || + (*seg)->hdr.seg_format_ver.minor > + pkg->pkg_info[i].ver.minor) { + state = ICE_DDP_PKG_FW_MISMATCH; + ice_debug(hw, ICE_DBG_INIT, + "OS package is not compatible with NVM.\n"); + } + /* done processing NVM package so break */ + break; + } +fw_ddp_compat_free_alloc: + kfree(pkg); + return state; +} + +/** + * ice_init_pkg_hints + * @hw: pointer to the HW structure + * @ice_seg: pointer to the segment of the package scan (non-NULL) + * + * This function will scan the package and save off relevant information + * (hints or metadata) for driver use. The ice_seg parameter must not be NULL + * since the first call to ice_enum_labels requires a pointer to an actual + * ice_seg structure. + */ +static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) +{ + struct ice_pkg_enum state; + char *label_name; + u16 val; + int i; + + memset(&hw->tnl, 0, sizeof(hw->tnl)); + memset(&state, 0, sizeof(state)); + + if (!ice_seg) + return; + + label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state, + &val); + + while (label_name) { + if (!strncmp(label_name, ICE_TNL_PRE, strlen(ICE_TNL_PRE))) + /* check for a tunnel entry */ + ice_add_tunnel_hint(hw, label_name, val); + + /* check for a dvm mode entry */ + else if (!strncmp(label_name, ICE_DVM_PRE, strlen(ICE_DVM_PRE))) + ice_add_dvm_hint(hw, val, true); + + /* check for a svm mode entry */ + else if (!strncmp(label_name, ICE_SVM_PRE, strlen(ICE_SVM_PRE))) + ice_add_dvm_hint(hw, val, false); + + label_name = ice_enum_labels(NULL, 0, &state, &val); + } + + /* Cache the appropriate boost TCAM entry pointers for tunnels */ + for (i = 0; i < hw->tnl.count; i++) { + ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr, + &hw->tnl.tbl[i].boost_entry); + if (hw->tnl.tbl[i].boost_entry) { + hw->tnl.tbl[i].valid = true; + if (hw->tnl.tbl[i].type < __TNL_TYPE_CNT) + hw->tnl.valid_count[hw->tnl.tbl[i].type]++; + } + } + + /* Cache the appropriate boost TCAM entry pointers for DVM and SVM */ + for (i = 0; i < hw->dvm_upd.count; i++) + ice_find_boost_entry(ice_seg, hw->dvm_upd.tbl[i].boost_addr, + &hw->dvm_upd.tbl[i].boost_entry); +} + +/** + * ice_fill_hw_ptype - fill the enabled PTYPE bit information + * @hw: pointer to the HW structure + */ +static void ice_fill_hw_ptype(struct ice_hw *hw) +{ + struct ice_marker_ptype_tcam_entry *tcam; + struct ice_seg *seg = hw->seg; + struct ice_pkg_enum state; + + bitmap_zero(hw->hw_ptype, ICE_FLOW_PTYPE_MAX); + if (!seg) + return; + + memset(&state, 0, sizeof(state)); + + do { + tcam = ice_pkg_enum_entry(seg, &state, + ICE_SID_RXPARSER_MARKER_PTYPE, NULL, + ice_marker_ptype_tcam_handler); + if (tcam && + le16_to_cpu(tcam->addr) < ICE_MARKER_PTYPE_TCAM_ADDR_MAX && + le16_to_cpu(tcam->ptype) < ICE_FLOW_PTYPE_MAX) + set_bit(le16_to_cpu(tcam->ptype), hw->hw_ptype); + + seg = NULL; + } while (tcam); +} + +/** + * ice_init_pkg - initialize/download package + * @hw: pointer to the hardware structure + * @buf: pointer to the package buffer + * @len: size of the package buffer + * + * This function initializes a package. The package contains HW tables + * required to do packet processing. First, the function extracts package + * information such as version. Then it finds the ice configuration segment + * within the package; this function then saves a copy of the segment pointer + * within the supplied package buffer. Next, the function will cache any hints + * from the package, followed by downloading the package itself. Note, that if + * a previous PF driver has already downloaded the package successfully, then + * the current driver will not have to download the package again. + * + * The local package contents will be used to query default behavior and to + * update specific sections of the HW's version of the package (e.g. to update + * the parse graph to understand new protocols). + * + * This function stores a pointer to the package buffer memory, and it is + * expected that the supplied buffer will not be freed immediately. If the + * package buffer needs to be freed, such as when read from a file, use + * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this + * case. + */ +enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) +{ + bool already_loaded = false; + enum ice_ddp_state state; + struct ice_pkg_hdr *pkg; + struct ice_seg *seg; + + if (!buf || !len) + return ICE_DDP_PKG_ERR; + + pkg = (struct ice_pkg_hdr *)buf; + state = ice_verify_pkg(pkg, len); + if (state) { + ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n", + state); + return state; + } + + /* initialize package info */ + state = ice_init_pkg_info(hw, pkg); + if (state) + return state; + + /* before downloading the package, check package version for + * compatibility with driver + */ + state = ice_chk_pkg_compat(hw, pkg, &seg); + if (state) + return state; + + /* initialize package hints and then download package */ + ice_init_pkg_hints(hw, seg); + state = ice_download_pkg(hw, seg); + if (state == ICE_DDP_PKG_ALREADY_LOADED) { + ice_debug(hw, ICE_DBG_INIT, + "package previously loaded - no work.\n"); + already_loaded = true; + } + + /* Get information on the package currently loaded in HW, then make sure + * the driver is compatible with this version. + */ + if (!state || state == ICE_DDP_PKG_ALREADY_LOADED) { + state = ice_get_pkg_info(hw); + if (!state) + state = ice_get_ddp_pkg_state(hw, already_loaded); + } + + if (ice_is_init_pkg_successful(state)) { + hw->seg = seg; + /* on successful package download update other required + * registers to support the package and fill HW tables + * with package content. + */ + ice_init_pkg_regs(hw); + ice_fill_blk_tbls(hw); + ice_fill_hw_ptype(hw); + ice_get_prof_index_max(hw); + } else { + ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", state); + } + + return state; +} + +/** + * ice_copy_and_init_pkg - initialize/download a copy of the package + * @hw: pointer to the hardware structure + * @buf: pointer to the package buffer + * @len: size of the package buffer + * + * This function copies the package buffer, and then calls ice_init_pkg() to + * initialize the copied package contents. + * + * The copying is necessary if the package buffer supplied is constant, or if + * the memory may disappear shortly after calling this function. + * + * If the package buffer resides in the data segment and can be modified, the + * caller is free to use ice_init_pkg() instead of ice_copy_and_init_pkg(). + * + * However, if the package buffer needs to be copied first, such as when being + * read from a file, the caller should use ice_copy_and_init_pkg(). + * + * This function will first copy the package buffer, before calling + * ice_init_pkg(). The caller is free to immediately destroy the original + * package buffer, as the new copy will be managed by this function and + * related routines. + */ +enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, + u32 len) +{ + enum ice_ddp_state state; + u8 *buf_copy; + + if (!buf || !len) + return ICE_DDP_PKG_ERR; + + buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL); + + state = ice_init_pkg(hw, buf_copy, len); + if (!ice_is_init_pkg_successful(state)) { + /* Free the copy, since we failed to initialize the package */ + devm_kfree(ice_hw_to_dev(hw), buf_copy); + } else { + /* Track the copied pkg so we can free it later */ + hw->pkg_copy = buf_copy; + hw->pkg_size = len; + } + + return state; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h new file mode 100644 index 000000000000..37eadb3d27a8 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -0,0 +1,445 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2022, Intel Corporation. */ + +#ifndef _ICE_DDP_H_ +#define _ICE_DDP_H_ + +#include "ice_type.h" + +/* Package minimal version supported */ +#define ICE_PKG_SUPP_VER_MAJ 1 +#define ICE_PKG_SUPP_VER_MNR 3 + +/* Package format version */ +#define ICE_PKG_FMT_VER_MAJ 1 +#define ICE_PKG_FMT_VER_MNR 0 +#define ICE_PKG_FMT_VER_UPD 0 +#define ICE_PKG_FMT_VER_DFT 0 + +#define ICE_PKG_CNT 4 + +#define ICE_FV_OFFSET_INVAL 0x1FF + +/* Extraction Sequence (Field Vector) Table */ +struct ice_fv_word { + u8 prot_id; + u16 off; /* Offset within the protocol header */ + u8 resvrd; +} __packed; + +#define ICE_MAX_NUM_PROFILES 256 + +#define ICE_MAX_FV_WORDS 48 +struct ice_fv { + struct ice_fv_word ew[ICE_MAX_FV_WORDS]; +}; + +enum ice_ddp_state { + /* Indicates that this call to ice_init_pkg + * successfully loaded the requested DDP package + */ + ICE_DDP_PKG_SUCCESS = 0, + + /* Generic error for already loaded errors, it is mapped later to + * the more specific one (one of the next 3) + */ + ICE_DDP_PKG_ALREADY_LOADED = -1, + + /* Indicates that a DDP package of the same version has already been + * loaded onto the device by a previous call or by another PF + */ + ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED = -2, + + /* The device has a DDP package that is not supported by the driver */ + ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED = -3, + + /* The device has a compatible package + * (but different from the request) already loaded + */ + ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED = -4, + + /* The firmware loaded on the device is not compatible with + * the DDP package loaded + */ + ICE_DDP_PKG_FW_MISMATCH = -5, + + /* The DDP package file is invalid */ + ICE_DDP_PKG_INVALID_FILE = -6, + + /* The version of the DDP package provided is higher than + * the driver supports + */ + ICE_DDP_PKG_FILE_VERSION_TOO_HIGH = -7, + + /* The version of the DDP package provided is lower than the + * driver supports + */ + ICE_DDP_PKG_FILE_VERSION_TOO_LOW = -8, + + /* The signature of the DDP package file provided is invalid */ + ICE_DDP_PKG_FILE_SIGNATURE_INVALID = -9, + + /* The DDP package file security revision is too low and not + * supported by firmware + */ + ICE_DDP_PKG_FILE_REVISION_TOO_LOW = -10, + + /* An error occurred in firmware while loading the DDP package */ + ICE_DDP_PKG_LOAD_ERROR = -11, + + /* Other errors */ + ICE_DDP_PKG_ERR = -12 +}; + +/* Package and segment headers and tables */ +struct ice_pkg_hdr { + struct ice_pkg_ver pkg_format_ver; + __le32 seg_count; + __le32 seg_offset[]; +}; + +/* generic segment */ +struct ice_generic_seg_hdr { +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_ICE 0x00000010 + __le32 seg_type; + struct ice_pkg_ver seg_format_ver; + __le32 seg_size; + char seg_id[ICE_PKG_NAME_SIZE]; +}; + +/* ice specific segment */ + +union ice_device_id { + struct { + __le16 device_id; + __le16 vendor_id; + } dev_vend_id; + __le32 id; +}; + +struct ice_device_id_entry { + union ice_device_id device; + union ice_device_id sub_device; +}; + +struct ice_seg { + struct ice_generic_seg_hdr hdr; + __le32 device_table_count; + struct ice_device_id_entry device_table[]; +}; + +struct ice_nvm_table { + __le32 table_count; + __le32 vers[]; +}; + +struct ice_buf { +#define ICE_PKG_BUF_SIZE 4096 + u8 buf[ICE_PKG_BUF_SIZE]; +}; + +struct ice_buf_table { + __le32 buf_count; + struct ice_buf buf_array[]; +}; + +struct ice_run_time_cfg_seg { + struct ice_generic_seg_hdr hdr; + u8 rsvd[8]; + struct ice_buf_table buf_table; +}; + +/* global metadata specific segment */ +struct ice_global_metadata_seg { + struct ice_generic_seg_hdr hdr; + struct ice_pkg_ver pkg_ver; + __le32 rsvd; + char pkg_name[ICE_PKG_NAME_SIZE]; +}; + +#define ICE_MIN_S_OFF 12 +#define ICE_MAX_S_OFF 4095 +#define ICE_MIN_S_SZ 1 +#define ICE_MAX_S_SZ 4084 + +/* section information */ +struct ice_section_entry { + __le32 type; + __le16 offset; + __le16 size; +}; + +#define ICE_MIN_S_COUNT 1 +#define ICE_MAX_S_COUNT 511 +#define ICE_MIN_S_DATA_END 12 +#define ICE_MAX_S_DATA_END 4096 + +#define ICE_METADATA_BUF 0x80000000 + +struct ice_buf_hdr { + __le16 section_count; + __le16 data_end; + struct ice_section_entry section_entry[]; +}; + +#define ICE_MAX_ENTRIES_IN_BUF(hd_sz, ent_sz) \ + ((ICE_PKG_BUF_SIZE - \ + struct_size((struct ice_buf_hdr *)0, section_entry, 1) - (hd_sz)) / \ + (ent_sz)) + +/* ice package section IDs */ +#define ICE_SID_METADATA 1 +#define ICE_SID_XLT0_SW 10 +#define ICE_SID_XLT_KEY_BUILDER_SW 11 +#define ICE_SID_XLT1_SW 12 +#define ICE_SID_XLT2_SW 13 +#define ICE_SID_PROFID_TCAM_SW 14 +#define ICE_SID_PROFID_REDIR_SW 15 +#define ICE_SID_FLD_VEC_SW 16 +#define ICE_SID_CDID_KEY_BUILDER_SW 17 + +struct ice_meta_sect { + struct ice_pkg_ver ver; +#define ICE_META_SECT_NAME_SIZE 28 + char name[ICE_META_SECT_NAME_SIZE]; + __le32 track_id; +}; + +#define ICE_SID_CDID_REDIR_SW 18 + +#define ICE_SID_XLT0_ACL 20 +#define ICE_SID_XLT_KEY_BUILDER_ACL 21 +#define ICE_SID_XLT1_ACL 22 +#define ICE_SID_XLT2_ACL 23 +#define ICE_SID_PROFID_TCAM_ACL 24 +#define ICE_SID_PROFID_REDIR_ACL 25 +#define ICE_SID_FLD_VEC_ACL 26 +#define ICE_SID_CDID_KEY_BUILDER_ACL 27 +#define ICE_SID_CDID_REDIR_ACL 28 + +#define ICE_SID_XLT0_FD 30 +#define ICE_SID_XLT_KEY_BUILDER_FD 31 +#define ICE_SID_XLT1_FD 32 +#define ICE_SID_XLT2_FD 33 +#define ICE_SID_PROFID_TCAM_FD 34 +#define ICE_SID_PROFID_REDIR_FD 35 +#define ICE_SID_FLD_VEC_FD 36 +#define ICE_SID_CDID_KEY_BUILDER_FD 37 +#define ICE_SID_CDID_REDIR_FD 38 + +#define ICE_SID_XLT0_RSS 40 +#define ICE_SID_XLT_KEY_BUILDER_RSS 41 +#define ICE_SID_XLT1_RSS 42 +#define ICE_SID_XLT2_RSS 43 +#define ICE_SID_PROFID_TCAM_RSS 44 +#define ICE_SID_PROFID_REDIR_RSS 45 +#define ICE_SID_FLD_VEC_RSS 46 +#define ICE_SID_CDID_KEY_BUILDER_RSS 47 +#define ICE_SID_CDID_REDIR_RSS 48 + +#define ICE_SID_RXPARSER_MARKER_PTYPE 55 +#define ICE_SID_RXPARSER_BOOST_TCAM 56 +#define ICE_SID_RXPARSER_METADATA_INIT 58 +#define ICE_SID_TXPARSER_BOOST_TCAM 66 + +#define ICE_SID_XLT0_PE 80 +#define ICE_SID_XLT_KEY_BUILDER_PE 81 +#define ICE_SID_XLT1_PE 82 +#define ICE_SID_XLT2_PE 83 +#define ICE_SID_PROFID_TCAM_PE 84 +#define ICE_SID_PROFID_REDIR_PE 85 +#define ICE_SID_FLD_VEC_PE 86 +#define ICE_SID_CDID_KEY_BUILDER_PE 87 +#define ICE_SID_CDID_REDIR_PE 88 + +/* Label Metadata section IDs */ +#define ICE_SID_LBL_FIRST 0x80000010 +#define ICE_SID_LBL_RXPARSER_TMEM 0x80000018 +/* The following define MUST be updated to reflect the last label section ID */ +#define ICE_SID_LBL_LAST 0x80000038 + +/* Label ICE runtime configuration section IDs */ +#define ICE_SID_TX_5_LAYER_TOPO 0x10 + +enum ice_block { + ICE_BLK_SW = 0, + ICE_BLK_ACL, + ICE_BLK_FD, + ICE_BLK_RSS, + ICE_BLK_PE, + ICE_BLK_COUNT +}; + +enum ice_sect { + ICE_XLT0 = 0, + ICE_XLT_KB, + ICE_XLT1, + ICE_XLT2, + ICE_PROF_TCAM, + ICE_PROF_REDIR, + ICE_VEC_TBL, + ICE_CDID_KB, + ICE_CDID_REDIR, + ICE_SECT_COUNT +}; + +/* package labels */ +struct ice_label { + __le16 value; +#define ICE_PKG_LABEL_SIZE 64 + char name[ICE_PKG_LABEL_SIZE]; +}; + +struct ice_label_section { + __le16 count; + struct ice_label label[]; +}; + +#define ICE_MAX_LABELS_IN_BUF \ + ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_label_section *)0, \ + label, 1) - \ + sizeof(struct ice_label), \ + sizeof(struct ice_label)) + +struct ice_sw_fv_section { + __le16 count; + __le16 base_offset; + struct ice_fv fv[]; +}; + +struct ice_sw_fv_list_entry { + struct list_head list_entry; + u32 profile_id; + struct ice_fv *fv_ptr; +}; + +/* The BOOST TCAM stores the match packet header in reverse order, meaning + * the fields are reversed; in addition, this means that the normally big endian + * fields of the packet are now little endian. + */ +struct ice_boost_key_value { +#define ICE_BOOST_REMAINING_HV_KEY 15 + u8 remaining_hv_key[ICE_BOOST_REMAINING_HV_KEY]; + __le16 hv_dst_port_key; + __le16 hv_src_port_key; + u8 tcam_search_key; +} __packed; + +struct ice_boost_key { + struct ice_boost_key_value key; + struct ice_boost_key_value key2; +}; + +/* package Boost TCAM entry */ +struct ice_boost_tcam_entry { + __le16 addr; + __le16 reserved; + /* break up the 40 bytes of key into different fields */ + struct ice_boost_key key; + u8 boost_hit_index_group; + /* The following contains bitfields which are not on byte boundaries. + * These fields are currently unused by driver software. + */ +#define ICE_BOOST_BIT_FIELDS 43 + u8 bit_fields[ICE_BOOST_BIT_FIELDS]; +}; + +struct ice_boost_tcam_section { + __le16 count; + __le16 reserved; + struct ice_boost_tcam_entry tcam[]; +}; + +#define ICE_MAX_BST_TCAMS_IN_BUF \ + ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_boost_tcam_section *)0, \ + tcam, 1) - \ + sizeof(struct ice_boost_tcam_entry), \ + sizeof(struct ice_boost_tcam_entry)) + +/* package Marker Ptype TCAM entry */ +struct ice_marker_ptype_tcam_entry { +#define ICE_MARKER_PTYPE_TCAM_ADDR_MAX 1024 + __le16 addr; + __le16 ptype; + u8 keys[20]; +}; + +struct ice_marker_ptype_tcam_section { + __le16 count; + __le16 reserved; + struct ice_marker_ptype_tcam_entry tcam[]; +}; + +#define ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF \ + ICE_MAX_ENTRIES_IN_BUF( \ + struct_size((struct ice_marker_ptype_tcam_section *)0, tcam, \ + 1) - \ + sizeof(struct ice_marker_ptype_tcam_entry), \ + sizeof(struct ice_marker_ptype_tcam_entry)) + +struct ice_xlt1_section { + __le16 count; + __le16 offset; + u8 value[]; +}; + +struct ice_xlt2_section { + __le16 count; + __le16 offset; + __le16 value[]; +}; + +struct ice_prof_redir_section { + __le16 count; + __le16 offset; + u8 redir_value[]; +}; + +/* package buffer building */ + +struct ice_buf_build { + struct ice_buf buf; + u16 reserved_section_table_entries; +}; + +struct ice_pkg_enum { + struct ice_buf_table *buf_table; + u32 buf_idx; + + u32 type; + struct ice_buf_hdr *buf; + u32 sect_idx; + void *sect; + u32 sect_type; + + u32 entry_idx; + void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset); +}; + +int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd); +int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd); + +void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size); + +enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len); + +struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw); + +struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, + struct ice_pkg_hdr *pkg_hdr); + +int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count); +int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); + +int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count); +u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); +void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, + u32 sect_type); + +struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf); + +#endif diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 4191994d8f3a..5b71d40a7dc0 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -664,7 +664,7 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi) if (status) goto err_start_rx_ring; - return status; + return 0; err_start_rx_ring: ice_vsi_free_rx_rings(vsi); @@ -1950,8 +1950,7 @@ ice_phy_type_to_ethtool(struct net_device *netdev, ICE_PHY_TYPE_LOW_100G_CAUI4 | ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC | ICE_PHY_TYPE_LOW_100G_AUI4 | - ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4 | - ICE_PHY_TYPE_LOW_100GBASE_CP2; + ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4; phy_type_mask_hi = ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC | ICE_PHY_TYPE_HIGH_100G_CAUI2 | ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC | @@ -1964,15 +1963,27 @@ ice_phy_type_to_ethtool(struct net_device *netdev, 100000baseCR4_Full); } - phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_SR4 | - ICE_PHY_TYPE_LOW_100GBASE_SR2; - if (phy_types_low & phy_type_mask_lo) { + if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseCR2_Full); + ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, + 100000baseCR2_Full); + } + + if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR4) { ethtool_link_ksettings_add_link_mode(ks, supported, 100000baseSR4_Full); ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, 100000baseSR4_Full); } + if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR2) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseSR2_Full); + ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, + 100000baseSR2_Full); + } + phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_LR4 | ICE_PHY_TYPE_LOW_100GBASE_DR; if (phy_types_low & phy_type_mask_lo) { @@ -1984,14 +1995,20 @@ ice_phy_type_to_ethtool(struct net_device *netdev, phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_KR4 | ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4; - phy_type_mask_hi = ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4; - if (phy_types_low & phy_type_mask_lo || - phy_types_high & phy_type_mask_hi) { + if (phy_types_low & phy_type_mask_lo) { ethtool_link_ksettings_add_link_mode(ks, supported, 100000baseKR4_Full); ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, 100000baseKR4_Full); } + + if (phy_types_high & ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseKR2_Full); + ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, + 100000baseKR2_Full); + } + } #define TEST_SET_BITS_TIMEOUT 50 @@ -2242,17 +2259,15 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) 100baseT_Full)) adv_link_speed |= ICE_AQ_LINK_SPEED_100MB; if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseX_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, 1000baseT_Full) || ethtool_link_ksettings_test_link_mode(ks, advertising, 1000baseKX_Full)) adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 2500baseT_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, 2500baseX_Full)) adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; if (ethtool_link_ksettings_test_link_mode(ks, advertising, @@ -2261,9 +2276,8 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) if (ethtool_link_ksettings_test_link_mode(ks, advertising, 10000baseT_Full) || ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseKR_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, 10000baseSR_Full) || ethtool_link_ksettings_test_link_mode(ks, advertising, 10000baseLR_Full)) @@ -2287,9 +2301,8 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) if (ethtool_link_ksettings_test_link_mode(ks, advertising, 50000baseCR2_Full) || ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseKR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_50GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 50000baseKR2_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, 50000baseSR2_Full)) adv_link_speed |= ICE_AQ_LINK_SPEED_50GB; if (ethtool_link_ksettings_test_link_mode(ks, advertising, @@ -2299,7 +2312,13 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) ethtool_link_ksettings_test_link_mode(ks, advertising, 100000baseLR4_ER4_Full) || ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR4_Full)) + 100000baseKR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 100000baseCR2_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 100000baseSR2_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 100000baseKR2_Full)) adv_link_speed |= ICE_AQ_LINK_SPEED_100GB; return adv_link_speed; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 4b3bb19e1d06..5ce413965930 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -6,23 +6,6 @@ #include "ice_flow.h" #include "ice.h" -/* For supporting double VLAN mode, it is necessary to enable or disable certain - * boost tcam entries. The metadata labels names that match the following - * prefixes will be saved to allow enabling double VLAN mode. - */ -#define ICE_DVM_PRE "BOOST_MAC_VLAN_DVM" /* enable these entries */ -#define ICE_SVM_PRE "BOOST_MAC_VLAN_SVM" /* disable these entries */ - -/* To support tunneling entries by PF, the package will append the PF number to - * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc. - */ -#define ICE_TNL_PRE "TNL_" -static const struct ice_tunnel_type_scan tnls[] = { - { TNL_VXLAN, "TNL_VXLAN_PF" }, - { TNL_GENEVE, "TNL_GENEVE_PF" }, - { TNL_LAST, "" } -}; - static const u32 ice_sect_lkup[ICE_BLK_COUNT][ICE_SECT_COUNT] = { /* SWITCH */ { @@ -104,225 +87,6 @@ static u32 ice_sect_id(enum ice_block blk, enum ice_sect sect) } /** - * ice_pkg_val_buf - * @buf: pointer to the ice buffer - * - * This helper function validates a buffer's header. - */ -static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) -{ - struct ice_buf_hdr *hdr; - u16 section_count; - u16 data_end; - - hdr = (struct ice_buf_hdr *)buf->buf; - /* verify data */ - section_count = le16_to_cpu(hdr->section_count); - if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT) - return NULL; - - data_end = le16_to_cpu(hdr->data_end); - if (data_end < ICE_MIN_S_DATA_END || data_end > ICE_MAX_S_DATA_END) - return NULL; - - return hdr; -} - -/** - * ice_find_buf_table - * @ice_seg: pointer to the ice segment - * - * Returns the address of the buffer table within the ice segment. - */ -static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg) -{ - struct ice_nvm_table *nvms; - - nvms = (struct ice_nvm_table *) - (ice_seg->device_table + - le32_to_cpu(ice_seg->device_table_count)); - - return (__force struct ice_buf_table *) - (nvms->vers + le32_to_cpu(nvms->table_count)); -} - -/** - * ice_pkg_enum_buf - * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) - * @state: pointer to the enum state - * - * This function will enumerate all the buffers in the ice segment. The first - * call is made with the ice_seg parameter non-NULL; on subsequent calls, - * ice_seg is set to NULL which continues the enumeration. When the function - * returns a NULL pointer, then the end of the buffers has been reached, or an - * unexpected value has been detected (for example an invalid section count or - * an invalid buffer end value). - */ -static struct ice_buf_hdr * -ice_pkg_enum_buf(struct ice_seg *ice_seg, struct ice_pkg_enum *state) -{ - if (ice_seg) { - state->buf_table = ice_find_buf_table(ice_seg); - if (!state->buf_table) - return NULL; - - state->buf_idx = 0; - return ice_pkg_val_buf(state->buf_table->buf_array); - } - - if (++state->buf_idx < le32_to_cpu(state->buf_table->buf_count)) - return ice_pkg_val_buf(state->buf_table->buf_array + - state->buf_idx); - else - return NULL; -} - -/** - * ice_pkg_advance_sect - * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) - * @state: pointer to the enum state - * - * This helper function will advance the section within the ice segment, - * also advancing the buffer if needed. - */ -static bool -ice_pkg_advance_sect(struct ice_seg *ice_seg, struct ice_pkg_enum *state) -{ - if (!ice_seg && !state->buf) - return false; - - if (!ice_seg && state->buf) - if (++state->sect_idx < le16_to_cpu(state->buf->section_count)) - return true; - - state->buf = ice_pkg_enum_buf(ice_seg, state); - if (!state->buf) - return false; - - /* start of new buffer, reset section index */ - state->sect_idx = 0; - return true; -} - -/** - * ice_pkg_enum_section - * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) - * @state: pointer to the enum state - * @sect_type: section type to enumerate - * - * This function will enumerate all the sections of a particular type in the - * ice segment. The first call is made with the ice_seg parameter non-NULL; - * on subsequent calls, ice_seg is set to NULL which continues the enumeration. - * When the function returns a NULL pointer, then the end of the matching - * sections has been reached. - */ -static void * -ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, - u32 sect_type) -{ - u16 offset, size; - - if (ice_seg) - state->type = sect_type; - - if (!ice_pkg_advance_sect(ice_seg, state)) - return NULL; - - /* scan for next matching section */ - while (state->buf->section_entry[state->sect_idx].type != - cpu_to_le32(state->type)) - if (!ice_pkg_advance_sect(NULL, state)) - return NULL; - - /* validate section */ - offset = le16_to_cpu(state->buf->section_entry[state->sect_idx].offset); - if (offset < ICE_MIN_S_OFF || offset > ICE_MAX_S_OFF) - return NULL; - - size = le16_to_cpu(state->buf->section_entry[state->sect_idx].size); - if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) - return NULL; - - /* make sure the section fits in the buffer */ - if (offset + size > ICE_PKG_BUF_SIZE) - return NULL; - - state->sect_type = - le32_to_cpu(state->buf->section_entry[state->sect_idx].type); - - /* calc pointer to this section */ - state->sect = ((u8 *)state->buf) + - le16_to_cpu(state->buf->section_entry[state->sect_idx].offset); - - return state->sect; -} - -/** - * ice_pkg_enum_entry - * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) - * @state: pointer to the enum state - * @sect_type: section type to enumerate - * @offset: pointer to variable that receives the offset in the table (optional) - * @handler: function that handles access to the entries into the section type - * - * This function will enumerate all the entries in particular section type in - * the ice segment. The first call is made with the ice_seg parameter non-NULL; - * on subsequent calls, ice_seg is set to NULL which continues the enumeration. - * When the function returns a NULL pointer, then the end of the entries has - * been reached. - * - * Since each section may have a different header and entry size, the handler - * function is needed to determine the number and location entries in each - * section. - * - * The offset parameter is optional, but should be used for sections that - * contain an offset for each section table. For such cases, the section handler - * function must return the appropriate offset + index to give the absolution - * offset for each entry. For example, if the base for a section's header - * indicates a base offset of 10, and the index for the entry is 2, then - * section handler function should set the offset to 10 + 2 = 12. - */ -static void * -ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state, - u32 sect_type, u32 *offset, - void *(*handler)(u32 sect_type, void *section, - u32 index, u32 *offset)) -{ - void *entry; - - if (ice_seg) { - if (!handler) - return NULL; - - if (!ice_pkg_enum_section(ice_seg, state, sect_type)) - return NULL; - - state->entry_idx = 0; - state->handler = handler; - } else { - state->entry_idx++; - } - - if (!state->handler) - return NULL; - - /* get entry */ - entry = state->handler(state->sect_type, state->sect, state->entry_idx, - offset); - if (!entry) { - /* end of a section, look for another section of this type */ - if (!ice_pkg_enum_section(NULL, state, 0)) - return NULL; - - state->entry_idx = 0; - entry = state->handler(state->sect_type, state->sect, - state->entry_idx, offset); - } - - return entry; -} - -/** * ice_hw_ptype_ena - check if the PTYPE is enabled or not * @hw: pointer to the HW structure * @ptype: the hardware PTYPE @@ -333,312 +97,6 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype) test_bit(ptype, hw->hw_ptype); } -/** - * ice_marker_ptype_tcam_handler - * @sect_type: section type - * @section: pointer to section - * @index: index of the Marker PType TCAM entry to be returned - * @offset: pointer to receive absolute offset, always 0 for ptype TCAM sections - * - * This is a callback function that can be passed to ice_pkg_enum_entry. - * Handles enumeration of individual Marker PType TCAM entries. - */ -static void * -ice_marker_ptype_tcam_handler(u32 sect_type, void *section, u32 index, - u32 *offset) -{ - struct ice_marker_ptype_tcam_section *marker_ptype; - - if (sect_type != ICE_SID_RXPARSER_MARKER_PTYPE) - return NULL; - - if (index > ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF) - return NULL; - - if (offset) - *offset = 0; - - marker_ptype = section; - if (index >= le16_to_cpu(marker_ptype->count)) - return NULL; - - return marker_ptype->tcam + index; -} - -/** - * ice_fill_hw_ptype - fill the enabled PTYPE bit information - * @hw: pointer to the HW structure - */ -static void ice_fill_hw_ptype(struct ice_hw *hw) -{ - struct ice_marker_ptype_tcam_entry *tcam; - struct ice_seg *seg = hw->seg; - struct ice_pkg_enum state; - - bitmap_zero(hw->hw_ptype, ICE_FLOW_PTYPE_MAX); - if (!seg) - return; - - memset(&state, 0, sizeof(state)); - - do { - tcam = ice_pkg_enum_entry(seg, &state, - ICE_SID_RXPARSER_MARKER_PTYPE, NULL, - ice_marker_ptype_tcam_handler); - if (tcam && - le16_to_cpu(tcam->addr) < ICE_MARKER_PTYPE_TCAM_ADDR_MAX && - le16_to_cpu(tcam->ptype) < ICE_FLOW_PTYPE_MAX) - set_bit(le16_to_cpu(tcam->ptype), hw->hw_ptype); - - seg = NULL; - } while (tcam); -} - -/** - * ice_boost_tcam_handler - * @sect_type: section type - * @section: pointer to section - * @index: index of the boost TCAM entry to be returned - * @offset: pointer to receive absolute offset, always 0 for boost TCAM sections - * - * This is a callback function that can be passed to ice_pkg_enum_entry. - * Handles enumeration of individual boost TCAM entries. - */ -static void * -ice_boost_tcam_handler(u32 sect_type, void *section, u32 index, u32 *offset) -{ - struct ice_boost_tcam_section *boost; - - if (!section) - return NULL; - - if (sect_type != ICE_SID_RXPARSER_BOOST_TCAM) - return NULL; - - /* cppcheck-suppress nullPointer */ - if (index > ICE_MAX_BST_TCAMS_IN_BUF) - return NULL; - - if (offset) - *offset = 0; - - boost = section; - if (index >= le16_to_cpu(boost->count)) - return NULL; - - return boost->tcam + index; -} - -/** - * ice_find_boost_entry - * @ice_seg: pointer to the ice segment (non-NULL) - * @addr: Boost TCAM address of entry to search for - * @entry: returns pointer to the entry - * - * Finds a particular Boost TCAM entry and returns a pointer to that entry - * if it is found. The ice_seg parameter must not be NULL since the first call - * to ice_pkg_enum_entry requires a pointer to an actual ice_segment structure. - */ -static int -ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr, - struct ice_boost_tcam_entry **entry) -{ - struct ice_boost_tcam_entry *tcam; - struct ice_pkg_enum state; - - memset(&state, 0, sizeof(state)); - - if (!ice_seg) - return -EINVAL; - - do { - tcam = ice_pkg_enum_entry(ice_seg, &state, - ICE_SID_RXPARSER_BOOST_TCAM, NULL, - ice_boost_tcam_handler); - if (tcam && le16_to_cpu(tcam->addr) == addr) { - *entry = tcam; - return 0; - } - - ice_seg = NULL; - } while (tcam); - - *entry = NULL; - return -EIO; -} - -/** - * ice_label_enum_handler - * @sect_type: section type - * @section: pointer to section - * @index: index of the label entry to be returned - * @offset: pointer to receive absolute offset, always zero for label sections - * - * This is a callback function that can be passed to ice_pkg_enum_entry. - * Handles enumeration of individual label entries. - */ -static void * -ice_label_enum_handler(u32 __always_unused sect_type, void *section, u32 index, - u32 *offset) -{ - struct ice_label_section *labels; - - if (!section) - return NULL; - - /* cppcheck-suppress nullPointer */ - if (index > ICE_MAX_LABELS_IN_BUF) - return NULL; - - if (offset) - *offset = 0; - - labels = section; - if (index >= le16_to_cpu(labels->count)) - return NULL; - - return labels->label + index; -} - -/** - * ice_enum_labels - * @ice_seg: pointer to the ice segment (NULL on subsequent calls) - * @type: the section type that will contain the label (0 on subsequent calls) - * @state: ice_pkg_enum structure that will hold the state of the enumeration - * @value: pointer to a value that will return the label's value if found - * - * Enumerates a list of labels in the package. The caller will call - * ice_enum_labels(ice_seg, type, ...) to start the enumeration, then call - * ice_enum_labels(NULL, 0, ...) to continue. When the function returns a NULL - * the end of the list has been reached. - */ -static char * -ice_enum_labels(struct ice_seg *ice_seg, u32 type, struct ice_pkg_enum *state, - u16 *value) -{ - struct ice_label *label; - - /* Check for valid label section on first call */ - if (type && !(type >= ICE_SID_LBL_FIRST && type <= ICE_SID_LBL_LAST)) - return NULL; - - label = ice_pkg_enum_entry(ice_seg, state, type, NULL, - ice_label_enum_handler); - if (!label) - return NULL; - - *value = le16_to_cpu(label->value); - return label->name; -} - -/** - * ice_add_tunnel_hint - * @hw: pointer to the HW structure - * @label_name: label text - * @val: value of the tunnel port boost entry - */ -static void ice_add_tunnel_hint(struct ice_hw *hw, char *label_name, u16 val) -{ - if (hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) { - u16 i; - - for (i = 0; tnls[i].type != TNL_LAST; i++) { - size_t len = strlen(tnls[i].label_prefix); - - /* Look for matching label start, before continuing */ - if (strncmp(label_name, tnls[i].label_prefix, len)) - continue; - - /* Make sure this label matches our PF. Note that the PF - * character ('0' - '7') will be located where our - * prefix string's null terminator is located. - */ - if ((label_name[len] - '0') == hw->pf_id) { - hw->tnl.tbl[hw->tnl.count].type = tnls[i].type; - hw->tnl.tbl[hw->tnl.count].valid = false; - hw->tnl.tbl[hw->tnl.count].boost_addr = val; - hw->tnl.tbl[hw->tnl.count].port = 0; - hw->tnl.count++; - break; - } - } - } -} - -/** - * ice_add_dvm_hint - * @hw: pointer to the HW structure - * @val: value of the boost entry - * @enable: true if entry needs to be enabled, or false if needs to be disabled - */ -static void ice_add_dvm_hint(struct ice_hw *hw, u16 val, bool enable) -{ - if (hw->dvm_upd.count < ICE_DVM_MAX_ENTRIES) { - hw->dvm_upd.tbl[hw->dvm_upd.count].boost_addr = val; - hw->dvm_upd.tbl[hw->dvm_upd.count].enable = enable; - hw->dvm_upd.count++; - } -} - -/** - * ice_init_pkg_hints - * @hw: pointer to the HW structure - * @ice_seg: pointer to the segment of the package scan (non-NULL) - * - * This function will scan the package and save off relevant information - * (hints or metadata) for driver use. The ice_seg parameter must not be NULL - * since the first call to ice_enum_labels requires a pointer to an actual - * ice_seg structure. - */ -static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) -{ - struct ice_pkg_enum state; - char *label_name; - u16 val; - int i; - - memset(&hw->tnl, 0, sizeof(hw->tnl)); - memset(&state, 0, sizeof(state)); - - if (!ice_seg) - return; - - label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state, - &val); - - while (label_name) { - if (!strncmp(label_name, ICE_TNL_PRE, strlen(ICE_TNL_PRE))) - /* check for a tunnel entry */ - ice_add_tunnel_hint(hw, label_name, val); - - /* check for a dvm mode entry */ - else if (!strncmp(label_name, ICE_DVM_PRE, strlen(ICE_DVM_PRE))) - ice_add_dvm_hint(hw, val, true); - - /* check for a svm mode entry */ - else if (!strncmp(label_name, ICE_SVM_PRE, strlen(ICE_SVM_PRE))) - ice_add_dvm_hint(hw, val, false); - - label_name = ice_enum_labels(NULL, 0, &state, &val); - } - - /* Cache the appropriate boost TCAM entry pointers for tunnels */ - for (i = 0; i < hw->tnl.count; i++) { - ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr, - &hw->tnl.tbl[i].boost_entry); - if (hw->tnl.tbl[i].boost_entry) { - hw->tnl.tbl[i].valid = true; - if (hw->tnl.tbl[i].type < __TNL_TYPE_CNT) - hw->tnl.valid_count[hw->tnl.tbl[i].type]++; - } - } - - /* Cache the appropriate boost TCAM entry pointers for DVM and SVM */ - for (i = 0; i < hw->dvm_upd.count; i++) - ice_find_boost_entry(ice_seg, hw->dvm_upd.tbl[i].boost_addr, - &hw->dvm_upd.tbl[i].boost_entry); -} - /* Key creation */ #define ICE_DC_KEY 0x1 /* don't care */ @@ -810,51 +268,6 @@ ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off, } /** - * ice_acquire_global_cfg_lock - * @hw: pointer to the HW structure - * @access: access type (read or write) - * - * This function will request ownership of the global config lock for reading - * or writing of the package. When attempting to obtain write access, the - * caller must check for the following two return values: - * - * 0 - Means the caller has acquired the global config lock - * and can perform writing of the package. - * -EALREADY - Indicates another driver has already written the - * package or has found that no update was necessary; in - * this case, the caller can just skip performing any - * update of the package. - */ -static int -ice_acquire_global_cfg_lock(struct ice_hw *hw, - enum ice_aq_res_access_type access) -{ - int status; - - status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access, - ICE_GLOBAL_CFG_LOCK_TIMEOUT); - - if (!status) - mutex_lock(&ice_global_cfg_lock_sw); - else if (status == -EALREADY) - ice_debug(hw, ICE_DBG_PKG, "Global config lock: No work to do\n"); - - return status; -} - -/** - * ice_release_global_cfg_lock - * @hw: pointer to the HW structure - * - * This function will release the global config lock. - */ -static void ice_release_global_cfg_lock(struct ice_hw *hw) -{ - mutex_unlock(&ice_global_cfg_lock_sw); - ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID); -} - -/** * ice_acquire_change_lock * @hw: pointer to the HW structure * @access: access type (read or write) @@ -880,1325 +293,6 @@ void ice_release_change_lock(struct ice_hw *hw) } /** - * ice_aq_download_pkg - * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer to transfer - * @buf_size: the size of the package buffer - * @last_buf: last buffer indicator - * @error_offset: returns error offset - * @error_info: returns error information - * @cd: pointer to command details structure or NULL - * - * Download Package (0x0C40) - */ -static int -ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd) -{ - struct ice_aqc_download_pkg *cmd; - struct ice_aq_desc desc; - int status; - - if (error_offset) - *error_offset = 0; - if (error_info) - *error_info = 0; - - cmd = &desc.params.download_pkg; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - - if (last_buf) - cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; - - status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == -EIO) { - /* Read error from buffer only when the FW returned an error */ - struct ice_aqc_download_pkg_resp *resp; - - resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } - - return status; -} - -/** - * ice_aq_upload_section - * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer which will receive the section - * @buf_size: the size of the package buffer - * @cd: pointer to command details structure or NULL - * - * Upload Section (0x0C41) - */ -int -ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, struct ice_sq_cd *cd) -{ - struct ice_aq_desc desc; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - - return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); -} - -/** - * ice_aq_update_pkg - * @hw: pointer to the hardware structure - * @pkg_buf: the package cmd buffer - * @buf_size: the size of the package cmd buffer - * @last_buf: last buffer indicator - * @error_offset: returns error offset - * @error_info: returns error information - * @cd: pointer to command details structure or NULL - * - * Update Package (0x0C42) - */ -static int -ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, - bool last_buf, u32 *error_offset, u32 *error_info, - struct ice_sq_cd *cd) -{ - struct ice_aqc_download_pkg *cmd; - struct ice_aq_desc desc; - int status; - - if (error_offset) - *error_offset = 0; - if (error_info) - *error_info = 0; - - cmd = &desc.params.download_pkg; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - - if (last_buf) - cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; - - status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == -EIO) { - /* Read error from buffer only when the FW returned an error */ - struct ice_aqc_download_pkg_resp *resp; - - resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } - - return status; -} - -/** - * ice_find_seg_in_pkg - * @hw: pointer to the hardware structure - * @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK) - * @pkg_hdr: pointer to the package header to be searched - * - * This function searches a package file for a particular segment type. On - * success it returns a pointer to the segment header, otherwise it will - * return NULL. - */ -static struct ice_generic_seg_hdr * -ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr) -{ - u32 i; - - ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n", - pkg_hdr->pkg_format_ver.major, pkg_hdr->pkg_format_ver.minor, - pkg_hdr->pkg_format_ver.update, - pkg_hdr->pkg_format_ver.draft); - - /* Search all package segments for the requested segment type */ - for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { - struct ice_generic_seg_hdr *seg; - - seg = (struct ice_generic_seg_hdr *) - ((u8 *)pkg_hdr + le32_to_cpu(pkg_hdr->seg_offset[i])); - - if (le32_to_cpu(seg->seg_type) == seg_type) - return seg; - } - - return NULL; -} - -/** - * ice_update_pkg_no_lock - * @hw: pointer to the hardware structure - * @bufs: pointer to an array of buffers - * @count: the number of buffers in the array - */ -static int -ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count) -{ - int status = 0; - u32 i; - - for (i = 0; i < count; i++) { - struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i); - bool last = ((i + 1) == count); - u32 offset, info; - - status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end), - last, &offset, &info, NULL); - - if (status) { - ice_debug(hw, ICE_DBG_PKG, "Update pkg failed: err %d off %d inf %d\n", - status, offset, info); - break; - } - } - - return status; -} - -/** - * ice_update_pkg - * @hw: pointer to the hardware structure - * @bufs: pointer to an array of buffers - * @count: the number of buffers in the array - * - * Obtains change lock and updates package. - */ -static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) -{ - int status; - - status = ice_acquire_change_lock(hw, ICE_RES_WRITE); - if (status) - return status; - - status = ice_update_pkg_no_lock(hw, bufs, count); - - ice_release_change_lock(hw); - - return status; -} - -static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err) -{ - switch (aq_err) { - case ICE_AQ_RC_ENOSEC: - case ICE_AQ_RC_EBADSIG: - return ICE_DDP_PKG_FILE_SIGNATURE_INVALID; - case ICE_AQ_RC_ESVN: - return ICE_DDP_PKG_FILE_REVISION_TOO_LOW; - case ICE_AQ_RC_EBADMAN: - case ICE_AQ_RC_EBADBUF: - return ICE_DDP_PKG_LOAD_ERROR; - default: - return ICE_DDP_PKG_ERR; - } -} - -/** - * ice_dwnld_cfg_bufs - * @hw: pointer to the hardware structure - * @bufs: pointer to an array of buffers - * @count: the number of buffers in the array - * - * Obtains global config lock and downloads the package configuration buffers - * to the firmware. Metadata buffers are skipped, and the first metadata buffer - * found indicates that the rest of the buffers are all metadata buffers. - */ -static enum ice_ddp_state -ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) -{ - enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; - struct ice_buf_hdr *bh; - enum ice_aq_err err; - u32 offset, info, i; - int status; - - if (!bufs || !count) - return ICE_DDP_PKG_ERR; - - /* If the first buffer's first section has its metadata bit set - * then there are no buffers to be downloaded, and the operation is - * considered a success. - */ - bh = (struct ice_buf_hdr *)bufs; - if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) - return ICE_DDP_PKG_SUCCESS; - - status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); - if (status) { - if (status == -EALREADY) - return ICE_DDP_PKG_ALREADY_LOADED; - return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); - } - - for (i = 0; i < count; i++) { - bool last = ((i + 1) == count); - - if (!last) { - /* check next buffer for metadata flag */ - bh = (struct ice_buf_hdr *)(bufs + i + 1); - - /* A set metadata flag in the next buffer will signal - * that the current buffer will be the last buffer - * downloaded - */ - if (le16_to_cpu(bh->section_count)) - if (le32_to_cpu(bh->section_entry[0].type) & - ICE_METADATA_BUF) - last = true; - } - - bh = (struct ice_buf_hdr *)(bufs + i); - - status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, - &offset, &info, NULL); - - /* Save AQ status from download package */ - if (status) { - ice_debug(hw, ICE_DBG_PKG, "Pkg download failed: err %d off %d inf %d\n", - status, offset, info); - err = hw->adminq.sq_last_status; - state = ice_map_aq_err_to_ddp_state(err); - break; - } - - if (last) - break; - } - - if (!status) { - status = ice_set_vlan_mode(hw); - if (status) - ice_debug(hw, ICE_DBG_PKG, "Failed to set VLAN mode: err %d\n", - status); - } - - ice_release_global_cfg_lock(hw); - - return state; -} - -/** - * ice_aq_get_pkg_info_list - * @hw: pointer to the hardware structure - * @pkg_info: the buffer which will receive the information list - * @buf_size: the size of the pkg_info information buffer - * @cd: pointer to command details structure or NULL - * - * Get Package Info List (0x0C43) - */ -static int -ice_aq_get_pkg_info_list(struct ice_hw *hw, - struct ice_aqc_get_pkg_info_resp *pkg_info, - u16 buf_size, struct ice_sq_cd *cd) -{ - struct ice_aq_desc desc; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); - - return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); -} - -/** - * ice_download_pkg - * @hw: pointer to the hardware structure - * @ice_seg: pointer to the segment of the package to be downloaded - * - * Handles the download of a complete package. - */ -static enum ice_ddp_state -ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) -{ - struct ice_buf_table *ice_buf_tbl; - int status; - - ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", - ice_seg->hdr.seg_format_ver.major, - ice_seg->hdr.seg_format_ver.minor, - ice_seg->hdr.seg_format_ver.update, - ice_seg->hdr.seg_format_ver.draft); - - ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n", - le32_to_cpu(ice_seg->hdr.seg_type), - le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id); - - ice_buf_tbl = ice_find_buf_table(ice_seg); - - ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", - le32_to_cpu(ice_buf_tbl->buf_count)); - - status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, - le32_to_cpu(ice_buf_tbl->buf_count)); - - ice_post_pkg_dwnld_vlan_mode_cfg(hw); - - return status; -} - -/** - * ice_init_pkg_info - * @hw: pointer to the hardware structure - * @pkg_hdr: pointer to the driver's package hdr - * - * Saves off the package details into the HW structure. - */ -static enum ice_ddp_state -ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) -{ - struct ice_generic_seg_hdr *seg_hdr; - - if (!pkg_hdr) - return ICE_DDP_PKG_ERR; - - seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); - if (seg_hdr) { - struct ice_meta_sect *meta; - struct ice_pkg_enum state; - - memset(&state, 0, sizeof(state)); - - /* Get package information from the Metadata Section */ - meta = ice_pkg_enum_section((struct ice_seg *)seg_hdr, &state, - ICE_SID_METADATA); - if (!meta) { - ice_debug(hw, ICE_DBG_INIT, "Did not find ice metadata section in package\n"); - return ICE_DDP_PKG_INVALID_FILE; - } - - hw->pkg_ver = meta->ver; - memcpy(hw->pkg_name, meta->name, sizeof(meta->name)); - - ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n", - meta->ver.major, meta->ver.minor, meta->ver.update, - meta->ver.draft, meta->name); - - hw->ice_seg_fmt_ver = seg_hdr->seg_format_ver; - memcpy(hw->ice_seg_id, seg_hdr->seg_id, - sizeof(hw->ice_seg_id)); - - ice_debug(hw, ICE_DBG_PKG, "Ice Seg: %d.%d.%d.%d, %s\n", - seg_hdr->seg_format_ver.major, - seg_hdr->seg_format_ver.minor, - seg_hdr->seg_format_ver.update, - seg_hdr->seg_format_ver.draft, - seg_hdr->seg_id); - } else { - ice_debug(hw, ICE_DBG_INIT, "Did not find ice segment in driver package\n"); - return ICE_DDP_PKG_INVALID_FILE; - } - - return ICE_DDP_PKG_SUCCESS; -} - -/** - * ice_get_pkg_info - * @hw: pointer to the hardware structure - * - * Store details of the package currently loaded in HW into the HW structure. - */ -static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) -{ - enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; - struct ice_aqc_get_pkg_info_resp *pkg_info; - u16 size; - u32 i; - - size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT); - pkg_info = kzalloc(size, GFP_KERNEL); - if (!pkg_info) - return ICE_DDP_PKG_ERR; - - if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) { - state = ICE_DDP_PKG_ERR; - goto init_pkg_free_alloc; - } - - for (i = 0; i < le32_to_cpu(pkg_info->count); i++) { -#define ICE_PKG_FLAG_COUNT 4 - char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 }; - u8 place = 0; - - if (pkg_info->pkg_info[i].is_active) { - flags[place++] = 'A'; - hw->active_pkg_ver = pkg_info->pkg_info[i].ver; - hw->active_track_id = - le32_to_cpu(pkg_info->pkg_info[i].track_id); - memcpy(hw->active_pkg_name, - pkg_info->pkg_info[i].name, - sizeof(pkg_info->pkg_info[i].name)); - hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm; - } - if (pkg_info->pkg_info[i].is_active_at_boot) - flags[place++] = 'B'; - if (pkg_info->pkg_info[i].is_modified) - flags[place++] = 'M'; - if (pkg_info->pkg_info[i].is_in_nvm) - flags[place++] = 'N'; - - ice_debug(hw, ICE_DBG_PKG, "Pkg[%d]: %d.%d.%d.%d,%s,%s\n", - i, pkg_info->pkg_info[i].ver.major, - pkg_info->pkg_info[i].ver.minor, - pkg_info->pkg_info[i].ver.update, - pkg_info->pkg_info[i].ver.draft, - pkg_info->pkg_info[i].name, flags); - } - -init_pkg_free_alloc: - kfree(pkg_info); - - return state; -} - -/** - * ice_verify_pkg - verify package - * @pkg: pointer to the package buffer - * @len: size of the package buffer - * - * Verifies various attributes of the package file, including length, format - * version, and the requirement of at least one segment. - */ -static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) -{ - u32 seg_count; - u32 i; - - if (len < struct_size(pkg, seg_offset, 1)) - return ICE_DDP_PKG_INVALID_FILE; - - if (pkg->pkg_format_ver.major != ICE_PKG_FMT_VER_MAJ || - pkg->pkg_format_ver.minor != ICE_PKG_FMT_VER_MNR || - pkg->pkg_format_ver.update != ICE_PKG_FMT_VER_UPD || - pkg->pkg_format_ver.draft != ICE_PKG_FMT_VER_DFT) - return ICE_DDP_PKG_INVALID_FILE; - - /* pkg must have at least one segment */ - seg_count = le32_to_cpu(pkg->seg_count); - if (seg_count < 1) - return ICE_DDP_PKG_INVALID_FILE; - - /* make sure segment array fits in package length */ - if (len < struct_size(pkg, seg_offset, seg_count)) - return ICE_DDP_PKG_INVALID_FILE; - - /* all segments must fit within length */ - for (i = 0; i < seg_count; i++) { - u32 off = le32_to_cpu(pkg->seg_offset[i]); - struct ice_generic_seg_hdr *seg; - - /* segment header must fit */ - if (len < off + sizeof(*seg)) - return ICE_DDP_PKG_INVALID_FILE; - - seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off); - - /* segment body must fit */ - if (len < off + le32_to_cpu(seg->seg_size)) - return ICE_DDP_PKG_INVALID_FILE; - } - - return ICE_DDP_PKG_SUCCESS; -} - -/** - * ice_free_seg - free package segment pointer - * @hw: pointer to the hardware structure - * - * Frees the package segment pointer in the proper manner, depending on if the - * segment was allocated or just the passed in pointer was stored. - */ -void ice_free_seg(struct ice_hw *hw) -{ - if (hw->pkg_copy) { - devm_kfree(ice_hw_to_dev(hw), hw->pkg_copy); - hw->pkg_copy = NULL; - hw->pkg_size = 0; - } - hw->seg = NULL; -} - -/** - * ice_init_pkg_regs - initialize additional package registers - * @hw: pointer to the hardware structure - */ -static void ice_init_pkg_regs(struct ice_hw *hw) -{ -#define ICE_SW_BLK_INP_MASK_L 0xFFFFFFFF -#define ICE_SW_BLK_INP_MASK_H 0x0000FFFF -#define ICE_SW_BLK_IDX 0 - - /* setup Switch block input mask, which is 48-bits in two parts */ - wr32(hw, GL_PREEXT_L2_PMASK0(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_L); - wr32(hw, GL_PREEXT_L2_PMASK1(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_H); -} - -/** - * ice_chk_pkg_version - check package version for compatibility with driver - * @pkg_ver: pointer to a version structure to check - * - * Check to make sure that the package about to be downloaded is compatible with - * the driver. To be compatible, the major and minor components of the package - * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR - * definitions. - */ -static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) -{ - if (pkg_ver->major > ICE_PKG_SUPP_VER_MAJ || - (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ && - pkg_ver->minor > ICE_PKG_SUPP_VER_MNR)) - return ICE_DDP_PKG_FILE_VERSION_TOO_HIGH; - else if (pkg_ver->major < ICE_PKG_SUPP_VER_MAJ || - (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ && - pkg_ver->minor < ICE_PKG_SUPP_VER_MNR)) - return ICE_DDP_PKG_FILE_VERSION_TOO_LOW; - - return ICE_DDP_PKG_SUCCESS; -} - -/** - * ice_chk_pkg_compat - * @hw: pointer to the hardware structure - * @ospkg: pointer to the package hdr - * @seg: pointer to the package segment hdr - * - * This function checks the package version compatibility with driver and NVM - */ -static enum ice_ddp_state -ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, - struct ice_seg **seg) -{ - struct ice_aqc_get_pkg_info_resp *pkg; - enum ice_ddp_state state; - u16 size; - u32 i; - - /* Check package version compatibility */ - state = ice_chk_pkg_version(&hw->pkg_ver); - if (state) { - ice_debug(hw, ICE_DBG_INIT, "Package version check failed.\n"); - return state; - } - - /* find ICE segment in given package */ - *seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, - ospkg); - if (!*seg) { - ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n"); - return ICE_DDP_PKG_INVALID_FILE; - } - - /* Check if FW is compatible with the OS package */ - size = struct_size(pkg, pkg_info, ICE_PKG_CNT); - pkg = kzalloc(size, GFP_KERNEL); - if (!pkg) - return ICE_DDP_PKG_ERR; - - if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) { - state = ICE_DDP_PKG_LOAD_ERROR; - goto fw_ddp_compat_free_alloc; - } - - for (i = 0; i < le32_to_cpu(pkg->count); i++) { - /* loop till we find the NVM package */ - if (!pkg->pkg_info[i].is_in_nvm) - continue; - if ((*seg)->hdr.seg_format_ver.major != - pkg->pkg_info[i].ver.major || - (*seg)->hdr.seg_format_ver.minor > - pkg->pkg_info[i].ver.minor) { - state = ICE_DDP_PKG_FW_MISMATCH; - ice_debug(hw, ICE_DBG_INIT, "OS package is not compatible with NVM.\n"); - } - /* done processing NVM package so break */ - break; - } -fw_ddp_compat_free_alloc: - kfree(pkg); - return state; -} - -/** - * ice_sw_fv_handler - * @sect_type: section type - * @section: pointer to section - * @index: index of the field vector entry to be returned - * @offset: ptr to variable that receives the offset in the field vector table - * - * This is a callback function that can be passed to ice_pkg_enum_entry. - * This function treats the given section as of type ice_sw_fv_section and - * enumerates offset field. "offset" is an index into the field vector table. - */ -static void * -ice_sw_fv_handler(u32 sect_type, void *section, u32 index, u32 *offset) -{ - struct ice_sw_fv_section *fv_section = section; - - if (!section || sect_type != ICE_SID_FLD_VEC_SW) - return NULL; - if (index >= le16_to_cpu(fv_section->count)) - return NULL; - if (offset) - /* "index" passed in to this function is relative to a given - * 4k block. To get to the true index into the field vector - * table need to add the relative index to the base_offset - * field of this section - */ - *offset = le16_to_cpu(fv_section->base_offset) + index; - return fv_section->fv + index; -} - -/** - * ice_get_prof_index_max - get the max profile index for used profile - * @hw: pointer to the HW struct - * - * Calling this function will get the max profile index for used profile - * and store the index number in struct ice_switch_info *switch_info - * in HW for following use. - */ -static int ice_get_prof_index_max(struct ice_hw *hw) -{ - u16 prof_index = 0, j, max_prof_index = 0; - struct ice_pkg_enum state; - struct ice_seg *ice_seg; - bool flag = false; - struct ice_fv *fv; - u32 offset; - - memset(&state, 0, sizeof(state)); - - if (!hw->seg) - return -EINVAL; - - ice_seg = hw->seg; - - do { - fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, - &offset, ice_sw_fv_handler); - if (!fv) - break; - ice_seg = NULL; - - /* in the profile that not be used, the prot_id is set to 0xff - * and the off is set to 0x1ff for all the field vectors. - */ - for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) - if (fv->ew[j].prot_id != ICE_PROT_INVALID || - fv->ew[j].off != ICE_FV_OFFSET_INVAL) - flag = true; - if (flag && prof_index > max_prof_index) - max_prof_index = prof_index; - - prof_index++; - flag = false; - } while (fv); - - hw->switch_info->max_used_prof_index = max_prof_index; - - return 0; -} - -/** - * ice_get_ddp_pkg_state - get DDP pkg state after download - * @hw: pointer to the HW struct - * @already_loaded: indicates if pkg was already loaded onto the device - */ -static enum ice_ddp_state -ice_get_ddp_pkg_state(struct ice_hw *hw, bool already_loaded) -{ - if (hw->pkg_ver.major == hw->active_pkg_ver.major && - hw->pkg_ver.minor == hw->active_pkg_ver.minor && - hw->pkg_ver.update == hw->active_pkg_ver.update && - hw->pkg_ver.draft == hw->active_pkg_ver.draft && - !memcmp(hw->pkg_name, hw->active_pkg_name, sizeof(hw->pkg_name))) { - if (already_loaded) - return ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED; - else - return ICE_DDP_PKG_SUCCESS; - } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ || - hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) { - return ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED; - } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && - hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) { - return ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED; - } else { - return ICE_DDP_PKG_ERR; - } -} - -/** - * ice_init_pkg - initialize/download package - * @hw: pointer to the hardware structure - * @buf: pointer to the package buffer - * @len: size of the package buffer - * - * This function initializes a package. The package contains HW tables - * required to do packet processing. First, the function extracts package - * information such as version. Then it finds the ice configuration segment - * within the package; this function then saves a copy of the segment pointer - * within the supplied package buffer. Next, the function will cache any hints - * from the package, followed by downloading the package itself. Note, that if - * a previous PF driver has already downloaded the package successfully, then - * the current driver will not have to download the package again. - * - * The local package contents will be used to query default behavior and to - * update specific sections of the HW's version of the package (e.g. to update - * the parse graph to understand new protocols). - * - * This function stores a pointer to the package buffer memory, and it is - * expected that the supplied buffer will not be freed immediately. If the - * package buffer needs to be freed, such as when read from a file, use - * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this - * case. - */ -enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) -{ - bool already_loaded = false; - enum ice_ddp_state state; - struct ice_pkg_hdr *pkg; - struct ice_seg *seg; - - if (!buf || !len) - return ICE_DDP_PKG_ERR; - - pkg = (struct ice_pkg_hdr *)buf; - state = ice_verify_pkg(pkg, len); - if (state) { - ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n", - state); - return state; - } - - /* initialize package info */ - state = ice_init_pkg_info(hw, pkg); - if (state) - return state; - - /* before downloading the package, check package version for - * compatibility with driver - */ - state = ice_chk_pkg_compat(hw, pkg, &seg); - if (state) - return state; - - /* initialize package hints and then download package */ - ice_init_pkg_hints(hw, seg); - state = ice_download_pkg(hw, seg); - if (state == ICE_DDP_PKG_ALREADY_LOADED) { - ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n"); - already_loaded = true; - } - - /* Get information on the package currently loaded in HW, then make sure - * the driver is compatible with this version. - */ - if (!state || state == ICE_DDP_PKG_ALREADY_LOADED) { - state = ice_get_pkg_info(hw); - if (!state) - state = ice_get_ddp_pkg_state(hw, already_loaded); - } - - if (ice_is_init_pkg_successful(state)) { - hw->seg = seg; - /* on successful package download update other required - * registers to support the package and fill HW tables - * with package content. - */ - ice_init_pkg_regs(hw); - ice_fill_blk_tbls(hw); - ice_fill_hw_ptype(hw); - ice_get_prof_index_max(hw); - } else { - ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", - state); - } - - return state; -} - -/** - * ice_copy_and_init_pkg - initialize/download a copy of the package - * @hw: pointer to the hardware structure - * @buf: pointer to the package buffer - * @len: size of the package buffer - * - * This function copies the package buffer, and then calls ice_init_pkg() to - * initialize the copied package contents. - * - * The copying is necessary if the package buffer supplied is constant, or if - * the memory may disappear shortly after calling this function. - * - * If the package buffer resides in the data segment and can be modified, the - * caller is free to use ice_init_pkg() instead of ice_copy_and_init_pkg(). - * - * However, if the package buffer needs to be copied first, such as when being - * read from a file, the caller should use ice_copy_and_init_pkg(). - * - * This function will first copy the package buffer, before calling - * ice_init_pkg(). The caller is free to immediately destroy the original - * package buffer, as the new copy will be managed by this function and - * related routines. - */ -enum ice_ddp_state -ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len) -{ - enum ice_ddp_state state; - u8 *buf_copy; - - if (!buf || !len) - return ICE_DDP_PKG_ERR; - - buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL); - - state = ice_init_pkg(hw, buf_copy, len); - if (!ice_is_init_pkg_successful(state)) { - /* Free the copy, since we failed to initialize the package */ - devm_kfree(ice_hw_to_dev(hw), buf_copy); - } else { - /* Track the copied pkg so we can free it later */ - hw->pkg_copy = buf_copy; - hw->pkg_size = len; - } - - return state; -} - -/** - * ice_is_init_pkg_successful - check if DDP init was successful - * @state: state of the DDP pkg after download - */ -bool ice_is_init_pkg_successful(enum ice_ddp_state state) -{ - switch (state) { - case ICE_DDP_PKG_SUCCESS: - case ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED: - case ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED: - return true; - default: - return false; - } -} - -/** - * ice_pkg_buf_alloc - * @hw: pointer to the HW structure - * - * Allocates a package buffer and returns a pointer to the buffer header. - * Note: all package contents must be in Little Endian form. - */ -static struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw) -{ - struct ice_buf_build *bld; - struct ice_buf_hdr *buf; - - bld = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*bld), GFP_KERNEL); - if (!bld) - return NULL; - - buf = (struct ice_buf_hdr *)bld; - buf->data_end = cpu_to_le16(offsetof(struct ice_buf_hdr, - section_entry)); - return bld; -} - -static bool ice_is_gtp_u_profile(u16 prof_idx) -{ - return (prof_idx >= ICE_PROFID_IPV6_GTPU_TEID && - prof_idx <= ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER) || - prof_idx == ICE_PROFID_IPV4_GTPU_TEID; -} - -static bool ice_is_gtp_c_profile(u16 prof_idx) -{ - switch (prof_idx) { - case ICE_PROFID_IPV4_GTPC_TEID: - case ICE_PROFID_IPV4_GTPC_NO_TEID: - case ICE_PROFID_IPV6_GTPC_TEID: - case ICE_PROFID_IPV6_GTPC_NO_TEID: - return true; - default: - return false; - } -} - -/** - * ice_get_sw_prof_type - determine switch profile type - * @hw: pointer to the HW structure - * @fv: pointer to the switch field vector - * @prof_idx: profile index to check - */ -static enum ice_prof_type -ice_get_sw_prof_type(struct ice_hw *hw, struct ice_fv *fv, u32 prof_idx) -{ - u16 i; - - if (ice_is_gtp_c_profile(prof_idx)) - return ICE_PROF_TUN_GTPC; - - if (ice_is_gtp_u_profile(prof_idx)) - return ICE_PROF_TUN_GTPU; - - for (i = 0; i < hw->blk[ICE_BLK_SW].es.fvw; i++) { - /* UDP tunnel will have UDP_OF protocol ID and VNI offset */ - if (fv->ew[i].prot_id == (u8)ICE_PROT_UDP_OF && - fv->ew[i].off == ICE_VNI_OFFSET) - return ICE_PROF_TUN_UDP; - - /* GRE tunnel will have GRE protocol */ - if (fv->ew[i].prot_id == (u8)ICE_PROT_GRE_OF) - return ICE_PROF_TUN_GRE; - } - - return ICE_PROF_NON_TUN; -} - -/** - * ice_get_sw_fv_bitmap - Get switch field vector bitmap based on profile type - * @hw: pointer to hardware structure - * @req_profs: type of profiles requested - * @bm: pointer to memory for returning the bitmap of field vectors - */ -void -ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, - unsigned long *bm) -{ - struct ice_pkg_enum state; - struct ice_seg *ice_seg; - struct ice_fv *fv; - - if (req_profs == ICE_PROF_ALL) { - bitmap_set(bm, 0, ICE_MAX_NUM_PROFILES); - return; - } - - memset(&state, 0, sizeof(state)); - bitmap_zero(bm, ICE_MAX_NUM_PROFILES); - ice_seg = hw->seg; - do { - enum ice_prof_type prof_type; - u32 offset; - - fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, - &offset, ice_sw_fv_handler); - ice_seg = NULL; - - if (fv) { - /* Determine field vector type */ - prof_type = ice_get_sw_prof_type(hw, fv, offset); - - if (req_profs & prof_type) - set_bit((u16)offset, bm); - } - } while (fv); -} - -/** - * ice_get_sw_fv_list - * @hw: pointer to the HW structure - * @lkups: list of protocol types - * @bm: bitmap of field vectors to consider - * @fv_list: Head of a list - * - * Finds all the field vector entries from switch block that contain - * a given protocol ID and offset and returns a list of structures of type - * "ice_sw_fv_list_entry". Every structure in the list has a field vector - * definition and profile ID information - * NOTE: The caller of the function is responsible for freeing the memory - * allocated for every list entry. - */ -int -ice_get_sw_fv_list(struct ice_hw *hw, struct ice_prot_lkup_ext *lkups, - unsigned long *bm, struct list_head *fv_list) -{ - struct ice_sw_fv_list_entry *fvl; - struct ice_sw_fv_list_entry *tmp; - struct ice_pkg_enum state; - struct ice_seg *ice_seg; - struct ice_fv *fv; - u32 offset; - - memset(&state, 0, sizeof(state)); - - if (!lkups->n_val_words || !hw->seg) - return -EINVAL; - - ice_seg = hw->seg; - do { - u16 i; - - fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, - &offset, ice_sw_fv_handler); - if (!fv) - break; - ice_seg = NULL; - - /* If field vector is not in the bitmap list, then skip this - * profile. - */ - if (!test_bit((u16)offset, bm)) - continue; - - for (i = 0; i < lkups->n_val_words; i++) { - int j; - - for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) - if (fv->ew[j].prot_id == - lkups->fv_words[i].prot_id && - fv->ew[j].off == lkups->fv_words[i].off) - break; - if (j >= hw->blk[ICE_BLK_SW].es.fvw) - break; - if (i + 1 == lkups->n_val_words) { - fvl = devm_kzalloc(ice_hw_to_dev(hw), - sizeof(*fvl), GFP_KERNEL); - if (!fvl) - goto err; - fvl->fv_ptr = fv; - fvl->profile_id = offset; - list_add(&fvl->list_entry, fv_list); - break; - } - } - } while (fv); - if (list_empty(fv_list)) { - dev_warn(ice_hw_to_dev(hw), "Required profiles not found in currently loaded DDP package"); - return -EIO; - } - - return 0; - -err: - list_for_each_entry_safe(fvl, tmp, fv_list, list_entry) { - list_del(&fvl->list_entry); - devm_kfree(ice_hw_to_dev(hw), fvl); - } - - return -ENOMEM; -} - -/** - * ice_init_prof_result_bm - Initialize the profile result index bitmap - * @hw: pointer to hardware structure - */ -void ice_init_prof_result_bm(struct ice_hw *hw) -{ - struct ice_pkg_enum state; - struct ice_seg *ice_seg; - struct ice_fv *fv; - - memset(&state, 0, sizeof(state)); - - if (!hw->seg) - return; - - ice_seg = hw->seg; - do { - u32 off; - u16 i; - - fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, - &off, ice_sw_fv_handler); - ice_seg = NULL; - if (!fv) - break; - - bitmap_zero(hw->switch_info->prof_res_bm[off], - ICE_MAX_FV_WORDS); - - /* Determine empty field vector indices, these can be - * used for recipe results. Skip index 0, since it is - * always used for Switch ID. - */ - for (i = 1; i < ICE_MAX_FV_WORDS; i++) - if (fv->ew[i].prot_id == ICE_PROT_INVALID && - fv->ew[i].off == ICE_FV_OFFSET_INVAL) - set_bit(i, hw->switch_info->prof_res_bm[off]); - } while (fv); -} - -/** - * ice_pkg_buf_free - * @hw: pointer to the HW structure - * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) - * - * Frees a package buffer - */ -void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) -{ - devm_kfree(ice_hw_to_dev(hw), bld); -} - -/** - * ice_pkg_buf_reserve_section - * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) - * @count: the number of sections to reserve - * - * Reserves one or more section table entries in a package buffer. This routine - * can be called multiple times as long as they are made before calling - * ice_pkg_buf_alloc_section(). Once ice_pkg_buf_alloc_section() - * is called once, the number of sections that can be allocated will not be able - * to be increased; not using all reserved sections is fine, but this will - * result in some wasted space in the buffer. - * Note: all package contents must be in Little Endian form. - */ -static int -ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count) -{ - struct ice_buf_hdr *buf; - u16 section_count; - u16 data_end; - - if (!bld) - return -EINVAL; - - buf = (struct ice_buf_hdr *)&bld->buf; - - /* already an active section, can't increase table size */ - section_count = le16_to_cpu(buf->section_count); - if (section_count > 0) - return -EIO; - - if (bld->reserved_section_table_entries + count > ICE_MAX_S_COUNT) - return -EIO; - bld->reserved_section_table_entries += count; - - data_end = le16_to_cpu(buf->data_end) + - flex_array_size(buf, section_entry, count); - buf->data_end = cpu_to_le16(data_end); - - return 0; -} - -/** - * ice_pkg_buf_alloc_section - * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) - * @type: the section type value - * @size: the size of the section to reserve (in bytes) - * - * Reserves memory in the buffer for a section's content and updates the - * buffers' status accordingly. This routine returns a pointer to the first - * byte of the section start within the buffer, which is used to fill in the - * section contents. - * Note: all package contents must be in Little Endian form. - */ -static void * -ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size) -{ - struct ice_buf_hdr *buf; - u16 sect_count; - u16 data_end; - - if (!bld || !type || !size) - return NULL; - - buf = (struct ice_buf_hdr *)&bld->buf; - - /* check for enough space left in buffer */ - data_end = le16_to_cpu(buf->data_end); - - /* section start must align on 4 byte boundary */ - data_end = ALIGN(data_end, 4); - - if ((data_end + size) > ICE_MAX_S_DATA_END) - return NULL; - - /* check for more available section table entries */ - sect_count = le16_to_cpu(buf->section_count); - if (sect_count < bld->reserved_section_table_entries) { - void *section_ptr = ((u8 *)buf) + data_end; - - buf->section_entry[sect_count].offset = cpu_to_le16(data_end); - buf->section_entry[sect_count].size = cpu_to_le16(size); - buf->section_entry[sect_count].type = cpu_to_le32(type); - - data_end += size; - buf->data_end = cpu_to_le16(data_end); - - buf->section_count = cpu_to_le16(sect_count + 1); - return section_ptr; - } - - /* no free section table entries */ - return NULL; -} - -/** - * ice_pkg_buf_alloc_single_section - * @hw: pointer to the HW structure - * @type: the section type value - * @size: the size of the section to reserve (in bytes) - * @section: returns pointer to the section - * - * Allocates a package buffer with a single section. - * Note: all package contents must be in Little Endian form. - */ -struct ice_buf_build * -ice_pkg_buf_alloc_single_section(struct ice_hw *hw, u32 type, u16 size, - void **section) -{ - struct ice_buf_build *buf; - - if (!section) - return NULL; - - buf = ice_pkg_buf_alloc(hw); - if (!buf) - return NULL; - - if (ice_pkg_buf_reserve_section(buf, 1)) - goto ice_pkg_buf_alloc_single_section_err; - - *section = ice_pkg_buf_alloc_section(buf, type, size); - if (!*section) - goto ice_pkg_buf_alloc_single_section_err; - - return buf; - -ice_pkg_buf_alloc_single_section_err: - ice_pkg_buf_free(hw, buf); - return NULL; -} - -/** - * ice_pkg_buf_get_active_sections - * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) - * - * Returns the number of active sections. Before using the package buffer - * in an update package command, the caller should make sure that there is at - * least one active section - otherwise, the buffer is not legal and should - * not be used. - * Note: all package contents must be in Little Endian form. - */ -static u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld) -{ - struct ice_buf_hdr *buf; - - if (!bld) - return 0; - - buf = (struct ice_buf_hdr *)&bld->buf; - return le16_to_cpu(buf->section_count); -} - -/** - * ice_pkg_buf - * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) - * - * Return a pointer to the buffer's header - */ -struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) -{ - if (!bld) - return NULL; - - return &bld->buf; -} - -/** * ice_get_open_tunnel_port - retrieve an open tunnel port * @hw: pointer to the HW structure * @port: returns open port @@ -2297,10 +391,11 @@ ice_upd_dvm_boost_entry_err: */ int ice_set_dvm_boost_entries(struct ice_hw *hw) { - int status; u16 i; for (i = 0; i < hw->dvm_upd.count; i++) { + int status; + status = ice_upd_dvm_boost_entry(hw, &hw->dvm_upd.tbl[i]); if (status) return status; @@ -2757,7 +852,6 @@ ice_match_prop_lst(struct list_head *list1, struct list_head *list2) count++; list_for_each_entry(tmp2, list2, list) chk_count++; - /* cppcheck-suppress knownConditionTrueFalse */ if (!count || count != chk_count) return false; @@ -5102,12 +3196,13 @@ ice_rem_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u16 idx = vsig & ICE_VSIG_IDX_M; struct ice_vsig_vsi *vsi_cur; struct ice_vsig_prof *d, *t; - int status; /* remove TCAM entries */ list_for_each_entry_safe(d, t, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst, list) { + int status; + status = ice_rem_prof_id(hw, blk, d); if (status) return status; @@ -5158,12 +3253,13 @@ ice_rem_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, { u16 idx = vsig & ICE_VSIG_IDX_M; struct ice_vsig_prof *p, *t; - int status; list_for_each_entry_safe(p, t, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst, list) if (p->profile_cookie == hdl) { + int status; + if (ice_vsig_prof_id_count(hw, blk, vsig) == 1) /* this is the last profile, remove the VSIG */ return ice_rem_vsig(hw, blk, vsig, chg); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 9c530c86703e..7af7c8e9aa4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -6,75 +6,6 @@ #include "ice_type.h" -/* Package minimal version supported */ -#define ICE_PKG_SUPP_VER_MAJ 1 -#define ICE_PKG_SUPP_VER_MNR 3 - -/* Package format version */ -#define ICE_PKG_FMT_VER_MAJ 1 -#define ICE_PKG_FMT_VER_MNR 0 -#define ICE_PKG_FMT_VER_UPD 0 -#define ICE_PKG_FMT_VER_DFT 0 - -#define ICE_PKG_CNT 4 - -enum ice_ddp_state { - /* Indicates that this call to ice_init_pkg - * successfully loaded the requested DDP package - */ - ICE_DDP_PKG_SUCCESS = 0, - - /* Generic error for already loaded errors, it is mapped later to - * the more specific one (one of the next 3) - */ - ICE_DDP_PKG_ALREADY_LOADED = -1, - - /* Indicates that a DDP package of the same version has already been - * loaded onto the device by a previous call or by another PF - */ - ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED = -2, - - /* The device has a DDP package that is not supported by the driver */ - ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED = -3, - - /* The device has a compatible package - * (but different from the request) already loaded - */ - ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED = -4, - - /* The firmware loaded on the device is not compatible with - * the DDP package loaded - */ - ICE_DDP_PKG_FW_MISMATCH = -5, - - /* The DDP package file is invalid */ - ICE_DDP_PKG_INVALID_FILE = -6, - - /* The version of the DDP package provided is higher than - * the driver supports - */ - ICE_DDP_PKG_FILE_VERSION_TOO_HIGH = -7, - - /* The version of the DDP package provided is lower than the - * driver supports - */ - ICE_DDP_PKG_FILE_VERSION_TOO_LOW = -8, - - /* The signature of the DDP package file provided is invalid */ - ICE_DDP_PKG_FILE_SIGNATURE_INVALID = -9, - - /* The DDP package file security revision is too low and not - * supported by firmware - */ - ICE_DDP_PKG_FILE_REVISION_TOO_LOW = -10, - - /* An error occurred in firmware while loading the DDP package */ - ICE_DDP_PKG_LOAD_ERROR = -11, - - /* Other errors */ - ICE_DDP_PKG_ERR = -12 -}; - int ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_change_lock(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 974d14a83b2e..4f42e14ed3ae 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -3,205 +3,7 @@ #ifndef _ICE_FLEX_TYPE_H_ #define _ICE_FLEX_TYPE_H_ - -#define ICE_FV_OFFSET_INVAL 0x1FF - -/* Extraction Sequence (Field Vector) Table */ -struct ice_fv_word { - u8 prot_id; - u16 off; /* Offset within the protocol header */ - u8 resvrd; -} __packed; - -#define ICE_MAX_NUM_PROFILES 256 - -#define ICE_MAX_FV_WORDS 48 -struct ice_fv { - struct ice_fv_word ew[ICE_MAX_FV_WORDS]; -}; - -/* Package and segment headers and tables */ -struct ice_pkg_hdr { - struct ice_pkg_ver pkg_format_ver; - __le32 seg_count; - __le32 seg_offset[]; -}; - -/* generic segment */ -struct ice_generic_seg_hdr { -#define SEGMENT_TYPE_METADATA 0x00000001 -#define SEGMENT_TYPE_ICE 0x00000010 - __le32 seg_type; - struct ice_pkg_ver seg_format_ver; - __le32 seg_size; - char seg_id[ICE_PKG_NAME_SIZE]; -}; - -/* ice specific segment */ - -union ice_device_id { - struct { - __le16 device_id; - __le16 vendor_id; - } dev_vend_id; - __le32 id; -}; - -struct ice_device_id_entry { - union ice_device_id device; - union ice_device_id sub_device; -}; - -struct ice_seg { - struct ice_generic_seg_hdr hdr; - __le32 device_table_count; - struct ice_device_id_entry device_table[]; -}; - -struct ice_nvm_table { - __le32 table_count; - __le32 vers[]; -}; - -struct ice_buf { -#define ICE_PKG_BUF_SIZE 4096 - u8 buf[ICE_PKG_BUF_SIZE]; -}; - -struct ice_buf_table { - __le32 buf_count; - struct ice_buf buf_array[]; -}; - -/* global metadata specific segment */ -struct ice_global_metadata_seg { - struct ice_generic_seg_hdr hdr; - struct ice_pkg_ver pkg_ver; - __le32 rsvd; - char pkg_name[ICE_PKG_NAME_SIZE]; -}; - -#define ICE_MIN_S_OFF 12 -#define ICE_MAX_S_OFF 4095 -#define ICE_MIN_S_SZ 1 -#define ICE_MAX_S_SZ 4084 - -/* section information */ -struct ice_section_entry { - __le32 type; - __le16 offset; - __le16 size; -}; - -#define ICE_MIN_S_COUNT 1 -#define ICE_MAX_S_COUNT 511 -#define ICE_MIN_S_DATA_END 12 -#define ICE_MAX_S_DATA_END 4096 - -#define ICE_METADATA_BUF 0x80000000 - -struct ice_buf_hdr { - __le16 section_count; - __le16 data_end; - struct ice_section_entry section_entry[]; -}; - -#define ICE_MAX_ENTRIES_IN_BUF(hd_sz, ent_sz) ((ICE_PKG_BUF_SIZE - \ - struct_size((struct ice_buf_hdr *)0, section_entry, 1) - (hd_sz)) /\ - (ent_sz)) - -/* ice package section IDs */ -#define ICE_SID_METADATA 1 -#define ICE_SID_XLT0_SW 10 -#define ICE_SID_XLT_KEY_BUILDER_SW 11 -#define ICE_SID_XLT1_SW 12 -#define ICE_SID_XLT2_SW 13 -#define ICE_SID_PROFID_TCAM_SW 14 -#define ICE_SID_PROFID_REDIR_SW 15 -#define ICE_SID_FLD_VEC_SW 16 -#define ICE_SID_CDID_KEY_BUILDER_SW 17 - -struct ice_meta_sect { - struct ice_pkg_ver ver; -#define ICE_META_SECT_NAME_SIZE 28 - char name[ICE_META_SECT_NAME_SIZE]; - __le32 track_id; -}; - -#define ICE_SID_CDID_REDIR_SW 18 - -#define ICE_SID_XLT0_ACL 20 -#define ICE_SID_XLT_KEY_BUILDER_ACL 21 -#define ICE_SID_XLT1_ACL 22 -#define ICE_SID_XLT2_ACL 23 -#define ICE_SID_PROFID_TCAM_ACL 24 -#define ICE_SID_PROFID_REDIR_ACL 25 -#define ICE_SID_FLD_VEC_ACL 26 -#define ICE_SID_CDID_KEY_BUILDER_ACL 27 -#define ICE_SID_CDID_REDIR_ACL 28 - -#define ICE_SID_XLT0_FD 30 -#define ICE_SID_XLT_KEY_BUILDER_FD 31 -#define ICE_SID_XLT1_FD 32 -#define ICE_SID_XLT2_FD 33 -#define ICE_SID_PROFID_TCAM_FD 34 -#define ICE_SID_PROFID_REDIR_FD 35 -#define ICE_SID_FLD_VEC_FD 36 -#define ICE_SID_CDID_KEY_BUILDER_FD 37 -#define ICE_SID_CDID_REDIR_FD 38 - -#define ICE_SID_XLT0_RSS 40 -#define ICE_SID_XLT_KEY_BUILDER_RSS 41 -#define ICE_SID_XLT1_RSS 42 -#define ICE_SID_XLT2_RSS 43 -#define ICE_SID_PROFID_TCAM_RSS 44 -#define ICE_SID_PROFID_REDIR_RSS 45 -#define ICE_SID_FLD_VEC_RSS 46 -#define ICE_SID_CDID_KEY_BUILDER_RSS 47 -#define ICE_SID_CDID_REDIR_RSS 48 - -#define ICE_SID_RXPARSER_MARKER_PTYPE 55 -#define ICE_SID_RXPARSER_BOOST_TCAM 56 -#define ICE_SID_RXPARSER_METADATA_INIT 58 -#define ICE_SID_TXPARSER_BOOST_TCAM 66 - -#define ICE_SID_XLT0_PE 80 -#define ICE_SID_XLT_KEY_BUILDER_PE 81 -#define ICE_SID_XLT1_PE 82 -#define ICE_SID_XLT2_PE 83 -#define ICE_SID_PROFID_TCAM_PE 84 -#define ICE_SID_PROFID_REDIR_PE 85 -#define ICE_SID_FLD_VEC_PE 86 -#define ICE_SID_CDID_KEY_BUILDER_PE 87 -#define ICE_SID_CDID_REDIR_PE 88 - -/* Label Metadata section IDs */ -#define ICE_SID_LBL_FIRST 0x80000010 -#define ICE_SID_LBL_RXPARSER_TMEM 0x80000018 -/* The following define MUST be updated to reflect the last label section ID */ -#define ICE_SID_LBL_LAST 0x80000038 - -enum ice_block { - ICE_BLK_SW = 0, - ICE_BLK_ACL, - ICE_BLK_FD, - ICE_BLK_RSS, - ICE_BLK_PE, - ICE_BLK_COUNT -}; - -enum ice_sect { - ICE_XLT0 = 0, - ICE_XLT_KB, - ICE_XLT1, - ICE_XLT2, - ICE_PROF_TCAM, - ICE_PROF_REDIR, - ICE_VEC_TBL, - ICE_CDID_KB, - ICE_CDID_REDIR, - ICE_SECT_COUNT -}; +#include "ice_ddp.h" /* Packet Type (PTYPE) values */ #define ICE_PTYPE_MAC_PAY 1 @@ -283,134 +85,6 @@ struct ice_ptype_attributes { enum ice_ptype_attrib_type attrib; }; -/* package labels */ -struct ice_label { - __le16 value; -#define ICE_PKG_LABEL_SIZE 64 - char name[ICE_PKG_LABEL_SIZE]; -}; - -struct ice_label_section { - __le16 count; - struct ice_label label[]; -}; - -#define ICE_MAX_LABELS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \ - struct_size((struct ice_label_section *)0, label, 1) - \ - sizeof(struct ice_label), sizeof(struct ice_label)) - -struct ice_sw_fv_section { - __le16 count; - __le16 base_offset; - struct ice_fv fv[]; -}; - -struct ice_sw_fv_list_entry { - struct list_head list_entry; - u32 profile_id; - struct ice_fv *fv_ptr; -}; - -/* The BOOST TCAM stores the match packet header in reverse order, meaning - * the fields are reversed; in addition, this means that the normally big endian - * fields of the packet are now little endian. - */ -struct ice_boost_key_value { -#define ICE_BOOST_REMAINING_HV_KEY 15 - u8 remaining_hv_key[ICE_BOOST_REMAINING_HV_KEY]; - __le16 hv_dst_port_key; - __le16 hv_src_port_key; - u8 tcam_search_key; -} __packed; - -struct ice_boost_key { - struct ice_boost_key_value key; - struct ice_boost_key_value key2; -}; - -/* package Boost TCAM entry */ -struct ice_boost_tcam_entry { - __le16 addr; - __le16 reserved; - /* break up the 40 bytes of key into different fields */ - struct ice_boost_key key; - u8 boost_hit_index_group; - /* The following contains bitfields which are not on byte boundaries. - * These fields are currently unused by driver software. - */ -#define ICE_BOOST_BIT_FIELDS 43 - u8 bit_fields[ICE_BOOST_BIT_FIELDS]; -}; - -struct ice_boost_tcam_section { - __le16 count; - __le16 reserved; - struct ice_boost_tcam_entry tcam[]; -}; - -#define ICE_MAX_BST_TCAMS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \ - struct_size((struct ice_boost_tcam_section *)0, tcam, 1) - \ - sizeof(struct ice_boost_tcam_entry), \ - sizeof(struct ice_boost_tcam_entry)) - -/* package Marker Ptype TCAM entry */ -struct ice_marker_ptype_tcam_entry { -#define ICE_MARKER_PTYPE_TCAM_ADDR_MAX 1024 - __le16 addr; - __le16 ptype; - u8 keys[20]; -}; - -struct ice_marker_ptype_tcam_section { - __le16 count; - __le16 reserved; - struct ice_marker_ptype_tcam_entry tcam[]; -}; - -#define ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF \ - ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_marker_ptype_tcam_section *)0, tcam, 1) - \ - sizeof(struct ice_marker_ptype_tcam_entry), \ - sizeof(struct ice_marker_ptype_tcam_entry)) - -struct ice_xlt1_section { - __le16 count; - __le16 offset; - u8 value[]; -}; - -struct ice_xlt2_section { - __le16 count; - __le16 offset; - __le16 value[]; -}; - -struct ice_prof_redir_section { - __le16 count; - __le16 offset; - u8 redir_value[]; -}; - -/* package buffer building */ - -struct ice_buf_build { - struct ice_buf buf; - u16 reserved_section_table_entries; -}; - -struct ice_pkg_enum { - struct ice_buf_table *buf_table; - u32 buf_idx; - - u32 type; - struct ice_buf_hdr *buf; - u32 sect_idx; - void *sect; - u32 sect_type; - - u32 entry_idx; - void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset); -}; - /* Tunnel enabling */ enum ice_tunnel_type { diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index 43e199b5b513..8dec748bb53a 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -3,15 +3,18 @@ #include "ice.h" #include "ice_lib.h" -#include <linux/tty_driver.h> /** - * ice_gnss_do_write - Write data to internal GNSS + * ice_gnss_do_write - Write data to internal GNSS receiver * @pf: board private structure * @buf: command buffer * @size: command buffer size * * Write UBX command data to the GNSS receiver + * + * Return: + * * number of bytes written - success + * * negative - error code */ static unsigned int ice_gnss_do_write(struct ice_pf *pf, unsigned char *buf, unsigned int size) @@ -82,6 +85,12 @@ static void ice_gnss_write_pending(struct kthread_work *work) write_work); struct ice_pf *pf = gnss->back; + if (!pf) + return; + + if (!test_bit(ICE_FLAG_GNSS, pf->flags)) + return; + if (!list_empty(&gnss->queue)) { struct gnss_write_buf *write_buf = NULL; unsigned int bytes; @@ -102,16 +111,14 @@ static void ice_gnss_write_pending(struct kthread_work *work) * ice_gnss_read - Read data from internal GNSS module * @work: GNSS read work structure * - * Read the data from internal GNSS receiver, number of bytes read will be - * returned in *read_data parameter. + * Read the data from internal GNSS receiver, write it to gnss_dev. */ static void ice_gnss_read(struct kthread_work *work) { struct gnss_serial *gnss = container_of(work, struct gnss_serial, read_work.work); + unsigned int i, bytes_read, data_len, count; struct ice_aqc_link_topo_addr link_topo; - unsigned int i, bytes_read, data_len; - struct tty_port *port; struct ice_pf *pf; struct ice_hw *hw; __be16 data_len_b; @@ -120,14 +127,15 @@ static void ice_gnss_read(struct kthread_work *work) int err = 0; pf = gnss->back; - if (!pf || !gnss->tty || !gnss->tty->port) { + if (!pf) { err = -EFAULT; goto exit; } - hw = &pf->hw; - port = gnss->tty->port; + if (!test_bit(ICE_FLAG_GNSS, pf->flags)) + return; + hw = &pf->hw; buf = (char *)get_zeroed_page(GFP_KERNEL); if (!buf) { err = -ENOMEM; @@ -159,7 +167,6 @@ static void ice_gnss_read(struct kthread_work *work) } data_len = min_t(typeof(data_len), data_len, PAGE_SIZE); - data_len = tty_buffer_request_room(port, data_len); if (!data_len) { err = -ENOMEM; goto exit_buf; @@ -179,12 +186,11 @@ static void ice_gnss_read(struct kthread_work *work) goto exit_buf; } - /* Send the data to the tty layer for users to read. This doesn't - * actually push the data through unless tty->low_latency is set. - */ - tty_insert_flip_string(port, buf, i); - tty_flip_buffer_push(port); - + count = gnss_insert_raw(pf->gnss_dev, buf, i); + if (count != i) + dev_warn(ice_pf_to_dev(pf), + "gnss_insert_raw ret=%d size=%d\n", + count, i); exit_buf: free_page((unsigned long)buf); kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, @@ -195,11 +201,16 @@ exit: } /** - * ice_gnss_struct_init - Initialize GNSS structure for the TTY + * ice_gnss_struct_init - Initialize GNSS receiver * @pf: Board private structure - * @index: TTY device index + * + * Initialize GNSS structures and workers. + * + * Return: + * * pointer to initialized gnss_serial struct - success + * * NULL - error */ -static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index) +static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct kthread_worker *kworker; @@ -209,17 +220,12 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index) if (!gnss) return NULL; - mutex_init(&gnss->gnss_mutex); - gnss->open_count = 0; gnss->back = pf; - pf->gnss_serial[index] = gnss; + pf->gnss_serial = gnss; kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); INIT_LIST_HEAD(&gnss->queue); kthread_init_work(&gnss->write_work, ice_gnss_write_pending); - /* Allocate a kworker for handling work required for the GNSS TTY - * writes. - */ kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); if (IS_ERR(kworker)) { kfree(gnss); @@ -232,140 +238,100 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf, int index) } /** - * ice_gnss_tty_open - Initialize GNSS structures on TTY device open - * @tty: pointer to the tty_struct - * @filp: pointer to the file + * ice_gnss_open - Open GNSS device + * @gdev: pointer to the gnss device struct + * + * Open GNSS device and start filling the read buffer for consumer. * - * This routine is mandatory. If this routine is not filled in, the attempted - * open will fail with ENODEV. + * Return: + * * 0 - success + * * negative - error code */ -static int ice_gnss_tty_open(struct tty_struct *tty, struct file *filp) +static int ice_gnss_open(struct gnss_device *gdev) { + struct ice_pf *pf = gnss_get_drvdata(gdev); struct gnss_serial *gnss; - struct ice_pf *pf; - pf = (struct ice_pf *)tty->driver->driver_state; if (!pf) return -EFAULT; - /* Clear the pointer in case something fails */ - tty->driver_data = NULL; - - /* Get the serial object associated with this tty pointer */ - gnss = pf->gnss_serial[tty->index]; - if (!gnss) { - /* Initialize GNSS struct on the first device open */ - gnss = ice_gnss_struct_init(pf, tty->index); - if (!gnss) - return -ENOMEM; - } + if (!test_bit(ICE_FLAG_GNSS, pf->flags)) + return -EFAULT; - mutex_lock(&gnss->gnss_mutex); + gnss = pf->gnss_serial; + if (!gnss) + return -ENODEV; - /* Save our structure within the tty structure */ - tty->driver_data = gnss; - gnss->tty = tty; - gnss->open_count++; kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, 0); - mutex_unlock(&gnss->gnss_mutex); - return 0; } /** - * ice_gnss_tty_close - Cleanup GNSS structures on tty device close - * @tty: pointer to the tty_struct - * @filp: pointer to the file + * ice_gnss_close - Close GNSS device + * @gdev: pointer to the gnss device struct + * + * Close GNSS device, cancel worker, stop filling the read buffer. */ -static void ice_gnss_tty_close(struct tty_struct *tty, struct file *filp) +static void ice_gnss_close(struct gnss_device *gdev) { - struct gnss_serial *gnss = tty->driver_data; - struct ice_pf *pf; - - if (!gnss) - return; + struct ice_pf *pf = gnss_get_drvdata(gdev); + struct gnss_serial *gnss; - pf = (struct ice_pf *)tty->driver->driver_state; if (!pf) return; - mutex_lock(&gnss->gnss_mutex); - - if (!gnss->open_count) { - /* Port was never opened */ - dev_err(ice_pf_to_dev(pf), "GNSS port not opened\n"); - goto exit; - } + gnss = pf->gnss_serial; + if (!gnss) + return; - gnss->open_count--; - if (gnss->open_count <= 0) { - /* Port is in shutdown state */ - kthread_cancel_delayed_work_sync(&gnss->read_work); - } -exit: - mutex_unlock(&gnss->gnss_mutex); + kthread_cancel_work_sync(&gnss->write_work); + kthread_cancel_delayed_work_sync(&gnss->read_work); } /** - * ice_gnss_tty_write - Write GNSS data - * @tty: pointer to the tty_struct + * ice_gnss_write - Write to GNSS device + * @gdev: pointer to the gnss device struct * @buf: pointer to the user data - * @count: the number of characters queued to be sent to the HW + * @count: size of the buffer to be sent to the GNSS device * - * The write function call is called by the user when there is data to be sent - * to the hardware. First the tty core receives the call, and then it passes the - * data on to the tty driver's write function. The tty core also tells the tty - * driver the size of the data being sent. - * If any errors happen during the write call, a negative error value should be - * returned instead of the number of characters queued to be written. + * Return: + * * number of written bytes - success + * * negative - error code */ static int -ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) +ice_gnss_write(struct gnss_device *gdev, const unsigned char *buf, + size_t count) { + struct ice_pf *pf = gnss_get_drvdata(gdev); struct gnss_write_buf *write_buf; struct gnss_serial *gnss; unsigned char *cmd_buf; - struct ice_pf *pf; int err = count; /* We cannot write a single byte using our I2C implementation. */ if (count <= 1 || count > ICE_GNSS_TTY_WRITE_BUF) return -EINVAL; - gnss = tty->driver_data; - if (!gnss) - return -EFAULT; - - pf = (struct ice_pf *)tty->driver->driver_state; if (!pf) return -EFAULT; - /* Only allow to write on TTY 0 */ - if (gnss != pf->gnss_serial[0]) - return -EIO; - - mutex_lock(&gnss->gnss_mutex); + if (!test_bit(ICE_FLAG_GNSS, pf->flags)) + return -EFAULT; - if (!gnss->open_count) { - err = -EINVAL; - goto exit; - } + gnss = pf->gnss_serial; + if (!gnss) + return -ENODEV; cmd_buf = kcalloc(count, sizeof(*buf), GFP_KERNEL); - if (!cmd_buf) { - err = -ENOMEM; - goto exit; - } + if (!cmd_buf) + return -ENOMEM; memcpy(cmd_buf, buf, count); - - /* Send the data out to a hardware port */ write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL); if (!write_buf) { kfree(cmd_buf); - err = -ENOMEM; - goto exit; + return -ENOMEM; } write_buf->buf = cmd_buf; @@ -373,141 +339,89 @@ ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) INIT_LIST_HEAD(&write_buf->queue); list_add_tail(&write_buf->queue, &gnss->queue); kthread_queue_work(gnss->kworker, &gnss->write_work); -exit: - mutex_unlock(&gnss->gnss_mutex); + return err; } +static const struct gnss_operations ice_gnss_ops = { + .open = ice_gnss_open, + .close = ice_gnss_close, + .write_raw = ice_gnss_write, +}; + /** - * ice_gnss_tty_write_room - Returns the numbers of characters to be written. - * @tty: pointer to the tty_struct + * ice_gnss_register - Register GNSS receiver + * @pf: Board private structure + * + * Allocate and register GNSS receiver in the Linux GNSS subsystem. * - * This routine returns the numbers of characters the tty driver will accept - * for queuing to be written or 0 if either the TTY is not open or user - * tries to write to the TTY other than the first. + * Return: + * * 0 - success + * * negative - error code */ -static unsigned int ice_gnss_tty_write_room(struct tty_struct *tty) +static int ice_gnss_register(struct ice_pf *pf) { - struct gnss_serial *gnss = tty->driver_data; - - /* Only allow to write on TTY 0 */ - if (!gnss || gnss != gnss->back->gnss_serial[0]) - return 0; - - mutex_lock(&gnss->gnss_mutex); + struct gnss_device *gdev; + int ret; + + gdev = gnss_allocate_device(ice_pf_to_dev(pf)); + if (!gdev) { + dev_err(ice_pf_to_dev(pf), + "gnss_allocate_device returns NULL\n"); + return -ENOMEM; + } - if (!gnss->open_count) { - mutex_unlock(&gnss->gnss_mutex); - return 0; + gdev->ops = &ice_gnss_ops; + gdev->type = GNSS_TYPE_UBX; + gnss_set_drvdata(gdev, pf); + ret = gnss_register_device(gdev); + if (ret) { + dev_err(ice_pf_to_dev(pf), "gnss_register_device err=%d\n", + ret); + gnss_put_device(gdev); + } else { + pf->gnss_dev = gdev; } - mutex_unlock(&gnss->gnss_mutex); - return ICE_GNSS_TTY_WRITE_BUF; + return ret; } -static const struct tty_operations tty_gps_ops = { - .open = ice_gnss_tty_open, - .close = ice_gnss_tty_close, - .write = ice_gnss_tty_write, - .write_room = ice_gnss_tty_write_room, -}; - /** - * ice_gnss_create_tty_driver - Create a TTY driver for GNSS + * ice_gnss_deregister - Deregister GNSS receiver * @pf: Board private structure + * + * Deregister GNSS receiver from the Linux GNSS subsystem, + * release its resources. */ -static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf) +static void ice_gnss_deregister(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); - const int ICE_TTYDRV_NAME_MAX = 14; - struct tty_driver *tty_driver; - char *ttydrv_name; - unsigned int i; - int err; - - tty_driver = tty_alloc_driver(ICE_GNSS_TTY_MINOR_DEVICES, - TTY_DRIVER_REAL_RAW); - if (IS_ERR(tty_driver)) { - dev_err(dev, "Failed to allocate memory for GNSS TTY\n"); - return NULL; - } - - ttydrv_name = kzalloc(ICE_TTYDRV_NAME_MAX, GFP_KERNEL); - if (!ttydrv_name) { - tty_driver_kref_put(tty_driver); - return NULL; + if (pf->gnss_dev) { + gnss_deregister_device(pf->gnss_dev); + gnss_put_device(pf->gnss_dev); + pf->gnss_dev = NULL; } - - snprintf(ttydrv_name, ICE_TTYDRV_NAME_MAX, "ttyGNSS_%02x%02x_", - (u8)pf->pdev->bus->number, (u8)PCI_SLOT(pf->pdev->devfn)); - - /* Initialize the tty driver*/ - tty_driver->owner = THIS_MODULE; - tty_driver->driver_name = dev_driver_string(dev); - tty_driver->name = (const char *)ttydrv_name; - tty_driver->type = TTY_DRIVER_TYPE_SERIAL; - tty_driver->subtype = SERIAL_TYPE_NORMAL; - tty_driver->init_termios = tty_std_termios; - tty_driver->init_termios.c_iflag &= ~INLCR; - tty_driver->init_termios.c_iflag |= IGNCR; - tty_driver->init_termios.c_oflag &= ~OPOST; - tty_driver->init_termios.c_lflag &= ~ICANON; - tty_driver->init_termios.c_cflag &= ~(CSIZE | CBAUD | CBAUDEX); - /* baud rate 9600 */ - tty_termios_encode_baud_rate(&tty_driver->init_termios, 9600, 9600); - tty_driver->driver_state = pf; - tty_set_operations(tty_driver, &tty_gps_ops); - - for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { - pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]), - GFP_KERNEL); - if (!pf->gnss_tty_port[i]) - goto err_out; - - pf->gnss_serial[i] = NULL; - - tty_port_init(pf->gnss_tty_port[i]); - tty_port_link_device(pf->gnss_tty_port[i], tty_driver, i); - } - - err = tty_register_driver(tty_driver); - if (err) { - dev_err(dev, "Failed to register TTY driver err=%d\n", err); - goto err_out; - } - - for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) - dev_info(dev, "%s%d registered\n", ttydrv_name, i); - - return tty_driver; - -err_out: - while (i--) { - tty_port_destroy(pf->gnss_tty_port[i]); - kfree(pf->gnss_tty_port[i]); - } - kfree(ttydrv_name); - tty_driver_kref_put(pf->ice_gnss_tty_driver); - - return NULL; } /** - * ice_gnss_init - Initialize GNSS TTY support + * ice_gnss_init - Initialize GNSS support * @pf: Board private structure */ void ice_gnss_init(struct ice_pf *pf) { - struct tty_driver *tty_driver; + int ret; - tty_driver = ice_gnss_create_tty_driver(pf); - if (!tty_driver) + pf->gnss_serial = ice_gnss_struct_init(pf); + if (!pf->gnss_serial) return; - pf->ice_gnss_tty_driver = tty_driver; - - set_bit(ICE_FLAG_GNSS, pf->flags); - dev_info(ice_pf_to_dev(pf), "GNSS TTY init successful\n"); + ret = ice_gnss_register(pf); + if (!ret) { + set_bit(ICE_FLAG_GNSS, pf->flags); + dev_info(ice_pf_to_dev(pf), "GNSS init successful\n"); + } else { + ice_gnss_exit(pf); + dev_err(ice_pf_to_dev(pf), "GNSS init failure\n"); + } } /** @@ -516,31 +430,20 @@ void ice_gnss_init(struct ice_pf *pf) */ void ice_gnss_exit(struct ice_pf *pf) { - unsigned int i; + ice_gnss_deregister(pf); + clear_bit(ICE_FLAG_GNSS, pf->flags); - if (!test_bit(ICE_FLAG_GNSS, pf->flags) || !pf->ice_gnss_tty_driver) - return; - - for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { - if (pf->gnss_tty_port[i]) { - tty_port_destroy(pf->gnss_tty_port[i]); - kfree(pf->gnss_tty_port[i]); - } + if (pf->gnss_serial) { + struct gnss_serial *gnss = pf->gnss_serial; - if (pf->gnss_serial[i]) { - struct gnss_serial *gnss = pf->gnss_serial[i]; + kthread_cancel_work_sync(&gnss->write_work); + kthread_cancel_delayed_work_sync(&gnss->read_work); + kthread_destroy_worker(gnss->kworker); + gnss->kworker = NULL; - kthread_cancel_work_sync(&gnss->write_work); - kthread_cancel_delayed_work_sync(&gnss->read_work); - kfree(gnss); - pf->gnss_serial[i] = NULL; - } + kfree(gnss); + pf->gnss_serial = NULL; } - - tty_unregister_driver(pf->ice_gnss_tty_driver); - kfree(pf->ice_gnss_tty_driver->name); - tty_driver_kref_put(pf->ice_gnss_tty_driver); - pf->ice_gnss_tty_driver = NULL; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index f454dd1d9285..31db0701d13f 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -4,15 +4,8 @@ #ifndef _ICE_GNSS_H_ #define _ICE_GNSS_H_ -#include <linux/tty.h> -#include <linux/tty_flip.h> - #define ICE_E810T_GNSS_I2C_BUS 0x2 #define ICE_GNSS_TIMER_DELAY_TIME (HZ / 10) /* 0.1 second per message */ -/* Create 2 minor devices, both using the same GNSS module. First one is RW, - * second one RO. - */ -#define ICE_GNSS_TTY_MINOR_DEVICES 2 #define ICE_GNSS_TTY_WRITE_BUF 250 #define ICE_MAX_I2C_DATA_SIZE FIELD_MAX(ICE_AQC_I2C_DATA_SIZE_M) #define ICE_MAX_I2C_WRITE_BYTES 4 @@ -36,13 +29,9 @@ struct gnss_write_buf { unsigned char *buf; }; - /** * struct gnss_serial - data used to initialize GNSS TTY port * @back: back pointer to PF - * @tty: pointer to the tty for this device - * @open_count: number of times this port has been opened - * @gnss_mutex: gnss_mutex used to protect GNSS serial operations * @kworker: kwork thread for handling periodic work * @read_work: read_work function for handling GNSS reads * @write_work: write_work function for handling GNSS writes @@ -50,16 +39,13 @@ struct gnss_write_buf { */ struct gnss_serial { struct ice_pf *back; - struct tty_struct *tty; - int open_count; - struct mutex gnss_mutex; /* protects GNSS serial structure */ struct kthread_worker *kworker; struct kthread_delayed_work read_work; struct kthread_work write_work; struct list_head queue; }; -#if IS_ENABLED(CONFIG_TTY) +#if IS_ENABLED(CONFIG_ICE_GNSS) void ice_gnss_init(struct ice_pf *pf); void ice_gnss_exit(struct ice_pf *pf); bool ice_gnss_is_gps_present(struct ice_hw *hw); @@ -70,5 +56,5 @@ static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) { return false; } -#endif /* IS_ENABLED(CONFIG_TTY) */ +#endif /* IS_ENABLED(CONFIG_ICE_GNSS) */ #endif /* _ICE_GNSS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 94aa834cd9a6..8316037b5548 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1670,7 +1670,7 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; - WRITE_ONCE(rx_ring_stats[i], ring_stats); + WRITE_ONCE(rx_ring_stats[i], ring_stats); } ring->ring_stats = ring_stats; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a9a7f8b52140..cb870da5c317 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3780,13 +3780,11 @@ static int ice_setup_pf_sw(struct ice_pf *pf) unroll_napi_add: ice_tc_indir_block_unregister(vsi); unroll_cfg_netdev: - if (vsi) { - ice_napi_del(vsi); - if (vsi->netdev) { - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } + ice_napi_del(vsi); + if (vsi->netdev) { + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + free_netdev(vsi->netdev); + vsi->netdev = NULL; } unroll_vsi_setup: @@ -5048,8 +5046,11 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf) static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); + struct ice_hw *hw; int i; + hw = &pf->hw; + ice_devlink_unregister(pf); for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { if (!ice_is_reset_in_progress(pf->state)) @@ -5082,7 +5083,7 @@ static void ice_remove(struct pci_dev *pdev) ice_remove_arfs(pf); ice_setup_mc_magic_wake(pf); ice_vsi_release_all(pf); - mutex_destroy(&(&pf->hw)->fdir_fltr_lock); + mutex_destroy(&hw->fdir_fltr_lock); ice_set_wake(pf); ice_free_irq_msix_misc(pf); ice_for_each_vsi(pf, i) { @@ -5094,13 +5095,13 @@ static void ice_remove(struct pci_dev *pdev) pf->vsi_stats = NULL; ice_deinit_pf(pf); ice_devlink_destroy_regions(pf); - ice_deinit_hw(&pf->hw); + ice_deinit_hw(hw); /* Issue a PFR as part of the prescribed driver unload flow. Do not * do it via ice_schedule_reset() since there is no need to rebuild * and the service task is already stopped. */ - ice_reset(&pf->hw, ICE_RESET_PFR); + ice_reset(hw, ICE_RESET_PFR); pci_wait_for_pending_transaction(pdev); ice_clear_interrupt_scheme(pf); pci_disable_pcie_error_reporting(pdev); @@ -6146,15 +6147,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi) { int err; - if (vsi->netdev) { + if (vsi->netdev && vsi->type == ICE_VSI_PF) { ice_set_rx_mode(vsi->netdev); - if (vsi->type != ICE_VSI_LB) { - err = ice_vsi_vlan_setup(vsi); - - if (err) - return err; - } + err = ice_vsi_vlan_setup(vsi); + if (err) + return err; } ice_vsi_cfg_dcb_rings(vsi); @@ -6335,7 +6333,7 @@ static int ice_up_complete(struct ice_vsi *vsi) if (vsi->port_info && (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) && - vsi->netdev) { + vsi->netdev && vsi->type == ICE_VSI_PF) { ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); @@ -6346,7 +6344,9 @@ static int ice_up_complete(struct ice_vsi *vsi) * set the baseline so counters are ready when interface is up */ ice_update_eth_stats(vsi); - ice_service_task_schedule(pf); + + if (vsi->type == ICE_VSI_PF) + ice_service_task_schedule(pf); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index c262dc886e6a..f6f52a248066 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -662,7 +662,6 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, /* Verify that the simple checksum is zero */ for (i = 0; i < sizeof(*tmp); i++) - /* cppcheck-suppress objectIndex */ sum += ((u8 *)tmp)[i]; if (sum) { diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index d63161d73eb1..3abc8db1d065 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2269,7 +2269,7 @@ static void ice_ptp_set_caps(struct ice_pf *pf) snprintf(info->name, sizeof(info->name) - 1, "%s-%s-clk", dev_driver_string(dev), dev_name(dev)); info->owner = THIS_MODULE; - info->max_adj = 999999999; + info->max_adj = 100000000; info->adjtime = ice_ptp_adjtime; info->adjfine = ice_ptp_adjfine; info->gettimex64 = ice_ptp_gettimex64; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 6d08b397df2a..4eca8d195ef0 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -1063,7 +1063,6 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, *num_nodes_added = 0; while (*num_nodes_added < num_nodes) { u16 max_child_nodes, num_added = 0; - /* cppcheck-suppress unusedVariable */ u32 temp; status = ice_sched_add_nodes_to_hw_layer(pi, tc_node, parent, @@ -1655,12 +1654,13 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, u32 first_node_teid; u16 num_added = 0; u8 i, qgl, vsil; - int status; qgl = ice_sched_get_qgrp_layer(hw); vsil = ice_sched_get_vsi_layer(hw); parent = ice_sched_get_vsi_node(pi, tc_node, vsi_handle); for (i = vsil + 1; i <= qgl; i++) { + int status; + if (!parent) return -EIO; @@ -1756,13 +1756,14 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, u32 first_node_teid; u16 num_added = 0; u8 i, vsil; - int status; if (!pi) return -EINVAL; vsil = ice_sched_get_vsi_layer(pi->hw); for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) { + int status; + status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i, num_nodes[i], &first_node_teid, diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index faba0f857cd9..80706f7330f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -792,7 +792,7 @@ static struct ice_vsi * ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) { struct ice_rx_ring *ring = NULL; - struct ice_vsi *ch_vsi = NULL; + struct ice_vsi *dest_vsi = NULL; struct ice_pf *pf = vsi->back; struct device *dev; u32 tc_class; @@ -810,7 +810,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) return ERR_PTR(-EOPNOTSUPP); } /* Locate ADQ VSI depending on hw_tc number */ - ch_vsi = vsi->tc_map_vsi[tc_class]; + dest_vsi = vsi->tc_map_vsi[tc_class]; break; case ICE_FWD_TO_Q: /* Locate the Rx queue */ @@ -824,7 +824,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) /* Determine destination VSI even though the action is * FWD_TO_QUEUE, because QUEUE is associated with VSI */ - ch_vsi = tc_fltr->dest_vsi; + dest_vsi = tc_fltr->dest_vsi; break; default: dev_err(dev, @@ -832,13 +832,13 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) tc_fltr->action.fltr_act); return ERR_PTR(-EINVAL); } - /* Must have valid ch_vsi (it could be main VSI or ADQ VSI) */ - if (!ch_vsi) { + /* Must have valid dest_vsi (it could be main VSI or ADQ VSI) */ + if (!dest_vsi) { dev_err(dev, "Unable to add filter because specified destination VSI doesn't exist\n"); return ERR_PTR(-EINVAL); } - return ch_vsi; + return dest_vsi; } /** @@ -860,7 +860,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 flags = tc_fltr->flags; - struct ice_vsi *ch_vsi; + struct ice_vsi *dest_vsi; struct device *dev; u16 lkups_cnt = 0; u16 l4_proto = 0; @@ -883,9 +883,11 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, } /* validate forwarding action VSI and queue */ - ch_vsi = ice_tc_forward_action(vsi, tc_fltr); - if (IS_ERR(ch_vsi)) - return PTR_ERR(ch_vsi); + if (ice_is_forward_action(tc_fltr->action.fltr_act)) { + dest_vsi = ice_tc_forward_action(vsi, tc_fltr); + if (IS_ERR(dest_vsi)) + return PTR_ERR(dest_vsi); + } lkups_cnt = ice_tc_count_lkups(flags, headers, tc_fltr); list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); @@ -904,7 +906,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, switch (tc_fltr->action.fltr_act) { case ICE_FWD_TO_VSI: - rule_info.sw_act.vsi_handle = ch_vsi->idx; + rule_info.sw_act.vsi_handle = dest_vsi->idx; rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; rule_info.sw_act.src = hw->pf_id; rule_info.rx = true; @@ -915,7 +917,7 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, case ICE_FWD_TO_Q: /* HW queue number in global space */ rule_info.sw_act.fwd_id.q_id = tc_fltr->action.fwd.q.hw_queue; - rule_info.sw_act.vsi_handle = ch_vsi->idx; + rule_info.sw_act.vsi_handle = dest_vsi->idx; rule_info.priority = ICE_SWITCH_FLTR_PRIO_QUEUE; rule_info.sw_act.src = hw->pf_id; rule_info.rx = true; @@ -923,14 +925,15 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, tc_fltr->action.fwd.q.queue, tc_fltr->action.fwd.q.hw_queue, lkups_cnt); break; - default: - rule_info.sw_act.flag |= ICE_FLTR_TX; - /* In case of Tx (LOOKUP_TX), src needs to be src VSI */ - rule_info.sw_act.src = vsi->idx; - /* 'Rx' is false, direction of rule(LOOKUPTRX) */ - rule_info.rx = false; + case ICE_DROP_PACKET: + rule_info.sw_act.flag |= ICE_FLTR_RX; + rule_info.sw_act.src = hw->pf_id; + rule_info.rx = true; rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; break; + default: + ret = -EOPNOTSUPP; + goto exit; } ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); @@ -953,11 +956,11 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, tc_fltr->dest_vsi_handle = rule_added.vsi_handle; if (tc_fltr->action.fltr_act == ICE_FWD_TO_VSI || tc_fltr->action.fltr_act == ICE_FWD_TO_Q) { - tc_fltr->dest_vsi = ch_vsi; + tc_fltr->dest_vsi = dest_vsi; /* keep track of advanced switch filter for * destination VSI */ - ch_vsi->num_chnl_fltr++; + dest_vsi->num_chnl_fltr++; /* keeps track of channel filters for PF VSI */ if (vsi->type == ICE_VSI_PF && @@ -978,6 +981,10 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, tc_fltr->action.fwd.q.hw_queue, rule_added.rid, rule_added.rule_id); break; + case ICE_DROP_PACKET: + dev_dbg(dev, "added switch rule (lkups_cnt %u, flags 0x%x), action is drop, rid %u, rule_id %u\n", + lkups_cnt, flags, rule_added.rid, rule_added.rule_id); + break; default: break; } @@ -1712,6 +1719,9 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, case FLOW_ACTION_RX_QUEUE_MAPPING: /* forward to queue */ return ice_tc_forward_to_queue(vsi, fltr, act); + case FLOW_ACTION_DROP: + fltr->action.fltr_act = ICE_DROP_PACKET; + return 0; default: NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported TC action"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index d916d1e92aa3..8d5e22ac7023 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -211,4 +211,14 @@ ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); void ice_replay_tc_fltrs(struct ice_pf *pf); bool ice_is_tunnel_supported(struct net_device *dev); +static inline bool ice_is_forward_action(enum ice_sw_fwd_act_type fltr_act) +{ + switch (fltr_act) { + case ICE_FWD_TO_VSI: + case ICE_FWD_TO_Q: + return true; + default: + return false; + } +} #endif /* _ICE_TC_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 086f0b3ab68d..ccf09c957a1c 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1996,7 +1996,6 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) if (err < 0) return err; - /* cppcheck-suppress unreadVariable */ protocol = vlan_get_protocol(skb); if (eth_p_mpls(protocol)) @@ -2033,8 +2032,6 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) } /* reset pointers to inner headers */ - - /* cppcheck-suppress unreadVariable */ ip.hdr = skb_inner_network_header(skb); l4.hdr = skb_inner_transport_header(skb); diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index a15927e77272..a1d815af507d 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -396,6 +396,35 @@ void igc_rx_fifo_flush_base(struct igc_hw *hw) rd32(IGC_MPC); } +bool igc_is_device_id_i225(struct igc_hw *hw) +{ + switch (hw->device_id) { + case IGC_DEV_ID_I225_LM: + case IGC_DEV_ID_I225_V: + case IGC_DEV_ID_I225_I: + case IGC_DEV_ID_I225_K: + case IGC_DEV_ID_I225_K2: + case IGC_DEV_ID_I225_LMVP: + case IGC_DEV_ID_I225_IT: + return true; + default: + return false; + } +} + +bool igc_is_device_id_i226(struct igc_hw *hw) +{ + switch (hw->device_id) { + case IGC_DEV_ID_I226_LM: + case IGC_DEV_ID_I226_V: + case IGC_DEV_ID_I226_K: + case IGC_DEV_ID_I226_IT: + return true; + default: + return false; + } +} + static struct igc_mac_operations igc_mac_ops_base = { .init_hw = igc_init_hw_base, .check_for_link = igc_check_for_copper_link, diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index ce530f5fd7bd..7a992befca24 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -7,6 +7,8 @@ /* forward declaration */ void igc_rx_fifo_flush_base(struct igc_hw *hw); void igc_power_down_phy_copper_base(struct igc_hw *hw); +bool igc_is_device_id_i225(struct igc_hw *hw); +bool igc_is_device_id_i226(struct igc_hw *hw); /* Transmit Descriptor - Advanced */ union igc_adv_tx_desc { diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index e9747ec5ac0b..9dec3563ce3a 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -524,6 +524,7 @@ /* Transmit Scheduling */ #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN 0x00000001 #define IGC_TQAVCTRL_ENHANCED_QAV 0x00000008 +#define IGC_TQAVCTRL_FUTSCDDIS 0x00000080 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT 0x00000001 #define IGC_TXQCTL_STRICT_CYCLE 0x00000002 diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 44b1740dc098..e86b15efaeb8 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5958,6 +5958,7 @@ static bool validate_schedule(struct igc_adapter *adapter, const struct tc_taprio_qopt_offload *qopt) { int queue_uses[IGC_MAX_TX_QUEUES] = { }; + struct igc_hw *hw = &adapter->hw; struct timespec64 now; size_t n; @@ -5970,8 +5971,10 @@ static bool validate_schedule(struct igc_adapter *adapter, * in the future, it will hold all the packets until that * time, causing a lot of TX Hangs, so to avoid that, we * reject schedules that would start in the future. + * Note: Limitation above is no longer in i226. */ - if (!is_base_time_past(qopt->base_time, &now)) + if (!is_base_time_past(qopt->base_time, &now) && + igc_is_device_id_i225(hw)) return false; for (n = 0; n < qopt->num_entries; n++) { @@ -6041,6 +6044,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct tc_taprio_qopt_offload *qopt) { bool queue_configured[IGC_MAX_TX_QUEUES] = { }; + struct igc_hw *hw = &adapter->hw; u32 start_time = 0, end_time = 0; size_t n; int i; @@ -6053,7 +6057,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (qopt->base_time < 0) return -ERANGE; - if (adapter->base_time) + if (igc_is_device_id_i225(hw) && adapter->base_time) return -EALREADY; if (!validate_schedule(adapter, qopt)) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index bb10d7b65232..a386c8d61dbf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Intel Corporation */ #include "igc.h" +#include "igc_hw.h" #include "igc_tsn.h" static bool is_any_launchtime(struct igc_adapter *adapter) @@ -92,7 +93,8 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | - IGC_TQAVCTRL_ENHANCED_QAV); + IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); + wr32(IGC_TQAVCTRL, tqavctrl); for (i = 0; i < adapter->num_tx_queues; i++) { @@ -117,20 +119,10 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) ktime_t base_time, systim; int i; - cycle = adapter->cycle_time; - base_time = adapter->base_time; - wr32(IGC_TSAUXC, 0); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); - tqavctrl = rd32(IGC_TQAVCTRL); - tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; - wr32(IGC_TQAVCTRL, tqavctrl); - - wr32(IGC_QBVCYCLET_S, cycle); - wr32(IGC_QBVCYCLET, cycle); - for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -233,21 +225,46 @@ skip_cbs: wr32(IGC_TXQCTL(i), txqctl); } + tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS; + tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; + + cycle = adapter->cycle_time; + base_time = adapter->base_time; + nsec = rd32(IGC_SYSTIML); sec = rd32(IGC_SYSTIMH); systim = ktime_set(sec, nsec); - if (ktime_compare(systim, base_time) > 0) { - s64 n; + s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); - n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); + } else { + /* According to datasheet section 7.5.2.9.3.3, FutScdDis bit + * has to be configured before the cycle time and base time. + * Tx won't hang if there is a GCL is already running, + * so in this case we don't need to set FutScdDis. + */ + if (igc_is_device_id_i226(hw) && + !(rd32(IGC_BASET_H) || rd32(IGC_BASET_L))) + tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS; } - baset_h = div_s64_rem(base_time, NSEC_PER_SEC, &baset_l); + wr32(IGC_TQAVCTRL, tqavctrl); + + wr32(IGC_QBVCYCLET_S, cycle); + wr32(IGC_QBVCYCLET, cycle); + baset_h = div_s64_rem(base_time, NSEC_PER_SEC, &baset_l); wr32(IGC_BASET_H, baset_h); + + /* In i226, Future base time is only supported when FutScdDis bit + * is enabled and only active for re-configuration. + * In this case, initialize the base time with zero to create + * "re-configuration" scenario then only set the desired base time. + */ + if (tqavctrl & IGC_TQAVCTRL_FUTSCDDIS) + wr32(IGC_BASET_L, 0); wr32(IGC_BASET_L, baset_l); return 0; @@ -274,17 +291,14 @@ int igc_tsn_reset(struct igc_adapter *adapter) int igc_tsn_offload_apply(struct igc_adapter *adapter) { - int err; + struct igc_hw *hw = &adapter->hw; - if (netif_running(adapter->netdev)) { + if (netif_running(adapter->netdev) && igc_is_device_id_i225(hw)) { schedule_work(&adapter->reset_task); return 0; } - err = igc_tsn_enable_offload(adapter); - if (err < 0) - return err; + igc_tsn_reset(adapter); - adapter->flags = igc_tsn_new_flags(adapter); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 38c4609bd429..878dd8dff528 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3292,13 +3292,14 @@ static bool ixgbe_need_crosstalk_fix(struct ixgbe_hw *hw) s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, bool *link_up, bool link_up_wait_to_complete) { + bool crosstalk_fix_active = ixgbe_need_crosstalk_fix(hw); u32 links_reg, links_orig; u32 i; /* If Crosstalk fix enabled do the sanity check of making sure * the SFP+ cage is full. */ - if (ixgbe_need_crosstalk_fix(hw)) { + if (crosstalk_fix_active) { u32 sfp_cage_full; switch (hw->mac.type) { @@ -3346,10 +3347,24 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); } } else { - if (links_reg & IXGBE_LINKS_UP) + if (links_reg & IXGBE_LINKS_UP) { + if (crosstalk_fix_active) { + /* Check the link state again after a delay + * to filter out spurious link up + * notifications. + */ + mdelay(5); + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + if (!(links_reg & IXGBE_LINKS_UP)) { + *link_up = false; + *speed = IXGBE_LINK_SPEED_UNKNOWN; + return 0; + } + } *link_up = true; - else + } else { *link_up = false; + } } switch (links_reg & IXGBE_LINKS_SPEED_82599) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ab8370c413f3..43a44c1e1576 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6647,7 +6647,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, rx_ring->queue_index, ixgbe_rx_napi_id(rx_ring)) < 0) goto err; - rx_ring->xdp_prog = adapter->xdp_prog; + WRITE_ONCE(rx_ring->xdp_prog, adapter->xdp_prog); return 0; err: @@ -8937,7 +8937,8 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) int regnum = addr; if (devad != MDIO_DEVAD_NONE) - regnum |= (devad << 16) | MII_ADDR_C45; + return mdiobus_c45_read(adapter->mii_bus, prtad, + devad, regnum); return mdiobus_read(adapter->mii_bus, prtad, regnum); } @@ -8960,7 +8961,8 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, int regnum = addr; if (devad != MDIO_DEVAD_NONE) - regnum |= (devad << 16) | MII_ADDR_C45; + return mdiobus_c45_write(adapter->mii_bus, prtad, devad, + regnum, value); return mdiobus_write(adapter->mii_bus, prtad, regnum, value); } @@ -10297,14 +10299,13 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) synchronize_rcu(); err = ixgbe_setup_tc(dev, adapter->hw_tcs); - if (err) { - rcu_assign_pointer(adapter->xdp_prog, old_prog); + if (err) return -EINVAL; - } } else { - for (i = 0; i < adapter->num_rx_queues; i++) - (void)xchg(&adapter->rx_ring[i]->xdp_prog, - adapter->xdp_prog); + for (i = 0; i < adapter->num_rx_queues; i++) { + WRITE_ONCE(adapter->rx_ring[i]->xdp_prog, + adapter->xdp_prog); + } } if (old_prog) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 123dca9ce468..689470c1e8ad 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -680,14 +680,14 @@ static s32 ixgbe_msca_cmd(struct ixgbe_hw *hw, u32 cmd) } /** - * ixgbe_mii_bus_read_generic - Read a clause 22/45 register with gssr flags + * ixgbe_mii_bus_read_generic_c22 - Read a clause 22 register with gssr flags * @hw: pointer to hardware structure * @addr: address * @regnum: register number * @gssr: semaphore flags to acquire **/ -static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr, - int regnum, u32 gssr) +static s32 ixgbe_mii_bus_read_generic_c22(struct ixgbe_hw *hw, int addr, + int regnum, u32 gssr) { u32 hwaddr, cmd; s32 data; @@ -696,31 +696,52 @@ static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr, return -EBUSY; hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; - if (regnum & MII_ADDR_C45) { - hwaddr |= regnum & GENMASK(21, 0); - cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; - } else { - hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; - cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | - IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND; - } + hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; + cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | + IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND; data = ixgbe_msca_cmd(hw, cmd); if (data < 0) goto mii_bus_read_done; - /* For a clause 45 access the address cycle just completed, we still - * need to do the read command, otherwise just get the data - */ - if (!(regnum & MII_ADDR_C45)) - goto do_mii_bus_read; + data = IXGBE_READ_REG(hw, IXGBE_MSRWD); + data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0); + +mii_bus_read_done: + hw->mac.ops.release_swfw_sync(hw, gssr); + return data; +} + +/** + * ixgbe_mii_bus_read_generic_c45 - Read a clause 45 register with gssr flags + * @hw: pointer to hardware structure + * @addr: address + * @devad: device address to read + * @regnum: register number + * @gssr: semaphore flags to acquire + **/ +static s32 ixgbe_mii_bus_read_generic_c45(struct ixgbe_hw *hw, int addr, + int devad, int regnum, u32 gssr) +{ + u32 hwaddr, cmd; + s32 data; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr)) + return -EBUSY; + + hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; + hwaddr |= devad << 16 | regnum; + cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; + + data = ixgbe_msca_cmd(hw, cmd); + if (data < 0) + goto mii_bus_read_done; cmd = hwaddr | IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND; data = ixgbe_msca_cmd(hw, cmd); if (data < 0) goto mii_bus_read_done; -do_mii_bus_read: data = IXGBE_READ_REG(hw, IXGBE_MSRWD); data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0); @@ -730,15 +751,15 @@ mii_bus_read_done: } /** - * ixgbe_mii_bus_write_generic - Write a clause 22/45 register with gssr flags + * ixgbe_mii_bus_write_generic_c22 - Write a clause 22 register with gssr flags * @hw: pointer to hardware structure * @addr: address * @regnum: register number * @val: value to write * @gssr: semaphore flags to acquire **/ -static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr, - int regnum, u16 val, u32 gssr) +static s32 ixgbe_mii_bus_write_generic_c22(struct ixgbe_hw *hw, int addr, + int regnum, u16 val, u32 gssr) { u32 hwaddr, cmd; s32 err; @@ -749,20 +770,43 @@ static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr, IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val); hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; - if (regnum & MII_ADDR_C45) { - hwaddr |= regnum & GENMASK(21, 0); - cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; - } else { - hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; - cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE | - IXGBE_MSCA_MDI_COMMAND; - } + hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; + cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE | + IXGBE_MSCA_MDI_COMMAND; + + err = ixgbe_msca_cmd(hw, cmd); + + hw->mac.ops.release_swfw_sync(hw, gssr); + return err; +} + +/** + * ixgbe_mii_bus_write_generic_c45 - Write a clause 45 register with gssr flags + * @hw: pointer to hardware structure + * @addr: address + * @devad: device address to read + * @regnum: register number + * @val: value to write + * @gssr: semaphore flags to acquire + **/ +static s32 ixgbe_mii_bus_write_generic_c45(struct ixgbe_hw *hw, int addr, + int devad, int regnum, u16 val, + u32 gssr) +{ + u32 hwaddr, cmd; + s32 err; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr)) + return -EBUSY; + + IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val); + + hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; + hwaddr |= devad << 16 | regnum; + cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; - /* For clause 45 this is an address cycle, for clause 22 this is the - * entire transaction - */ err = ixgbe_msca_cmd(hw, cmd); - if (err < 0 || !(regnum & MII_ADDR_C45)) + if (err < 0) goto mii_bus_write_done; cmd = hwaddr | IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND; @@ -774,70 +818,144 @@ mii_bus_write_done: } /** - * ixgbe_mii_bus_read - Read a clause 22/45 register + * ixgbe_mii_bus_read_c22 - Read a clause 22 register + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + **/ +static s32 ixgbe_mii_bus_read_c22(struct mii_bus *bus, int addr, int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + return ixgbe_mii_bus_read_generic_c22(hw, addr, regnum, gssr); +} + +/** + * ixgbe_mii_bus_read_c45 - Read a clause 45 register * @bus: pointer to mii_bus structure which points to our driver private + * @devad: device address to read * @addr: address * @regnum: register number **/ -static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum) +static s32 ixgbe_mii_bus_read_c45(struct mii_bus *bus, int devad, int addr, + int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + return ixgbe_mii_bus_read_generic_c45(hw, addr, devad, regnum, gssr); +} + +/** + * ixgbe_mii_bus_write_c22 - Write a clause 22 register + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + * @val: value to write + **/ +static s32 ixgbe_mii_bus_write_c22(struct mii_bus *bus, int addr, int regnum, + u16 val) { struct ixgbe_adapter *adapter = bus->priv; struct ixgbe_hw *hw = &adapter->hw; u32 gssr = hw->phy.phy_semaphore_mask; - return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr); + return ixgbe_mii_bus_write_generic_c22(hw, addr, regnum, val, gssr); } /** - * ixgbe_mii_bus_write - Write a clause 22/45 register + * ixgbe_mii_bus_write_c45 - Write a clause 45 register * @bus: pointer to mii_bus structure which points to our driver private * @addr: address + * @devad: device address to read * @regnum: register number * @val: value to write **/ -static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum, - u16 val) +static s32 ixgbe_mii_bus_write_c45(struct mii_bus *bus, int addr, int devad, + int regnum, u16 val) { struct ixgbe_adapter *adapter = bus->priv; struct ixgbe_hw *hw = &adapter->hw; u32 gssr = hw->phy.phy_semaphore_mask; - return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr); + return ixgbe_mii_bus_write_generic_c45(hw, addr, devad, regnum, val, + gssr); } /** - * ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a + * ixgbe_x550em_a_mii_bus_read_c22 - Read a clause 22 register on x550em_a * @bus: pointer to mii_bus structure which points to our driver private * @addr: address * @regnum: register number **/ -static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr, - int regnum) +static s32 ixgbe_x550em_a_mii_bus_read_c22(struct mii_bus *bus, int addr, + int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; + return ixgbe_mii_bus_read_generic_c22(hw, addr, regnum, gssr); +} + +/** + * ixgbe_x550em_a_mii_bus_read_c45 - Read a clause 45 register on x550em_a + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @devad: device address to read + * @regnum: register number + **/ +static s32 ixgbe_x550em_a_mii_bus_read_c45(struct mii_bus *bus, int addr, + int devad, int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; + return ixgbe_mii_bus_read_generic_c45(hw, addr, devad, regnum, gssr); +} + +/** + * ixgbe_x550em_a_mii_bus_write_c22 - Write a clause 22 register on x550em_a + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + * @val: value to write + **/ +static s32 ixgbe_x550em_a_mii_bus_write_c22(struct mii_bus *bus, int addr, + int regnum, u16 val) { struct ixgbe_adapter *adapter = bus->priv; struct ixgbe_hw *hw = &adapter->hw; u32 gssr = hw->phy.phy_semaphore_mask; gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; - return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr); + return ixgbe_mii_bus_write_generic_c22(hw, addr, regnum, val, gssr); } /** - * ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a + * ixgbe_x550em_a_mii_bus_write_c45 - Write a clause 45 register on x550em_a * @bus: pointer to mii_bus structure which points to our driver private * @addr: address + * @devad: device address to read * @regnum: register number * @val: value to write **/ -static s32 ixgbe_x550em_a_mii_bus_write(struct mii_bus *bus, int addr, - int regnum, u16 val) +static s32 ixgbe_x550em_a_mii_bus_write_c45(struct mii_bus *bus, int addr, + int devad, int regnum, u16 val) { struct ixgbe_adapter *adapter = bus->priv; struct ixgbe_hw *hw = &adapter->hw; u32 gssr = hw->phy.phy_semaphore_mask; gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; - return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr); + return ixgbe_mii_bus_write_generic_c45(hw, addr, devad, regnum, val, + gssr); } /** @@ -909,8 +1027,11 @@ out: **/ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) { - s32 (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); - s32 (*read)(struct mii_bus *bus, int addr, int regnum); + s32 (*write_c22)(struct mii_bus *bus, int addr, int regnum, u16 val); + s32 (*read_c22)(struct mii_bus *bus, int addr, int regnum); + s32 (*write_c45)(struct mii_bus *bus, int addr, int devad, int regnum, + u16 val); + s32 (*read_c45)(struct mii_bus *bus, int addr, int devad, int regnum); struct ixgbe_adapter *adapter = hw->back; struct pci_dev *pdev = adapter->pdev; struct device *dev = &adapter->netdev->dev; @@ -929,12 +1050,16 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_A_1G_T_L: if (!ixgbe_x550em_a_has_mii(hw)) return 0; - read = &ixgbe_x550em_a_mii_bus_read; - write = &ixgbe_x550em_a_mii_bus_write; + read_c22 = ixgbe_x550em_a_mii_bus_read_c22; + write_c22 = ixgbe_x550em_a_mii_bus_write_c22; + read_c45 = ixgbe_x550em_a_mii_bus_read_c45; + write_c45 = ixgbe_x550em_a_mii_bus_write_c45; break; default: - read = &ixgbe_mii_bus_read; - write = &ixgbe_mii_bus_write; + read_c22 = ixgbe_mii_bus_read_c22; + write_c22 = ixgbe_mii_bus_write_c22; + read_c45 = ixgbe_mii_bus_read_c45; + write_c45 = ixgbe_mii_bus_write_c45; break; } @@ -942,8 +1067,10 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) if (!bus) return -ENOMEM; - bus->read = read; - bus->write = write; + bus->read = read_c22; + bus->write = write_c22; + bus->read_c45 = read_c45; + bus->write_c45 = write_c45; /* Use the position of the device in the PCI hierarchy as the id */ snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mdio-%s", ixgbe_driver_name, diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index ef878973b859..2d654a40af13 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -204,21 +204,17 @@ static const struct orion_mdio_ops orion_mdio_xsmi_ops = { .poll_interval_max = MVMDIO_XSMI_POLL_INTERVAL_MAX, }; -static int orion_mdio_xsmi_read(struct mii_bus *bus, int mii_id, - int regnum) +static int orion_mdio_xsmi_read_c45(struct mii_bus *bus, int mii_id, + int dev_addr, int regnum) { struct orion_mdio_dev *dev = bus->priv; - u16 dev_addr = (regnum >> 16) & GENMASK(4, 0); int ret; - if (!(regnum & MII_ADDR_C45)) - return -EOPNOTSUPP; - ret = orion_mdio_wait_ready(&orion_mdio_xsmi_ops, bus); if (ret < 0) return ret; - writel(regnum & GENMASK(15, 0), dev->regs + MVMDIO_XSMI_ADDR_REG); + writel(regnum, dev->regs + MVMDIO_XSMI_ADDR_REG); writel((mii_id << MVMDIO_XSMI_PHYADDR_SHIFT) | (dev_addr << MVMDIO_XSMI_DEVADDR_SHIFT) | MVMDIO_XSMI_READ_OPERATION, @@ -237,21 +233,17 @@ static int orion_mdio_xsmi_read(struct mii_bus *bus, int mii_id, return readl(dev->regs + MVMDIO_XSMI_MGNT_REG) & GENMASK(15, 0); } -static int orion_mdio_xsmi_write(struct mii_bus *bus, int mii_id, - int regnum, u16 value) +static int orion_mdio_xsmi_write_c45(struct mii_bus *bus, int mii_id, + int dev_addr, int regnum, u16 value) { struct orion_mdio_dev *dev = bus->priv; - u16 dev_addr = (regnum >> 16) & GENMASK(4, 0); int ret; - if (!(regnum & MII_ADDR_C45)) - return -EOPNOTSUPP; - ret = orion_mdio_wait_ready(&orion_mdio_xsmi_ops, bus); if (ret < 0) return ret; - writel(regnum & GENMASK(15, 0), dev->regs + MVMDIO_XSMI_ADDR_REG); + writel(regnum, dev->regs + MVMDIO_XSMI_ADDR_REG); writel((mii_id << MVMDIO_XSMI_PHYADDR_SHIFT) | (dev_addr << MVMDIO_XSMI_DEVADDR_SHIFT) | MVMDIO_XSMI_WRITE_OPERATION | value, @@ -302,8 +294,8 @@ static int orion_mdio_probe(struct platform_device *pdev) bus->write = orion_mdio_smi_write; break; case BUS_TYPE_XSMI: - bus->read = orion_mdio_xsmi_read; - bus->write = orion_mdio_xsmi_write; + bus->read_c45 = orion_mdio_xsmi_read_c45; + bus->write_c45 = orion_mdio_xsmi_write_c45; break; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index d2584ebb7a70..5727d67e0259 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -195,6 +195,9 @@ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \ M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \ msg_rsp) \ M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \ +M(CPT_LF_RESET, 0xA08, cpt_lf_reset, cpt_lf_rst_req, msg_rsp) \ +M(CPT_FLT_ENG_INFO, 0xA09, cpt_flt_eng_info, cpt_flt_eng_info_req, \ + cpt_flt_eng_info_rsp) \ /* SDP mbox IDs (range 0x1000 - 0x11FF) */ \ M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \ M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \ @@ -297,6 +300,8 @@ M(NIX_BANDPROF_FREE, 0x801e, nix_bandprof_free, nix_bandprof_free_req, \ msg_rsp) \ M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req, \ nix_bandprof_get_hwinfo_rsp) \ +M(NIX_READ_INLINE_IPSEC_CFG, 0x8023, nix_read_inline_ipsec_cfg, \ + msg_req, nix_inline_ipsec_cfg) \ /* MCS mbox IDs (range 0xA000 - 0xBFFF) */ \ M(MCS_ALLOC_RESOURCES, 0xa000, mcs_alloc_resources, mcs_alloc_rsrc_req, \ mcs_alloc_rsrc_rsp) \ @@ -1196,7 +1201,7 @@ struct nix_inline_ipsec_cfg { u32 cpt_credit; struct { u8 egrp; - u8 opcode; + u16 opcode; u16 param1; u16 param2; } gen_cfg; @@ -1205,6 +1210,8 @@ struct nix_inline_ipsec_cfg { u8 cpt_slot; } inst_qsel; u8 enable; + u16 bpid; + u32 credit_th; }; /* Per NIX LF inline IPSec configuration */ @@ -1609,6 +1616,8 @@ struct cpt_lf_alloc_req_msg { u16 sso_pf_func; u16 eng_grpmsk; int blkaddr; + u8 ctx_ilen_valid : 1; + u8 ctx_ilen : 7; }; #define CPT_INLINE_INBOUND 0 @@ -1692,6 +1701,28 @@ struct cpt_inst_lmtst_req { u64 rsvd; }; +/* Mailbox message format to request for CPT LF reset */ +struct cpt_lf_rst_req { + struct mbox_msghdr hdr; + u32 slot; + u32 rsvd; +}; + +/* Mailbox message format to request for CPT faulted engines */ +struct cpt_flt_eng_info_req { + struct mbox_msghdr hdr; + int blkaddr; + bool reset; + u32 rsvd; +}; + +struct cpt_flt_eng_info_rsp { + struct mbox_msghdr hdr; + u64 flt_eng_map[CPT_10K_AF_INT_VEC_RVU]; + u64 rcvrd_eng_map[CPT_10K_AF_INT_VEC_RVU]; + u64 rsvd; +}; + struct sdp_node_info { /* Node to which this PF belons to */ u8 node_id; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 3f5e09b77d4b..8683ce57ed3f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1164,8 +1164,16 @@ cpt: goto nix_err; } + err = rvu_cpt_init(rvu); + if (err) { + dev_err(rvu->dev, "%s: Failed to initialize cpt\n", __func__); + goto mcs_err; + } + return 0; +mcs_err: + rvu_mcs_exit(rvu); nix_err: rvu_nix_freemem(rvu); npa_err: diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 7f0a64731c67..5eea2b6cf6bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -108,6 +108,8 @@ struct rvu_block { u64 lfreset_reg; unsigned char name[NAME_SIZE]; struct rvu *rvu; + u64 cpt_flt_eng_map[3]; + u64 cpt_rcvrd_eng_map[3]; }; struct nix_mcast { @@ -459,6 +461,7 @@ struct rvu { struct rvu_pfvf *pf; struct rvu_pfvf *hwvf; struct mutex rsrc_lock; /* Serialize resource alloc/free */ + struct mutex alias_lock; /* Serialize bar2 alias access */ int vfs; /* Number of VFs attached to RVU */ int nix_blkaddr[MAX_NIX_BLKS]; @@ -510,6 +513,7 @@ struct rvu { struct ptp *ptp; int mcs_blk_cnt; + int cpt_pf_num; #ifdef CONFIG_DEBUG_FS struct rvu_debugfs rvu_dbg; @@ -524,6 +528,8 @@ struct rvu { struct list_head mcs_intrq_head; /* mcs interrupt queue lock */ spinlock_t mcs_intrq_lock; + /* CPT interrupt lock */ + spinlock_t cpt_intr_lock; }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) @@ -546,6 +552,17 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset) return readq(rvu->pfreg_base + offset); } +static inline void rvu_bar2_sel_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) +{ + /* HW requires read back of RVU_AF_BAR2_SEL register to make sure completion of + * write operation. + */ + rvu_write64(rvu, block, offset, val); + rvu_read64(rvu, block, offset); + /* Barrier to ensure read completes before accessing LF registers */ + mb(); +} + /* Silicon revisions */ static inline bool is_rvu_pre_96xx_C0(struct rvu *rvu) { @@ -865,6 +882,7 @@ void rvu_cpt_unregister_interrupts(struct rvu *rvu); int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot); int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc); +int rvu_cpt_init(struct rvu *rvu); /* CN10K RVU */ int rvu_set_channels_base(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 38bbae5d9ae0..f047185f38e0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -17,7 +17,7 @@ #define PCI_DEVID_OTX2_CPT10K_PF 0xA0F2 /* Length of initial context fetch in 128 byte words */ -#define CPT_CTX_ILEN 2ULL +#define CPT_CTX_ILEN 1ULL #define cpt_get_eng_sts(e_min, e_max, rsp, etype) \ ({ \ @@ -37,34 +37,68 @@ (_rsp)->free_sts_##etype = free_sts; \ }) -static irqreturn_t rvu_cpt_af_flt_intr_handler(int irq, void *ptr) +static irqreturn_t cpt_af_flt_intr_handler(int vec, void *ptr) { struct rvu_block *block = ptr; struct rvu *rvu = block->rvu; int blkaddr = block->addr; - u64 reg0, reg1, reg2; - - reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0)); - reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1)); - if (!is_rvu_otx2(rvu)) { - reg2 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(2)); - dev_err_ratelimited(rvu->dev, - "Received CPTAF FLT irq : 0x%llx, 0x%llx, 0x%llx", - reg0, reg1, reg2); - } else { - dev_err_ratelimited(rvu->dev, - "Received CPTAF FLT irq : 0x%llx, 0x%llx", - reg0, reg1); + u64 reg, val; + int i, eng; + u8 grp; + + reg = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(vec)); + dev_err_ratelimited(rvu->dev, "Received CPTAF FLT%d irq : 0x%llx", vec, reg); + + i = -1; + while ((i = find_next_bit((unsigned long *)®, 64, i + 1)) < 64) { + switch (vec) { + case 0: + eng = i; + break; + case 1: + eng = i + 64; + break; + case 2: + eng = i + 128; + break; + } + grp = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng)) & 0xFF; + /* Disable and enable the engine which triggers fault */ + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), 0x0); + val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng)); + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val & ~1ULL); + + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), grp); + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val | 1ULL); + + spin_lock(&rvu->cpt_intr_lock); + block->cpt_flt_eng_map[vec] |= BIT_ULL(i); + val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_STS(eng)); + val = val & 0x3; + if (val == 0x1 || val == 0x2) + block->cpt_rcvrd_eng_map[vec] |= BIT_ULL(i); + spin_unlock(&rvu->cpt_intr_lock); } - - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(0), reg0); - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(1), reg1); - if (!is_rvu_otx2(rvu)) - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(2), reg2); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(vec), reg); return IRQ_HANDLED; } +static irqreturn_t rvu_cpt_af_flt0_intr_handler(int irq, void *ptr) +{ + return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT0, ptr); +} + +static irqreturn_t rvu_cpt_af_flt1_intr_handler(int irq, void *ptr) +{ + return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT1, ptr); +} + +static irqreturn_t rvu_cpt_af_flt2_intr_handler(int irq, void *ptr) +{ + return cpt_af_flt_intr_handler(CPT_10K_AF_INT_VEC_FLT2, ptr); +} + static irqreturn_t rvu_cpt_af_rvu_intr_handler(int irq, void *ptr) { struct rvu_block *block = ptr; @@ -119,8 +153,10 @@ static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off) int i; /* Disable all CPT AF interrupts */ - for (i = 0; i < CPT_10K_AF_INT_VEC_RVU; i++) - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(0), ~0ULL); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(1), ~0ULL); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(2), 0xFFFF); + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); @@ -151,7 +187,7 @@ static void cpt_unregister_interrupts(struct rvu *rvu, int blkaddr) /* Disable all CPT AF interrupts */ for (i = 0; i < CPT_AF_INT_VEC_RVU; i++) - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), ~0ULL); rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); @@ -172,16 +208,31 @@ static int cpt_10k_register_interrupts(struct rvu_block *block, int off) { struct rvu *rvu = block->rvu; int blkaddr = block->addr; + irq_handler_t flt_fn; int i, ret; for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) { sprintf(&rvu->irq_name[(off + i) * NAME_SIZE], "CPTAF FLT%d", i); + + switch (i) { + case CPT_10K_AF_INT_VEC_FLT0: + flt_fn = rvu_cpt_af_flt0_intr_handler; + break; + case CPT_10K_AF_INT_VEC_FLT1: + flt_fn = rvu_cpt_af_flt1_intr_handler; + break; + case CPT_10K_AF_INT_VEC_FLT2: + flt_fn = rvu_cpt_af_flt2_intr_handler; + break; + } ret = rvu_cpt_do_register_interrupt(block, off + i, - rvu_cpt_af_flt_intr_handler, - &rvu->irq_name[(off + i) * NAME_SIZE]); + flt_fn, &rvu->irq_name[(off + i) * NAME_SIZE]); if (ret) goto err; - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + if (i == CPT_10K_AF_INT_VEC_FLT2) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0xFFFF); + else + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL); } ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU, @@ -208,8 +259,8 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr) { struct rvu_hwinfo *hw = rvu->hw; struct rvu_block *block; + irq_handler_t flt_fn; int i, offs, ret = 0; - char irq_name[16]; if (!is_block_implemented(rvu->hw, blkaddr)) return 0; @@ -226,13 +277,20 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr) return cpt_10k_register_interrupts(block, offs); for (i = CPT_AF_INT_VEC_FLT0; i < CPT_AF_INT_VEC_RVU; i++) { - snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i); + sprintf(&rvu->irq_name[(offs + i) * NAME_SIZE], "CPTAF FLT%d", i); + switch (i) { + case CPT_AF_INT_VEC_FLT0: + flt_fn = rvu_cpt_af_flt0_intr_handler; + break; + case CPT_AF_INT_VEC_FLT1: + flt_fn = rvu_cpt_af_flt1_intr_handler; + break; + } ret = rvu_cpt_do_register_interrupt(block, offs + i, - rvu_cpt_af_flt_intr_handler, - irq_name); + flt_fn, &rvu->irq_name[(offs + i) * NAME_SIZE]); if (ret) goto err; - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL); } ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RVU, @@ -290,7 +348,7 @@ static int get_cpt_pf_num(struct rvu *rvu) static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc) { - int cpt_pf_num = get_cpt_pf_num(rvu); + int cpt_pf_num = rvu->cpt_pf_num; if (rvu_get_pf(pcifunc) != cpt_pf_num) return false; @@ -302,7 +360,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc) static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc) { - int cpt_pf_num = get_cpt_pf_num(rvu); + int cpt_pf_num = rvu->cpt_pf_num; if (rvu_get_pf(pcifunc) != cpt_pf_num) return false; @@ -371,8 +429,12 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu, /* Set CPT LF group and priority */ val = (u64)req->eng_grpmsk << 48 | 1; - if (!is_rvu_otx2(rvu)) - val |= (CPT_CTX_ILEN << 17); + if (!is_rvu_otx2(rvu)) { + if (req->ctx_ilen_valid) + val |= (req->ctx_ilen << 17); + else + val |= (CPT_CTX_ILEN << 17); + } rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val); @@ -762,10 +824,21 @@ int rvu_mbox_handler_cpt_sts(struct rvu *rvu, struct cpt_sts_req *req, #define RXC_ZOMBIE_COUNT GENMASK_ULL(60, 48) static void cpt_rxc_time_cfg(struct rvu *rvu, struct cpt_rxc_time_cfg_req *req, - int blkaddr) + int blkaddr, struct cpt_rxc_time_cfg_req *save) { u64 dfrg_reg; + if (save) { + /* Save older config */ + dfrg_reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_DFRG); + save->zombie_thres = FIELD_GET(RXC_ZOMBIE_THRES, dfrg_reg); + save->zombie_limit = FIELD_GET(RXC_ZOMBIE_LIMIT, dfrg_reg); + save->active_thres = FIELD_GET(RXC_ACTIVE_THRES, dfrg_reg); + save->active_limit = FIELD_GET(RXC_ACTIVE_LIMIT, dfrg_reg); + + save->step = rvu_read64(rvu, blkaddr, CPT_AF_RXC_TIME_CFG); + } + dfrg_reg = FIELD_PREP(RXC_ZOMBIE_THRES, req->zombie_thres); dfrg_reg |= FIELD_PREP(RXC_ZOMBIE_LIMIT, req->zombie_limit); dfrg_reg |= FIELD_PREP(RXC_ACTIVE_THRES, req->active_thres); @@ -790,7 +863,7 @@ int rvu_mbox_handler_cpt_rxc_time_cfg(struct rvu *rvu, !is_cpt_vf(rvu, req->hdr.pcifunc)) return CPT_AF_ERR_ACCESS_DENIED; - cpt_rxc_time_cfg(rvu, req, blkaddr); + cpt_rxc_time_cfg(rvu, req, blkaddr, NULL); return 0; } @@ -801,9 +874,67 @@ int rvu_mbox_handler_cpt_ctx_cache_sync(struct rvu *rvu, struct msg_req *req, return rvu_cpt_ctx_flush(rvu, req->hdr.pcifunc); } +int rvu_mbox_handler_cpt_lf_reset(struct rvu *rvu, struct cpt_lf_rst_req *req, + struct msg_rsp *rsp) +{ + u16 pcifunc = req->hdr.pcifunc; + struct rvu_block *block; + int cptlf, blkaddr, ret; + u16 actual_slot; + u64 ctl, ctl2; + + blkaddr = rvu_get_blkaddr_from_slot(rvu, BLKTYPE_CPT, pcifunc, + req->slot, &actual_slot); + if (blkaddr < 0) + return CPT_AF_ERR_LF_INVALID; + + block = &rvu->hw->block[blkaddr]; + + cptlf = rvu_get_lf(rvu, block, pcifunc, actual_slot); + if (cptlf < 0) + return CPT_AF_ERR_LF_INVALID; + ctl = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf)); + ctl2 = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf)); + + ret = rvu_lf_reset(rvu, block, cptlf); + if (ret) + dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n", + block->addr, cptlf); + + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), ctl); + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), ctl2); + + return 0; +} + +int rvu_mbox_handler_cpt_flt_eng_info(struct rvu *rvu, struct cpt_flt_eng_info_req *req, + struct cpt_flt_eng_info_rsp *rsp) +{ + struct rvu_block *block; + unsigned long flags; + int blkaddr, vec; + + blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr); + if (blkaddr < 0) + return blkaddr; + + block = &rvu->hw->block[blkaddr]; + for (vec = 0; vec < CPT_10K_AF_INT_VEC_RVU; vec++) { + spin_lock_irqsave(&rvu->cpt_intr_lock, flags); + rsp->flt_eng_map[vec] = block->cpt_flt_eng_map[vec]; + rsp->rcvrd_eng_map[vec] = block->cpt_rcvrd_eng_map[vec]; + if (req->reset) { + block->cpt_flt_eng_map[vec] = 0x0; + block->cpt_rcvrd_eng_map[vec] = 0x0; + } + spin_unlock_irqrestore(&rvu->cpt_intr_lock, flags); + } + return 0; +} + static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr) { - struct cpt_rxc_time_cfg_req req; + struct cpt_rxc_time_cfg_req req, prev; int timeout = 2000; u64 reg; @@ -819,7 +950,7 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr) req.active_thres = 1; req.active_limit = 1; - cpt_rxc_time_cfg(rvu, &req, blkaddr); + cpt_rxc_time_cfg(rvu, &req, blkaddr, &prev); do { reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ACTIVE_STS); @@ -845,70 +976,68 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr) if (timeout == 0) dev_warn(rvu->dev, "Poll for RXC zombie count hits hard loop counter\n"); + + /* Restore config */ + cpt_rxc_time_cfg(rvu, &prev, blkaddr, NULL); } -#define INPROG_INFLIGHT(reg) ((reg) & 0x1FF) -#define INPROG_GRB_PARTIAL(reg) ((reg) & BIT_ULL(31)) -#define INPROG_GRB(reg) (((reg) >> 32) & 0xFF) -#define INPROG_GWB(reg) (((reg) >> 40) & 0xFF) +#define INFLIGHT GENMASK_ULL(8, 0) +#define GRB_CNT GENMASK_ULL(39, 32) +#define GWB_CNT GENMASK_ULL(47, 40) +#define XQ_XOR GENMASK_ULL(63, 63) +#define DQPTR GENMASK_ULL(19, 0) +#define NQPTR GENMASK_ULL(51, 32) static void cpt_lf_disable_iqueue(struct rvu *rvu, int blkaddr, int slot) { - int i = 0, hard_lp_ctr = 100000; - u64 inprog, grp_ptr; - u16 nq_ptr, dq_ptr; + int timeout = 1000000; + u64 inprog, inst_ptr; + u64 qsize, pending; + int i = 0; /* Disable instructions enqueuing */ rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_CTL), 0x0); - /* Disable executions in the LF's queue */ inprog = rvu_read64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG)); - inprog &= ~BIT_ULL(16); + inprog |= BIT_ULL(16); rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG), inprog); - /* Wait for CPT queue to become execution-quiescent */ + qsize = rvu_read64(rvu, blkaddr, + CPT_AF_BAR2_ALIASX(slot, CPT_LF_Q_SIZE)) & 0x7FFF; do { - inprog = rvu_read64(rvu, blkaddr, - CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG)); - if (INPROG_GRB_PARTIAL(inprog)) { - i = 0; - hard_lp_ctr--; - } else { - i++; - } - - grp_ptr = rvu_read64(rvu, blkaddr, - CPT_AF_BAR2_ALIASX(slot, - CPT_LF_Q_GRP_PTR)); - nq_ptr = (grp_ptr >> 32) & 0x7FFF; - dq_ptr = grp_ptr & 0x7FFF; - - } while (hard_lp_ctr && (i < 10) && (nq_ptr != dq_ptr)); + inst_ptr = rvu_read64(rvu, blkaddr, + CPT_AF_BAR2_ALIASX(slot, CPT_LF_Q_INST_PTR)); + pending = (FIELD_GET(XQ_XOR, inst_ptr) * qsize * 40) + + FIELD_GET(NQPTR, inst_ptr) - + FIELD_GET(DQPTR, inst_ptr); + udelay(1); + timeout--; + } while ((pending != 0) && (timeout != 0)); - if (hard_lp_ctr == 0) - dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n"); + if (timeout == 0) + dev_warn(rvu->dev, "TIMEOUT: CPT poll on pending instructions\n"); - i = 0; - hard_lp_ctr = 100000; + timeout = 1000000; + /* Wait for CPT queue to become execution-quiescent */ do { inprog = rvu_read64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG)); - if ((INPROG_INFLIGHT(inprog) == 0) && - (INPROG_GWB(inprog) < 40) && - ((INPROG_GRB(inprog) == 0) || - (INPROG_GRB((inprog)) == 40))) { + if ((FIELD_GET(INFLIGHT, inprog) == 0) && + (FIELD_GET(GRB_CNT, inprog) == 0)) { i++; } else { i = 0; - hard_lp_ctr--; + timeout--; } - } while (hard_lp_ctr && (i < 10)); + } while ((timeout != 0) && (i < 10)); - if (hard_lp_ctr == 0) - dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n"); + if (timeout == 0) + dev_warn(rvu->dev, "TIMEOUT: CPT poll on inflight count\n"); + /* Wait for 2 us to flush all queue writes to memory */ + udelay(2); } int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot) @@ -918,18 +1047,15 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s if (is_cpt_pf(rvu, pcifunc) || is_cpt_vf(rvu, pcifunc)) cpt_rxc_teardown(rvu, blkaddr); + mutex_lock(&rvu->alias_lock); /* Enable BAR2 ALIAS for this pcifunc. */ reg = BIT_ULL(16) | pcifunc; - rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg); + rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg); cpt_lf_disable_iqueue(rvu, blkaddr, slot); - /* Set group drop to help clear out hardware */ - reg = rvu_read64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG)); - reg |= BIT_ULL(17); - rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG), reg); - - rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0); + rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0); + mutex_unlock(&rvu->alias_lock); return 0; } @@ -940,7 +1066,7 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s static int cpt_inline_inb_lf_cmd_send(struct rvu *rvu, int blkaddr, int nix_blkaddr) { - int cpt_pf_num = get_cpt_pf_num(rvu); + int cpt_pf_num = rvu->cpt_pf_num; struct cpt_inst_lmtst_req *req; dma_addr_t res_daddr; int timeout = 3000; @@ -1064,7 +1190,7 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc) /* Enable BAR2 ALIAS for this pcifunc. */ reg = BIT_ULL(16) | pcifunc; - rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg); + rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg); for (i = 0; i < max_ctx_entries; i++) { cam_data = rvu_read64(rvu, blkaddr, CPT_AF_CTX_CAM_DATA(i)); @@ -1077,10 +1203,19 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc) reg); } } - rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0); + rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0); unlock: mutex_unlock(&rvu->rsrc_lock); return 0; } + +int rvu_cpt_init(struct rvu *rvu) +{ + /* Retrieve CPT PF number */ + rvu->cpt_pf_num = get_cpt_pf_num(rvu); + spin_lock_init(&rvu->cpt_intr_lock); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 6b8747ebc08c..89e94569e74c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4731,6 +4731,10 @@ int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu, #define CPT_INST_QSEL_PF_FUNC GENMASK_ULL(23, 8) #define CPT_INST_QSEL_SLOT GENMASK_ULL(7, 0) +#define CPT_INST_CREDIT_TH GENMASK_ULL(53, 32) +#define CPT_INST_CREDIT_BPID GENMASK_ULL(30, 22) +#define CPT_INST_CREDIT_CNT GENMASK_ULL(21, 0) + static void nix_inline_ipsec_cfg(struct rvu *rvu, struct nix_inline_ipsec_cfg *req, int blkaddr) { @@ -4767,14 +4771,23 @@ static void nix_inline_ipsec_cfg(struct rvu *rvu, struct nix_inline_ipsec_cfg *r val); /* Set CPT credit */ - rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), - req->cpt_credit); + val = rvu_read64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx)); + if ((val & 0x3FFFFF) != 0x3FFFFF) + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), + 0x3FFFFF - val); + + val = FIELD_PREP(CPT_INST_CREDIT_CNT, req->cpt_credit); + val |= FIELD_PREP(CPT_INST_CREDIT_BPID, req->bpid); + val |= FIELD_PREP(CPT_INST_CREDIT_TH, req->credit_th); + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), val); } else { rvu_write64(rvu, blkaddr, NIX_AF_RX_IPSEC_GEN_CFG, 0x0); rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_INST_QSEL(cpt_idx), 0x0); - rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), - 0x3FFFFF); + val = rvu_read64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx)); + if ((val & 0x3FFFFF) != 0x3FFFFF) + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), + 0x3FFFFF - val); } } @@ -4792,6 +4805,30 @@ int rvu_mbox_handler_nix_inline_ipsec_cfg(struct rvu *rvu, return 0; } +int rvu_mbox_handler_nix_read_inline_ipsec_cfg(struct rvu *rvu, + struct msg_req *req, + struct nix_inline_ipsec_cfg *rsp) + +{ + u64 val; + + if (!is_block_implemented(rvu->hw, BLKADDR_CPT0)) + return 0; + + val = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_RX_IPSEC_GEN_CFG); + rsp->gen_cfg.egrp = FIELD_GET(IPSEC_GEN_CFG_EGRP, val); + rsp->gen_cfg.opcode = FIELD_GET(IPSEC_GEN_CFG_OPCODE, val); + rsp->gen_cfg.param1 = FIELD_GET(IPSEC_GEN_CFG_PARAM1, val); + rsp->gen_cfg.param2 = FIELD_GET(IPSEC_GEN_CFG_PARAM2, val); + + val = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_RX_CPTX_CREDIT(0)); + rsp->cpt_credit = FIELD_GET(CPT_INST_CREDIT_CNT, val); + rsp->credit_th = FIELD_GET(CPT_INST_CREDIT_TH, val); + rsp->bpid = FIELD_GET(CPT_INST_CREDIT_BPID, val); + + return 0; +} + int rvu_mbox_handler_nix_inline_ipsec_lf_cfg(struct rvu *rvu, struct nix_inline_ipsec_lf_cfg *req, struct msg_rsp *rsp) @@ -4835,6 +4872,7 @@ int rvu_mbox_handler_nix_inline_ipsec_lf_cfg(struct rvu *rvu, return 0; } + void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc) { bool from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 0e0d536645ac..5437bd20c719 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -545,6 +545,8 @@ #define CPT_LF_CTL 0x10 #define CPT_LF_INPROG 0x40 +#define CPT_LF_Q_SIZE 0x100 +#define CPT_LF_Q_INST_PTR 0x110 #define CPT_LF_Q_GRP_PTR 0x120 #define CPT_LF_CTX_FLUSH 0x510 diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index cf456d62677f..87fff539d39d 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -965,7 +965,7 @@ static int pxa168_init_phy(struct net_device *dev) if (dev->phydev) return 0; - phy = mdiobus_scan(pep->smi_bus, pep->phy_addr); + phy = mdiobus_scan_c22(pep->smi_bus, pep->phy_addr); if (IS_ERR(phy)) return PTR_ERR(phy); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e3de9a53b2d9..801deac58bf7 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -51,6 +51,7 @@ static const struct mtk_reg_map mtk_reg_map = { .delay_irq = 0x0a0c, .irq_status = 0x0a20, .irq_mask = 0x0a28, + .adma_rx_dbg0 = 0x0a38, .int_grp = 0x0a50, }, .qdma = { @@ -82,6 +83,8 @@ static const struct mtk_reg_map mtk_reg_map = { [0] = 0x2800, [1] = 0x2c00, }, + .pse_iq_sta = 0x0110, + .pse_oq_sta = 0x0118, }; static const struct mtk_reg_map mt7628_reg_map = { @@ -112,6 +115,7 @@ static const struct mtk_reg_map mt7986_reg_map = { .delay_irq = 0x620c, .irq_status = 0x6220, .irq_mask = 0x6228, + .adma_rx_dbg0 = 0x6238, .int_grp = 0x6250, }, .qdma = { @@ -143,6 +147,8 @@ static const struct mtk_reg_map mt7986_reg_map = { [0] = 0x4800, [1] = 0x4c00, }, + .pse_iq_sta = 0x0180, + .pse_oq_sta = 0x01a0, }; /* strings used by ethtool */ @@ -215,8 +221,8 @@ static int mtk_mdio_busy_wait(struct mtk_eth *eth) return -ETIMEDOUT; } -static int _mtk_mdio_write(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg, - u32 write_data) +static int _mtk_mdio_write_c22(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg, + u32 write_data) { int ret; @@ -224,35 +230,13 @@ static int _mtk_mdio_write(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg, if (ret < 0) return ret; - if (phy_reg & MII_ADDR_C45) { - mtk_w32(eth, PHY_IAC_ACCESS | - PHY_IAC_START_C45 | - PHY_IAC_CMD_C45_ADDR | - PHY_IAC_REG(mdiobus_c45_devad(phy_reg)) | - PHY_IAC_ADDR(phy_addr) | - PHY_IAC_DATA(mdiobus_c45_regad(phy_reg)), - MTK_PHY_IAC); - - ret = mtk_mdio_busy_wait(eth); - if (ret < 0) - return ret; - - mtk_w32(eth, PHY_IAC_ACCESS | - PHY_IAC_START_C45 | - PHY_IAC_CMD_WRITE | - PHY_IAC_REG(mdiobus_c45_devad(phy_reg)) | - PHY_IAC_ADDR(phy_addr) | - PHY_IAC_DATA(write_data), - MTK_PHY_IAC); - } else { - mtk_w32(eth, PHY_IAC_ACCESS | - PHY_IAC_START_C22 | - PHY_IAC_CMD_WRITE | - PHY_IAC_REG(phy_reg) | - PHY_IAC_ADDR(phy_addr) | - PHY_IAC_DATA(write_data), - MTK_PHY_IAC); - } + mtk_w32(eth, PHY_IAC_ACCESS | + PHY_IAC_START_C22 | + PHY_IAC_CMD_WRITE | + PHY_IAC_REG(phy_reg) | + PHY_IAC_ADDR(phy_addr) | + PHY_IAC_DATA(write_data), + MTK_PHY_IAC); ret = mtk_mdio_busy_wait(eth); if (ret < 0) @@ -261,7 +245,8 @@ static int _mtk_mdio_write(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg, return 0; } -static int _mtk_mdio_read(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg) +static int _mtk_mdio_write_c45(struct mtk_eth *eth, u32 phy_addr, + u32 devad, u32 phy_reg, u32 write_data) { int ret; @@ -269,33 +254,47 @@ static int _mtk_mdio_read(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg) if (ret < 0) return ret; - if (phy_reg & MII_ADDR_C45) { - mtk_w32(eth, PHY_IAC_ACCESS | - PHY_IAC_START_C45 | - PHY_IAC_CMD_C45_ADDR | - PHY_IAC_REG(mdiobus_c45_devad(phy_reg)) | - PHY_IAC_ADDR(phy_addr) | - PHY_IAC_DATA(mdiobus_c45_regad(phy_reg)), - MTK_PHY_IAC); - - ret = mtk_mdio_busy_wait(eth); - if (ret < 0) - return ret; - - mtk_w32(eth, PHY_IAC_ACCESS | - PHY_IAC_START_C45 | - PHY_IAC_CMD_C45_READ | - PHY_IAC_REG(mdiobus_c45_devad(phy_reg)) | - PHY_IAC_ADDR(phy_addr), - MTK_PHY_IAC); - } else { - mtk_w32(eth, PHY_IAC_ACCESS | - PHY_IAC_START_C22 | - PHY_IAC_CMD_C22_READ | - PHY_IAC_REG(phy_reg) | - PHY_IAC_ADDR(phy_addr), - MTK_PHY_IAC); - } + mtk_w32(eth, PHY_IAC_ACCESS | + PHY_IAC_START_C45 | + PHY_IAC_CMD_C45_ADDR | + PHY_IAC_REG(devad) | + PHY_IAC_ADDR(phy_addr) | + PHY_IAC_DATA(phy_reg), + MTK_PHY_IAC); + + ret = mtk_mdio_busy_wait(eth); + if (ret < 0) + return ret; + + mtk_w32(eth, PHY_IAC_ACCESS | + PHY_IAC_START_C45 | + PHY_IAC_CMD_WRITE | + PHY_IAC_REG(devad) | + PHY_IAC_ADDR(phy_addr) | + PHY_IAC_DATA(write_data), + MTK_PHY_IAC); + + ret = mtk_mdio_busy_wait(eth); + if (ret < 0) + return ret; + + return 0; +} + +static int _mtk_mdio_read_c22(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg) +{ + int ret; + + ret = mtk_mdio_busy_wait(eth); + if (ret < 0) + return ret; + + mtk_w32(eth, PHY_IAC_ACCESS | + PHY_IAC_START_C22 | + PHY_IAC_CMD_C22_READ | + PHY_IAC_REG(phy_reg) | + PHY_IAC_ADDR(phy_addr), + MTK_PHY_IAC); ret = mtk_mdio_busy_wait(eth); if (ret < 0) @@ -304,19 +303,70 @@ static int _mtk_mdio_read(struct mtk_eth *eth, u32 phy_addr, u32 phy_reg) return mtk_r32(eth, MTK_PHY_IAC) & PHY_IAC_DATA_MASK; } -static int mtk_mdio_write(struct mii_bus *bus, int phy_addr, - int phy_reg, u16 val) +static int _mtk_mdio_read_c45(struct mtk_eth *eth, u32 phy_addr, + u32 devad, u32 phy_reg) +{ + int ret; + + ret = mtk_mdio_busy_wait(eth); + if (ret < 0) + return ret; + + mtk_w32(eth, PHY_IAC_ACCESS | + PHY_IAC_START_C45 | + PHY_IAC_CMD_C45_ADDR | + PHY_IAC_REG(devad) | + PHY_IAC_ADDR(phy_addr) | + PHY_IAC_DATA(phy_reg), + MTK_PHY_IAC); + + ret = mtk_mdio_busy_wait(eth); + if (ret < 0) + return ret; + + mtk_w32(eth, PHY_IAC_ACCESS | + PHY_IAC_START_C45 | + PHY_IAC_CMD_C45_READ | + PHY_IAC_REG(devad) | + PHY_IAC_ADDR(phy_addr), + MTK_PHY_IAC); + + ret = mtk_mdio_busy_wait(eth); + if (ret < 0) + return ret; + + return mtk_r32(eth, MTK_PHY_IAC) & PHY_IAC_DATA_MASK; +} + +static int mtk_mdio_write_c22(struct mii_bus *bus, int phy_addr, + int phy_reg, u16 val) +{ + struct mtk_eth *eth = bus->priv; + + return _mtk_mdio_write_c22(eth, phy_addr, phy_reg, val); +} + +static int mtk_mdio_write_c45(struct mii_bus *bus, int phy_addr, + int devad, int phy_reg, u16 val) +{ + struct mtk_eth *eth = bus->priv; + + return _mtk_mdio_write_c45(eth, phy_addr, devad, phy_reg, val); +} + +static int mtk_mdio_read_c22(struct mii_bus *bus, int phy_addr, int phy_reg) { struct mtk_eth *eth = bus->priv; - return _mtk_mdio_write(eth, phy_addr, phy_reg, val); + return _mtk_mdio_read_c22(eth, phy_addr, phy_reg); } -static int mtk_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg) +static int mtk_mdio_read_c45(struct mii_bus *bus, int phy_addr, int devad, + int phy_reg) { struct mtk_eth *eth = bus->priv; - return _mtk_mdio_read(eth, phy_addr, phy_reg); + return _mtk_mdio_read_c45(eth, phy_addr, devad, phy_reg); } static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth, @@ -760,9 +810,10 @@ static int mtk_mdio_init(struct mtk_eth *eth) } eth->mii_bus->name = "mdio"; - eth->mii_bus->read = mtk_mdio_read; - eth->mii_bus->write = mtk_mdio_write; - eth->mii_bus->probe_capabilities = MDIOBUS_C22_C45; + eth->mii_bus->read = mtk_mdio_read_c22; + eth->mii_bus->write = mtk_mdio_write_c22; + eth->mii_bus->read_c45 = mtk_mdio_read_c45; + eth->mii_bus->write_c45 = mtk_mdio_write_c45; eth->mii_bus->priv = eth; eth->mii_bus->parent = eth->dev; @@ -2984,14 +3035,29 @@ static void mtk_dma_free(struct mtk_eth *eth) kfree(eth->scratch_head); } +static bool mtk_hw_reset_check(struct mtk_eth *eth) +{ + u32 val = mtk_r32(eth, MTK_INT_STATUS2); + + return (val & MTK_FE_INT_FQ_EMPTY) || (val & MTK_FE_INT_RFIFO_UF) || + (val & MTK_FE_INT_RFIFO_OV) || (val & MTK_FE_INT_TSO_FAIL) || + (val & MTK_FE_INT_TSO_ALIGN) || (val & MTK_FE_INT_TSO_ILLEGAL); +} + static void mtk_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; + if (test_bit(MTK_RESETTING, ð->state)) + return; + + if (!mtk_hw_reset_check(eth)) + return; + eth->netdev[mac->id]->stats.tx_errors++; - netif_err(eth, tx_err, dev, - "transmit timed out\n"); + netif_err(eth, tx_err, dev, "transmit timed out\n"); + schedule_work(ð->pending_work); } @@ -3471,22 +3537,188 @@ static void mtk_set_mcr_max_rx(struct mtk_mac *mac, u32 val) mtk_w32(mac->hw, mcr_new, MTK_MAC_MCR(mac->id)); } -static int mtk_hw_init(struct mtk_eth *eth) +static void mtk_hw_reset(struct mtk_eth *eth) +{ + u32 val; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { + regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, 0); + val = RSTCTRL_PPE0_V2; + } else { + val = RSTCTRL_PPE0; + } + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) + val |= RSTCTRL_PPE1; + + ethsys_reset(eth, RSTCTRL_ETH | RSTCTRL_FE | val); + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, + 0x3ffffff); +} + +static u32 mtk_hw_reset_read(struct mtk_eth *eth) +{ + u32 val; + + regmap_read(eth->ethsys, ETHSYS_RSTCTRL, &val); + return val; +} + +static void mtk_hw_warm_reset(struct mtk_eth *eth) +{ + u32 rst_mask, val; + + regmap_update_bits(eth->ethsys, ETHSYS_RSTCTRL, RSTCTRL_FE, + RSTCTRL_FE); + if (readx_poll_timeout_atomic(mtk_hw_reset_read, eth, val, + val & RSTCTRL_FE, 1, 1000)) { + dev_err(eth->dev, "warm reset failed\n"); + mtk_hw_reset(eth); + return; + } + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0_V2; + else + rst_mask = RSTCTRL_ETH | RSTCTRL_PPE0; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) + rst_mask |= RSTCTRL_PPE1; + + regmap_update_bits(eth->ethsys, ETHSYS_RSTCTRL, rst_mask, rst_mask); + + udelay(1); + val = mtk_hw_reset_read(eth); + if (!(val & rst_mask)) + dev_err(eth->dev, "warm reset stage0 failed %08x (%08x)\n", + val, rst_mask); + + rst_mask |= RSTCTRL_FE; + regmap_update_bits(eth->ethsys, ETHSYS_RSTCTRL, rst_mask, ~rst_mask); + + udelay(1); + val = mtk_hw_reset_read(eth); + if (val & rst_mask) + dev_err(eth->dev, "warm reset stage1 failed %08x (%08x)\n", + val, rst_mask); +} + +static bool mtk_hw_check_dma_hang(struct mtk_eth *eth) +{ + const struct mtk_reg_map *reg_map = eth->soc->reg_map; + bool gmac1_tx, gmac2_tx, gdm1_tx, gdm2_tx; + bool oq_hang, cdm1_busy, adma_busy; + bool wtx_busy, cdm_full, oq_free; + u32 wdidx, val, gdm1_fc, gdm2_fc; + bool qfsm_hang, qfwd_hang; + bool ret = false; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + return false; + + /* WDMA sanity checks */ + wdidx = mtk_r32(eth, reg_map->wdma_base[0] + 0xc); + + val = mtk_r32(eth, reg_map->wdma_base[0] + 0x204); + wtx_busy = FIELD_GET(MTK_TX_DMA_BUSY, val); + + val = mtk_r32(eth, reg_map->wdma_base[0] + 0x230); + cdm_full = !FIELD_GET(MTK_CDM_TXFIFO_RDY, val); + + oq_free = (!(mtk_r32(eth, reg_map->pse_oq_sta) & GENMASK(24, 16)) && + !(mtk_r32(eth, reg_map->pse_oq_sta + 0x4) & GENMASK(8, 0)) && + !(mtk_r32(eth, reg_map->pse_oq_sta + 0x10) & GENMASK(24, 16))); + + if (wdidx == eth->reset.wdidx && wtx_busy && cdm_full && oq_free) { + if (++eth->reset.wdma_hang_count > 2) { + eth->reset.wdma_hang_count = 0; + ret = true; + } + goto out; + } + + /* QDMA sanity checks */ + qfsm_hang = !!mtk_r32(eth, reg_map->qdma.qtx_cfg + 0x234); + qfwd_hang = !mtk_r32(eth, reg_map->qdma.qtx_cfg + 0x308); + + gdm1_tx = FIELD_GET(GENMASK(31, 16), mtk_r32(eth, MTK_FE_GDM1_FSM)) > 0; + gdm2_tx = FIELD_GET(GENMASK(31, 16), mtk_r32(eth, MTK_FE_GDM2_FSM)) > 0; + gmac1_tx = FIELD_GET(GENMASK(31, 24), mtk_r32(eth, MTK_MAC_FSM(0))) != 1; + gmac2_tx = FIELD_GET(GENMASK(31, 24), mtk_r32(eth, MTK_MAC_FSM(1))) != 1; + gdm1_fc = mtk_r32(eth, reg_map->gdm1_cnt + 0x24); + gdm2_fc = mtk_r32(eth, reg_map->gdm1_cnt + 0x64); + + if (qfsm_hang && qfwd_hang && + ((gdm1_tx && gmac1_tx && gdm1_fc < 1) || + (gdm2_tx && gmac2_tx && gdm2_fc < 1))) { + if (++eth->reset.qdma_hang_count > 2) { + eth->reset.qdma_hang_count = 0; + ret = true; + } + goto out; + } + + /* ADMA sanity checks */ + oq_hang = !!(mtk_r32(eth, reg_map->pse_oq_sta) & GENMASK(8, 0)); + cdm1_busy = !!(mtk_r32(eth, MTK_FE_CDM1_FSM) & GENMASK(31, 16)); + adma_busy = !(mtk_r32(eth, reg_map->pdma.adma_rx_dbg0) & GENMASK(4, 0)) && + !(mtk_r32(eth, reg_map->pdma.adma_rx_dbg0) & BIT(6)); + + if (oq_hang && cdm1_busy && adma_busy) { + if (++eth->reset.adma_hang_count > 2) { + eth->reset.adma_hang_count = 0; + ret = true; + } + goto out; + } + + eth->reset.wdma_hang_count = 0; + eth->reset.qdma_hang_count = 0; + eth->reset.adma_hang_count = 0; +out: + eth->reset.wdidx = wdidx; + + return ret; +} + +static void mtk_hw_reset_monitor_work(struct work_struct *work) +{ + struct delayed_work *del_work = to_delayed_work(work); + struct mtk_eth *eth = container_of(del_work, struct mtk_eth, + reset.monitor_work); + + if (test_bit(MTK_RESETTING, ð->state)) + goto out; + + /* DMA stuck checks */ + if (mtk_hw_check_dma_hang(eth)) + schedule_work(ð->pending_work); + +out: + schedule_delayed_work(ð->reset.monitor_work, + MTK_DMA_MONITOR_TIMEOUT); +} + +static int mtk_hw_init(struct mtk_eth *eth, bool reset) { u32 dma_mask = ETHSYS_DMA_AG_MAP_PDMA | ETHSYS_DMA_AG_MAP_QDMA | ETHSYS_DMA_AG_MAP_PPE; const struct mtk_reg_map *reg_map = eth->soc->reg_map; int i, val, ret; - if (test_and_set_bit(MTK_HW_INIT, ð->state)) + if (!reset && test_and_set_bit(MTK_HW_INIT, ð->state)) return 0; - pm_runtime_enable(eth->dev); - pm_runtime_get_sync(eth->dev); + if (!reset) { + pm_runtime_enable(eth->dev); + pm_runtime_get_sync(eth->dev); - ret = mtk_clk_enable(eth); - if (ret) - goto err_disable_pm; + ret = mtk_clk_enable(eth); + if (ret) + goto err_disable_pm; + } if (eth->ethsys) regmap_update_bits(eth->ethsys, ETHSYS_DMA_AG_MAP, dma_mask, @@ -3510,22 +3742,14 @@ static int mtk_hw_init(struct mtk_eth *eth) return 0; } - if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, 0); - val = RSTCTRL_PPE0_V2; - } else { - val = RSTCTRL_PPE0; - } - - if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) - val |= RSTCTRL_PPE1; + msleep(100); - ethsys_reset(eth, RSTCTRL_ETH | RSTCTRL_FE | val); + if (reset) + mtk_hw_warm_reset(eth); + else + mtk_hw_reset(eth); if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - regmap_write(eth->ethsys, ETHSYS_FE_RST_CHK_IDLE_EN, - 0x3ffffff); - /* Set FE to PDMAv2 if necessary */ val = mtk_r32(eth, MTK_FE_GLO_MISC); mtk_w32(eth, val | BIT(4), MTK_FE_GLO_MISC); @@ -3627,8 +3851,10 @@ static int mtk_hw_init(struct mtk_eth *eth) return 0; err_disable_pm: - pm_runtime_put_sync(eth->dev); - pm_runtime_disable(eth->dev); + if (!reset) { + pm_runtime_put_sync(eth->dev); + pm_runtime_disable(eth->dev); + } return ret; } @@ -3707,52 +3933,86 @@ static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EOPNOTSUPP; } +static void mtk_prepare_for_reset(struct mtk_eth *eth) +{ + u32 val; + int i; + + /* disabe FE P3 and P4 */ + val = mtk_r32(eth, MTK_FE_GLO_CFG) | MTK_FE_LINK_DOWN_P3; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) + val |= MTK_FE_LINK_DOWN_P4; + mtk_w32(eth, val, MTK_FE_GLO_CFG); + + /* adjust PPE configurations to prepare for reset */ + for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) + mtk_ppe_prepare_reset(eth->ppe[i]); + + /* disable NETSYS interrupts */ + mtk_w32(eth, 0, MTK_FE_INT_ENABLE); + + /* force link down GMAC */ + for (i = 0; i < 2; i++) { + val = mtk_r32(eth, MTK_MAC_MCR(i)) & ~MAC_MCR_FORCE_LINK; + mtk_w32(eth, val, MTK_MAC_MCR(i)); + } +} + static void mtk_pending_work(struct work_struct *work) { struct mtk_eth *eth = container_of(work, struct mtk_eth, pending_work); - int err, i; unsigned long restart = 0; + u32 val; + int i; rtnl_lock(); - - dev_dbg(eth->dev, "[%s][%d] reset\n", __func__, __LINE__); set_bit(MTK_RESETTING, ð->state); + mtk_prepare_for_reset(eth); + mtk_wed_fe_reset(); + /* Run again reset preliminary configuration in order to avoid any + * possible race during FE reset since it can run releasing RTNL lock. + */ + mtk_prepare_for_reset(eth); + /* stop all devices to make sure that dma is properly shut down */ for (i = 0; i < MTK_MAC_COUNT; i++) { - if (!eth->netdev[i]) + if (!eth->netdev[i] || !netif_running(eth->netdev[i])) continue; + mtk_stop(eth->netdev[i]); __set_bit(i, &restart); } - dev_dbg(eth->dev, "[%s][%d] mtk_stop ends\n", __func__, __LINE__); - /* restart underlying hardware such as power, clock, pin mux - * and the connected phy - */ - mtk_hw_deinit(eth); + usleep_range(15000, 16000); if (eth->dev->pins) pinctrl_select_state(eth->dev->pins->p, eth->dev->pins->default_state); - mtk_hw_init(eth); + mtk_hw_init(eth, true); /* restart DMA and enable IRQs */ for (i = 0; i < MTK_MAC_COUNT; i++) { if (!test_bit(i, &restart)) continue; - err = mtk_open(eth->netdev[i]); - if (err) { + + if (mtk_open(eth->netdev[i])) { netif_alert(eth, ifup, eth->netdev[i], - "Driver up/down cycle failed, closing device.\n"); + "Driver up/down cycle failed\n"); dev_close(eth->netdev[i]); } } - dev_dbg(eth->dev, "[%s][%d] reset done\n", __func__, __LINE__); + /* enabe FE P3 and P4 */ + val = mtk_r32(eth, MTK_FE_GLO_CFG) & ~MTK_FE_LINK_DOWN_P3; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_RSTCTRL_PPE1)) + val &= ~MTK_FE_LINK_DOWN_P4; + mtk_w32(eth, val, MTK_FE_GLO_CFG); clear_bit(MTK_RESETTING, ð->state); + mtk_wed_fe_reset_complete(); + rtnl_unlock(); } @@ -3797,6 +4057,7 @@ static int mtk_cleanup(struct mtk_eth *eth) mtk_unreg_dev(eth); mtk_free_dev(eth); cancel_work_sync(ð->pending_work); + cancel_delayed_work_sync(ð->reset.monitor_work); return 0; } @@ -4251,6 +4512,7 @@ static int mtk_probe(struct platform_device *pdev) eth->rx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; INIT_WORK(ð->rx_dim.work, mtk_dim_rx); + INIT_DELAYED_WORK(ð->reset.monitor_work, mtk_hw_reset_monitor_work); eth->tx_dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; INIT_WORK(ð->tx_dim.work, mtk_dim_tx); @@ -4364,7 +4626,7 @@ static int mtk_probe(struct platform_device *pdev) eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE); INIT_WORK(ð->pending_work, mtk_pending_work); - err = mtk_hw_init(eth); + err = mtk_hw_init(eth, false); if (err) goto err_wed_exit; @@ -4453,6 +4715,8 @@ static int mtk_probe(struct platform_device *pdev) netif_napi_add(ð->dummy_dev, ð->rx_napi, mtk_napi_rx); platform_set_drvdata(pdev, eth); + schedule_delayed_work(ð->reset.monitor_work, + MTK_DMA_MONITOR_TIMEOUT); return 0; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 18a50529ce7b..dff0e3ad2de6 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -77,12 +77,24 @@ #define MTK_HW_LRO_REPLACE_DELTA 1000 #define MTK_HW_LRO_SDL_REMAIN_ROOM 1522 +/* Frame Engine Global Configuration */ +#define MTK_FE_GLO_CFG 0x00 +#define MTK_FE_LINK_DOWN_P3 BIT(11) +#define MTK_FE_LINK_DOWN_P4 BIT(12) + /* Frame Engine Global Reset Register */ #define MTK_RST_GL 0x04 #define RST_GL_PSE BIT(0) /* Frame Engine Interrupt Status Register */ #define MTK_INT_STATUS2 0x08 +#define MTK_FE_INT_ENABLE 0x0c +#define MTK_FE_INT_FQ_EMPTY BIT(8) +#define MTK_FE_INT_TSO_FAIL BIT(12) +#define MTK_FE_INT_TSO_ILLEGAL BIT(13) +#define MTK_FE_INT_TSO_ALIGN BIT(14) +#define MTK_FE_INT_RFIFO_OV BIT(18) +#define MTK_FE_INT_RFIFO_UF BIT(19) #define MTK_GDM1_AF BIT(28) #define MTK_GDM2_AF BIT(29) @@ -272,6 +284,8 @@ #define MTK_RX_DONE_INT_V2 BIT(14) +#define MTK_CDM_TXFIFO_RDY BIT(7) + /* QDMA Interrupt grouping registers */ #define MTK_RLS_DONE_INT BIT(0) @@ -562,6 +576,17 @@ #define MT7628_SDM_RBCNT (MT7628_SDM_OFFSET + 0x10c) #define MT7628_SDM_CS_ERR (MT7628_SDM_OFFSET + 0x110) +#define MTK_FE_CDM1_FSM 0x220 +#define MTK_FE_CDM2_FSM 0x224 +#define MTK_FE_CDM3_FSM 0x238 +#define MTK_FE_CDM4_FSM 0x298 +#define MTK_FE_CDM5_FSM 0x318 +#define MTK_FE_CDM6_FSM 0x328 +#define MTK_FE_GDM1_FSM 0x228 +#define MTK_FE_GDM2_FSM 0x22C + +#define MTK_MAC_FSM(x) (0x1010C + ((x) * 0x100)) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; @@ -958,6 +983,7 @@ struct mtk_reg_map { u32 delay_irq; /* delay interrupt */ u32 irq_status; /* interrupt status */ u32 irq_mask; /* interrupt mask */ + u32 adma_rx_dbg0; u32 int_grp; } pdma; struct { @@ -986,6 +1012,8 @@ struct mtk_reg_map { u32 gdma_to_ppe; u32 ppe_base; u32 wdma_base[2]; + u32 pse_iq_sta; + u32 pse_oq_sta; }; /* struct mtk_eth_data - This is the structure holding all differences @@ -1028,6 +1056,8 @@ struct mtk_soc_data { } txrx; }; +#define MTK_DMA_MONITOR_TIMEOUT msecs_to_jiffies(1000) + /* currently no SoC has more than 2 macs */ #define MTK_MAX_DEVS 2 @@ -1152,6 +1182,14 @@ struct mtk_eth { struct rhashtable flow_table; struct bpf_prog __rcu *prog; + + struct { + struct delayed_work monitor_work; + u32 wdidx; + u8 wdma_hang_count; + u8 qdma_hang_count; + u8 adma_hang_count; + } reset; }; /* struct mtk_mac - the structure that holds the info about the MACs of the diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 269208a841c7..451a87b1bc20 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -730,6 +730,33 @@ int mtk_foe_entry_idle_time(struct mtk_ppe *ppe, struct mtk_flow_entry *entry) return __mtk_foe_entry_idle_time(ppe, entry->data.ib1); } +int mtk_ppe_prepare_reset(struct mtk_ppe *ppe) +{ + if (!ppe) + return -EINVAL; + + /* disable KA */ + ppe_clear(ppe, MTK_PPE_TB_CFG, MTK_PPE_TB_CFG_KEEPALIVE); + ppe_clear(ppe, MTK_PPE_BIND_LMT1, MTK_PPE_NTU_KEEPALIVE); + ppe_w32(ppe, MTK_PPE_KEEPALIVE, 0); + usleep_range(10000, 11000); + + /* set KA timer to maximum */ + ppe_set(ppe, MTK_PPE_BIND_LMT1, MTK_PPE_NTU_KEEPALIVE); + ppe_w32(ppe, MTK_PPE_KEEPALIVE, 0xffffffff); + + /* set KA tick select */ + ppe_set(ppe, MTK_PPE_TB_CFG, MTK_PPE_TB_TICK_SEL); + ppe_set(ppe, MTK_PPE_TB_CFG, MTK_PPE_TB_CFG_KEEPALIVE); + usleep_range(10000, 11000); + + /* disable scan mode */ + ppe_clear(ppe, MTK_PPE_TB_CFG, MTK_PPE_TB_CFG_SCAN_MODE); + usleep_range(10000, 11000); + + return mtk_ppe_wait_busy(ppe); +} + struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int version, int index) { diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index ea64fac1d425..16b02e1d4649 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -309,6 +309,7 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, void mtk_ppe_deinit(struct mtk_eth *eth); void mtk_ppe_start(struct mtk_ppe *ppe); int mtk_ppe_stop(struct mtk_ppe *ppe); +int mtk_ppe_prepare_reset(struct mtk_ppe *ppe); void __mtk_ppe_check_skb(struct mtk_ppe *ppe, struct sk_buff *skb, u16 hash); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_regs.h b/drivers/net/ethernet/mediatek/mtk_ppe_regs.h index 59596d823d8b..0fdb983b0a88 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_regs.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe_regs.h @@ -58,6 +58,12 @@ #define MTK_PPE_TB_CFG_SCAN_MODE GENMASK(17, 16) #define MTK_PPE_TB_CFG_HASH_DEBUG GENMASK(19, 18) #define MTK_PPE_TB_CFG_INFO_SEL BIT(20) +#define MTK_PPE_TB_TICK_SEL BIT(24) + +#define MTK_PPE_BIND_LMT1 0x230 +#define MTK_PPE_NTU_KEEPALIVE GENMASK(23, 16) + +#define MTK_PPE_KEEPALIVE 0x234 enum { MTK_PPE_SCAN_MODE_DISABLED, diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index a6271449617f..95ac4f71d2b2 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -206,6 +206,48 @@ mtk_wed_wo_reset(struct mtk_wed_device *dev) iounmap(reg); } +void mtk_wed_fe_reset(void) +{ + int i; + + mutex_lock(&hw_lock); + + for (i = 0; i < ARRAY_SIZE(hw_list); i++) { + struct mtk_wed_hw *hw = hw_list[i]; + struct mtk_wed_device *dev = hw->wed_dev; + int err; + + if (!dev || !dev->wlan.reset) + continue; + + /* reset callback blocks until WLAN reset is completed */ + err = dev->wlan.reset(dev); + if (err) + dev_err(dev->dev, "wlan reset failed: %d\n", err); + } + + mutex_unlock(&hw_lock); +} + +void mtk_wed_fe_reset_complete(void) +{ + int i; + + mutex_lock(&hw_lock); + + for (i = 0; i < ARRAY_SIZE(hw_list); i++) { + struct mtk_wed_hw *hw = hw_list[i]; + struct mtk_wed_device *dev = hw->wed_dev; + + if (!dev || !dev->wlan.reset_complete) + continue; + + dev->wlan.reset_complete(dev); + } + + mutex_unlock(&hw_lock); +} + static struct mtk_wed_hw * mtk_wed_assign(struct mtk_wed_device *dev) { diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h index e012b8a82133..43ab77eaf683 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.h +++ b/drivers/net/ethernet/mediatek/mtk_wed.h @@ -128,6 +128,8 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, void mtk_wed_exit(void); int mtk_wed_flow_add(int index); void mtk_wed_flow_remove(int index); +void mtk_wed_fe_reset(void); +void mtk_wed_fe_reset_complete(void); #else static inline void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, @@ -147,6 +149,13 @@ static inline void mtk_wed_flow_remove(int index) { } +static inline void mtk_wed_fe_reset(void) +{ +} + +static inline void mtk_wed_fe_reset_complete(void) +{ +} #endif #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index a0a39643caf7..69fba29055e9 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -138,7 +138,6 @@ mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, enum dma_data_direction dir = rx ? DMA_FROM_DEVICE : DMA_TO_DEVICE; int n_buf = 0; - spin_lock_bh(&q->lock); while (q->queued < q->n_desc) { struct mtk_wed_wo_queue_entry *entry; dma_addr_t addr; @@ -172,7 +171,6 @@ mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, q->queued++; n_buf++; } - spin_unlock_bh(&q->lock); return n_buf; } @@ -260,7 +258,6 @@ mtk_wed_wo_queue_alloc(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, int n_desc, int buf_size, int index, struct mtk_wed_wo_queue_regs *regs) { - spin_lock_init(&q->lock); q->regs = *regs; q->n_desc = n_desc; q->buf_size = buf_size; @@ -292,7 +289,6 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) struct page *page; int i; - spin_lock_bh(&q->lock); for (i = 0; i < q->n_desc; i++) { struct mtk_wed_wo_queue_entry *entry = &q->entry[i]; @@ -301,7 +297,6 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) skb_free_frag(entry->buf); entry->buf = NULL; } - spin_unlock_bh(&q->lock); if (!q->cache.va) return; @@ -316,7 +311,6 @@ mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { struct page *page; - spin_lock_bh(&q->lock); for (;;) { void *buf = mtk_wed_wo_dequeue(wo, q, NULL, true); @@ -325,7 +319,6 @@ mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) skb_free_frag(buf); } - spin_unlock_bh(&q->lock); if (!q->cache.va) return; @@ -351,8 +344,6 @@ int mtk_wed_wo_queue_tx_skb(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, int ret = 0, index; u32 ctrl; - spin_lock_bh(&q->lock); - q->tail = mtk_wed_mmio_r32(wo, q->regs.dma_idx); index = (q->head + 1) % q->n_desc; if (q->tail == index) { @@ -383,8 +374,6 @@ int mtk_wed_wo_queue_tx_skb(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, mtk_wed_wo_queue_kick(wo, q, q->head); mtk_wed_wo_kickout(wo); out: - spin_unlock_bh(&q->lock); - dev_kfree_skb(skb); return ret; diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h index c8fb85795864..dbcf42ce9173 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -211,7 +211,6 @@ struct mtk_wed_wo_queue { struct mtk_wed_wo_queue_regs regs; struct page_frag_cache cache; - spinlock_t lock; struct mtk_wed_wo_queue_desc *desc; dma_addr_t desc_dma; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index c837103a9ee3..382d02f6619c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -47,6 +47,25 @@ #define CREATE_TRACE_POINTS #include "diag/cmd_tracepoint.h" +struct mlx5_ifc_mbox_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_mbox_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + enum { CMD_IF_REV = 5, }; @@ -70,6 +89,26 @@ enum { MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10, }; +static u16 in_to_opcode(void *in) +{ + return MLX5_GET(mbox_in, in, opcode); +} + +/* Returns true for opcodes that might be triggered very frequently and throttle + * the command interface. Limit their command slots usage. + */ +static bool mlx5_cmd_is_throttle_opcode(u16 op) +{ + switch (op) { + case MLX5_CMD_OP_CREATE_GENERAL_OBJECT: + case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: + case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT: + case MLX5_CMD_OP_QUERY_GENERAL_OBJECT: + return true; + } + return false; +} + static struct mlx5_cmd_work_ent * cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, struct mlx5_cmd_msg *out, void *uout, int uout_size, @@ -91,6 +130,7 @@ cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, ent->context = context; ent->cmd = cmd; ent->page_queue = page_queue; + ent->op = in_to_opcode(in->first.data); refcount_set(&ent->refcnt, 1); return ent; @@ -752,25 +792,6 @@ static int cmd_status_to_err(u8 status) } } -struct mlx5_ifc_mbox_out_bits { - u8 status[0x8]; - u8 reserved_at_8[0x18]; - - u8 syndrome[0x20]; - - u8 reserved_at_40[0x40]; -}; - -struct mlx5_ifc_mbox_in_bits { - u8 opcode[0x10]; - u8 uid[0x10]; - - u8 reserved_at_20[0x10]; - u8 op_mod[0x10]; - - u8 reserved_at_40[0x40]; -}; - void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out) { u32 syndrome = MLX5_GET(mbox_out, out, syndrome); @@ -788,11 +809,12 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) u16 opcode, op_mod; u16 uid; - opcode = MLX5_GET(mbox_in, in, opcode); + opcode = in_to_opcode(in); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid); - if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY) + if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY && + opcode != MLX5_CMD_OP_CREATE_UCTX) mlx5_cmd_out_err(dev, opcode, op_mod, out); } @@ -800,7 +822,7 @@ int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out) { /* aborted due to PCI error or via reset flow mlx5_cmd_trigger_completions() */ if (err == -ENXIO) { - u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 opcode = in_to_opcode(in); u32 syndrome; u8 status; @@ -829,9 +851,9 @@ static void dump_command(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent, int input) { struct mlx5_cmd_msg *msg = input ? ent->in : ent->out; - u16 op = MLX5_GET(mbox_in, ent->lay->in, opcode); struct mlx5_cmd_mailbox *next = msg->next; int n = mlx5_calc_cmd_blocks(msg); + u16 op = ent->op; int data_only; u32 offset = 0; int dump_len; @@ -883,11 +905,6 @@ static void dump_command(struct mlx5_core_dev *dev, mlx5_core_dbg(dev, "cmd[%d]: end dump\n", ent->idx); } -static u16 msg_to_opcode(struct mlx5_cmd_msg *in) -{ - return MLX5_GET(mbox_in, in->first.data, opcode); -} - static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced); static void cb_timeout_handler(struct work_struct *work) @@ -905,13 +922,13 @@ static void cb_timeout_handler(struct work_struct *work) /* Maybe got handled by eq recover ? */ if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) { mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx, - mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); goto out; /* phew, already handled */ } ent->ret = -ETIMEDOUT; mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", - ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + ent->idx, mlx5_command_str(ent->op), ent->op); mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); out: @@ -985,7 +1002,6 @@ static void cmd_work_handler(struct work_struct *work) ent->lay = lay; memset(lay, 0, sizeof(*lay)); memcpy(lay->in, ent->in->first.data, sizeof(lay->in)); - ent->op = be32_to_cpu(lay->in[0]) >> 16; if (ent->in->next) lay->in_ptr = cpu_to_be64(ent->in->next->dma); lay->inlen = cpu_to_be32(ent->in->len); @@ -1098,12 +1114,12 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, */ if (wait_for_completion_timeout(&ent->done, timeout)) { mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx, - mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); return; } mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx, - mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); ent->ret = -ETIMEDOUT; mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); @@ -1130,12 +1146,10 @@ out_err: if (err == -ETIMEDOUT) { mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); } else if (err == -ECANCELED) { mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); } mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n", err, deliv_status_to_str(ent->status), ent->status); @@ -1169,7 +1183,6 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, u8 status = 0; int err = 0; s64 ds; - u16 op; if (callback && page_queue) return -EINVAL; @@ -1209,9 +1222,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, goto out_free; ds = ent->ts2 - ent->ts1; - op = MLX5_GET(mbox_in, in->first.data, opcode); - if (op < MLX5_CMD_OP_MAX) { - stats = &cmd->stats[op]; + if (ent->op < MLX5_CMD_OP_MAX) { + stats = &cmd->stats[ent->op]; spin_lock_irq(&stats->lock); stats->sum += ds; ++stats->n; @@ -1219,7 +1231,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, } mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME, "fw exec time for %s is %lld nsec\n", - mlx5_command_str(op), ds); + mlx5_command_str(ent->op), ds); out_free: status = ent->status; @@ -1816,7 +1828,7 @@ cache_miss: static int is_manage_pages(void *in) { - return MLX5_GET(mbox_in, in, opcode) == MLX5_CMD_OP_MANAGE_PAGES; + return in_to_opcode(in) == MLX5_CMD_OP_MANAGE_PAGES; } /* Notes: @@ -1827,8 +1839,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size, mlx5_cmd_cbk_t callback, void *context, bool force_polling) { - u16 opcode = MLX5_GET(mbox_in, in, opcode); struct mlx5_cmd_msg *inb, *outb; + u16 opcode = in_to_opcode(in); + bool throttle_op; int pages_queue; gfp_t gfp; u8 token; @@ -1837,13 +1850,21 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) return -ENXIO; + throttle_op = mlx5_cmd_is_throttle_opcode(opcode); + if (throttle_op) { + /* atomic context may not sleep */ + if (callback) + return -EINVAL; + down(&dev->cmd.throttle_sem); + } + pages_queue = is_manage_pages(in); gfp = callback ? GFP_ATOMIC : GFP_KERNEL; inb = alloc_msg(dev, in_size, gfp); if (IS_ERR(inb)) { err = PTR_ERR(inb); - return err; + goto out_up; } token = alloc_token(&dev->cmd); @@ -1877,6 +1898,9 @@ out_out: mlx5_free_cmd_msg(dev, outb); out_in: free_msg(dev, inb); +out_up: + if (throttle_op) + up(&dev->cmd.throttle_sem); return err; } @@ -1950,8 +1974,8 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size) { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); - u16 opcode = MLX5_GET(mbox_in, in, opcode); u16 op_mod = MLX5_GET(mbox_in, in, op_mod); + u16 opcode = in_to_opcode(in); return cmd_status_err(dev, err, opcode, op_mod, out); } @@ -1996,8 +2020,8 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size) { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); - u16 opcode = MLX5_GET(mbox_in, in, opcode); u16 op_mod = MLX5_GET(mbox_in, in, op_mod); + u16 opcode = in_to_opcode(in); err = cmd_status_err(dev, err, opcode, op_mod, out); return mlx5_cmd_check(dev, err, in, out); @@ -2049,7 +2073,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; - work->opcode = MLX5_GET(mbox_in, in, opcode); + work->opcode = in_to_opcode(in); work->op_mod = MLX5_GET(mbox_in, in, op_mod); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) @@ -2220,6 +2244,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) sema_init(&cmd->sem, cmd->max_reg_cmds); sema_init(&cmd->pages_sem, 1); + sema_init(&cmd->throttle_sem, DIV_ROUND_UP(cmd->max_reg_cmds, 2)); cmd_h = (u32)((u64)(cmd->dma) >> 32); cmd_l = (u32)(cmd->dma); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 0571e40c6ee5..2b444fb12388 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -59,6 +59,9 @@ bool mlx5_eth_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) return false; + if (mlx5_core_is_management_pf(dev)) + return false; + if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return false; @@ -198,6 +201,9 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return false; + if (mlx5_core_is_management_pf(dev)) + return false; + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) return false; @@ -343,7 +349,6 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) devl_assert_locked(priv_to_devlink(dev)); mutex_lock(&mlx5_intf_mutex); priv->flags &= ~MLX5_PRIV_FLAGS_DETACH; - priv->flags |= MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW; for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { if (!priv->adev[i]) { bool is_supported = false; @@ -391,7 +396,6 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) break; } } - priv->flags &= ~MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW; mutex_unlock(&mlx5_intf_mutex); return ret; } @@ -406,7 +410,6 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) devl_assert_locked(priv_to_devlink(dev)); mutex_lock(&mlx5_intf_mutex); - priv->flags |= MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW; for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) { if (!priv->adev[i]) continue; @@ -435,7 +438,6 @@ skip_suspend: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; } - priv->flags &= ~MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW; priv->flags |= MLX5_PRIV_FLAGS_DETACH; mutex_unlock(&mlx5_intf_mutex); } @@ -534,22 +536,16 @@ del_adev: int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - int err = 0; lockdep_assert_held(&mlx5_intf_mutex); if (priv->flags & MLX5_PRIV_FLAGS_DETACH) return 0; - priv->flags |= MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW; delete_drivers(dev); if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) - goto out; - - err = add_drivers(dev); + return 0; -out: - priv->flags &= ~MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW; - return err; + return add_drivers(dev); } bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 464eb3a18450..b70e36025d92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -75,6 +75,10 @@ int mlx5_ec_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return 0; + /* Management PF don't have a peer PF */ + if (mlx5_core_is_management_pf(dev)) + return 0; + return mlx5_host_pf_init(dev); } @@ -85,6 +89,10 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return; + /* Management PF don't have a peer PF */ + if (mlx5_core_is_management_pf(dev)) + return; + mlx5_host_pf_cleanup(dev); err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2d77fb8a8a01..da58322cbc3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -247,7 +247,7 @@ struct mlx5e_rx_wqe_ll { }; struct mlx5e_rx_wqe_cyc { - struct mlx5_wqe_data_seg data[0]; + DECLARE_FLEX_ARRAY(struct mlx5_wqe_data_seg, data); }; struct mlx5e_umr_wqe { @@ -968,6 +968,11 @@ struct mlx5e_priv { struct mlx5e_scratchpad scratchpad; struct mlx5e_htb *htb; struct mlx5e_mqprio_rl *mqprio_rl; + struct dentry *dfs_root; +}; + +struct mlx5e_dev { + struct mlx5e_priv *priv; }; struct mlx5e_rx_handlers { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 83adaabf59f5..03ad3b61dfc7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -4,6 +4,29 @@ #include "en/devlink.h" #include "eswitch.h" +static const struct devlink_ops mlx5e_devlink_ops = { +}; + +struct mlx5e_dev *mlx5e_create_devlink(struct device *dev) +{ + struct mlx5e_dev *mlx5e_dev; + struct devlink *devlink; + + devlink = devlink_alloc(&mlx5e_devlink_ops, sizeof(*mlx5e_dev), dev); + if (!devlink) + return ERR_PTR(-ENOMEM); + devlink_register(devlink); + return devlink_priv(devlink); +} + +void mlx5e_destroy_devlink(struct mlx5e_dev *mlx5e_dev) +{ + struct devlink *devlink = priv_to_devlink(mlx5e_dev); + + devlink_unregister(devlink); + devlink_free(devlink); +} + static void mlx5e_devlink_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) { @@ -14,14 +37,14 @@ mlx5e_devlink_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_i memcpy(ppid->id, &parent_id, sizeof(parent_id)); } -int mlx5e_devlink_port_register(struct mlx5e_priv *priv) +int mlx5e_devlink_port_register(struct mlx5e_dev *mlx5e_dev, + struct mlx5e_priv *priv) { - struct devlink *devlink = priv_to_devlink(priv->mdev); + struct devlink *devlink = priv_to_devlink(mlx5e_dev); struct devlink_port_attrs attrs = {}; struct netdev_phys_item_id ppid = {}; struct devlink_port *dl_port; unsigned int dl_port_index; - int ret; if (mlx5_core_is_pf(priv->mdev)) { attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; @@ -42,23 +65,12 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) memset(dl_port, 0, sizeof(*dl_port)); devlink_port_attrs_set(dl_port, &attrs); - if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) - devl_lock(devlink); - ret = devl_port_register(devlink, dl_port, dl_port_index); - if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) - devl_unlock(devlink); - - return ret; + return devlink_port_register(devlink, dl_port, dl_port_index); } void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) { struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); - struct devlink *devlink = priv_to_devlink(priv->mdev); - if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) - devl_lock(devlink); - devl_port_unregister(dl_port); - if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) - devl_unlock(devlink); + devlink_port_unregister(dl_port); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h index 4f238d4fff55..19b1d8e9634e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h @@ -7,7 +7,10 @@ #include <net/devlink.h> #include "en.h" -int mlx5e_devlink_port_register(struct mlx5e_priv *priv); +struct mlx5e_dev *mlx5e_create_devlink(struct device *dev); +void mlx5e_destroy_devlink(struct mlx5e_dev *mlx5e_dev); +int mlx5e_devlink_port_register(struct mlx5e_dev *mlx5e_dev, + struct mlx5e_priv *priv); void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv); static inline struct devlink_port * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 379c6dc9a3be..5233d4daca41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -145,7 +145,8 @@ void mlx5e_destroy_flow_steering(struct mlx5e_flow_steering *fs, bool ntuple, struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile, struct mlx5_core_dev *mdev, - bool state_destroy); + bool state_destroy, + struct dentry *dfs_root); void mlx5e_fs_cleanup(struct mlx5e_flow_steering *fs); struct mlx5e_vlan_table *mlx5e_fs_get_vlan(struct mlx5e_flow_steering *fs); void mlx5e_fs_set_tc(struct mlx5e_flow_steering *fs, struct mlx5e_tc_table *tc); @@ -189,6 +190,8 @@ int mlx5e_fs_vlan_rx_kill_vid(struct mlx5e_flow_steering *fs, __be16 proto, u16 vid); void mlx5e_fs_init_l2_addr(struct mlx5e_flow_steering *fs, struct net_device *netdev); +struct dentry *mlx5e_fs_get_debugfs_root(struct mlx5e_flow_steering *fs); + #define fs_err(fs, fmt, ...) \ mlx5_core_err(mlx5e_fs_get_mdev(fs), fmt, ##__VA_ARGS__) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c index 17325c5d6516..cf60f0a3ff23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c @@ -47,6 +47,7 @@ void mlx5e_mod_hdr_tbl_init(struct mod_hdr_tbl *tbl) void mlx5e_mod_hdr_tbl_destroy(struct mod_hdr_tbl *tbl) { + WARN_ON(!hash_empty(tbl->hlist)); mutex_destroy(&tbl->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 4ad19c981294..a21bd1179477 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -411,9 +411,14 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, { enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk); u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk); + u8 log_wqe_size, log_stride_size; - return mlx5e_mpwrq_log_wqe_sz(mdev, page_shift, umr_mode) - - mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); + log_wqe_size = mlx5e_mpwrq_log_wqe_sz(mdev, page_shift, umr_mode); + log_stride_size = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); + WARN(log_wqe_size < log_stride_size, + "Log WQE size %u < log stride size %u (page shift %u, umr mode %d, xsk on? %d)\n", + log_wqe_size, log_stride_size, page_shift, umr_mode, !!xsk); + return log_wqe_size - log_stride_size; } u8 mlx5e_mpwqe_get_min_wqe_bulk(unsigned int wq_sz) @@ -580,11 +585,16 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk); u16 max_mtu_pkts; - if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode)) + if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode)) { + mlx5_core_err(mdev, "Striding RQ for XSK can't be activated with page_shift %u and umr_mode %d\n", + page_shift, umr_mode); return -EOPNOTSUPP; + } - if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk)) + if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk)) { + mlx5_core_err(mdev, "Striding RQ linear mode for XSK can't be activated with current params\n"); return -EINVAL; + } /* Current RQ length is too big for the given frame size, the * needed number of WQEs exceeds the maximum. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 89510cac46c2..505ba41195b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -287,6 +287,78 @@ int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in) return err; } +int mlx5e_port_query_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir, + u8 pool_idx, void *out, int size_out) +{ + u32 in[MLX5_ST_SZ_DW(sbpr_reg)] = {}; + + MLX5_SET(sbpr_reg, in, desc, desc); + MLX5_SET(sbpr_reg, in, dir, dir); + MLX5_SET(sbpr_reg, in, pool, pool_idx); + + return mlx5_core_access_reg(mdev, in, sizeof(in), out, size_out, MLX5_REG_SBPR, 0, 0); +} + +int mlx5e_port_set_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir, + u8 pool_idx, u32 infi_size, u32 size) +{ + u32 out[MLX5_ST_SZ_DW(sbpr_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(sbpr_reg)] = {}; + + MLX5_SET(sbpr_reg, in, desc, desc); + MLX5_SET(sbpr_reg, in, dir, dir); + MLX5_SET(sbpr_reg, in, pool, pool_idx); + MLX5_SET(sbpr_reg, in, infi_size, infi_size); + MLX5_SET(sbpr_reg, in, size, size); + MLX5_SET(sbpr_reg, in, mode, 1); + + return mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_SBPR, 0, 1); +} + +static int mlx5e_port_query_sbcm(struct mlx5_core_dev *mdev, u32 desc, + u8 pg_buff_idx, u8 dir, void *out, + int size_out) +{ + u32 in[MLX5_ST_SZ_DW(sbcm_reg)] = {}; + + MLX5_SET(sbcm_reg, in, desc, desc); + MLX5_SET(sbcm_reg, in, local_port, 1); + MLX5_SET(sbcm_reg, in, pg_buff, pg_buff_idx); + MLX5_SET(sbcm_reg, in, dir, dir); + + return mlx5_core_access_reg(mdev, in, sizeof(in), out, size_out, MLX5_REG_SBCM, 0, 0); +} + +int mlx5e_port_set_sbcm(struct mlx5_core_dev *mdev, u32 desc, u8 pg_buff_idx, + u8 dir, u8 infi_size, u32 max_buff, u8 pool_idx) +{ + u32 out[MLX5_ST_SZ_DW(sbcm_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(sbcm_reg)] = {}; + u32 min_buff; + int err; + u8 exc; + + err = mlx5e_port_query_sbcm(mdev, desc, pg_buff_idx, dir, out, + sizeof(out)); + if (err) + return err; + + exc = MLX5_GET(sbcm_reg, out, exc); + min_buff = MLX5_GET(sbcm_reg, out, min_buff); + + MLX5_SET(sbcm_reg, in, desc, desc); + MLX5_SET(sbcm_reg, in, local_port, 1); + MLX5_SET(sbcm_reg, in, pg_buff, pg_buff_idx); + MLX5_SET(sbcm_reg, in, dir, dir); + MLX5_SET(sbcm_reg, in, exc, exc); + MLX5_SET(sbcm_reg, in, min_buff, min_buff); + MLX5_SET(sbcm_reg, in, infi_max, infi_size); + MLX5_SET(sbcm_reg, in, max_buff, max_buff); + MLX5_SET(sbcm_reg, in, pool, pool_idx); + + return mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_SBCM, 0, 1); +} + /* buffer[i]: buffer that priority i mapped to */ int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index 7a7defe60792..3f474e370828 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -57,6 +57,12 @@ u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); +int mlx5e_port_query_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir, + u8 pool_idx, void *out, int size_out); +int mlx5e_port_set_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir, + u8 pool_idx, u32 infi_size, u32 size); +int mlx5e_port_set_sbcm(struct mlx5_core_dev *mdev, u32 desc, u8 pg_buff_idx, + u8 dir, u8 infi_size, u32 max_buff, u8 pool_idx); int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); int mlx5e_port_set_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index c9d5d8d93994..57f4b1b50421 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -73,6 +73,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, port_buffer->buffer[i].lossy); } + port_buffer->headroom_size = total_used; port_buffer->port_buffer_size = MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz; port_buffer->spare_buffer_size = @@ -86,16 +87,204 @@ out: return err; } +struct mlx5e_buffer_pool { + u32 infi_size; + u32 size; + u32 buff_occupancy; +}; + +static int mlx5e_port_query_pool(struct mlx5_core_dev *mdev, + struct mlx5e_buffer_pool *buffer_pool, + u32 desc, u8 dir, u8 pool_idx) +{ + u32 out[MLX5_ST_SZ_DW(sbpr_reg)] = {}; + int err; + + err = mlx5e_port_query_sbpr(mdev, desc, dir, pool_idx, out, + sizeof(out)); + if (err) + return err; + + buffer_pool->size = MLX5_GET(sbpr_reg, out, size); + buffer_pool->infi_size = MLX5_GET(sbpr_reg, out, infi_size); + buffer_pool->buff_occupancy = MLX5_GET(sbpr_reg, out, buff_occupancy); + + return err; +} + +enum { + MLX5_INGRESS_DIR = 0, + MLX5_EGRESS_DIR = 1, +}; + +enum { + MLX5_LOSSY_POOL = 0, + MLX5_LOSSLESS_POOL = 1, +}; + +/* No limit on usage of shared buffer pool (max_buff=0) */ +#define MLX5_SB_POOL_NO_THRESHOLD 0 +/* Shared buffer pool usage threshold when calculated + * dynamically in alpha units. alpha=13 is equivalent to + * HW_alpha of [(1/128) * 2 ^ (alpha-1)] = 32, where HW_alpha + * equates to the following portion of the shared buffer pool: + * [32 / (1 + n * 32)] While *n* is the number of buffers + * that are using the shared buffer pool. + */ +#define MLX5_SB_POOL_THRESHOLD 13 + +/* Shared buffer class management parameters */ +struct mlx5_sbcm_params { + u8 pool_idx; + u8 max_buff; + u8 infi_size; +}; + +static const struct mlx5_sbcm_params sbcm_default = { + .pool_idx = MLX5_LOSSY_POOL, + .max_buff = MLX5_SB_POOL_NO_THRESHOLD, + .infi_size = 0, +}; + +static const struct mlx5_sbcm_params sbcm_lossy = { + .pool_idx = MLX5_LOSSY_POOL, + .max_buff = MLX5_SB_POOL_NO_THRESHOLD, + .infi_size = 1, +}; + +static const struct mlx5_sbcm_params sbcm_lossless = { + .pool_idx = MLX5_LOSSLESS_POOL, + .max_buff = MLX5_SB_POOL_THRESHOLD, + .infi_size = 0, +}; + +static const struct mlx5_sbcm_params sbcm_lossless_no_threshold = { + .pool_idx = MLX5_LOSSLESS_POOL, + .max_buff = MLX5_SB_POOL_NO_THRESHOLD, + .infi_size = 1, +}; + +/** + * select_sbcm_params() - selects the shared buffer pool configuration + * + * @buffer: <input> port buffer to retrieve params of + * @lossless_buff_count: <input> number of lossless buffers in total + * + * The selection is based on the following rules: + * 1. If buffer size is 0, no shared buffer pool is used. + * 2. If buffer is lossy, use lossy shared buffer pool. + * 3. If there are more than 1 lossless buffers, use lossless shared buffer pool + * with threshold. + * 4. If there is only 1 lossless buffer, use lossless shared buffer pool + * without threshold. + * + * @return const struct mlx5_sbcm_params* selected values + */ +static const struct mlx5_sbcm_params * +select_sbcm_params(struct mlx5e_bufferx_reg *buffer, u8 lossless_buff_count) +{ + if (buffer->size == 0) + return &sbcm_default; + + if (buffer->lossy) + return &sbcm_lossy; + + if (lossless_buff_count > 1) + return &sbcm_lossless; + + return &sbcm_lossless_no_threshold; +} + +static int port_update_pool_cfg(struct mlx5_core_dev *mdev, + struct mlx5e_port_buffer *port_buffer) +{ + const struct mlx5_sbcm_params *p; + u8 lossless_buff_count = 0; + int err; + int i; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return 0; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) + lossless_buff_count += ((port_buffer->buffer[i].size) && + (!(port_buffer->buffer[i].lossy))); + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count); + err = mlx5e_port_set_sbcm(mdev, 0, i, + MLX5_INGRESS_DIR, + p->infi_size, + p->max_buff, + p->pool_idx); + if (err) + return err; + } + + return 0; +} + +static int port_update_shared_buffer(struct mlx5_core_dev *mdev, + u32 current_headroom_size, + u32 new_headroom_size) +{ + struct mlx5e_buffer_pool lossless_ipool; + struct mlx5e_buffer_pool lossy_epool; + u32 lossless_ipool_size; + u32 shared_buffer_size; + u32 total_buffer_size; + u32 lossy_epool_size; + int err; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return 0; + + err = mlx5e_port_query_pool(mdev, &lossy_epool, 0, MLX5_EGRESS_DIR, + MLX5_LOSSY_POOL); + if (err) + return err; + + err = mlx5e_port_query_pool(mdev, &lossless_ipool, 0, MLX5_INGRESS_DIR, + MLX5_LOSSLESS_POOL); + if (err) + return err; + + total_buffer_size = current_headroom_size + lossy_epool.size + + lossless_ipool.size; + shared_buffer_size = total_buffer_size - new_headroom_size; + + if (shared_buffer_size < 4) { + pr_err("Requested port buffer is too large, not enough space left for shared buffer\n"); + return -EINVAL; + } + + /* Total shared buffer size is split in a ratio of 3:1 between + * lossy and lossless pools respectively. + */ + lossy_epool_size = (shared_buffer_size / 4) * 3; + lossless_ipool_size = shared_buffer_size / 4; + + mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0, + lossy_epool_size); + mlx5e_port_set_sbpr(mdev, 0, MLX5_INGRESS_DIR, MLX5_LOSSLESS_POOL, 0, + lossless_ipool_size); + return 0; +} + static int port_set_buffer(struct mlx5e_priv *priv, struct mlx5e_port_buffer *port_buffer) { u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; struct mlx5_core_dev *mdev = priv->mdev; int sz = MLX5_ST_SZ_BYTES(pbmc_reg); + u32 new_headroom_size = 0; + u32 current_headroom_size; void *in; int err; int i; + current_headroom_size = port_buffer->headroom_size; + in = kzalloc(sz, GFP_KERNEL); if (!in) return -ENOMEM; @@ -110,6 +299,7 @@ static int port_set_buffer(struct mlx5e_priv *priv, u64 xoff = port_buffer->buffer[i].xoff; u64 xon = port_buffer->buffer[i].xon; + new_headroom_size += size; do_div(size, port_buff_cell_sz); do_div(xoff, port_buff_cell_sz); do_div(xon, port_buff_cell_sz); @@ -119,6 +309,17 @@ static int port_set_buffer(struct mlx5e_priv *priv, MLX5_SET(bufferx_reg, buffer, xon_threshold, xon); } + new_headroom_size /= port_buff_cell_sz; + current_headroom_size /= port_buff_cell_sz; + err = port_update_shared_buffer(priv->mdev, current_headroom_size, + new_headroom_size); + if (err) + return err; + + err = port_update_pool_cfg(priv->mdev, port_buffer); + if (err) + return err; + err = mlx5e_port_set_pbmc(mdev, in); out: kfree(in); @@ -174,6 +375,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, /** * update_buffer_lossy - Update buffer configuration based on pfc + * @mdev: port function core device * @max_mtu: netdev's max_mtu * @pfc_en: <input> current pfc configuration * @buffer: <input> current prio to buffer mapping @@ -192,7 +394,8 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * @return: 0 if no error, * sets change to true if buffer configuration was modified. */ -static int update_buffer_lossy(unsigned int max_mtu, +static int update_buffer_lossy(struct mlx5_core_dev *mdev, + unsigned int max_mtu, u8 pfc_en, u8 *buffer, u32 xoff, u16 port_buff_cell_sz, struct mlx5e_port_buffer *port_buffer, bool *change) @@ -229,6 +432,10 @@ static int update_buffer_lossy(unsigned int max_mtu, } if (changed) { + err = port_update_pool_cfg(mdev, port_buffer); + if (err) + return err; + err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; @@ -293,23 +500,30 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, } if (change & MLX5E_PORT_BUFFER_PFC) { + mlx5e_dbg(HW, priv, "%s: requested PFC per priority bitmask: 0x%x\n", + __func__, pfc->pfc_en); err = mlx5e_port_query_priority2buffer(priv->mdev, buffer); if (err) return err; - err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, port_buff_cell_sz, - &port_buffer, &update_buffer); + err = update_buffer_lossy(priv->mdev, max_mtu, pfc->pfc_en, buffer, xoff, + port_buff_cell_sz, &port_buffer, + &update_buffer); if (err) return err; } if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { update_prio2buffer = true; + for (i = 0; i < MLX5E_MAX_BUFFER; i++) + mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n", + __func__, i, prio2buffer[i]); + err = fill_pfc_en(priv->mdev, &curr_pfc_en); if (err) return err; - err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, xoff, + err = update_buffer_lossy(priv->mdev, max_mtu, curr_pfc_en, prio2buffer, xoff, port_buff_cell_sz, &port_buffer, &update_buffer); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h index 80af7a5ac604..a6ef118de758 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h @@ -60,6 +60,7 @@ struct mlx5e_bufferx_reg { struct mlx5e_port_buffer { u32 port_buffer_size; u32 spare_buffer_size; + u32 headroom_size; struct mlx5e_bufferx_reg buffer[MLX5E_MAX_BUFFER]; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 1ae15b8536a8..95edab4a1732 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -754,6 +754,6 @@ void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv) if (!priv->rx_reporter) return; - devlink_port_health_reporter_destroy(priv->rx_reporter); + devlink_health_reporter_destroy(priv->rx_reporter); priv->rx_reporter = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 60bc5b577ab9..b195dbbf6c90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -609,6 +609,6 @@ void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv) if (!priv->tx_reporter) return; - devlink_port_health_reporter_destroy(priv->tx_reporter); + devlink_health_reporter_destroy(priv->tx_reporter); priv->tx_reporter = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c index 78af8a3175bf..7758a425bfa8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c @@ -28,7 +28,7 @@ struct mlx5e_flow_meter_aso_obj { int base_id; int total_meters; - unsigned long meters_map[0]; /* must be at the end of this struct */ + unsigned long meters_map[]; /* must be at the end of this struct */ }; struct mlx5e_flow_meters { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 2b7fd1c0e643..f575646d2f50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -95,8 +95,6 @@ struct mlx5e_tc_flow { */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; - struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */ - struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */ struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ struct list_head peer; /* flows with peer flow */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index e6f64d890fb3..83bb0811e774 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -745,8 +745,6 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, if (err) goto out; - esw_attr->rx_tun_attr->vni = MLX5_GET(fte_match_param, spec->match_value, - misc_parameters.vxlan_vni); esw_attr->rx_tun_attr->decap_vport = vport_num; } else if (netif_is_ovs_master(attr.route_dev) && mlx5e_tc_int_port_supported(esw)) { int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 2aaf8ab857b8..780224fd67a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1349,7 +1349,8 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv, mlx5e_tc_unoffload_from_slow_path(esw, flow); else mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr); - mlx5_modify_header_dealloc(priv->mdev, attr->modify_hdr); + + mlx5e_tc_detach_mod_hdr(priv, flow, attr); attr->modify_hdr = NULL; esw_attr->dests[flow->tmp_entry_index].flags &= @@ -1405,7 +1406,7 @@ static void mlx5e_reoffload_encap(struct mlx5e_priv *priv, continue; } - err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr); + err = mlx5e_tc_attach_mod_hdr(priv, flow, attr); if (err) { mlx5_core_warn(priv->mdev, "Failed to update flow mod_hdr err=%d", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 853f312cd757..5578f92f7e0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -445,7 +445,7 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_size) { - WARN_ON_ONCE(PAGE_SIZE / MLX5_SEND_WQE_BB < mlx5e_get_max_sq_wqebbs(mdev)); + WARN_ON_ONCE(PAGE_SIZE / MLX5_SEND_WQE_BB < (u16)mlx5e_get_max_sq_wqebbs(mdev)); /* A WQE must not cross the page boundary, hence two conditions: * 1. Its size must not exceed the page size. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index ff03c43833bb..81a567e17264 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -7,6 +7,18 @@ #include "en/health.h" #include <net/xdp_sock_drv.h> +static int mlx5e_legacy_rq_validate_xsk(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) +{ + if (!mlx5e_rx_is_linear_skb(mdev, params, xsk)) { + mlx5_core_err(mdev, "Legacy RQ linear mode for XSK can't be activated with current params\n"); + return -EINVAL; + } + + return 0; +} + /* The limitation of 2048 can be altered, but shouldn't go beyond the minimal * stride size of striding RQ. */ @@ -17,8 +29,11 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5_core_dev *mdev) { /* AF_XDP doesn't support frames larger than PAGE_SIZE. */ - if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) + if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) { + mlx5_core_err(mdev, "XSK chunk size %u out of bounds [%u, %lu]\n", xsk->chunk_size, + MLX5E_MIN_XSK_CHUNK_SIZE, PAGE_SIZE); return false; + } /* frag_sz is different for regular and XSK RQs, so ensure that linear * SKB mode is possible. @@ -27,7 +42,7 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: return !mlx5e_mpwrq_validate_xsk(mdev, params, xsk); default: /* MLX5_WQ_TYPE_CYCLIC */ - return mlx5e_rx_is_linear_skb(mdev, params, xsk); + return !mlx5e_legacy_rq_validate_xsk(mdev, params, xsk); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index d7c020f72401..88a5aed9d678 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -365,7 +365,7 @@ void mlx5e_accel_fs_tcp_destroy(struct mlx5e_flow_steering *fs) for (i = 0; i < ACCEL_FS_TCP_NUM_TYPES; i++) accel_fs_tcp_destroy_table(fs, i); - kvfree(accel_tcp); + kfree(accel_tcp); mlx5e_fs_set_accel_tcp(fs, NULL); } @@ -377,7 +377,7 @@ int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs) if (!MLX5_CAP_FLOWTABLE_NIC_RX(mlx5e_fs_get_mdev(fs), ft_field_support.outer_ip_version)) return -EOPNOTSUPP; - accel_tcp = kvzalloc(sizeof(*accel_tcp), GFP_KERNEL); + accel_tcp = kzalloc(sizeof(*accel_tcp), GFP_KERNEL); if (!accel_tcp) return -ENOMEM; mlx5e_fs_set_accel_tcp(fs, accel_tcp); @@ -397,7 +397,7 @@ int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs) err_destroy_tables: while (--i >= 0) accel_fs_tcp_destroy_table(fs, i); - kvfree(accel_tcp); + kfree(accel_tcp); mlx5e_fs_set_accel_tcp(fs, NULL); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index da2184c94203..eb5b09f81dec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2019 Mellanox Technologies. +#include <linux/debugfs.h> #include "en.h" #include "lib/mlx5.h" #include "en_accel/ktls.h" @@ -177,6 +178,15 @@ void mlx5e_ktls_cleanup_rx(struct mlx5e_priv *priv) destroy_workqueue(priv->tls->rx_wq); } +static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls, + struct dentry *dfs_root) +{ + if (IS_ERR_OR_NULL(dfs_root)) + return; + + tls->debugfs.dfs = debugfs_create_dir("tls", dfs_root); +} + int mlx5e_ktls_init(struct mlx5e_priv *priv) { struct mlx5e_tls *tls; @@ -189,11 +199,23 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv) return -ENOMEM; priv->tls = tls; + priv->tls->mdev = priv->mdev; + + mlx5e_tls_debugfs_init(tls, priv->dfs_root); + return 0; } void mlx5e_ktls_cleanup(struct mlx5e_priv *priv) { + struct mlx5e_tls *tls = priv->tls; + + if (!mlx5e_is_ktls_device(priv->mdev)) + return; + + debugfs_remove_recursive(tls->debugfs.dfs); + tls->debugfs.dfs = NULL; + kfree(priv->tls); priv->tls = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index 1c35045e41fb..fccf995ee16d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -4,6 +4,7 @@ #ifndef __MLX5E_KTLS_H__ #define __MLX5E_KTLS_H__ +#include <linux/debugfs.h> #include <linux/tls.h> #include <net/tls.h> #include "en.h" @@ -72,10 +73,17 @@ struct mlx5e_tls_sw_stats { atomic64_t rx_tls_del; }; +struct mlx5e_tls_debugfs { + struct dentry *dfs; + struct dentry *dfs_tx; +}; + struct mlx5e_tls { + struct mlx5_core_dev *mdev; struct mlx5e_tls_sw_stats sw_stats; struct workqueue_struct *rx_wq; struct mlx5e_tls_tx_pool *tx_pool; + struct mlx5e_tls_debugfs debugfs; }; int mlx5e_ktls_init(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 78072bf93f3f..6db27062b765 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2019 Mellanox Technologies. +#include <linux/debugfs.h> #include "en_accel/ktls.h" #include "en_accel/ktls_txrx.h" #include "en_accel/ktls_utils.h" @@ -886,8 +887,24 @@ err_out: return false; } +static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls, + struct dentry *dfs_root) +{ + if (IS_ERR_OR_NULL(dfs_root)) + return; + + tls->debugfs.dfs_tx = debugfs_create_dir("tx", dfs_root); + if (!tls->debugfs.dfs_tx) + return; + + debugfs_create_size_t("pool_size", 0400, tls->debugfs.dfs_tx, + &tls->tx_pool->size); +} + int mlx5e_ktls_init_tx(struct mlx5e_priv *priv) { + struct mlx5e_tls *tls = priv->tls; + if (!mlx5e_is_ktls_tx(priv->mdev)) return 0; @@ -895,6 +912,8 @@ int mlx5e_ktls_init_tx(struct mlx5e_priv *priv) if (!priv->tls->tx_pool) return -ENOMEM; + mlx5e_tls_tx_debugfs_init(tls, tls->debugfs.dfs); + return 0; } @@ -903,6 +922,9 @@ void mlx5e_ktls_cleanup_tx(struct mlx5e_priv *priv) if (!mlx5e_is_ktls_tx(priv->mdev)) return; + debugfs_remove_recursive(priv->tls->debugfs.dfs_tx); + priv->tls->debugfs.dfs_tx = NULL; + mlx5e_tls_tx_pool_cleanup(priv->tls->tx_pool); priv->tls->tx_pool = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 1892ccb889b3..7298fe782e9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include <linux/debugfs.h> #include <linux/list.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -67,6 +68,7 @@ struct mlx5e_flow_steering { struct mlx5e_fs_udp *udp; struct mlx5e_fs_any *any; struct mlx5e_ptp_fs *ptp_fs; + struct dentry *dfs_root; }; static int mlx5e_add_l2_flow_rule(struct mlx5e_flow_steering *fs, @@ -104,6 +106,11 @@ static inline int mlx5e_hash_l2(const u8 *addr) return addr[5]; } +struct dentry *mlx5e_fs_get_debugfs_root(struct mlx5e_flow_steering *fs) +{ + return fs->dfs_root; +} + static void mlx5e_add_l2_to_hash(struct hlist_head *hash, const u8 *addr) { struct mlx5e_l2_hash_node *hn; @@ -1429,9 +1436,19 @@ static int mlx5e_fs_ethtool_alloc(struct mlx5e_flow_steering *fs) static void mlx5e_fs_ethtool_free(struct mlx5e_flow_steering *fs) { } #endif +static void mlx5e_fs_debugfs_init(struct mlx5e_flow_steering *fs, + struct dentry *dfs_root) +{ + if (IS_ERR_OR_NULL(dfs_root)) + return; + + fs->dfs_root = debugfs_create_dir("fs", dfs_root); +} + struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile, struct mlx5_core_dev *mdev, - bool state_destroy) + bool state_destroy, + struct dentry *dfs_root) { struct mlx5e_flow_steering *fs; int err; @@ -1458,6 +1475,8 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile, if (err) goto err_free_tc; + mlx5e_fs_debugfs_init(fs, dfs_root); + return fs; err_free_tc: mlx5e_fs_tc_free(fs); @@ -1471,6 +1490,7 @@ err: void mlx5e_fs_cleanup(struct mlx5e_flow_steering *fs) { + debugfs_remove_recursive(fs->dfs_root); mlx5e_fs_ethtool_free(fs); mlx5e_fs_tc_free(fs); mlx5e_fs_vlan_free(fs); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index abcc614b6191..1e0afaa31dd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -35,6 +35,7 @@ #include <net/vxlan.h> #include <net/geneve.h> #include <linux/bpf.h> +#include <linux/debugfs.h> #include <linux/if_bridge.h> #include <linux/filter.h> #include <net/page_pool.h> @@ -5233,7 +5234,8 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); fs = mlx5e_fs_init(priv->profile, mdev, - !test_bit(MLX5E_STATE_DESTROYING, &priv->state)); + !test_bit(MLX5E_STATE_DESTROYING, &priv->state), + priv->dfs_root); if (!fs) { err = -ENOMEM; mlx5_core_err(mdev, "FS initialization failed, %d\n", err); @@ -5874,7 +5876,8 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv) static int mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); - struct mlx5e_priv *priv = auxiliary_get_drvdata(adev); + struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); + struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = edev->mdev; int err; @@ -5897,7 +5900,8 @@ static int mlx5e_resume(struct auxiliary_device *adev) static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) { - struct mlx5e_priv *priv = auxiliary_get_drvdata(adev); + struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); + struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; @@ -5915,26 +5919,36 @@ static int mlx5e_probe(struct auxiliary_device *adev, struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); const struct mlx5e_profile *profile = &mlx5e_nic_profile; struct mlx5_core_dev *mdev = edev->mdev; + struct mlx5e_dev *mlx5e_dev; struct net_device *netdev; pm_message_t state = {}; struct mlx5e_priv *priv; int err; + mlx5e_dev = mlx5e_create_devlink(&adev->dev); + if (IS_ERR(mlx5e_dev)) + return PTR_ERR(mlx5e_dev); + auxiliary_set_drvdata(adev, mlx5e_dev); + netdev = mlx5e_create_netdev(mdev, profile); if (!netdev) { mlx5_core_err(mdev, "mlx5e_create_netdev failed\n"); - return -ENOMEM; + err = -ENOMEM; + goto err_devlink_unregister; } mlx5e_build_nic_netdev(netdev); priv = netdev_priv(netdev); - auxiliary_set_drvdata(adev, priv); + mlx5e_dev->priv = priv; priv->profile = profile; priv->ppriv = NULL; - err = mlx5e_devlink_port_register(priv); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(priv->mdev)); + + err = mlx5e_devlink_port_register(mlx5e_dev, priv); if (err) { mlx5_core_err(mdev, "mlx5e_devlink_port_register failed, %d\n", err); goto err_destroy_netdev; @@ -5971,13 +5985,17 @@ err_profile_cleanup: err_devlink_cleanup: mlx5e_devlink_port_unregister(priv); err_destroy_netdev: + debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); +err_devlink_unregister: + mlx5e_destroy_devlink(mlx5e_dev); return err; } static void mlx5e_remove(struct auxiliary_device *adev) { - struct mlx5e_priv *priv = auxiliary_get_drvdata(adev); + struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); + struct mlx5e_priv *priv = mlx5e_dev->priv; pm_message_t state = {}; mlx5e_dcbnl_delete_app(priv); @@ -5985,7 +6003,9 @@ static void mlx5e_remove(struct auxiliary_device *adev) mlx5e_suspend(adev, state); priv->profile->cleanup(priv); mlx5e_devlink_port_unregister(priv); + debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); + mlx5e_destroy_devlink(mlx5e_dev); } static const struct auxiliary_device_id mlx5e_id_table[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7d90e5b72854..8d29310c7e48 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -789,8 +789,10 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev, { struct mlx5e_priv *priv = netdev_priv(netdev); - priv->fs = mlx5e_fs_init(priv->profile, mdev, - !test_bit(MLX5E_STATE_DESTROYING, &priv->state)); + priv->fs = + mlx5e_fs_init(priv->profile, mdev, + !test_bit(MLX5E_STATE_DESTROYING, &priv->state), + priv->dfs_root); if (!priv->fs) { netdev_err(priv->netdev, "FS allocation failed\n"); return -ENOMEM; @@ -808,7 +810,8 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv = netdev_priv(netdev); priv->fs = mlx5e_fs_init(priv->profile, mdev, - !test_bit(MLX5E_STATE_DESTROYING, &priv->state)); + !test_bit(MLX5E_STATE_DESTROYING, &priv->state), + priv->dfs_root); if (!priv->fs) { netdev_err(priv->netdev, "FS allocation failed\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 243d5d7750be..4e6f5caf8ab6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -71,6 +71,12 @@ #define MLX5E_TC_TABLE_NUM_GROUPS 4 #define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(18) +struct mlx5e_hairpin_params { + struct mlx5_core_dev *mdev; + u32 num_queues; + u32 queue_size; +}; + struct mlx5e_tc_table { /* Protects the dynamic assignment of the t parameter * which is the nic tc root table. @@ -93,6 +99,8 @@ struct mlx5e_tc_table { struct mlx5_tc_ct_priv *ct; struct mapping_ctx *mapping; + struct mlx5e_hairpin_params hairpin_params; + struct dentry *dfs_root; }; struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { @@ -639,36 +647,36 @@ get_mod_hdr_table(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) &tc->mod_hdr; } -static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5e_tc_flow_parse_attr *parse_attr) +int mlx5e_tc_attach_mod_hdr(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) { - struct mlx5_modify_hdr *modify_hdr; struct mlx5e_mod_hdr_handle *mh; mh = mlx5e_mod_hdr_attach(priv->mdev, get_mod_hdr_table(priv, flow), mlx5e_get_flow_namespace(flow), - &parse_attr->mod_hdr_acts); + &attr->parse_attr->mod_hdr_acts); if (IS_ERR(mh)) return PTR_ERR(mh); - modify_hdr = mlx5e_mod_hdr_get(mh); - flow->attr->modify_hdr = modify_hdr; - flow->mh = mh; + WARN_ON(attr->modify_hdr); + attr->modify_hdr = mlx5e_mod_hdr_get(mh); + attr->mh = mh; return 0; } -static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow) +void mlx5e_tc_detach_mod_hdr(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) { /* flow wasn't fully initialized */ - if (!flow->mh) + if (!attr->mh) return; mlx5e_mod_hdr_detach(priv->mdev, get_mod_hdr_table(priv, flow), - flow->mh); - flow->mh = NULL; + attr->mh); + attr->mh = NULL; } static @@ -1017,6 +1025,138 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, return 0; } +static int debugfs_hairpin_queues_set(void *data, u64 val) +{ + struct mlx5e_hairpin_params *hp = data; + + if (!val) { + mlx5_core_err(hp->mdev, + "Number of hairpin queues must be > 0\n"); + return -EINVAL; + } + + hp->num_queues = val; + + return 0; +} + +static int debugfs_hairpin_queues_get(void *data, u64 *val) +{ + struct mlx5e_hairpin_params *hp = data; + + *val = hp->num_queues; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queues, debugfs_hairpin_queues_get, + debugfs_hairpin_queues_set, "%llu\n"); + +static int debugfs_hairpin_queue_size_set(void *data, u64 val) +{ + struct mlx5e_hairpin_params *hp = data; + + if (val > BIT(MLX5_CAP_GEN(hp->mdev, log_max_hairpin_num_packets))) { + mlx5_core_err(hp->mdev, + "Invalid hairpin queue size, must be <= %lu\n", + BIT(MLX5_CAP_GEN(hp->mdev, + log_max_hairpin_num_packets))); + return -EINVAL; + } + + hp->queue_size = roundup_pow_of_two(val); + + return 0; +} + +static int debugfs_hairpin_queue_size_get(void *data, u64 *val) +{ + struct mlx5e_hairpin_params *hp = data; + + *val = hp->queue_size; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queue_size, + debugfs_hairpin_queue_size_get, + debugfs_hairpin_queue_size_set, "%llu\n"); + +static int debugfs_hairpin_num_active_get(void *data, u64 *val) +{ + struct mlx5e_tc_table *tc = data; + struct mlx5e_hairpin_entry *hpe; + u32 cnt = 0; + u32 bkt; + + mutex_lock(&tc->hairpin_tbl_lock); + hash_for_each(tc->hairpin_tbl, bkt, hpe, hairpin_hlist) + cnt++; + mutex_unlock(&tc->hairpin_tbl_lock); + + *val = cnt; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_num_active, + debugfs_hairpin_num_active_get, NULL, "%llu\n"); + +static int debugfs_hairpin_table_dump_show(struct seq_file *file, void *priv) + +{ + struct mlx5e_tc_table *tc = file->private; + struct mlx5e_hairpin_entry *hpe; + u32 bkt; + + mutex_lock(&tc->hairpin_tbl_lock); + hash_for_each(tc->hairpin_tbl, bkt, hpe, hairpin_hlist) + seq_printf(file, "Hairpin peer_vhca_id %u prio %u refcnt %u\n", + hpe->peer_vhca_id, hpe->prio, + refcount_read(&hpe->refcnt)); + mutex_unlock(&tc->hairpin_tbl_lock); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(debugfs_hairpin_table_dump); + +static void mlx5e_tc_debugfs_init(struct mlx5e_tc_table *tc, + struct dentry *dfs_root) +{ + if (IS_ERR_OR_NULL(dfs_root)) + return; + + tc->dfs_root = debugfs_create_dir("tc", dfs_root); + if (!tc->dfs_root) + return; + + debugfs_create_file("hairpin_num_queues", 0644, tc->dfs_root, + &tc->hairpin_params, &fops_hairpin_queues); + debugfs_create_file("hairpin_queue_size", 0644, tc->dfs_root, + &tc->hairpin_params, &fops_hairpin_queue_size); + debugfs_create_file("hairpin_num_active", 0444, tc->dfs_root, tc, + &fops_hairpin_num_active); + debugfs_create_file("hairpin_table_dump", 0444, tc->dfs_root, tc, + &debugfs_hairpin_table_dump_fops); +} + +static void +mlx5e_hairpin_params_init(struct mlx5e_hairpin_params *hairpin_params, + struct mlx5_core_dev *mdev) +{ + u64 link_speed64; + u32 link_speed; + + hairpin_params->mdev = mdev; + /* set hairpin pair per each 50Gbs share of the link */ + mlx5e_port_max_linkspeed(mdev, &link_speed); + link_speed = max_t(u32, link_speed, 50000); + link_speed64 = link_speed; + do_div(link_speed64, 50000); + hairpin_params->num_queues = link_speed64; + + hairpin_params->queue_size = + BIT(min_t(u32, 16 - MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), + MLX5_CAP_GEN(mdev, log_max_hairpin_num_packets))); +} + static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr, @@ -1028,8 +1168,6 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, struct mlx5_core_dev *peer_mdev; struct mlx5e_hairpin_entry *hpe; struct mlx5e_hairpin *hp; - u64 link_speed64; - u32 link_speed; u8 match_prio; u16 peer_id; int err; @@ -1082,21 +1220,16 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, hash_hairpin_info(peer_id, match_prio)); mutex_unlock(&tc->hairpin_tbl_lock); - params.log_data_size = clamp_t(u8, 16, - MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz), - MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); - params.log_num_packets = params.log_data_size - - MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(priv->mdev); - params.log_num_packets = min_t(u8, params.log_num_packets, - MLX5_CAP_GEN(priv->mdev, log_max_hairpin_num_packets)); + params.log_num_packets = ilog2(tc->hairpin_params.queue_size); + params.log_data_size = + clamp_t(u32, + params.log_num_packets + + MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(priv->mdev), + MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz), + MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); params.q_counter = priv->q_counter; - /* set hairpin pair per each 50Gbs share of the link */ - mlx5e_port_max_linkspeed(priv->mdev, &link_speed); - link_speed = max_t(u32, link_speed, 50000); - link_speed64 = link_speed; - do_div(link_speed64, 50000); - params.num_channels = link_speed64; + params.num_channels = tc->hairpin_params.num_queues; hp = mlx5e_hairpin_create(priv, ¶ms, peer_ifindex); hpe->hp = hp; @@ -1301,7 +1434,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); + err = mlx5e_tc_attach_mod_hdr(priv, flow, attr); if (err) return err; } @@ -1361,7 +1494,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); - mlx5e_detach_mod_hdr(priv, flow); + mlx5e_tc_detach_mod_hdr(priv, flow, attr); } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) @@ -1472,7 +1605,7 @@ skip_restore: goto err_offload; } - flow->slow_mh = mh; + flow->attr->slow_mh = mh; flow->chain_mapping = chain_mapping; flow_flag_set(flow, SLOW); @@ -1497,6 +1630,7 @@ err_get_chain: void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow) { + struct mlx5e_mod_hdr_handle *slow_mh = flow->attr->slow_mh; struct mlx5_flow_attr *slow_attr; slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB); @@ -1509,16 +1643,16 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->esw_attr->split_count = 0; slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; - if (flow->slow_mh) { + if (slow_mh) { slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - slow_attr->modify_hdr = mlx5e_mod_hdr_get(flow->slow_mh); + slow_attr->modify_hdr = mlx5e_mod_hdr_get(slow_mh); } mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); - if (flow->slow_mh) { - mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), flow->slow_mh); + if (slow_mh) { + mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), slow_mh); mlx5_chains_put_chain_mapping(esw_chains(esw), flow->chain_mapping); flow->chain_mapping = 0; - flow->slow_mh = NULL; + flow->attr->slow_mh = NULL; } flow_flag_clear(flow, SLOW); kfree(slow_attr); @@ -1629,26 +1763,6 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro return err; } -int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr) -{ - struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &attr->parse_attr->mod_hdr_acts; - struct mlx5_modify_hdr *mod_hdr; - - mod_hdr = mlx5_modify_header_alloc(priv->mdev, - mlx5e_get_flow_namespace(flow), - mod_hdr_acts->num_actions, - mod_hdr_acts->actions); - if (IS_ERR(mod_hdr)) - return PTR_ERR(mod_hdr); - - WARN_ON(attr->modify_hdr); - attr->modify_hdr = mod_hdr; - - return 0; -} - static int set_encap_dests(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, @@ -1768,7 +1882,6 @@ verify_attr_actions(u32 actions, struct netlink_ext_ack *extack) static int post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, - bool is_post_act_attr, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; @@ -1790,27 +1903,21 @@ post_process_attr(struct mlx5e_tc_flow *flow, } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - if (vf_tun || is_post_act_attr) { - err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr); - if (err) - goto err_out; - } else { - err = mlx5e_attach_mod_hdr(flow->priv, flow, attr->parse_attr); - if (err) - goto err_out; - } + err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); + if (err) + goto err_out; } if (attr->branch_true && attr->branch_true->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr->branch_true); + err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr->branch_true); if (err) goto err_out; } if (attr->branch_false && attr->branch_false->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { - err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr->branch_false); + err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr->branch_false); if (err) goto err_out; } @@ -1924,7 +2031,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - err = post_process_attr(flow, attr, false, extack); + err = post_process_attr(flow, attr, extack); if (err) goto err_out; @@ -2009,10 +2116,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); - if (vf_tun && attr->modify_hdr) - mlx5_modify_header_dealloc(priv->mdev, attr->modify_hdr); - else - mlx5e_detach_mod_hdr(priv, flow); + mlx5e_tc_detach_mod_hdr(priv, flow, attr); } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) @@ -2492,13 +2596,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, err = mlx5e_tc_set_attr_rx_tun(flow, spec); if (err) return err; - } else if (tunnel && tunnel->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + } else if (tunnel) { struct mlx5_flow_spec *tmp_spec; tmp_spec = kvzalloc(sizeof(*tmp_spec), GFP_KERNEL); if (!tmp_spec) { - NL_SET_ERR_MSG_MOD(extack, "Failed to allocate memory for vxlan tmp spec"); - netdev_warn(priv->netdev, "Failed to allocate memory for vxlan tmp spec"); + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate memory for tunnel tmp spec"); + netdev_warn(priv->netdev, "Failed to allocate memory for tunnel tmp spec"); return -ENOMEM; } memcpy(tmp_spec, spec, sizeof(*tmp_spec)); @@ -3831,7 +3935,7 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (err) goto out_free; - err = post_process_attr(flow, attr, true, extack); + err = post_process_attr(flow, attr, extack); if (err) goto out_free; @@ -4398,8 +4502,7 @@ mlx5_free_flow_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); - if (attr->modify_hdr) - mlx5_modify_header_dealloc(flow->priv->mdev, attr->modify_hdr); + mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr); } } @@ -4521,9 +4624,6 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_free; - /* always set IP version for indirect table handling */ - flow->attr->ip_version = mlx5e_tc_get_ip_version(&parse_attr->spec, true); - err = parse_tc_fdb_actions(priv, &rule->action, flow, extack); if (err) goto err_free; @@ -5220,6 +5320,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) tc->ct = mlx5_tc_ct_init(priv, tc->chains, &tc->mod_hdr, MLX5_FLOW_NAMESPACE_KERNEL, tc->post_act); + mlx5e_hairpin_params_init(&tc->hairpin_params, dev); + tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; err = register_netdevice_notifier_dev_net(priv->netdev, &tc->netdevice_nb, @@ -5230,6 +5332,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) goto err_reg; } + mlx5e_tc_debugfs_init(tc, mlx5e_fs_get_debugfs_root(priv->fs)); + return 0; err_reg: @@ -5258,6 +5362,8 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = mlx5e_fs_get_tc(priv->fs); + debugfs_remove_recursive(tc->dfs_root); + if (tc->netdevice_nb.notifier_call) unregister_netdevice_notifier_dev_net(priv->netdev, &tc->netdevice_nb, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 50af70ef22f3..ce516dc7f3fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -71,6 +71,8 @@ struct mlx5_flow_attr { u32 action; struct mlx5_fc *counter; struct mlx5_modify_hdr *modify_hdr; + struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */ + struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */ struct mlx5_ct_attr ct_attr; struct mlx5e_sample_attr sample_attr; struct mlx5e_meter_attr meter_attr; @@ -82,7 +84,6 @@ struct mlx5_flow_attr { struct mlx5_flow_table *dest_ft; u8 inner_match_level; u8 outer_match_level; - u8 ip_version; u8 tun_ip_version; int tunnel_id; /* mapped tunnel id */ u32 flags; @@ -134,7 +135,6 @@ struct mlx5_rx_tun_attr { __be32 v4; struct in6_addr v6; } dst_ip; /* Valid if decap_vport is not zero */ - u32 vni; }; #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16 @@ -285,9 +285,13 @@ int mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev, enum mlx5e_tc_attr_to_reg type, u32 data); -int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr); +int mlx5e_tc_attach_mod_hdr(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); + +void mlx5e_tc_detach_mod_hdr(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev, struct flow_match_basic *match, bool outer, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c index c9a91158e99c..9959e9fd15a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c @@ -16,18 +16,12 @@ #include "lib/fs_chains.h" #include "en/mod_hdr.h" -#define MLX5_ESW_INDIR_TABLE_SIZE 128 -#define MLX5_ESW_INDIR_TABLE_RECIRC_IDX_MAX (MLX5_ESW_INDIR_TABLE_SIZE - 2) +#define MLX5_ESW_INDIR_TABLE_SIZE 2 +#define MLX5_ESW_INDIR_TABLE_RECIRC_IDX (MLX5_ESW_INDIR_TABLE_SIZE - 2) #define MLX5_ESW_INDIR_TABLE_FWD_IDX (MLX5_ESW_INDIR_TABLE_SIZE - 1) struct mlx5_esw_indir_table_rule { - struct list_head list; struct mlx5_flow_handle *handle; - union { - __be32 v4; - struct in6_addr v6; - } dst_ip; - u32 vni; struct mlx5_modify_hdr *mh; refcount_t refcnt; }; @@ -38,12 +32,10 @@ struct mlx5_esw_indir_table_entry { struct mlx5_flow_group *recirc_grp; struct mlx5_flow_group *fwd_grp; struct mlx5_flow_handle *fwd_rule; - struct list_head recirc_rules; - int recirc_cnt; + struct mlx5_esw_indir_table_rule *recirc_rule; int fwd_ref; u16 vport; - u8 ip_version; }; struct mlx5_esw_indir_table { @@ -89,7 +81,6 @@ mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw, return esw_attr->in_rep->vport == MLX5_VPORT_UPLINK && vf_sf_vport && esw->dev == dest_mdev && - attr->ip_version && attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE; } @@ -101,27 +92,8 @@ mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr) return esw_attr->rx_tun_attr ? esw_attr->rx_tun_attr->decap_vport : 0; } -static struct mlx5_esw_indir_table_rule * -mlx5_esw_indir_table_rule_lookup(struct mlx5_esw_indir_table_entry *e, - struct mlx5_esw_flow_attr *attr) -{ - struct mlx5_esw_indir_table_rule *rule; - - list_for_each_entry(rule, &e->recirc_rules, list) - if (rule->vni == attr->rx_tun_attr->vni && - !memcmp(&rule->dst_ip, &attr->rx_tun_attr->dst_ip, - sizeof(attr->rx_tun_attr->dst_ip))) - goto found; - return NULL; - -found: - refcount_inc(&rule->refcnt); - return rule; -} - static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, struct mlx5_esw_indir_table_entry *e) { struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; @@ -130,73 +102,18 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw, struct mlx5_flow_destination dest = {}; struct mlx5_esw_indir_table_rule *rule; struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_spec *rule_spec; struct mlx5_flow_handle *handle; int err = 0; u32 data; - rule = mlx5_esw_indir_table_rule_lookup(e, esw_attr); - if (rule) + if (e->recirc_rule) { + refcount_inc(&e->recirc_rule->refcnt); return 0; - - if (e->recirc_cnt == MLX5_ESW_INDIR_TABLE_RECIRC_IDX_MAX) - return -EINVAL; - - rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); - if (!rule_spec) - return -ENOMEM; - - rule = kzalloc(sizeof(*rule), GFP_KERNEL); - if (!rule) { - err = -ENOMEM; - goto out; - } - - rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS | - MLX5_MATCH_MISC_PARAMETERS_2; - if (MLX5_CAP_FLOWTABLE_NIC_RX(esw->dev, ft_field_support.outer_ip_version)) { - MLX5_SET(fte_match_param, rule_spec->match_criteria, - outer_headers.ip_version, 0xf); - MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.ip_version, - attr->ip_version); - } else if (attr->ip_version) { - MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, - outer_headers.ethertype); - MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.ethertype, - (attr->ip_version == 4 ? ETH_P_IP : ETH_P_IPV6)); - } else { - err = -EOPNOTSUPP; - goto err_ethertype; } - if (attr->ip_version == 4) { - MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, - outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); - MLX5_SET(fte_match_param, rule_spec->match_value, - outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(esw_attr->rx_tun_attr->dst_ip.v4)); - } else if (attr->ip_version == 6) { - int len = sizeof(struct in6_addr); - - memset(MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, - outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - 0xff, len); - memcpy(MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, - outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &esw_attr->rx_tun_attr->dst_ip.v6, len); - } - - MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, - misc_parameters.vxlan_vni); - MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters.vxlan_vni, - MLX5_GET(fte_match_param, spec->match_value, misc_parameters.vxlan_vni)); - - MLX5_SET(fte_match_param, rule_spec->match_criteria, - misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask()); - MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0, - mlx5_eswitch_get_vport_metadata_for_match(esw_attr->in_mdev->priv.eswitch, - MLX5_VPORT_UPLINK)); + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return -ENOMEM; /* Modify flow source to recirculate packet */ data = mlx5_eswitch_get_vport_metadata_for_set(esw, esw_attr->rx_tun_attr->decap_vport); @@ -219,13 +136,14 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw, flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL | FLOW_ACT_NO_APPEND; + flow_act.fg = e->recirc_grp; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest.ft = mlx5_chains_get_table(chains, 0, 1, 0); if (IS_ERR(dest.ft)) { err = PTR_ERR(dest.ft); goto err_table; } - handle = mlx5_add_flow_rules(e->ft, rule_spec, &flow_act, &dest, 1); + handle = mlx5_add_flow_rules(e->ft, NULL, &flow_act, &dest, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto err_handle; @@ -233,14 +151,10 @@ static int mlx5_esw_indir_table_rule_get(struct mlx5_eswitch *esw, mlx5e_mod_hdr_dealloc(&mod_acts); rule->handle = handle; - rule->vni = esw_attr->rx_tun_attr->vni; rule->mh = flow_act.modify_hdr; - memcpy(&rule->dst_ip, &esw_attr->rx_tun_attr->dst_ip, - sizeof(esw_attr->rx_tun_attr->dst_ip)); refcount_set(&rule->refcnt, 1); - list_add(&rule->list, &e->recirc_rules); - e->recirc_cnt++; - goto out; + e->recirc_rule = rule; + return 0; err_handle: mlx5_chains_put_table(chains, 0, 1, 0); @@ -250,89 +164,44 @@ err_mod_hdr_alloc: err_mod_hdr_regc1: mlx5e_mod_hdr_dealloc(&mod_acts); err_mod_hdr_regc0: -err_ethertype: kfree(rule); -out: - kvfree(rule_spec); return err; } static void mlx5_esw_indir_table_rule_put(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr, struct mlx5_esw_indir_table_entry *e) { - struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct mlx5_esw_indir_table_rule *rule = e->recirc_rule; struct mlx5_fs_chains *chains = esw_chains(esw); - struct mlx5_esw_indir_table_rule *rule; - list_for_each_entry(rule, &e->recirc_rules, list) - if (rule->vni == esw_attr->rx_tun_attr->vni && - !memcmp(&rule->dst_ip, &esw_attr->rx_tun_attr->dst_ip, - sizeof(esw_attr->rx_tun_attr->dst_ip))) - goto found; - - return; + if (!rule) + return; -found: if (!refcount_dec_and_test(&rule->refcnt)) return; mlx5_del_flow_rules(rule->handle); mlx5_chains_put_table(chains, 0, 1, 0); mlx5_modify_header_dealloc(esw->dev, rule->mh); - list_del(&rule->list); kfree(rule); - e->recirc_cnt--; + e->recirc_rule = NULL; } -static int mlx5_create_indir_recirc_group(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, - struct mlx5_esw_indir_table_entry *e) +static int mlx5_create_indir_recirc_group(struct mlx5_esw_indir_table_entry *e) { int err = 0, inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - u32 *in, *match; + u32 *in; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; - MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS | MLX5_MATCH_MISC_PARAMETERS_2); - match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - - if (MLX5_CAP_FLOWTABLE_NIC_RX(esw->dev, ft_field_support.outer_ip_version)) - MLX5_SET(fte_match_param, match, outer_headers.ip_version, 0xf); - else - MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.ethertype); - - if (attr->ip_version == 4) { - MLX5_SET_TO_ONES(fte_match_param, match, - outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); - } else if (attr->ip_version == 6) { - memset(MLX5_ADDR_OF(fte_match_param, match, - outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - 0xff, sizeof(struct in6_addr)); - } else { - err = -EOPNOTSUPP; - goto out; - } - - MLX5_SET_TO_ONES(fte_match_param, match, misc_parameters.vxlan_vni); - MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, - mlx5_eswitch_get_vport_metadata_mask()); MLX5_SET(create_flow_group_in, in, start_flow_index, 0); - MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_RECIRC_IDX_MAX); + MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_RECIRC_IDX); e->recirc_grp = mlx5_create_flow_group(e->ft, in); - if (IS_ERR(e->recirc_grp)) { + if (IS_ERR(e->recirc_grp)) err = PTR_ERR(e->recirc_grp); - goto out; - } - INIT_LIST_HEAD(&e->recirc_rules); - e->recirc_cnt = 0; - -out: kvfree(in); return err; } @@ -343,19 +212,12 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, int err = 0, inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_spec *spec; u32 *in; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) { - kvfree(in); - return -ENOMEM; - } - /* Hold one entry */ MLX5_SET(create_flow_group_in, in, start_flow_index, MLX5_ESW_INDIR_TABLE_FWD_IDX); MLX5_SET(create_flow_group_in, in, end_flow_index, MLX5_ESW_INDIR_TABLE_FWD_IDX); @@ -366,25 +228,25 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, } flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_act.fg = e->fwd_grp; dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport.num = e->vport; dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; - e->fwd_rule = mlx5_add_flow_rules(e->ft, spec, &flow_act, &dest, 1); + e->fwd_rule = mlx5_add_flow_rules(e->ft, NULL, &flow_act, &dest, 1); if (IS_ERR(e->fwd_rule)) { mlx5_destroy_flow_group(e->fwd_grp); err = PTR_ERR(e->fwd_rule); } err_out: - kvfree(spec); kvfree(in); return err; } static struct mlx5_esw_indir_table_entry * mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, u16 vport, bool decap) + u16 vport, bool decap) { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_namespace *root_ns; @@ -412,15 +274,14 @@ mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_att } e->ft = ft; e->vport = vport; - e->ip_version = attr->ip_version; e->fwd_ref = !decap; - err = mlx5_create_indir_recirc_group(esw, attr, spec, e); + err = mlx5_create_indir_recirc_group(e); if (err) goto recirc_grp_err; if (decap) { - err = mlx5_esw_indir_table_rule_get(esw, attr, spec, e); + err = mlx5_esw_indir_table_rule_get(esw, attr, e); if (err) goto recirc_rule_err; } @@ -430,13 +291,13 @@ mlx5_esw_indir_table_entry_create(struct mlx5_eswitch *esw, struct mlx5_flow_att goto fwd_grp_err; hash_add(esw->fdb_table.offloads.indir->table, &e->hlist, - vport << 16 | attr->ip_version); + vport << 16); return e; fwd_grp_err: if (decap) - mlx5_esw_indir_table_rule_put(esw, attr, e); + mlx5_esw_indir_table_rule_put(esw, e); recirc_rule_err: mlx5_destroy_flow_group(e->recirc_grp); recirc_grp_err: @@ -447,13 +308,13 @@ tbl_err: } static struct mlx5_esw_indir_table_entry * -mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport, u8 ip_version) +mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport) { struct mlx5_esw_indir_table_entry *e; - u32 key = vport << 16 | ip_version; + u32 key = vport << 16; hash_for_each_possible(esw->fdb_table.offloads.indir->table, e, hlist, key) - if (e->vport == vport && e->ip_version == ip_version) + if (e->vport == vport) return e; return NULL; @@ -461,24 +322,23 @@ mlx5_esw_indir_table_entry_lookup(struct mlx5_eswitch *esw, u16 vport, u8 ip_ver struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, u16 vport, bool decap) { struct mlx5_esw_indir_table_entry *e; int err; mutex_lock(&esw->fdb_table.offloads.indir->lock); - e = mlx5_esw_indir_table_entry_lookup(esw, vport, attr->ip_version); + e = mlx5_esw_indir_table_entry_lookup(esw, vport); if (e) { if (!decap) { e->fwd_ref++; } else { - err = mlx5_esw_indir_table_rule_get(esw, attr, spec, e); + err = mlx5_esw_indir_table_rule_get(esw, attr, e); if (err) goto out_err; } } else { - e = mlx5_esw_indir_table_entry_create(esw, attr, spec, vport, decap); + e = mlx5_esw_indir_table_entry_create(esw, attr, vport, decap); if (IS_ERR(e)) { err = PTR_ERR(e); esw_warn(esw->dev, "Failed to create indirection table, err %d.\n", err); @@ -494,22 +354,21 @@ out_err: } void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr, u16 vport, bool decap) { struct mlx5_esw_indir_table_entry *e; mutex_lock(&esw->fdb_table.offloads.indir->lock); - e = mlx5_esw_indir_table_entry_lookup(esw, vport, attr->ip_version); + e = mlx5_esw_indir_table_entry_lookup(esw, vport); if (!e) goto out; if (!decap) e->fwd_ref--; else - mlx5_esw_indir_table_rule_put(esw, attr, e); + mlx5_esw_indir_table_rule_put(esw, e); - if (e->fwd_ref || e->recirc_cnt) + if (e->fwd_ref || e->recirc_rule) goto out; hash_del(&e->hlist); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h index 21d56b49d14b..036f5b3a341b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h @@ -13,10 +13,8 @@ mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir); struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, u16 vport, bool decap); void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr, u16 vport, bool decap); bool @@ -44,7 +42,6 @@ mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir) static inline struct mlx5_flow_table * mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, u16 vport, bool decap) { return ERR_PTR(-EOPNOTSUPP); @@ -52,7 +49,6 @@ mlx5_esw_indir_table_get(struct mlx5_eswitch *esw, static inline void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr, u16 vport, bool decap) { } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 9daf55e90367..d809c9192496 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1250,7 +1250,7 @@ static int mlx5_esw_acls_ns_init(struct mlx5_eswitch *esw) if (err) return err; } else { - esw_warn(dev, "engress ACL is not supported by FW\n"); + esw_warn(dev, "egress ACL is not supported by FW\n"); } if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) { @@ -1406,9 +1406,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); if (clear_vf) mlx5_eswitch_clear_vf_vports_info(esw); - /* If disabling sriov in switchdev mode, free meta rules here - * because it depends on num_vfs. - */ + if (esw->mode == MLX5_ESWITCH_OFFLOADS) { struct devlink *devlink = priv_to_devlink(esw->dev); @@ -1489,7 +1487,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 * void *hca_caps; int err; - if (!mlx5_core_is_ecpf(dev)) { + if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_management_pf(dev)) { *max_sfs = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index c981fa77f439..5fb9d5e99734 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -179,15 +179,14 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, static int esw_setup_decap_indir(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec) + struct mlx5_flow_attr *attr) { struct mlx5_flow_table *ft; if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; - ft = mlx5_esw_indir_table_get(esw, attr, spec, + ft = mlx5_esw_indir_table_get(esw, attr, mlx5_esw_indir_table_decap_vport(attr), true); return PTR_ERR_OR_ZERO(ft); } @@ -197,7 +196,7 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) { if (mlx5_esw_indir_table_decap_vport(attr)) - mlx5_esw_indir_table_put(esw, attr, + mlx5_esw_indir_table_put(esw, mlx5_esw_indir_table_decap_vport(attr), true); } @@ -235,7 +234,6 @@ esw_setup_ft_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, int i) { flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; @@ -243,7 +241,7 @@ esw_setup_ft_dest(struct mlx5_flow_destination *dest, dest[i].ft = attr->dest_ft; if (mlx5_esw_indir_table_decap_vport(attr)) - return esw_setup_decap_indir(esw, attr, spec); + return esw_setup_decap_indir(esw, attr); return 0; } @@ -298,7 +296,7 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_ mlx5_chains_put_table(chains, 0, 1, 0); else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, esw_attr->dests[i].mdev)) - mlx5_esw_indir_table_put(esw, attr, esw_attr->dests[i].rep->vport, + mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport, false); } @@ -384,7 +382,6 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr, - struct mlx5_flow_spec *spec, bool ignore_flow_lvl, int *i) { @@ -399,7 +396,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; - dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, spec, + dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, esw_attr->dests[j].rep->vport, false); if (IS_ERR(dest[*i].ft)) { err = PTR_ERR(dest[*i].ft); @@ -408,7 +405,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, } if (mlx5_esw_indir_table_decap_vport(attr)) { - err = esw_setup_decap_indir(esw, attr, spec); + err = esw_setup_decap_indir(esw, attr); if (err) goto err_indir_tbl_get; } @@ -511,14 +508,14 @@ esw_setup_dests(struct mlx5_flow_destination *dest, err = esw_setup_mtu_dest(dest, &attr->meter_attr, *i); (*i)++; } else if (esw_is_indir_table(esw, attr)) { - err = esw_setup_indir_table(dest, flow_act, esw, attr, spec, true, i); + err = esw_setup_indir_table(dest, flow_act, esw, attr, true, i); } else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) { err = esw_setup_chain_src_port_rewrite(dest, flow_act, esw, chains, attr, i); } else { *i = esw_setup_vport_dests(dest, flow_act, esw, esw_attr, *i); if (attr->dest_ft) { - err = esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i); + err = esw_setup_ft_dest(dest, flow_act, esw, attr, *i); (*i)++; } else if (attr->dest_chain) { err = esw_setup_chain_dest(dest, flow_act, chains, attr->dest_chain, @@ -727,7 +724,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; for (i = 0; i < esw_attr->split_count; i++) { if (esw_is_indir_table(esw, attr)) - err = esw_setup_indir_table(dest, &flow_act, esw, attr, spec, false, &i); + err = esw_setup_indir_table(dest, &flow_act, esw, attr, false, &i); else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) err = esw_setup_chain_src_port_rewrite(dest, &flow_act, esw, chains, attr, &i); @@ -3575,9 +3572,9 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) if (IS_ERR(esw)) return PTR_ERR(esw); - down_write(&esw->mode_lock); + down_read(&esw->mode_lock); err = esw_mode_to_devlink(esw->mode, mode); - up_write(&esw->mode_lock); + up_read(&esw->mode_lock); return err; } @@ -3675,9 +3672,9 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) if (IS_ERR(esw)) return PTR_ERR(esw); - down_write(&esw->mode_lock); + down_read(&esw->mode_lock); err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); - up_write(&esw->mode_lock); + up_read(&esw->mode_lock); return err; } @@ -3749,9 +3746,9 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, if (IS_ERR(esw)) return PTR_ERR(esw); - down_write(&esw->mode_lock); + down_read(&esw->mode_lock); *encap = esw->offloads.encap; - up_write(&esw->mode_lock); + up_read(&esw->mode_lock); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 911cf4d23964..c2a4f86bc890 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -412,7 +412,8 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) int err; priv->fs = mlx5e_fs_init(priv->profile, mdev, - !test_bit(MLX5E_STATE_DESTROYING, &priv->state)); + !test_bit(MLX5E_STATE_DESTROYING, &priv->state), + priv->dfs_root); if (!priv->fs) { netdev_err(priv->netdev, "FS allocation failed\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 69318b143268..75510a12ab02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -69,6 +69,13 @@ enum { MLX5_MTPPS_FS_OUT_PULSE_DURATION_NS = BIT(0xa), }; +enum { + MLX5_MTUTC_OPERATION_ADJUST_TIME_MIN = S16_MIN, + MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX = S16_MAX, + MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MIN = -200000, + MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000, +}; + static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev) { return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev)); @@ -86,6 +93,22 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev) return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify); } +static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta) +{ + s64 min = MLX5_MTUTC_OPERATION_ADJUST_TIME_MIN; + s64 max = MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX; + + if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range)) { + min = MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MIN; + max = MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX; + } + + if (delta < min || delta > max) + return false; + + return true; +} + static int mlx5_set_mtutc(struct mlx5_core_dev *dev, u32 *mtutc, u32 size) { u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {}; @@ -288,8 +311,8 @@ static int mlx5_ptp_adjtime_real_time(struct mlx5_core_dev *mdev, s64 delta) if (!mlx5_modify_mtutc_allowed(mdev)) return 0; - /* HW time adjustment range is s16. If out of range, settime instead */ - if (delta < S16_MIN || delta > S16_MAX) { + /* HW time adjustment range is checked. If out of range, settime instead */ + if (!mlx5_is_mtutc_time_adj_cap(mdev, delta)) { struct timespec64 ts; s64 ns; @@ -326,6 +349,19 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } +static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + if (!mlx5_is_mtutc_time_adj_cap(mdev, delta)) + return -ERANGE; + + return mlx5_ptp_adjtime(ptp, delta); +} + static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq) { u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; @@ -688,6 +724,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .n_pins = 0, .pps = 0, .adjfine = mlx5_ptp_adjfine, + .adjphase = mlx5_ptp_adjphase, .adjtime = mlx5_ptp_adjtime, .gettimex64 = mlx5_ptp_gettimex, .settime64 = mlx5_ptp_settime, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index a4476cb4c3b3..fd2d31cdbcf9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -724,7 +724,6 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, struct mlx5dr_action *action) { struct postsend_info send_info = {}; - int ret; send_info.write.addr = (uintptr_t)action->rewrite->data; send_info.write.length = action->rewrite->num_of_actions * @@ -734,9 +733,7 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, mlx5dr_icm_pool_get_chunk_mr_addr(action->rewrite->chunk); send_info.rkey = mlx5dr_icm_pool_get_chunk_rkey(action->rewrite->chunk); - ret = dr_postsend_icm_data(dmn, &send_info); - - return ret; + return dr_postsend_icm_data(dmn, &send_info); } static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index 5a1027b07215..a453b9cd9033 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -14,6 +14,7 @@ #include <linux/irqreturn.h> #include <linux/netdevice.h> #include <linux/irq.h> +#include <linux/phy.h> /* The silicon design supports a maximum RX ring size of * 32K entries. Based on current testing this maximum size @@ -67,6 +68,29 @@ struct mlxbf_gige_stats { u64 rx_filter_discard_pkts; }; +struct mlxbf_gige_reg_param { + u32 mask; + u32 shift; +}; + +struct mlxbf_gige_mdio_gw { + u32 gw_address; + u32 read_data_address; + struct mlxbf_gige_reg_param busy; + struct mlxbf_gige_reg_param write_data; + struct mlxbf_gige_reg_param read_data; + struct mlxbf_gige_reg_param devad; + struct mlxbf_gige_reg_param partad; + struct mlxbf_gige_reg_param opcode; + struct mlxbf_gige_reg_param st1; +}; + +struct mlxbf_gige_link_cfg { + void (*set_phy_link_mode)(struct phy_device *phydev); + void (*adjust_link)(struct net_device *netdev); + phy_interface_t phy_mode; +}; + struct mlxbf_gige { void __iomem *base; void __iomem *llu_base; @@ -102,6 +126,9 @@ struct mlxbf_gige { u8 valid_polarity; struct napi_struct napi; struct mlxbf_gige_stats stats; + u8 hw_version; + struct mlxbf_gige_mdio_gw *mdio_gw; + int prev_speed; }; /* Rx Work Queue Element definitions */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c index 41ebef25a930..253d7ad9b809 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c @@ -135,4 +135,5 @@ const struct ethtool_ops mlxbf_gige_ethtool_ops = { .nway_reset = phy_ethtool_nway_reset, .get_pauseparam = mlxbf_gige_get_pauseparam, .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, }; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 2292d63a279c..694de9513b9f 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -205,7 +205,7 @@ static int mlxbf_gige_stop(struct net_device *netdev) } static int mlxbf_gige_eth_ioctl(struct net_device *netdev, - struct ifreq *ifr, int cmd) + struct ifreq *ifr, int cmd) { if (!(netif_running(netdev))) return -EINVAL; @@ -263,13 +263,99 @@ static const struct net_device_ops mlxbf_gige_netdev_ops = { .ndo_get_stats64 = mlxbf_gige_get_stats64, }; -static void mlxbf_gige_adjust_link(struct net_device *netdev) +static void mlxbf_gige_bf2_adjust_link(struct net_device *netdev) { struct phy_device *phydev = netdev->phydev; phy_print_status(phydev); } +static void mlxbf_gige_bf3_adjust_link(struct net_device *netdev) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + struct phy_device *phydev = netdev->phydev; + u8 sgmii_mode; + u16 ipg_size; + u32 val; + + if (phydev->link && phydev->speed != priv->prev_speed) { + switch (phydev->speed) { + case 1000: + ipg_size = MLXBF_GIGE_1G_IPG_SIZE; + sgmii_mode = MLXBF_GIGE_1G_SGMII_MODE; + break; + case 100: + ipg_size = MLXBF_GIGE_100M_IPG_SIZE; + sgmii_mode = MLXBF_GIGE_100M_SGMII_MODE; + break; + case 10: + ipg_size = MLXBF_GIGE_10M_IPG_SIZE; + sgmii_mode = MLXBF_GIGE_10M_SGMII_MODE; + break; + default: + return; + } + + val = readl(priv->plu_base + MLXBF_GIGE_PLU_TX_REG0); + val &= ~(MLXBF_GIGE_PLU_TX_IPG_SIZE_MASK | MLXBF_GIGE_PLU_TX_SGMII_MODE_MASK); + val |= FIELD_PREP(MLXBF_GIGE_PLU_TX_IPG_SIZE_MASK, ipg_size); + val |= FIELD_PREP(MLXBF_GIGE_PLU_TX_SGMII_MODE_MASK, sgmii_mode); + writel(val, priv->plu_base + MLXBF_GIGE_PLU_TX_REG0); + + val = readl(priv->plu_base + MLXBF_GIGE_PLU_RX_REG0); + val &= ~MLXBF_GIGE_PLU_RX_SGMII_MODE_MASK; + val |= FIELD_PREP(MLXBF_GIGE_PLU_RX_SGMII_MODE_MASK, sgmii_mode); + writel(val, priv->plu_base + MLXBF_GIGE_PLU_RX_REG0); + + priv->prev_speed = phydev->speed; + } + + phy_print_status(phydev); +} + +static void mlxbf_gige_bf2_set_phy_link_mode(struct phy_device *phydev) +{ + /* MAC only supports 1000T full duplex mode */ + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + + /* Only symmetric pause with flow control enabled is supported so no + * need to negotiate pause. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->advertising); + linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising); +} + +static void mlxbf_gige_bf3_set_phy_link_mode(struct phy_device *phydev) +{ + /* MAC only supports full duplex mode */ + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + + /* Only symmetric pause with flow control enabled is supported so no + * need to negotiate pause. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->advertising); + linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising); +} + +static struct mlxbf_gige_link_cfg mlxbf_gige_link_cfgs[] = { + [MLXBF_GIGE_VERSION_BF2] = { + .set_phy_link_mode = mlxbf_gige_bf2_set_phy_link_mode, + .adjust_link = mlxbf_gige_bf2_adjust_link, + .phy_mode = PHY_INTERFACE_MODE_GMII + }, + [MLXBF_GIGE_VERSION_BF3] = { + .set_phy_link_mode = mlxbf_gige_bf3_set_phy_link_mode, + .adjust_link = mlxbf_gige_bf3_adjust_link, + .phy_mode = PHY_INTERFACE_MODE_SGMII + } +}; + static int mlxbf_gige_probe(struct platform_device *pdev) { struct phy_device *phydev; @@ -315,6 +401,8 @@ static int mlxbf_gige_probe(struct platform_device *pdev) spin_lock_init(&priv->lock); + priv->hw_version = readq(base + MLXBF_GIGE_VERSION); + /* Attach MDIO device */ err = mlxbf_gige_mdio_probe(pdev, priv); if (err) @@ -357,25 +445,14 @@ static int mlxbf_gige_probe(struct platform_device *pdev) phydev->irq = phy_irq; err = phy_connect_direct(netdev, phydev, - mlxbf_gige_adjust_link, - PHY_INTERFACE_MODE_GMII); + mlxbf_gige_link_cfgs[priv->hw_version].adjust_link, + mlxbf_gige_link_cfgs[priv->hw_version].phy_mode); if (err) { dev_err(&pdev->dev, "Could not attach to PHY\n"); goto out; } - /* MAC only supports 1000T full duplex mode */ - phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); - phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT); - phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); - phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); - phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); - - /* Only symmetric pause with flow control enabled is supported so no - * need to negotiate pause. - */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising); + mlxbf_gige_link_cfgs[priv->hw_version].set_phy_link_mode(phydev); /* Display information about attached PHY device */ phy_attached_info(phydev); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c index aa780b1614a3..7ac06fd31011 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c @@ -23,9 +23,75 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h" +#include "mlxbf_gige_mdio_bf2.h" +#include "mlxbf_gige_mdio_bf3.h" -#define MLXBF_GIGE_MDIO_GW_OFFSET 0x0 -#define MLXBF_GIGE_MDIO_CFG_OFFSET 0x4 +static struct mlxbf_gige_mdio_gw mlxbf_gige_mdio_gw_t[] = { + [MLXBF_GIGE_VERSION_BF2] = { + .gw_address = MLXBF2_GIGE_MDIO_GW_OFFSET, + .read_data_address = MLXBF2_GIGE_MDIO_GW_OFFSET, + .busy = { + .mask = MLXBF2_GIGE_MDIO_GW_BUSY_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_BUSY_SHIFT, + }, + .read_data = { + .mask = MLXBF2_GIGE_MDIO_GW_AD_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_AD_SHIFT, + }, + .write_data = { + .mask = MLXBF2_GIGE_MDIO_GW_AD_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_AD_SHIFT, + }, + .devad = { + .mask = MLXBF2_GIGE_MDIO_GW_DEVAD_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_DEVAD_SHIFT, + }, + .partad = { + .mask = MLXBF2_GIGE_MDIO_GW_PARTAD_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_PARTAD_SHIFT, + }, + .opcode = { + .mask = MLXBF2_GIGE_MDIO_GW_OPCODE_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_OPCODE_SHIFT, + }, + .st1 = { + .mask = MLXBF2_GIGE_MDIO_GW_ST1_MASK, + .shift = MLXBF2_GIGE_MDIO_GW_ST1_SHIFT, + }, + }, + [MLXBF_GIGE_VERSION_BF3] = { + .gw_address = MLXBF3_GIGE_MDIO_GW_OFFSET, + .read_data_address = MLXBF3_GIGE_MDIO_DATA_READ, + .busy = { + .mask = MLXBF3_GIGE_MDIO_GW_BUSY_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_BUSY_SHIFT, + }, + .read_data = { + .mask = MLXBF3_GIGE_MDIO_GW_DATA_READ_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_DATA_READ_SHIFT, + }, + .write_data = { + .mask = MLXBF3_GIGE_MDIO_GW_DATA_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_DATA_SHIFT, + }, + .devad = { + .mask = MLXBF3_GIGE_MDIO_GW_DEVAD_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_DEVAD_SHIFT, + }, + .partad = { + .mask = MLXBF3_GIGE_MDIO_GW_PARTAD_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_PARTAD_SHIFT, + }, + .opcode = { + .mask = MLXBF3_GIGE_MDIO_GW_OPCODE_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_OPCODE_SHIFT, + }, + .st1 = { + .mask = MLXBF3_GIGE_MDIO_GW_ST1_MASK, + .shift = MLXBF3_GIGE_MDIO_GW_ST1_SHIFT, + }, + }, +}; #define MLXBF_GIGE_MDIO_FREQ_REFERENCE 156250000ULL #define MLXBF_GIGE_MDIO_COREPLL_CONST 16384ULL @@ -47,30 +113,10 @@ /* Busy bit is set by software and cleared by hardware */ #define MLXBF_GIGE_MDIO_SET_BUSY 0x1 -/* MDIO GW register bits */ -#define MLXBF_GIGE_MDIO_GW_AD_MASK GENMASK(15, 0) -#define MLXBF_GIGE_MDIO_GW_DEVAD_MASK GENMASK(20, 16) -#define MLXBF_GIGE_MDIO_GW_PARTAD_MASK GENMASK(25, 21) -#define MLXBF_GIGE_MDIO_GW_OPCODE_MASK GENMASK(27, 26) -#define MLXBF_GIGE_MDIO_GW_ST1_MASK GENMASK(28, 28) -#define MLXBF_GIGE_MDIO_GW_BUSY_MASK GENMASK(30, 30) - -/* MDIO config register bits */ -#define MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK GENMASK(1, 0) -#define MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK GENMASK(2, 2) -#define MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK GENMASK(4, 4) -#define MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK GENMASK(15, 8) -#define MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK GENMASK(23, 16) -#define MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK GENMASK(31, 24) - -#define MLXBF_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \ - FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \ - FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \ - FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \ - FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13)) - #define MLXBF_GIGE_BF2_COREPLL_ADDR 0x02800c30 #define MLXBF_GIGE_BF2_COREPLL_SIZE 0x0000000c +#define MLXBF_GIGE_BF3_COREPLL_ADDR 0x13409824 +#define MLXBF_GIGE_BF3_COREPLL_SIZE 0x00000010 static struct resource corepll_params[] = { [MLXBF_GIGE_VERSION_BF2] = { @@ -78,6 +124,11 @@ static struct resource corepll_params[] = { .end = MLXBF_GIGE_BF2_COREPLL_ADDR + MLXBF_GIGE_BF2_COREPLL_SIZE - 1, .name = "COREPLL_RES" }, + [MLXBF_GIGE_VERSION_BF3] = { + .start = MLXBF_GIGE_BF3_COREPLL_ADDR, + .end = MLXBF_GIGE_BF3_COREPLL_ADDR + MLXBF_GIGE_BF3_COREPLL_SIZE - 1, + .name = "COREPLL_RES" + } }; /* Returns core clock i1clk in Hz */ @@ -134,19 +185,23 @@ static u8 mdio_period_map(struct mlxbf_gige *priv) return mdio_period; } -static u32 mlxbf_gige_mdio_create_cmd(u16 data, int phy_add, +static u32 mlxbf_gige_mdio_create_cmd(struct mlxbf_gige_mdio_gw *mdio_gw, u16 data, int phy_add, int phy_reg, u32 opcode) { u32 gw_reg = 0; - gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_AD_MASK, data); - gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_DEVAD_MASK, phy_reg); - gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_PARTAD_MASK, phy_add); - gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_OPCODE_MASK, opcode); - gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_ST1_MASK, - MLXBF_GIGE_MDIO_CL22_ST1); - gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_BUSY_MASK, - MLXBF_GIGE_MDIO_SET_BUSY); + gw_reg |= ((data << mdio_gw->write_data.shift) & + mdio_gw->write_data.mask); + gw_reg |= ((phy_reg << mdio_gw->devad.shift) & + mdio_gw->devad.mask); + gw_reg |= ((phy_add << mdio_gw->partad.shift) & + mdio_gw->partad.mask); + gw_reg |= ((opcode << mdio_gw->opcode.shift) & + mdio_gw->opcode.mask); + gw_reg |= ((MLXBF_GIGE_MDIO_CL22_ST1 << mdio_gw->st1.shift) & + mdio_gw->st1.mask); + gw_reg |= ((MLXBF_GIGE_MDIO_SET_BUSY << mdio_gw->busy.shift) & + mdio_gw->busy.mask); return gw_reg; } @@ -162,25 +217,26 @@ static int mlxbf_gige_mdio_read(struct mii_bus *bus, int phy_add, int phy_reg) return -EOPNOTSUPP; /* Send mdio read request */ - cmd = mlxbf_gige_mdio_create_cmd(0, phy_add, phy_reg, MLXBF_GIGE_MDIO_CL22_READ); + cmd = mlxbf_gige_mdio_create_cmd(priv->mdio_gw, 0, phy_add, phy_reg, + MLXBF_GIGE_MDIO_CL22_READ); - writel(cmd, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + writel(cmd, priv->mdio_io + priv->mdio_gw->gw_address); - ret = readl_poll_timeout_atomic(priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET, - val, !(val & MLXBF_GIGE_MDIO_GW_BUSY_MASK), + ret = readl_poll_timeout_atomic(priv->mdio_io + priv->mdio_gw->gw_address, + val, !(val & priv->mdio_gw->busy.mask), 5, 1000000); if (ret) { - writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + writel(0, priv->mdio_io + priv->mdio_gw->gw_address); return ret; } - ret = readl(priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + ret = readl(priv->mdio_io + priv->mdio_gw->read_data_address); /* Only return ad bits of the gw register */ - ret &= MLXBF_GIGE_MDIO_GW_AD_MASK; + ret &= priv->mdio_gw->read_data.mask; /* The MDIO lock is set on read. To release it, clear gw register */ - writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + writel(0, priv->mdio_io + priv->mdio_gw->gw_address); return ret; } @@ -197,17 +253,17 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add, return -EOPNOTSUPP; /* Send mdio write request */ - cmd = mlxbf_gige_mdio_create_cmd(val, phy_add, phy_reg, + cmd = mlxbf_gige_mdio_create_cmd(priv->mdio_gw, val, phy_add, phy_reg, MLXBF_GIGE_MDIO_CL22_WRITE); - writel(cmd, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + writel(cmd, priv->mdio_io + priv->mdio_gw->gw_address); /* If the poll timed out, drop the request */ - ret = readl_poll_timeout_atomic(priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET, - temp, !(temp & MLXBF_GIGE_MDIO_GW_BUSY_MASK), + ret = readl_poll_timeout_atomic(priv->mdio_io + priv->mdio_gw->gw_address, + temp, !(temp & priv->mdio_gw->busy.mask), 5, 1000000); /* The MDIO lock is set on read. To release it, clear gw register */ - writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + writel(0, priv->mdio_io + priv->mdio_gw->gw_address); return ret; } @@ -219,9 +275,20 @@ static void mlxbf_gige_mdio_cfg(struct mlxbf_gige *priv) mdio_period = mdio_period_map(priv); - val = MLXBF_GIGE_MDIO_CFG_VAL; - val |= FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK, mdio_period); - writel(val, priv->mdio_io + MLXBF_GIGE_MDIO_CFG_OFFSET); + if (priv->hw_version == MLXBF_GIGE_VERSION_BF2) { + val = MLXBF2_GIGE_MDIO_CFG_VAL; + val |= FIELD_PREP(MLXBF2_GIGE_MDIO_CFG_MDC_PERIOD_MASK, mdio_period); + writel(val, priv->mdio_io + MLXBF2_GIGE_MDIO_CFG_OFFSET); + } else { + val = FIELD_PREP(MLXBF3_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | + FIELD_PREP(MLXBF3_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1); + writel(val, priv->mdio_io + MLXBF3_GIGE_MDIO_CFG_REG0); + val = FIELD_PREP(MLXBF3_GIGE_MDIO_CFG_MDC_PERIOD_MASK, mdio_period); + writel(val, priv->mdio_io + MLXBF3_GIGE_MDIO_CFG_REG1); + val = FIELD_PREP(MLXBF3_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | + FIELD_PREP(MLXBF3_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13); + writel(val, priv->mdio_io + MLXBF3_GIGE_MDIO_CFG_REG2); + } } int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv) @@ -230,6 +297,9 @@ int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv) struct resource *res; int ret; + if (priv->hw_version > MLXBF_GIGE_VERSION_BF3) + return -ENODEV; + priv->mdio_io = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MDIO9); if (IS_ERR(priv->mdio_io)) return PTR_ERR(priv->mdio_io); @@ -242,13 +312,15 @@ int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv) /* For backward compatibility with older ACPI tables, also keep * CLK resource internal to the driver. */ - res = &corepll_params[MLXBF_GIGE_VERSION_BF2]; + res = &corepll_params[priv->hw_version]; } priv->clk_io = devm_ioremap(dev, res->start, resource_size(res)); if (!priv->clk_io) return -ENOMEM; + priv->mdio_gw = &mlxbf_gige_mdio_gw_t[priv->hw_version]; + mlxbf_gige_mdio_cfg(priv); priv->mdiobus = devm_mdiobus_alloc(dev); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio_bf2.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio_bf2.h new file mode 100644 index 000000000000..7f1ff0ac7699 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio_bf2.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */ + +/* MDIO support for Mellanox Gigabit Ethernet driver + * + * Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES, ALL RIGHTS RESERVED. + * + * This software product is a proprietary product of NVIDIA CORPORATION & + * AFFILIATES (the "Company") and all right, title, and interest in and to the + * software product, including all associated intellectual property rights, are + * and shall remain exclusively with the Company. + * + * This software product is governed by the End User License Agreement + * provided with the software product. + */ + +#ifndef __MLXBF_GIGE_MDIO_BF2_H__ +#define __MLXBF_GIGE_MDIO_BF2_H__ + +#include <linux/bitfield.h> + +#define MLXBF2_GIGE_MDIO_GW_OFFSET 0x0 +#define MLXBF2_GIGE_MDIO_CFG_OFFSET 0x4 + +/* MDIO GW register bits */ +#define MLXBF2_GIGE_MDIO_GW_AD_MASK GENMASK(15, 0) +#define MLXBF2_GIGE_MDIO_GW_DEVAD_MASK GENMASK(20, 16) +#define MLXBF2_GIGE_MDIO_GW_PARTAD_MASK GENMASK(25, 21) +#define MLXBF2_GIGE_MDIO_GW_OPCODE_MASK GENMASK(27, 26) +#define MLXBF2_GIGE_MDIO_GW_ST1_MASK GENMASK(28, 28) +#define MLXBF2_GIGE_MDIO_GW_BUSY_MASK GENMASK(30, 30) + +#define MLXBF2_GIGE_MDIO_GW_AD_SHIFT 0 +#define MLXBF2_GIGE_MDIO_GW_DEVAD_SHIFT 16 +#define MLXBF2_GIGE_MDIO_GW_PARTAD_SHIFT 21 +#define MLXBF2_GIGE_MDIO_GW_OPCODE_SHIFT 26 +#define MLXBF2_GIGE_MDIO_GW_ST1_SHIFT 28 +#define MLXBF2_GIGE_MDIO_GW_BUSY_SHIFT 30 + +/* MDIO config register bits */ +#define MLXBF2_GIGE_MDIO_CFG_MDIO_MODE_MASK GENMASK(1, 0) +#define MLXBF2_GIGE_MDIO_CFG_MDIO3_3_MASK GENMASK(2, 2) +#define MLXBF2_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK GENMASK(4, 4) +#define MLXBF2_GIGE_MDIO_CFG_MDC_PERIOD_MASK GENMASK(15, 8) +#define MLXBF2_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK GENMASK(23, 16) +#define MLXBF2_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK GENMASK(31, 24) + +#define MLXBF2_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF2_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \ + FIELD_PREP(MLXBF2_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \ + FIELD_PREP(MLXBF2_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \ + FIELD_PREP(MLXBF2_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \ + FIELD_PREP(MLXBF2_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13)) + +#endif /* __MLXBF_GIGE_MDIO_BF2_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio_bf3.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio_bf3.h new file mode 100644 index 000000000000..9dd9144b9173 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio_bf3.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */ + +/* MDIO support for Mellanox Gigabit Ethernet driver + * + * Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES, ALL RIGHTS RESERVED. + * + * This software product is a proprietary product of NVIDIA CORPORATION & + * AFFILIATES (the "Company") and all right, title, and interest in and to the + * software product, including all associated intellectual property rights, are + * and shall remain exclusively with the Company. + * + * This software product is governed by the End User License Agreement + * provided with the software product. + */ + +#ifndef __MLXBF_GIGE_MDIO_BF3_H__ +#define __MLXBF_GIGE_MDIO_BF3_H__ + +#include <linux/bitfield.h> + +#define MLXBF3_GIGE_MDIO_GW_OFFSET 0x80 +#define MLXBF3_GIGE_MDIO_DATA_READ 0x8c +#define MLXBF3_GIGE_MDIO_CFG_REG0 0x100 +#define MLXBF3_GIGE_MDIO_CFG_REG1 0x104 +#define MLXBF3_GIGE_MDIO_CFG_REG2 0x108 + +/* MDIO GW register bits */ +#define MLXBF3_GIGE_MDIO_GW_ST1_MASK GENMASK(1, 1) +#define MLXBF3_GIGE_MDIO_GW_OPCODE_MASK GENMASK(3, 2) +#define MLXBF3_GIGE_MDIO_GW_PARTAD_MASK GENMASK(8, 4) +#define MLXBF3_GIGE_MDIO_GW_DEVAD_MASK GENMASK(13, 9) +/* For BlueField-3, this field is only used for mdio write */ +#define MLXBF3_GIGE_MDIO_GW_DATA_MASK GENMASK(29, 14) +#define MLXBF3_GIGE_MDIO_GW_BUSY_MASK GENMASK(30, 30) + +#define MLXBF3_GIGE_MDIO_GW_DATA_READ_MASK GENMASK(15, 0) + +#define MLXBF3_GIGE_MDIO_GW_ST1_SHIFT 1 +#define MLXBF3_GIGE_MDIO_GW_OPCODE_SHIFT 2 +#define MLXBF3_GIGE_MDIO_GW_PARTAD_SHIFT 4 +#define MLXBF3_GIGE_MDIO_GW_DEVAD_SHIFT 9 +#define MLXBF3_GIGE_MDIO_GW_DATA_SHIFT 14 +#define MLXBF3_GIGE_MDIO_GW_BUSY_SHIFT 30 + +#define MLXBF3_GIGE_MDIO_GW_DATA_READ_SHIFT 0 + +/* MDIO config register bits */ +#define MLXBF3_GIGE_MDIO_CFG_MDIO_MODE_MASK GENMASK(1, 0) +#define MLXBF3_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK GENMASK(2, 2) +#define MLXBF3_GIGE_MDIO_CFG_MDC_PERIOD_MASK GENMASK(7, 0) +#define MLXBF3_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK GENMASK(7, 0) +#define MLXBF3_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK GENMASK(15, 8) + +#endif /* __MLXBF_GIGE_MDIO_BF3_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index 7be3a793984d..cd0973229c9b 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -8,8 +8,11 @@ #ifndef __MLXBF_GIGE_REGS_H__ #define __MLXBF_GIGE_REGS_H__ +#include <linux/bitfield.h> + #define MLXBF_GIGE_VERSION 0x0000 #define MLXBF_GIGE_VERSION_BF2 0x0 +#define MLXBF_GIGE_VERSION_BF3 0x1 #define MLXBF_GIGE_STATUS 0x0010 #define MLXBF_GIGE_STATUS_READY BIT(0) #define MLXBF_GIGE_INT_STATUS 0x0028 @@ -77,4 +80,23 @@ */ #define MLXBF_GIGE_MMIO_REG_SZ (MLXBF_GIGE_MAC_CFG + 8) +#define MLXBF_GIGE_PLU_TX_REG0 0x80 +#define MLXBF_GIGE_PLU_TX_IPG_SIZE_MASK GENMASK(11, 0) +#define MLXBF_GIGE_PLU_TX_SGMII_MODE_MASK GENMASK(15, 14) + +#define MLXBF_GIGE_PLU_RX_REG0 0x10 +#define MLXBF_GIGE_PLU_RX_SGMII_MODE_MASK GENMASK(25, 24) + +#define MLXBF_GIGE_1G_SGMII_MODE 0x0 +#define MLXBF_GIGE_10M_SGMII_MODE 0x1 +#define MLXBF_GIGE_100M_SGMII_MODE 0x2 + +/* ipg_size default value for 1G is fixed by HW to 11 + End = 12. + * So for 100M it is 12 * 10 - 1 = 119 + * For 10M, it is 12 * 100 - 1 = 1199 + */ +#define MLXBF_GIGE_1G_IPG_SIZE 11 +#define MLXBF_GIGE_100M_IPG_SIZE 119 +#define MLXBF_GIGE_10M_IPG_SIZE 1199 + #endif /* !defined(__MLXBF_GIGE_REGS_H__) */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index a0a06e2eff82..33ef726e4d54 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -2051,8 +2051,8 @@ static int mlxsw_core_health_init(struct mlxsw_core *mlxsw_core) if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX)) return 0; - fw_fatal = devlink_health_reporter_create(devlink, &mlxsw_core_health_fw_fatal_ops, - 0, mlxsw_core); + fw_fatal = devl_health_reporter_create(devlink, &mlxsw_core_health_fw_fatal_ops, + 0, mlxsw_core); if (IS_ERR(fw_fatal)) { dev_err(mlxsw_core->bus_info->dev, "Failed to create fw fatal reporter"); return PTR_ERR(fw_fatal); @@ -2072,7 +2072,7 @@ static int mlxsw_core_health_init(struct mlxsw_core *mlxsw_core) err_fw_fatal_config: mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_core_health_listener, mlxsw_core); err_trap_register: - devlink_health_reporter_destroy(mlxsw_core->health.fw_fatal); + devl_health_reporter_destroy(mlxsw_core->health.fw_fatal); return err; } @@ -2085,7 +2085,7 @@ static void mlxsw_core_health_fini(struct mlxsw_core *mlxsw_core) mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_core_health_listener, mlxsw_core); /* Make sure there is no more event work scheduled */ mlxsw_core_flush_owq(); - devlink_health_reporter_destroy(mlxsw_core->health.fw_fatal); + devl_health_reporter_destroy(mlxsw_core->health.fw_fatal); } static void mlxsw_core_irq_event_handler_init(struct mlxsw_core *mlxsw_core) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c index 83d2dc91ba2c..025e0db983fe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c @@ -1259,9 +1259,9 @@ static int mlxsw_linecard_init(struct mlxsw_core *mlxsw_core, linecard->linecards = linecards; mutex_init(&linecard->lock); - devlink_linecard = devlink_linecard_create(priv_to_devlink(mlxsw_core), - slot_index, &mlxsw_linecard_ops, - linecard); + devlink_linecard = devl_linecard_create(priv_to_devlink(mlxsw_core), + slot_index, &mlxsw_linecard_ops, + linecard); if (IS_ERR(devlink_linecard)) return PTR_ERR(devlink_linecard); @@ -1285,7 +1285,7 @@ static void mlxsw_linecard_fini(struct mlxsw_core *mlxsw_core, if (linecard->active) mlxsw_linecard_active_clear(linecard); mlxsw_linecard_bdev_del(linecard); - devlink_linecard_destroy(linecard->devlink_linecard); + devl_linecard_destroy(linecard->devlink_linecard); mutex_destroy(&linecard->lock); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 534840f9a7ca..7e0871b631e4 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -792,7 +792,7 @@ static int lan743x_mac_mii_wait_till_not_busy(struct lan743x_adapter *adapter) !(data & MAC_MII_ACC_MII_BUSY_), 0, 1000000); } -static int lan743x_mdiobus_read(struct mii_bus *bus, int phy_id, int index) +static int lan743x_mdiobus_read_c22(struct mii_bus *bus, int phy_id, int index) { struct lan743x_adapter *adapter = bus->priv; u32 val, mii_access; @@ -814,8 +814,8 @@ static int lan743x_mdiobus_read(struct mii_bus *bus, int phy_id, int index) return (int)(val & 0xFFFF); } -static int lan743x_mdiobus_write(struct mii_bus *bus, - int phy_id, int index, u16 regval) +static int lan743x_mdiobus_write_c22(struct mii_bus *bus, + int phy_id, int index, u16 regval) { struct lan743x_adapter *adapter = bus->priv; u32 val, mii_access; @@ -835,12 +835,10 @@ static int lan743x_mdiobus_write(struct mii_bus *bus, return ret; } -static u32 lan743x_mac_mmd_access(int id, int index, int op) +static u32 lan743x_mac_mmd_access(int id, int dev_addr, int op) { - u16 dev_addr; u32 ret; - dev_addr = (index >> 16) & 0x1f; ret = (id << MAC_MII_ACC_PHY_ADDR_SHIFT_) & MAC_MII_ACC_PHY_ADDR_MASK_; ret |= (dev_addr << MAC_MII_ACC_MIIMMD_SHIFT_) & @@ -858,7 +856,8 @@ static u32 lan743x_mac_mmd_access(int id, int index, int op) return ret; } -static int lan743x_mdiobus_c45_read(struct mii_bus *bus, int phy_id, int index) +static int lan743x_mdiobus_read_c45(struct mii_bus *bus, int phy_id, + int dev_addr, int index) { struct lan743x_adapter *adapter = bus->priv; u32 mmd_access; @@ -868,32 +867,30 @@ static int lan743x_mdiobus_c45_read(struct mii_bus *bus, int phy_id, int index) ret = lan743x_mac_mii_wait_till_not_busy(adapter); if (ret < 0) return ret; - if (index & MII_ADDR_C45) { - /* Load Register Address */ - lan743x_csr_write(adapter, MAC_MII_DATA, (u32)(index & 0xffff)); - mmd_access = lan743x_mac_mmd_access(phy_id, index, - MMD_ACCESS_ADDRESS); - lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); - ret = lan743x_mac_mii_wait_till_not_busy(adapter); - if (ret < 0) - return ret; - /* Read Data */ - mmd_access = lan743x_mac_mmd_access(phy_id, index, - MMD_ACCESS_READ); - lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); - ret = lan743x_mac_mii_wait_till_not_busy(adapter); - if (ret < 0) - return ret; - ret = lan743x_csr_read(adapter, MAC_MII_DATA); - return (int)(ret & 0xFFFF); - } - ret = lan743x_mdiobus_read(bus, phy_id, index); - return ret; + /* Load Register Address */ + lan743x_csr_write(adapter, MAC_MII_DATA, index); + mmd_access = lan743x_mac_mmd_access(phy_id, dev_addr, + MMD_ACCESS_ADDRESS); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + + /* Read Data */ + mmd_access = lan743x_mac_mmd_access(phy_id, dev_addr, + MMD_ACCESS_READ); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + + ret = lan743x_csr_read(adapter, MAC_MII_DATA); + return (int)(ret & 0xFFFF); } -static int lan743x_mdiobus_c45_write(struct mii_bus *bus, - int phy_id, int index, u16 regval) +static int lan743x_mdiobus_write_c45(struct mii_bus *bus, int phy_id, + int dev_addr, int index, u16 regval) { struct lan743x_adapter *adapter = bus->priv; u32 mmd_access; @@ -903,26 +900,23 @@ static int lan743x_mdiobus_c45_write(struct mii_bus *bus, ret = lan743x_mac_mii_wait_till_not_busy(adapter); if (ret < 0) return ret; - if (index & MII_ADDR_C45) { - /* Load Register Address */ - lan743x_csr_write(adapter, MAC_MII_DATA, (u32)(index & 0xffff)); - mmd_access = lan743x_mac_mmd_access(phy_id, index, - MMD_ACCESS_ADDRESS); - lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); - ret = lan743x_mac_mii_wait_till_not_busy(adapter); - if (ret < 0) - return ret; - /* Write Data */ - lan743x_csr_write(adapter, MAC_MII_DATA, (u32)regval); - mmd_access = lan743x_mac_mmd_access(phy_id, index, - MMD_ACCESS_WRITE); - lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); - ret = lan743x_mac_mii_wait_till_not_busy(adapter); - } else { - ret = lan743x_mdiobus_write(bus, phy_id, index, regval); - } - return ret; + /* Load Register Address */ + lan743x_csr_write(adapter, MAC_MII_DATA, (u32)index); + mmd_access = lan743x_mac_mmd_access(phy_id, dev_addr, + MMD_ACCESS_ADDRESS); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + + /* Write Data */ + lan743x_csr_write(adapter, MAC_MII_DATA, (u32)regval); + mmd_access = lan743x_mac_mmd_access(phy_id, dev_addr, + MMD_ACCESS_WRITE); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + + return lan743x_mac_mii_wait_till_not_busy(adapter); } static int lan743x_sgmii_wait_till_not_busy(struct lan743x_adapter *adapter) @@ -1424,14 +1418,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) data = lan743x_csr_read(adapter, MAC_CR); - /* set interface mode */ - if (phy_interface_is_rgmii(phydev)) - /* RGMII */ - data &= ~MAC_CR_MII_EN_; - else - /* GMII */ - data |= MAC_CR_MII_EN_; - /* set duplex mode */ if (phydev->duplex) data |= MAC_CR_DPX_; @@ -1483,10 +1469,33 @@ static void lan743x_phy_close(struct lan743x_adapter *adapter) netdev->phydev = NULL; } +static void lan743x_phy_interface_select(struct lan743x_adapter *adapter) +{ + u32 id_rev; + u32 data; + + data = lan743x_csr_read(adapter, MAC_CR); + id_rev = adapter->csr.id_rev & ID_REV_ID_MASK_; + + if (adapter->is_pci11x1x && adapter->is_sgmii_en) + adapter->phy_interface = PHY_INTERFACE_MODE_SGMII; + else if (id_rev == ID_REV_ID_LAN7430_) + adapter->phy_interface = PHY_INTERFACE_MODE_GMII; + else if ((id_rev == ID_REV_ID_LAN7431_) && (data & MAC_CR_MII_EN_)) + adapter->phy_interface = PHY_INTERFACE_MODE_MII; + else + adapter->phy_interface = PHY_INTERFACE_MODE_RGMII; +} + static int lan743x_phy_open(struct lan743x_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct lan743x_phy *phy = &adapter->phy; + struct fixed_phy_status fphy_status = { + .link = 1, + .speed = SPEED_1000, + .duplex = DUPLEX_FULL, + }; struct phy_device *phydev; int ret = -EIO; @@ -1497,17 +1506,25 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) if (!phydev) { /* try internal phy */ phydev = phy_find_first(adapter->mdiobus); - if (!phydev) - goto return_error; + if (!phydev) { + if ((adapter->csr.id_rev & ID_REV_ID_MASK_) == + ID_REV_ID_LAN7431_) { + phydev = fixed_phy_register(PHY_POLL, + &fphy_status, NULL); + if (IS_ERR(phydev)) { + netdev_err(netdev, "No PHY/fixed_PHY found\n"); + return -EIO; + } + } else { + goto return_error; + } + } - if (adapter->is_pci11x1x) - ret = phy_connect_direct(netdev, phydev, - lan743x_phy_link_status_change, - PHY_INTERFACE_MODE_RGMII); - else - ret = phy_connect_direct(netdev, phydev, - lan743x_phy_link_status_change, - PHY_INTERFACE_MODE_GMII); + lan743x_phy_interface_select(adapter); + + ret = phy_connect_direct(netdev, phydev, + lan743x_phy_link_status_change, + adapter->phy_interface); if (ret) goto return_error; } @@ -3285,9 +3302,10 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); netif_dbg(adapter, drv, adapter->netdev, "SGMII operation\n"); - adapter->mdiobus->probe_capabilities = MDIOBUS_C22_C45; - adapter->mdiobus->read = lan743x_mdiobus_c45_read; - adapter->mdiobus->write = lan743x_mdiobus_c45_write; + adapter->mdiobus->read = lan743x_mdiobus_read_c22; + adapter->mdiobus->write = lan743x_mdiobus_write_c22; + adapter->mdiobus->read_c45 = lan743x_mdiobus_read_c45; + adapter->mdiobus->write_c45 = lan743x_mdiobus_write_c45; adapter->mdiobus->name = "lan743x-mdiobus-c45"; netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus-c45\n"); @@ -3299,16 +3317,15 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) netif_dbg(adapter, drv, adapter->netdev, "RGMII operation\n"); // Only C22 support when RGMII I/F - adapter->mdiobus->probe_capabilities = MDIOBUS_C22; - adapter->mdiobus->read = lan743x_mdiobus_read; - adapter->mdiobus->write = lan743x_mdiobus_write; + adapter->mdiobus->read = lan743x_mdiobus_read_c22; + adapter->mdiobus->write = lan743x_mdiobus_write_c22; adapter->mdiobus->name = "lan743x-mdiobus"; netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus\n"); } } else { - adapter->mdiobus->read = lan743x_mdiobus_read; - adapter->mdiobus->write = lan743x_mdiobus_write; + adapter->mdiobus->read = lan743x_mdiobus_read_c22; + adapter->mdiobus->write = lan743x_mdiobus_write_c22; adapter->mdiobus->name = "lan743x-mdiobus"; netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus\n"); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 8438c3dbcf36..52609fc13ad9 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -1042,6 +1042,7 @@ struct lan743x_adapter { #define LAN743X_ADAPTER_FLAG_OTP BIT(0) u32 flags; u32 hw_cfg; + phy_interface_t phy_interface; }; #define LAN743X_COMPONENT_FLAG_RX(channel) BIT(20 + (channel)) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c b/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c index bf0cfe24a8fc..9b18156eea1a 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_goto.c @@ -4,7 +4,7 @@ #include "vcap_api_client.h" int lan966x_goto_port_add(struct lan966x_port *port, - struct flow_action_entry *act, + int from_cid, int to_cid, unsigned long goto_id, struct netlink_ext_ack *extack) { @@ -12,7 +12,7 @@ int lan966x_goto_port_add(struct lan966x_port *port, int err; err = vcap_enable_lookups(lan966x->vcap_ctrl, port->dev, - act->chain_index, goto_id, + from_cid, to_cid, goto_id, true); if (err == -EFAULT) { NL_SET_ERR_MSG_MOD(extack, "Unsupported goto chain"); @@ -29,8 +29,6 @@ int lan966x_goto_port_add(struct lan966x_port *port, return err; } - port->tc.goto_id = goto_id; - return 0; } @@ -41,14 +39,12 @@ int lan966x_goto_port_del(struct lan966x_port *port, struct lan966x *lan966x = port->lan966x; int err; - err = vcap_enable_lookups(lan966x->vcap_ctrl, port->dev, 0, + err = vcap_enable_lookups(lan966x->vcap_ctrl, port->dev, 0, 0, goto_id, false); if (err) { NL_SET_ERR_MSG_MOD(extack, "Could not disable VCAP lookups"); return err; } - port->tc.goto_id = 0; - return 0; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 3491f1961835..0106f9487cbe 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -332,7 +332,6 @@ struct lan966x_port_tc { unsigned long police_id; unsigned long ingress_mirror_id; unsigned long egress_mirror_id; - unsigned long goto_id; struct flow_stats police_stat; struct flow_stats mirror_stat; }; @@ -607,7 +606,7 @@ int lan966x_tc_flower(struct lan966x_port *port, struct flow_cls_offload *f); int lan966x_goto_port_add(struct lan966x_port *port, - struct flow_action_entry *act, + int from_cid, int to_cid, unsigned long goto_id, struct netlink_ext_ack *extack); int lan966x_goto_port_del(struct lan966x_port *port, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c index ba3fa917d6b7..b66a8725a071 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c @@ -82,8 +82,8 @@ static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, } static int lan966x_tc_flower_action_check(struct vcap_control *vctrl, - struct flow_cls_offload *fco, - struct vcap_admin *admin) + struct net_device *dev, + struct flow_cls_offload *fco) { struct flow_rule *rule = flow_cls_offload_flow_rule(fco); struct flow_action_entry *actent, *last_actent = NULL; @@ -109,21 +109,23 @@ static int lan966x_tc_flower_action_check(struct vcap_control *vctrl, last_actent = actent; /* Save last action for later check */ } - /* Check that last action is a goto */ - if (last_actent->id != FLOW_ACTION_GOTO) { + /* Check that last action is a goto + * The last chain/lookup does not need to have goto action + */ + if (last_actent->id == FLOW_ACTION_GOTO) { + /* Check if the destination chain is in one of the VCAPs */ + if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, + last_actent->chain_index)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Invalid goto chain"); + return -EINVAL; + } + } else if (!vcap_is_last_chain(vctrl, fco->common.chain_index)) { NL_SET_ERR_MSG_MOD(fco->common.extack, "Last action must be 'goto'"); return -EINVAL; } - /* Check if the goto chain is in the next lookup */ - if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, - last_actent->chain_index)) { - NL_SET_ERR_MSG_MOD(fco->common.extack, - "Invalid goto chain"); - return -EINVAL; - } - /* Catch unsupported combinations of actions */ if (action_mask & BIT(FLOW_ACTION_TRAP) && action_mask & BIT(FLOW_ACTION_ACCEPT)) { @@ -145,8 +147,8 @@ static int lan966x_tc_flower_add(struct lan966x_port *port, struct vcap_rule *vrule; int err, idx; - err = lan966x_tc_flower_action_check(port->lan966x->vcap_ctrl, f, - admin); + err = lan966x_tc_flower_action_check(port->lan966x->vcap_ctrl, + port->dev, f); if (err) return err; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c index a539abaad9b6..20627323d656 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_matchall.c @@ -24,7 +24,8 @@ static int lan966x_tc_matchall_add(struct lan966x_port *port, return lan966x_mirror_port_add(port, act, f->cookie, ingress, f->common.extack); case FLOW_ACTION_GOTO: - return lan966x_goto_port_add(port, act, f->cookie, + return lan966x_goto_port_add(port, f->common.chain_index, + act->chain_index, f->cookie, f->common.extack); default: NL_SET_ERR_MSG_MOD(f->common.extack, @@ -46,13 +47,8 @@ static int lan966x_tc_matchall_del(struct lan966x_port *port, f->cookie == port->tc.egress_mirror_id) { return lan966x_mirror_port_del(port, ingress, f->common.extack); - } else if (f->cookie == port->tc.goto_id) { - return lan966x_goto_port_del(port, f->cookie, - f->common.extack); } else { - NL_SET_ERR_MSG_MOD(f->common.extack, - "Unsupported action"); - return -EOPNOTSUPP; + return lan966x_goto_port_del(port, f->cookie, f->common.extack); } return 0; @@ -80,12 +76,6 @@ int lan966x_tc_matchall(struct lan966x_port *port, struct tc_cls_matchall_offload *f, bool ingress) { - if (!tc_cls_can_offload_and_chain0(port->dev, &f->common)) { - NL_SET_ERR_MSG_MOD(f->common.extack, - "Only chain zero is supported"); - return -EOPNOTSUPP; - } - switch (f->command) { case TC_CLSMATCHALL_REPLACE: return lan966x_tc_matchall_add(port, f, ingress); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index a54c0426a35f..76a9fb113f50 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -390,20 +390,6 @@ static int lan966x_vcap_port_info(struct net_device *dev, return 0; } -static int lan966x_vcap_enable(struct net_device *dev, - struct vcap_admin *admin, - bool enable) -{ - struct lan966x_port *port = netdev_priv(dev); - struct lan966x *lan966x = port->lan966x; - - lan_rmw(ANA_VCAP_S2_CFG_ENA_SET(enable), - ANA_VCAP_S2_CFG_ENA, - lan966x, ANA_VCAP_S2_CFG(port->chip_port)); - - return 0; -} - static struct vcap_operations lan966x_vcap_ops = { .validate_keyset = lan966x_vcap_validate_keyset, .add_default_fields = lan966x_vcap_add_default_fields, @@ -414,7 +400,6 @@ static struct vcap_operations lan966x_vcap_ops = { .update = lan966x_vcap_update, .move = lan966x_vcap_move, .port_info = lan966x_vcap_port_info, - .enable = lan966x_vcap_enable, }; static void lan966x_vcap_admin_free(struct vcap_admin *admin) @@ -521,6 +506,12 @@ int lan966x_vcap_init(struct lan966x *lan966x) list_add_tail(&admin->list, &ctrl->list); } + for (int p = 0; p < lan966x->num_phys_ports; ++p) + if (lan966x->ports[p]) + lan_rmw(ANA_VCAP_S2_CFG_ENA_SET(true), + ANA_VCAP_S2_CFG_ENA, lan966x, + ANA_VCAP_S2_CFG(lan966x->ports[p]->chip_port)); + lan966x->vcap_ctrl = ctrl; return 0; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c b/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c index 74abb946b2a3..871a3e62f852 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_dcb.c @@ -133,12 +133,17 @@ static bool sparx5_dcb_apptrust_contains(int portno, u8 selector) static int sparx5_dcb_app_update(struct net_device *dev) { + struct dcb_ieee_app_prio_map dscp_rewr_map = {0}; + struct dcb_rewr_prio_pcp_map pcp_rewr_map = {0}; struct sparx5_port *port = netdev_priv(dev); struct sparx5_port_qos_dscp_map *dscp_map; struct sparx5_port_qos_pcp_map *pcp_map; struct sparx5_port_qos qos = {0}; struct dcb_app app_itr = {0}; int portno = port->portno; + bool dscp_rewr = false; + bool pcp_rewr = false; + u16 dscp; int i; dscp_map = &qos.dscp.map; @@ -163,31 +168,72 @@ static int sparx5_dcb_app_update(struct net_device *dev) pcp_map->map[i] = dcb_getapp(dev, &app_itr); } + /* Get pcp rewrite mapping */ + dcb_getrewr_prio_pcp_mask_map(dev, &pcp_rewr_map); + for (i = 0; i < ARRAY_SIZE(pcp_rewr_map.map); i++) { + if (!pcp_rewr_map.map[i]) + continue; + pcp_rewr = true; + qos.pcp_rewr.map.map[i] = fls(pcp_rewr_map.map[i]) - 1; + } + + /* Get dscp rewrite mapping */ + dcb_getrewr_prio_dscp_mask_map(dev, &dscp_rewr_map); + for (i = 0; i < ARRAY_SIZE(dscp_rewr_map.map); i++) { + if (!dscp_rewr_map.map[i]) + continue; + + /* The rewrite table of the switch has 32 entries; one for each + * priority for each DP level. Currently, the rewrite map does + * not indicate DP level, so we map classified QoS class to + * classified DSCP, for each classified DP level. Rewrite of + * DSCP is only enabled, if we have active mappings. + */ + dscp_rewr = true; + dscp = fls64(dscp_rewr_map.map[i]) - 1; + qos.dscp_rewr.map.map[i] = dscp; /* DP 0 */ + qos.dscp_rewr.map.map[i + 8] = dscp; /* DP 1 */ + qos.dscp_rewr.map.map[i + 16] = dscp; /* DP 2 */ + qos.dscp_rewr.map.map[i + 24] = dscp; /* DP 3 */ + } + /* Enable use of pcp for queue classification ? */ if (sparx5_dcb_apptrust_contains(portno, DCB_APP_SEL_PCP)) { qos.pcp.qos_enable = true; qos.pcp.dp_enable = qos.pcp.qos_enable; + /* Enable rewrite of PCP and DEI if PCP is trusted *and* rewrite + * table is not empty. + */ + if (pcp_rewr) + qos.pcp_rewr.enable = true; } /* Enable use of dscp for queue classification ? */ if (sparx5_dcb_apptrust_contains(portno, IEEE_8021QAZ_APP_SEL_DSCP)) { qos.dscp.qos_enable = true; qos.dscp.dp_enable = qos.dscp.qos_enable; + if (dscp_rewr) + /* Do not enable rewrite if no mappings are active, as + * classified DSCP will then be zero for all classified + * QoS class and DP combinations. + */ + qos.dscp_rewr.enable = true; } return sparx5_port_qos_set(port, &qos); } -/* Set or delete dscp app entry. +/* Set or delete DSCP app entry. * - * Dscp mapping is global for all ports, so set and delete app entries are + * DSCP mapping is global for all ports, so set and delete app entries are * replicated for each port. */ -static int sparx5_dcb_ieee_dscp_setdel_app(struct net_device *dev, - struct dcb_app *app, bool del) +static int sparx5_dcb_ieee_dscp_setdel(struct net_device *dev, + struct dcb_app *app, + int (*setdel)(struct net_device *, + struct dcb_app *)) { struct sparx5_port *port = netdev_priv(dev); - struct dcb_app apps[SPX5_PORTS]; struct sparx5_port *port_itr; int err, i; @@ -195,11 +241,7 @@ static int sparx5_dcb_ieee_dscp_setdel_app(struct net_device *dev, port_itr = port->sparx5->ports[i]; if (!port_itr) continue; - memcpy(&apps[i], app, sizeof(struct dcb_app)); - if (del) - err = dcb_ieee_delapp(port_itr->ndev, &apps[i]); - else - err = dcb_ieee_setapp(port_itr->ndev, &apps[i]); + err = setdel(port_itr->ndev, app); if (err) return err; } @@ -226,7 +268,7 @@ static int sparx5_dcb_ieee_setapp(struct net_device *dev, struct dcb_app *app) } if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) - err = sparx5_dcb_ieee_dscp_setdel_app(dev, app, false); + err = sparx5_dcb_ieee_dscp_setdel(dev, app, dcb_ieee_setapp); else err = dcb_ieee_setapp(dev, app); @@ -244,7 +286,7 @@ static int sparx5_dcb_ieee_delapp(struct net_device *dev, struct dcb_app *app) int err; if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) - err = sparx5_dcb_ieee_dscp_setdel_app(dev, app, true); + err = sparx5_dcb_ieee_dscp_setdel(dev, app, dcb_ieee_delapp); else err = dcb_ieee_delapp(dev, app); @@ -283,11 +325,60 @@ static int sparx5_dcb_getapptrust(struct net_device *dev, u8 *selectors, return 0; } +static int sparx5_dcb_delrewr(struct net_device *dev, struct dcb_app *app) +{ + int err; + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = sparx5_dcb_ieee_dscp_setdel(dev, app, dcb_delrewr); + else + err = dcb_delrewr(dev, app); + + if (err < 0) + return err; + + return sparx5_dcb_app_update(dev); +} + +static int sparx5_dcb_setrewr(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app app_itr; + int err = 0; + u16 proto; + + err = sparx5_dcb_app_validate(dev, app); + if (err) + goto out; + + /* Delete current mapping, if it exists. */ + proto = dcb_getrewr(dev, app); + if (proto) { + app_itr = *app; + app_itr.protocol = proto; + sparx5_dcb_delrewr(dev, &app_itr); + } + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = sparx5_dcb_ieee_dscp_setdel(dev, app, dcb_setrewr); + else + err = dcb_setrewr(dev, app); + + if (err) + goto out; + + sparx5_dcb_app_update(dev); + +out: + return err; +} + const struct dcbnl_rtnl_ops sparx5_dcbnl_ops = { .ieee_setapp = sparx5_dcb_ieee_setapp, .ieee_delapp = sparx5_dcb_ieee_delapp, .dcbnl_setapptrust = sparx5_dcb_setapptrust, .dcbnl_getapptrust = sparx5_dcb_getapptrust, + .dcbnl_setrewr = sparx5_dcb_setrewr, + .dcbnl_delrewr = sparx5_dcb_delrewr, }; int sparx5_dcb_init(struct sparx5 *sparx5) @@ -304,6 +395,12 @@ int sparx5_dcb_init(struct sparx5 *sparx5) sparx5_port_apptrust[port->portno] = &sparx5_dcb_apptrust_policies [SPARX5_DCB_APPTRUST_DSCP_PCP]; + + /* Enable DSCP classification based on classified QoS class and + * DP, for all DSCP values, for all ports. + */ + sparx5_port_qos_dscp_rewr_mode_set(port, + SPARX5_PORT_REW_DSCP_ALL); } return 0; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h index 6c93dd6b01b0..a4a4d893dcb2 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -4,8 +4,8 @@ * Copyright (c) 2021 Microchip Technology Inc. */ -/* This file is autogenerated by cml-utils 2022-09-28 11:17:02 +0200. - * Commit ID: 385c8a11d71a9f6a60368d3a3cb648fa257b479a +/* This file is autogenerated by cml-utils 2022-11-04 11:22:22 +0100. + * Commit ID: 498242727be5db9b423cc0923bc966fc7b40607e */ #ifndef _SPARX5_MAIN_REGS_H_ @@ -885,6 +885,16 @@ enum sparx5_target { #define ANA_CL_DSCP_CFG_DSCP_TRUST_ENA_GET(x)\ FIELD_GET(ANA_CL_DSCP_CFG_DSCP_TRUST_ENA, x) +/* ANA_CL:COMMON:QOS_MAP_CFG */ +#define ANA_CL_QOS_MAP_CFG(r) \ + __REG(TARGET_ANA_CL, 0, 1, 166912, 0, 1, 756, 512, r, 32, 4) + +#define ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL GENMASK(9, 4) +#define ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL_SET(x)\ + FIELD_PREP(ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL, x) +#define ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL_GET(x)\ + FIELD_GET(ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL, x) + /* ANA_L2:COMMON:AUTO_LRN_CFG */ #define ANA_L2_AUTO_LRN_CFG __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 24, 0, 1, 4) @@ -5345,6 +5355,62 @@ enum sparx5_target { #define REW_PORT_VLAN_CFG_PORT_VID_GET(x)\ FIELD_GET(REW_PORT_VLAN_CFG_PORT_VID, x) +/* REW:PORT:PCP_MAP_DE0 */ +#define REW_PCP_MAP_DE0(g, r) \ + __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 4, r, 8, 4) + +#define REW_PCP_MAP_DE0_PCP_DE0 GENMASK(2, 0) +#define REW_PCP_MAP_DE0_PCP_DE0_SET(x)\ + FIELD_PREP(REW_PCP_MAP_DE0_PCP_DE0, x) +#define REW_PCP_MAP_DE0_PCP_DE0_GET(x)\ + FIELD_GET(REW_PCP_MAP_DE0_PCP_DE0, x) + +/* REW:PORT:PCP_MAP_DE1 */ +#define REW_PCP_MAP_DE1(g, r) \ + __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 36, r, 8, 4) + +#define REW_PCP_MAP_DE1_PCP_DE1 GENMASK(2, 0) +#define REW_PCP_MAP_DE1_PCP_DE1_SET(x)\ + FIELD_PREP(REW_PCP_MAP_DE1_PCP_DE1, x) +#define REW_PCP_MAP_DE1_PCP_DE1_GET(x)\ + FIELD_GET(REW_PCP_MAP_DE1_PCP_DE1, x) + +/* REW:PORT:DEI_MAP_DE0 */ +#define REW_DEI_MAP_DE0(g, r) \ + __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 68, r, 8, 4) + +#define REW_DEI_MAP_DE0_DEI_DE0 BIT(0) +#define REW_DEI_MAP_DE0_DEI_DE0_SET(x)\ + FIELD_PREP(REW_DEI_MAP_DE0_DEI_DE0, x) +#define REW_DEI_MAP_DE0_DEI_DE0_GET(x)\ + FIELD_GET(REW_DEI_MAP_DE0_DEI_DE0, x) + +/* REW:PORT:DEI_MAP_DE1 */ +#define REW_DEI_MAP_DE1(g, r) \ + __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 100, r, 8, 4) + +#define REW_DEI_MAP_DE1_DEI_DE1 BIT(0) +#define REW_DEI_MAP_DE1_DEI_DE1_SET(x)\ + FIELD_PREP(REW_DEI_MAP_DE1_DEI_DE1, x) +#define REW_DEI_MAP_DE1_DEI_DE1_GET(x)\ + FIELD_GET(REW_DEI_MAP_DE1_DEI_DE1, x) + +/* REW:PORT:DSCP_MAP */ +#define REW_DSCP_MAP(g) \ + __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 136, 0, 1, 4) + +#define REW_DSCP_MAP_DSCP_UPDATE_ENA BIT(1) +#define REW_DSCP_MAP_DSCP_UPDATE_ENA_SET(x)\ + FIELD_PREP(REW_DSCP_MAP_DSCP_UPDATE_ENA, x) +#define REW_DSCP_MAP_DSCP_UPDATE_ENA_GET(x)\ + FIELD_GET(REW_DSCP_MAP_DSCP_UPDATE_ENA, x) + +#define REW_DSCP_MAP_DSCP_REMAP_ENA BIT(0) +#define REW_DSCP_MAP_DSCP_REMAP_ENA_SET(x)\ + FIELD_PREP(REW_DSCP_MAP_DSCP_REMAP_ENA, x) +#define REW_DSCP_MAP_DSCP_REMAP_ENA_GET(x)\ + FIELD_GET(REW_DSCP_MAP_DSCP_REMAP_ENA, x) + /* REW:PORT:TAG_CTRL */ #define REW_TAG_CTRL(g) __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 132, 0, 1, 4) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 107b9cd931c0..246259b2ae94 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -1151,11 +1151,69 @@ int sparx5_port_qos_set(struct sparx5_port *port, { sparx5_port_qos_dscp_set(port, &qos->dscp); sparx5_port_qos_pcp_set(port, &qos->pcp); + sparx5_port_qos_pcp_rewr_set(port, &qos->pcp_rewr); + sparx5_port_qos_dscp_rewr_set(port, &qos->dscp_rewr); sparx5_port_qos_default_set(port, qos); return 0; } +int sparx5_port_qos_pcp_rewr_set(const struct sparx5_port *port, + struct sparx5_port_qos_pcp_rewr *qos) +{ + int i, mode = SPARX5_PORT_REW_TAG_CTRL_CLASSIFIED; + struct sparx5 *sparx5 = port->sparx5; + u8 pcp, dei; + + /* Use mapping table, with classified QoS as index, to map QoS and DP + * to tagged PCP and DEI, if PCP is trusted. Otherwise use classified + * PCP. Classified PCP equals frame PCP. + */ + if (qos->enable) + mode = SPARX5_PORT_REW_TAG_CTRL_MAPPED; + + spx5_rmw(REW_TAG_CTRL_TAG_PCP_CFG_SET(mode) | + REW_TAG_CTRL_TAG_DEI_CFG_SET(mode), + REW_TAG_CTRL_TAG_PCP_CFG | REW_TAG_CTRL_TAG_DEI_CFG, + port->sparx5, REW_TAG_CTRL(port->portno)); + + for (i = 0; i < ARRAY_SIZE(qos->map.map); i++) { + /* Extract PCP and DEI */ + pcp = qos->map.map[i]; + if (pcp > SPARX5_PORT_QOS_PCP_COUNT) + dei = 1; + else + dei = 0; + + /* Rewrite PCP and DEI, for each classified QoS class and DP + * level. This table is only used if tag ctrl mode is set to + * 'mapped'. + * + * 0:0nd - prio=0 and dp:0 => pcp=0 and dei=0 + * 0:0de - prio=0 and dp:1 => pcp=0 and dei=1 + */ + if (dei) { + spx5_rmw(REW_PCP_MAP_DE1_PCP_DE1_SET(pcp), + REW_PCP_MAP_DE1_PCP_DE1, sparx5, + REW_PCP_MAP_DE1(port->portno, i)); + + spx5_rmw(REW_DEI_MAP_DE1_DEI_DE1_SET(dei), + REW_DEI_MAP_DE1_DEI_DE1, port->sparx5, + REW_DEI_MAP_DE1(port->portno, i)); + } else { + spx5_rmw(REW_PCP_MAP_DE0_PCP_DE0_SET(pcp), + REW_PCP_MAP_DE0_PCP_DE0, sparx5, + REW_PCP_MAP_DE0(port->portno, i)); + + spx5_rmw(REW_DEI_MAP_DE0_DEI_DE0_SET(dei), + REW_DEI_MAP_DE0_DEI_DE0, port->sparx5, + REW_DEI_MAP_DE0(port->portno, i)); + } + } + + return 0; +} + int sparx5_port_qos_pcp_set(const struct sparx5_port *port, struct sparx5_port_qos_pcp *qos) { @@ -1184,6 +1242,45 @@ int sparx5_port_qos_pcp_set(const struct sparx5_port *port, return 0; } +void sparx5_port_qos_dscp_rewr_mode_set(const struct sparx5_port *port, + int mode) +{ + spx5_rmw(ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL_SET(mode), + ANA_CL_QOS_CFG_DSCP_REWR_MODE_SEL, port->sparx5, + ANA_CL_QOS_CFG(port->portno)); +} + +int sparx5_port_qos_dscp_rewr_set(const struct sparx5_port *port, + struct sparx5_port_qos_dscp_rewr *qos) +{ + struct sparx5 *sparx5 = port->sparx5; + bool rewr = false; + u16 dscp; + int i; + + /* On egress, rewrite DSCP value to either classified DSCP or frame + * DSCP. If enabled; classified DSCP, if disabled; frame DSCP. + */ + if (qos->enable) + rewr = true; + + spx5_rmw(REW_DSCP_MAP_DSCP_UPDATE_ENA_SET(rewr), + REW_DSCP_MAP_DSCP_UPDATE_ENA, sparx5, + REW_DSCP_MAP(port->portno)); + + /* On ingress, map each classified QoS class and DP to classified DSCP + * value. This mapping table is global for all ports. + */ + for (i = 0; i < ARRAY_SIZE(qos->map.map); i++) { + dscp = qos->map.map[i]; + spx5_rmw(ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL_SET(dscp), + ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL, sparx5, + ANA_CL_QOS_MAP_CFG(i)); + } + + return 0; +} + int sparx5_port_qos_dscp_set(const struct sparx5_port *port, struct sparx5_port_qos_dscp *qos) { diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h index fbafe22e25cc..607c4ff1df6b 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h @@ -9,6 +9,17 @@ #include "sparx5_main.h" +/* Port PCP rewrite mode */ +#define SPARX5_PORT_REW_TAG_CTRL_CLASSIFIED 0 +#define SPARX5_PORT_REW_TAG_CTRL_DEFAULT 1 +#define SPARX5_PORT_REW_TAG_CTRL_MAPPED 2 + +/* Port DSCP rewrite mode */ +#define SPARX5_PORT_REW_DSCP_NONE 0 +#define SPARX5_PORT_REW_DSCP_IF_ZERO 1 +#define SPARX5_PORT_REW_DSCP_SELECTED 2 +#define SPARX5_PORT_REW_DSCP_ALL 3 + static inline bool sparx5_port_is_2g5(int portno) { return portno >= 16 && portno <= 47; @@ -99,6 +110,15 @@ struct sparx5_port_qos_pcp_map { u8 map[SPARX5_PORT_QOS_PCP_DEI_COUNT]; }; +struct sparx5_port_qos_pcp_rewr_map { + u16 map[SPX5_PRIOS]; +}; + +#define SPARX5_PORT_QOS_DP_NUM 4 +struct sparx5_port_qos_dscp_rewr_map { + u16 map[SPX5_PRIOS * SPARX5_PORT_QOS_DP_NUM]; +}; + #define SPARX5_PORT_QOS_DSCP_COUNT 64 struct sparx5_port_qos_dscp_map { u8 map[SPARX5_PORT_QOS_DSCP_COUNT]; @@ -110,15 +130,27 @@ struct sparx5_port_qos_pcp { bool dp_enable; }; +struct sparx5_port_qos_pcp_rewr { + struct sparx5_port_qos_pcp_rewr_map map; + bool enable; +}; + struct sparx5_port_qos_dscp { struct sparx5_port_qos_dscp_map map; bool qos_enable; bool dp_enable; }; +struct sparx5_port_qos_dscp_rewr { + struct sparx5_port_qos_dscp_rewr_map map; + bool enable; +}; + struct sparx5_port_qos { struct sparx5_port_qos_pcp pcp; + struct sparx5_port_qos_pcp_rewr pcp_rewr; struct sparx5_port_qos_dscp dscp; + struct sparx5_port_qos_dscp_rewr dscp_rewr; u8 default_prio; }; @@ -127,9 +159,18 @@ int sparx5_port_qos_set(struct sparx5_port *port, struct sparx5_port_qos *qos); int sparx5_port_qos_pcp_set(const struct sparx5_port *port, struct sparx5_port_qos_pcp *qos); +int sparx5_port_qos_pcp_rewr_set(const struct sparx5_port *port, + struct sparx5_port_qos_pcp_rewr *qos); + int sparx5_port_qos_dscp_set(const struct sparx5_port *port, struct sparx5_port_qos_dscp *qos); +void sparx5_port_qos_dscp_rewr_mode_set(const struct sparx5_port *port, + int mode); + +int sparx5_port_qos_dscp_rewr_set(const struct sparx5_port *port, + struct sparx5_port_qos_dscp_rewr *qos); + int sparx5_port_qos_default_set(const struct sparx5_port *port, const struct sparx5_port_qos *qos); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 1ed304a816cc..affaa1656710 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -35,11 +35,6 @@ struct sparx5_tc_flower_parse_usage { unsigned int used_keys; }; -struct sparx5_tc_rule_pkt_cnt { - u64 cookie; - u32 pkts; -}; - /* These protocols have dedicated keysets in IS2 and a TC dissector * ETH_P_ARP does not have a TC dissector */ @@ -573,8 +568,8 @@ static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, } static int sparx5_tc_flower_action_check(struct vcap_control *vctrl, - struct flow_cls_offload *fco, - struct vcap_admin *admin) + struct net_device *ndev, + struct flow_cls_offload *fco) { struct flow_rule *rule = flow_cls_offload_flow_rule(fco); struct flow_action_entry *actent, *last_actent = NULL; @@ -600,21 +595,23 @@ static int sparx5_tc_flower_action_check(struct vcap_control *vctrl, last_actent = actent; /* Save last action for later check */ } - /* Check that last action is a goto */ - if (last_actent->id != FLOW_ACTION_GOTO) { + /* Check if last action is a goto + * The last chain/lookup does not need to have a goto action + */ + if (last_actent->id == FLOW_ACTION_GOTO) { + /* Check if the destination chain is in one of the VCAPs */ + if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, + last_actent->chain_index)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Invalid goto chain"); + return -EINVAL; + } + } else if (!vcap_is_last_chain(vctrl, fco->common.chain_index)) { NL_SET_ERR_MSG_MOD(fco->common.extack, "Last action must be 'goto'"); return -EINVAL; } - /* Check if the goto chain is in the next lookup */ - if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, - last_actent->chain_index)) { - NL_SET_ERR_MSG_MOD(fco->common.extack, - "Invalid goto chain"); - return -EINVAL; - } - /* Catch unsupported combinations of actions */ if (action_mask & BIT(FLOW_ACTION_TRAP) && action_mask & BIT(FLOW_ACTION_ACCEPT)) { @@ -833,7 +830,7 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, vctrl = port->sparx5->vcap_ctrl; - err = sparx5_tc_flower_action_check(vctrl, fco, admin); + err = sparx5_tc_flower_action_check(vctrl, ndev, fco); if (err) return err; @@ -945,44 +942,21 @@ static int sparx5_tc_flower_destroy(struct net_device *ndev, return err; } -/* Collect packet counts from all rules with the same cookie */ -static int sparx5_tc_rule_counter_cb(void *arg, struct vcap_rule *rule) -{ - struct sparx5_tc_rule_pkt_cnt *rinfo = arg; - struct vcap_counter counter; - int err = 0; - - if (rule->cookie == rinfo->cookie) { - err = vcap_rule_get_counter(rule, &counter); - if (err) - return err; - rinfo->pkts += counter.value; - /* Reset the rule counter */ - counter.value = 0; - vcap_rule_set_counter(rule, &counter); - } - return err; -} - static int sparx5_tc_flower_stats(struct net_device *ndev, struct flow_cls_offload *fco, struct vcap_admin *admin) { struct sparx5_port *port = netdev_priv(ndev); - struct sparx5_tc_rule_pkt_cnt rinfo = {}; + struct vcap_counter ctr = {}; struct vcap_control *vctrl; ulong lastused = 0; - u64 drops = 0; - u32 pkts = 0; int err; - rinfo.cookie = fco->cookie; vctrl = port->sparx5->vcap_ctrl; - err = vcap_rule_iter(vctrl, sparx5_tc_rule_counter_cb, &rinfo); + err = vcap_get_rule_count_by_cookie(vctrl, &ctr, fco->cookie); if (err) return err; - pkts = rinfo.pkts; - flow_stats_update(&fco->stats, 0x0, pkts, drops, lastused, + flow_stats_update(&fco->stats, 0x0, ctr.value, 0, lastused, FLOW_ACTION_HW_STATS_IMMEDIATE); return err; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c index 30dd61e5d150..d88a93f22606 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c @@ -31,6 +31,7 @@ static int sparx5_tc_matchall_replace(struct net_device *ndev, switch (action->id) { case FLOW_ACTION_GOTO: err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, + tmo->common.chain_index, action->chain_index, tmo->cookie, true); if (err == -EFAULT) { @@ -43,6 +44,11 @@ static int sparx5_tc_matchall_replace(struct net_device *ndev, "VCAP already enabled"); return -EOPNOTSUPP; } + if (err == -EADDRNOTAVAIL) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Already matching this chain"); + return -EOPNOTSUPP; + } if (err) { NL_SET_ERR_MSG_MOD(tmo->common.extack, "Could not enable VCAP lookups"); @@ -66,8 +72,8 @@ static int sparx5_tc_matchall_destroy(struct net_device *ndev, sparx5 = port->sparx5; if (!tmo->rule && tmo->cookie) { - err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, 0, - tmo->cookie, false); + err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, + 0, 0, tmo->cookie, false); if (err) return err; return 0; @@ -80,12 +86,6 @@ int sparx5_tc_matchall(struct net_device *ndev, struct tc_cls_matchall_offload *tmo, bool ingress) { - if (!tc_cls_can_offload_and_chain0(ndev, &tmo->common)) { - NL_SET_ERR_MSG_MOD(tmo->common.extack, - "Only chain zero is supported"); - return -EOPNOTSUPP; - } - switch (tmo->command) { case TC_CLSMATCHALL_REPLACE: return sparx5_tc_matchall_replace(ndev, tmo, ingress); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c index b91e05ffe2f4..c9423adc92ce 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_debugfs.c @@ -29,7 +29,7 @@ static void sparx5_vcap_port_keys(struct sparx5 *sparx5, /* Get lookup state */ value = spx5_rd(sparx5, ANA_ACL_VCAP_S2_CFG(port->portno)); out->prf(out->dst, "\n state: "); - if (ANA_ACL_VCAP_S2_CFG_SEC_ENA_GET(value)) + if (ANA_ACL_VCAP_S2_CFG_SEC_ENA_GET(value) & BIT(lookup)) out->prf(out->dst, "on"); else out->prf(out->dst, "off"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index a0c126ba9a87..0d4b40997bb4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -510,28 +510,6 @@ static void sparx5_vcap_move(struct net_device *ndev, struct vcap_admin *admin, sparx5_vcap_wait_super_update(sparx5); } -/* Enable all lookups in the VCAP instance */ -static int sparx5_vcap_enable(struct net_device *ndev, - struct vcap_admin *admin, - bool enable) -{ - struct sparx5_port *port = netdev_priv(ndev); - struct sparx5 *sparx5; - int portno; - - sparx5 = port->sparx5; - portno = port->portno; - - /* For now we only consider IS2 */ - if (enable) - spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0xf), sparx5, - ANA_ACL_VCAP_S2_CFG(portno)); - else - spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0), sparx5, - ANA_ACL_VCAP_S2_CFG(portno)); - return 0; -} - /* API callback operations: only IS2 is supported for now */ static struct vcap_operations sparx5_vcap_ops = { .validate_keyset = sparx5_vcap_validate_keyset, @@ -543,7 +521,6 @@ static struct vcap_operations sparx5_vcap_ops = { .update = sparx5_vcap_update, .move = sparx5_vcap_move, .port_info = sparx5_port_info, - .enable = sparx5_vcap_enable, }; /* Enable lookups per port and set the keyset generation: only IS2 for now */ @@ -568,6 +545,12 @@ static void sparx5_vcap_port_key_selection(struct sparx5 *sparx5, ANA_ACL_VCAP_S2_KEY_SEL(portno, lookup)); } } + /* IS2 lookups are in bit 0:3 */ + for (portno = 0; portno < SPX5_PORTS; ++portno) + spx5_rmw(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0xf), + ANA_ACL_VCAP_S2_CFG_SEC_ENA, + sparx5, + ANA_ACL_VCAP_S2_CFG(portno)); } /* Disable lookups per port and set the keyset generation: only IS2 for now */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index 664aae3e2acd..71f787a78295 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -37,11 +37,13 @@ struct vcap_rule_move { int count; /* blocksize of addresses to move */ }; -/* Stores the filter cookie that enabled the port */ +/* Stores the filter cookie and chain id that enabled the port */ struct vcap_enabled_port { struct list_head list; /* for insertion in enabled ports list */ struct net_device *ndev; /* the enabled port */ unsigned long cookie; /* filter that enabled the port */ + int src_cid; /* source chain id */ + int dst_cid; /* destination chain id */ }; void vcap_iter_set(struct vcap_stream_iter *itr, int sw_width, @@ -508,10 +510,133 @@ static void vcap_encode_keyfield_typegroups(struct vcap_control *vctrl, vcap_encode_typegroups(cache->maskstream, sw_width, tgt, true); } +/* Copy data from src to dst but reverse the data in chunks of 32bits. + * For example if src is 00:11:22:33:44:55 where 55 is LSB the dst will + * have the value 22:33:44:55:00:11. + */ +static void vcap_copy_to_w32be(u8 *dst, const u8 *src, int size) +{ + for (int idx = 0; idx < size; ++idx) { + int first_byte_index = 0; + int nidx; + + first_byte_index = size - (((idx >> 2) + 1) << 2); + if (first_byte_index < 0) + first_byte_index = 0; + nidx = idx + first_byte_index - (idx & ~0x3); + dst[nidx] = src[idx]; + } +} + +static void +vcap_copy_from_client_keyfield(struct vcap_rule *rule, + struct vcap_client_keyfield *dst, + const struct vcap_client_keyfield *src) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_client_keyfield_data *sdata; + struct vcap_client_keyfield_data *ddata; + int size; + + dst->ctrl.type = src->ctrl.type; + dst->ctrl.key = src->ctrl.key; + INIT_LIST_HEAD(&dst->ctrl.list); + sdata = &src->data; + ddata = &dst->data; + + if (!ri->admin->w32be) { + memcpy(ddata, sdata, sizeof(dst->data)); + return; + } + + size = keyfield_size_table[dst->ctrl.type] / 2; + + switch (dst->ctrl.type) { + case VCAP_FIELD_BIT: + case VCAP_FIELD_U32: + memcpy(ddata, sdata, sizeof(dst->data)); + break; + case VCAP_FIELD_U48: + vcap_copy_to_w32be(ddata->u48.value, src->data.u48.value, size); + vcap_copy_to_w32be(ddata->u48.mask, src->data.u48.mask, size); + break; + case VCAP_FIELD_U56: + vcap_copy_to_w32be(ddata->u56.value, sdata->u56.value, size); + vcap_copy_to_w32be(ddata->u56.mask, sdata->u56.mask, size); + break; + case VCAP_FIELD_U64: + vcap_copy_to_w32be(ddata->u64.value, sdata->u64.value, size); + vcap_copy_to_w32be(ddata->u64.mask, sdata->u64.mask, size); + break; + case VCAP_FIELD_U72: + vcap_copy_to_w32be(ddata->u72.value, sdata->u72.value, size); + vcap_copy_to_w32be(ddata->u72.mask, sdata->u72.mask, size); + break; + case VCAP_FIELD_U112: + vcap_copy_to_w32be(ddata->u112.value, sdata->u112.value, size); + vcap_copy_to_w32be(ddata->u112.mask, sdata->u112.mask, size); + break; + case VCAP_FIELD_U128: + vcap_copy_to_w32be(ddata->u128.value, sdata->u128.value, size); + vcap_copy_to_w32be(ddata->u128.mask, sdata->u128.mask, size); + break; + } +} + +static void +vcap_copy_from_client_actionfield(struct vcap_rule *rule, + struct vcap_client_actionfield *dst, + const struct vcap_client_actionfield *src) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_client_actionfield_data *sdata; + struct vcap_client_actionfield_data *ddata; + int size; + + dst->ctrl.type = src->ctrl.type; + dst->ctrl.action = src->ctrl.action; + INIT_LIST_HEAD(&dst->ctrl.list); + sdata = &src->data; + ddata = &dst->data; + + if (!ri->admin->w32be) { + memcpy(ddata, sdata, sizeof(dst->data)); + return; + } + + size = actionfield_size_table[dst->ctrl.type]; + + switch (dst->ctrl.type) { + case VCAP_FIELD_BIT: + case VCAP_FIELD_U32: + memcpy(ddata, sdata, sizeof(dst->data)); + break; + case VCAP_FIELD_U48: + vcap_copy_to_w32be(ddata->u48.value, sdata->u48.value, size); + break; + case VCAP_FIELD_U56: + vcap_copy_to_w32be(ddata->u56.value, sdata->u56.value, size); + break; + case VCAP_FIELD_U64: + vcap_copy_to_w32be(ddata->u64.value, sdata->u64.value, size); + break; + case VCAP_FIELD_U72: + vcap_copy_to_w32be(ddata->u72.value, sdata->u72.value, size); + break; + case VCAP_FIELD_U112: + vcap_copy_to_w32be(ddata->u112.value, sdata->u112.value, size); + break; + case VCAP_FIELD_U128: + vcap_copy_to_w32be(ddata->u128.value, sdata->u128.value, size); + break; + } +} + static int vcap_encode_rule_keyset(struct vcap_rule_internal *ri) { const struct vcap_client_keyfield *ckf; const struct vcap_typegroup *tg_table; + struct vcap_client_keyfield tempkf; const struct vcap_field *kf_table; int keyset_size; @@ -552,7 +677,9 @@ static int vcap_encode_rule_keyset(struct vcap_rule_internal *ri) __func__, __LINE__, ckf->ctrl.key); return -EINVAL; } - vcap_encode_keyfield(ri, ckf, &kf_table[ckf->ctrl.key], tg_table); + vcap_copy_from_client_keyfield(&ri->data, &tempkf, ckf); + vcap_encode_keyfield(ri, &tempkf, &kf_table[ckf->ctrl.key], + tg_table); } /* Add typegroup bits to the key/mask bitstreams */ vcap_encode_keyfield_typegroups(ri->vctrl, ri, tg_table); @@ -667,6 +794,7 @@ static int vcap_encode_rule_actionset(struct vcap_rule_internal *ri) { const struct vcap_client_actionfield *caf; const struct vcap_typegroup *tg_table; + struct vcap_client_actionfield tempaf; const struct vcap_field *af_table; int actionset_size; @@ -707,8 +835,9 @@ static int vcap_encode_rule_actionset(struct vcap_rule_internal *ri) __func__, __LINE__, caf->ctrl.action); return -EINVAL; } - vcap_encode_actionfield(ri, caf, &af_table[caf->ctrl.action], - tg_table); + vcap_copy_from_client_actionfield(&ri->data, &tempaf, caf); + vcap_encode_actionfield(ri, &tempaf, + &af_table[caf->ctrl.action], tg_table); } /* Add typegroup bits to the entry bitstreams */ vcap_encode_actionfield_typegroups(ri, tg_table); @@ -738,7 +867,7 @@ int vcap_api_check(struct vcap_control *ctrl) !ctrl->ops->add_default_fields || !ctrl->ops->cache_erase || !ctrl->ops->cache_write || !ctrl->ops->cache_read || !ctrl->ops->init || !ctrl->ops->update || !ctrl->ops->move || - !ctrl->ops->port_info || !ctrl->ops->enable) { + !ctrl->ops->port_info) { pr_err("%s:%d: client operations are missing\n", __func__, __LINE__); return -ENOENT; @@ -791,9 +920,8 @@ int vcap_set_rule_set_actionset(struct vcap_rule *rule, } EXPORT_SYMBOL_GPL(vcap_set_rule_set_actionset); -/* Find a rule with a provided rule id */ -static struct vcap_rule_internal *vcap_lookup_rule(struct vcap_control *vctrl, - u32 id) +/* Check if a rule with this id exists */ +static bool vcap_rule_exists(struct vcap_control *vctrl, u32 id) { struct vcap_rule_internal *ri; struct vcap_admin *admin; @@ -802,7 +930,25 @@ static struct vcap_rule_internal *vcap_lookup_rule(struct vcap_control *vctrl, list_for_each_entry(admin, &vctrl->list, list) list_for_each_entry(ri, &admin->rules, list) if (ri->data.id == id) + return true; + return false; +} + +/* Find a rule with a provided rule id return a locked vcap */ +static struct vcap_rule_internal * +vcap_get_locked_rule(struct vcap_control *vctrl, u32 id) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + + /* Look for the rule id in all vcaps */ + list_for_each_entry(admin, &vctrl->list, list) { + mutex_lock(&admin->lock); + list_for_each_entry(ri, &admin->rules, list) + if (ri->data.id == id) return ri; + mutex_unlock(&admin->lock); + } return NULL; } @@ -811,19 +957,31 @@ int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie) { struct vcap_rule_internal *ri; struct vcap_admin *admin; + int id = 0; /* Look for the rule id in all vcaps */ - list_for_each_entry(admin, &vctrl->list, list) - list_for_each_entry(ri, &admin->rules, list) - if (ri->data.cookie == cookie) - return ri->data.id; + list_for_each_entry(admin, &vctrl->list, list) { + mutex_lock(&admin->lock); + list_for_each_entry(ri, &admin->rules, list) { + if (ri->data.cookie == cookie) { + id = ri->data.id; + break; + } + } + mutex_unlock(&admin->lock); + if (id) + return id; + } return -ENOENT; } EXPORT_SYMBOL_GPL(vcap_lookup_rule_by_cookie); -/* Make a shallow copy of the rule without the fields */ -struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri) +/* Make a copy of the rule, shallow or full */ +static struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri, + bool full) { + struct vcap_client_actionfield *caf, *newcaf; + struct vcap_client_keyfield *ckf, *newckf; struct vcap_rule_internal *duprule; /* Allocate the client part */ @@ -836,6 +994,27 @@ struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri) /* No elements in these lists */ INIT_LIST_HEAD(&duprule->data.keyfields); INIT_LIST_HEAD(&duprule->data.actionfields); + + /* A full rule copy includes keys and actions */ + if (!full) + return duprule; + + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) { + newckf = kzalloc(sizeof(*newckf), GFP_KERNEL); + if (!newckf) + return ERR_PTR(-ENOMEM); + memcpy(newckf, ckf, sizeof(*newckf)); + list_add_tail(&newckf->ctrl.list, &duprule->data.keyfields); + } + + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) { + newcaf = kzalloc(sizeof(*newcaf), GFP_KERNEL); + if (!newcaf) + return ERR_PTR(-ENOMEM); + memcpy(newcaf, caf, sizeof(*newcaf)); + list_add_tail(&newcaf->ctrl.list, &duprule->data.actionfields); + } + return duprule; } @@ -1424,39 +1603,31 @@ struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid) } EXPORT_SYMBOL_GPL(vcap_find_admin); -/* Is the next chain id in the following lookup, possible in another VCAP */ -bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid) +/* Is the next chain id in one of the following lookups + * For now this does not support filters linked to other filters using + * keys and actions. That will be added later. + */ +bool vcap_is_next_lookup(struct vcap_control *vctrl, int src_cid, int dst_cid) { - struct vcap_admin *admin, *next_admin; - int lookup, next_lookup; + struct vcap_admin *admin; + int next_cid; - /* The offset must be at least one lookup */ - if (next_cid < cur_cid + VCAP_CID_LOOKUP_SIZE) + if (vcap_api_check(vctrl)) return false; - if (vcap_api_check(vctrl)) + /* The offset must be at least one lookup, round up */ + next_cid = src_cid + VCAP_CID_LOOKUP_SIZE; + next_cid /= VCAP_CID_LOOKUP_SIZE; + next_cid *= VCAP_CID_LOOKUP_SIZE; + + if (dst_cid < next_cid) return false; - admin = vcap_find_admin(vctrl, cur_cid); + admin = vcap_find_admin(vctrl, dst_cid); if (!admin) return false; - /* If no VCAP contains the next chain, the next chain must be beyond - * the last chain in the current VCAP - */ - next_admin = vcap_find_admin(vctrl, next_cid); - if (!next_admin) - return next_cid > admin->last_cid; - - lookup = vcap_chain_id_to_lookup(admin, cur_cid); - next_lookup = vcap_chain_id_to_lookup(next_admin, next_cid); - - /* Next lookup must be the following lookup */ - if (admin == next_admin || admin->vtype == next_admin->vtype) - return next_lookup == lookup + 1; - - /* Must be the first lookup in the next VCAP instance */ - return next_lookup == 0; + return true; } EXPORT_SYMBOL_GPL(vcap_is_next_lookup); @@ -1721,7 +1892,7 @@ static u32 vcap_set_rule_id(struct vcap_rule_internal *ri) return ri->data.id; for (u32 next_id = 1; next_id < ~0; ++next_id) { - if (!vcap_lookup_rule(ri->vctrl, next_id)) { + if (!vcap_rule_exists(ri->vctrl, next_id)) { ri->data.id = next_id; break; } @@ -1756,8 +1927,8 @@ static int vcap_insert_rule(struct vcap_rule_internal *ri, ri->addr = vcap_next_rule_addr(admin->last_used_addr, ri); admin->last_used_addr = ri->addr; - /* Add a shallow copy of the rule to the VCAP list */ - duprule = vcap_dup_rule(ri); + /* Add a copy of the rule to the VCAP list */ + duprule = vcap_dup_rule(ri, ri->state == VCAP_RS_DISABLED); if (IS_ERR(duprule)) return PTR_ERR(duprule); @@ -1770,8 +1941,8 @@ static int vcap_insert_rule(struct vcap_rule_internal *ri, ri->addr = vcap_next_rule_addr(addr, ri); addr = ri->addr; - /* Add a shallow copy of the rule to the VCAP list */ - duprule = vcap_dup_rule(ri); + /* Add a copy of the rule to the VCAP list */ + duprule = vcap_dup_rule(ri, ri->state == VCAP_RS_DISABLED); if (IS_ERR(duprule)) return PTR_ERR(duprule); @@ -1803,11 +1974,94 @@ static void vcap_move_rules(struct vcap_rule_internal *ri, move->offset, move->count); } +/* Check if the chain is already used to enable a VCAP lookup for this port */ +static bool vcap_is_chain_used(struct vcap_control *vctrl, + struct net_device *ndev, int src_cid) +{ + struct vcap_enabled_port *eport; + struct vcap_admin *admin; + + list_for_each_entry(admin, &vctrl->list, list) + list_for_each_entry(eport, &admin->enabled, list) + if (eport->src_cid == src_cid && eport->ndev == ndev) + return true; + + return false; +} + +/* Fetch the next chain in the enabled list for the port */ +static int vcap_get_next_chain(struct vcap_control *vctrl, + struct net_device *ndev, + int dst_cid) +{ + struct vcap_enabled_port *eport; + struct vcap_admin *admin; + + list_for_each_entry(admin, &vctrl->list, list) { + list_for_each_entry(eport, &admin->enabled, list) { + if (eport->ndev != ndev) + continue; + if (eport->src_cid == dst_cid) + return eport->dst_cid; + } + } + + return 0; +} + +static bool vcap_path_exist(struct vcap_control *vctrl, struct net_device *ndev, + int dst_cid) +{ + struct vcap_enabled_port *eport, *elem; + struct vcap_admin *admin; + int tmp; + + if (dst_cid == 0) /* Chain zero is always available */ + return true; + + /* Find first entry that starts from chain 0*/ + list_for_each_entry(admin, &vctrl->list, list) { + list_for_each_entry(elem, &admin->enabled, list) { + if (elem->src_cid == 0 && elem->ndev == ndev) { + eport = elem; + break; + } + } + if (eport) + break; + } + + if (!eport) + return false; + + tmp = eport->dst_cid; + while (tmp != dst_cid && tmp != 0) + tmp = vcap_get_next_chain(vctrl, ndev, tmp); + + return !!tmp; +} + +/* Internal clients can always store their rules in HW + * External clients can store their rules if the chain is enabled all + * the way from chain 0, otherwise the rule will be cached until + * the chain is enabled. + */ +static void vcap_rule_set_state(struct vcap_rule_internal *ri) +{ + if (ri->data.user <= VCAP_USER_QOS) + ri->state = VCAP_RS_PERMANENT; + else if (vcap_path_exist(ri->vctrl, ri->ndev, ri->data.vcap_chain_id)) + ri->state = VCAP_RS_ENABLED; + else + ri->state = VCAP_RS_DISABLED; +} + /* Encode and write a validated rule to the VCAP */ int vcap_add_rule(struct vcap_rule *rule) { struct vcap_rule_internal *ri = to_intrule(rule); struct vcap_rule_move move = {0}; + struct vcap_counter ctr = {0}; int ret; ret = vcap_api_check(ri->vctrl); @@ -1815,6 +2069,8 @@ int vcap_add_rule(struct vcap_rule *rule) return ret; /* Insert the new rule in the list of vcap rules */ mutex_lock(&ri->admin->lock); + + vcap_rule_set_state(ri); ret = vcap_insert_rule(ri, &move); if (ret < 0) { pr_err("%s:%d: could not insert rule in vcap list: %d\n", @@ -1823,6 +2079,14 @@ int vcap_add_rule(struct vcap_rule *rule) } if (move.count > 0) vcap_move_rules(ri, &move); + + if (ri->state == VCAP_RS_DISABLED) { + /* Erase the rule area */ + ri->vctrl->ops->init(ri->ndev, ri->admin, ri->addr, ri->size); + goto out; + } + + vcap_erase_cache(ri); ret = vcap_encode_rule(ri); if (ret) { pr_err("%s:%d: rule encoding error: %d\n", __func__, __LINE__, ret); @@ -1830,8 +2094,12 @@ int vcap_add_rule(struct vcap_rule *rule) } ret = vcap_write_rule(ri); - if (ret) + if (ret) { pr_err("%s:%d: rule write error: %d\n", __func__, __LINE__, ret); + goto out; + } + /* Set the counter to zero */ + ret = vcap_write_counter(ri, &ctr); out: mutex_unlock(&ri->admin->lock); return ret; @@ -1860,17 +2128,28 @@ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, /* Sanity check that this VCAP is supported on this platform */ if (vctrl->vcaps[admin->vtype].rows == 0) return ERR_PTR(-EINVAL); + + mutex_lock(&admin->lock); /* Check if a rule with this id already exists */ - if (vcap_lookup_rule(vctrl, id)) - return ERR_PTR(-EEXIST); + if (vcap_rule_exists(vctrl, id)) { + err = -EINVAL; + goto out_unlock; + } + /* Check if there is room for the rule in the block(s) of the VCAP */ maxsize = vctrl->vcaps[admin->vtype].sw_count; /* worst case rule size */ - if (vcap_rule_space(admin, maxsize)) - return ERR_PTR(-ENOSPC); + if (vcap_rule_space(admin, maxsize)) { + err = -ENOSPC; + goto out_unlock; + } + /* Create a container for the rule and return it */ ri = kzalloc(sizeof(*ri), GFP_KERNEL); - if (!ri) - return ERR_PTR(-ENOMEM); + if (!ri) { + err = -ENOMEM; + goto out_unlock; + } + ri->data.vcap_chain_id = vcap_chain_id; ri->data.user = user; ri->data.priority = priority; @@ -1883,14 +2162,21 @@ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, ri->ndev = ndev; ri->admin = admin; /* refer to the vcap instance */ ri->vctrl = vctrl; /* refer to the client */ - if (vcap_set_rule_id(ri) == 0) + + if (vcap_set_rule_id(ri) == 0) { + err = -EINVAL; goto out_free; - vcap_erase_cache(ri); + } + + mutex_unlock(&admin->lock); return (struct vcap_rule *)ri; out_free: kfree(ri); - return ERR_PTR(-EINVAL); +out_unlock: + mutex_unlock(&admin->lock); + return ERR_PTR(err); + } EXPORT_SYMBOL_GPL(vcap_alloc_rule); @@ -1915,43 +2201,52 @@ void vcap_free_rule(struct vcap_rule *rule) } EXPORT_SYMBOL_GPL(vcap_free_rule); -struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id) +/* Decode a rule from the VCAP cache and return a copy */ +struct vcap_rule *vcap_decode_rule(struct vcap_rule_internal *elem) { - struct vcap_rule_internal *elem; struct vcap_rule_internal *ri; int err; - ri = NULL; + ri = vcap_dup_rule(elem, elem->state == VCAP_RS_DISABLED); + if (IS_ERR(ri)) + return ERR_PTR(PTR_ERR(ri)); + + if (ri->state == VCAP_RS_DISABLED) + goto out; + + err = vcap_read_rule(ri); + if (err) + return ERR_PTR(err); + + err = vcap_decode_keyset(ri); + if (err) + return ERR_PTR(err); + + err = vcap_decode_actionset(ri); + if (err) + return ERR_PTR(err); + +out: + return &ri->data; +} + +struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id) +{ + struct vcap_rule_internal *elem; + struct vcap_rule *rule; + int err; err = vcap_api_check(vctrl); if (err) return ERR_PTR(err); - elem = vcap_lookup_rule(vctrl, id); + + elem = vcap_get_locked_rule(vctrl, id); if (!elem) return NULL; - mutex_lock(&elem->admin->lock); - ri = vcap_dup_rule(elem); - if (IS_ERR(ri)) - goto unlock; - err = vcap_read_rule(ri); - if (err) { - ri = ERR_PTR(err); - goto unlock; - } - err = vcap_decode_keyset(ri); - if (err) { - ri = ERR_PTR(err); - goto unlock; - } - err = vcap_decode_actionset(ri); - if (err) { - ri = ERR_PTR(err); - goto unlock; - } -unlock: + rule = vcap_decode_rule(elem); mutex_unlock(&elem->admin->lock); - return (struct vcap_rule *)ri; + return rule; } EXPORT_SYMBOL_GPL(vcap_get_rule); @@ -1966,10 +2261,13 @@ int vcap_mod_rule(struct vcap_rule *rule) if (err) return err; - if (!vcap_lookup_rule(ri->vctrl, ri->data.id)) + if (!vcap_get_locked_rule(ri->vctrl, ri->data.id)) return -ENOENT; - mutex_lock(&ri->admin->lock); + vcap_rule_set_state(ri); + if (ri->state == VCAP_RS_DISABLED) + goto out; + /* Encode the bitstreams to the VCAP cache */ vcap_erase_cache(ri); err = vcap_encode_rule(ri); @@ -1982,8 +2280,6 @@ int vcap_mod_rule(struct vcap_rule *rule) memset(&ctr, 0, sizeof(ctr)); err = vcap_write_counter(ri, &ctr); - if (err) - goto out; out: mutex_unlock(&ri->admin->lock); @@ -2050,20 +2346,19 @@ int vcap_del_rule(struct vcap_control *vctrl, struct net_device *ndev, u32 id) if (err) return err; /* Look for the rule id in all vcaps */ - ri = vcap_lookup_rule(vctrl, id); + ri = vcap_get_locked_rule(vctrl, id); if (!ri) - return -EINVAL; + return -ENOENT; + admin = ri->admin; if (ri->addr > admin->last_used_addr) gap = vcap_fill_rule_gap(ri); /* Delete the rule from the list of rules and the cache */ - mutex_lock(&admin->lock); list_del(&ri->list); vctrl->ops->init(ndev, admin, admin->last_used_addr, ri->size + gap); - kfree(ri); - mutex_unlock(&admin->lock); + vcap_free_rule(&ri->data); /* Update the last used address, set to default when no rules */ if (list_empty(&admin->rules)) { @@ -2073,7 +2368,9 @@ int vcap_del_rule(struct vcap_control *vctrl, struct net_device *ndev, u32 id) list); admin->last_used_addr = elem->addr; } - return 0; + + mutex_unlock(&admin->lock); + return err; } EXPORT_SYMBOL_GPL(vcap_del_rule); @@ -2091,7 +2388,7 @@ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) list_for_each_entry_safe(ri, next_ri, &admin->rules, list) { vctrl->ops->init(ri->ndev, admin, ri->addr, ri->size); list_del(&ri->list); - kfree(ri); + vcap_free_rule(&ri->data); } admin->last_used_addr = admin->last_valid_addr; @@ -2137,69 +2434,6 @@ const struct vcap_field *vcap_lookup_keyfield(struct vcap_rule *rule, } EXPORT_SYMBOL_GPL(vcap_lookup_keyfield); -/* Copy data from src to dst but reverse the data in chunks of 32bits. - * For example if src is 00:11:22:33:44:55 where 55 is LSB the dst will - * have the value 22:33:44:55:00:11. - */ -static void vcap_copy_to_w32be(u8 *dst, u8 *src, int size) -{ - for (int idx = 0; idx < size; ++idx) { - int first_byte_index = 0; - int nidx; - - first_byte_index = size - (((idx >> 2) + 1) << 2); - if (first_byte_index < 0) - first_byte_index = 0; - nidx = idx + first_byte_index - (idx & ~0x3); - dst[nidx] = src[idx]; - } -} - -static void vcap_copy_from_client_keyfield(struct vcap_rule *rule, - struct vcap_client_keyfield *field, - struct vcap_client_keyfield_data *data) -{ - struct vcap_rule_internal *ri = to_intrule(rule); - int size; - - if (!ri->admin->w32be) { - memcpy(&field->data, data, sizeof(field->data)); - return; - } - - size = keyfield_size_table[field->ctrl.type] / 2; - switch (field->ctrl.type) { - case VCAP_FIELD_BIT: - case VCAP_FIELD_U32: - memcpy(&field->data, data, sizeof(field->data)); - break; - case VCAP_FIELD_U48: - vcap_copy_to_w32be(field->data.u48.value, data->u48.value, size); - vcap_copy_to_w32be(field->data.u48.mask, data->u48.mask, size); - break; - case VCAP_FIELD_U56: - vcap_copy_to_w32be(field->data.u56.value, data->u56.value, size); - vcap_copy_to_w32be(field->data.u56.mask, data->u56.mask, size); - break; - case VCAP_FIELD_U64: - vcap_copy_to_w32be(field->data.u64.value, data->u64.value, size); - vcap_copy_to_w32be(field->data.u64.mask, data->u64.mask, size); - break; - case VCAP_FIELD_U72: - vcap_copy_to_w32be(field->data.u72.value, data->u72.value, size); - vcap_copy_to_w32be(field->data.u72.mask, data->u72.mask, size); - break; - case VCAP_FIELD_U112: - vcap_copy_to_w32be(field->data.u112.value, data->u112.value, size); - vcap_copy_to_w32be(field->data.u112.mask, data->u112.mask, size); - break; - case VCAP_FIELD_U128: - vcap_copy_to_w32be(field->data.u128.value, data->u128.value, size); - vcap_copy_to_w32be(field->data.u128.mask, data->u128.mask, size); - break; - } -} - /* Check if the keyfield is already in the rule */ static bool vcap_keyfield_unique(struct vcap_rule *rule, enum vcap_key_field key) @@ -2257,9 +2491,9 @@ static int vcap_rule_add_key(struct vcap_rule *rule, field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) return -ENOMEM; + memcpy(&field->data, data, sizeof(field->data)); field->ctrl.key = key; field->ctrl.type = ftype; - vcap_copy_from_client_keyfield(rule, field, data); list_add_tail(&field->ctrl.list, &rule->keyfields); return 0; } @@ -2367,45 +2601,6 @@ vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act) return NULL; } -static void vcap_copy_from_client_actionfield(struct vcap_rule *rule, - struct vcap_client_actionfield *field, - struct vcap_client_actionfield_data *data) -{ - struct vcap_rule_internal *ri = to_intrule(rule); - int size; - - if (!ri->admin->w32be) { - memcpy(&field->data, data, sizeof(field->data)); - return; - } - - size = actionfield_size_table[field->ctrl.type]; - switch (field->ctrl.type) { - case VCAP_FIELD_BIT: - case VCAP_FIELD_U32: - memcpy(&field->data, data, sizeof(field->data)); - break; - case VCAP_FIELD_U48: - vcap_copy_to_w32be(field->data.u48.value, data->u48.value, size); - break; - case VCAP_FIELD_U56: - vcap_copy_to_w32be(field->data.u56.value, data->u56.value, size); - break; - case VCAP_FIELD_U64: - vcap_copy_to_w32be(field->data.u64.value, data->u64.value, size); - break; - case VCAP_FIELD_U72: - vcap_copy_to_w32be(field->data.u72.value, data->u72.value, size); - break; - case VCAP_FIELD_U112: - vcap_copy_to_w32be(field->data.u112.value, data->u112.value, size); - break; - case VCAP_FIELD_U128: - vcap_copy_to_w32be(field->data.u128.value, data->u128.value, size); - break; - } -} - /* Check if the actionfield is already in the rule */ static bool vcap_actionfield_unique(struct vcap_rule *rule, enum vcap_action_field act) @@ -2463,9 +2658,9 @@ static int vcap_rule_add_action(struct vcap_rule *rule, field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) return -ENOMEM; + memcpy(&field->data, data, sizeof(field->data)); field->ctrl.action = action; field->ctrl.type = ftype; - vcap_copy_from_client_actionfield(rule, field, data); list_add_tail(&field->ctrl.list, &rule->actionfields); return 0; } @@ -2564,24 +2759,153 @@ void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule) } EXPORT_SYMBOL_GPL(vcap_set_tc_exterr); +/* Write a rule to VCAP HW to enable it */ +static int vcap_enable_rule(struct vcap_rule_internal *ri) +{ + struct vcap_client_actionfield *af, *naf; + struct vcap_client_keyfield *kf, *nkf; + int err; + + vcap_erase_cache(ri); + err = vcap_encode_rule(ri); + if (err) + goto out; + err = vcap_write_rule(ri); + if (err) + goto out; + + /* Deallocate the list of keys and actions */ + list_for_each_entry_safe(kf, nkf, &ri->data.keyfields, ctrl.list) { + list_del(&kf->ctrl.list); + kfree(kf); + } + list_for_each_entry_safe(af, naf, &ri->data.actionfields, ctrl.list) { + list_del(&af->ctrl.list); + kfree(af); + } + ri->state = VCAP_RS_ENABLED; +out: + return err; +} + +/* Enable all disabled rules for a specific chain/port in the VCAP HW */ +static int vcap_enable_rules(struct vcap_control *vctrl, + struct net_device *ndev, int chain) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + int err = 0; + + list_for_each_entry(admin, &vctrl->list, list) { + if (!(chain >= admin->first_cid && chain <= admin->last_cid)) + continue; + + /* Found the admin, now find the offloadable rules */ + mutex_lock(&admin->lock); + list_for_each_entry(ri, &admin->rules, list) { + if (ri->data.vcap_chain_id != chain) + continue; + + if (ri->ndev != ndev) + continue; + + if (ri->state != VCAP_RS_DISABLED) + continue; + + err = vcap_enable_rule(ri); + if (err) + break; + } + mutex_unlock(&admin->lock); + if (err) + break; + } + return err; +} + +/* Read and erase a rule from VCAP HW to disable it */ +static int vcap_disable_rule(struct vcap_rule_internal *ri) +{ + int err; + + err = vcap_read_rule(ri); + if (err) + return err; + err = vcap_decode_keyset(ri); + if (err) + return err; + err = vcap_decode_actionset(ri); + if (err) + return err; + + ri->state = VCAP_RS_DISABLED; + ri->vctrl->ops->init(ri->ndev, ri->admin, ri->addr, ri->size); + return 0; +} + +/* Disable all enabled rules for a specific chain/port in the VCAP HW */ +static int vcap_disable_rules(struct vcap_control *vctrl, + struct net_device *ndev, int chain) +{ + struct vcap_rule_internal *ri; + struct vcap_admin *admin; + int err = 0; + + list_for_each_entry(admin, &vctrl->list, list) { + if (!(chain >= admin->first_cid && chain <= admin->last_cid)) + continue; + + /* Found the admin, now find the rules on the chain */ + mutex_lock(&admin->lock); + list_for_each_entry(ri, &admin->rules, list) { + if (ri->data.vcap_chain_id != chain) + continue; + + if (ri->ndev != ndev) + continue; + + if (ri->state != VCAP_RS_ENABLED) + continue; + + err = vcap_disable_rule(ri); + if (err) + break; + } + mutex_unlock(&admin->lock); + if (err) + break; + } + return err; +} + /* Check if this port is already enabled for this VCAP instance */ -static bool vcap_is_enabled(struct vcap_admin *admin, struct net_device *ndev, - unsigned long cookie) +static bool vcap_is_enabled(struct vcap_control *vctrl, struct net_device *ndev, + int dst_cid) { struct vcap_enabled_port *eport; + struct vcap_admin *admin; - list_for_each_entry(eport, &admin->enabled, list) - if (eport->cookie == cookie || eport->ndev == ndev) - return true; + list_for_each_entry(admin, &vctrl->list, list) + list_for_each_entry(eport, &admin->enabled, list) + if (eport->dst_cid == dst_cid && eport->ndev == ndev) + return true; return false; } -/* Enable this port for this VCAP instance */ -static int vcap_enable(struct vcap_admin *admin, struct net_device *ndev, - unsigned long cookie) +/* Enable this port and chain id in a VCAP instance */ +static int vcap_enable(struct vcap_control *vctrl, struct net_device *ndev, + unsigned long cookie, int src_cid, int dst_cid) { struct vcap_enabled_port *eport; + struct vcap_admin *admin; + + if (src_cid >= dst_cid) + return -EFAULT; + + admin = vcap_find_admin(vctrl, dst_cid); + if (!admin) + return -ENOENT; eport = kzalloc(sizeof(*eport), GFP_KERNEL); if (!eport) @@ -2589,48 +2913,72 @@ static int vcap_enable(struct vcap_admin *admin, struct net_device *ndev, eport->ndev = ndev; eport->cookie = cookie; + eport->src_cid = src_cid; + eport->dst_cid = dst_cid; + mutex_lock(&admin->lock); list_add_tail(&eport->list, &admin->enabled); + mutex_unlock(&admin->lock); + if (vcap_path_exist(vctrl, ndev, src_cid)) { + /* Enable chained lookups */ + while (dst_cid) { + admin = vcap_find_admin(vctrl, dst_cid); + if (!admin) + return -ENOENT; + + vcap_enable_rules(vctrl, ndev, dst_cid); + dst_cid = vcap_get_next_chain(vctrl, ndev, dst_cid); + } + } return 0; } -/* Disable this port for this VCAP instance */ -static int vcap_disable(struct vcap_admin *admin, struct net_device *ndev, +/* Disable this port and chain id for a VCAP instance */ +static int vcap_disable(struct vcap_control *vctrl, struct net_device *ndev, unsigned long cookie) { - struct vcap_enabled_port *eport; + struct vcap_enabled_port *elem, *eport = NULL; + struct vcap_admin *found = NULL, *admin; + int dst_cid; - list_for_each_entry(eport, &admin->enabled, list) { - if (eport->cookie == cookie && eport->ndev == ndev) { - list_del(&eport->list); - kfree(eport); - return 0; + list_for_each_entry(admin, &vctrl->list, list) { + list_for_each_entry(elem, &admin->enabled, list) { + if (elem->cookie == cookie && elem->ndev == ndev) { + eport = elem; + found = admin; + break; + } } + if (eport) + break; } - return -ENOENT; -} + if (!eport) + return -ENOENT; -/* Find the VCAP instance that enabled the port using a specific filter */ -static struct vcap_admin *vcap_find_admin_by_cookie(struct vcap_control *vctrl, - unsigned long cookie) -{ - struct vcap_enabled_port *eport; - struct vcap_admin *admin; + /* Disable chained lookups */ + dst_cid = eport->dst_cid; + while (dst_cid) { + admin = vcap_find_admin(vctrl, dst_cid); + if (!admin) + return -ENOENT; - list_for_each_entry(admin, &vctrl->list, list) - list_for_each_entry(eport, &admin->enabled, list) - if (eport->cookie == cookie) - return admin; + vcap_disable_rules(vctrl, ndev, dst_cid); + dst_cid = vcap_get_next_chain(vctrl, ndev, dst_cid); + } - return NULL; + mutex_lock(&found->lock); + list_del(&eport->list); + mutex_unlock(&found->lock); + kfree(eport); + return 0; } -/* Enable/Disable the VCAP instance lookups. Chain id 0 means disable */ +/* Enable/Disable the VCAP instance lookups */ int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, - int chain_id, unsigned long cookie, bool enable) + int src_cid, int dst_cid, unsigned long cookie, + bool enable) { - struct vcap_admin *admin; int err; err = vcap_api_check(vctrl); @@ -2640,36 +2988,45 @@ int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, if (!ndev) return -ENODEV; - if (chain_id) - admin = vcap_find_admin(vctrl, chain_id); - else - admin = vcap_find_admin_by_cookie(vctrl, cookie); - if (!admin) - return -ENOENT; - - /* first instance and first chain */ - if (admin->vinst || chain_id > admin->first_cid) + /* Source and destination must be the first chain in a lookup */ + if (src_cid % VCAP_CID_LOOKUP_SIZE) + return -EFAULT; + if (dst_cid % VCAP_CID_LOOKUP_SIZE) return -EFAULT; - err = vctrl->ops->enable(ndev, admin, enable); - if (err) - return err; - - if (chain_id) { - if (vcap_is_enabled(admin, ndev, cookie)) + if (enable) { + if (vcap_is_enabled(vctrl, ndev, dst_cid)) return -EADDRINUSE; - mutex_lock(&admin->lock); - vcap_enable(admin, ndev, cookie); + if (vcap_is_chain_used(vctrl, ndev, src_cid)) + return -EADDRNOTAVAIL; + err = vcap_enable(vctrl, ndev, cookie, src_cid, dst_cid); } else { - mutex_lock(&admin->lock); - vcap_disable(admin, ndev, cookie); + err = vcap_disable(vctrl, ndev, cookie); } - mutex_unlock(&admin->lock); - return 0; + return err; } EXPORT_SYMBOL_GPL(vcap_enable_lookups); +/* Is this chain id the last lookup of all VCAPs */ +bool vcap_is_last_chain(struct vcap_control *vctrl, int cid) +{ + struct vcap_admin *admin; + int lookup; + + if (vcap_api_check(vctrl)) + return false; + + admin = vcap_find_admin(vctrl, cid); + if (!admin) + return false; + + /* This must be the last lookup in this VCAP type */ + lookup = vcap_chain_id_to_lookup(admin, cid); + return lookup == admin->lookups - 1; +} +EXPORT_SYMBOL_GPL(vcap_is_last_chain); + /* Set a rule counter id (for certain vcaps only) */ void vcap_rule_set_counter_id(struct vcap_rule *rule, u32 counter_id) { @@ -2679,31 +3036,6 @@ void vcap_rule_set_counter_id(struct vcap_rule *rule, u32 counter_id) } EXPORT_SYMBOL_GPL(vcap_rule_set_counter_id); -/* Provide all rules via a callback interface */ -int vcap_rule_iter(struct vcap_control *vctrl, - int (*callback)(void *, struct vcap_rule *), void *arg) -{ - struct vcap_rule_internal *ri; - struct vcap_admin *admin; - int ret; - - ret = vcap_api_check(vctrl); - if (ret) - return ret; - - /* Iterate all rules in each VCAP instance */ - list_for_each_entry(admin, &vctrl->list, list) { - list_for_each_entry(ri, &admin->rules, list) { - ret = callback(arg, &ri->data); - if (ret) - return ret; - } - } - - return 0; -} -EXPORT_SYMBOL_GPL(vcap_rule_iter); - int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr) { struct vcap_rule_internal *ri = to_intrule(rule); @@ -2716,7 +3048,12 @@ int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr) pr_err("%s:%d: counter is missing\n", __func__, __LINE__); return -EINVAL; } - return vcap_write_counter(ri, ctr); + + mutex_lock(&ri->admin->lock); + err = vcap_write_counter(ri, ctr); + mutex_unlock(&ri->admin->lock); + + return err; } EXPORT_SYMBOL_GPL(vcap_rule_set_counter); @@ -2732,10 +3069,116 @@ int vcap_rule_get_counter(struct vcap_rule *rule, struct vcap_counter *ctr) pr_err("%s:%d: counter is missing\n", __func__, __LINE__); return -EINVAL; } - return vcap_read_counter(ri, ctr); + + mutex_lock(&ri->admin->lock); + err = vcap_read_counter(ri, ctr); + mutex_unlock(&ri->admin->lock); + + return err; } EXPORT_SYMBOL_GPL(vcap_rule_get_counter); +/* Get a copy of a client key field */ +static int vcap_rule_get_key(struct vcap_rule *rule, + enum vcap_key_field key, + struct vcap_client_keyfield *ckf) +{ + struct vcap_client_keyfield *field; + + field = vcap_find_keyfield(rule, key); + if (!field) + return -EINVAL; + memcpy(ckf, field, sizeof(*ckf)); + INIT_LIST_HEAD(&ckf->ctrl.list); + return 0; +} + +/* Get the keysets that matches the rule key type/mask */ +int vcap_rule_get_keysets(struct vcap_rule_internal *ri, + struct vcap_keyset_list *matches) +{ + struct vcap_control *vctrl = ri->vctrl; + enum vcap_type vt = ri->admin->vtype; + const struct vcap_set *keyfield_set; + struct vcap_client_keyfield kf = {}; + u32 value, mask; + int err, idx; + + err = vcap_rule_get_key(&ri->data, VCAP_KF_TYPE, &kf); + if (err) + return err; + + if (kf.ctrl.type == VCAP_FIELD_BIT) { + value = kf.data.u1.value; + mask = kf.data.u1.mask; + } else if (kf.ctrl.type == VCAP_FIELD_U32) { + value = kf.data.u32.value; + mask = kf.data.u32.mask; + } else { + return -EINVAL; + } + + keyfield_set = vctrl->vcaps[vt].keyfield_set; + for (idx = 0; idx < vctrl->vcaps[vt].keyfield_set_size; ++idx) { + if (keyfield_set[idx].sw_per_item != ri->keyset_sw) + continue; + + if (keyfield_set[idx].type_id == (u8)-1) { + vcap_keyset_list_add(matches, idx); + continue; + } + + if ((keyfield_set[idx].type_id & mask) == value) + vcap_keyset_list_add(matches, idx); + } + if (matches->cnt > 0) + return 0; + + return -EINVAL; +} + +/* Collect packet counts from all rules with the same cookie */ +int vcap_get_rule_count_by_cookie(struct vcap_control *vctrl, + struct vcap_counter *ctr, u64 cookie) +{ + struct vcap_rule_internal *ri; + struct vcap_counter temp = {}; + struct vcap_admin *admin; + int err; + + err = vcap_api_check(vctrl); + if (err) + return err; + + /* Iterate all rules in each VCAP instance */ + list_for_each_entry(admin, &vctrl->list, list) { + mutex_lock(&admin->lock); + list_for_each_entry(ri, &admin->rules, list) { + if (ri->data.cookie != cookie) + continue; + + err = vcap_read_counter(ri, &temp); + if (err) + goto unlock; + ctr->value += temp.value; + + /* Reset the rule counter */ + temp.value = 0; + temp.sticky = 0; + err = vcap_write_counter(ri, &temp); + if (err) + goto unlock; + } + mutex_unlock(&admin->lock); + } + return err; + +unlock: + mutex_unlock(&admin->lock); + return err; +} +EXPORT_SYMBOL_GPL(vcap_get_rule_count_by_cookie); + static int vcap_rule_mod_key(struct vcap_rule *rule, enum vcap_key_field key, enum vcap_field_type ftype, @@ -2746,7 +3189,7 @@ static int vcap_rule_mod_key(struct vcap_rule *rule, field = vcap_find_keyfield(rule, key); if (!field) return vcap_rule_add_key(rule, key, ftype, data); - vcap_copy_from_client_keyfield(rule, field, data); + memcpy(&field->data, data, sizeof(field->data)); return 0; } @@ -2772,7 +3215,7 @@ static int vcap_rule_mod_action(struct vcap_rule *rule, field = vcap_find_actionfield(rule, action); if (!field) return vcap_rule_add_action(rule, action, ftype, data); - vcap_copy_from_client_actionfield(rule, field, data); + memcpy(&field->data, data, sizeof(field->data)); return 0; } diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h index 689c7270f2a8..c61f13a65030 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -259,11 +259,6 @@ struct vcap_operations { (struct net_device *ndev, struct vcap_admin *admin, struct vcap_output_print *out); - /* enable/disable the lookups in a vcap instance */ - int (*enable) - (struct net_device *ndev, - struct vcap_admin *admin, - bool enable); }; /* VCAP API Client control interface */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h index 0319866f9c94..2cdcd3b56b30 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h @@ -148,9 +148,10 @@ struct vcap_counter { bool sticky; }; -/* Enable/Disable the VCAP instance lookups. Chain id 0 means disable */ +/* Enable/Disable the VCAP instance lookups */ int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, - int chain_id, unsigned long cookie, bool enable); + int from_cid, int to_cid, unsigned long cookie, + bool enable); /* VCAP rule operations */ /* Allocate a rule and fill in the basic information */ @@ -201,6 +202,8 @@ int vcap_rule_add_action_u32(struct vcap_rule *rule, enum vcap_action_field action, u32 value); /* VCAP rule counter operations */ +int vcap_get_rule_count_by_cookie(struct vcap_control *vctrl, + struct vcap_counter *ctr, u64 cookie); int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr); int vcap_rule_get_counter(struct vcap_rule *rule, struct vcap_counter *ctr); @@ -216,6 +219,8 @@ const struct vcap_field *vcap_lookup_keyfield(struct vcap_rule *rule, int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie); /* Is the next chain id in the following lookup, possible in another VCAP */ bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid); +/* Is this chain id the last lookup of all VCAPs */ +bool vcap_is_last_chain(struct vcap_control *vctrl, int cid); /* Provide all rules via a callback interface */ int vcap_rule_iter(struct vcap_control *vctrl, int (*callback)(void *, struct vcap_rule *), void *arg); @@ -261,5 +266,4 @@ int vcap_rule_mod_action_u32(struct vcap_rule *rule, /* Get a 32 bit key field value and mask from the rule */ int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, u32 *value, u32 *mask); - #endif /* __VCAP_API_CLIENT__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c index e0b206247f2e..d49b1cf7712f 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c @@ -152,37 +152,48 @@ vcap_debugfs_show_rule_actionfield(struct vcap_control *vctrl, out->prf(out->dst, "\n"); } -static int vcap_debugfs_show_rule_keyset(struct vcap_rule_internal *ri, - struct vcap_output_print *out) +static int vcap_debugfs_show_keysets(struct vcap_rule_internal *ri, + struct vcap_output_print *out) { - struct vcap_control *vctrl = ri->vctrl; struct vcap_admin *admin = ri->admin; enum vcap_keyfield_set keysets[10]; - const struct vcap_field *keyfield; - enum vcap_type vt = admin->vtype; - struct vcap_client_keyfield *ckf; struct vcap_keyset_list matches; - u32 *maskstream; - u32 *keystream; - int res; + int err; - keystream = admin->cache.keystream; - maskstream = admin->cache.maskstream; matches.keysets = keysets; matches.cnt = 0; matches.max = ARRAY_SIZE(keysets); - res = vcap_find_keystream_keysets(vctrl, vt, keystream, maskstream, - false, 0, &matches); - if (res < 0) { + + if (ri->state == VCAP_RS_DISABLED) + err = vcap_rule_get_keysets(ri, &matches); + else + err = vcap_find_keystream_keysets(ri->vctrl, admin->vtype, + admin->cache.keystream, + admin->cache.maskstream, + false, 0, &matches); + if (err) { pr_err("%s:%d: could not find valid keysets: %d\n", - __func__, __LINE__, res); - return -EINVAL; + __func__, __LINE__, err); + return err; } + out->prf(out->dst, " keysets:"); for (int idx = 0; idx < matches.cnt; ++idx) out->prf(out->dst, " %s", - vcap_keyset_name(vctrl, matches.keysets[idx])); + vcap_keyset_name(ri->vctrl, matches.keysets[idx])); out->prf(out->dst, "\n"); + return 0; +} + +static int vcap_debugfs_show_rule_keyset(struct vcap_rule_internal *ri, + struct vcap_output_print *out) +{ + struct vcap_control *vctrl = ri->vctrl; + struct vcap_admin *admin = ri->admin; + const struct vcap_field *keyfield; + struct vcap_client_keyfield *ckf; + + vcap_debugfs_show_keysets(ri, out); out->prf(out->dst, " keyset_sw: %d\n", ri->keyset_sw); out->prf(out->dst, " keyset_sw_regs: %d\n", ri->keyset_sw_regs); @@ -233,6 +244,18 @@ static void vcap_show_admin_rule(struct vcap_control *vctrl, out->prf(out->dst, " chain_id: %d\n", ri->data.vcap_chain_id); out->prf(out->dst, " user: %d\n", ri->data.user); out->prf(out->dst, " priority: %d\n", ri->data.priority); + out->prf(out->dst, " state: "); + switch (ri->state) { + case VCAP_RS_PERMANENT: + out->prf(out->dst, "permanent\n"); + break; + case VCAP_RS_DISABLED: + out->prf(out->dst, "disabled\n"); + break; + case VCAP_RS_ENABLED: + out->prf(out->dst, "enabled\n"); + break; + } vcap_debugfs_show_rule_keyset(ri, out); vcap_debugfs_show_rule_actionset(ri, out); } @@ -272,7 +295,7 @@ static int vcap_show_admin(struct vcap_control *vctrl, vcap_show_admin_info(vctrl, admin, out); list_for_each_entry(elem, &admin->rules, list) { - vrule = vcap_get_rule(vctrl, elem->data.id); + vrule = vcap_decode_rule(elem); if (IS_ERR_OR_NULL(vrule)) { ret = PTR_ERR(vrule); break; @@ -381,8 +404,12 @@ static int vcap_debugfs_show(struct seq_file *m, void *unused) .prf = (void *)seq_printf, .dst = m, }; + int ret; - return vcap_show_admin(info->vctrl, info->admin, &out); + mutex_lock(&info->admin->lock); + ret = vcap_show_admin(info->vctrl, info->admin, &out); + mutex_unlock(&info->admin->lock); + return ret; } DEFINE_SHOW_ATTRIBUTE(vcap_debugfs); @@ -394,8 +421,12 @@ static int vcap_raw_debugfs_show(struct seq_file *m, void *unused) .prf = (void *)seq_printf, .dst = m, }; + int ret; - return vcap_show_admin_raw(info->vctrl, info->admin, &out); + mutex_lock(&info->admin->lock); + ret = vcap_show_admin_raw(info->vctrl, info->admin, &out); + mutex_unlock(&info->admin->lock); + return ret; } DEFINE_SHOW_ATTRIBUTE(vcap_raw_debugfs); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c index cf594668d5d9..cbf7e0f110b8 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c @@ -221,13 +221,6 @@ static int vcap_test_port_info(struct net_device *ndev, return 0; } -static int vcap_test_enable(struct net_device *ndev, - struct vcap_admin *admin, - bool enable) -{ - return 0; -} - static struct vcap_operations test_callbacks = { .validate_keyset = test_val_keyset, .add_default_fields = test_add_def_fields, @@ -238,7 +231,6 @@ static struct vcap_operations test_callbacks = { .update = test_cache_update, .move = test_cache_move, .port_info = vcap_test_port_info, - .enable = vcap_test_enable, }; static struct vcap_control test_vctrl = { @@ -253,6 +245,8 @@ static void vcap_test_api_init(struct vcap_admin *admin) INIT_LIST_HEAD(&test_vctrl.list); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); + INIT_LIST_HEAD(&admin->enabled); + mutex_init(&admin->lock); list_add_tail(&admin->list, &test_vctrl.list); memset(test_updateaddr, 0, sizeof(test_updateaddr)); test_updateaddridx = 0; @@ -452,6 +446,7 @@ static const char * const test_admin_expect[] = { " chain_id: 0\n", " user: 0\n", " priority: 0\n", + " state: permanent\n", " keysets: VCAP_KFS_MAC_ETYPE\n", " keyset_sw: 6\n", " keyset_sw_regs: 2\n", diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index 76a31215ebfb..82981176218c 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -211,13 +211,6 @@ static int vcap_test_port_info(struct net_device *ndev, return 0; } -static int vcap_test_enable(struct net_device *ndev, - struct vcap_admin *admin, - bool enable) -{ - return 0; -} - static struct vcap_operations test_callbacks = { .validate_keyset = test_val_keyset, .add_default_fields = test_add_def_fields, @@ -228,7 +221,6 @@ static struct vcap_operations test_callbacks = { .update = test_cache_update, .move = test_cache_move, .port_info = vcap_test_port_info, - .enable = vcap_test_enable, }; static struct vcap_control test_vctrl = { @@ -243,6 +235,8 @@ static void vcap_test_api_init(struct vcap_admin *admin) INIT_LIST_HEAD(&test_vctrl.list); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); + INIT_LIST_HEAD(&admin->enabled); + mutex_init(&admin->lock); list_add_tail(&admin->list, &test_vctrl.list); memset(test_updateaddr, 0, sizeof(test_updateaddr)); test_updateaddridx = 0; @@ -1312,8 +1306,8 @@ static void vcap_api_encode_rule_test(struct kunit *test) struct vcap_admin is2_admin = { .vtype = VCAP_TYPE_IS2, - .first_cid = 10000, - .last_cid = 19999, + .first_cid = 8000000, + .last_cid = 8099999, .lookups = 4, .last_valid_addr = 3071, .first_valid_addr = 0, @@ -1326,7 +1320,7 @@ static void vcap_api_encode_rule_test(struct kunit *test) }; struct vcap_rule *rule; struct vcap_rule_internal *ri; - int vcap_chain_id = 10005; + int vcap_chain_id = 8000000; enum vcap_user user = VCAP_USER_VCAP_UTIL; u16 priority = 10; int id = 100; @@ -1343,8 +1337,8 @@ static void vcap_api_encode_rule_test(struct kunit *test) u32 port_mask_rng_mask = 0x0f; u32 igr_port_mask_value = 0xffabcd01; u32 igr_port_mask_mask = ~0; - /* counter is not written yet, so it is not in expwriteaddr */ - u32 expwriteaddr[] = {792, 793, 794, 795, 796, 797, 0}; + /* counter is written as the last operation */ + u32 expwriteaddr[] = {792, 793, 794, 795, 796, 797, 792}; int idx; vcap_test_api_init(&is2_admin); @@ -1398,6 +1392,11 @@ static void vcap_api_encode_rule_test(struct kunit *test) KUNIT_EXPECT_EQ(test, 2, ri->keyset_sw_regs); KUNIT_EXPECT_EQ(test, 4, ri->actionset_sw_regs); + /* Enable lookup, so the rule will be written */ + ret = vcap_enable_lookups(&test_vctrl, &test_netdev, 0, + rule->vcap_chain_id, rule->cookie, true); + KUNIT_EXPECT_EQ(test, 0, ret); + /* Add rule with write callback */ ret = vcap_add_rule(rule); KUNIT_EXPECT_EQ(test, 0, ret); @@ -1872,7 +1871,7 @@ static void vcap_api_next_lookup_basic_test(struct kunit *test) ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8301000); KUNIT_EXPECT_EQ(test, false, ret); ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8401000); - KUNIT_EXPECT_EQ(test, true, ret); + KUNIT_EXPECT_EQ(test, false, ret); } static void vcap_api_next_lookup_advanced_test(struct kunit *test) @@ -1933,9 +1932,9 @@ static void vcap_api_next_lookup_advanced_test(struct kunit *test) ret = vcap_is_next_lookup(&test_vctrl, 1100000, 1201000); KUNIT_EXPECT_EQ(test, true, ret); ret = vcap_is_next_lookup(&test_vctrl, 1100000, 1301000); - KUNIT_EXPECT_EQ(test, false, ret); + KUNIT_EXPECT_EQ(test, true, ret); ret = vcap_is_next_lookup(&test_vctrl, 1100000, 8101000); - KUNIT_EXPECT_EQ(test, false, ret); + KUNIT_EXPECT_EQ(test, true, ret); ret = vcap_is_next_lookup(&test_vctrl, 1300000, 1401000); KUNIT_EXPECT_EQ(test, true, ret); ret = vcap_is_next_lookup(&test_vctrl, 1400000, 1501000); @@ -1951,7 +1950,7 @@ static void vcap_api_next_lookup_advanced_test(struct kunit *test) ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8301000); KUNIT_EXPECT_EQ(test, false, ret); ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8401000); - KUNIT_EXPECT_EQ(test, true, ret); + KUNIT_EXPECT_EQ(test, false, ret); } static void vcap_api_filter_unsupported_keys_test(struct kunit *test) diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h index 4fd21da97679..df81d9ff502b 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h @@ -13,6 +13,12 @@ #define to_intrule(rule) container_of((rule), struct vcap_rule_internal, data) +enum vcap_rule_state { + VCAP_RS_PERMANENT, /* the rule is always stored in HW */ + VCAP_RS_ENABLED, /* enabled in HW but can be disabled */ + VCAP_RS_DISABLED, /* disabled (stored in SW) and can be enabled */ +}; + /* Private VCAP API rule data */ struct vcap_rule_internal { struct vcap_rule data; /* provided by the client */ @@ -29,6 +35,7 @@ struct vcap_rule_internal { u32 addr; /* address in the VCAP at insertion */ u32 counter_id; /* counter id (if a dedicated counter is available) */ struct vcap_counter counter; /* last read counter value */ + enum vcap_rule_state state; /* rule storage state */ }; /* Bit iterator for the VCAP cache streams */ @@ -43,8 +50,6 @@ struct vcap_stream_iter { /* Check that the control has a valid set of callbacks */ int vcap_api_check(struct vcap_control *ctrl); -/* Make a shallow copy of the rule without the fields */ -struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri); /* Erase the VCAP cache area used or encoding and decoding */ void vcap_erase_cache(struct vcap_rule_internal *ri); @@ -110,4 +115,10 @@ int vcap_find_keystream_keysets(struct vcap_control *vctrl, enum vcap_type vt, u32 *keystream, u32 *mskstream, bool mask, int sw_max, struct vcap_keyset_list *kslist); +/* Get the keysets that matches the rule key type/mask */ +int vcap_rule_get_keysets(struct vcap_rule_internal *ri, + struct vcap_keyset_list *matches); +/* Decode a rule from the VCAP cache and return a copy */ +struct vcap_rule *vcap_decode_rule(struct vcap_rule_internal *elem); + #endif /* __VCAP_API_PRIVATE__ */ diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig index e785c00b5845..d03d6e96f730 100644 --- a/drivers/net/ethernet/netronome/Kconfig +++ b/drivers/net/ethernet/netronome/Kconfig @@ -18,7 +18,7 @@ if NET_VENDOR_NETRONOME config NFP tristate "Netronome(R) NFP4000/NFP6000 NIC driver" - depends on PCI && PCI_MSI + depends on PCI_MSI depends on VXLAN || VXLAN=n depends on TLS && TLS_DEVICE || TLS_DEVICE=n select NET_DEVLINK diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index 8a250214e289..c90d35f5ebca 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -83,3 +83,5 @@ endif nfp-$(CONFIG_NFP_NET_IPSEC) += crypto/ipsec.o nfd3/ipsec.o nfp-$(CONFIG_NFP_DEBUG) += nfp_net_debugfs.o + +nfp-$(CONFIG_DCB) += nic/dcb.o diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 51124309ae1f..a4096050c9bd 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -413,6 +413,7 @@ #define NFP_NET_CFG_MBOX_CMD_IPSEC 3 #define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET 5 #define NFP_NET_CFG_MBOX_CMD_TLV_CMSG 6 +#define NFP_NET_CFG_MBOX_CMD_DCB_UPDATE 7 #define NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD 8 #define NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL 9 diff --git a/drivers/net/ethernet/netronome/nfp/nic/dcb.c b/drivers/net/ethernet/netronome/nfp/nic/dcb.c new file mode 100644 index 000000000000..bb498ac6bd7d --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nic/dcb.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2023 Corigine, Inc. */ + +#include <linux/device.h> +#include <linux/netdevice.h> +#include <net/dcbnl.h> + +#include "../nfp_app.h" +#include "../nfp_net.h" +#include "../nfp_main.h" +#include "../nfpcore/nfp_cpp.h" +#include "../nfpcore/nfp_nffw.h" +#include "../nfp_net_sriov.h" + +#include "main.h" + +#define NFP_DCB_TRUST_PCP 1 +#define NFP_DCB_TRUST_DSCP 2 +#define NFP_DCB_TRUST_INVALID 0xff + +#define NFP_DCB_TSA_VENDOR 1 +#define NFP_DCB_TSA_STRICT 2 +#define NFP_DCB_TSA_ETS 3 + +#define NFP_DCB_GBL_ENABLE BIT(0) +#define NFP_DCB_QOS_ENABLE BIT(1) +#define NFP_DCB_DISABLE 0 +#define NFP_DCB_ALL_QOS_ENABLE (NFP_DCB_GBL_ENABLE | NFP_DCB_QOS_ENABLE) + +#define NFP_DCB_UPDATE_MSK_SZ 4 +#define NFP_DCB_TC_RATE_MAX 0xffff + +#define NFP_DCB_DATA_OFF_DSCP2IDX 0 +#define NFP_DCB_DATA_OFF_PCP2IDX 64 +#define NFP_DCB_DATA_OFF_TSA 80 +#define NFP_DCB_DATA_OFF_IDX_BW_PCT 88 +#define NFP_DCB_DATA_OFF_RATE 96 +#define NFP_DCB_DATA_OFF_CAP 112 +#define NFP_DCB_DATA_OFF_ENABLE 116 +#define NFP_DCB_DATA_OFF_TRUST 120 + +#define NFP_DCB_MSG_MSK_ENABLE BIT(31) +#define NFP_DCB_MSG_MSK_TRUST BIT(30) +#define NFP_DCB_MSG_MSK_TSA BIT(29) +#define NFP_DCB_MSG_MSK_DSCP BIT(28) +#define NFP_DCB_MSG_MSK_PCP BIT(27) +#define NFP_DCB_MSG_MSK_RATE BIT(26) +#define NFP_DCB_MSG_MSK_PCT BIT(25) + +static struct nfp_dcb *get_dcb_priv(struct nfp_net *nn) +{ + struct nfp_dcb *dcb = &((struct nfp_app_nic_private *)nn->app_priv)->dcb; + + return dcb; +} + +static u8 nfp_tsa_ieee2nfp(u8 tsa) +{ + switch (tsa) { + case IEEE_8021QAZ_TSA_STRICT: + return NFP_DCB_TSA_STRICT; + case IEEE_8021QAZ_TSA_ETS: + return NFP_DCB_TSA_ETS; + default: + return NFP_DCB_TSA_VENDOR; + } +} + +static int nfp_nic_dcbnl_ieee_getets(struct net_device *dev, + struct ieee_ets *ets) +{ + struct nfp_net *nn = netdev_priv(dev); + struct nfp_dcb *dcb; + + dcb = get_dcb_priv(nn); + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + ets->prio_tc[i] = dcb->prio2tc[i]; + ets->tc_tx_bw[i] = dcb->tc_tx_pct[i]; + ets->tc_tsa[i] = dcb->tc_tsa[i]; + } + + return 0; +} + +static bool nfp_refresh_tc2idx(struct nfp_net *nn) +{ + u8 tc2idx[IEEE_8021QAZ_MAX_TCS]; + bool change = false; + struct nfp_dcb *dcb; + int maxstrict = 0; + + dcb = get_dcb_priv(nn); + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + tc2idx[i] = i; + if (dcb->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT) + maxstrict = i; + } + + if (maxstrict > 0 && dcb->tc_tsa[0] != IEEE_8021QAZ_TSA_STRICT) { + tc2idx[0] = maxstrict; + tc2idx[maxstrict] = 0; + } + + for (unsigned int j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) { + if (dcb->tc2idx[j] != tc2idx[j]) { + change = true; + dcb->tc2idx[j] = tc2idx[j]; + } + } + + return change; +} + +static int nfp_fill_maxrate(struct nfp_net *nn, u64 *max_rate_array) +{ + struct nfp_app *app = nn->app; + struct nfp_dcb *dcb; + u32 ratembps; + + dcb = get_dcb_priv(nn); + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + /* Convert bandwidth from kbps to mbps. */ + ratembps = max_rate_array[i] / 1024; + + /* Reject input values >= NFP_DCB_TC_RATE_MAX */ + if (ratembps >= NFP_DCB_TC_RATE_MAX) { + nfp_warn(app->cpp, "ratembps(%d) must less than %d.", + ratembps, NFP_DCB_TC_RATE_MAX); + return -EINVAL; + } + /* Input value 0 mapped to NFP_DCB_TC_RATE_MAX for firmware. */ + if (ratembps == 0) + ratembps = NFP_DCB_TC_RATE_MAX; + + writew((u16)ratembps, dcb->dcbcfg_tbl + + dcb->cfg_offset + NFP_DCB_DATA_OFF_RATE + dcb->tc2idx[i] * 2); + /* for rate value from user space, need to sync to dcb structure */ + if (dcb->tc_maxrate != max_rate_array) + dcb->tc_maxrate[i] = max_rate_array[i]; + } + + return 0; +} + +static int update_dscp_maxrate(struct net_device *dev, u32 *update) +{ + struct nfp_net *nn = netdev_priv(dev); + struct nfp_dcb *dcb; + int err; + + dcb = get_dcb_priv(nn); + + err = nfp_fill_maxrate(nn, dcb->tc_maxrate); + if (err) + return err; + + *update |= NFP_DCB_MSG_MSK_RATE; + + /* We only refresh dscp in dscp trust mode. */ + if (dcb->dscp_cnt > 0) { + for (unsigned int i = 0; i < NFP_NET_MAX_DSCP; i++) { + writeb(dcb->tc2idx[dcb->prio2tc[dcb->dscp2prio[i]]], + dcb->dcbcfg_tbl + dcb->cfg_offset + + NFP_DCB_DATA_OFF_DSCP2IDX + i); + } + *update |= NFP_DCB_MSG_MSK_DSCP; + } + + return 0; +} + +static void nfp_nic_set_trust(struct nfp_net *nn, u32 *update) +{ + struct nfp_dcb *dcb; + u8 trust; + + dcb = get_dcb_priv(nn); + + if (dcb->trust_status != NFP_DCB_TRUST_INVALID) + return; + + trust = dcb->dscp_cnt > 0 ? NFP_DCB_TRUST_DSCP : NFP_DCB_TRUST_PCP; + writeb(trust, dcb->dcbcfg_tbl + dcb->cfg_offset + + NFP_DCB_DATA_OFF_TRUST); + + dcb->trust_status = trust; + *update |= NFP_DCB_MSG_MSK_TRUST; +} + +static void nfp_nic_set_enable(struct nfp_net *nn, u32 enable, u32 *update) +{ + struct nfp_dcb *dcb; + u32 value = 0; + + dcb = get_dcb_priv(nn); + + value = readl(dcb->dcbcfg_tbl + dcb->cfg_offset + + NFP_DCB_DATA_OFF_ENABLE); + if (value != enable) { + writel(enable, dcb->dcbcfg_tbl + dcb->cfg_offset + + NFP_DCB_DATA_OFF_ENABLE); + *update |= NFP_DCB_MSG_MSK_ENABLE; + } +} + +static int dcb_ets_check(struct net_device *dev, struct ieee_ets *ets) +{ + struct nfp_net *nn = netdev_priv(dev); + struct nfp_app *app = nn->app; + bool ets_exists = false; + int sum = 0; + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + /* For ets mode, check bw percentage sum. */ + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { + ets_exists = true; + sum += ets->tc_tx_bw[i]; + } else if (ets->tc_tx_bw[i]) { + nfp_warn(app->cpp, "ETS BW for strict/vendor TC must be 0."); + return -EINVAL; + } + } + + if (ets_exists && sum != 100) { + nfp_warn(app->cpp, "Failed to validate ETS BW: sum must be 100."); + return -EINVAL; + } + + return 0; +} + +static void nfp_nic_fill_ets(struct nfp_net *nn) +{ + struct nfp_dcb *dcb; + + dcb = get_dcb_priv(nn); + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + writeb(dcb->tc2idx[dcb->prio2tc[i]], + dcb->dcbcfg_tbl + dcb->cfg_offset + NFP_DCB_DATA_OFF_PCP2IDX + i); + writeb(dcb->tc_tx_pct[i], dcb->dcbcfg_tbl + + dcb->cfg_offset + NFP_DCB_DATA_OFF_IDX_BW_PCT + dcb->tc2idx[i]); + writeb(nfp_tsa_ieee2nfp(dcb->tc_tsa[i]), dcb->dcbcfg_tbl + + dcb->cfg_offset + NFP_DCB_DATA_OFF_TSA + dcb->tc2idx[i]); + } +} + +static void nfp_nic_ets_init(struct nfp_net *nn, u32 *update) +{ + struct nfp_dcb *dcb = get_dcb_priv(nn); + + if (dcb->ets_init) + return; + + nfp_nic_fill_ets(nn); + dcb->ets_init = true; + *update |= NFP_DCB_MSG_MSK_TSA | NFP_DCB_MSG_MSK_PCT | NFP_DCB_MSG_MSK_PCP; +} + +static int nfp_nic_dcbnl_ieee_setets(struct net_device *dev, + struct ieee_ets *ets) +{ + const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE; + struct nfp_net *nn = netdev_priv(dev); + struct nfp_app *app = nn->app; + struct nfp_dcb *dcb; + u32 update = 0; + bool change; + int err; + + err = dcb_ets_check(dev, ets); + if (err) + return err; + + dcb = get_dcb_priv(nn); + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + dcb->prio2tc[i] = ets->prio_tc[i]; + dcb->tc_tx_pct[i] = ets->tc_tx_bw[i]; + dcb->tc_tsa[i] = ets->tc_tsa[i]; + } + + change = nfp_refresh_tc2idx(nn); + nfp_nic_fill_ets(nn); + dcb->ets_init = true; + if (change || !dcb->rate_init) { + err = update_dscp_maxrate(dev, &update); + if (err) { + nfp_warn(app->cpp, + "nfp dcbnl ieee setets ERROR:%d.", + err); + return err; + } + + dcb->rate_init = true; + } + nfp_nic_set_enable(nn, NFP_DCB_ALL_QOS_ENABLE, &update); + nfp_nic_set_trust(nn, &update); + err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ); + if (err) + return err; + + nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL, + update | NFP_DCB_MSG_MSK_TSA | NFP_DCB_MSG_MSK_PCT | + NFP_DCB_MSG_MSK_PCP); + + return nfp_net_mbox_reconfig_and_unlock(nn, cmd); +} + +static int nfp_nic_dcbnl_ieee_getmaxrate(struct net_device *dev, + struct ieee_maxrate *maxrate) +{ + struct nfp_net *nn = netdev_priv(dev); + struct nfp_dcb *dcb; + + dcb = get_dcb_priv(nn); + + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + maxrate->tc_maxrate[i] = dcb->tc_maxrate[i]; + + return 0; +} + +static int nfp_nic_dcbnl_ieee_setmaxrate(struct net_device *dev, + struct ieee_maxrate *maxrate) +{ + const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE; + struct nfp_net *nn = netdev_priv(dev); + struct nfp_app *app = nn->app; + struct nfp_dcb *dcb; + u32 update = 0; + int err; + + err = nfp_fill_maxrate(nn, maxrate->tc_maxrate); + if (err) { + nfp_warn(app->cpp, + "nfp dcbnl ieee setmaxrate ERROR:%d.", + err); + return err; + } + + dcb = get_dcb_priv(nn); + + dcb->rate_init = true; + nfp_nic_set_enable(nn, NFP_DCB_ALL_QOS_ENABLE, &update); + nfp_nic_set_trust(nn, &update); + nfp_nic_ets_init(nn, &update); + + err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ); + if (err) + return err; + + nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL, + update | NFP_DCB_MSG_MSK_RATE); + + return nfp_net_mbox_reconfig_and_unlock(nn, cmd); +} + +static int nfp_nic_set_trust_status(struct nfp_net *nn, u8 status) +{ + const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE; + struct nfp_dcb *dcb; + u32 update = 0; + int err; + + dcb = get_dcb_priv(nn); + if (!dcb->rate_init) { + err = nfp_fill_maxrate(nn, dcb->tc_maxrate); + if (err) + return err; + + update |= NFP_DCB_MSG_MSK_RATE; + dcb->rate_init = true; + } + + err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ); + if (err) + return err; + + nfp_nic_ets_init(nn, &update); + writeb(status, dcb->dcbcfg_tbl + dcb->cfg_offset + + NFP_DCB_DATA_OFF_TRUST); + nfp_nic_set_enable(nn, NFP_DCB_ALL_QOS_ENABLE, &update); + nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL, + update | NFP_DCB_MSG_MSK_TRUST); + + err = nfp_net_mbox_reconfig_and_unlock(nn, cmd); + if (err) + return err; + + dcb->trust_status = status; + + return 0; +} + +static int nfp_nic_set_dscp2prio(struct nfp_net *nn, u8 dscp, u8 prio) +{ + const u32 cmd = NFP_NET_CFG_MBOX_CMD_DCB_UPDATE; + struct nfp_dcb *dcb; + u8 idx, tc; + int err; + + err = nfp_net_mbox_lock(nn, NFP_DCB_UPDATE_MSK_SZ); + if (err) + return err; + + dcb = get_dcb_priv(nn); + + tc = dcb->prio2tc[prio]; + idx = dcb->tc2idx[tc]; + + writeb(idx, dcb->dcbcfg_tbl + dcb->cfg_offset + + NFP_DCB_DATA_OFF_DSCP2IDX + dscp); + + nn_writel(nn, nn->tlv_caps.mbox_off + + NFP_NET_CFG_MBOX_SIMPLE_VAL, NFP_DCB_MSG_MSK_DSCP); + + err = nfp_net_mbox_reconfig_and_unlock(nn, cmd); + if (err) + return err; + + dcb->dscp2prio[dscp] = prio; + + return 0; +} + +static int nfp_nic_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) +{ + struct nfp_net *nn = netdev_priv(dev); + struct dcb_app old_app; + struct nfp_dcb *dcb; + bool is_new; + int err; + + if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) + return -EINVAL; + + dcb = get_dcb_priv(nn); + + /* Save the old entry info */ + old_app.selector = IEEE_8021QAZ_APP_SEL_DSCP; + old_app.protocol = app->protocol; + old_app.priority = dcb->dscp2prio[app->protocol]; + + /* Check trust status */ + if (!dcb->dscp_cnt) { + err = nfp_nic_set_trust_status(nn, NFP_DCB_TRUST_DSCP); + if (err) + return err; + } + + /* Check if the new mapping is same as old or in init stage */ + if (app->priority != old_app.priority || app->priority == 0) { + err = nfp_nic_set_dscp2prio(nn, app->protocol, app->priority); + if (err) + return err; + } + + /* Delete the old entry if exists */ + is_new = !!dcb_ieee_delapp(dev, &old_app); + + /* Add new entry and update counter */ + err = dcb_ieee_setapp(dev, app); + if (err) + return err; + + if (is_new) + dcb->dscp_cnt++; + + return 0; +} + +static int nfp_nic_dcbnl_ieee_delapp(struct net_device *dev, + struct dcb_app *app) +{ + struct nfp_net *nn = netdev_priv(dev); + struct nfp_dcb *dcb; + int err; + + if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) + return -EINVAL; + + dcb = get_dcb_priv(nn); + + /* Check if the dcb_app param match fw */ + if (app->priority != dcb->dscp2prio[app->protocol]) + return -ENOENT; + + /* Set fw dscp mapping to 0 */ + err = nfp_nic_set_dscp2prio(nn, app->protocol, 0); + if (err) + return err; + + /* Delete app from dcb list */ + err = dcb_ieee_delapp(dev, app); + if (err) + return err; + + /* Decrease dscp counter */ + dcb->dscp_cnt--; + + /* If no dscp mapping is configured, trust pcp */ + if (dcb->dscp_cnt == 0) + return nfp_nic_set_trust_status(nn, NFP_DCB_TRUST_PCP); + + return 0; +} + +static const struct dcbnl_rtnl_ops nfp_nic_dcbnl_ops = { + /* ieee 802.1Qaz std */ + .ieee_getets = nfp_nic_dcbnl_ieee_getets, + .ieee_setets = nfp_nic_dcbnl_ieee_setets, + .ieee_getmaxrate = nfp_nic_dcbnl_ieee_getmaxrate, + .ieee_setmaxrate = nfp_nic_dcbnl_ieee_setmaxrate, + .ieee_setapp = nfp_nic_dcbnl_ieee_setapp, + .ieee_delapp = nfp_nic_dcbnl_ieee_delapp, +}; + +int nfp_nic_dcb_init(struct nfp_net *nn) +{ + struct nfp_app *app = nn->app; + struct nfp_dcb *dcb; + int err; + + dcb = get_dcb_priv(nn); + dcb->cfg_offset = NFP_DCB_CFG_STRIDE * nn->id; + dcb->dcbcfg_tbl = nfp_pf_map_rtsym(app->pf, "net.dcbcfg_tbl", + "_abi_dcb_cfg", + dcb->cfg_offset, &dcb->dcbcfg_tbl_area); + if (IS_ERR(dcb->dcbcfg_tbl)) { + if (PTR_ERR(dcb->dcbcfg_tbl) != -ENOENT) { + err = PTR_ERR(dcb->dcbcfg_tbl); + dcb->dcbcfg_tbl = NULL; + nfp_err(app->cpp, + "Failed to map dcbcfg_tbl area, min_size %u.\n", + dcb->cfg_offset); + return err; + } + dcb->dcbcfg_tbl = NULL; + } + + if (dcb->dcbcfg_tbl) { + for (unsigned int i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + dcb->prio2tc[i] = i; + dcb->tc2idx[i] = i; + dcb->tc_tx_pct[i] = 0; + dcb->tc_maxrate[i] = 0; + dcb->tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR; + } + dcb->trust_status = NFP_DCB_TRUST_INVALID; + dcb->rate_init = false; + dcb->ets_init = false; + + nn->dp.netdev->dcbnl_ops = &nfp_nic_dcbnl_ops; + } + + return 0; +} + +void nfp_nic_dcb_clean(struct nfp_net *nn) +{ + struct nfp_dcb *dcb; + + dcb = get_dcb_priv(nn); + if (dcb->dcbcfg_tbl_area) + nfp_cpp_area_release_free(dcb->dcbcfg_tbl_area); +} diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.c b/drivers/net/ethernet/netronome/nfp/nic/main.c index aea8579206ee..f78c2447d45b 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.c +++ b/drivers/net/ethernet/netronome/nfp/nic/main.c @@ -5,6 +5,8 @@ #include "../nfpcore/nfp_nsp.h" #include "../nfp_app.h" #include "../nfp_main.h" +#include "../nfp_net.h" +#include "main.h" static int nfp_nic_init(struct nfp_app *app) { @@ -28,13 +30,46 @@ static void nfp_nic_sriov_disable(struct nfp_app *app) { } +static int nfp_nic_vnic_init(struct nfp_app *app, struct nfp_net *nn) +{ + nfp_nic_dcb_init(nn); + + return 0; +} + +static int nfp_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, + unsigned int id) +{ + struct nfp_app_nic_private *app_pri = nn->app_priv; + int err; + + err = nfp_app_nic_vnic_alloc(app, nn, id); + if (err) + return err; + + if (sizeof(*app_pri)) { + nn->app_priv = kzalloc(sizeof(*app_pri), GFP_KERNEL); + if (!nn->app_priv) + return -ENOMEM; + } + + return 0; +} + +static void nfp_nic_vnic_free(struct nfp_app *app, struct nfp_net *nn) +{ + kfree(nn->app_priv); +} + const struct nfp_app_type app_nic = { .id = NFP_APP_CORE_NIC, .name = "nic", .init = nfp_nic_init, - .vnic_alloc = nfp_app_nic_vnic_alloc, - + .vnic_alloc = nfp_nic_vnic_alloc, + .vnic_free = nfp_nic_vnic_free, .sriov_enable = nfp_nic_sriov_enable, .sriov_disable = nfp_nic_sriov_disable, + + .vnic_init = nfp_nic_vnic_init, }; diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h new file mode 100644 index 000000000000..7ba04451b8ba --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nic/main.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2023 Corigine, Inc. */ + +#ifndef __NFP_NIC_H__ +#define __NFP_NIC_H__ 1 + +#include <linux/netdevice.h> + +#ifdef CONFIG_DCB +/* DCB feature definitions */ +#define NFP_NET_MAX_DSCP 4 +#define NFP_NET_MAX_TC IEEE_8021QAZ_MAX_TCS +#define NFP_NET_MAX_PRIO 8 +#define NFP_DCB_CFG_STRIDE 256 + +struct nfp_dcb { + u8 dscp2prio[NFP_NET_MAX_DSCP]; + u8 prio2tc[NFP_NET_MAX_PRIO]; + u8 tc2idx[IEEE_8021QAZ_MAX_TCS]; + u64 tc_maxrate[IEEE_8021QAZ_MAX_TCS]; + u8 tc_tx_pct[IEEE_8021QAZ_MAX_TCS]; + u8 tc_tsa[IEEE_8021QAZ_MAX_TCS]; + u8 dscp_cnt; + u8 trust_status; + bool rate_init; + bool ets_init; + + struct nfp_cpp_area *dcbcfg_tbl_area; + u8 __iomem *dcbcfg_tbl; + u32 cfg_offset; +}; + +int nfp_nic_dcb_init(struct nfp_net *nn); +void nfp_nic_dcb_clean(struct nfp_net *nn); +#else +static inline int nfp_nic_dcb_init(struct nfp_net *nn) {return 0; } +static inline void nfp_nic_dcb_clean(struct nfp_net *nn) {} +#endif + +struct nfp_app_nic_private { +#ifdef CONFIG_DCB + struct nfp_dcb dcb; +#endif +}; + +#endif diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 62320be4de5a..56e02cba0b8a 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1081,40 +1081,59 @@ static const struct ethtool_ops nixge_ethtool_ops = { .get_link = ethtool_op_get_link, }; -static int nixge_mdio_read(struct mii_bus *bus, int phy_id, int reg) +static int nixge_mdio_read_c22(struct mii_bus *bus, int phy_id, int reg) { struct nixge_priv *priv = bus->priv; u32 status, tmp; int err; u16 device; - if (reg & MII_ADDR_C45) { - device = (reg >> 16) & 0x1f; + device = reg & 0x1f; - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_ADDR, reg & 0xffff); + tmp = NIXGE_MDIO_CLAUSE22 | NIXGE_MDIO_OP(NIXGE_MDIO_C22_READ) | + NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); - tmp = NIXGE_MDIO_CLAUSE45 | NIXGE_MDIO_OP(NIXGE_MDIO_OP_ADDRESS) - | NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); + err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, + !status, 10, 1000); + if (err) { + dev_err(priv->dev, "timeout setting read command"); + return err; + } - err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, - !status, 10, 1000); - if (err) { - dev_err(priv->dev, "timeout setting address"); - return err; - } + status = nixge_ctrl_read_reg(priv, NIXGE_REG_MDIO_DATA); - tmp = NIXGE_MDIO_CLAUSE45 | NIXGE_MDIO_OP(NIXGE_MDIO_C45_READ) | - NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); - } else { - device = reg & 0x1f; + return status; +} - tmp = NIXGE_MDIO_CLAUSE22 | NIXGE_MDIO_OP(NIXGE_MDIO_C22_READ) | - NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); +static int nixge_mdio_read_c45(struct mii_bus *bus, int phy_id, int device, + int reg) +{ + struct nixge_priv *priv = bus->priv; + u32 status, tmp; + int err; + + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_ADDR, reg & 0xffff); + + tmp = NIXGE_MDIO_CLAUSE45 | + NIXGE_MDIO_OP(NIXGE_MDIO_OP_ADDRESS) | + NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); + + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); + + err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, + !status, 10, 1000); + if (err) { + dev_err(priv->dev, "timeout setting address"); + return err; } + tmp = NIXGE_MDIO_CLAUSE45 | NIXGE_MDIO_OP(NIXGE_MDIO_C45_READ) | + NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); @@ -1130,57 +1149,65 @@ static int nixge_mdio_read(struct mii_bus *bus, int phy_id, int reg) return status; } -static int nixge_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val) +static int nixge_mdio_write_c22(struct mii_bus *bus, int phy_id, int reg, + u16 val) { struct nixge_priv *priv = bus->priv; u32 status, tmp; u16 device; int err; - if (reg & MII_ADDR_C45) { - device = (reg >> 16) & 0x1f; + device = reg & 0x1f; - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_ADDR, reg & 0xffff); + tmp = NIXGE_MDIO_CLAUSE22 | NIXGE_MDIO_OP(NIXGE_MDIO_C22_WRITE) | + NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); - tmp = NIXGE_MDIO_CLAUSE45 | NIXGE_MDIO_OP(NIXGE_MDIO_OP_ADDRESS) - | NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_DATA, val); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); + err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, + !status, 10, 1000); + if (err) + dev_err(priv->dev, "timeout setting write command"); - err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, - !status, 10, 1000); - if (err) { - dev_err(priv->dev, "timeout setting address"); - return err; - } + return err; +} - tmp = NIXGE_MDIO_CLAUSE45 | NIXGE_MDIO_OP(NIXGE_MDIO_C45_WRITE) - | NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); +static int nixge_mdio_write_c45(struct mii_bus *bus, int phy_id, + int device, int reg, u16 val) +{ + struct nixge_priv *priv = bus->priv; + u32 status, tmp; + int err; - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_DATA, val); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); - err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, - !status, 10, 1000); - if (err) - dev_err(priv->dev, "timeout setting write command"); - } else { - device = reg & 0x1f; + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_ADDR, reg & 0xffff); - tmp = NIXGE_MDIO_CLAUSE22 | - NIXGE_MDIO_OP(NIXGE_MDIO_C22_WRITE) | - NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); + tmp = NIXGE_MDIO_CLAUSE45 | + NIXGE_MDIO_OP(NIXGE_MDIO_OP_ADDRESS) | + NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_DATA, val); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); - nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_CTRL, 1); - err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, - !status, 10, 1000); - if (err) - dev_err(priv->dev, "timeout setting write command"); + err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, + !status, 10, 1000); + if (err) { + dev_err(priv->dev, "timeout setting address"); + return err; } + tmp = NIXGE_MDIO_CLAUSE45 | NIXGE_MDIO_OP(NIXGE_MDIO_C45_WRITE) | + NIXGE_MDIO_ADDR(phy_id) | NIXGE_MDIO_MMD(device); + + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_DATA, val); + nixge_ctrl_write_reg(priv, NIXGE_REG_MDIO_OP, tmp); + + err = nixge_ctrl_poll_timeout(priv, NIXGE_REG_MDIO_CTRL, status, + !status, 10, 1000); + if (err) + dev_err(priv->dev, "timeout setting write command"); + return err; } @@ -1195,8 +1222,10 @@ static int nixge_mdio_setup(struct nixge_priv *priv, struct device_node *np) snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev)); bus->priv = priv; bus->name = "nixge_mii_bus"; - bus->read = nixge_mdio_read; - bus->write = nixge_mdio_write; + bus->read = nixge_mdio_read_c22; + bus->write = nixge_mdio_write_c22; + bus->read_c45 = nixge_mdio_read_c45; + bus->write_c45 = nixge_mdio_write_c45; bus->parent = priv->dev; priv->mii_bus = bus; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 0848b5529d48..2bf18748581d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -831,7 +831,7 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn, * @p_hwfn: HW device data. * @p_ptt: PTT window for writing the registers. * @vf: VF info data. - * @enable: The actual permision for this VF. + * @enable: The actual permission for this VF. * * In E4, queue zone permission table size is 320x9. There * are 320 VF queues for single engine device (256 for dual diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 27b1663c476e..39d24e07f306 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -12,6 +12,7 @@ #include "rmnet_handlers.h" #include "rmnet_vnd.h" #include "rmnet_private.h" +#include "rmnet_map.h" /* Local Definitions and Declarations */ @@ -39,6 +40,8 @@ static int rmnet_unregister_real_device(struct net_device *real_dev) if (port->nr_rmnet_devs) return -EINVAL; + rmnet_map_tx_aggregate_exit(port); + netdev_rx_handler_unregister(real_dev); kfree(port); @@ -79,6 +82,8 @@ static int rmnet_register_real_device(struct net_device *real_dev, for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++) INIT_HLIST_HEAD(&port->muxed_ep[entry]); + rmnet_map_tx_aggregate_init(port); + netdev_dbg(real_dev, "registered with rmnet\n"); return 0; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index 3d3cba56c516..ed112d51ac5a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -6,6 +6,7 @@ */ #include <linux/skbuff.h> +#include <linux/time.h> #include <net/gro_cells.h> #ifndef _RMNET_CONFIG_H_ @@ -19,6 +20,12 @@ struct rmnet_endpoint { struct hlist_node hlnode; }; +struct rmnet_egress_agg_params { + u32 bytes; + u32 count; + u64 time_nsec; +}; + /* One instance of this structure is instantiated for each real_dev associated * with rmnet. */ @@ -30,6 +37,19 @@ struct rmnet_port { struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; struct net_device *bridge_ep; struct net_device *rmnet_dev; + + /* Egress aggregation information */ + struct rmnet_egress_agg_params egress_agg_params; + /* Protect aggregation related elements */ + spinlock_t agg_lock; + struct sk_buff *skbagg_head; + struct sk_buff *skbagg_tail; + int agg_state; + u8 agg_count; + struct timespec64 agg_time; + struct timespec64 agg_last; + struct hrtimer hrtimer; + struct work_struct agg_wq; }; extern struct rtnl_link_ops rmnet_link_ops; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index a313242a762e..9f3479500f85 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -164,8 +164,18 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, map_header->mux_id = mux_id; - skb->protocol = htons(ETH_P_MAP); + if (READ_ONCE(port->egress_agg_params.count) > 1) { + unsigned int len; + + len = rmnet_map_tx_aggregate(skb, port, orig_dev); + if (likely(len)) { + rmnet_vnd_tx_fixup_len(len, orig_dev); + return -EINPROGRESS; + } + return -ENOMEM; + } + skb->protocol = htons(ETH_P_MAP); return 0; } @@ -235,6 +245,7 @@ void rmnet_egress_handler(struct sk_buff *skb) struct rmnet_port *port; struct rmnet_priv *priv; u8 mux_id; + int err; sk_pacing_shift_update(skb->sk, 8); @@ -247,8 +258,11 @@ void rmnet_egress_handler(struct sk_buff *skb) if (!port) goto drop; - if (rmnet_map_egress_handler(skb, port, mux_id, orig_dev)) + err = rmnet_map_egress_handler(skb, port, mux_id, orig_dev); + if (err == -ENOMEM) goto drop; + else if (err == -EINPROGRESS) + return; rmnet_vnd_tx_fixup(skb, orig_dev); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h index 2b033060fc20..b70284095568 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -53,5 +53,11 @@ void rmnet_map_checksum_uplink_packet(struct sk_buff *skb, struct net_device *orig_dev, int csum_type); int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, u16 len); +unsigned int rmnet_map_tx_aggregate(struct sk_buff *skb, struct rmnet_port *port, + struct net_device *orig_dev); +void rmnet_map_tx_aggregate_init(struct rmnet_port *port); +void rmnet_map_tx_aggregate_exit(struct rmnet_port *port); +void rmnet_map_update_ul_agg_config(struct rmnet_port *port, u32 size, + u32 count, u32 time); #endif /* _RMNET_MAP_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index ba194698cc14..a5e3d1a88305 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -12,6 +12,7 @@ #include "rmnet_config.h" #include "rmnet_map.h" #include "rmnet_private.h" +#include "rmnet_vnd.h" #define RMNET_MAP_DEAGGR_SPACING 64 #define RMNET_MAP_DEAGGR_HEADROOM (RMNET_MAP_DEAGGR_SPACING / 2) @@ -518,3 +519,193 @@ int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, return 0; } + +#define RMNET_AGG_BYPASS_TIME_NSEC 10000000L + +static void reset_aggr_params(struct rmnet_port *port) +{ + port->skbagg_head = NULL; + port->agg_count = 0; + port->agg_state = 0; + memset(&port->agg_time, 0, sizeof(struct timespec64)); +} + +static void rmnet_send_skb(struct rmnet_port *port, struct sk_buff *skb) +{ + if (skb_needs_linearize(skb, port->dev->features)) { + if (unlikely(__skb_linearize(skb))) { + struct rmnet_priv *priv; + + priv = netdev_priv(port->rmnet_dev); + this_cpu_inc(priv->pcpu_stats->stats.tx_drops); + dev_kfree_skb_any(skb); + return; + } + } + + dev_queue_xmit(skb); +} + +static void rmnet_map_flush_tx_packet_work(struct work_struct *work) +{ + struct sk_buff *skb = NULL; + struct rmnet_port *port; + + port = container_of(work, struct rmnet_port, agg_wq); + + spin_lock_bh(&port->agg_lock); + if (likely(port->agg_state == -EINPROGRESS)) { + /* Buffer may have already been shipped out */ + if (likely(port->skbagg_head)) { + skb = port->skbagg_head; + reset_aggr_params(port); + } + port->agg_state = 0; + } + + spin_unlock_bh(&port->agg_lock); + if (skb) + rmnet_send_skb(port, skb); +} + +static enum hrtimer_restart rmnet_map_flush_tx_packet_queue(struct hrtimer *t) +{ + struct rmnet_port *port; + + port = container_of(t, struct rmnet_port, hrtimer); + + schedule_work(&port->agg_wq); + + return HRTIMER_NORESTART; +} + +unsigned int rmnet_map_tx_aggregate(struct sk_buff *skb, struct rmnet_port *port, + struct net_device *orig_dev) +{ + struct timespec64 diff, last; + unsigned int len = skb->len; + struct sk_buff *agg_skb; + int size; + + spin_lock_bh(&port->agg_lock); + memcpy(&last, &port->agg_last, sizeof(struct timespec64)); + ktime_get_real_ts64(&port->agg_last); + + if (!port->skbagg_head) { + /* Check to see if we should agg first. If the traffic is very + * sparse, don't aggregate. + */ +new_packet: + diff = timespec64_sub(port->agg_last, last); + size = port->egress_agg_params.bytes - skb->len; + + if (size < 0) { + /* dropped */ + spin_unlock_bh(&port->agg_lock); + return 0; + } + + if (diff.tv_sec > 0 || diff.tv_nsec > RMNET_AGG_BYPASS_TIME_NSEC || + size == 0) + goto no_aggr; + + port->skbagg_head = skb_copy_expand(skb, 0, size, GFP_ATOMIC); + if (!port->skbagg_head) + goto no_aggr; + + dev_kfree_skb_any(skb); + port->skbagg_head->protocol = htons(ETH_P_MAP); + port->agg_count = 1; + ktime_get_real_ts64(&port->agg_time); + skb_frag_list_init(port->skbagg_head); + goto schedule; + } + diff = timespec64_sub(port->agg_last, port->agg_time); + size = port->egress_agg_params.bytes - port->skbagg_head->len; + + if (skb->len > size) { + agg_skb = port->skbagg_head; + reset_aggr_params(port); + spin_unlock_bh(&port->agg_lock); + hrtimer_cancel(&port->hrtimer); + rmnet_send_skb(port, agg_skb); + spin_lock_bh(&port->agg_lock); + goto new_packet; + } + + if (skb_has_frag_list(port->skbagg_head)) + port->skbagg_tail->next = skb; + else + skb_shinfo(port->skbagg_head)->frag_list = skb; + + port->skbagg_head->len += skb->len; + port->skbagg_head->data_len += skb->len; + port->skbagg_head->truesize += skb->truesize; + port->skbagg_tail = skb; + port->agg_count++; + + if (diff.tv_sec > 0 || diff.tv_nsec > port->egress_agg_params.time_nsec || + port->agg_count >= port->egress_agg_params.count || + port->skbagg_head->len == port->egress_agg_params.bytes) { + agg_skb = port->skbagg_head; + reset_aggr_params(port); + spin_unlock_bh(&port->agg_lock); + hrtimer_cancel(&port->hrtimer); + rmnet_send_skb(port, agg_skb); + return len; + } + +schedule: + if (!hrtimer_active(&port->hrtimer) && port->agg_state != -EINPROGRESS) { + port->agg_state = -EINPROGRESS; + hrtimer_start(&port->hrtimer, + ns_to_ktime(port->egress_agg_params.time_nsec), + HRTIMER_MODE_REL); + } + spin_unlock_bh(&port->agg_lock); + + return len; + +no_aggr: + spin_unlock_bh(&port->agg_lock); + skb->protocol = htons(ETH_P_MAP); + dev_queue_xmit(skb); + + return len; +} + +void rmnet_map_update_ul_agg_config(struct rmnet_port *port, u32 size, + u32 count, u32 time) +{ + spin_lock_bh(&port->agg_lock); + port->egress_agg_params.bytes = size; + WRITE_ONCE(port->egress_agg_params.count, count); + port->egress_agg_params.time_nsec = time * NSEC_PER_USEC; + spin_unlock_bh(&port->agg_lock); +} + +void rmnet_map_tx_aggregate_init(struct rmnet_port *port) +{ + hrtimer_init(&port->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + port->hrtimer.function = rmnet_map_flush_tx_packet_queue; + spin_lock_init(&port->agg_lock); + rmnet_map_update_ul_agg_config(port, 4096, 1, 800); + INIT_WORK(&port->agg_wq, rmnet_map_flush_tx_packet_work); +} + +void rmnet_map_tx_aggregate_exit(struct rmnet_port *port) +{ + hrtimer_cancel(&port->hrtimer); + cancel_work_sync(&port->agg_wq); + + spin_lock_bh(&port->agg_lock); + if (port->agg_state == -EINPROGRESS) { + if (port->skbagg_head) { + dev_kfree_skb_any(port->skbagg_head); + reset_aggr_params(port); + } + + port->agg_state = 0; + } + spin_unlock_bh(&port->agg_lock); +} diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 3f5e6572d20e..046b5f7d8e7c 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -29,7 +29,7 @@ void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev) u64_stats_update_end(&pcpu_ptr->syncp); } -void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev) +void rmnet_vnd_tx_fixup_len(unsigned int len, struct net_device *dev) { struct rmnet_priv *priv = netdev_priv(dev); struct rmnet_pcpu_stats *pcpu_ptr; @@ -38,10 +38,15 @@ void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev) u64_stats_update_begin(&pcpu_ptr->syncp); pcpu_ptr->stats.tx_pkts++; - pcpu_ptr->stats.tx_bytes += skb->len; + pcpu_ptr->stats.tx_bytes += len; u64_stats_update_end(&pcpu_ptr->syncp); } +void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev) +{ + rmnet_vnd_tx_fixup_len(skb->len, dev); +} + /* Network Device Operations */ static netdev_tx_t rmnet_vnd_start_xmit(struct sk_buff *skb, @@ -210,7 +215,52 @@ static void rmnet_get_ethtool_stats(struct net_device *dev, memcpy(data, st, ARRAY_SIZE(rmnet_gstrings_stats) * sizeof(u64)); } +static int rmnet_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct rmnet_priv *priv = netdev_priv(dev); + struct rmnet_port *port; + + port = rmnet_get_port_rtnl(priv->real_dev); + + memset(kernel_coal, 0, sizeof(*kernel_coal)); + kernel_coal->tx_aggr_max_bytes = port->egress_agg_params.bytes; + kernel_coal->tx_aggr_max_frames = port->egress_agg_params.count; + kernel_coal->tx_aggr_time_usecs = div_u64(port->egress_agg_params.time_nsec, + NSEC_PER_USEC); + + return 0; +} + +static int rmnet_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct rmnet_priv *priv = netdev_priv(dev); + struct rmnet_port *port; + + port = rmnet_get_port_rtnl(priv->real_dev); + + if (kernel_coal->tx_aggr_max_frames < 1 || kernel_coal->tx_aggr_max_frames > 64) + return -EINVAL; + + if (kernel_coal->tx_aggr_max_bytes > 32768) + return -EINVAL; + + rmnet_map_update_ul_agg_config(port, kernel_coal->tx_aggr_max_bytes, + kernel_coal->tx_aggr_max_frames, + kernel_coal->tx_aggr_time_usecs); + + return 0; +} + static const struct ethtool_ops rmnet_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_TX_AGGR, + .get_coalesce = rmnet_get_coalesce, + .set_coalesce = rmnet_set_coalesce, .get_ethtool_stats = rmnet_get_ethtool_stats, .get_strings = rmnet_get_strings, .get_sset_count = rmnet_get_sset_count, diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index dc3a4443ef0a..c2b2baf86894 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -16,6 +16,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, struct rmnet_endpoint *ep); void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); +void rmnet_vnd_tx_fixup_len(unsigned int len, struct net_device *dev); void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); void rmnet_vnd_setup(struct net_device *dev); int rmnet_vnd_validate_real_dev_mtu(struct net_device *real_dev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index dadd61bccfe7..45147a1016be 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -576,6 +576,7 @@ struct rtl8169_tc_offsets { enum rtl_flag { RTL_FLAG_TASK_ENABLED = 0, RTL_FLAG_TASK_RESET_PENDING, + RTL_FLAG_TASK_TX_TIMEOUT, RTL_FLAG_MAX }; @@ -3928,7 +3929,7 @@ static void rtl8169_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct rtl8169_private *tp = netdev_priv(dev); - rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING); + rtl_schedule_task(tp, RTL_FLAG_TASK_TX_TIMEOUT); } static int rtl8169_tx_map(struct rtl8169_private *tp, const u32 *opts, u32 len, @@ -4522,6 +4523,7 @@ static void rtl_task(struct work_struct *work) { struct rtl8169_private *tp = container_of(work, struct rtl8169_private, wk.work); + int ret; rtnl_lock(); @@ -4529,7 +4531,27 @@ static void rtl_task(struct work_struct *work) !test_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags)) goto out_unlock; + if (test_and_clear_bit(RTL_FLAG_TASK_TX_TIMEOUT, tp->wk.flags)) { + /* if chip isn't accessible, reset bus to revive it */ + if (RTL_R32(tp, TxConfig) == ~0) { + ret = pci_reset_bus(tp->pci_dev); + if (ret < 0) { + netdev_err(tp->dev, "Can't reset secondary PCI bus, detach NIC\n"); + netif_device_detach(tp->dev); + goto out_unlock; + } + } + + /* ASPM compatibility issues are a typical reason for tx timeouts */ + ret = pci_disable_link_state(tp->pci_dev, PCIE_LINK_STATE_L1 | + PCIE_LINK_STATE_L0S); + if (!ret) + netdev_warn_once(tp->dev, "ASPM disabled on Tx timeout\n"); + goto reset; + } + if (test_and_clear_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags)) { +reset: rtl_reset_work(tp); netif_wake_queue(tp->dev); } diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 6441892636db..885fdb077b62 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1024,34 +1024,18 @@ static int rswitch_etha_set_access(struct rswitch_etha *etha, bool read, return ret; } -static int rswitch_etha_mii_read(struct mii_bus *bus, int addr, int regnum) +static int rswitch_etha_mii_read_c45(struct mii_bus *bus, int addr, int devad, + int regad) { struct rswitch_etha *etha = bus->priv; - int mode, devad, regad; - - mode = regnum & MII_ADDR_C45; - devad = (regnum >> MII_DEVADDR_C45_SHIFT) & 0x1f; - regad = regnum & MII_REGADDR_C45_MASK; - - /* Not support Clause 22 access method */ - if (!mode) - return -EOPNOTSUPP; return rswitch_etha_set_access(etha, true, addr, devad, regad, 0); } -static int rswitch_etha_mii_write(struct mii_bus *bus, int addr, int regnum, u16 val) +static int rswitch_etha_mii_write_c45(struct mii_bus *bus, int addr, int devad, + int regad, u16 val) { struct rswitch_etha *etha = bus->priv; - int mode, devad, regad; - - mode = regnum & MII_ADDR_C45; - devad = (regnum >> MII_DEVADDR_C45_SHIFT) & 0x1f; - regad = regnum & MII_REGADDR_C45_MASK; - - /* Not support Clause 22 access method */ - if (!mode) - return -EOPNOTSUPP; return rswitch_etha_set_access(etha, false, addr, devad, regad, val); } @@ -1142,8 +1126,8 @@ static int rswitch_mii_register(struct rswitch_device *rdev) mii_bus->name = "rswitch_mii"; sprintf(mii_bus->id, "etha%d", rdev->etha->index); mii_bus->priv = rdev->etha; - mii_bus->read = rswitch_etha_mii_read; - mii_bus->write = rswitch_etha_mii_write; + mii_bus->read_c45 = rswitch_etha_mii_read_c45; + mii_bus->write_c45 = rswitch_etha_mii_write_c45; mii_bus->parent = &rdev->priv->pdev->dev; mdio_np = rswitch_get_mdio_node(rdev); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 71a499113308..ed17163d7811 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3044,23 +3044,46 @@ static int sh_mdio_release(struct sh_eth_private *mdp) return 0; } -static int sh_mdiobb_read(struct mii_bus *bus, int phy, int reg) +static int sh_mdiobb_read_c22(struct mii_bus *bus, int phy, int reg) { int res; pm_runtime_get_sync(bus->parent); - res = mdiobb_read(bus, phy, reg); + res = mdiobb_read_c22(bus, phy, reg); pm_runtime_put(bus->parent); return res; } -static int sh_mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) +static int sh_mdiobb_write_c22(struct mii_bus *bus, int phy, int reg, u16 val) { int res; pm_runtime_get_sync(bus->parent); - res = mdiobb_write(bus, phy, reg, val); + res = mdiobb_write_c22(bus, phy, reg, val); + pm_runtime_put(bus->parent); + + return res; +} + +static int sh_mdiobb_read_c45(struct mii_bus *bus, int phy, int devad, int reg) +{ + int res; + + pm_runtime_get_sync(bus->parent); + res = mdiobb_read_c45(bus, phy, devad, reg); + pm_runtime_put(bus->parent); + + return res; +} + +static int sh_mdiobb_write_c45(struct mii_bus *bus, int phy, int devad, + int reg, u16 val) +{ + int res; + + pm_runtime_get_sync(bus->parent); + res = mdiobb_write_c45(bus, phy, devad, reg, val); pm_runtime_put(bus->parent); return res; @@ -3091,8 +3114,10 @@ static int sh_mdio_init(struct sh_eth_private *mdp, return -ENOMEM; /* Wrap accessors with Runtime PM-aware ops */ - mdp->mii_bus->read = sh_mdiobb_read; - mdp->mii_bus->write = sh_mdiobb_write; + mdp->mii_bus->read = sh_mdiobb_read_c22; + mdp->mii_bus->write = sh_mdiobb_write_c22; + mdp->mii_bus->read_c45 = sh_mdiobb_read_c45; + mdp->mii_bus->write_c45 = sh_mdiobb_write_c45; /* Hook up MII support for ethtool */ mdp->mii_bus->name = "sh_mii"; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c index fceb6d637235..0227223c06fa 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c @@ -50,12 +50,12 @@ static void sxgbe_mdio_ctrl_data(struct sxgbe_priv_data *sp, u32 cmd, } static void sxgbe_mdio_c45(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr, - int phyreg, u16 phydata) + int devad, int phyreg, u16 phydata) { u32 reg; /* set mdio address register */ - reg = ((phyreg >> 16) & 0x1f) << 21; + reg = (devad & 0x1f) << 21; reg |= (phyaddr << 16) | (phyreg & 0xffff); writel(reg, sp->ioaddr + sp->hw->mii.addr); @@ -76,8 +76,8 @@ static void sxgbe_mdio_c22(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr, sxgbe_mdio_ctrl_data(sp, cmd, phydata); } -static int sxgbe_mdio_access(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr, - int phyreg, u16 phydata) +static int sxgbe_mdio_access_c22(struct sxgbe_priv_data *sp, u32 cmd, + int phyaddr, int phyreg, u16 phydata) { const struct mii_regs *mii = &sp->hw->mii; int rc; @@ -86,33 +86,46 @@ static int sxgbe_mdio_access(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr, if (rc < 0) return rc; - if (phyreg & MII_ADDR_C45) { - sxgbe_mdio_c45(sp, cmd, phyaddr, phyreg, phydata); - } else { - /* Ports 0-3 only support C22. */ - if (phyaddr >= 4) - return -ENODEV; + /* Ports 0-3 only support C22. */ + if (phyaddr >= 4) + return -ENODEV; - sxgbe_mdio_c22(sp, cmd, phyaddr, phyreg, phydata); - } + sxgbe_mdio_c22(sp, cmd, phyaddr, phyreg, phydata); + + return sxgbe_mdio_busy_wait(sp->ioaddr, mii->data); +} + +static int sxgbe_mdio_access_c45(struct sxgbe_priv_data *sp, u32 cmd, + int phyaddr, int devad, int phyreg, + u16 phydata) +{ + const struct mii_regs *mii = &sp->hw->mii; + int rc; + + rc = sxgbe_mdio_busy_wait(sp->ioaddr, mii->data); + if (rc < 0) + return rc; + + sxgbe_mdio_c45(sp, cmd, phyaddr, devad, phyreg, phydata); return sxgbe_mdio_busy_wait(sp->ioaddr, mii->data); } /** - * sxgbe_mdio_read + * sxgbe_mdio_read_c22 * @bus: points to the mii_bus structure * @phyaddr: address of phy port * @phyreg: address of register with in phy register - * Description: this function used for C45 and C22 MDIO Read + * Description: this function used for C22 MDIO Read */ -static int sxgbe_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg) +static int sxgbe_mdio_read_c22(struct mii_bus *bus, int phyaddr, int phyreg) { struct net_device *ndev = bus->priv; struct sxgbe_priv_data *priv = netdev_priv(ndev); int rc; - rc = sxgbe_mdio_access(priv, SXGBE_SMA_READ_CMD, phyaddr, phyreg, 0); + rc = sxgbe_mdio_access_c22(priv, SXGBE_SMA_READ_CMD, phyaddr, + phyreg, 0); if (rc < 0) return rc; @@ -120,21 +133,63 @@ static int sxgbe_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg) } /** - * sxgbe_mdio_write + * sxgbe_mdio_read_c45 + * @bus: points to the mii_bus structure + * @phyaddr: address of phy port + * @devad: device (MMD) address + * @phyreg: address of register with in phy register + * Description: this function used for C45 MDIO Read + */ +static int sxgbe_mdio_read_c45(struct mii_bus *bus, int phyaddr, int devad, + int phyreg) +{ + struct net_device *ndev = bus->priv; + struct sxgbe_priv_data *priv = netdev_priv(ndev); + int rc; + + rc = sxgbe_mdio_access_c45(priv, SXGBE_SMA_READ_CMD, phyaddr, + devad, phyreg, 0); + if (rc < 0) + return rc; + + return readl(priv->ioaddr + priv->hw->mii.data) & 0xffff; +} + +/** + * sxgbe_mdio_write_c22 + * @bus: points to the mii_bus structure + * @phyaddr: address of phy port + * @phyreg: address of phy registers + * @phydata: data to be written into phy register + * Description: this function is used for C22 MDIO write + */ +static int sxgbe_mdio_write_c22(struct mii_bus *bus, int phyaddr, int phyreg, + u16 phydata) +{ + struct net_device *ndev = bus->priv; + struct sxgbe_priv_data *priv = netdev_priv(ndev); + + return sxgbe_mdio_access_c22(priv, SXGBE_SMA_WRITE_CMD, phyaddr, phyreg, + phydata); +} + +/** + * sxgbe_mdio_write_c45 * @bus: points to the mii_bus structure * @phyaddr: address of phy port * @phyreg: address of phy registers + * @devad: device (MMD) address * @phydata: data to be written into phy register - * Description: this function is used for C45 and C22 MDIO write + * Description: this function is used for C45 MDIO write */ -static int sxgbe_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg, - u16 phydata) +static int sxgbe_mdio_write_c45(struct mii_bus *bus, int phyaddr, int devad, + int phyreg, u16 phydata) { struct net_device *ndev = bus->priv; struct sxgbe_priv_data *priv = netdev_priv(ndev); - return sxgbe_mdio_access(priv, SXGBE_SMA_WRITE_CMD, phyaddr, phyreg, - phydata); + return sxgbe_mdio_access_c45(priv, SXGBE_SMA_WRITE_CMD, phyaddr, + devad, phyreg, phydata); } int sxgbe_mdio_register(struct net_device *ndev) @@ -161,8 +216,10 @@ int sxgbe_mdio_register(struct net_device *ndev) /* assign mii bus fields */ mdio_bus->name = "sxgbe"; - mdio_bus->read = &sxgbe_mdio_read; - mdio_bus->write = &sxgbe_mdio_write; + mdio_bus->read = sxgbe_mdio_read_c22; + mdio_bus->write = sxgbe_mdio_write_c22; + mdio_bus->read_c45 = sxgbe_mdio_read_c45; + mdio_bus->write_c45 = sxgbe_mdio_write_c45; snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-%x", mdio_bus->name, priv->plat->bus_id); mdio_bus->priv = ndev; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index bd52fb7cf486..ac8580f501e2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -31,6 +31,12 @@ #define GPR_ENET_QOS_CLK_TX_CLK_SEL (0x1 << 20) #define GPR_ENET_QOS_RGMII_EN (0x1 << 21) +#define MX93_GPR_ENET_QOS_INTF_MODE_MASK GENMASK(3, 0) +#define MX93_GPR_ENET_QOS_INTF_SEL_MII (0x0 << 1) +#define MX93_GPR_ENET_QOS_INTF_SEL_RMII (0x4 << 1) +#define MX93_GPR_ENET_QOS_INTF_SEL_RGMII (0x1 << 1) +#define MX93_GPR_ENET_QOS_CLK_GEN_EN (0x1 << 0) + struct imx_dwmac_ops { u32 addr_width; bool mac_rgmii_txclk_auto_adj; @@ -90,6 +96,35 @@ imx8dxl_set_intf_mode(struct plat_stmmacenet_data *plat_dat) return ret; } +static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct imx_priv_data *dwmac = plat_dat->bsp_priv; + int val; + + switch (plat_dat->interface) { + case PHY_INTERFACE_MODE_MII: + val = MX93_GPR_ENET_QOS_INTF_SEL_MII; + break; + case PHY_INTERFACE_MODE_RMII: + val = MX93_GPR_ENET_QOS_INTF_SEL_RMII; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + val = MX93_GPR_ENET_QOS_INTF_SEL_RGMII; + break; + default: + dev_dbg(dwmac->dev, "imx dwmac doesn't support %d interface\n", + plat_dat->interface); + return -EINVAL; + } + + val |= MX93_GPR_ENET_QOS_CLK_GEN_EN; + return regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off, + MX93_GPR_ENET_QOS_INTF_MODE_MASK, val); +}; + static int imx_dwmac_clks_config(void *priv, bool enabled) { struct imx_priv_data *dwmac = priv; @@ -188,7 +223,9 @@ imx_dwmac_parse_dt(struct imx_priv_data *dwmac, struct device *dev) } dwmac->clk_mem = NULL; - if (of_machine_is_compatible("fsl,imx8dxl")) { + + if (of_machine_is_compatible("fsl,imx8dxl") || + of_machine_is_compatible("fsl,imx93")) { dwmac->clk_mem = devm_clk_get(dev, "mem"); if (IS_ERR(dwmac->clk_mem)) { dev_err(dev, "failed to get mem clock\n"); @@ -196,10 +233,11 @@ imx_dwmac_parse_dt(struct imx_priv_data *dwmac, struct device *dev) } } - if (of_machine_is_compatible("fsl,imx8mp")) { - /* Binding doc describes the property: - is required by i.MX8MP. - is optional for i.MX8DXL. + if (of_machine_is_compatible("fsl,imx8mp") || + of_machine_is_compatible("fsl,imx93")) { + /* Binding doc describes the propety: + * is required by i.MX8MP, i.MX93. + * is optinoal for i.MX8DXL. */ dwmac->intf_regmap = syscon_regmap_lookup_by_phandle(np, "intf_mode"); if (IS_ERR(dwmac->intf_regmap)) @@ -296,9 +334,16 @@ static struct imx_dwmac_ops imx8dxl_dwmac_data = { .set_intf_mode = imx8dxl_set_intf_mode, }; +static struct imx_dwmac_ops imx93_dwmac_data = { + .addr_width = 32, + .mac_rgmii_txclk_auto_adj = true, + .set_intf_mode = imx93_set_intf_mode, +}; + static const struct of_device_id imx_dwmac_match[] = { { .compatible = "nxp,imx8mp-dwmac-eqos", .data = &imx8mp_dwmac_data }, { .compatible = "nxp,imx8dxl-dwmac-eqos", .data = &imx8dxl_dwmac_data }, + { .compatible = "nxp,imx93-dwmac-eqos", .data = &imx93_dwmac_data }, { } }; MODULE_DEVICE_TABLE(of, imx_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 5f177ea80725..21aaa2730ac8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -45,8 +45,8 @@ #define MII_XGMAC_PA_SHIFT 16 #define MII_XGMAC_DA_SHIFT 21 -static int stmmac_xgmac2_c45_format(struct stmmac_priv *priv, int phyaddr, - int phyreg, u32 *hw_addr) +static void stmmac_xgmac2_c45_format(struct stmmac_priv *priv, int phyaddr, + int devad, int phyreg, u32 *hw_addr) { u32 tmp; @@ -56,19 +56,14 @@ static int stmmac_xgmac2_c45_format(struct stmmac_priv *priv, int phyaddr, writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P); *hw_addr = (phyaddr << MII_XGMAC_PA_SHIFT) | (phyreg & 0xffff); - *hw_addr |= (phyreg >> MII_DEVADDR_C45_SHIFT) << MII_XGMAC_DA_SHIFT; - return 0; + *hw_addr |= devad << MII_XGMAC_DA_SHIFT; } -static int stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr, - int phyreg, u32 *hw_addr) +static void stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr, + int phyreg, u32 *hw_addr) { u32 tmp; - /* HW does not support C22 addr >= 4 */ - if (phyaddr > MII_XGMAC_MAX_C22ADDR) - return -ENODEV; - /* Set port as Clause 22 */ tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P); tmp &= ~MII_XGMAC_C22P_MASK; @@ -76,16 +71,14 @@ static int stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr, writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P); *hw_addr = (phyaddr << MII_XGMAC_PA_SHIFT) | (phyreg & 0x1f); - return 0; } -static int stmmac_xgmac2_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg) +static int stmmac_xgmac2_mdio_read(struct stmmac_priv *priv, u32 addr, + u32 value) { - struct net_device *ndev = bus->priv; - struct stmmac_priv *priv = netdev_priv(ndev); unsigned int mii_address = priv->hw->mii.addr; unsigned int mii_data = priv->hw->mii.data; - u32 tmp, addr, value = MII_XGMAC_BUSY; + u32 tmp; int ret; ret = pm_runtime_resume_and_get(priv->device); @@ -99,20 +92,6 @@ static int stmmac_xgmac2_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg) goto err_disable_clks; } - if (phyreg & MII_ADDR_C45) { - phyreg &= ~MII_ADDR_C45; - - ret = stmmac_xgmac2_c45_format(priv, phyaddr, phyreg, &addr); - if (ret) - goto err_disable_clks; - } else { - ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr); - if (ret) - goto err_disable_clks; - - value |= MII_XGMAC_SADDR; - } - value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift) & priv->hw->mii.clk_csr_mask; value |= MII_XGMAC_READ; @@ -144,14 +123,44 @@ err_disable_clks: return ret; } -static int stmmac_xgmac2_mdio_write(struct mii_bus *bus, int phyaddr, - int phyreg, u16 phydata) +static int stmmac_xgmac2_mdio_read_c22(struct mii_bus *bus, int phyaddr, + int phyreg) { struct net_device *ndev = bus->priv; - struct stmmac_priv *priv = netdev_priv(ndev); + struct stmmac_priv *priv; + u32 addr; + + priv = netdev_priv(ndev); + + /* HW does not support C22 addr >= 4 */ + if (phyaddr > MII_XGMAC_MAX_C22ADDR) + return -ENODEV; + + stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr); + + return stmmac_xgmac2_mdio_read(priv, addr, MII_XGMAC_BUSY); +} + +static int stmmac_xgmac2_mdio_read_c45(struct mii_bus *bus, int phyaddr, + int devad, int phyreg) +{ + struct net_device *ndev = bus->priv; + struct stmmac_priv *priv; + u32 addr; + + priv = netdev_priv(ndev); + + stmmac_xgmac2_c45_format(priv, phyaddr, devad, phyreg, &addr); + + return stmmac_xgmac2_mdio_read(priv, addr, MII_XGMAC_BUSY); +} + +static int stmmac_xgmac2_mdio_write(struct stmmac_priv *priv, u32 addr, + u32 value, u16 phydata) +{ unsigned int mii_address = priv->hw->mii.addr; unsigned int mii_data = priv->hw->mii.data; - u32 addr, tmp, value = MII_XGMAC_BUSY; + u32 tmp; int ret; ret = pm_runtime_resume_and_get(priv->device); @@ -165,20 +174,6 @@ static int stmmac_xgmac2_mdio_write(struct mii_bus *bus, int phyaddr, goto err_disable_clks; } - if (phyreg & MII_ADDR_C45) { - phyreg &= ~MII_ADDR_C45; - - ret = stmmac_xgmac2_c45_format(priv, phyaddr, phyreg, &addr); - if (ret) - goto err_disable_clks; - } else { - ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr); - if (ret) - goto err_disable_clks; - - value |= MII_XGMAC_SADDR; - } - value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift) & priv->hw->mii.clk_csr_mask; value |= phydata; @@ -205,8 +200,63 @@ err_disable_clks: return ret; } +static int stmmac_xgmac2_mdio_write_c22(struct mii_bus *bus, int phyaddr, + int phyreg, u16 phydata) +{ + struct net_device *ndev = bus->priv; + struct stmmac_priv *priv; + u32 addr; + + priv = netdev_priv(ndev); + + /* HW does not support C22 addr >= 4 */ + if (phyaddr > MII_XGMAC_MAX_C22ADDR) + return -ENODEV; + + stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr); + + return stmmac_xgmac2_mdio_write(priv, addr, + MII_XGMAC_BUSY | MII_XGMAC_SADDR, phydata); +} + +static int stmmac_xgmac2_mdio_write_c45(struct mii_bus *bus, int phyaddr, + int devad, int phyreg, u16 phydata) +{ + struct net_device *ndev = bus->priv; + struct stmmac_priv *priv; + u32 addr; + + priv = netdev_priv(ndev); + + stmmac_xgmac2_c45_format(priv, phyaddr, devad, phyreg, &addr); + + return stmmac_xgmac2_mdio_write(priv, addr, MII_XGMAC_BUSY, + phydata); +} + +static int stmmac_mdio_read(struct stmmac_priv *priv, int data, u32 value) +{ + unsigned int mii_address = priv->hw->mii.addr; + unsigned int mii_data = priv->hw->mii.data; + u32 v; + + if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), + 100, 10000)) + return -EBUSY; + + writel(data, priv->ioaddr + mii_data); + writel(value, priv->ioaddr + mii_address); + + if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), + 100, 10000)) + return -EBUSY; + + /* Read the data from the MII data register */ + return readl(priv->ioaddr + mii_data) & MII_DATA_MASK; +} + /** - * stmmac_mdio_read + * stmmac_mdio_read_c22 * @bus: points to the mii_bus structure * @phyaddr: MII addr * @phyreg: MII reg @@ -215,15 +265,12 @@ err_disable_clks: * accessing the PHY registers. * Fortunately, it seems this has no drawback for the 7109 MAC. */ -static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg) +static int stmmac_mdio_read_c22(struct mii_bus *bus, int phyaddr, int phyreg) { struct net_device *ndev = bus->priv; struct stmmac_priv *priv = netdev_priv(ndev); - unsigned int mii_address = priv->hw->mii.addr; - unsigned int mii_data = priv->hw->mii.data; u32 value = MII_BUSY; int data = 0; - u32 v; data = pm_runtime_resume_and_get(priv->device); if (data < 0) @@ -236,60 +283,94 @@ static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg) & priv->hw->mii.clk_csr_mask; if (priv->plat->has_gmac4) { value |= MII_GMAC4_READ; - if (phyreg & MII_ADDR_C45) { - value |= MII_GMAC4_C45E; - value &= ~priv->hw->mii.reg_mask; - value |= ((phyreg >> MII_DEVADDR_C45_SHIFT) << - priv->hw->mii.reg_shift) & - priv->hw->mii.reg_mask; - - data |= (phyreg & MII_REGADDR_C45_MASK) << - MII_GMAC4_REG_ADDR_SHIFT; - } } - if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), - 100, 10000)) { - data = -EBUSY; - goto err_disable_clks; - } + data = stmmac_mdio_read(priv, data, value); - writel(data, priv->ioaddr + mii_data); - writel(value, priv->ioaddr + mii_address); + pm_runtime_put(priv->device); - if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), - 100, 10000)) { - data = -EBUSY; - goto err_disable_clks; + return data; +} + +/** + * stmmac_mdio_read_c45 + * @bus: points to the mii_bus structure + * @phyaddr: MII addr + * @devad: device address to read + * @phyreg: MII reg + * Description: it reads data from the MII register from within the phy device. + * For the 7111 GMAC, we must set the bit 0 in the MII address register while + * accessing the PHY registers. + * Fortunately, it seems this has no drawback for the 7109 MAC. + */ +static int stmmac_mdio_read_c45(struct mii_bus *bus, int phyaddr, int devad, + int phyreg) +{ + struct net_device *ndev = bus->priv; + struct stmmac_priv *priv = netdev_priv(ndev); + u32 value = MII_BUSY; + int data = 0; + + data = pm_runtime_get_sync(priv->device); + if (data < 0) { + pm_runtime_put_noidle(priv->device); + return data; } - /* Read the data from the MII data register */ - data = (int)readl(priv->ioaddr + mii_data) & MII_DATA_MASK; + value |= (phyaddr << priv->hw->mii.addr_shift) + & priv->hw->mii.addr_mask; + value |= (phyreg << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask; + value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift) + & priv->hw->mii.clk_csr_mask; + value |= MII_GMAC4_READ; + value |= MII_GMAC4_C45E; + value &= ~priv->hw->mii.reg_mask; + value |= (devad << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask; + + data |= phyreg << MII_GMAC4_REG_ADDR_SHIFT; + + data = stmmac_mdio_read(priv, data, value); -err_disable_clks: pm_runtime_put(priv->device); return data; } +static int stmmac_mdio_write(struct stmmac_priv *priv, int data, u32 value) +{ + unsigned int mii_address = priv->hw->mii.addr; + unsigned int mii_data = priv->hw->mii.data; + u32 v; + + /* Wait until any existing MII operation is complete */ + if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), + 100, 10000)) + return -EBUSY; + + /* Set the MII address register to write */ + writel(data, priv->ioaddr + mii_data); + writel(value, priv->ioaddr + mii_address); + + /* Wait until any existing MII operation is complete */ + return readl_poll_timeout(priv->ioaddr + mii_address, v, + !(v & MII_BUSY), 100, 10000); +} + /** - * stmmac_mdio_write + * stmmac_mdio_write_c22 * @bus: points to the mii_bus structure * @phyaddr: MII addr * @phyreg: MII reg * @phydata: phy data * Description: it writes the data into the MII register from within the device. */ -static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg, - u16 phydata) +static int stmmac_mdio_write_c22(struct mii_bus *bus, int phyaddr, int phyreg, + u16 phydata) { struct net_device *ndev = bus->priv; struct stmmac_priv *priv = netdev_priv(ndev); - unsigned int mii_address = priv->hw->mii.addr; - unsigned int mii_data = priv->hw->mii.data; int ret, data = phydata; u32 value = MII_BUSY; - u32 v; ret = pm_runtime_resume_and_get(priv->device); if (ret < 0) @@ -301,38 +382,57 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg, value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift) & priv->hw->mii.clk_csr_mask; - if (priv->plat->has_gmac4) { + if (priv->plat->has_gmac4) value |= MII_GMAC4_WRITE; - if (phyreg & MII_ADDR_C45) { - value |= MII_GMAC4_C45E; - value &= ~priv->hw->mii.reg_mask; - value |= ((phyreg >> MII_DEVADDR_C45_SHIFT) << - priv->hw->mii.reg_shift) & - priv->hw->mii.reg_mask; - - data |= (phyreg & MII_REGADDR_C45_MASK) << - MII_GMAC4_REG_ADDR_SHIFT; - } - } else { + else value |= MII_WRITE; - } - /* Wait until any existing MII operation is complete */ - if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), - 100, 10000)) { - ret = -EBUSY; - goto err_disable_clks; + ret = stmmac_mdio_write(priv, data, value); + + pm_runtime_put(priv->device); + + return ret; +} + +/** + * stmmac_mdio_write_c45 + * @bus: points to the mii_bus structure + * @phyaddr: MII addr + * @phyreg: MII reg + * @devad: device address to read + * @phydata: phy data + * Description: it writes the data into the MII register from within the device. + */ +static int stmmac_mdio_write_c45(struct mii_bus *bus, int phyaddr, + int devad, int phyreg, u16 phydata) +{ + struct net_device *ndev = bus->priv; + struct stmmac_priv *priv = netdev_priv(ndev); + int ret, data = phydata; + u32 value = MII_BUSY; + + ret = pm_runtime_get_sync(priv->device); + if (ret < 0) { + pm_runtime_put_noidle(priv->device); + return ret; } - /* Set the MII address register to write */ - writel(data, priv->ioaddr + mii_data); - writel(value, priv->ioaddr + mii_address); + value |= (phyaddr << priv->hw->mii.addr_shift) + & priv->hw->mii.addr_mask; + value |= (phyreg << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask; - /* Wait until any existing MII operation is complete */ - ret = readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY), - 100, 10000); + value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift) + & priv->hw->mii.clk_csr_mask; + + value |= MII_GMAC4_WRITE; + value |= MII_GMAC4_C45E; + value &= ~priv->hw->mii.reg_mask; + value |= (devad << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask; + + data |= phyreg << MII_GMAC4_REG_ADDR_SHIFT; + + ret = stmmac_mdio_write(priv, data, value); -err_disable_clks: pm_runtime_put(priv->device); return ret; @@ -453,12 +553,11 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->name = "stmmac"; - if (priv->plat->has_gmac4) - new_bus->probe_capabilities = MDIOBUS_C22_C45; - if (priv->plat->has_xgmac) { - new_bus->read = &stmmac_xgmac2_mdio_read; - new_bus->write = &stmmac_xgmac2_mdio_write; + new_bus->read = &stmmac_xgmac2_mdio_read_c22; + new_bus->write = &stmmac_xgmac2_mdio_write_c22; + new_bus->read_c45 = &stmmac_xgmac2_mdio_read_c45; + new_bus->write_c45 = &stmmac_xgmac2_mdio_write_c45; /* Right now only C22 phys are supported */ max_addr = MII_XGMAC_MAX_C22ADDR + 1; @@ -468,8 +567,13 @@ int stmmac_mdio_register(struct net_device *ndev) dev_err(dev, "Unsupported phy_addr (max=%d)\n", MII_XGMAC_MAX_C22ADDR); } else { - new_bus->read = &stmmac_mdio_read; - new_bus->write = &stmmac_mdio_write; + new_bus->read = &stmmac_mdio_read_c22; + new_bus->write = &stmmac_mdio_write_c22; + if (priv->plat->has_gmac4) { + new_bus->read_c45 = &stmmac_mdio_read_c45; + new_bus->write_c45 = &stmmac_mdio_write_c45; + } + max_addr = PHY_MAX_ADDR; } @@ -490,7 +594,7 @@ int stmmac_mdio_register(struct net_device *ndev) /* Looks like we need a dummy read for XGMAC only and C45 PHYs */ if (priv->plat->has_xgmac) - stmmac_xgmac2_mdio_read(new_bus, 0, MII_ADDR_C45); + stmmac_xgmac2_mdio_read_c45(new_bus, 0, 0, 0); /* If fixed-link is set, skip PHY scanning */ if (!fwnode) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index ecbde83b5243..c696da89962f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1416,6 +1416,70 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, }; +static void am65_cpsw_disable_phy(struct phy *phy) +{ + phy_power_off(phy); + phy_exit(phy); +} + +static int am65_cpsw_enable_phy(struct phy *phy) +{ + int ret; + + ret = phy_init(phy); + if (ret < 0) + return ret; + + ret = phy_power_on(phy); + if (ret < 0) { + phy_exit(phy); + return ret; + } + + return 0; +} + +static void am65_cpsw_disable_serdes_phy(struct am65_cpsw_common *common) +{ + struct am65_cpsw_port *port; + struct phy *phy; + int i; + + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + phy = port->slave.serdes_phy; + if (phy) + am65_cpsw_disable_phy(phy); + } +} + +static int am65_cpsw_init_serdes_phy(struct device *dev, struct device_node *port_np, + struct am65_cpsw_port *port) +{ + const char *name = "serdes-phy"; + struct phy *phy; + int ret; + + phy = devm_of_phy_get(dev, port_np, name); + if (PTR_ERR(phy) == -ENODEV) + return 0; + if (IS_ERR(phy)) + return PTR_ERR(phy); + + /* Serdes PHY exists. Store it. */ + port->slave.serdes_phy = phy; + + ret = am65_cpsw_enable_phy(phy); + if (ret < 0) + goto err_phy; + + return 0; + +err_phy: + devm_phy_put(dev, phy); + return ret; +} + static void am65_cpsw_nuss_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -1959,6 +2023,11 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) goto of_node_put; } + /* Initialize the Serdes PHY for the port */ + ret = am65_cpsw_init_serdes_phy(dev, port_np, port); + if (ret) + return ret; + port->slave.mac_only = of_property_read_bool(port_np, "ti,mac-only"); @@ -2684,11 +2753,19 @@ static const struct am65_cpsw_pdata j7200_cpswxg_pdata = { .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII), }; +static const struct am65_cpsw_pdata j721e_cpswxg_pdata = { + .quirks = 0, + .ale_dev_id = "am64-cpswxg", + .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, + .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII), +}; + static const struct of_device_id am65_cpsw_nuss_of_mtable[] = { { .compatible = "ti,am654-cpsw-nuss", .data = &am65x_sr1_0}, { .compatible = "ti,j721e-cpsw-nuss", .data = &j721e_pdata}, { .compatible = "ti,am642-cpsw-nuss", .data = &am64x_cpswxg_pdata}, { .compatible = "ti,j7200-cpswxg-nuss", .data = &j7200_cpswxg_pdata}, + { .compatible = "ti,j721e-cpswxg-nuss", .data = &j721e_cpswxg_pdata}, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, am65_cpsw_nuss_of_mtable); @@ -2870,6 +2947,7 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) */ am65_cpsw_nuss_cleanup_ndev(common); am65_cpsw_nuss_phylink_cleanup(common); + am65_cpsw_disable_serdes_phy(common); of_platform_device_destroy(common->mdio_dev, NULL); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 4b75620f8d28..ed26768a6e51 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -32,6 +32,7 @@ struct am65_cpsw_slave_data { struct device_node *phy_node; phy_interface_t phy_if; struct phy *ifphy; + struct phy *serdes_phy; bool rx_pause; bool tx_pause; u8 mac_addr[ETH_ALEN]; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 9535396b28cd..bf0f74b20ba6 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -176,6 +176,10 @@ struct am65_cpts { u32 genf_enable; u32 hw_ts_enable; struct sk_buff_head txq; + bool pps_enabled; + bool pps_present; + u32 pps_hw_ts_idx; + u32 pps_genf_idx; /* context save/restore */ u64 sr_cpts_ns; u64 sr_ktime_ns; @@ -319,8 +323,15 @@ static int am65_cpts_fifo_read(struct am65_cpts *cpts) case AM65_CPTS_EV_HW: pevent.index = am65_cpts_event_get_port(event) - 1; pevent.timestamp = event->timestamp; - pevent.type = PTP_CLOCK_EXTTS; - dev_dbg(cpts->dev, "AM65_CPTS_EV_HW p:%d t:%llu\n", + if (cpts->pps_enabled && pevent.index == cpts->pps_hw_ts_idx) { + pevent.type = PTP_CLOCK_PPSUSR; + pevent.pps_times.ts_real = ns_to_timespec64(pevent.timestamp); + } else { + pevent.type = PTP_CLOCK_EXTTS; + } + dev_dbg(cpts->dev, "AM65_CPTS_EV_HW:%s p:%d t:%llu\n", + pevent.type == PTP_CLOCK_EXTTS ? + "extts" : "pps", pevent.index, event->timestamp); ptp_clock_event(cpts->ptp_clock, &pevent); @@ -394,10 +405,13 @@ static irqreturn_t am65_cpts_interrupt(int irq, void *dev_id) static int am65_cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info); + u32 pps_ctrl_val = 0, pps_ppm_hi = 0, pps_ppm_low = 0; s32 ppb = scaled_ppm_to_ppb(scaled_ppm); + int pps_index = cpts->pps_genf_idx; + u64 adj_period, pps_adj_period; + u32 ctrl_val, ppm_hi, ppm_low; + unsigned long flags; int neg_adj = 0; - u64 adj_period; - u32 val; if (ppb < 0) { neg_adj = 1; @@ -417,17 +431,53 @@ static int am65_cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) mutex_lock(&cpts->ptp_clk_lock); - val = am65_cpts_read32(cpts, control); + ctrl_val = am65_cpts_read32(cpts, control); if (neg_adj) - val |= AM65_CPTS_CONTROL_TS_PPM_DIR; + ctrl_val |= AM65_CPTS_CONTROL_TS_PPM_DIR; else - val &= ~AM65_CPTS_CONTROL_TS_PPM_DIR; - am65_cpts_write32(cpts, val, control); + ctrl_val &= ~AM65_CPTS_CONTROL_TS_PPM_DIR; + + ppm_hi = upper_32_bits(adj_period) & 0x3FF; + ppm_low = lower_32_bits(adj_period); + + if (cpts->pps_enabled) { + pps_ctrl_val = am65_cpts_read32(cpts, genf[pps_index].control); + if (neg_adj) + pps_ctrl_val &= ~BIT(1); + else + pps_ctrl_val |= BIT(1); + + /* GenF PPM will do correction using cpts refclk tick which is + * (cpts->ts_add_val + 1) ns, so GenF length PPM adj period + * need to be corrected. + */ + pps_adj_period = adj_period * (cpts->ts_add_val + 1); + pps_ppm_hi = upper_32_bits(pps_adj_period) & 0x3FF; + pps_ppm_low = lower_32_bits(pps_adj_period); + } - val = upper_32_bits(adj_period) & 0x3FF; - am65_cpts_write32(cpts, val, ts_ppm_hi); - val = lower_32_bits(adj_period); - am65_cpts_write32(cpts, val, ts_ppm_low); + spin_lock_irqsave(&cpts->lock, flags); + + /* All below writes must be done extremely fast: + * - delay between PPM dir and PPM value changes can cause err due old + * PPM correction applied in wrong direction + * - delay between CPTS-clock PPM cfg and GenF PPM cfg can cause err + * due CPTS-clock PPM working with new cfg while GenF PPM cfg still + * with old for short period of time + */ + + am65_cpts_write32(cpts, ctrl_val, control); + am65_cpts_write32(cpts, ppm_hi, ts_ppm_hi); + am65_cpts_write32(cpts, ppm_low, ts_ppm_low); + + if (cpts->pps_enabled) { + am65_cpts_write32(cpts, pps_ctrl_val, genf[pps_index].control); + am65_cpts_write32(cpts, pps_ppm_hi, genf[pps_index].ppm_hi); + am65_cpts_write32(cpts, pps_ppm_low, genf[pps_index].ppm_low); + } + + /* All GenF/EstF can be updated here the same way */ + spin_unlock_irqrestore(&cpts->lock, flags); mutex_unlock(&cpts->ptp_clk_lock); @@ -507,7 +557,13 @@ static void am65_cpts_extts_enable_hw(struct am65_cpts *cpts, u32 index, int on) static int am65_cpts_extts_enable(struct am65_cpts *cpts, u32 index, int on) { - if (!!(cpts->hw_ts_enable & BIT(index)) == !!on) + if (index >= cpts->ptp_info.n_ext_ts) + return -ENXIO; + + if (cpts->pps_present && index == cpts->pps_hw_ts_idx) + return -EINVAL; + + if (((cpts->hw_ts_enable & BIT(index)) >> index) == on) return 0; mutex_lock(&cpts->ptp_clk_lock); @@ -591,6 +647,12 @@ static void am65_cpts_perout_enable_hw(struct am65_cpts *cpts, static int am65_cpts_perout_enable(struct am65_cpts *cpts, struct ptp_perout_request *req, int on) { + if (req->index >= cpts->ptp_info.n_per_out) + return -ENXIO; + + if (cpts->pps_present && req->index == cpts->pps_genf_idx) + return -EINVAL; + if (!!(cpts->genf_enable & BIT(req->index)) == !!on) return 0; @@ -604,6 +666,48 @@ static int am65_cpts_perout_enable(struct am65_cpts *cpts, return 0; } +static int am65_cpts_pps_enable(struct am65_cpts *cpts, int on) +{ + int ret = 0; + struct timespec64 ts; + struct ptp_clock_request rq; + u64 ns; + + if (!cpts->pps_present) + return -EINVAL; + + if (cpts->pps_enabled == !!on) + return 0; + + mutex_lock(&cpts->ptp_clk_lock); + + if (on) { + am65_cpts_extts_enable_hw(cpts, cpts->pps_hw_ts_idx, on); + + ns = am65_cpts_gettime(cpts, NULL); + ts = ns_to_timespec64(ns); + rq.perout.period.sec = 1; + rq.perout.period.nsec = 0; + rq.perout.start.sec = ts.tv_sec + 2; + rq.perout.start.nsec = 0; + rq.perout.index = cpts->pps_genf_idx; + + am65_cpts_perout_enable_hw(cpts, &rq.perout, on); + cpts->pps_enabled = true; + } else { + rq.perout.index = cpts->pps_genf_idx; + am65_cpts_perout_enable_hw(cpts, &rq.perout, on); + am65_cpts_extts_enable_hw(cpts, cpts->pps_hw_ts_idx, on); + cpts->pps_enabled = false; + } + + mutex_unlock(&cpts->ptp_clk_lock); + + dev_dbg(cpts->dev, "%s: pps: %s\n", + __func__, on ? "enabled" : "disabled"); + return ret; +} + static int am65_cpts_ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { @@ -614,6 +718,8 @@ static int am65_cpts_ptp_enable(struct ptp_clock_info *ptp, return am65_cpts_extts_enable(cpts, rq->extts.index, on); case PTP_CLK_REQ_PEROUT: return am65_cpts_perout_enable(cpts, &rq->perout, on); + case PTP_CLK_REQ_PPS: + return am65_cpts_pps_enable(cpts, on); default: break; } @@ -926,6 +1032,23 @@ static int am65_cpts_of_parse(struct am65_cpts *cpts, struct device_node *node) if (!of_property_read_u32(node, "ti,cpts-periodic-outputs", &prop[0])) cpts->genf_num = prop[0]; + if (!of_property_read_u32_array(node, "ti,pps", prop, 2)) { + cpts->pps_present = true; + + if (prop[0] > 7) { + dev_err(cpts->dev, "invalid HWx_TS_PUSH index: %u provided\n", prop[0]); + cpts->pps_present = false; + } + if (prop[1] > 1) { + dev_err(cpts->dev, "invalid GENFy index: %u provided\n", prop[1]); + cpts->pps_present = false; + } + if (cpts->pps_present) { + cpts->pps_hw_ts_idx = prop[0]; + cpts->pps_genf_idx = prop[1]; + } + } + return cpts_of_mux_clk_setup(cpts, node); } @@ -993,6 +1116,8 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, cpts->ptp_info.n_ext_ts = cpts->ext_ts_inputs; if (cpts->genf_num) cpts->ptp_info.n_per_out = cpts->genf_num; + if (cpts->pps_present) + cpts->ptp_info.pps = 1; am65_cpts_set_add_val(cpts); @@ -1028,9 +1153,9 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, return ERR_PTR(ret); } - dev_info(dev, "CPTS ver 0x%08x, freq:%u, add_val:%u\n", + dev_info(dev, "CPTS ver 0x%08x, freq:%u, add_val:%u pps:%d\n", am65_cpts_read32(cpts, idver), - cpts->refclk_freq, cpts->ts_add_val); + cpts->refclk_freq, cpts->ts_add_val, cpts->pps_present); return cpts; diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c index 946b9753ccfb..23169e36a3d4 100644 --- a/drivers/net/ethernet/ti/davinci_mdio.c +++ b/drivers/net/ethernet/ti/davinci_mdio.c @@ -225,7 +225,7 @@ static int davinci_get_mdio_data(struct mdiobb_ctrl *ctrl) return test_bit(MDIO_PIN, ®); } -static int davinci_mdiobb_read(struct mii_bus *bus, int phy, int reg) +static int davinci_mdiobb_read_c22(struct mii_bus *bus, int phy, int reg) { int ret; @@ -233,7 +233,7 @@ static int davinci_mdiobb_read(struct mii_bus *bus, int phy, int reg) if (ret < 0) return ret; - ret = mdiobb_read(bus, phy, reg); + ret = mdiobb_read_c22(bus, phy, reg); pm_runtime_mark_last_busy(bus->parent); pm_runtime_put_autosuspend(bus->parent); @@ -241,8 +241,8 @@ static int davinci_mdiobb_read(struct mii_bus *bus, int phy, int reg) return ret; } -static int davinci_mdiobb_write(struct mii_bus *bus, int phy, int reg, - u16 val) +static int davinci_mdiobb_write_c22(struct mii_bus *bus, int phy, int reg, + u16 val) { int ret; @@ -250,7 +250,41 @@ static int davinci_mdiobb_write(struct mii_bus *bus, int phy, int reg, if (ret < 0) return ret; - ret = mdiobb_write(bus, phy, reg, val); + ret = mdiobb_write_c22(bus, phy, reg, val); + + pm_runtime_mark_last_busy(bus->parent); + pm_runtime_put_autosuspend(bus->parent); + + return ret; +} + +static int davinci_mdiobb_read_c45(struct mii_bus *bus, int phy, int devad, + int reg) +{ + int ret; + + ret = pm_runtime_resume_and_get(bus->parent); + if (ret < 0) + return ret; + + ret = mdiobb_read_c45(bus, phy, devad, reg); + + pm_runtime_mark_last_busy(bus->parent); + pm_runtime_put_autosuspend(bus->parent); + + return ret; +} + +static int davinci_mdiobb_write_c45(struct mii_bus *bus, int phy, int devad, + int reg, u16 val) +{ + int ret; + + ret = pm_runtime_resume_and_get(bus->parent); + if (ret < 0) + return ret; + + ret = mdiobb_write_c45(bus, phy, devad, reg, val); pm_runtime_mark_last_busy(bus->parent); pm_runtime_put_autosuspend(bus->parent); @@ -573,8 +607,10 @@ static int davinci_mdio_probe(struct platform_device *pdev) data->bus->name = dev_name(dev); if (data->manual_mode) { - data->bus->read = davinci_mdiobb_read; - data->bus->write = davinci_mdiobb_write; + data->bus->read = davinci_mdiobb_read_c22; + data->bus->write = davinci_mdiobb_write_c22; + data->bus->read_c45 = davinci_mdiobb_read_c45; + data->bus->write_c45 = davinci_mdiobb_write_c45; data->bus->reset = davinci_mdiobb_reset; dev_info(dev, "Configuring MDIO in manual mode\n"); diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index 86310588c6c1..0922beac3ec0 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -25,6 +25,7 @@ config NGBE tristate "Wangxun(R) GbE PCI Express adapters support" depends on PCI select LIBWX + select PHYLIB help This driver supports Wangxun(R) GbE PCI Express family of adapters. diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index c57dc3238b3f..3d7ba0c0df38 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -2,6 +2,7 @@ /* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ #include <linux/etherdevice.h> +#include <linux/netdevice.h> #include <linux/if_ether.h> #include <linux/iopoll.h> #include <linux/pci.h> @@ -9,18 +10,18 @@ #include "wx_type.h" #include "wx_hw.h" -static void wx_intr_disable(struct wx_hw *wxhw, u64 qmask) +static void wx_intr_disable(struct wx *wx, u64 qmask) { u32 mask; mask = (qmask & 0xFFFFFFFF); if (mask) - wr32(wxhw, WX_PX_IMS(0), mask); + wr32(wx, WX_PX_IMS(0), mask); - if (wxhw->mac.type == wx_mac_sp) { + if (wx->mac.type == wx_mac_sp) { mask = (qmask >> 32); if (mask) - wr32(wxhw, WX_PX_IMS(1), mask); + wr32(wx, WX_PX_IMS(1), mask); } } @@ -28,33 +29,33 @@ static void wx_intr_disable(struct wx_hw *wxhw, u64 qmask) * 1. to be sector address, when implemented erase sector command * 2. to be flash address when implemented read, write flash address */ -static int wx_fmgr_cmd_op(struct wx_hw *wxhw, u32 cmd, u32 cmd_addr) +static int wx_fmgr_cmd_op(struct wx *wx, u32 cmd, u32 cmd_addr) { u32 cmd_val = 0, val = 0; cmd_val = WX_SPI_CMD_CMD(cmd) | WX_SPI_CMD_CLK(WX_SPI_CLK_DIV) | cmd_addr; - wr32(wxhw, WX_SPI_CMD, cmd_val); + wr32(wx, WX_SPI_CMD, cmd_val); return read_poll_timeout(rd32, val, (val & 0x1), 10, 100000, - false, wxhw, WX_SPI_STATUS); + false, wx, WX_SPI_STATUS); } -static int wx_flash_read_dword(struct wx_hw *wxhw, u32 addr, u32 *data) +static int wx_flash_read_dword(struct wx *wx, u32 addr, u32 *data) { int ret = 0; - ret = wx_fmgr_cmd_op(wxhw, WX_SPI_CMD_READ_DWORD, addr); + ret = wx_fmgr_cmd_op(wx, WX_SPI_CMD_READ_DWORD, addr); if (ret < 0) return ret; - *data = rd32(wxhw, WX_SPI_DATA); + *data = rd32(wx, WX_SPI_DATA); return ret; } -int wx_check_flash_load(struct wx_hw *hw, u32 check_bit) +int wx_check_flash_load(struct wx *hw, u32 check_bit) { u32 reg = 0; int err = 0; @@ -73,29 +74,25 @@ int wx_check_flash_load(struct wx_hw *hw, u32 check_bit) } EXPORT_SYMBOL(wx_check_flash_load); -void wx_control_hw(struct wx_hw *wxhw, bool drv) +void wx_control_hw(struct wx *wx, bool drv) { - if (drv) { - /* Let firmware know the driver has taken over */ - wr32m(wxhw, WX_CFG_PORT_CTL, - WX_CFG_PORT_CTL_DRV_LOAD, WX_CFG_PORT_CTL_DRV_LOAD); - } else { - /* Let firmware take over control of hw */ - wr32m(wxhw, WX_CFG_PORT_CTL, - WX_CFG_PORT_CTL_DRV_LOAD, 0); - } + /* True : Let firmware know the driver has taken over + * False : Let firmware take over control of hw + */ + wr32m(wx, WX_CFG_PORT_CTL, WX_CFG_PORT_CTL_DRV_LOAD, + drv ? WX_CFG_PORT_CTL_DRV_LOAD : 0); } EXPORT_SYMBOL(wx_control_hw); /** * wx_mng_present - returns 0 when management capability is present - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure */ -int wx_mng_present(struct wx_hw *wxhw) +int wx_mng_present(struct wx *wx) { u32 fwsm; - fwsm = rd32(wxhw, WX_MIS_ST); + fwsm = rd32(wx, WX_MIS_ST); if (fwsm & WX_MIS_ST_MNG_INIT_DN) return 0; else @@ -108,40 +105,40 @@ static DEFINE_MUTEX(wx_sw_sync_lock); /** * wx_release_sw_sync - Release SW semaphore - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @mask: Mask to specify which semaphore to release * * Releases the SW semaphore for the specified * function (CSR, PHY0, PHY1, EEPROM, Flash) **/ -static void wx_release_sw_sync(struct wx_hw *wxhw, u32 mask) +static void wx_release_sw_sync(struct wx *wx, u32 mask) { mutex_lock(&wx_sw_sync_lock); - wr32m(wxhw, WX_MNG_SWFW_SYNC, mask, 0); + wr32m(wx, WX_MNG_SWFW_SYNC, mask, 0); mutex_unlock(&wx_sw_sync_lock); } /** * wx_acquire_sw_sync - Acquire SW semaphore - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @mask: Mask to specify which semaphore to acquire * * Acquires the SW semaphore for the specified * function (CSR, PHY0, PHY1, EEPROM, Flash) **/ -static int wx_acquire_sw_sync(struct wx_hw *wxhw, u32 mask) +static int wx_acquire_sw_sync(struct wx *wx, u32 mask) { u32 sem = 0; int ret = 0; mutex_lock(&wx_sw_sync_lock); ret = read_poll_timeout(rd32, sem, !(sem & mask), - 5000, 2000000, false, wxhw, WX_MNG_SWFW_SYNC); + 5000, 2000000, false, wx, WX_MNG_SWFW_SYNC); if (!ret) { sem |= mask; - wr32(wxhw, WX_MNG_SWFW_SYNC, sem); + wr32(wx, WX_MNG_SWFW_SYNC, sem); } else { - wx_err(wxhw, "SW Semaphore not granted: 0x%x.\n", sem); + wx_err(wx, "SW Semaphore not granted: 0x%x.\n", sem); } mutex_unlock(&wx_sw_sync_lock); @@ -150,7 +147,7 @@ static int wx_acquire_sw_sync(struct wx_hw *wxhw, u32 mask) /** * wx_host_interface_command - Issue command to manageability block - * @wxhw: pointer to the HW structure + * @wx: pointer to the HW structure * @buffer: contains the command to write and where the return status will * be placed * @length: length of buffer, must be multiple of 4 bytes @@ -162,7 +159,7 @@ static int wx_acquire_sw_sync(struct wx_hw *wxhw, u32 mask) * So we will leave this up to the caller to read back the data * in these cases. **/ -int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, +int wx_host_interface_command(struct wx *wx, u32 *buffer, u32 length, u32 timeout, bool return_data) { u32 hdr_size = sizeof(struct wx_hic_hdr); @@ -172,17 +169,17 @@ int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, u16 buf_len; if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) { - wx_err(wxhw, "Buffer length failure buffersize=%d.\n", length); + wx_err(wx, "Buffer length failure buffersize=%d.\n", length); return -EINVAL; } - status = wx_acquire_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_MB); + status = wx_acquire_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB); if (status != 0) return status; /* Calculate length in DWORDs. We must be DWORD aligned */ if ((length % (sizeof(u32))) != 0) { - wx_err(wxhw, "Buffer length failure, not aligned to dword"); + wx_err(wx, "Buffer length failure, not aligned to dword"); status = -EINVAL; goto rel_out; } @@ -193,38 +190,38 @@ int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, * into the ram area. */ for (i = 0; i < dword_len; i++) { - wr32a(wxhw, WX_MNG_MBOX, i, (__force u32)cpu_to_le32(buffer[i])); + wr32a(wx, WX_MNG_MBOX, i, (__force u32)cpu_to_le32(buffer[i])); /* write flush */ - buf[i] = rd32a(wxhw, WX_MNG_MBOX, i); + buf[i] = rd32a(wx, WX_MNG_MBOX, i); } /* Setting this bit tells the ARC that a new command is pending. */ - wr32m(wxhw, WX_MNG_MBOX_CTL, + wr32m(wx, WX_MNG_MBOX_CTL, WX_MNG_MBOX_CTL_SWRDY, WX_MNG_MBOX_CTL_SWRDY); status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000, - timeout * 1000, false, wxhw, WX_MNG_MBOX_CTL); + timeout * 1000, false, wx, WX_MNG_MBOX_CTL); /* Check command completion */ if (status) { - wx_dbg(wxhw, "Command has failed with no status valid.\n"); + wx_dbg(wx, "Command has failed with no status valid.\n"); - buf[0] = rd32(wxhw, WX_MNG_MBOX); + buf[0] = rd32(wx, WX_MNG_MBOX); if ((buffer[0] & 0xff) != (~buf[0] >> 24)) { status = -EINVAL; goto rel_out; } if ((buf[0] & 0xff0000) >> 16 == 0x80) { - wx_dbg(wxhw, "It's unknown cmd.\n"); + wx_dbg(wx, "It's unknown cmd.\n"); status = -EINVAL; goto rel_out; } - wx_dbg(wxhw, "write value:\n"); + wx_dbg(wx, "write value:\n"); for (i = 0; i < dword_len; i++) - wx_dbg(wxhw, "%x ", buffer[i]); - wx_dbg(wxhw, "read value:\n"); + wx_dbg(wx, "%x ", buffer[i]); + wx_dbg(wx, "read value:\n"); for (i = 0; i < dword_len; i++) - wx_dbg(wxhw, "%x ", buf[i]); + wx_dbg(wx, "%x ", buf[i]); } if (!return_data) @@ -235,7 +232,7 @@ int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, /* first pull in the header so we know the buffer length */ for (bi = 0; bi < dword_len; bi++) { - buffer[bi] = rd32a(wxhw, WX_MNG_MBOX, bi); + buffer[bi] = rd32a(wx, WX_MNG_MBOX, bi); le32_to_cpus(&buffer[bi]); } @@ -245,7 +242,7 @@ int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, goto rel_out; if (length < buf_len + hdr_size) { - wx_err(wxhw, "Buffer not large enough for reply message.\n"); + wx_err(wx, "Buffer not large enough for reply message.\n"); status = -EFAULT; goto rel_out; } @@ -255,12 +252,12 @@ int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, /* Pull in the rest of the buffer (bi is where we left off) */ for (; bi <= dword_len; bi++) { - buffer[bi] = rd32a(wxhw, WX_MNG_MBOX, bi); + buffer[bi] = rd32a(wx, WX_MNG_MBOX, bi); le32_to_cpus(&buffer[bi]); } rel_out: - wx_release_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_MB); + wx_release_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB); return status; } EXPORT_SYMBOL(wx_host_interface_command); @@ -268,13 +265,13 @@ EXPORT_SYMBOL(wx_host_interface_command); /** * wx_read_ee_hostif_data - Read EEPROM word using a host interface cmd * assuming that the semaphore is already obtained. - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @offset: offset of word in the EEPROM to read * @data: word read from the EEPROM * * Reads a 16 bit word from the EEPROM using the hostif. **/ -static int wx_read_ee_hostif_data(struct wx_hw *wxhw, u16 offset, u16 *data) +static int wx_read_ee_hostif_data(struct wx *wx, u16 offset, u16 *data) { struct wx_hic_read_shadow_ram buffer; int status; @@ -289,33 +286,33 @@ static int wx_read_ee_hostif_data(struct wx_hw *wxhw, u16 offset, u16 *data) /* one word */ buffer.length = (__force u16)cpu_to_be16(sizeof(u16)); - status = wx_host_interface_command(wxhw, (u32 *)&buffer, sizeof(buffer), + status = wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), WX_HI_COMMAND_TIMEOUT, false); if (status != 0) return status; - *data = (u16)rd32a(wxhw, WX_MNG_MBOX, FW_NVM_DATA_OFFSET); + *data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET); return status; } /** * wx_read_ee_hostif - Read EEPROM word using a host interface cmd - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @offset: offset of word in the EEPROM to read * @data: word read from the EEPROM * * Reads a 16 bit word from the EEPROM using the hostif. **/ -int wx_read_ee_hostif(struct wx_hw *wxhw, u16 offset, u16 *data) +int wx_read_ee_hostif(struct wx *wx, u16 offset, u16 *data) { int status = 0; - status = wx_acquire_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + status = wx_acquire_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_FLASH); if (status == 0) { - status = wx_read_ee_hostif_data(wxhw, offset, data); - wx_release_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + status = wx_read_ee_hostif_data(wx, offset, data); + wx_release_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_FLASH); } return status; @@ -324,14 +321,14 @@ EXPORT_SYMBOL(wx_read_ee_hostif); /** * wx_read_ee_hostif_buffer- Read EEPROM word(s) using hostif - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @offset: offset of word in the EEPROM to read * @words: number of words * @data: word(s) read from the EEPROM * * Reads a 16 bit word(s) from the EEPROM using the hostif. **/ -int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, +int wx_read_ee_hostif_buffer(struct wx *wx, u16 offset, u16 words, u16 *data) { struct wx_hic_read_shadow_ram buffer; @@ -342,7 +339,7 @@ int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, u32 i; /* Take semaphore for the entire operation. */ - status = wx_acquire_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + status = wx_acquire_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_FLASH); if (status != 0) return status; @@ -361,20 +358,20 @@ int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, buffer.address = (__force u32)cpu_to_be32((offset + current_word) * 2); buffer.length = (__force u16)cpu_to_be16(words_to_read * 2); - status = wx_host_interface_command(wxhw, (u32 *)&buffer, + status = wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), WX_HI_COMMAND_TIMEOUT, false); if (status != 0) { - wx_err(wxhw, "Host interface command failed\n"); + wx_err(wx, "Host interface command failed\n"); goto out; } for (i = 0; i < words_to_read; i++) { u32 reg = WX_MNG_MBOX + (FW_NVM_DATA_OFFSET << 2) + 2 * i; - value = rd32(wxhw, reg); + value = rd32(wx, reg); data[current_word] = (u16)(value & 0xffff); current_word++; i++; @@ -388,7 +385,7 @@ int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, } out: - wx_release_sw_sync(wxhw, WX_MNG_SWFW_SYNC_SW_FLASH); + wx_release_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_FLASH); return status; } EXPORT_SYMBOL(wx_read_ee_hostif_buffer); @@ -416,12 +413,12 @@ static u8 wx_calculate_checksum(u8 *buffer, u32 length) /** * wx_reset_hostif - send reset cmd to fw - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * * Sends reset cmd to firmware through the manageability * block. **/ -int wx_reset_hostif(struct wx_hw *wxhw) +int wx_reset_hostif(struct wx *wx) { struct wx_hic_reset reset_cmd; int ret_val = 0; @@ -430,15 +427,15 @@ int wx_reset_hostif(struct wx_hw *wxhw) reset_cmd.hdr.cmd = FW_RESET_CMD; reset_cmd.hdr.buf_len = FW_RESET_LEN; reset_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; - reset_cmd.lan_id = wxhw->bus.func; - reset_cmd.reset_type = (u16)wxhw->reset_type; + reset_cmd.lan_id = wx->bus.func; + reset_cmd.reset_type = (u16)wx->reset_type; reset_cmd.hdr.checksum = 0; reset_cmd.hdr.checksum = wx_calculate_checksum((u8 *)&reset_cmd, (FW_CEM_HDR_LEN + reset_cmd.hdr.buf_len)); for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { - ret_val = wx_host_interface_command(wxhw, (u32 *)&reset_cmd, + ret_val = wx_host_interface_command(wx, (u32 *)&reset_cmd, sizeof(reset_cmd), WX_HI_COMMAND_TIMEOUT, true); @@ -460,14 +457,14 @@ EXPORT_SYMBOL(wx_reset_hostif); /** * wx_init_eeprom_params - Initialize EEPROM params - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * * Initializes the EEPROM parameters wx_eeprom_info within the * wx_hw struct in order to set up EEPROM access. **/ -void wx_init_eeprom_params(struct wx_hw *wxhw) +void wx_init_eeprom_params(struct wx *wx) { - struct wx_eeprom_info *eeprom = &wxhw->eeprom; + struct wx_eeprom_info *eeprom = &wx->eeprom; u16 eeprom_size; u16 data = 0x80; @@ -475,21 +472,21 @@ void wx_init_eeprom_params(struct wx_hw *wxhw) eeprom->semaphore_delay = 10; eeprom->type = wx_eeprom_none; - if (!(rd32(wxhw, WX_SPI_STATUS) & + if (!(rd32(wx, WX_SPI_STATUS) & WX_SPI_STATUS_FLASH_BYPASS)) { eeprom->type = wx_flash; eeprom_size = 4096; eeprom->word_size = eeprom_size >> 1; - wx_dbg(wxhw, "Eeprom params: type = %d, size = %d\n", + wx_dbg(wx, "Eeprom params: type = %d, size = %d\n", eeprom->type, eeprom->word_size); } } - if (wxhw->mac.type == wx_mac_sp) { - if (wx_read_ee_hostif(wxhw, WX_SW_REGION_PTR, &data)) { - wx_err(wxhw, "NVM Read Error\n"); + if (wx->mac.type == wx_mac_sp) { + if (wx_read_ee_hostif(wx, WX_SW_REGION_PTR, &data)) { + wx_err(wx, "NVM Read Error\n"); return; } data = data >> 1; @@ -501,22 +498,22 @@ EXPORT_SYMBOL(wx_init_eeprom_params); /** * wx_get_mac_addr - Generic get MAC address - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @mac_addr: Adapter MAC address * * Reads the adapter's MAC address from first Receive Address Register (RAR0) * A reset of the adapter must be performed prior to calling this function * in order for the MAC address to have been loaded from the EEPROM into RAR0 **/ -void wx_get_mac_addr(struct wx_hw *wxhw, u8 *mac_addr) +void wx_get_mac_addr(struct wx *wx, u8 *mac_addr) { u32 rar_high; u32 rar_low; u16 i; - wr32(wxhw, WX_PSR_MAC_SWC_IDX, 0); - rar_high = rd32(wxhw, WX_PSR_MAC_SWC_AD_H); - rar_low = rd32(wxhw, WX_PSR_MAC_SWC_AD_L); + wr32(wx, WX_PSR_MAC_SWC_IDX, 0); + rar_high = rd32(wx, WX_PSR_MAC_SWC_AD_H); + rar_low = rd32(wx, WX_PSR_MAC_SWC_AD_L); for (i = 0; i < 2; i++) mac_addr[i] = (u8)(rar_high >> (1 - i) * 8); @@ -528,7 +525,7 @@ EXPORT_SYMBOL(wx_get_mac_addr); /** * wx_set_rar - Set Rx address register - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @index: Receive address register to write * @addr: Address to put into receive address register * @pools: VMDq "set" or "pool" index @@ -536,25 +533,25 @@ EXPORT_SYMBOL(wx_get_mac_addr); * * Puts an ethernet address into a receive address register. **/ -int wx_set_rar(struct wx_hw *wxhw, u32 index, u8 *addr, u64 pools, - u32 enable_addr) +static int wx_set_rar(struct wx *wx, u32 index, u8 *addr, u64 pools, + u32 enable_addr) { - u32 rar_entries = wxhw->mac.num_rar_entries; + u32 rar_entries = wx->mac.num_rar_entries; u32 rar_low, rar_high; /* Make sure we are using a valid rar index range */ if (index >= rar_entries) { - wx_err(wxhw, "RAR index %d is out of range.\n", index); + wx_err(wx, "RAR index %d is out of range.\n", index); return -EINVAL; } /* select the MAC address */ - wr32(wxhw, WX_PSR_MAC_SWC_IDX, index); + wr32(wx, WX_PSR_MAC_SWC_IDX, index); /* setup VMDq pool mapping */ - wr32(wxhw, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF); - if (wxhw->mac.type == wx_mac_sp) - wr32(wxhw, WX_PSR_MAC_SWC_VM_H, pools >> 32); + wr32(wx, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF); + if (wx->mac.type == wx_mac_sp) + wr32(wx, WX_PSR_MAC_SWC_VM_H, pools >> 32); /* HW expects these in little endian so we reverse the byte * order from network order (big endian) to little endian @@ -572,31 +569,30 @@ int wx_set_rar(struct wx_hw *wxhw, u32 index, u8 *addr, u64 pools, if (enable_addr != 0) rar_high |= WX_PSR_MAC_SWC_AD_H_AV; - wr32(wxhw, WX_PSR_MAC_SWC_AD_L, rar_low); - wr32m(wxhw, WX_PSR_MAC_SWC_AD_H, - (WX_PSR_MAC_SWC_AD_H_AD(~0) | - WX_PSR_MAC_SWC_AD_H_ADTYPE(~0) | + wr32(wx, WX_PSR_MAC_SWC_AD_L, rar_low); + wr32m(wx, WX_PSR_MAC_SWC_AD_H, + (WX_PSR_MAC_SWC_AD_H_AD(U16_MAX) | + WX_PSR_MAC_SWC_AD_H_ADTYPE(1) | WX_PSR_MAC_SWC_AD_H_AV), rar_high); return 0; } -EXPORT_SYMBOL(wx_set_rar); /** * wx_clear_rar - Remove Rx address register - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @index: Receive address register to write * * Clears an ethernet address from a receive address register. **/ -int wx_clear_rar(struct wx_hw *wxhw, u32 index) +static int wx_clear_rar(struct wx *wx, u32 index) { - u32 rar_entries = wxhw->mac.num_rar_entries; + u32 rar_entries = wx->mac.num_rar_entries; /* Make sure we are using a valid rar index range */ if (index >= rar_entries) { - wx_err(wxhw, "RAR index %d is out of range.\n", index); + wx_err(wx, "RAR index %d is out of range.\n", index); return -EINVAL; } @@ -604,78 +600,77 @@ int wx_clear_rar(struct wx_hw *wxhw, u32 index) * so save everything except the lower 16 bits that hold part * of the address and the address valid bit. */ - wr32(wxhw, WX_PSR_MAC_SWC_IDX, index); + wr32(wx, WX_PSR_MAC_SWC_IDX, index); - wr32(wxhw, WX_PSR_MAC_SWC_VM_L, 0); - wr32(wxhw, WX_PSR_MAC_SWC_VM_H, 0); + wr32(wx, WX_PSR_MAC_SWC_VM_L, 0); + wr32(wx, WX_PSR_MAC_SWC_VM_H, 0); - wr32(wxhw, WX_PSR_MAC_SWC_AD_L, 0); - wr32m(wxhw, WX_PSR_MAC_SWC_AD_H, - (WX_PSR_MAC_SWC_AD_H_AD(~0) | - WX_PSR_MAC_SWC_AD_H_ADTYPE(~0) | + wr32(wx, WX_PSR_MAC_SWC_AD_L, 0); + wr32m(wx, WX_PSR_MAC_SWC_AD_H, + (WX_PSR_MAC_SWC_AD_H_AD(U16_MAX) | + WX_PSR_MAC_SWC_AD_H_ADTYPE(1) | WX_PSR_MAC_SWC_AD_H_AV), 0); return 0; } -EXPORT_SYMBOL(wx_clear_rar); /** * wx_clear_vmdq - Disassociate a VMDq pool index from a rx address - * @wxhw: pointer to hardware struct + * @wx: pointer to hardware struct * @rar: receive address register index to disassociate * @vmdq: VMDq pool index to remove from the rar **/ -static int wx_clear_vmdq(struct wx_hw *wxhw, u32 rar, u32 __maybe_unused vmdq) +static int wx_clear_vmdq(struct wx *wx, u32 rar, u32 __maybe_unused vmdq) { - u32 rar_entries = wxhw->mac.num_rar_entries; + u32 rar_entries = wx->mac.num_rar_entries; u32 mpsar_lo, mpsar_hi; /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { - wx_err(wxhw, "RAR index %d is out of range.\n", rar); + wx_err(wx, "RAR index %d is out of range.\n", rar); return -EINVAL; } - wr32(wxhw, WX_PSR_MAC_SWC_IDX, rar); - mpsar_lo = rd32(wxhw, WX_PSR_MAC_SWC_VM_L); - mpsar_hi = rd32(wxhw, WX_PSR_MAC_SWC_VM_H); + wr32(wx, WX_PSR_MAC_SWC_IDX, rar); + mpsar_lo = rd32(wx, WX_PSR_MAC_SWC_VM_L); + mpsar_hi = rd32(wx, WX_PSR_MAC_SWC_VM_H); if (!mpsar_lo && !mpsar_hi) return 0; /* was that the last pool using this rar? */ if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0) - wx_clear_rar(wxhw, rar); + wx_clear_rar(wx, rar); return 0; } /** * wx_init_uta_tables - Initialize the Unicast Table Array - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure **/ -static void wx_init_uta_tables(struct wx_hw *wxhw) +static void wx_init_uta_tables(struct wx *wx) { int i; - wx_dbg(wxhw, " Clearing UTA\n"); + wx_dbg(wx, " Clearing UTA\n"); for (i = 0; i < 128; i++) - wr32(wxhw, WX_PSR_UC_TBL(i), 0); + wr32(wx, WX_PSR_UC_TBL(i), 0); } /** * wx_init_rx_addrs - Initializes receive address filters. - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * * Places the MAC address in receive address register 0 and clears the rest * of the receive address registers. Clears the multicast table. Assumes * the receiver is in reset when the routine is called. **/ -void wx_init_rx_addrs(struct wx_hw *wxhw) +void wx_init_rx_addrs(struct wx *wx) { - u32 rar_entries = wxhw->mac.num_rar_entries; + u32 rar_entries = wx->mac.num_rar_entries; u32 psrctl; int i; @@ -683,67 +678,166 @@ void wx_init_rx_addrs(struct wx_hw *wxhw) * to the permanent address. * Otherwise, use the permanent address from the eeprom. */ - if (!is_valid_ether_addr(wxhw->mac.addr)) { + if (!is_valid_ether_addr(wx->mac.addr)) { /* Get the MAC address from the RAR0 for later reference */ - wx_get_mac_addr(wxhw, wxhw->mac.addr); - wx_dbg(wxhw, "Keeping Current RAR0 Addr = %pM\n", wxhw->mac.addr); + wx_get_mac_addr(wx, wx->mac.addr); + wx_dbg(wx, "Keeping Current RAR0 Addr = %pM\n", wx->mac.addr); } else { /* Setup the receive address. */ - wx_dbg(wxhw, "Overriding MAC Address in RAR[0]\n"); - wx_dbg(wxhw, "New MAC Addr = %pM\n", wxhw->mac.addr); + wx_dbg(wx, "Overriding MAC Address in RAR[0]\n"); + wx_dbg(wx, "New MAC Addr = %pM\n", wx->mac.addr); - wx_set_rar(wxhw, 0, wxhw->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV); + wx_set_rar(wx, 0, wx->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV); - if (wxhw->mac.type == wx_mac_sp) { + if (wx->mac.type == wx_mac_sp) { /* clear VMDq pool/queue selection for RAR 0 */ - wx_clear_vmdq(wxhw, 0, WX_CLEAR_VMDQ_ALL); + wx_clear_vmdq(wx, 0, WX_CLEAR_VMDQ_ALL); } } /* Zero out the other receive addresses. */ - wx_dbg(wxhw, "Clearing RAR[1-%d]\n", rar_entries - 1); + wx_dbg(wx, "Clearing RAR[1-%d]\n", rar_entries - 1); for (i = 1; i < rar_entries; i++) { - wr32(wxhw, WX_PSR_MAC_SWC_IDX, i); - wr32(wxhw, WX_PSR_MAC_SWC_AD_L, 0); - wr32(wxhw, WX_PSR_MAC_SWC_AD_H, 0); + wr32(wx, WX_PSR_MAC_SWC_IDX, i); + wr32(wx, WX_PSR_MAC_SWC_AD_L, 0); + wr32(wx, WX_PSR_MAC_SWC_AD_H, 0); } /* Clear the MTA */ - wxhw->addr_ctrl.mta_in_use = 0; - psrctl = rd32(wxhw, WX_PSR_CTL); + wx->addr_ctrl.mta_in_use = 0; + psrctl = rd32(wx, WX_PSR_CTL); psrctl &= ~(WX_PSR_CTL_MO | WX_PSR_CTL_MFE); - psrctl |= wxhw->mac.mc_filter_type << WX_PSR_CTL_MO_SHIFT; - wr32(wxhw, WX_PSR_CTL, psrctl); - wx_dbg(wxhw, " Clearing MTA\n"); - for (i = 0; i < wxhw->mac.mcft_size; i++) - wr32(wxhw, WX_PSR_MC_TBL(i), 0); + psrctl |= wx->mac.mc_filter_type << WX_PSR_CTL_MO_SHIFT; + wr32(wx, WX_PSR_CTL, psrctl); + wx_dbg(wx, " Clearing MTA\n"); + for (i = 0; i < wx->mac.mcft_size; i++) + wr32(wx, WX_PSR_MC_TBL(i), 0); - wx_init_uta_tables(wxhw); + wx_init_uta_tables(wx); } EXPORT_SYMBOL(wx_init_rx_addrs); -void wx_disable_rx(struct wx_hw *wxhw) +static void wx_sync_mac_table(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (wx->mac_table[i].state & WX_MAC_STATE_MODIFIED) { + if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) { + wx_set_rar(wx, i, + wx->mac_table[i].addr, + wx->mac_table[i].pools, + WX_PSR_MAC_SWC_AD_H_AV); + } else { + wx_clear_rar(wx, i); + } + wx->mac_table[i].state &= ~(WX_MAC_STATE_MODIFIED); + } + } +} + +/* this function destroys the first RAR entry */ +void wx_mac_set_default_filter(struct wx *wx, u8 *addr) +{ + memcpy(&wx->mac_table[0].addr, addr, ETH_ALEN); + wx->mac_table[0].pools = 1ULL; + wx->mac_table[0].state = (WX_MAC_STATE_DEFAULT | WX_MAC_STATE_IN_USE); + wx_set_rar(wx, 0, wx->mac_table[0].addr, + wx->mac_table[0].pools, + WX_PSR_MAC_SWC_AD_H_AV); +} +EXPORT_SYMBOL(wx_mac_set_default_filter); + +void wx_flush_sw_mac_table(struct wx *wx) +{ + u32 i; + + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (!(wx->mac_table[i].state & WX_MAC_STATE_IN_USE)) + continue; + + wx->mac_table[i].state |= WX_MAC_STATE_MODIFIED; + wx->mac_table[i].state &= ~WX_MAC_STATE_IN_USE; + memset(wx->mac_table[i].addr, 0, ETH_ALEN); + wx->mac_table[i].pools = 0; + } + wx_sync_mac_table(wx); +} +EXPORT_SYMBOL(wx_flush_sw_mac_table); + +static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool) +{ + u32 i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* search table for addr, if found, set to 0 and sync */ + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (!ether_addr_equal(addr, wx->mac_table[i].addr)) + continue; + + wx->mac_table[i].state |= WX_MAC_STATE_MODIFIED; + wx->mac_table[i].pools &= ~(1ULL << pool); + if (!wx->mac_table[i].pools) { + wx->mac_table[i].state &= ~WX_MAC_STATE_IN_USE; + memset(wx->mac_table[i].addr, 0, ETH_ALEN); + } + wx_sync_mac_table(wx); + return 0; + } + return -ENOMEM; +} + +/** + * wx_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + **/ +int wx_set_mac(struct net_device *netdev, void *p) +{ + struct wx *wx = netdev_priv(netdev); + struct sockaddr *addr = p; + int retval; + + retval = eth_prepare_mac_addr_change(netdev, addr); + if (retval) + return retval; + + wx_del_mac_filter(wx, wx->mac.addr, 0); + eth_hw_addr_set(netdev, addr->sa_data); + memcpy(wx->mac.addr, addr->sa_data, netdev->addr_len); + + wx_mac_set_default_filter(wx, wx->mac.addr); + + return 0; +} +EXPORT_SYMBOL(wx_set_mac); + +void wx_disable_rx(struct wx *wx) { u32 pfdtxgswc; u32 rxctrl; - rxctrl = rd32(wxhw, WX_RDB_PB_CTL); + rxctrl = rd32(wx, WX_RDB_PB_CTL); if (rxctrl & WX_RDB_PB_CTL_RXEN) { - pfdtxgswc = rd32(wxhw, WX_PSR_CTL); + pfdtxgswc = rd32(wx, WX_PSR_CTL); if (pfdtxgswc & WX_PSR_CTL_SW_EN) { pfdtxgswc &= ~WX_PSR_CTL_SW_EN; - wr32(wxhw, WX_PSR_CTL, pfdtxgswc); - wxhw->mac.set_lben = true; + wr32(wx, WX_PSR_CTL, pfdtxgswc); + wx->mac.set_lben = true; } else { - wxhw->mac.set_lben = false; + wx->mac.set_lben = false; } rxctrl &= ~WX_RDB_PB_CTL_RXEN; - wr32(wxhw, WX_RDB_PB_CTL, rxctrl); + wr32(wx, WX_RDB_PB_CTL, rxctrl); - if (!(((wxhw->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || - ((wxhw->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) { + if (!(((wx->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || + ((wx->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) { /* disable mac receiver */ - wr32m(wxhw, WX_MAC_RX_CFG, + wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, 0); } } @@ -752,28 +846,28 @@ EXPORT_SYMBOL(wx_disable_rx); /** * wx_disable_pcie_master - Disable PCI-express master access - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * * Disables PCI-Express master access and verifies there are no pending * requests. **/ -int wx_disable_pcie_master(struct wx_hw *wxhw) +int wx_disable_pcie_master(struct wx *wx) { int status = 0; u32 val; /* Always set this bit to ensure any future transactions are blocked */ - pci_clear_master(wxhw->pdev); + pci_clear_master(wx->pdev); /* Exit if master requests are blocked */ - if (!(rd32(wxhw, WX_PX_TRANSACTION_PENDING))) + if (!(rd32(wx, WX_PX_TRANSACTION_PENDING))) return 0; /* Poll for master request bit to clear */ status = read_poll_timeout(rd32, val, !val, 100, WX_PCI_MASTER_DISABLE_TIMEOUT, - false, wxhw, WX_PX_TRANSACTION_PENDING); + false, wx, WX_PX_TRANSACTION_PENDING); if (status < 0) - wx_err(wxhw, "PCIe transaction pending bit did not clear.\n"); + wx_err(wx, "PCIe transaction pending bit did not clear.\n"); return status; } @@ -781,106 +875,106 @@ EXPORT_SYMBOL(wx_disable_pcie_master); /** * wx_stop_adapter - Generic stop Tx/Rx units - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * * Sets the adapter_stopped flag within wx_hw struct. Clears interrupts, * disables transmit and receive units. The adapter_stopped flag is used by * the shared code and drivers to determine if the adapter is in a stopped * state and should not touch the hardware. **/ -int wx_stop_adapter(struct wx_hw *wxhw) +int wx_stop_adapter(struct wx *wx) { u16 i; /* Set the adapter_stopped flag so other driver functions stop touching * the hardware */ - wxhw->adapter_stopped = true; + wx->adapter_stopped = true; /* Disable the receive unit */ - wx_disable_rx(wxhw); + wx_disable_rx(wx); /* Set interrupt mask to stop interrupts from being generated */ - wx_intr_disable(wxhw, WX_INTR_ALL); + wx_intr_disable(wx, WX_INTR_ALL); /* Clear any pending interrupts, flush previous writes */ - wr32(wxhw, WX_PX_MISC_IC, 0xffffffff); - wr32(wxhw, WX_BME_CTL, 0x3); + wr32(wx, WX_PX_MISC_IC, 0xffffffff); + wr32(wx, WX_BME_CTL, 0x3); /* Disable the transmit unit. Each queue must be disabled. */ - for (i = 0; i < wxhw->mac.max_tx_queues; i++) { - wr32m(wxhw, WX_PX_TR_CFG(i), + for (i = 0; i < wx->mac.max_tx_queues; i++) { + wr32m(wx, WX_PX_TR_CFG(i), WX_PX_TR_CFG_SWFLSH | WX_PX_TR_CFG_ENABLE, WX_PX_TR_CFG_SWFLSH); } /* Disable the receive unit by stopping each queue */ - for (i = 0; i < wxhw->mac.max_rx_queues; i++) { - wr32m(wxhw, WX_PX_RR_CFG(i), + for (i = 0; i < wx->mac.max_rx_queues; i++) { + wr32m(wx, WX_PX_RR_CFG(i), WX_PX_RR_CFG_RR_EN, 0); } /* flush all queues disables */ - WX_WRITE_FLUSH(wxhw); + WX_WRITE_FLUSH(wx); /* Prevent the PCI-E bus from hanging by disabling PCI-E master * access and verify no pending requests */ - return wx_disable_pcie_master(wxhw); + return wx_disable_pcie_master(wx); } EXPORT_SYMBOL(wx_stop_adapter); -void wx_reset_misc(struct wx_hw *wxhw) +void wx_reset_misc(struct wx *wx) { int i; /* receive packets that size > 2048 */ - wr32m(wxhw, WX_MAC_RX_CFG, WX_MAC_RX_CFG_JE, WX_MAC_RX_CFG_JE); + wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_JE, WX_MAC_RX_CFG_JE); /* clear counters on read */ - wr32m(wxhw, WX_MMC_CONTROL, + wr32m(wx, WX_MMC_CONTROL, WX_MMC_CONTROL_RSTONRD, WX_MMC_CONTROL_RSTONRD); - wr32m(wxhw, WX_MAC_RX_FLOW_CTRL, + wr32m(wx, WX_MAC_RX_FLOW_CTRL, WX_MAC_RX_FLOW_CTRL_RFE, WX_MAC_RX_FLOW_CTRL_RFE); - wr32(wxhw, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); + wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); - wr32m(wxhw, WX_MIS_RST_ST, + wr32m(wx, WX_MIS_RST_ST, WX_MIS_RST_ST_RST_INIT, 0x1E00); /* errata 4: initialize mng flex tbl and wakeup flex tbl*/ - wr32(wxhw, WX_PSR_MNG_FLEX_SEL, 0); + wr32(wx, WX_PSR_MNG_FLEX_SEL, 0); for (i = 0; i < 16; i++) { - wr32(wxhw, WX_PSR_MNG_FLEX_DW_L(i), 0); - wr32(wxhw, WX_PSR_MNG_FLEX_DW_H(i), 0); - wr32(wxhw, WX_PSR_MNG_FLEX_MSK(i), 0); + wr32(wx, WX_PSR_MNG_FLEX_DW_L(i), 0); + wr32(wx, WX_PSR_MNG_FLEX_DW_H(i), 0); + wr32(wx, WX_PSR_MNG_FLEX_MSK(i), 0); } - wr32(wxhw, WX_PSR_LAN_FLEX_SEL, 0); + wr32(wx, WX_PSR_LAN_FLEX_SEL, 0); for (i = 0; i < 16; i++) { - wr32(wxhw, WX_PSR_LAN_FLEX_DW_L(i), 0); - wr32(wxhw, WX_PSR_LAN_FLEX_DW_H(i), 0); - wr32(wxhw, WX_PSR_LAN_FLEX_MSK(i), 0); + wr32(wx, WX_PSR_LAN_FLEX_DW_L(i), 0); + wr32(wx, WX_PSR_LAN_FLEX_DW_H(i), 0); + wr32(wx, WX_PSR_LAN_FLEX_MSK(i), 0); } /* set pause frame dst mac addr */ - wr32(wxhw, WX_RDB_PFCMACDAL, 0xC2000001); - wr32(wxhw, WX_RDB_PFCMACDAH, 0x0180); + wr32(wx, WX_RDB_PFCMACDAL, 0xC2000001); + wr32(wx, WX_RDB_PFCMACDAH, 0x0180); } EXPORT_SYMBOL(wx_reset_misc); /** * wx_get_pcie_msix_counts - Gets MSI-X vector count - * @wxhw: pointer to hardware structure + * @wx: pointer to hardware structure * @msix_count: number of MSI interrupts that can be obtained * @max_msix_count: number of MSI interrupts that mac need * * Read PCIe configuration space, and get the MSI-X vector count from * the capabilities table. **/ -int wx_get_pcie_msix_counts(struct wx_hw *wxhw, u16 *msix_count, u16 max_msix_count) +int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count) { - struct pci_dev *pdev = wxhw->pdev; + struct pci_dev *pdev = wx->pdev; struct device *dev = &pdev->dev; int pos; @@ -904,31 +998,39 @@ int wx_get_pcie_msix_counts(struct wx_hw *wxhw, u16 *msix_count, u16 max_msix_co } EXPORT_SYMBOL(wx_get_pcie_msix_counts); -int wx_sw_init(struct wx_hw *wxhw) +int wx_sw_init(struct wx *wx) { - struct pci_dev *pdev = wxhw->pdev; + struct pci_dev *pdev = wx->pdev; u32 ssid = 0; int err = 0; - wxhw->vendor_id = pdev->vendor; - wxhw->device_id = pdev->device; - wxhw->revision_id = pdev->revision; - wxhw->oem_svid = pdev->subsystem_vendor; - wxhw->oem_ssid = pdev->subsystem_device; - wxhw->bus.device = PCI_SLOT(pdev->devfn); - wxhw->bus.func = PCI_FUNC(pdev->devfn); - - if (wxhw->oem_svid == PCI_VENDOR_ID_WANGXUN) { - wxhw->subsystem_vendor_id = pdev->subsystem_vendor; - wxhw->subsystem_device_id = pdev->subsystem_device; + wx->vendor_id = pdev->vendor; + wx->device_id = pdev->device; + wx->revision_id = pdev->revision; + wx->oem_svid = pdev->subsystem_vendor; + wx->oem_ssid = pdev->subsystem_device; + wx->bus.device = PCI_SLOT(pdev->devfn); + wx->bus.func = PCI_FUNC(pdev->devfn); + + if (wx->oem_svid == PCI_VENDOR_ID_WANGXUN) { + wx->subsystem_vendor_id = pdev->subsystem_vendor; + wx->subsystem_device_id = pdev->subsystem_device; } else { - err = wx_flash_read_dword(wxhw, 0xfffdc, &ssid); + err = wx_flash_read_dword(wx, 0xfffdc, &ssid); if (!err) - wxhw->subsystem_device_id = swab16((u16)ssid); + wx->subsystem_device_id = swab16((u16)ssid); return err; } + wx->mac_table = kcalloc(wx->mac.num_rar_entries, + sizeof(struct wx_mac_addr), + GFP_KERNEL); + if (!wx->mac_table) { + wx_err(wx, "mac_table allocation failed\n"); + return -ENOMEM; + } + return 0; } EXPORT_SYMBOL(wx_sw_init); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index a0652f5e9939..803983546f3a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -4,25 +4,26 @@ #ifndef _WX_HW_H_ #define _WX_HW_H_ -int wx_check_flash_load(struct wx_hw *hw, u32 check_bit); -void wx_control_hw(struct wx_hw *wxhw, bool drv); -int wx_mng_present(struct wx_hw *wxhw); -int wx_host_interface_command(struct wx_hw *wxhw, u32 *buffer, +int wx_check_flash_load(struct wx *wx, u32 check_bit); +void wx_control_hw(struct wx *wx, bool drv); +int wx_mng_present(struct wx *wx); +int wx_host_interface_command(struct wx *wx, u32 *buffer, u32 length, u32 timeout, bool return_data); -int wx_read_ee_hostif(struct wx_hw *wxhw, u16 offset, u16 *data); -int wx_read_ee_hostif_buffer(struct wx_hw *wxhw, +int wx_read_ee_hostif(struct wx *wx, u16 offset, u16 *data); +int wx_read_ee_hostif_buffer(struct wx *wx, u16 offset, u16 words, u16 *data); -int wx_reset_hostif(struct wx_hw *wxhw); -void wx_init_eeprom_params(struct wx_hw *wxhw); -void wx_get_mac_addr(struct wx_hw *wxhw, u8 *mac_addr); -int wx_set_rar(struct wx_hw *wxhw, u32 index, u8 *addr, u64 pools, u32 enable_addr); -int wx_clear_rar(struct wx_hw *wxhw, u32 index); -void wx_init_rx_addrs(struct wx_hw *wxhw); -void wx_disable_rx(struct wx_hw *wxhw); -int wx_disable_pcie_master(struct wx_hw *wxhw); -int wx_stop_adapter(struct wx_hw *wxhw); -void wx_reset_misc(struct wx_hw *wxhw); -int wx_get_pcie_msix_counts(struct wx_hw *wxhw, u16 *msix_count, u16 max_msix_count); -int wx_sw_init(struct wx_hw *wxhw); +int wx_reset_hostif(struct wx *wx); +void wx_init_eeprom_params(struct wx *wx); +void wx_get_mac_addr(struct wx *wx, u8 *mac_addr); +void wx_init_rx_addrs(struct wx *wx); +void wx_mac_set_default_filter(struct wx *wx, u8 *addr); +void wx_flush_sw_mac_table(struct wx *wx); +int wx_set_mac(struct net_device *netdev, void *p); +void wx_disable_rx(struct wx *wx); +int wx_disable_pcie_master(struct wx *wx); +int wx_stop_adapter(struct wx *wx); +void wx_reset_misc(struct wx *wx); +int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count); +int wx_sw_init(struct wx *wx); #endif /* _WX_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 1cbeef8230bf..c86a37914d43 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -4,6 +4,8 @@ #ifndef _WX_TYPE_H_ #define _WX_TYPE_H_ +#include <linux/bitfield.h> + /* Vendor ID */ #ifndef PCI_VENDOR_ID_WANGXUN #define PCI_VENDOR_ID_WANGXUN 0x8088 @@ -36,12 +38,11 @@ #define WX_SPI_CMD 0x10104 #define WX_SPI_CMD_READ_DWORD 0x1 #define WX_SPI_CLK_DIV 0x3 -#define WX_SPI_CMD_CMD(_v) (((_v) & 0x7) << 28) -#define WX_SPI_CMD_CLK(_v) (((_v) & 0x7) << 25) -#define WX_SPI_CMD_ADDR(_v) (((_v) & 0xFFFFFF)) +#define WX_SPI_CMD_CMD(_v) FIELD_PREP(GENMASK(30, 28), _v) +#define WX_SPI_CMD_CLK(_v) FIELD_PREP(GENMASK(27, 25), _v) +#define WX_SPI_CMD_ADDR(_v) FIELD_PREP(GENMASK(23, 0), _v) #define WX_SPI_DATA 0x10108 #define WX_SPI_DATA_BYPASS BIT(31) -#define WX_SPI_DATA_STATUS(_v) (((_v) & 0xFF) << 16) #define WX_SPI_DATA_OP_DONE BIT(0) #define WX_SPI_STATUS 0x1010C #define WX_SPI_STATUS_OPDONE BIT(0) @@ -113,8 +114,8 @@ /* mac switcher */ #define WX_PSR_MAC_SWC_AD_L 0x16200 #define WX_PSR_MAC_SWC_AD_H 0x16204 -#define WX_PSR_MAC_SWC_AD_H_AD(v) (((v) & 0xFFFF)) -#define WX_PSR_MAC_SWC_AD_H_ADTYPE(v) (((v) & 0x1) << 30) +#define WX_PSR_MAC_SWC_AD_H_AD(v) FIELD_PREP(U16_MAX, v) +#define WX_PSR_MAC_SWC_AD_H_ADTYPE(v) FIELD_PREP(BIT(30), v) #define WX_PSR_MAC_SWC_AD_H_AV BIT(31) #define WX_PSR_MAC_SWC_VM_L 0x16208 #define WX_PSR_MAC_SWC_VM_H 0x1620C @@ -133,11 +134,14 @@ /************************************* ETH MAC *****************************/ #define WX_MAC_TX_CFG 0x11000 #define WX_MAC_TX_CFG_TE BIT(0) +#define WX_MAC_TX_CFG_SPEED_MASK GENMASK(30, 29) +#define WX_MAC_TX_CFG_SPEED_1G FIELD_PREP(WX_MAC_TX_CFG_SPEED_MASK, 3) #define WX_MAC_RX_CFG 0x11004 #define WX_MAC_RX_CFG_RE BIT(0) #define WX_MAC_RX_CFG_JE BIT(8) #define WX_MAC_PKT_FLT 0x11008 #define WX_MAC_PKT_FLT_PR BIT(0) /* promiscuous mode */ +#define WX_MAC_WDG_TIMEOUT 0x1100C #define WX_MAC_RX_FLOW_CTRL 0x11090 #define WX_MAC_RX_FLOW_CTRL_RFE BIT(0) /* receive fc enable */ #define WX_MMC_CONTROL 0x11800 @@ -185,6 +189,12 @@ #define WX_SW_REGION_PTR 0x1C +#define WX_MAC_STATE_DEFAULT 0x1 +#define WX_MAC_STATE_MODIFIED 0x2 +#define WX_MAC_STATE_IN_USE 0x4 + +#define WX_CFG_PORT_ST 0x14404 + /* Host Interface Command Structures */ struct wx_hic_hdr { u8 cmd; @@ -249,6 +259,12 @@ enum wx_mac_type { wx_mac_em }; +enum em_mac_type { + em_mac_type_unknown = 0, + em_mac_type_mdi, + em_mac_type_rgmii +}; + struct wx_mac_info { enum wx_mac_type type; bool set_lben; @@ -284,19 +300,28 @@ struct wx_addr_filter_info { bool user_set_promisc; }; +struct wx_mac_addr { + u8 addr[ETH_ALEN]; + u16 state; /* bitmask */ + u64 pools; +}; + enum wx_reset_type { WX_LAN_RESET = 0, WX_SW_RESET, WX_GLOBAL_RESET }; -struct wx_hw { +struct wx { u8 __iomem *hw_addr; struct pci_dev *pdev; + struct net_device *netdev; struct wx_bus_info bus; struct wx_mac_info mac; + enum em_mac_type mac_type; struct wx_eeprom_info eeprom; struct wx_addr_filter_info addr_ctrl; + struct wx_mac_addr *mac_table; u16 device_id; u16 vendor_id; u16 subsystem_device_id; @@ -304,8 +329,45 @@ struct wx_hw { u8 revision_id; u16 oem_ssid; u16 oem_svid; + u16 msg_enable; bool adapter_stopped; + char eeprom_id[32]; enum wx_reset_type reset_type; + + /* PHY stuff */ + unsigned int link; + int speed; + int duplex; + struct phy_device *phydev; + + bool wol_enabled; + bool ncsi_enabled; + bool gpio_ctrl; + + /* Tx fast path data */ + int num_tx_queues; + u16 tx_itr_setting; + u16 tx_work_limit; + + /* Rx fast path data */ + int num_rx_queues; + u16 rx_itr_setting; + u16 rx_work_limit; + + int num_q_vectors; /* current number of q_vectors for device */ + int max_q_vectors; /* upper limit of q_vectors for device */ + + u32 tx_ring_count; + u32 rx_ring_count; + +#define WX_MAX_RETA_ENTRIES 128 + u8 rss_indir_tbl[WX_MAX_RETA_ENTRIES]; + +#define WX_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ + u32 *rss_key; + u32 wol; + + u16 bd_number; }; #define WX_INTR_ALL (~0ULL) @@ -319,23 +381,23 @@ struct wx_hw { wr32((a), (reg) + ((off) << 2), (val)) static inline u32 -rd32m(struct wx_hw *wxhw, u32 reg, u32 mask) +rd32m(struct wx *wx, u32 reg, u32 mask) { u32 val; - val = rd32(wxhw, reg); + val = rd32(wx, reg); return val & mask; } static inline void -wr32m(struct wx_hw *wxhw, u32 reg, u32 mask, u32 field) +wr32m(struct wx *wx, u32 reg, u32 mask, u32 field) { u32 val; - val = rd32(wxhw, reg); + val = rd32(wx, reg); val = ((val & ~mask) | (field & mask)); - wr32(wxhw, reg, val); + wr32(wx, reg, val); } /* On some domestic CPU platforms, sometimes IO is not synchronized with @@ -343,10 +405,10 @@ wr32m(struct wx_hw *wxhw, u32 reg, u32 mask, u32 field) */ #define WX_WRITE_FLUSH(H) rd32(H, WX_MIS_PWR) -#define wx_err(wxhw, fmt, arg...) \ - dev_err(&(wxhw)->pdev->dev, fmt, ##arg) +#define wx_err(wx, fmt, arg...) \ + dev_err(&(wx)->pdev->dev, fmt, ##arg) -#define wx_dbg(wxhw, fmt, arg...) \ - dev_dbg(&(wxhw)->pdev->dev, fmt, ##arg) +#define wx_dbg(wx, fmt, arg...) \ + dev_dbg(&(wx)->pdev->dev, fmt, ##arg) #endif /* _WX_TYPE_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/Makefile b/drivers/net/ethernet/wangxun/ngbe/Makefile index 391c2cbc1bb4..50fdca87d2a5 100644 --- a/drivers/net/ethernet/wangxun/ngbe/Makefile +++ b/drivers/net/ethernet/wangxun/ngbe/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_NGBE) += ngbe.o -ngbe-objs := ngbe_main.o ngbe_hw.o +ngbe-objs := ngbe_main.o ngbe_hw.o ngbe_mdio.o diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe.h b/drivers/net/ethernet/wangxun/ngbe/ngbe.h deleted file mode 100644 index af147ca8605c..000000000000 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe.h +++ /dev/null @@ -1,79 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. */ - -#ifndef _NGBE_H_ -#define _NGBE_H_ - -#include "ngbe_type.h" - -#define NGBE_MAX_FDIR_INDICES 7 - -#define NGBE_MAX_RX_QUEUES (NGBE_MAX_FDIR_INDICES + 1) -#define NGBE_MAX_TX_QUEUES (NGBE_MAX_FDIR_INDICES + 1) - -#define NGBE_ETH_LENGTH_OF_ADDRESS 6 -#define NGBE_MAX_MSIX_VECTORS 0x09 -#define NGBE_RAR_ENTRIES 32 - -/* TX/RX descriptor defines */ -#define NGBE_DEFAULT_TXD 512 /* default ring size */ -#define NGBE_DEFAULT_TX_WORK 256 -#define NGBE_MAX_TXD 8192 -#define NGBE_MIN_TXD 128 - -#define NGBE_DEFAULT_RXD 512 /* default ring size */ -#define NGBE_DEFAULT_RX_WORK 256 -#define NGBE_MAX_RXD 8192 -#define NGBE_MIN_RXD 128 - -#define NGBE_MAC_STATE_DEFAULT 0x1 -#define NGBE_MAC_STATE_MODIFIED 0x2 -#define NGBE_MAC_STATE_IN_USE 0x4 - -struct ngbe_mac_addr { - u8 addr[ETH_ALEN]; - u16 state; /* bitmask */ - u64 pools; -}; - -/* board specific private data structure */ -struct ngbe_adapter { - u8 __iomem *io_addr; /* Mainly for iounmap use */ - /* OS defined structs */ - struct net_device *netdev; - struct pci_dev *pdev; - - /* structs defined in ngbe_hw.h */ - struct ngbe_hw hw; - struct ngbe_mac_addr *mac_table; - u16 msg_enable; - - /* Tx fast path data */ - int num_tx_queues; - u16 tx_itr_setting; - u16 tx_work_limit; - - /* Rx fast path data */ - int num_rx_queues; - u16 rx_itr_setting; - u16 rx_work_limit; - - int num_q_vectors; /* current number of q_vectors for device */ - int max_q_vectors; /* upper limit of q_vectors for device */ - - u32 tx_ring_count; - u32 rx_ring_count; - -#define NGBE_MAX_RETA_ENTRIES 128 - u8 rss_indir_tbl[NGBE_MAX_RETA_ENTRIES]; - -#define NGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ - u32 *rss_key; - u32 wol; - - u16 bd_number; -}; - -extern char ngbe_driver_name[]; - -#endif /* _NGBE_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c index 0e3923b3737e..6562a2de9527 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.c @@ -9,12 +9,10 @@ #include "../libwx/wx_hw.h" #include "ngbe_type.h" #include "ngbe_hw.h" -#include "ngbe.h" -int ngbe_eeprom_chksum_hostif(struct ngbe_hw *hw) +int ngbe_eeprom_chksum_hostif(struct wx *wx) { struct wx_hic_read_shadow_ram buffer; - struct wx_hw *wxhw = &hw->wxhw; int status; int tmp; @@ -27,61 +25,73 @@ int ngbe_eeprom_chksum_hostif(struct ngbe_hw *hw) /* one word */ buffer.length = 0; - status = wx_host_interface_command(wxhw, (u32 *)&buffer, sizeof(buffer), + status = wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), WX_HI_COMMAND_TIMEOUT, false); if (status < 0) return status; - tmp = rd32a(wxhw, WX_MNG_MBOX, 1); + tmp = rd32a(wx, WX_MNG_MBOX, 1); if (tmp == NGBE_FW_CMD_ST_PASS) return 0; return -EIO; } -static int ngbe_reset_misc(struct ngbe_hw *hw) +static int ngbe_reset_misc(struct wx *wx) { - struct wx_hw *wxhw = &hw->wxhw; - - wx_reset_misc(wxhw); - if (hw->mac_type == ngbe_mac_type_rgmii) - wr32(wxhw, NGBE_MDIO_CLAUSE_SELECT, 0xF); - if (hw->gpio_ctrl) { + wx_reset_misc(wx); + if (wx->gpio_ctrl) { /* gpio0 is used to power on/off control*/ - wr32(wxhw, NGBE_GPIO_DDR, 0x1); - wr32(wxhw, NGBE_GPIO_DR, NGBE_GPIO_DR_0); + wr32(wx, NGBE_GPIO_DDR, 0x1); + ngbe_sfp_modules_txrx_powerctl(wx, false); } return 0; } +void ngbe_sfp_modules_txrx_powerctl(struct wx *wx, bool swi) +{ + /* gpio0 is used to power on control . 0 is on */ + wr32(wx, NGBE_GPIO_DR, swi ? 0 : NGBE_GPIO_DR_0); +} + /** * ngbe_reset_hw - Perform hardware reset - * @hw: pointer to hardware structure + * @wx: pointer to hardware structure * * Resets the hardware by resetting the transmit and receive units, masks * and clears all interrupts, perform a PHY reset, and perform a link (MAC) * reset. **/ -int ngbe_reset_hw(struct ngbe_hw *hw) +int ngbe_reset_hw(struct wx *wx) { - struct wx_hw *wxhw = &hw->wxhw; - int status = 0; - u32 reset = 0; + u32 val = 0; + int ret = 0; - /* Call adapter stop to disable tx/rx and clear interrupts */ - status = wx_stop_adapter(wxhw); - if (status != 0) - return status; - reset = WX_MIS_RST_LAN_RST(wxhw->bus.func); - wr32(wxhw, WX_MIS_RST, reset | rd32(wxhw, WX_MIS_RST)); - ngbe_reset_misc(hw); + /* Call wx stop to disable tx/rx and clear interrupts */ + ret = wx_stop_adapter(wx); + if (ret != 0) + return ret; + + if (wx->mac_type != em_mac_type_mdi) { + val = WX_MIS_RST_LAN_RST(wx->bus.func); + wr32(wx, WX_MIS_RST, val | rd32(wx, WX_MIS_RST)); + + ret = read_poll_timeout(rd32, val, + !(val & (BIT(9) << wx->bus.func)), 1000, + 100000, false, wx, 0x10028); + if (ret) { + wx_err(wx, "Lan reset exceed s maximum times.\n"); + return ret; + } + } + ngbe_reset_misc(wx); /* Store the permanent mac address */ - wx_get_mac_addr(wxhw, wxhw->mac.perm_addr); + wx_get_mac_addr(wx, wx->mac.perm_addr); /* reset num_rar_entries to 128 */ - wxhw->mac.num_rar_entries = NGBE_RAR_ENTRIES; - wx_init_rx_addrs(wxhw); - pci_set_master(wxhw->pdev); + wx->mac.num_rar_entries = NGBE_RAR_ENTRIES; + wx_init_rx_addrs(wx); + pci_set_master(wx->pdev); return 0; } diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h index 42476a3fe57c..a4693e006816 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_hw.h @@ -7,6 +7,7 @@ #ifndef _NGBE_HW_H_ #define _NGBE_HW_H_ -int ngbe_eeprom_chksum_hostif(struct ngbe_hw *hw); -int ngbe_reset_hw(struct ngbe_hw *hw); +int ngbe_eeprom_chksum_hostif(struct wx *wx); +void ngbe_sfp_modules_txrx_powerctl(struct wx *wx, bool swi); +int ngbe_reset_hw(struct wx *wx); #endif /* _NGBE_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index f0b24366da18..ed52f80b5475 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -9,12 +9,14 @@ #include <linux/aer.h> #include <linux/etherdevice.h> #include <net/ip.h> +#include <linux/phy.h> #include "../libwx/wx_type.h" #include "../libwx/wx_hw.h" #include "ngbe_type.h" +#include "ngbe_mdio.h" #include "ngbe_hw.h" -#include "ngbe.h" + char ngbe_driver_name[] = "ngbe"; /* ngbe_pci_tbl - PCI Device ID Table @@ -39,70 +41,27 @@ static const struct pci_device_id ngbe_pci_tbl[] = { { .device = 0 } }; -static void ngbe_mac_set_default_filter(struct ngbe_adapter *adapter, u8 *addr) -{ - struct ngbe_hw *hw = &adapter->hw; - - memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN); - adapter->mac_table[0].pools = 1ULL; - adapter->mac_table[0].state = (NGBE_MAC_STATE_DEFAULT | - NGBE_MAC_STATE_IN_USE); - wx_set_rar(&hw->wxhw, 0, adapter->mac_table[0].addr, - adapter->mac_table[0].pools, - WX_PSR_MAC_SWC_AD_H_AV); -} - /** * ngbe_init_type_code - Initialize the shared code - * @hw: pointer to hardware structure + * @wx: pointer to hardware structure **/ -static void ngbe_init_type_code(struct ngbe_hw *hw) +static void ngbe_init_type_code(struct wx *wx) { int wol_mask = 0, ncsi_mask = 0; - struct wx_hw *wxhw = &hw->wxhw; - u16 type_mask = 0; + u16 type_mask = 0, val; - wxhw->mac.type = wx_mac_em; - type_mask = (u16)(wxhw->subsystem_device_id & NGBE_OEM_MASK); - ncsi_mask = wxhw->subsystem_device_id & NGBE_NCSI_MASK; - wol_mask = wxhw->subsystem_device_id & NGBE_WOL_MASK; - - switch (type_mask) { - case NGBE_SUBID_M88E1512_SFP: - case NGBE_SUBID_LY_M88E1512_SFP: - hw->phy.type = ngbe_phy_m88e1512_sfi; - break; - case NGBE_SUBID_M88E1512_RJ45: - hw->phy.type = ngbe_phy_m88e1512; - break; - case NGBE_SUBID_M88E1512_MIX: - hw->phy.type = ngbe_phy_m88e1512_unknown; - break; - case NGBE_SUBID_YT8521S_SFP: - case NGBE_SUBID_YT8521S_SFP_GPIO: - case NGBE_SUBID_LY_YT8521S_SFP: - hw->phy.type = ngbe_phy_yt8521s_sfi; - break; - case NGBE_SUBID_INTERNAL_YT8521S_SFP: - case NGBE_SUBID_INTERNAL_YT8521S_SFP_GPIO: - hw->phy.type = ngbe_phy_internal_yt8521s_sfi; - break; - case NGBE_SUBID_RGMII_FPGA: - case NGBE_SUBID_OCP_CARD: - fallthrough; - default: - hw->phy.type = ngbe_phy_internal; - break; - } + wx->mac.type = wx_mac_em; + type_mask = (u16)(wx->subsystem_device_id & NGBE_OEM_MASK); + ncsi_mask = wx->subsystem_device_id & NGBE_NCSI_MASK; + wol_mask = wx->subsystem_device_id & NGBE_WOL_MASK; - if (hw->phy.type == ngbe_phy_internal || - hw->phy.type == ngbe_phy_internal_yt8521s_sfi) - hw->mac_type = ngbe_mac_type_mdi; - else - hw->mac_type = ngbe_mac_type_rgmii; + val = rd32(wx, WX_CFG_PORT_ST); + wx->mac_type = (val & BIT(7)) >> 7 ? + em_mac_type_rgmii : + em_mac_type_mdi; - hw->wol_enabled = (wol_mask == NGBE_WOL_SUP) ? 1 : 0; - hw->ncsi_enabled = (ncsi_mask == NGBE_NCSI_MASK || + wx->wol_enabled = (wol_mask == NGBE_WOL_SUP) ? 1 : 0; + wx->ncsi_enabled = (ncsi_mask == NGBE_NCSI_MASK || type_mask == NGBE_SUBID_OCP_CARD) ? 1 : 0; switch (type_mask) { @@ -110,31 +69,31 @@ static void ngbe_init_type_code(struct ngbe_hw *hw) case NGBE_SUBID_LY_M88E1512_SFP: case NGBE_SUBID_YT8521S_SFP_GPIO: case NGBE_SUBID_INTERNAL_YT8521S_SFP_GPIO: - hw->gpio_ctrl = 1; + wx->gpio_ctrl = 1; break; default: - hw->gpio_ctrl = 0; + wx->gpio_ctrl = 0; break; } } /** - * ngbe_init_rss_key - Initialize adapter RSS key - * @adapter: device handle + * ngbe_init_rss_key - Initialize wx RSS key + * @wx: device handle * * Allocates and initializes the RSS key if it is not allocated. **/ -static inline int ngbe_init_rss_key(struct ngbe_adapter *adapter) +static inline int ngbe_init_rss_key(struct wx *wx) { u32 *rss_key; - if (!adapter->rss_key) { - rss_key = kzalloc(NGBE_RSS_KEY_SIZE, GFP_KERNEL); + if (!wx->rss_key) { + rss_key = kzalloc(WX_RSS_KEY_SIZE, GFP_KERNEL); if (unlikely(!rss_key)) return -ENOMEM; - netdev_rss_key_fill(rss_key, NGBE_RSS_KEY_SIZE); - adapter->rss_key = rss_key; + netdev_rss_key_fill(rss_key, WX_RSS_KEY_SIZE); + wx->rss_key = rss_key; } return 0; @@ -142,72 +101,76 @@ static inline int ngbe_init_rss_key(struct ngbe_adapter *adapter) /** * ngbe_sw_init - Initialize general software structures - * @adapter: board private structure to initialize + * @wx: board private structure to initialize **/ -static int ngbe_sw_init(struct ngbe_adapter *adapter) +static int ngbe_sw_init(struct wx *wx) { - struct pci_dev *pdev = adapter->pdev; - struct ngbe_hw *hw = &adapter->hw; - struct wx_hw *wxhw = &hw->wxhw; + struct pci_dev *pdev = wx->pdev; u16 msix_count = 0; int err = 0; - wxhw->hw_addr = adapter->io_addr; - wxhw->pdev = pdev; + wx->mac.num_rar_entries = NGBE_RAR_ENTRIES; + wx->mac.max_rx_queues = NGBE_MAX_RX_QUEUES; + wx->mac.max_tx_queues = NGBE_MAX_TX_QUEUES; /* PCI config space info */ - err = wx_sw_init(wxhw); + err = wx_sw_init(wx); if (err < 0) { - netif_err(adapter, probe, adapter->netdev, - "Read of internal subsystem device id failed\n"); + wx_err(wx, "read of internal subsystem device id failed\n"); return err; } /* mac type, phy type , oem type */ - ngbe_init_type_code(hw); + ngbe_init_type_code(wx); - wxhw->mac.max_rx_queues = NGBE_MAX_RX_QUEUES; - wxhw->mac.max_tx_queues = NGBE_MAX_TX_QUEUES; - wxhw->mac.num_rar_entries = NGBE_RAR_ENTRIES; /* Set common capability flags and settings */ - adapter->max_q_vectors = NGBE_MAX_MSIX_VECTORS; - - err = wx_get_pcie_msix_counts(wxhw, &msix_count, NGBE_MAX_MSIX_VECTORS); + wx->max_q_vectors = NGBE_MAX_MSIX_VECTORS; + err = wx_get_pcie_msix_counts(wx, &msix_count, NGBE_MAX_MSIX_VECTORS); if (err) dev_err(&pdev->dev, "Do not support MSI-X\n"); - wxhw->mac.max_msix_vectors = msix_count; + wx->mac.max_msix_vectors = msix_count; - adapter->mac_table = kcalloc(wxhw->mac.num_rar_entries, - sizeof(struct ngbe_mac_addr), - GFP_KERNEL); - if (!adapter->mac_table) { - dev_err(&pdev->dev, "mac_table allocation failed: %d\n", err); - return -ENOMEM; - } - - if (ngbe_init_rss_key(adapter)) + if (ngbe_init_rss_key(wx)) return -ENOMEM; /* enable itr by default in dynamic mode */ - adapter->rx_itr_setting = 1; - adapter->tx_itr_setting = 1; + wx->rx_itr_setting = 1; + wx->tx_itr_setting = 1; /* set default ring sizes */ - adapter->tx_ring_count = NGBE_DEFAULT_TXD; - adapter->rx_ring_count = NGBE_DEFAULT_RXD; + wx->tx_ring_count = NGBE_DEFAULT_TXD; + wx->rx_ring_count = NGBE_DEFAULT_RXD; /* set default work limits */ - adapter->tx_work_limit = NGBE_DEFAULT_TX_WORK; - adapter->rx_work_limit = NGBE_DEFAULT_RX_WORK; + wx->tx_work_limit = NGBE_DEFAULT_TX_WORK; + wx->rx_work_limit = NGBE_DEFAULT_RX_WORK; return 0; } -static void ngbe_down(struct ngbe_adapter *adapter) +static void ngbe_disable_device(struct wx *wx) { - netif_carrier_off(adapter->netdev); - netif_tx_disable(adapter->netdev); -}; + struct net_device *netdev = wx->netdev; + + /* disable receives */ + wx_disable_rx(wx); + netif_tx_disable(netdev); + if (wx->gpio_ctrl) + ngbe_sfp_modules_txrx_powerctl(wx, false); +} + +static void ngbe_down(struct wx *wx) +{ + phy_stop(wx->phydev); + ngbe_disable_device(wx); +} + +static void ngbe_up(struct wx *wx) +{ + if (wx->gpio_ctrl) + ngbe_sfp_modules_txrx_powerctl(wx, true); + phy_start(wx->phydev); +} /** * ngbe_open - Called when a network interface is made active @@ -220,11 +183,14 @@ static void ngbe_down(struct ngbe_adapter *adapter) **/ static int ngbe_open(struct net_device *netdev) { - struct ngbe_adapter *adapter = netdev_priv(netdev); - struct ngbe_hw *hw = &adapter->hw; - struct wx_hw *wxhw = &hw->wxhw; + struct wx *wx = netdev_priv(netdev); + int err; - wx_control_hw(wxhw, true); + wx_control_hw(wx, true); + err = ngbe_phy_connect(wx); + if (err) + return err; + ngbe_up(wx); return 0; } @@ -242,10 +208,11 @@ static int ngbe_open(struct net_device *netdev) **/ static int ngbe_close(struct net_device *netdev) { - struct ngbe_adapter *adapter = netdev_priv(netdev); + struct wx *wx = netdev_priv(netdev); - ngbe_down(adapter); - wx_control_hw(&adapter->hw.wxhw, false); + ngbe_down(wx); + phy_disconnect(wx->phydev); + wx_control_hw(wx, false); return 0; } @@ -256,52 +223,29 @@ static netdev_tx_t ngbe_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; } -/** - * ngbe_set_mac - Change the Ethernet Address of the NIC - * @netdev: network interface device structure - * @p: pointer to an address structure - * - * Returns 0 on success, negative on failure - **/ -static int ngbe_set_mac(struct net_device *netdev, void *p) -{ - struct ngbe_adapter *adapter = netdev_priv(netdev); - struct wx_hw *wxhw = &adapter->hw.wxhw; - struct sockaddr *addr = p; - - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - - eth_hw_addr_set(netdev, addr->sa_data); - memcpy(wxhw->mac.addr, addr->sa_data, netdev->addr_len); - - ngbe_mac_set_default_filter(adapter, wxhw->mac.addr); - - return 0; -} - static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) { - struct ngbe_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; + struct wx *wx = pci_get_drvdata(pdev); + struct net_device *netdev; + netdev = wx->netdev; netif_device_detach(netdev); rtnl_lock(); if (netif_running(netdev)) - ngbe_down(adapter); + ngbe_down(wx); rtnl_unlock(); - wx_control_hw(&adapter->hw.wxhw, false); + wx_control_hw(wx, false); pci_disable_device(pdev); } static void ngbe_shutdown(struct pci_dev *pdev) { - struct ngbe_adapter *adapter = pci_get_drvdata(pdev); + struct wx *wx = pci_get_drvdata(pdev); bool wake; - wake = !!adapter->wol; + wake = !!wx->wol; ngbe_dev_shutdown(pdev, &wake); @@ -316,7 +260,7 @@ static const struct net_device_ops ngbe_netdev_ops = { .ndo_stop = ngbe_close, .ndo_start_xmit = ngbe_xmit_frame, .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = ngbe_set_mac, + .ndo_set_mac_address = wx_set_mac, }; /** @@ -326,18 +270,16 @@ static const struct net_device_ops ngbe_netdev_ops = { * * Returns 0 on success, negative on failure * - * ngbe_probe initializes an adapter identified by a pci_dev structure. - * The OS initialization, configuring of the adapter private structure, + * ngbe_probe initializes an wx identified by a pci_dev structure. + * The OS initialization, configuring of the wx private structure, * and a hardware reset occur. **/ static int ngbe_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { - struct ngbe_adapter *adapter = NULL; - struct ngbe_hw *hw = NULL; - struct wx_hw *wxhw = NULL; struct net_device *netdev; u32 e2rom_cksum_cap = 0; + struct wx *wx = NULL; static int func_nums; u16 e2rom_ver = 0; u32 etrack_id = 0; @@ -368,7 +310,7 @@ static int ngbe_probe(struct pci_dev *pdev, pci_set_master(pdev); netdev = devm_alloc_etherdev_mqs(&pdev->dev, - sizeof(struct ngbe_adapter), + sizeof(struct wx), NGBE_MAX_TX_QUEUES, NGBE_MAX_RX_QUEUES); if (!netdev) { @@ -378,17 +320,15 @@ static int ngbe_probe(struct pci_dev *pdev, SET_NETDEV_DEV(netdev, &pdev->dev); - adapter = netdev_priv(netdev); - adapter->netdev = netdev; - adapter->pdev = pdev; - hw = &adapter->hw; - wxhw = &hw->wxhw; - adapter->msg_enable = BIT(3) - 1; - - adapter->io_addr = devm_ioremap(&pdev->dev, - pci_resource_start(pdev, 0), - pci_resource_len(pdev, 0)); - if (!adapter->io_addr) { + wx = netdev_priv(netdev); + wx->netdev = netdev; + wx->pdev = pdev; + wx->msg_enable = BIT(3) - 1; + + wx->hw_addr = devm_ioremap(&pdev->dev, + pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0)); + if (!wx->hw_addr) { err = -EIO; goto err_pci_release_regions; } @@ -397,44 +337,44 @@ static int ngbe_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_HIGHDMA; - adapter->bd_number = func_nums; + wx->bd_number = func_nums; /* setup the private structure */ - err = ngbe_sw_init(adapter); + err = ngbe_sw_init(wx); if (err) goto err_free_mac_table; /* check if flash load is done after hw power up */ - err = wx_check_flash_load(wxhw, NGBE_SPI_ILDR_STATUS_PERST); + err = wx_check_flash_load(wx, NGBE_SPI_ILDR_STATUS_PERST); if (err) goto err_free_mac_table; - err = wx_check_flash_load(wxhw, NGBE_SPI_ILDR_STATUS_PWRRST); + err = wx_check_flash_load(wx, NGBE_SPI_ILDR_STATUS_PWRRST); if (err) goto err_free_mac_table; - err = wx_mng_present(wxhw); + err = wx_mng_present(wx); if (err) { dev_err(&pdev->dev, "Management capability is not present\n"); goto err_free_mac_table; } - err = ngbe_reset_hw(hw); + err = ngbe_reset_hw(wx); if (err) { dev_err(&pdev->dev, "HW Init failed: %d\n", err); goto err_free_mac_table; } - if (wxhw->bus.func == 0) { - wr32(wxhw, NGBE_CALSUM_CAP_STATUS, 0x0); - wr32(wxhw, NGBE_EEPROM_VERSION_STORE_REG, 0x0); + if (wx->bus.func == 0) { + wr32(wx, NGBE_CALSUM_CAP_STATUS, 0x0); + wr32(wx, NGBE_EEPROM_VERSION_STORE_REG, 0x0); } else { - e2rom_cksum_cap = rd32(wxhw, NGBE_CALSUM_CAP_STATUS); - saved_ver = rd32(wxhw, NGBE_EEPROM_VERSION_STORE_REG); + e2rom_cksum_cap = rd32(wx, NGBE_CALSUM_CAP_STATUS); + saved_ver = rd32(wx, NGBE_EEPROM_VERSION_STORE_REG); } - wx_init_eeprom_params(wxhw); - if (wxhw->bus.func == 0 || e2rom_cksum_cap == 0) { + wx_init_eeprom_params(wx); + if (wx->bus.func == 0 || e2rom_cksum_cap == 0) { /* make sure the EEPROM is ready */ - err = ngbe_eeprom_chksum_hostif(hw); + err = ngbe_eeprom_chksum_hostif(wx); if (err) { dev_err(&pdev->dev, "The EEPROM Checksum Is Not Valid\n"); err = -EIO; @@ -442,14 +382,14 @@ static int ngbe_probe(struct pci_dev *pdev, } } - adapter->wol = 0; - if (hw->wol_enabled) - adapter->wol = NGBE_PSR_WKUP_CTL_MAG; + wx->wol = 0; + if (wx->wol_enabled) + wx->wol = NGBE_PSR_WKUP_CTL_MAG; - hw->wol_enabled = !!(adapter->wol); - wr32(wxhw, NGBE_PSR_WKUP_CTL, adapter->wol); + wx->wol_enabled = !!(wx->wol); + wr32(wx, NGBE_PSR_WKUP_CTL, wx->wol); - device_set_wakeup_enable(&pdev->dev, adapter->wol); + device_set_wakeup_enable(&pdev->dev, wx->wol); /* Save off EEPROM version number and Option Rom version which * together make a unique identify for the eeprom @@ -457,37 +397,42 @@ static int ngbe_probe(struct pci_dev *pdev, if (saved_ver) { etrack_id = saved_ver; } else { - wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + NGBE_EEPROM_VERSION_H, + wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + NGBE_EEPROM_VERSION_H, &e2rom_ver); etrack_id = e2rom_ver << 16; - wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + NGBE_EEPROM_VERSION_L, + wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + NGBE_EEPROM_VERSION_L, &e2rom_ver); etrack_id |= e2rom_ver; - wr32(wxhw, NGBE_EEPROM_VERSION_STORE_REG, etrack_id); + wr32(wx, NGBE_EEPROM_VERSION_STORE_REG, etrack_id); } - eth_hw_addr_set(netdev, wxhw->mac.perm_addr); - ngbe_mac_set_default_filter(adapter, wxhw->mac.perm_addr); + eth_hw_addr_set(netdev, wx->mac.perm_addr); + wx_mac_set_default_filter(wx, wx->mac.perm_addr); + + /* phy Interface Configuration */ + err = ngbe_mdio_init(wx); + if (err) + goto err_free_mac_table; err = register_netdev(netdev); if (err) goto err_register; - pci_set_drvdata(pdev, adapter); + pci_set_drvdata(pdev, wx); - netif_info(adapter, probe, netdev, + netif_info(wx, probe, netdev, "PHY: %s, PBA No: Wang Xun GbE Family Controller\n", - hw->phy.type == ngbe_phy_internal ? "Internal" : "External"); - netif_info(adapter, probe, netdev, "%pM\n", netdev->dev_addr); + wx->mac_type == em_mac_type_mdi ? "Internal" : "External"); + netif_info(wx, probe, netdev, "%pM\n", netdev->dev_addr); return 0; err_register: - wx_control_hw(wxhw, false); + wx_control_hw(wx, false); err_free_mac_table: - kfree(adapter->mac_table); + kfree(wx->mac_table); err_pci_release_regions: pci_disable_pcie_error_reporting(pdev); pci_release_selected_regions(pdev, @@ -508,15 +453,15 @@ err_pci_disable_dev: **/ static void ngbe_remove(struct pci_dev *pdev) { - struct ngbe_adapter *adapter = pci_get_drvdata(pdev); + struct wx *wx = pci_get_drvdata(pdev); struct net_device *netdev; - netdev = adapter->netdev; + netdev = wx->netdev; unregister_netdev(netdev); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); - kfree(adapter->mac_table); + kfree(wx->mac_table); pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c new file mode 100644 index 000000000000..ba33a57b42c2 --- /dev/null +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/ethtool.h> +#include <linux/iopoll.h> +#include <linux/pci.h> +#include <linux/phy.h> + +#include "../libwx/wx_type.h" +#include "../libwx/wx_hw.h" +#include "ngbe_type.h" +#include "ngbe_mdio.h" + +static int ngbe_phy_read_reg_internal(struct mii_bus *bus, int phy_addr, int regnum) +{ + struct wx *wx = bus->priv; + + if (phy_addr != 0) + return 0xffff; + return (u16)rd32(wx, NGBE_PHY_CONFIG(regnum)); +} + +static int ngbe_phy_write_reg_internal(struct mii_bus *bus, int phy_addr, int regnum, u16 value) +{ + struct wx *wx = bus->priv; + + if (phy_addr == 0) + wr32(wx, NGBE_PHY_CONFIG(regnum), value); + return 0; +} + +static int ngbe_phy_read_reg_mdi_c22(struct mii_bus *bus, int phy_addr, int regnum) +{ + u32 command, val, device_type = 0; + struct wx *wx = bus->priv; + int ret; + + wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0xF); + /* setup and write the address cycle command */ + command = NGBE_MSCA_RA(regnum) | + NGBE_MSCA_PA(phy_addr) | + NGBE_MSCA_DA(device_type); + wr32(wx, NGBE_MSCA, command); + command = NGBE_MSCC_CMD(NGBE_MSCA_CMD_READ) | + NGBE_MSCC_BUSY | + NGBE_MDIO_CLK(6); + wr32(wx, NGBE_MSCC, command); + + /* wait to complete */ + ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000, + 100000, false, wx, NGBE_MSCC); + if (ret) { + wx_err(wx, "Mdio read c22 command did not complete.\n"); + return ret; + } + + return (u16)rd32(wx, NGBE_MSCC); +} + +static int ngbe_phy_write_reg_mdi_c22(struct mii_bus *bus, int phy_addr, int regnum, u16 value) +{ + u32 command, val, device_type = 0; + struct wx *wx = bus->priv; + int ret; + + wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0xF); + /* setup and write the address cycle command */ + command = NGBE_MSCA_RA(regnum) | + NGBE_MSCA_PA(phy_addr) | + NGBE_MSCA_DA(device_type); + wr32(wx, NGBE_MSCA, command); + command = value | + NGBE_MSCC_CMD(NGBE_MSCA_CMD_WRITE) | + NGBE_MSCC_BUSY | + NGBE_MDIO_CLK(6); + wr32(wx, NGBE_MSCC, command); + + /* wait to complete */ + ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000, + 100000, false, wx, NGBE_MSCC); + if (ret) + wx_err(wx, "Mdio write c22 command did not complete.\n"); + + return ret; +} + +static int ngbe_phy_read_reg_mdi_c45(struct mii_bus *bus, int phy_addr, int devnum, int regnum) +{ + struct wx *wx = bus->priv; + u32 val, command; + int ret; + + wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0x0); + /* setup and write the address cycle command */ + command = NGBE_MSCA_RA(mdiobus_c45_regad(regnum)) | + NGBE_MSCA_PA(phy_addr) | + NGBE_MSCA_DA(devnum); + wr32(wx, NGBE_MSCA, command); + command = NGBE_MSCC_CMD(NGBE_MSCA_CMD_READ) | + NGBE_MSCC_BUSY | + NGBE_MDIO_CLK(6); + wr32(wx, NGBE_MSCC, command); + + /* wait to complete */ + ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000, + 100000, false, wx, NGBE_MSCC); + if (ret) { + wx_err(wx, "Mdio read c45 command did not complete.\n"); + return ret; + } + + return (u16)rd32(wx, NGBE_MSCC); +} + +static int ngbe_phy_write_reg_mdi_c45(struct mii_bus *bus, int phy_addr, + int devnum, int regnum, u16 value) +{ + struct wx *wx = bus->priv; + int ret, command; + u16 val; + + wr32(wx, NGBE_MDIO_CLAUSE_SELECT, 0x0); + /* setup and write the address cycle command */ + command = NGBE_MSCA_RA(mdiobus_c45_regad(regnum)) | + NGBE_MSCA_PA(phy_addr) | + NGBE_MSCA_DA(devnum); + wr32(wx, NGBE_MSCA, command); + command = value | + NGBE_MSCC_CMD(NGBE_MSCA_CMD_WRITE) | + NGBE_MSCC_BUSY | + NGBE_MDIO_CLK(6); + wr32(wx, NGBE_MSCC, command); + + /* wait to complete */ + ret = read_poll_timeout(rd32, val, !(val & NGBE_MSCC_BUSY), 1000, + 100000, false, wx, NGBE_MSCC); + if (ret) + wx_err(wx, "Mdio write c45 command did not complete.\n"); + + return ret; +} + +static int ngbe_phy_read_reg_c22(struct mii_bus *bus, int phy_addr, int regnum) +{ + struct wx *wx = bus->priv; + u16 phy_data; + + if (wx->mac_type == em_mac_type_mdi) + phy_data = ngbe_phy_read_reg_internal(bus, phy_addr, regnum); + else + phy_data = ngbe_phy_read_reg_mdi_c22(bus, phy_addr, regnum); + + return phy_data; +} + +static int ngbe_phy_write_reg_c22(struct mii_bus *bus, int phy_addr, + int regnum, u16 value) +{ + struct wx *wx = bus->priv; + int ret; + + if (wx->mac_type == em_mac_type_mdi) + ret = ngbe_phy_write_reg_internal(bus, phy_addr, regnum, value); + else + ret = ngbe_phy_write_reg_mdi_c22(bus, phy_addr, regnum, value); + + return ret; +} + +static void ngbe_handle_link_change(struct net_device *dev) +{ + struct wx *wx = netdev_priv(dev); + struct phy_device *phydev; + u32 lan_speed, reg; + + phydev = wx->phydev; + if (!(wx->link != phydev->link || + wx->speed != phydev->speed || + wx->duplex != phydev->duplex)) + return; + + wx->link = phydev->link; + wx->speed = phydev->speed; + wx->duplex = phydev->duplex; + switch (phydev->speed) { + case SPEED_10: + lan_speed = 0; + break; + case SPEED_100: + lan_speed = 1; + break; + case SPEED_1000: + default: + lan_speed = 2; + break; + } + wr32m(wx, NGBE_CFG_LAN_SPEED, 0x3, lan_speed); + + if (phydev->link) { + reg = rd32(wx, WX_MAC_TX_CFG); + reg &= ~WX_MAC_TX_CFG_SPEED_MASK; + reg |= WX_MAC_TX_CFG_SPEED_1G | WX_MAC_TX_CFG_TE; + wr32(wx, WX_MAC_TX_CFG, reg); + /* Re configure MAC RX */ + reg = rd32(wx, WX_MAC_RX_CFG); + wr32(wx, WX_MAC_RX_CFG, reg); + wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); + reg = rd32(wx, WX_MAC_WDG_TIMEOUT); + wr32(wx, WX_MAC_WDG_TIMEOUT, reg); + } + phy_print_status(phydev); +} + +int ngbe_phy_connect(struct wx *wx) +{ + int ret; + + ret = phy_connect_direct(wx->netdev, + wx->phydev, + ngbe_handle_link_change, + PHY_INTERFACE_MODE_RGMII_ID); + if (ret) { + wx_err(wx, "PHY connect failed.\n"); + return ret; + } + + return 0; +} + +static void ngbe_phy_fixup(struct wx *wx) +{ + struct phy_device *phydev = wx->phydev; + struct ethtool_eee eee; + + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + + if (wx->mac_type != em_mac_type_mdi) + return; + /* disable EEE, internal phy does not support eee */ + memset(&eee, 0, sizeof(eee)); + phy_ethtool_set_eee(phydev, &eee); +} + +int ngbe_mdio_init(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + struct mii_bus *mii_bus; + int ret; + + mii_bus = devm_mdiobus_alloc(&pdev->dev); + if (!mii_bus) + return -ENOMEM; + + mii_bus->name = "ngbe_mii_bus"; + mii_bus->read = ngbe_phy_read_reg_c22; + mii_bus->write = ngbe_phy_write_reg_c22; + mii_bus->phy_mask = GENMASK(31, 4); + mii_bus->parent = &pdev->dev; + mii_bus->priv = wx; + + if (wx->mac_type == em_mac_type_rgmii) { + mii_bus->read_c45 = ngbe_phy_read_reg_mdi_c45; + mii_bus->write_c45 = ngbe_phy_write_reg_mdi_c45; + } + + snprintf(mii_bus->id, MII_BUS_ID_SIZE, "ngbe-%x", + (pdev->bus->number << 8) | pdev->devfn); + ret = devm_mdiobus_register(&pdev->dev, mii_bus); + if (ret) + return ret; + + wx->phydev = phy_find_first(mii_bus); + if (!wx->phydev) + return -ENODEV; + + phy_attached_info(wx->phydev); + ngbe_phy_fixup(wx); + + wx->link = 0; + wx->speed = 0; + wx->duplex = 0; + + return 0; +} diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h new file mode 100644 index 000000000000..0a6400dd89c4 --- /dev/null +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * WangXun Gigabit PCI Express Linux driver + * Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. + */ + +#ifndef _NGBE_MDIO_H_ +#define _NGBE_MDIO_H_ + +int ngbe_phy_connect(struct wx *wx); +int ngbe_mdio_init(struct wx *wx); +#endif /* _NGBE_MDIO_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index 39f6c03f1a54..fd71260f73de 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -49,7 +49,6 @@ #define NGBE_SPI_ILDR_STATUS 0x10120 #define NGBE_SPI_ILDR_STATUS_PERST BIT(0) /* PCIE_PERST is done */ #define NGBE_SPI_ILDR_STATUS_PWRRST BIT(1) /* Power on reset is done */ -#define NGBE_SPI_ILDR_STATUS_LAN_SW_RST(_i) BIT((_i) + 9) /* lan soft reset done */ /* Checksum and EEPROM pointers */ #define NGBE_CALSUM_COMMAND 0xE9 @@ -60,6 +59,25 @@ #define NGBE_EEPROM_VERSION_L 0x1D #define NGBE_EEPROM_VERSION_H 0x1E +/* mdio access */ +#define NGBE_MSCA 0x11200 +#define NGBE_MSCA_RA(v) FIELD_PREP(U16_MAX, v) +#define NGBE_MSCA_PA(v) FIELD_PREP(GENMASK(20, 16), v) +#define NGBE_MSCA_DA(v) FIELD_PREP(GENMASK(25, 21), v) +#define NGBE_MSCC 0x11204 +#define NGBE_MSCC_CMD(v) FIELD_PREP(GENMASK(17, 16), v) + +enum NGBE_MSCA_CMD_value { + NGBE_MSCA_CMD_RSV = 0, + NGBE_MSCA_CMD_WRITE, + NGBE_MSCA_CMD_POST_READ, + NGBE_MSCA_CMD_READ, +}; + +#define NGBE_MSCC_SADDR BIT(18) +#define NGBE_MSCC_BUSY BIT(22) +#define NGBE_MDIO_CLK(v) FIELD_PREP(GENMASK(21, 19), v) + /* Media-dependent registers. */ #define NGBE_MDIO_CLAUSE_SELECT 0x11220 @@ -72,6 +90,10 @@ #define NGBE_GPIO_DDR_0 BIT(0) /* SDP0 IO direction */ #define NGBE_GPIO_DDR_1 BIT(1) /* SDP1 IO direction */ +#define NGBE_PHY_CONFIG(reg_offset) (0x14000 + ((reg_offset) * 4)) +#define NGBE_CFG_LAN_SPEED 0x14440 +#define NGBE_CFG_PORT_ST 0x14404 + /* Wake up registers */ #define NGBE_PSR_WKUP_CTL 0x15B80 /* Wake Up Filter Control Bit */ @@ -90,50 +112,26 @@ #define NGBE_FW_CMD_ST_PASS 0x80658383 #define NGBE_FW_CMD_ST_FAIL 0x70657376 -enum ngbe_phy_type { - ngbe_phy_unknown = 0, - ngbe_phy_none, - ngbe_phy_internal, - ngbe_phy_m88e1512, - ngbe_phy_m88e1512_sfi, - ngbe_phy_m88e1512_unknown, - ngbe_phy_yt8521s, - ngbe_phy_yt8521s_sfi, - ngbe_phy_internal_yt8521s_sfi, - ngbe_phy_generic -}; +#define NGBE_MAX_FDIR_INDICES 7 -enum ngbe_media_type { - ngbe_media_type_unknown = 0, - ngbe_media_type_fiber, - ngbe_media_type_copper, - ngbe_media_type_backplane, -}; +#define NGBE_MAX_RX_QUEUES (NGBE_MAX_FDIR_INDICES + 1) +#define NGBE_MAX_TX_QUEUES (NGBE_MAX_FDIR_INDICES + 1) -enum ngbe_mac_type { - ngbe_mac_type_unknown = 0, - ngbe_mac_type_mdi, - ngbe_mac_type_rgmii -}; - -struct ngbe_phy_info { - enum ngbe_phy_type type; - enum ngbe_media_type media_type; +#define NGBE_ETH_LENGTH_OF_ADDRESS 6 +#define NGBE_MAX_MSIX_VECTORS 0x09 +#define NGBE_RAR_ENTRIES 32 - u32 addr; - u32 id; +/* TX/RX descriptor defines */ +#define NGBE_DEFAULT_TXD 512 /* default ring size */ +#define NGBE_DEFAULT_TX_WORK 256 +#define NGBE_MAX_TXD 8192 +#define NGBE_MIN_TXD 128 - bool reset_if_overtemp; +#define NGBE_DEFAULT_RXD 512 /* default ring size */ +#define NGBE_DEFAULT_RX_WORK 256 +#define NGBE_MAX_RXD 8192 +#define NGBE_MIN_RXD 128 -}; +extern char ngbe_driver_name[]; -struct ngbe_hw { - struct wx_hw wxhw; - struct ngbe_phy_info phy; - enum ngbe_mac_type mac_type; - - bool wol_enabled; - bool ncsi_enabled; - bool gpio_ctrl; -}; #endif /* _NGBE_TYPE_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe.h b/drivers/net/ethernet/wangxun/txgbe/txgbe.h deleted file mode 100644 index 19e61377bd00..000000000000 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe.h +++ /dev/null @@ -1,43 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2015 - 2022 Beijing WangXun Technology Co., Ltd. */ - -#ifndef _TXGBE_H_ -#define _TXGBE_H_ - -#define TXGBE_MAX_FDIR_INDICES 63 - -#define TXGBE_MAX_RX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) -#define TXGBE_MAX_TX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) - -#define TXGBE_SP_MAX_TX_QUEUES 128 -#define TXGBE_SP_MAX_RX_QUEUES 128 -#define TXGBE_SP_RAR_ENTRIES 128 -#define TXGBE_SP_MC_TBL_SIZE 128 - -struct txgbe_mac_addr { - u8 addr[ETH_ALEN]; - u16 state; /* bitmask */ - u64 pools; -}; - -#define TXGBE_MAC_STATE_DEFAULT 0x1 -#define TXGBE_MAC_STATE_MODIFIED 0x2 -#define TXGBE_MAC_STATE_IN_USE 0x4 - -/* board specific private data structure */ -struct txgbe_adapter { - u8 __iomem *io_addr; /* Mainly for iounmap use */ - /* OS defined structs */ - struct net_device *netdev; - struct pci_dev *pdev; - - /* structs defined in txgbe_type.h */ - struct txgbe_hw hw; - u16 msg_enable; - struct txgbe_mac_addr *mac_table; - char eeprom_id[32]; -}; - -extern char txgbe_driver_name[]; - -#endif /* _TXGBE_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index 167f7ff73192..ebc46f3be056 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -12,70 +12,67 @@ #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_hw.h" -#include "txgbe.h" /** * txgbe_init_thermal_sensor_thresh - Inits thermal sensor thresholds - * @hw: pointer to hardware structure + * @wx: pointer to hardware structure * * Inits the thermal sensor thresholds according to the NVM map * and save off the threshold and location values into mac.thermal_sensor_data **/ -static void txgbe_init_thermal_sensor_thresh(struct txgbe_hw *hw) +static void txgbe_init_thermal_sensor_thresh(struct wx *wx) { - struct wx_hw *wxhw = &hw->wxhw; - struct wx_thermal_sensor_data *data = &wxhw->mac.sensor; + struct wx_thermal_sensor_data *data = &wx->mac.sensor; memset(data, 0, sizeof(struct wx_thermal_sensor_data)); /* Only support thermal sensors attached to SP physical port 0 */ - if (wxhw->bus.func) + if (wx->bus.func) return; - wr32(wxhw, TXGBE_TS_CTL, TXGBE_TS_CTL_EVAL_MD); + wr32(wx, TXGBE_TS_CTL, TXGBE_TS_CTL_EVAL_MD); - wr32(wxhw, WX_TS_INT_EN, + wr32(wx, WX_TS_INT_EN, WX_TS_INT_EN_ALARM_INT_EN | WX_TS_INT_EN_DALARM_INT_EN); - wr32(wxhw, WX_TS_EN, WX_TS_EN_ENA); + wr32(wx, WX_TS_EN, WX_TS_EN_ENA); data->alarm_thresh = 100; - wr32(wxhw, WX_TS_ALARM_THRE, 677); + wr32(wx, WX_TS_ALARM_THRE, 677); data->dalarm_thresh = 90; - wr32(wxhw, WX_TS_DALARM_THRE, 614); + wr32(wx, WX_TS_DALARM_THRE, 614); } /** * txgbe_read_pba_string - Reads part number string from EEPROM - * @hw: pointer to hardware structure + * @wx: pointer to hardware structure * @pba_num: stores the part number string from the EEPROM * @pba_num_size: part number string buffer length * * Reads the part number string from the EEPROM. **/ -int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size) +int txgbe_read_pba_string(struct wx *wx, u8 *pba_num, u32 pba_num_size) { u16 pba_ptr, offset, length, data; - struct wx_hw *wxhw = &hw->wxhw; int ret_val; if (!pba_num) { - wx_err(wxhw, "PBA string buffer was null\n"); + wx_err(wx, "PBA string buffer was null\n"); return -EINVAL; } - ret_val = wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + TXGBE_PBANUM0_PTR, + ret_val = wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + TXGBE_PBANUM0_PTR, &data); if (ret_val != 0) { - wx_err(wxhw, "NVM Read Error\n"); + wx_err(wx, "NVM Read Error\n"); return ret_val; } - ret_val = wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + TXGBE_PBANUM1_PTR, + ret_val = wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + TXGBE_PBANUM1_PTR, &pba_ptr); if (ret_val != 0) { - wx_err(wxhw, "NVM Read Error\n"); + wx_err(wx, "NVM Read Error\n"); return ret_val; } @@ -84,11 +81,11 @@ int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size) * and we can decode it into an ascii string */ if (data != TXGBE_PBANUM_PTR_GUARD) { - wx_err(wxhw, "NVM PBA number is not stored as string\n"); + wx_err(wx, "NVM PBA number is not stored as string\n"); /* we will need 11 characters to store the PBA */ if (pba_num_size < 11) { - wx_err(wxhw, "PBA string buffer too small\n"); + wx_err(wx, "PBA string buffer too small\n"); return -ENOMEM; } @@ -118,20 +115,20 @@ int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size) return 0; } - ret_val = wx_read_ee_hostif(wxhw, pba_ptr, &length); + ret_val = wx_read_ee_hostif(wx, pba_ptr, &length); if (ret_val != 0) { - wx_err(wxhw, "NVM Read Error\n"); + wx_err(wx, "NVM Read Error\n"); return ret_val; } if (length == 0xFFFF || length == 0) { - wx_err(wxhw, "NVM PBA number section invalid length\n"); + wx_err(wx, "NVM PBA number section invalid length\n"); return -EINVAL; } /* check if pba_num buffer is big enough */ if (pba_num_size < (((u32)length * 2) - 1)) { - wx_err(wxhw, "PBA string buffer too small\n"); + wx_err(wx, "PBA string buffer too small\n"); return -ENOMEM; } @@ -140,9 +137,9 @@ int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size) length--; for (offset = 0; offset < length; offset++) { - ret_val = wx_read_ee_hostif(wxhw, pba_ptr + offset, &data); + ret_val = wx_read_ee_hostif(wx, pba_ptr + offset, &data); if (ret_val != 0) { - wx_err(wxhw, "NVM Read Error\n"); + wx_err(wx, "NVM Read Error\n"); return ret_val; } pba_num[offset * 2] = (u8)(data >> 8); @@ -155,14 +152,13 @@ int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size) /** * txgbe_calc_eeprom_checksum - Calculates and returns the checksum - * @hw: pointer to hardware structure + * @wx: pointer to hardware structure * @checksum: pointer to cheksum * * Returns a negative error code on error **/ -static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) +static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum) { - struct wx_hw *wxhw = &hw->wxhw; u16 *eeprom_ptrs = NULL; u32 buffer_size = 0; u16 *buffer = NULL; @@ -170,7 +166,7 @@ static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) int status; u16 i; - wx_init_eeprom_params(wxhw); + wx_init_eeprom_params(wx); if (!buffer) { eeprom_ptrs = kvmalloc_array(TXGBE_EEPROM_LAST_WORD, sizeof(u16), @@ -178,11 +174,11 @@ static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) if (!eeprom_ptrs) return -ENOMEM; /* Read pointer area */ - status = wx_read_ee_hostif_buffer(wxhw, 0, + status = wx_read_ee_hostif_buffer(wx, 0, TXGBE_EEPROM_LAST_WORD, eeprom_ptrs); if (status != 0) { - wx_err(wxhw, "Failed to read EEPROM image\n"); + wx_err(wx, "Failed to read EEPROM image\n"); kvfree(eeprom_ptrs); return status; } @@ -194,7 +190,7 @@ static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) } for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) - if (i != wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) + if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) *checksum += local_buffer[i]; if (eeprom_ptrs) @@ -210,15 +206,14 @@ static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) /** * txgbe_validate_eeprom_checksum - Validate EEPROM checksum - * @hw: pointer to hardware structure + * @wx: pointer to hardware structure * @checksum_val: calculated checksum * * Performs checksum calculation and validates the EEPROM checksum. If the * caller does not need checksum_val, the value can be NULL. **/ -int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val) +int txgbe_validate_eeprom_checksum(struct wx *wx, u16 *checksum_val) { - struct wx_hw *wxhw = &hw->wxhw; u16 read_checksum = 0; u16 checksum; int status; @@ -227,18 +222,18 @@ int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val) * not continue or we could be in for a very long wait while every * EEPROM read fails */ - status = wx_read_ee_hostif(wxhw, 0, &checksum); + status = wx_read_ee_hostif(wx, 0, &checksum); if (status) { - wx_err(wxhw, "EEPROM read failed\n"); + wx_err(wx, "EEPROM read failed\n"); return status; } checksum = 0; - status = txgbe_calc_eeprom_checksum(hw, &checksum); + status = txgbe_calc_eeprom_checksum(wx, &checksum); if (status != 0) return status; - status = wx_read_ee_hostif(wxhw, wxhw->eeprom.sw_region_offset + + status = wx_read_ee_hostif(wx, wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM, &read_checksum); if (status != 0) return status; @@ -248,7 +243,7 @@ int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val) */ if (read_checksum != checksum) { status = -EIO; - wx_err(wxhw, "Invalid EEPROM checksum\n"); + wx_err(wx, "Invalid EEPROM checksum\n"); } /* If the user cares, return the calculated checksum */ @@ -258,55 +253,52 @@ int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val) return status; } -static void txgbe_reset_misc(struct txgbe_hw *hw) +static void txgbe_reset_misc(struct wx *wx) { - struct wx_hw *wxhw = &hw->wxhw; - - wx_reset_misc(wxhw); - txgbe_init_thermal_sensor_thresh(hw); + wx_reset_misc(wx); + txgbe_init_thermal_sensor_thresh(wx); } /** * txgbe_reset_hw - Perform hardware reset - * @hw: pointer to hardware structure + * @wx: pointer to wx structure * * Resets the hardware by resetting the transmit and receive units, masks * and clears all interrupts, perform a PHY reset, and perform a link (MAC) * reset. **/ -int txgbe_reset_hw(struct txgbe_hw *hw) +int txgbe_reset_hw(struct wx *wx) { - struct wx_hw *wxhw = &hw->wxhw; int status; /* Call adapter stop to disable tx/rx and clear interrupts */ - status = wx_stop_adapter(wxhw); + status = wx_stop_adapter(wx); if (status != 0) return status; - if (!(((wxhw->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || - ((wxhw->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) - wx_reset_hostif(wxhw); + if (!(((wx->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || + ((wx->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) + wx_reset_hostif(wx); usleep_range(10, 100); - status = wx_check_flash_load(wxhw, TXGBE_SPI_ILDR_STATUS_LAN_SW_RST(wxhw->bus.func)); + status = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_LAN_SW_RST(wx->bus.func)); if (status != 0) return status; - txgbe_reset_misc(hw); + txgbe_reset_misc(wx); /* Store the permanent mac address */ - wx_get_mac_addr(wxhw, wxhw->mac.perm_addr); + wx_get_mac_addr(wx, wx->mac.perm_addr); /* Store MAC address from RAR0, clear receive address registers, and * clear the multicast table. Also reset num_rar_entries to 128, * since we modify this value when programming the SAN MAC address. */ - wxhw->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; - wx_init_rx_addrs(wxhw); + wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; + wx_init_rx_addrs(wx); - pci_set_master(wxhw->pdev); + pci_set_master(wx->pdev); return 0; } diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h index 6a751a69177b..e82f65dff8a6 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h @@ -4,8 +4,8 @@ #ifndef _TXGBE_HW_H_ #define _TXGBE_HW_H_ -int txgbe_read_pba_string(struct txgbe_hw *hw, u8 *pba_num, u32 pba_num_size); -int txgbe_validate_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum_val); -int txgbe_reset_hw(struct txgbe_hw *hw); +int txgbe_read_pba_string(struct wx *wx, u8 *pba_num, u32 pba_num_size); +int txgbe_validate_eeprom_checksum(struct wx *wx, u16 *checksum_val); +int txgbe_reset_hw(struct wx *wx); #endif /* _TXGBE_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 36780e7f05b7..aa4d09df3b01 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -14,7 +14,6 @@ #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_hw.h" -#include "txgbe.h" char txgbe_driver_name[] = "txgbe"; @@ -35,26 +34,26 @@ static const struct pci_device_id txgbe_pci_tbl[] = { #define DEFAULT_DEBUG_LEVEL_SHIFT 3 -static void txgbe_check_minimum_link(struct txgbe_adapter *adapter) +static void txgbe_check_minimum_link(struct wx *wx) { struct pci_dev *pdev; - pdev = adapter->pdev; + pdev = wx->pdev; pcie_print_link_status(pdev); } /** * txgbe_enumerate_functions - Get the number of ports this device has - * @adapter: adapter structure + * @wx: wx structure * * This function enumerates the phsyical functions co-located on a single slot, * in order to determine how many ports a device has. This is most useful in * determining the required GT/s of PCIe bandwidth necessary for optimal * performance. **/ -static int txgbe_enumerate_functions(struct txgbe_adapter *adapter) +static int txgbe_enumerate_functions(struct wx *wx) { - struct pci_dev *entry, *pdev = adapter->pdev; + struct pci_dev *entry, *pdev = wx->pdev; int physfns = 0; list_for_each_entry(entry, &pdev->bus->devices, bus_list) { @@ -73,197 +72,90 @@ static int txgbe_enumerate_functions(struct txgbe_adapter *adapter) return physfns; } -static void txgbe_sync_mac_table(struct txgbe_adapter *adapter) +static void txgbe_up_complete(struct wx *wx) { - struct txgbe_hw *hw = &adapter->hw; - struct wx_hw *wxhw = &hw->wxhw; - int i; - - for (i = 0; i < wxhw->mac.num_rar_entries; i++) { - if (adapter->mac_table[i].state & TXGBE_MAC_STATE_MODIFIED) { - if (adapter->mac_table[i].state & TXGBE_MAC_STATE_IN_USE) { - wx_set_rar(wxhw, i, - adapter->mac_table[i].addr, - adapter->mac_table[i].pools, - WX_PSR_MAC_SWC_AD_H_AV); - } else { - wx_clear_rar(wxhw, i); - } - adapter->mac_table[i].state &= ~(TXGBE_MAC_STATE_MODIFIED); - } - } -} - -/* this function destroys the first RAR entry */ -static void txgbe_mac_set_default_filter(struct txgbe_adapter *adapter, - u8 *addr) -{ - struct wx_hw *wxhw = &adapter->hw.wxhw; - - memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN); - adapter->mac_table[0].pools = 1ULL; - adapter->mac_table[0].state = (TXGBE_MAC_STATE_DEFAULT | - TXGBE_MAC_STATE_IN_USE); - wx_set_rar(wxhw, 0, adapter->mac_table[0].addr, - adapter->mac_table[0].pools, - WX_PSR_MAC_SWC_AD_H_AV); -} - -static void txgbe_flush_sw_mac_table(struct txgbe_adapter *adapter) -{ - struct wx_hw *wxhw = &adapter->hw.wxhw; - u32 i; - - for (i = 0; i < wxhw->mac.num_rar_entries; i++) { - adapter->mac_table[i].state |= TXGBE_MAC_STATE_MODIFIED; - adapter->mac_table[i].state &= ~TXGBE_MAC_STATE_IN_USE; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); - adapter->mac_table[i].pools = 0; - } - txgbe_sync_mac_table(adapter); -} - -static int txgbe_del_mac_filter(struct txgbe_adapter *adapter, u8 *addr, u16 pool) -{ - struct wx_hw *wxhw = &adapter->hw.wxhw; - u32 i; - - if (is_zero_ether_addr(addr)) - return -EINVAL; - - /* search table for addr, if found, set to 0 and sync */ - for (i = 0; i < wxhw->mac.num_rar_entries; i++) { - if (ether_addr_equal(addr, adapter->mac_table[i].addr)) { - if (adapter->mac_table[i].pools & (1ULL << pool)) { - adapter->mac_table[i].state |= TXGBE_MAC_STATE_MODIFIED; - adapter->mac_table[i].state &= ~TXGBE_MAC_STATE_IN_USE; - adapter->mac_table[i].pools &= ~(1ULL << pool); - txgbe_sync_mac_table(adapter); - } - return 0; - } - - if (adapter->mac_table[i].pools != (1 << pool)) - continue; - if (!ether_addr_equal(addr, adapter->mac_table[i].addr)) - continue; - - adapter->mac_table[i].state |= TXGBE_MAC_STATE_MODIFIED; - adapter->mac_table[i].state &= ~TXGBE_MAC_STATE_IN_USE; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); - adapter->mac_table[i].pools = 0; - txgbe_sync_mac_table(adapter); - return 0; - } - return -ENOMEM; -} - -static void txgbe_up_complete(struct txgbe_adapter *adapter) -{ - struct txgbe_hw *hw = &adapter->hw; - struct wx_hw *wxhw = &hw->wxhw; - - wx_control_hw(wxhw, true); + wx_control_hw(wx, true); } -static void txgbe_reset(struct txgbe_adapter *adapter) +static void txgbe_reset(struct wx *wx) { - struct net_device *netdev = adapter->netdev; - struct txgbe_hw *hw = &adapter->hw; + struct net_device *netdev = wx->netdev; u8 old_addr[ETH_ALEN]; int err; - err = txgbe_reset_hw(hw); + err = txgbe_reset_hw(wx); if (err != 0) - dev_err(&adapter->pdev->dev, "Hardware Error: %d\n", err); + wx_err(wx, "Hardware Error: %d\n", err); /* do not flush user set addresses */ - memcpy(old_addr, &adapter->mac_table[0].addr, netdev->addr_len); - txgbe_flush_sw_mac_table(adapter); - txgbe_mac_set_default_filter(adapter, old_addr); + memcpy(old_addr, &wx->mac_table[0].addr, netdev->addr_len); + wx_flush_sw_mac_table(wx); + wx_mac_set_default_filter(wx, old_addr); } -static void txgbe_disable_device(struct txgbe_adapter *adapter) +static void txgbe_disable_device(struct wx *wx) { - struct net_device *netdev = adapter->netdev; - struct wx_hw *wxhw = &adapter->hw.wxhw; + struct net_device *netdev = wx->netdev; - wx_disable_pcie_master(wxhw); + wx_disable_pcie_master(wx); /* disable receives */ - wx_disable_rx(wxhw); + wx_disable_rx(wx); netif_carrier_off(netdev); netif_tx_disable(netdev); - if (wxhw->bus.func < 2) - wr32m(wxhw, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wxhw->bus.func), 0); + if (wx->bus.func < 2) + wr32m(wx, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wx->bus.func), 0); else - dev_err(&adapter->pdev->dev, - "%s: invalid bus lan id %d\n", - __func__, wxhw->bus.func); + wx_err(wx, "%s: invalid bus lan id %d\n", + __func__, wx->bus.func); - if (!(((wxhw->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || - ((wxhw->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) { + if (!(((wx->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) || + ((wx->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) { /* disable mac transmiter */ - wr32m(wxhw, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); + wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); } /* Disable the Tx DMA engine */ - wr32m(wxhw, WX_TDM_CTL, WX_TDM_CTL_TE, 0); + wr32m(wx, WX_TDM_CTL, WX_TDM_CTL_TE, 0); } -static void txgbe_down(struct txgbe_adapter *adapter) +static void txgbe_down(struct wx *wx) { - txgbe_disable_device(adapter); - txgbe_reset(adapter); + txgbe_disable_device(wx); + txgbe_reset(wx); } /** - * txgbe_sw_init - Initialize general software structures (struct txgbe_adapter) - * @adapter: board private structure to initialize + * txgbe_sw_init - Initialize general software structures (struct wx) + * @wx: board private structure to initialize **/ -static int txgbe_sw_init(struct txgbe_adapter *adapter) +static int txgbe_sw_init(struct wx *wx) { - struct pci_dev *pdev = adapter->pdev; - struct txgbe_hw *hw = &adapter->hw; - struct wx_hw *wxhw = &hw->wxhw; int err; - wxhw->hw_addr = adapter->io_addr; - wxhw->pdev = pdev; + wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; + wx->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES; + wx->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES; + wx->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE; /* PCI config space info */ - err = wx_sw_init(wxhw); + err = wx_sw_init(wx); if (err < 0) { - netif_err(adapter, probe, adapter->netdev, - "read of internal subsystem device id failed\n"); + wx_err(wx, "read of internal subsystem device id failed\n"); return err; } - switch (wxhw->device_id) { + switch (wx->device_id) { case TXGBE_DEV_ID_SP1000: case TXGBE_DEV_ID_WX1820: - wxhw->mac.type = wx_mac_sp; + wx->mac.type = wx_mac_sp; break; default: - wxhw->mac.type = wx_mac_unknown; + wx->mac.type = wx_mac_unknown; break; } - wxhw->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; - wxhw->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES; - wxhw->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES; - wxhw->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE; - - adapter->mac_table = kcalloc(wxhw->mac.num_rar_entries, - sizeof(struct txgbe_mac_addr), - GFP_KERNEL); - if (!adapter->mac_table) { - netif_err(adapter, probe, adapter->netdev, - "mac_table allocation failed\n"); - return -ENOMEM; - } - return 0; } @@ -278,23 +170,23 @@ static int txgbe_sw_init(struct txgbe_adapter *adapter) **/ static int txgbe_open(struct net_device *netdev) { - struct txgbe_adapter *adapter = netdev_priv(netdev); + struct wx *wx = netdev_priv(netdev); - txgbe_up_complete(adapter); + txgbe_up_complete(wx); return 0; } /** * txgbe_close_suspend - actions necessary to both suspend and close flows - * @adapter: the private adapter struct + * @wx: the private wx struct * * This function should contain the necessary work common to both suspending * and closing of the device. */ -static void txgbe_close_suspend(struct txgbe_adapter *adapter) +static void txgbe_close_suspend(struct wx *wx) { - txgbe_disable_device(adapter); + txgbe_disable_device(wx); } /** @@ -310,29 +202,28 @@ static void txgbe_close_suspend(struct txgbe_adapter *adapter) **/ static int txgbe_close(struct net_device *netdev) { - struct txgbe_adapter *adapter = netdev_priv(netdev); + struct wx *wx = netdev_priv(netdev); - txgbe_down(adapter); - wx_control_hw(&adapter->hw.wxhw, false); + txgbe_down(wx); + wx_control_hw(wx, false); return 0; } static void txgbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) { - struct txgbe_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; - struct txgbe_hw *hw = &adapter->hw; - struct wx_hw *wxhw = &hw->wxhw; + struct wx *wx = pci_get_drvdata(pdev); + struct net_device *netdev; + netdev = wx->netdev; netif_device_detach(netdev); rtnl_lock(); if (netif_running(netdev)) - txgbe_close_suspend(adapter); + txgbe_close_suspend(wx); rtnl_unlock(); - wx_control_hw(wxhw, false); + wx_control_hw(wx, false); pci_disable_device(pdev); } @@ -355,39 +246,12 @@ static netdev_tx_t txgbe_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; } -/** - * txgbe_set_mac - Change the Ethernet Address of the NIC - * @netdev: network interface device structure - * @p: pointer to an address structure - * - * Returns 0 on success, negative on failure - **/ -static int txgbe_set_mac(struct net_device *netdev, void *p) -{ - struct txgbe_adapter *adapter = netdev_priv(netdev); - struct wx_hw *wxhw = &adapter->hw.wxhw; - struct sockaddr *addr = p; - int retval; - - retval = eth_prepare_mac_addr_change(netdev, addr); - if (retval) - return retval; - - txgbe_del_mac_filter(adapter, wxhw->mac.addr, 0); - eth_hw_addr_set(netdev, addr->sa_data); - memcpy(wxhw->mac.addr, addr->sa_data, netdev->addr_len); - - txgbe_mac_set_default_filter(adapter, wxhw->mac.addr); - - return 0; -} - static const struct net_device_ops txgbe_netdev_ops = { .ndo_open = txgbe_open, .ndo_stop = txgbe_close, .ndo_start_xmit = txgbe_xmit_frame, .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = txgbe_set_mac, + .ndo_set_mac_address = wx_set_mac, }; /** @@ -398,17 +262,15 @@ static const struct net_device_ops txgbe_netdev_ops = { * Returns 0 on success, negative on failure * * txgbe_probe initializes an adapter identified by a pci_dev structure. - * The OS initialization, configuring of the adapter private structure, + * The OS initialization, configuring of the wx private structure, * and a hardware reset occur. **/ static int txgbe_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { - struct txgbe_adapter *adapter = NULL; - struct txgbe_hw *hw = NULL; - struct wx_hw *wxhw = NULL; struct net_device *netdev; int err, expected_gts; + struct wx *wx = NULL; u16 eeprom_verh = 0, eeprom_verl = 0, offset = 0; u16 eeprom_cfg_blkh = 0, eeprom_cfg_blkl = 0; @@ -440,7 +302,7 @@ static int txgbe_probe(struct pci_dev *pdev, pci_set_master(pdev); netdev = devm_alloc_etherdev_mqs(&pdev->dev, - sizeof(struct txgbe_adapter), + sizeof(struct wx), TXGBE_MAX_TX_QUEUES, TXGBE_MAX_RX_QUEUES); if (!netdev) { @@ -450,17 +312,16 @@ static int txgbe_probe(struct pci_dev *pdev, SET_NETDEV_DEV(netdev, &pdev->dev); - adapter = netdev_priv(netdev); - adapter->netdev = netdev; - adapter->pdev = pdev; - hw = &adapter->hw; - wxhw = &hw->wxhw; - adapter->msg_enable = (1 << DEFAULT_DEBUG_LEVEL_SHIFT) - 1; - - adapter->io_addr = devm_ioremap(&pdev->dev, - pci_resource_start(pdev, 0), - pci_resource_len(pdev, 0)); - if (!adapter->io_addr) { + wx = netdev_priv(netdev); + wx->netdev = netdev; + wx->pdev = pdev; + + wx->msg_enable = (1 << DEFAULT_DEBUG_LEVEL_SHIFT) - 1; + + wx->hw_addr = devm_ioremap(&pdev->dev, + pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0)); + if (!wx->hw_addr) { err = -EIO; goto err_pci_release_regions; } @@ -468,25 +329,25 @@ static int txgbe_probe(struct pci_dev *pdev, netdev->netdev_ops = &txgbe_netdev_ops; /* setup the private structure */ - err = txgbe_sw_init(adapter); + err = txgbe_sw_init(wx); if (err) goto err_free_mac_table; /* check if flash load is done after hw power up */ - err = wx_check_flash_load(wxhw, TXGBE_SPI_ILDR_STATUS_PERST); + err = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_PERST); if (err) goto err_free_mac_table; - err = wx_check_flash_load(wxhw, TXGBE_SPI_ILDR_STATUS_PWRRST); + err = wx_check_flash_load(wx, TXGBE_SPI_ILDR_STATUS_PWRRST); if (err) goto err_free_mac_table; - err = wx_mng_present(wxhw); + err = wx_mng_present(wx); if (err) { dev_err(&pdev->dev, "Management capability is not present\n"); goto err_free_mac_table; } - err = txgbe_reset_hw(hw); + err = txgbe_reset_hw(wx); if (err) { dev_err(&pdev->dev, "HW Init failed: %d\n", err); goto err_free_mac_table; @@ -495,36 +356,36 @@ static int txgbe_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_HIGHDMA; /* make sure the EEPROM is good */ - err = txgbe_validate_eeprom_checksum(hw, NULL); + err = txgbe_validate_eeprom_checksum(wx, NULL); if (err != 0) { dev_err(&pdev->dev, "The EEPROM Checksum Is Not Valid\n"); - wr32(wxhw, WX_MIS_RST, WX_MIS_RST_SW_RST); + wr32(wx, WX_MIS_RST, WX_MIS_RST_SW_RST); err = -EIO; goto err_free_mac_table; } - eth_hw_addr_set(netdev, wxhw->mac.perm_addr); - txgbe_mac_set_default_filter(adapter, wxhw->mac.perm_addr); + eth_hw_addr_set(netdev, wx->mac.perm_addr); + wx_mac_set_default_filter(wx, wx->mac.perm_addr); /* Save off EEPROM version number and Option Rom version which * together make a unique identify for the eeprom */ - wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_VERSION_H, + wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + TXGBE_EEPROM_VERSION_H, &eeprom_verh); - wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_VERSION_L, + wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + TXGBE_EEPROM_VERSION_L, &eeprom_verl); etrack_id = (eeprom_verh << 16) | eeprom_verl; - wx_read_ee_hostif(wxhw, - wxhw->eeprom.sw_region_offset + TXGBE_ISCSI_BOOT_CONFIG, + wx_read_ee_hostif(wx, + wx->eeprom.sw_region_offset + TXGBE_ISCSI_BOOT_CONFIG, &offset); /* Make sure offset to SCSI block is valid */ if (!(offset == 0x0) && !(offset == 0xffff)) { - wx_read_ee_hostif(wxhw, offset + 0x84, &eeprom_cfg_blkh); - wx_read_ee_hostif(wxhw, offset + 0x83, &eeprom_cfg_blkl); + wx_read_ee_hostif(wx, offset + 0x84, &eeprom_cfg_blkh); + wx_read_ee_hostif(wx, offset + 0x83, &eeprom_cfg_blkl); /* Only display Option Rom if exist */ if (eeprom_cfg_blkl && eeprom_cfg_blkh) { @@ -532,15 +393,15 @@ static int txgbe_probe(struct pci_dev *pdev, build = (eeprom_cfg_blkl << 8) | (eeprom_cfg_blkh >> 8); patch = eeprom_cfg_blkh & 0x00ff; - snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + snprintf(wx->eeprom_id, sizeof(wx->eeprom_id), "0x%08x, %d.%d.%d", etrack_id, major, build, patch); } else { - snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + snprintf(wx->eeprom_id, sizeof(wx->eeprom_id), "0x%08x", etrack_id); } } else { - snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + snprintf(wx->eeprom_id, sizeof(wx->eeprom_id), "0x%08x", etrack_id); } @@ -548,7 +409,7 @@ static int txgbe_probe(struct pci_dev *pdev, if (err) goto err_release_hw; - pci_set_drvdata(pdev, adapter); + pci_set_drvdata(pdev, wx); /* calculate the expected PCIe bandwidth required for optimal * performance. Note that some older parts will never have enough @@ -556,27 +417,27 @@ static int txgbe_probe(struct pci_dev *pdev, * parts to ensure that no warning is displayed, as this could confuse * users otherwise. */ - expected_gts = txgbe_enumerate_functions(adapter) * 10; + expected_gts = txgbe_enumerate_functions(wx) * 10; /* don't check link if we failed to enumerate functions */ if (expected_gts > 0) - txgbe_check_minimum_link(adapter); + txgbe_check_minimum_link(wx); else dev_warn(&pdev->dev, "Failed to enumerate PF devices.\n"); /* First try to read PBA as a string */ - err = txgbe_read_pba_string(hw, part_str, TXGBE_PBANUM_LENGTH); + err = txgbe_read_pba_string(wx, part_str, TXGBE_PBANUM_LENGTH); if (err) strncpy(part_str, "Unknown", TXGBE_PBANUM_LENGTH); - netif_info(adapter, probe, netdev, "%pM\n", netdev->dev_addr); + netif_info(wx, probe, netdev, "%pM\n", netdev->dev_addr); return 0; err_release_hw: - wx_control_hw(wxhw, false); + wx_control_hw(wx, false); err_free_mac_table: - kfree(adapter->mac_table); + kfree(wx->mac_table); err_pci_release_regions: pci_disable_pcie_error_reporting(pdev); pci_release_selected_regions(pdev, @@ -597,16 +458,16 @@ err_pci_disable_dev: **/ static void txgbe_remove(struct pci_dev *pdev) { - struct txgbe_adapter *adapter = pci_get_drvdata(pdev); + struct wx *wx = pci_get_drvdata(pdev); struct net_device *netdev; - netdev = adapter->netdev; + netdev = wx->netdev; unregister_netdev(netdev); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); - kfree(adapter->mac_table); + kfree(wx->mac_table); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 740a1c447e20..cbd705a9f4bd 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -67,8 +67,16 @@ #define TXGBE_PBANUM1_PTR 0x06 #define TXGBE_PBANUM_PTR_GUARD 0xFAFA -struct txgbe_hw { - struct wx_hw wxhw; -}; +#define TXGBE_MAX_FDIR_INDICES 63 + +#define TXGBE_MAX_RX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) +#define TXGBE_MAX_TX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) + +#define TXGBE_SP_MAX_TX_QUEUES 128 +#define TXGBE_SP_MAX_RX_QUEUES 128 +#define TXGBE_SP_RAR_ENTRIES 128 +#define TXGBE_SP_MC_TBL_SIZE 128 + +extern char txgbe_driver_name[]; #endif /* _TXGBE_TYPE_H_ */ diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index bd3b0c2655a2..83ff882f5d97 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -623,16 +623,10 @@ static int receive(struct net_device *dev, int cnt) /* --------------------------------------------------------------------- */ -#if defined(__i386__) && !defined(CONFIG_UML) -#include <asm/msr.h> #define GETTICK(x) \ ({ \ - if (boot_cpu_has(X86_FEATURE_TSC)) \ - x = (unsigned int)rdtsc(); \ + x = (unsigned int)get_cycles(); \ }) -#else /* __i386__ && !CONFIG_UML */ -#define GETTICK(x) -#endif /* __i386__ && !CONFIG_UML */ static void epp_bh(struct work_struct *work) { diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index c1b3977e1ae4..c19cd27ac852 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -26,6 +26,8 @@ #include "ipa.h" #include "ipa_reg.h" #include "ipa_endpoint.h" +#include "ipa_power.h" +#include "ipa_uc.h" #include "ipa_interrupt.h" /** @@ -33,47 +35,47 @@ * @ipa: IPA pointer * @irq: Linux IRQ number used for IPA interrupts * @enabled: Mask indicating which interrupts are enabled - * @handler: Array of handlers indexed by IPA interrupt ID */ struct ipa_interrupt { struct ipa *ipa; u32 irq; u32 enabled; - ipa_irq_handler_t handler[IPA_IRQ_COUNT]; }; -/* Returns true if the interrupt type is associated with the microcontroller */ -static bool ipa_interrupt_uc(struct ipa_interrupt *interrupt, u32 irq_id) -{ - return irq_id == IPA_IRQ_UC_0 || irq_id == IPA_IRQ_UC_1; -} - /* Process a particular interrupt type that has been received */ static void ipa_interrupt_process(struct ipa_interrupt *interrupt, u32 irq_id) { - bool uc_irq = ipa_interrupt_uc(interrupt, irq_id); struct ipa *ipa = interrupt->ipa; const struct ipa_reg *reg; u32 mask = BIT(irq_id); u32 offset; - /* For microcontroller interrupts, clear the interrupt right away, - * "to avoid clearing unhandled interrupts." - */ reg = ipa_reg(ipa, IPA_IRQ_CLR); offset = ipa_reg_offset(reg); - if (uc_irq) - iowrite32(mask, ipa->reg_virt + offset); - - if (irq_id < IPA_IRQ_COUNT && interrupt->handler[irq_id]) - interrupt->handler[irq_id](interrupt->ipa, irq_id); - /* Clearing the SUSPEND_TX interrupt also clears the register - * that tells us which suspended endpoint(s) caused the interrupt, - * so defer clearing until after the handler has been called. - */ - if (!uc_irq) + switch (irq_id) { + case IPA_IRQ_UC_0: + case IPA_IRQ_UC_1: + /* For microcontroller interrupts, clear the interrupt right + * away, "to avoid clearing unhandled interrupts." + */ + iowrite32(mask, ipa->reg_virt + offset); + ipa_uc_interrupt_handler(ipa, irq_id); + break; + + case IPA_IRQ_TX_SUSPEND: + /* Clearing the SUSPEND_TX interrupt also clears the + * register that tells us which suspended endpoint(s) + * caused the interrupt, so defer clearing until after + * the handler has been called. + */ + ipa_power_suspend_handler(ipa, irq_id); + fallthrough; + + default: /* Silently ignore (and clear) any other condition */ iowrite32(mask, ipa->reg_virt + offset); + break; + } } /* IPA IRQ handler is threaded */ @@ -127,6 +129,29 @@ out_power_put: return IRQ_HANDLED; } +static void ipa_interrupt_enabled_update(struct ipa *ipa) +{ + const struct ipa_reg *reg = ipa_reg(ipa, IPA_IRQ_EN); + + iowrite32(ipa->interrupt->enabled, ipa->reg_virt + ipa_reg_offset(reg)); +} + +/* Enable an IPA interrupt type */ +void ipa_interrupt_enable(struct ipa *ipa, enum ipa_irq_id ipa_irq) +{ + /* Update the IPA interrupt mask to enable it */ + ipa->interrupt->enabled |= BIT(ipa_irq); + ipa_interrupt_enabled_update(ipa); +} + +/* Disable an IPA interrupt type */ +void ipa_interrupt_disable(struct ipa *ipa, enum ipa_irq_id ipa_irq) +{ + /* Update the IPA interrupt mask to disable it */ + ipa->interrupt->enabled &= ~BIT(ipa_irq); + ipa_interrupt_enabled_update(ipa); +} + void ipa_interrupt_irq_disable(struct ipa *ipa) { disable_irq(ipa->interrupt->irq); @@ -210,44 +235,6 @@ void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt) ipa_interrupt_process(interrupt, IPA_IRQ_TX_SUSPEND); } -/* Add a handler for an IPA interrupt */ -void ipa_interrupt_add(struct ipa_interrupt *interrupt, - enum ipa_irq_id ipa_irq, ipa_irq_handler_t handler) -{ - struct ipa *ipa = interrupt->ipa; - const struct ipa_reg *reg; - - if (WARN_ON(ipa_irq >= IPA_IRQ_COUNT)) - return; - - interrupt->handler[ipa_irq] = handler; - - /* Update the IPA interrupt mask to enable it */ - interrupt->enabled |= BIT(ipa_irq); - - reg = ipa_reg(ipa, IPA_IRQ_EN); - iowrite32(interrupt->enabled, ipa->reg_virt + ipa_reg_offset(reg)); -} - -/* Remove the handler for an IPA interrupt type */ -void -ipa_interrupt_remove(struct ipa_interrupt *interrupt, enum ipa_irq_id ipa_irq) -{ - struct ipa *ipa = interrupt->ipa; - const struct ipa_reg *reg; - - if (WARN_ON(ipa_irq >= IPA_IRQ_COUNT)) - return; - - /* Update the IPA interrupt mask to disable it */ - interrupt->enabled &= ~BIT(ipa_irq); - - reg = ipa_reg(ipa, IPA_IRQ_EN); - iowrite32(interrupt->enabled, ipa->reg_virt + ipa_reg_offset(reg)); - - interrupt->handler[ipa_irq] = NULL; -} - /* Configure the IPA interrupt framework */ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) { diff --git a/drivers/net/ipa/ipa_interrupt.h b/drivers/net/ipa/ipa_interrupt.h index 8a1bd5b89393..12e3e798ccb3 100644 --- a/drivers/net/ipa/ipa_interrupt.h +++ b/drivers/net/ipa/ipa_interrupt.h @@ -11,39 +11,7 @@ struct ipa; struct ipa_interrupt; - -/** - * typedef ipa_irq_handler_t - IPA interrupt handler function type - * @ipa: IPA pointer - * @irq_id: interrupt type - * - * Callback function registered by ipa_interrupt_add() to handle a specific - * IPA interrupt type - */ -typedef void (*ipa_irq_handler_t)(struct ipa *ipa, enum ipa_irq_id irq_id); - -/** - * ipa_interrupt_add() - Register a handler for an IPA interrupt type - * @interrupt: IPA interrupt structure - * @irq_id: IPA interrupt type - * @handler: Handler function for the interrupt - * - * Add a handler for an IPA interrupt and enable it. IPA interrupt - * handlers are run in threaded interrupt context, so are allowed to - * block. - */ -void ipa_interrupt_add(struct ipa_interrupt *interrupt, enum ipa_irq_id irq_id, - ipa_irq_handler_t handler); - -/** - * ipa_interrupt_remove() - Remove the handler for an IPA interrupt type - * @interrupt: IPA interrupt structure - * @irq_id: IPA interrupt type - * - * Remove an IPA interrupt handler and disable it. - */ -void ipa_interrupt_remove(struct ipa_interrupt *interrupt, - enum ipa_irq_id irq_id); +enum ipa_irq_id; /** * ipa_interrupt_suspend_enable - Enable TX_SUSPEND for an endpoint @@ -86,6 +54,20 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt); void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt); /** + * ipa_interrupt_enable() - Enable an IPA interrupt type + * @ipa: IPA pointer + * @ipa_irq: IPA interrupt ID + */ +void ipa_interrupt_enable(struct ipa *ipa, enum ipa_irq_id ipa_irq); + +/** + * ipa_interrupt_disable() - Disable an IPA interrupt type + * @ipa: IPA pointer + * @ipa_irq: IPA interrupt ID + */ +void ipa_interrupt_disable(struct ipa *ipa, enum ipa_irq_id ipa_irq); + +/** * ipa_interrupt_irq_enable() - Enable IPA interrupts * @ipa: IPA pointer * diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c index 8057be8cda80..921eecf3eff6 100644 --- a/drivers/net/ipa/ipa_power.c +++ b/drivers/net/ipa/ipa_power.c @@ -219,17 +219,7 @@ u32 ipa_core_clock_rate(struct ipa *ipa) return ipa->power ? (u32)clk_get_rate(ipa->power->core) : 0; } -/** - * ipa_suspend_handler() - Handle the suspend IPA interrupt - * @ipa: IPA pointer - * @irq_id: IPA interrupt type (unused) - * - * If an RX endpoint is suspended, and the IPA has a packet destined for - * that endpoint, the IPA generates a SUSPEND interrupt to inform the AP - * that it should resume the endpoint. If we get one of these interrupts - * we just wake up the system. - */ -static void ipa_suspend_handler(struct ipa *ipa, enum ipa_irq_id irq_id) +void ipa_power_suspend_handler(struct ipa *ipa, enum ipa_irq_id irq_id) { /* To handle an IPA interrupt we will have resumed the hardware * just to handle the interrupt, so we're done. If we are in a @@ -352,12 +342,11 @@ int ipa_power_setup(struct ipa *ipa) { int ret; - ipa_interrupt_add(ipa->interrupt, IPA_IRQ_TX_SUSPEND, - ipa_suspend_handler); + ipa_interrupt_enable(ipa, IPA_IRQ_TX_SUSPEND); ret = device_init_wakeup(&ipa->pdev->dev, true); if (ret) - ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_TX_SUSPEND); + ipa_interrupt_disable(ipa, IPA_IRQ_TX_SUSPEND); return ret; } @@ -365,7 +354,7 @@ int ipa_power_setup(struct ipa *ipa) void ipa_power_teardown(struct ipa *ipa) { (void)device_init_wakeup(&ipa->pdev->dev, false); - ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_TX_SUSPEND); + ipa_interrupt_disable(ipa, IPA_IRQ_TX_SUSPEND); } /* Initialize IPA power management */ diff --git a/drivers/net/ipa/ipa_power.h b/drivers/net/ipa/ipa_power.h index 896f052e51a1..3a4c59ea1222 100644 --- a/drivers/net/ipa/ipa_power.h +++ b/drivers/net/ipa/ipa_power.h @@ -10,6 +10,7 @@ struct device; struct ipa; struct ipa_power_data; +enum ipa_irq_id; /* IPA device power management function block */ extern const struct dev_pm_ops ipa_pm_ops; @@ -48,6 +49,17 @@ void ipa_power_modem_queue_active(struct ipa *ipa); void ipa_power_retention(struct ipa *ipa, bool enable); /** + * ipa_power_suspend_handler() - Handler for SUSPEND IPA interrupts + * @ipa: IPA pointer + * @irq_id: IPA interrupt ID (unused) + * + * If an RX endpoint is suspended, and the IPA has a packet destined for + * that endpoint, the IPA generates a SUSPEND interrupt to inform the AP + * that it should resume the endpoint. + */ +void ipa_power_suspend_handler(struct ipa *ipa, enum ipa_irq_id irq_id); + +/** * ipa_power_setup() - Set up IPA power management * @ipa: IPA pointer * diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index f0ee47281015..cb8a76a75f21 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -124,7 +124,7 @@ static struct ipa_uc_mem_area *ipa_uc_shared(struct ipa *ipa) } /* Microcontroller event IPA interrupt handler */ -static void ipa_uc_event_handler(struct ipa *ipa, enum ipa_irq_id irq_id) +static void ipa_uc_event_handler(struct ipa *ipa) { struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa); struct device *dev = &ipa->pdev->dev; @@ -138,7 +138,7 @@ static void ipa_uc_event_handler(struct ipa *ipa, enum ipa_irq_id irq_id) } /* Microcontroller response IPA interrupt handler */ -static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id) +static void ipa_uc_response_hdlr(struct ipa *ipa) { struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa); struct device *dev = &ipa->pdev->dev; @@ -170,13 +170,22 @@ static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id) } } +void ipa_uc_interrupt_handler(struct ipa *ipa, enum ipa_irq_id irq_id) +{ + /* Silently ignore anything unrecognized */ + if (irq_id == IPA_IRQ_UC_0) + ipa_uc_event_handler(ipa); + else if (irq_id == IPA_IRQ_UC_1) + ipa_uc_response_hdlr(ipa); +} + /* Configure the IPA microcontroller subsystem */ void ipa_uc_config(struct ipa *ipa) { ipa->uc_powered = false; ipa->uc_loaded = false; - ipa_interrupt_add(ipa->interrupt, IPA_IRQ_UC_0, ipa_uc_event_handler); - ipa_interrupt_add(ipa->interrupt, IPA_IRQ_UC_1, ipa_uc_response_hdlr); + ipa_interrupt_enable(ipa, IPA_IRQ_UC_0); + ipa_interrupt_enable(ipa, IPA_IRQ_UC_1); } /* Inverse of ipa_uc_config() */ @@ -184,8 +193,8 @@ void ipa_uc_deconfig(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_1); - ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_0); + ipa_interrupt_disable(ipa, IPA_IRQ_UC_1); + ipa_interrupt_disable(ipa, IPA_IRQ_UC_0); if (ipa->uc_loaded) ipa_power_retention(ipa, false); diff --git a/drivers/net/ipa/ipa_uc.h b/drivers/net/ipa/ipa_uc.h index 8514096e6f36..85aa0df818c2 100644 --- a/drivers/net/ipa/ipa_uc.h +++ b/drivers/net/ipa/ipa_uc.h @@ -7,6 +7,14 @@ #define _IPA_UC_H_ struct ipa; +enum ipa_irq_id; + +/** + * ipa_uc_interrupt_handler() - Handler for microcontroller IPA interrupts + * @ipa: IPA pointer + * @irq_id: IPA interrupt ID + */ +void ipa_uc_interrupt_handler(struct ipa *ipa, enum ipa_irq_id irq_id); /** * ipa_uc_config() - Configure the IPA microcontroller subsystem diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index bf8ac7a3ded7..17452f818b0d 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2583,16 +2583,56 @@ static bool macsec_is_configured(struct macsec_dev *macsec) return false; } +static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload) +{ + enum macsec_offload prev_offload; + const struct macsec_ops *ops; + struct macsec_context ctx; + struct macsec_dev *macsec; + int ret = 0; + + macsec = macsec_priv(dev); + + /* Check if the offloading mode is supported by the underlying layers */ + if (offload != MACSEC_OFFLOAD_OFF && + !macsec_check_offload(offload, macsec)) + return -EOPNOTSUPP; + + /* Check if the net device is busy. */ + if (netif_running(dev)) + return -EBUSY; + + /* Check if the device already has rules configured: we do not support + * rules migration. + */ + if (macsec_is_configured(macsec)) + return -EBUSY; + + prev_offload = macsec->offload; + + ops = __macsec_get_ops(offload == MACSEC_OFFLOAD_OFF ? prev_offload : offload, + macsec, &ctx); + if (!ops) + return -EOPNOTSUPP; + + macsec->offload = offload; + + ctx.secy = &macsec->secy; + ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx) + : macsec_offload(ops->mdo_add_secy, &ctx); + if (ret) + macsec->offload = prev_offload; + + return ret; +} + static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb_offload[MACSEC_OFFLOAD_ATTR_MAX + 1]; - enum macsec_offload offload, prev_offload; - int (*func)(struct macsec_context *ctx); struct nlattr **attrs = info->attrs; - struct net_device *dev; - const struct macsec_ops *ops; - struct macsec_context ctx; + enum macsec_offload offload; struct macsec_dev *macsec; + struct net_device *dev; int ret = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) @@ -2621,55 +2661,9 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) } offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]); - if (macsec->offload == offload) - goto out; - - /* Check if the offloading mode is supported by the underlying layers */ - if (offload != MACSEC_OFFLOAD_OFF && - !macsec_check_offload(offload, macsec)) { - ret = -EOPNOTSUPP; - goto out; - } - - /* Check if the net device is busy. */ - if (netif_running(dev)) { - ret = -EBUSY; - goto out; - } - - prev_offload = macsec->offload; - macsec->offload = offload; - /* Check if the device already has rules configured: we do not support - * rules migration. - */ - if (macsec_is_configured(macsec)) { - ret = -EBUSY; - goto rollback; - } - - ops = __macsec_get_ops(offload == MACSEC_OFFLOAD_OFF ? prev_offload : offload, - macsec, &ctx); - if (!ops) { - ret = -EOPNOTSUPP; - goto rollback; - } - - if (prev_offload == MACSEC_OFFLOAD_OFF) - func = ops->mdo_add_secy; - else - func = ops->mdo_del_secy; - - ctx.secy = &macsec->secy; - ret = macsec_offload(func, &ctx); - if (ret) - goto rollback; - - rtnl_unlock(); - return 0; - -rollback: - macsec->offload = prev_offload; + if (macsec->offload != offload) + ret = macsec_update_offload(dev, offload); out: rtnl_unlock(); return ret; @@ -3817,6 +3811,8 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); + bool macsec_offload_state_change = false; + enum macsec_offload offload; struct macsec_tx_sc tx_sc; struct macsec_secy secy; int ret; @@ -3840,8 +3836,18 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], if (ret) goto cleanup; + if (data[IFLA_MACSEC_OFFLOAD]) { + offload = nla_get_u8(data[IFLA_MACSEC_OFFLOAD]); + if (macsec->offload != offload) { + macsec_offload_state_change = true; + ret = macsec_update_offload(dev, offload); + if (ret) + goto cleanup; + } + } + /* If h/w offloading is available, propagate to the device */ - if (macsec_is_offloaded(macsec)) { + if (!macsec_offload_state_change && macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; @@ -4240,16 +4246,22 @@ static size_t macsec_get_size(const struct net_device *dev) nla_total_size(1) + /* IFLA_MACSEC_SCB */ nla_total_size(1) + /* IFLA_MACSEC_REPLAY_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_VALIDATION */ + nla_total_size(1) + /* IFLA_MACSEC_OFFLOAD */ 0; } static int macsec_fill_info(struct sk_buff *skb, const struct net_device *dev) { - struct macsec_secy *secy = &macsec_priv(dev)->secy; - struct macsec_tx_sc *tx_sc = &secy->tx_sc; + struct macsec_tx_sc *tx_sc; + struct macsec_dev *macsec; + struct macsec_secy *secy; u64 csid; + macsec = macsec_priv(dev); + secy = &macsec->secy; + tx_sc = &secy->tx_sc; + switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; @@ -4274,6 +4286,7 @@ static int macsec_fill_info(struct sk_buff *skb, nla_put_u8(skb, IFLA_MACSEC_SCB, tx_sc->scb) || nla_put_u8(skb, IFLA_MACSEC_REPLAY_PROTECT, secy->replay_protect) || nla_put_u8(skb, IFLA_MACSEC_VALIDATION, secy->validate_frames) || + nla_put_u8(skb, IFLA_MACSEC_OFFLOAD, macsec->offload) || 0) goto nla_put_failure; diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index 944d005d2bd1..c727103c8b05 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -104,61 +104,36 @@ static int aspeed_mdio_write_c22(struct mii_bus *bus, int addr, int regnum, addr, regnum, val); } -static int aspeed_mdio_read_c45(struct mii_bus *bus, int addr, int regnum) +static int aspeed_mdio_read_c45(struct mii_bus *bus, int addr, int devad, + int regnum) { - u8 c45_dev = (regnum >> 16) & 0x1F; - u16 c45_addr = regnum & 0xFFFF; int rc; rc = aspeed_mdio_op(bus, ASPEED_MDIO_CTRL_ST_C45, MDIO_C45_OP_ADDR, - addr, c45_dev, c45_addr); + addr, devad, regnum); if (rc < 0) return rc; rc = aspeed_mdio_op(bus, ASPEED_MDIO_CTRL_ST_C45, MDIO_C45_OP_READ, - addr, c45_dev, 0); + addr, devad, 0); if (rc < 0) return rc; return aspeed_mdio_get_data(bus); } -static int aspeed_mdio_write_c45(struct mii_bus *bus, int addr, int regnum, - u16 val) +static int aspeed_mdio_write_c45(struct mii_bus *bus, int addr, int devad, + int regnum, u16 val) { - u8 c45_dev = (regnum >> 16) & 0x1F; - u16 c45_addr = regnum & 0xFFFF; int rc; rc = aspeed_mdio_op(bus, ASPEED_MDIO_CTRL_ST_C45, MDIO_C45_OP_ADDR, - addr, c45_dev, c45_addr); + addr, devad, regnum); if (rc < 0) return rc; return aspeed_mdio_op(bus, ASPEED_MDIO_CTRL_ST_C45, MDIO_C45_OP_WRITE, - addr, c45_dev, val); -} - -static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum) -{ - dev_dbg(&bus->dev, "%s: addr: %d, regnum: %d\n", __func__, addr, - regnum); - - if (regnum & MII_ADDR_C45) - return aspeed_mdio_read_c45(bus, addr, regnum); - - return aspeed_mdio_read_c22(bus, addr, regnum); -} - -static int aspeed_mdio_write(struct mii_bus *bus, int addr, int regnum, u16 val) -{ - dev_dbg(&bus->dev, "%s: addr: %d, regnum: %d, val: 0x%x\n", - __func__, addr, regnum, val); - - if (regnum & MII_ADDR_C45) - return aspeed_mdio_write_c45(bus, addr, regnum, val); - - return aspeed_mdio_write_c22(bus, addr, regnum, val); + addr, devad, val); } static int aspeed_mdio_probe(struct platform_device *pdev) @@ -185,9 +160,10 @@ static int aspeed_mdio_probe(struct platform_device *pdev) bus->name = DRV_NAME; snprintf(bus->id, MII_BUS_ID_SIZE, "%s%d", pdev->name, pdev->id); bus->parent = &pdev->dev; - bus->read = aspeed_mdio_read; - bus->write = aspeed_mdio_write; - bus->probe_capabilities = MDIOBUS_C22_C45; + bus->read = aspeed_mdio_read_c22; + bus->write = aspeed_mdio_write_c22; + bus->read_c45 = aspeed_mdio_read_c45; + bus->write_c45 = aspeed_mdio_write_c45; rc = of_mdiobus_register(bus, pdev->dev.of_node); if (rc) { diff --git a/drivers/net/mdio/mdio-bitbang.c b/drivers/net/mdio/mdio-bitbang.c index 07609114a26b..b83932562be2 100644 --- a/drivers/net/mdio/mdio-bitbang.c +++ b/drivers/net/mdio/mdio-bitbang.c @@ -127,14 +127,12 @@ static void mdiobb_cmd(struct mdiobb_ctrl *ctrl, int op, u8 phy, u8 reg) /* In clause 45 mode all commands are prefixed by MDIO_ADDR to specify the lower 16 bits of the 21 bit address. This transfer is done identically to a - MDIO_WRITE except for a different code. To enable clause 45 mode or - MII_ADDR_C45 into the address. Theoretically clause 45 and normal devices - can exist on the same bus. Normal devices should ignore the MDIO_ADDR + MDIO_WRITE except for a different code. Theoretically clause 45 and normal + devices can exist on the same bus. Normal devices should ignore the MDIO_ADDR phase. */ -static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr) +static void mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, int dev_addr, + int reg) { - unsigned int dev_addr = (addr >> 16) & 0x1F; - unsigned int reg = addr & 0xFFFF; mdiobb_cmd(ctrl, MDIO_C45_ADDR, phy, dev_addr); /* send the turnaround (10) */ @@ -145,21 +143,13 @@ static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr) ctrl->ops->set_mdio_dir(ctrl, 0); mdiobb_get_bit(ctrl); - - return dev_addr; } -int mdiobb_read(struct mii_bus *bus, int phy, int reg) +static int mdiobb_read_common(struct mii_bus *bus, int phy) { struct mdiobb_ctrl *ctrl = bus->priv; int ret, i; - if (reg & MII_ADDR_C45) { - reg = mdiobb_cmd_addr(ctrl, phy, reg); - mdiobb_cmd(ctrl, MDIO_C45_READ, phy, reg); - } else - mdiobb_cmd(ctrl, ctrl->op_c22_read, phy, reg); - ctrl->ops->set_mdio_dir(ctrl, 0); /* check the turnaround bit: the PHY should be driving it to zero, if this @@ -180,17 +170,31 @@ int mdiobb_read(struct mii_bus *bus, int phy, int reg) mdiobb_get_bit(ctrl); return ret; } -EXPORT_SYMBOL(mdiobb_read); -int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) +int mdiobb_read_c22(struct mii_bus *bus, int phy, int reg) { struct mdiobb_ctrl *ctrl = bus->priv; - if (reg & MII_ADDR_C45) { - reg = mdiobb_cmd_addr(ctrl, phy, reg); - mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, reg); - } else - mdiobb_cmd(ctrl, ctrl->op_c22_write, phy, reg); + mdiobb_cmd(ctrl, ctrl->op_c22_read, phy, reg); + + return mdiobb_read_common(bus, phy); +} +EXPORT_SYMBOL(mdiobb_read_c22); + +int mdiobb_read_c45(struct mii_bus *bus, int phy, int devad, int reg) +{ + struct mdiobb_ctrl *ctrl = bus->priv; + + mdiobb_cmd_addr(ctrl, phy, devad, reg); + mdiobb_cmd(ctrl, MDIO_C45_READ, phy, reg); + + return mdiobb_read_common(bus, phy); +} +EXPORT_SYMBOL(mdiobb_read_c45); + +static int mdiobb_write_common(struct mii_bus *bus, u16 val) +{ + struct mdiobb_ctrl *ctrl = bus->priv; /* send the turnaround (10) */ mdiobb_send_bit(ctrl, 1); @@ -202,7 +206,27 @@ int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) mdiobb_get_bit(ctrl); return 0; } -EXPORT_SYMBOL(mdiobb_write); + +int mdiobb_write_c22(struct mii_bus *bus, int phy, int reg, u16 val) +{ + struct mdiobb_ctrl *ctrl = bus->priv; + + mdiobb_cmd(ctrl, ctrl->op_c22_write, phy, reg); + + return mdiobb_write_common(bus, val); +} +EXPORT_SYMBOL(mdiobb_write_c22); + +int mdiobb_write_c45(struct mii_bus *bus, int phy, int devad, int reg, u16 val) +{ + struct mdiobb_ctrl *ctrl = bus->priv; + + mdiobb_cmd_addr(ctrl, phy, devad, reg); + mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, reg); + + return mdiobb_write_common(bus, val); +} +EXPORT_SYMBOL(mdiobb_write_c45); struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl) { @@ -214,8 +238,11 @@ struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl) __module_get(ctrl->ops->owner); - bus->read = mdiobb_read; - bus->write = mdiobb_write; + bus->read = mdiobb_read_c22; + bus->write = mdiobb_write_c22; + bus->read_c45 = mdiobb_read_c45; + bus->write_c45 = mdiobb_write_c45; + bus->priv = ctrl; if (!ctrl->override_op_c22) { ctrl->op_c22_read = MDIO_READ; diff --git a/drivers/net/mdio/mdio-cavium.c b/drivers/net/mdio/mdio-cavium.c index 95ce274c1be1..100e46a702ee 100644 --- a/drivers/net/mdio/mdio-cavium.c +++ b/drivers/net/mdio/mdio-cavium.c @@ -26,7 +26,7 @@ static void cavium_mdiobus_set_mode(struct cavium_mdiobus *p, } static int cavium_mdiobus_c45_addr(struct cavium_mdiobus *p, - int phy_id, int regnum) + int phy_id, int devad, int regnum) { union cvmx_smix_cmd smi_cmd; union cvmx_smix_wr_dat smi_wr; @@ -38,12 +38,10 @@ static int cavium_mdiobus_c45_addr(struct cavium_mdiobus *p, smi_wr.s.dat = regnum & 0xffff; oct_mdio_writeq(smi_wr.u64, p->register_base + SMI_WR_DAT); - regnum = (regnum >> 16) & 0x1f; - smi_cmd.u64 = 0; smi_cmd.s.phy_op = 0; /* MDIO_CLAUSE_45_ADDRESS */ smi_cmd.s.phy_adr = phy_id; - smi_cmd.s.reg_adr = regnum; + smi_cmd.s.reg_adr = devad; oct_mdio_writeq(smi_cmd.u64, p->register_base + SMI_CMD); do { @@ -59,28 +57,51 @@ static int cavium_mdiobus_c45_addr(struct cavium_mdiobus *p, return 0; } -int cavium_mdiobus_read(struct mii_bus *bus, int phy_id, int regnum) +int cavium_mdiobus_read_c22(struct mii_bus *bus, int phy_id, int regnum) { struct cavium_mdiobus *p = bus->priv; union cvmx_smix_cmd smi_cmd; union cvmx_smix_rd_dat smi_rd; - unsigned int op = 1; /* MDIO_CLAUSE_22_READ */ int timeout = 1000; - if (regnum & MII_ADDR_C45) { - int r = cavium_mdiobus_c45_addr(p, phy_id, regnum); + cavium_mdiobus_set_mode(p, C22); + + smi_cmd.u64 = 0; + smi_cmd.s.phy_op = 1; /* MDIO_CLAUSE_22_READ */ + smi_cmd.s.phy_adr = phy_id; + smi_cmd.s.reg_adr = regnum; + oct_mdio_writeq(smi_cmd.u64, p->register_base + SMI_CMD); + + do { + /* Wait 1000 clocks so we don't saturate the RSL bus + * doing reads. + */ + __delay(1000); + smi_rd.u64 = oct_mdio_readq(p->register_base + SMI_RD_DAT); + } while (smi_rd.s.pending && --timeout); + + if (smi_rd.s.val) + return smi_rd.s.dat; + else + return -EIO; +} +EXPORT_SYMBOL(cavium_mdiobus_read_c22); - if (r < 0) - return r; +int cavium_mdiobus_read_c45(struct mii_bus *bus, int phy_id, int devad, + int regnum) +{ + struct cavium_mdiobus *p = bus->priv; + union cvmx_smix_cmd smi_cmd; + union cvmx_smix_rd_dat smi_rd; + int timeout = 1000; + int r; - regnum = (regnum >> 16) & 0x1f; - op = 3; /* MDIO_CLAUSE_45_READ */ - } else { - cavium_mdiobus_set_mode(p, C22); - } + r = cavium_mdiobus_c45_addr(p, phy_id, devad, regnum); + if (r < 0) + return r; smi_cmd.u64 = 0; - smi_cmd.s.phy_op = op; + smi_cmd.s.phy_op = 3; /* MDIO_CLAUSE_45_READ */ smi_cmd.s.phy_adr = phy_id; smi_cmd.s.reg_adr = regnum; oct_mdio_writeq(smi_cmd.u64, p->register_base + SMI_CMD); @@ -98,36 +119,64 @@ int cavium_mdiobus_read(struct mii_bus *bus, int phy_id, int regnum) else return -EIO; } -EXPORT_SYMBOL(cavium_mdiobus_read); +EXPORT_SYMBOL(cavium_mdiobus_read_c45); -int cavium_mdiobus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val) +int cavium_mdiobus_write_c22(struct mii_bus *bus, int phy_id, int regnum, + u16 val) { struct cavium_mdiobus *p = bus->priv; union cvmx_smix_cmd smi_cmd; union cvmx_smix_wr_dat smi_wr; - unsigned int op = 0; /* MDIO_CLAUSE_22_WRITE */ int timeout = 1000; - if (regnum & MII_ADDR_C45) { - int r = cavium_mdiobus_c45_addr(p, phy_id, regnum); + cavium_mdiobus_set_mode(p, C22); - if (r < 0) - return r; + smi_wr.u64 = 0; + smi_wr.s.dat = val; + oct_mdio_writeq(smi_wr.u64, p->register_base + SMI_WR_DAT); - regnum = (regnum >> 16) & 0x1f; - op = 1; /* MDIO_CLAUSE_45_WRITE */ - } else { - cavium_mdiobus_set_mode(p, C22); - } + smi_cmd.u64 = 0; + smi_cmd.s.phy_op = 0; /* MDIO_CLAUSE_22_WRITE */ + smi_cmd.s.phy_adr = phy_id; + smi_cmd.s.reg_adr = regnum; + oct_mdio_writeq(smi_cmd.u64, p->register_base + SMI_CMD); + + do { + /* Wait 1000 clocks so we don't saturate the RSL bus + * doing reads. + */ + __delay(1000); + smi_wr.u64 = oct_mdio_readq(p->register_base + SMI_WR_DAT); + } while (smi_wr.s.pending && --timeout); + + if (timeout <= 0) + return -EIO; + + return 0; +} +EXPORT_SYMBOL(cavium_mdiobus_write_c22); + +int cavium_mdiobus_write_c45(struct mii_bus *bus, int phy_id, int devad, + int regnum, u16 val) +{ + struct cavium_mdiobus *p = bus->priv; + union cvmx_smix_cmd smi_cmd; + union cvmx_smix_wr_dat smi_wr; + int timeout = 1000; + int r; + + r = cavium_mdiobus_c45_addr(p, phy_id, devad, regnum); + if (r < 0) + return r; smi_wr.u64 = 0; smi_wr.s.dat = val; oct_mdio_writeq(smi_wr.u64, p->register_base + SMI_WR_DAT); smi_cmd.u64 = 0; - smi_cmd.s.phy_op = op; + smi_cmd.s.phy_op = 1; /* MDIO_CLAUSE_45_WRITE */ smi_cmd.s.phy_adr = phy_id; - smi_cmd.s.reg_adr = regnum; + smi_cmd.s.reg_adr = devad; oct_mdio_writeq(smi_cmd.u64, p->register_base + SMI_CMD); do { @@ -143,7 +192,7 @@ int cavium_mdiobus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val) return 0; } -EXPORT_SYMBOL(cavium_mdiobus_write); +EXPORT_SYMBOL(cavium_mdiobus_write_c45); MODULE_DESCRIPTION("Common code for OCTEON and Thunder MDIO bus drivers"); MODULE_AUTHOR("David Daney"); diff --git a/drivers/net/mdio/mdio-cavium.h b/drivers/net/mdio/mdio-cavium.h index a2245d436f5d..71b8e20cd664 100644 --- a/drivers/net/mdio/mdio-cavium.h +++ b/drivers/net/mdio/mdio-cavium.h @@ -114,5 +114,10 @@ static inline u64 oct_mdio_readq(void __iomem *addr) #define oct_mdio_readq(addr) readq(addr) #endif -int cavium_mdiobus_read(struct mii_bus *bus, int phy_id, int regnum); -int cavium_mdiobus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val); +int cavium_mdiobus_read_c22(struct mii_bus *bus, int phy_id, int regnum); +int cavium_mdiobus_write_c22(struct mii_bus *bus, int phy_id, int regnum, + u16 val); +int cavium_mdiobus_read_c45(struct mii_bus *bus, int phy_id, int devad, + int regnum); +int cavium_mdiobus_write_c45(struct mii_bus *bus, int phy_id, int devad, + int regnum, u16 val); diff --git a/drivers/net/mdio/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index bf8bf5e20faf..9577a1842997 100644 --- a/drivers/net/mdio/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -30,7 +30,8 @@ static unsigned int i2c_mii_phy_addr(int phy_id) return phy_id + 0x40; } -static int i2c_mii_read_default(struct mii_bus *bus, int phy_id, int reg) +static int i2c_mii_read_default_c45(struct mii_bus *bus, int phy_id, int devad, + int reg) { struct i2c_adapter *i2c = bus->priv; struct i2c_msg msgs[2]; @@ -41,8 +42,8 @@ static int i2c_mii_read_default(struct mii_bus *bus, int phy_id, int reg) return 0xffff; p = addr; - if (reg & MII_ADDR_C45) { - *p++ = 0x20 | ((reg >> 16) & 31); + if (devad >= 0) { + *p++ = 0x20 | devad; *p++ = reg >> 8; } *p++ = reg; @@ -64,8 +65,8 @@ static int i2c_mii_read_default(struct mii_bus *bus, int phy_id, int reg) return data[0] << 8 | data[1]; } -static int i2c_mii_write_default(struct mii_bus *bus, int phy_id, int reg, - u16 val) +static int i2c_mii_write_default_c45(struct mii_bus *bus, int phy_id, + int devad, int reg, u16 val) { struct i2c_adapter *i2c = bus->priv; struct i2c_msg msg; @@ -76,8 +77,8 @@ static int i2c_mii_write_default(struct mii_bus *bus, int phy_id, int reg, return 0; p = data; - if (reg & MII_ADDR_C45) { - *p++ = (reg >> 16) & 31; + if (devad >= 0) { + *p++ = devad; *p++ = reg >> 8; } *p++ = reg; @@ -94,6 +95,17 @@ static int i2c_mii_write_default(struct mii_bus *bus, int phy_id, int reg, return ret < 0 ? ret : 0; } +static int i2c_mii_read_default_c22(struct mii_bus *bus, int phy_id, int reg) +{ + return i2c_mii_read_default_c45(bus, phy_id, -1, reg); +} + +static int i2c_mii_write_default_c22(struct mii_bus *bus, int phy_id, int reg, + u16 val) +{ + return i2c_mii_write_default_c45(bus, phy_id, -1, reg, val); +} + /* RollBall SFPs do not access internal PHY via I2C address 0x56, but * instead via address 0x51, when SFP page is set to 0x03 and password to * 0xffffffff. @@ -403,8 +415,10 @@ struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, mii->write = i2c_mii_write_rollball; break; default: - mii->read = i2c_mii_read_default; - mii->write = i2c_mii_write_default; + mii->read = i2c_mii_read_default_c22; + mii->write = i2c_mii_write_default_c22; + mii->read_c45 = i2c_mii_read_default_c45; + mii->write_c45 = i2c_mii_write_default_c45; break; } diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c index 4eba5a91075c..78b93de636f5 100644 --- a/drivers/net/mdio/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c @@ -53,7 +53,8 @@ static int ipq4019_mdio_wait_busy(struct mii_bus *bus) IPQ4019_MDIO_SLEEP, IPQ4019_MDIO_TIMEOUT); } -static int ipq4019_mdio_read(struct mii_bus *bus, int mii_id, int regnum) +static int ipq4019_mdio_read_c45(struct mii_bus *bus, int mii_id, int mmd, + int reg) { struct ipq4019_mdio_data *priv = bus->priv; unsigned int data; @@ -62,61 +63,71 @@ static int ipq4019_mdio_read(struct mii_bus *bus, int mii_id, int regnum) if (ipq4019_mdio_wait_busy(bus)) return -ETIMEDOUT; - /* Clause 45 support */ - if (regnum & MII_ADDR_C45) { - unsigned int mmd = (regnum >> 16) & 0x1F; - unsigned int reg = regnum & 0xFFFF; + data = readl(priv->membase + MDIO_MODE_REG); - /* Enter Clause 45 mode */ - data = readl(priv->membase + MDIO_MODE_REG); + data |= MDIO_MODE_C45; - data |= MDIO_MODE_C45; + writel(data, priv->membase + MDIO_MODE_REG); - writel(data, priv->membase + MDIO_MODE_REG); + /* issue the phy address and mmd */ + writel((mii_id << 8) | mmd, priv->membase + MDIO_ADDR_REG); - /* issue the phy address and mmd */ - writel((mii_id << 8) | mmd, priv->membase + MDIO_ADDR_REG); + /* issue reg */ + writel(reg, priv->membase + MDIO_DATA_WRITE_REG); - /* issue reg */ - writel(reg, priv->membase + MDIO_DATA_WRITE_REG); + cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_ADDR; - cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_ADDR; - } else { - /* Enter Clause 22 mode */ - data = readl(priv->membase + MDIO_MODE_REG); + /* issue read command */ + writel(cmd, priv->membase + MDIO_CMD_REG); - data &= ~MDIO_MODE_C45; + /* Wait read complete */ + if (ipq4019_mdio_wait_busy(bus)) + return -ETIMEDOUT; - writel(data, priv->membase + MDIO_MODE_REG); + cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_READ; - /* issue the phy address and reg */ - writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG); + writel(cmd, priv->membase + MDIO_CMD_REG); - cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_READ; - } + if (ipq4019_mdio_wait_busy(bus)) + return -ETIMEDOUT; - /* issue read command */ - writel(cmd, priv->membase + MDIO_CMD_REG); + /* Read and return data */ + return readl(priv->membase + MDIO_DATA_READ_REG); +} + +static int ipq4019_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum) +{ + struct ipq4019_mdio_data *priv = bus->priv; + unsigned int data; + unsigned int cmd; - /* Wait read complete */ if (ipq4019_mdio_wait_busy(bus)) return -ETIMEDOUT; - if (regnum & MII_ADDR_C45) { - cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_READ; + data = readl(priv->membase + MDIO_MODE_REG); - writel(cmd, priv->membase + MDIO_CMD_REG); + data &= ~MDIO_MODE_C45; - if (ipq4019_mdio_wait_busy(bus)) - return -ETIMEDOUT; - } + writel(data, priv->membase + MDIO_MODE_REG); + + /* issue the phy address and reg */ + writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG); + + cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_READ; + + /* issue read command */ + writel(cmd, priv->membase + MDIO_CMD_REG); + + /* Wait read complete */ + if (ipq4019_mdio_wait_busy(bus)) + return -ETIMEDOUT; /* Read and return data */ return readl(priv->membase + MDIO_DATA_READ_REG); } -static int ipq4019_mdio_write(struct mii_bus *bus, int mii_id, int regnum, - u16 value) +static int ipq4019_mdio_write_c45(struct mii_bus *bus, int mii_id, int mmd, + int reg, u16 value) { struct ipq4019_mdio_data *priv = bus->priv; unsigned int data; @@ -125,50 +136,63 @@ static int ipq4019_mdio_write(struct mii_bus *bus, int mii_id, int regnum, if (ipq4019_mdio_wait_busy(bus)) return -ETIMEDOUT; - /* Clause 45 support */ - if (regnum & MII_ADDR_C45) { - unsigned int mmd = (regnum >> 16) & 0x1F; - unsigned int reg = regnum & 0xFFFF; + data = readl(priv->membase + MDIO_MODE_REG); - /* Enter Clause 45 mode */ - data = readl(priv->membase + MDIO_MODE_REG); + data |= MDIO_MODE_C45; - data |= MDIO_MODE_C45; + writel(data, priv->membase + MDIO_MODE_REG); - writel(data, priv->membase + MDIO_MODE_REG); + /* issue the phy address and mmd */ + writel((mii_id << 8) | mmd, priv->membase + MDIO_ADDR_REG); - /* issue the phy address and mmd */ - writel((mii_id << 8) | mmd, priv->membase + MDIO_ADDR_REG); + /* issue reg */ + writel(reg, priv->membase + MDIO_DATA_WRITE_REG); - /* issue reg */ - writel(reg, priv->membase + MDIO_DATA_WRITE_REG); + cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_ADDR; - cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_ADDR; + writel(cmd, priv->membase + MDIO_CMD_REG); - writel(cmd, priv->membase + MDIO_CMD_REG); + if (ipq4019_mdio_wait_busy(bus)) + return -ETIMEDOUT; - if (ipq4019_mdio_wait_busy(bus)) - return -ETIMEDOUT; - } else { - /* Enter Clause 22 mode */ - data = readl(priv->membase + MDIO_MODE_REG); + /* issue write data */ + writel(value, priv->membase + MDIO_DATA_WRITE_REG); - data &= ~MDIO_MODE_C45; + cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_WRITE; + writel(cmd, priv->membase + MDIO_CMD_REG); - writel(data, priv->membase + MDIO_MODE_REG); + /* Wait write complete */ + if (ipq4019_mdio_wait_busy(bus)) + return -ETIMEDOUT; - /* issue the phy address and reg */ - writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG); - } + return 0; +} + +static int ipq4019_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum, + u16 value) +{ + struct ipq4019_mdio_data *priv = bus->priv; + unsigned int data; + unsigned int cmd; + + if (ipq4019_mdio_wait_busy(bus)) + return -ETIMEDOUT; + + /* Enter Clause 22 mode */ + data = readl(priv->membase + MDIO_MODE_REG); + + data &= ~MDIO_MODE_C45; + + writel(data, priv->membase + MDIO_MODE_REG); + + /* issue the phy address and reg */ + writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG); /* issue write data */ writel(value, priv->membase + MDIO_DATA_WRITE_REG); /* issue write command */ - if (regnum & MII_ADDR_C45) - cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_WRITE; - else - cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_WRITE; + cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_WRITE; writel(cmd, priv->membase + MDIO_CMD_REG); @@ -235,8 +259,10 @@ static int ipq4019_mdio_probe(struct platform_device *pdev) priv->eth_ldo_rdy = devm_ioremap_resource(&pdev->dev, res); bus->name = "ipq4019_mdio"; - bus->read = ipq4019_mdio_read; - bus->write = ipq4019_mdio_write; + bus->read = ipq4019_mdio_read_c22; + bus->write = ipq4019_mdio_write_c22; + bus->read_c45 = ipq4019_mdio_read_c45; + bus->write_c45 = ipq4019_mdio_write_c45; bus->reset = ipq_mdio_reset; bus->parent = &pdev->dev; snprintf(bus->id, MII_BUS_ID_SIZE, "%s%d", pdev->name, pdev->id); diff --git a/drivers/net/mdio/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c index 014c0baedbd2..956d54846b62 100644 --- a/drivers/net/mdio/mdio-mux-bcm-iproc.c +++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c @@ -98,7 +98,7 @@ static int iproc_mdio_wait_for_idle(void __iomem *base, bool result) * Return value: Successful Read operation returns read reg values and write * operation returns 0. Failure operation returns negative error code. */ -static int start_miim_ops(void __iomem *base, +static int start_miim_ops(void __iomem *base, bool c45, u16 phyid, u32 reg, u16 val, u32 op) { u32 param; @@ -112,7 +112,7 @@ static int start_miim_ops(void __iomem *base, param = readl(base + MDIO_PARAM_OFFSET); param |= phyid << MDIO_PARAM_PHY_ID; param |= val << MDIO_PARAM_PHY_DATA; - if (reg & MII_ADDR_C45) + if (c45) param |= BIT(MDIO_PARAM_C45_SEL); writel(param, base + MDIO_PARAM_OFFSET); @@ -131,28 +131,58 @@ err: return ret; } -static int iproc_mdiomux_read(struct mii_bus *bus, int phyid, int reg) +static int iproc_mdiomux_read_c22(struct mii_bus *bus, int phyid, int reg) { struct iproc_mdiomux_desc *md = bus->priv; int ret; - ret = start_miim_ops(md->base, phyid, reg, 0, MDIO_CTRL_READ_OP); + ret = start_miim_ops(md->base, false, phyid, reg, 0, MDIO_CTRL_READ_OP); if (ret < 0) - dev_err(&bus->dev, "mdiomux read operation failed!!!"); + dev_err(&bus->dev, "mdiomux c22 read operation failed!!!"); return ret; } -static int iproc_mdiomux_write(struct mii_bus *bus, - int phyid, int reg, u16 val) +static int iproc_mdiomux_read_c45(struct mii_bus *bus, int phyid, int devad, + int reg) +{ + struct iproc_mdiomux_desc *md = bus->priv; + int ret; + + ret = start_miim_ops(md->base, true, phyid, reg | devad << 16, 0, + MDIO_CTRL_READ_OP); + if (ret < 0) + dev_err(&bus->dev, "mdiomux read c45 operation failed!!!"); + + return ret; +} + +static int iproc_mdiomux_write_c22(struct mii_bus *bus, + int phyid, int reg, u16 val) +{ + struct iproc_mdiomux_desc *md = bus->priv; + int ret; + + /* Write val at reg offset */ + ret = start_miim_ops(md->base, false, phyid, reg, val, + MDIO_CTRL_WRITE_OP); + if (ret < 0) + dev_err(&bus->dev, "mdiomux write c22 operation failed!!!"); + + return ret; +} + +static int iproc_mdiomux_write_c45(struct mii_bus *bus, + int phyid, int devad, int reg, u16 val) { struct iproc_mdiomux_desc *md = bus->priv; int ret; /* Write val at reg offset */ - ret = start_miim_ops(md->base, phyid, reg, val, MDIO_CTRL_WRITE_OP); + ret = start_miim_ops(md->base, true, phyid, reg | devad << 16, val, + MDIO_CTRL_WRITE_OP); if (ret < 0) - dev_err(&bus->dev, "mdiomux write operation failed!!!"); + dev_err(&bus->dev, "mdiomux write c45 operation failed!!!"); return ret; } @@ -223,8 +253,10 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev) bus->name = "iProc MDIO mux bus"; snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id); bus->parent = &pdev->dev; - bus->read = iproc_mdiomux_read; - bus->write = iproc_mdiomux_write; + bus->read = iproc_mdiomux_read_c22; + bus->write = iproc_mdiomux_write_c22; + bus->read_c45 = iproc_mdiomux_read_c45; + bus->write_c45 = iproc_mdiomux_write_c45; bus->phy_mask = ~0; bus->dev.of_node = pdev->dev.of_node; diff --git a/drivers/net/mdio/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index e096e68ac667..7c65c547d377 100644 --- a/drivers/net/mdio/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c @@ -58,8 +58,10 @@ static int octeon_mdiobus_probe(struct platform_device *pdev) snprintf(bus->mii_bus->id, MII_BUS_ID_SIZE, "%px", bus->register_base); bus->mii_bus->parent = &pdev->dev; - bus->mii_bus->read = cavium_mdiobus_read; - bus->mii_bus->write = cavium_mdiobus_write; + bus->mii_bus->read = cavium_mdiobus_read_c22; + bus->mii_bus->write = cavium_mdiobus_write_c22; + bus->mii_bus->read_c45 = cavium_mdiobus_read_c45; + bus->mii_bus->write_c45 = cavium_mdiobus_write_c45; platform_set_drvdata(pdev, bus); diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index 822d2cdd2f35..3847ee92c109 100644 --- a/drivers/net/mdio/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c @@ -93,8 +93,10 @@ static int thunder_mdiobus_pci_probe(struct pci_dev *pdev, bus->mii_bus->name = KBUILD_MODNAME; snprintf(bus->mii_bus->id, MII_BUS_ID_SIZE, "%llx", r.start); bus->mii_bus->parent = &pdev->dev; - bus->mii_bus->read = cavium_mdiobus_read; - bus->mii_bus->write = cavium_mdiobus_write; + bus->mii_bus->read = cavium_mdiobus_read_c22; + bus->mii_bus->write = cavium_mdiobus_write_c22; + bus->mii_bus->read_c45 = cavium_mdiobus_read_c45; + bus->mii_bus->write_c45 = cavium_mdiobus_write_c45; err = of_mdiobus_register(bus->mii_bus, node); if (err) diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index b962fc8e1397..738784fda117 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1556,14 +1556,18 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) goto err_devlink_unlock; } - err = nsim_dev_resources_register(devlink); + err = devl_register(devlink); if (err) goto err_vfc_free; + err = nsim_dev_resources_register(devlink); + if (err) + goto err_dl_unregister; + err = devlink_params_register(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); if (err) - goto err_dl_unregister; + goto err_resource_unregister; nsim_devlink_set_params_init_values(nsim_dev, devlink); err = nsim_dev_dummy_region_init(nsim_dev, devlink); @@ -1607,7 +1611,6 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; devlink_set_features(devlink, DEVLINK_F_RELOAD); devl_unlock(devlink); - devlink_register(devlink); return 0; err_hwstats_exit: @@ -1629,8 +1632,10 @@ err_dummy_region_exit: err_params_unregister: devlink_params_unregister(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); -err_dl_unregister: +err_resource_unregister: devl_resources_unregister(devlink); +err_dl_unregister: + devl_unregister(devlink); err_vfc_free: kfree(nsim_dev->vfconfigs); err_devlink_unlock: @@ -1668,7 +1673,6 @@ void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev) struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); struct devlink *devlink = priv_to_devlink(nsim_dev); - devlink_unregister(devlink); devl_lock(devlink); nsim_dev_reload_destroy(nsim_dev); @@ -1677,6 +1681,7 @@ void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev) devlink_params_unregister(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); devl_resources_unregister(devlink); + devl_unregister(devlink); kfree(nsim_dev->vfconfigs); kfree(nsim_dev->fa_cookie); devl_unlock(devlink); diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index aa77af4a68df..eb04ed715d2d 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -233,16 +233,16 @@ int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) int err; health->empty_reporter = - devlink_health_reporter_create(devlink, - &nsim_dev_empty_reporter_ops, - 0, health); + devl_health_reporter_create(devlink, + &nsim_dev_empty_reporter_ops, + 0, health); if (IS_ERR(health->empty_reporter)) return PTR_ERR(health->empty_reporter); health->dummy_reporter = - devlink_health_reporter_create(devlink, - &nsim_dev_dummy_reporter_ops, - 0, health); + devl_health_reporter_create(devlink, + &nsim_dev_dummy_reporter_ops, + 0, health); if (IS_ERR(health->dummy_reporter)) { err = PTR_ERR(health->dummy_reporter); goto err_empty_reporter_destroy; @@ -266,9 +266,9 @@ int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) return 0; err_dummy_reporter_destroy: - devlink_health_reporter_destroy(health->dummy_reporter); + devl_health_reporter_destroy(health->dummy_reporter); err_empty_reporter_destroy: - devlink_health_reporter_destroy(health->empty_reporter); + devl_health_reporter_destroy(health->empty_reporter); return err; } @@ -278,6 +278,6 @@ void nsim_dev_health_exit(struct nsim_dev *nsim_dev) debugfs_remove_recursive(health->ddir); kfree(health->recovered_break_msg); - devlink_health_reporter_destroy(health->dummy_reporter); - devlink_health_reporter_destroy(health->empty_reporter); + devl_health_reporter_destroy(health->dummy_reporter); + devl_health_reporter_destroy(health->empty_reporter); } diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index 7d5fc7f54b2f..3903f3baba2b 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -10,9 +10,6 @@ #define SGMII_CLOCK_PERIOD_NS 8 /* PCS is clocked at 125 MHz */ #define LINK_TIMER_VAL(ns) ((u32)((ns) / SGMII_CLOCK_PERIOD_NS)) -#define SGMII_AN_LINK_TIMER_NS 1600000 /* defined by SGMII spec */ -#define IEEE8023_LINK_TIMER_NS 10000000 - #define LINK_TIMER_LO 0x12 #define LINK_TIMER_HI 0x13 #define IF_MODE 0x14 @@ -126,26 +123,25 @@ static int lynx_pcs_config_giga(struct mdio_device *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising) { + int link_timer_ns; u32 link_timer; u16 if_mode; int err; - if (interface == PHY_INTERFACE_MODE_1000BASEX) { - link_timer = LINK_TIMER_VAL(IEEE8023_LINK_TIMER_NS); + link_timer_ns = phylink_get_link_timer_ns(interface); + if (link_timer_ns > 0) { + link_timer = LINK_TIMER_VAL(link_timer_ns); + mdiodev_write(pcs, LINK_TIMER_LO, link_timer & 0xffff); mdiodev_write(pcs, LINK_TIMER_HI, link_timer >> 16); + } + if (interface == PHY_INTERFACE_MODE_1000BASEX) { if_mode = 0; } else { if_mode = IF_MODE_SGMII_EN; - if (mode == MLO_AN_INBAND) { + if (mode == MLO_AN_INBAND) if_mode |= IF_MODE_USE_SGMII_AN; - - /* Adjust link timer for SGMII */ - link_timer = LINK_TIMER_VAL(SGMII_AN_LINK_TIMER_NS); - mdiodev_write(pcs, LINK_TIMER_LO, link_timer & 0xffff); - mdiodev_write(pcs, LINK_TIMER_HI, link_timer >> 16); - } } err = mdiodev_modify(pcs, IF_MODE, diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index f6a038a1d51e..bc428a816719 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -199,9 +199,7 @@ int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val) static int xpcs_modify_changed(struct dw_xpcs *xpcs, int dev, u32 reg, u16 mask, u16 set) { - u32 reg_addr = mdiobus_c45_addr(dev, reg); - - return mdiodev_modify_changed(xpcs->mdiodev, reg_addr, mask, set); + return mdiodev_c45_modify_changed(xpcs->mdiodev, dev, reg, mask, set); } static int xpcs_read_vendor(struct dw_xpcs *xpcs, int dev, u32 reg) diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 1327290decab..f5df2edc94a5 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -277,6 +277,13 @@ config NXP_TJA11XX_PHY help Currently supports the NXP TJA1100 and TJA1101 PHY. +config NCN26000_PHY + tristate "Onsemi 10BASE-T1S Ethernet PHY" + help + Adds support for the onsemi 10BASE-T1S Ethernet PHY. + Currently supports the NCN26000 10BASE-T1S Industrial PHY + with MII interface. + config AT803X_PHY tristate "Qualcomm Atheros AR803X PHYs and QCA833x PHYs" depends on REGULATOR diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index f7138d3c896b..b5138066ba04 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_MICROCHIP_T1_PHY) += microchip_t1.o obj-$(CONFIG_MICROSEMI_PHY) += mscc/ obj-$(CONFIG_MOTORCOMM_PHY) += motorcomm.o obj-$(CONFIG_NATIONAL_PHY) += national.o +obj-$(CONFIG_NCN26000_PHY) += ncn26000.o obj-$(CONFIG_NXP_C45_TJA11XX_PHY) += nxp-c45-tja11xx.o obj-$(CONFIG_NXP_TJA11XX_PHY) += nxp-tja11xx.o obj-$(CONFIG_QSEMI_PHY) += qsemi.o diff --git a/drivers/net/phy/mdio-open-alliance.h b/drivers/net/phy/mdio-open-alliance.h new file mode 100644 index 000000000000..931e14660d75 --- /dev/null +++ b/drivers/net/phy/mdio-open-alliance.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * mdio-open-alliance.h - definition of OPEN Alliance SIG standard registers + */ + +#ifndef __MDIO_OPEN_ALLIANCE__ +#define __MDIO_OPEN_ALLIANCE__ + +#include <linux/mdio.h> + +/* NOTE: all OATC14 registers are located in MDIO_MMD_VEND2 */ + +/* Open Alliance TC14 (10BASE-T1S) registers */ +#define MDIO_OATC14_PLCA_IDVER 0xca00 /* PLCA ID and version */ +#define MDIO_OATC14_PLCA_CTRL0 0xca01 /* PLCA Control register 0 */ +#define MDIO_OATC14_PLCA_CTRL1 0xca02 /* PLCA Control register 1 */ +#define MDIO_OATC14_PLCA_STATUS 0xca03 /* PLCA Status register */ +#define MDIO_OATC14_PLCA_TOTMR 0xca04 /* PLCA TO Timer register */ +#define MDIO_OATC14_PLCA_BURST 0xca05 /* PLCA BURST mode register */ + +/* Open Alliance TC14 PLCA IDVER register */ +#define MDIO_OATC14_PLCA_IDM 0xff00 /* PLCA MAP ID */ +#define MDIO_OATC14_PLCA_VER 0x00ff /* PLCA MAP version */ + +/* Open Alliance TC14 PLCA CTRL0 register */ +#define MDIO_OATC14_PLCA_EN BIT(15) /* PLCA enable */ +#define MDIO_OATC14_PLCA_RST BIT(14) /* PLCA reset */ + +/* Open Alliance TC14 PLCA CTRL1 register */ +#define MDIO_OATC14_PLCA_NCNT 0xff00 /* PLCA node count */ +#define MDIO_OATC14_PLCA_ID 0x00ff /* PLCA local node ID */ + +/* Open Alliance TC14 PLCA STATUS register */ +#define MDIO_OATC14_PLCA_PST BIT(15) /* PLCA status indication */ + +/* Open Alliance TC14 PLCA TOTMR register */ +#define MDIO_OATC14_PLCA_TOT 0x00ff + +/* Open Alliance TC14 PLCA BURST register */ +#define MDIO_OATC14_PLCA_MAXBC 0xff00 +#define MDIO_OATC14_PLCA_BTMR 0x00ff + +/* Version Identifiers */ +#define OATC14_IDM 0x0a00 + +#endif /* __MDIO_OPEN_ALLIANCE__ */ diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 16e021b477f0..fb633fa3e872 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -19,6 +19,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> +#include <linux/micrel_phy.h> #include <linux/mii.h> #include <linux/mm.h> #include <linux/module.h> @@ -511,6 +512,126 @@ static int mdiobus_create_device(struct mii_bus *bus, return ret; } +static struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr, bool c45) +{ + struct phy_device *phydev = ERR_PTR(-ENODEV); + int err; + + phydev = get_phy_device(bus, addr, c45); + if (IS_ERR(phydev)) + return phydev; + + /* For DT, see if the auto-probed phy has a corresponding child + * in the bus node, and set the of_node pointer in this case. + */ + of_mdiobus_link_mdiodev(bus, &phydev->mdio); + + err = phy_device_register(phydev); + if (err) { + phy_device_free(phydev); + return ERR_PTR(-ENODEV); + } + + return phydev; +} + +/** + * mdiobus_scan_c22 - scan one address on a bus for C22 MDIO devices. + * @bus: mii_bus to scan + * @addr: address on bus to scan + * + * This function scans one address on the MDIO bus, looking for + * devices which can be identified using a vendor/product ID in + * registers 2 and 3. Not all MDIO devices have such registers, but + * PHY devices typically do. Hence this function assumes anything + * found is a PHY, or can be treated as a PHY. Other MDIO devices, + * such as switches, will probably not be found during the scan. + */ +struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr) +{ + return mdiobus_scan(bus, addr, false); +} +EXPORT_SYMBOL(mdiobus_scan_c22); + +/** + * mdiobus_scan_c45 - scan one address on a bus for C45 MDIO devices. + * @bus: mii_bus to scan + * @addr: address on bus to scan + * + * This function scans one address on the MDIO bus, looking for + * devices which can be identified using a vendor/product ID in + * registers 2 and 3. Not all MDIO devices have such registers, but + * PHY devices typically do. Hence this function assumes anything + * found is a PHY, or can be treated as a PHY. Other MDIO devices, + * such as switches, will probably not be found during the scan. + */ +static struct phy_device *mdiobus_scan_c45(struct mii_bus *bus, int addr) +{ + return mdiobus_scan(bus, addr, true); +} + +static int mdiobus_scan_bus_c22(struct mii_bus *bus) +{ + int i; + + for (i = 0; i < PHY_MAX_ADDR; i++) { + if ((bus->phy_mask & BIT(i)) == 0) { + struct phy_device *phydev; + + phydev = mdiobus_scan_c22(bus, i); + if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV)) + return PTR_ERR(phydev); + } + } + return 0; +} + +static int mdiobus_scan_bus_c45(struct mii_bus *bus) +{ + int i; + + for (i = 0; i < PHY_MAX_ADDR; i++) { + if ((bus->phy_mask & BIT(i)) == 0) { + struct phy_device *phydev; + + /* Don't scan C45 if we already have a C22 device */ + if (bus->mdio_map[i]) + continue; + + phydev = mdiobus_scan_c45(bus, i); + if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV)) + return PTR_ERR(phydev); + } + } + return 0; +} + +/* There are some C22 PHYs which do bad things when where is a C45 + * transaction on the bus, like accepting a read themselves, and + * stomping over the true devices reply, to performing a write to + * themselves which was intended for another device. Now that C22 + * devices have been found, see if any of them are bad for C45, and if we + * should skip the C45 scan. + */ +static bool mdiobus_prevent_c45_scan(struct mii_bus *bus) +{ + int i; + + for (i = 0; i < PHY_MAX_ADDR; i++) { + struct phy_device *phydev; + u32 oui; + + phydev = mdiobus_get_phy(bus, i); + if (!phydev) + continue; + oui = phydev->phy_id >> 10; + + if (oui == MICREL_OUI) + return true; + } + return false; +} + /** * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus * @bus: target mii_bus @@ -528,11 +649,19 @@ static int mdiobus_create_device(struct mii_bus *bus, int __mdiobus_register(struct mii_bus *bus, struct module *owner) { struct mdio_device *mdiodev; - int i, err; struct gpio_desc *gpiod; + bool prevent_c45_scan; + int i, err; + + if (!bus || !bus->name) + return -EINVAL; - if (NULL == bus || NULL == bus->name || - NULL == bus->read || NULL == bus->write) + /* An access method always needs both read and write operations */ + if (!!bus->read != !!bus->write || !!bus->read_c45 != !!bus->write_c45) + return -EINVAL; + + /* At least one method is mandatory */ + if (!bus->read && !bus->read_c45) return -EINVAL; if (bus->parent && bus->parent->of_node) @@ -587,16 +716,18 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) goto error_reset_gpiod; } - for (i = 0; i < PHY_MAX_ADDR; i++) { - if ((bus->phy_mask & BIT(i)) == 0) { - struct phy_device *phydev; + if (bus->read) { + err = mdiobus_scan_bus_c22(bus); + if (err) + goto error; + } - phydev = mdiobus_scan(bus, i); - if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV)) { - err = PTR_ERR(phydev); - goto error; - } - } + prevent_c45_scan = mdiobus_prevent_c45_scan(bus); + + if (!prevent_c45_scan && bus->read_c45) { + err = mdiobus_scan_bus_c45(bus); + if (err) + goto error; } mdiobus_setup_mdiodev_from_board_info(bus, mdiobus_create_device); @@ -606,7 +737,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) return 0; error: - while (--i >= 0) { + for (i = 0; i < PHY_MAX_ADDR; i++) { mdiodev = bus->mdio_map[i]; if (!mdiodev) continue; @@ -677,57 +808,6 @@ void mdiobus_free(struct mii_bus *bus) } EXPORT_SYMBOL(mdiobus_free); -/** - * mdiobus_scan - scan a bus for MDIO devices. - * @bus: mii_bus to scan - * @addr: address on bus to scan - * - * This function scans the MDIO bus, looking for devices which can be - * identified using a vendor/product ID in registers 2 and 3. Not all - * MDIO devices have such registers, but PHY devices typically - * do. Hence this function assumes anything found is a PHY, or can be - * treated as a PHY. Other MDIO devices, such as switches, will - * probably not be found during the scan. - */ -struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr) -{ - struct phy_device *phydev = ERR_PTR(-ENODEV); - int err; - - switch (bus->probe_capabilities) { - case MDIOBUS_NO_CAP: - case MDIOBUS_C22: - phydev = get_phy_device(bus, addr, false); - break; - case MDIOBUS_C45: - phydev = get_phy_device(bus, addr, true); - break; - case MDIOBUS_C22_C45: - phydev = get_phy_device(bus, addr, false); - if (IS_ERR(phydev)) - phydev = get_phy_device(bus, addr, true); - break; - } - - if (IS_ERR(phydev)) - return phydev; - - /* - * For DT, see if the auto-probed phy has a correspoding child - * in the bus node, and set the of_node pointer in this case. - */ - of_mdiobus_link_mdiodev(bus, &phydev->mdio); - - err = phy_device_register(phydev); - if (err) { - phy_device_free(phydev); - return ERR_PTR(-ENODEV); - } - - return phydev; -} -EXPORT_SYMBOL(mdiobus_scan); - static void mdiobus_stats_acct(struct mdio_bus_stats *stats, bool op, int ret) { preempt_disable(); @@ -764,7 +844,10 @@ int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum) lockdep_assert_held_once(&bus->mdio_lock); - retval = bus->read(bus, addr, regnum); + if (bus->read) + retval = bus->read(bus, addr, regnum); + else + retval = -EOPNOTSUPP; trace_mdio_access(bus, 1, addr, regnum, retval, retval); mdiobus_stats_acct(&bus->stats[addr], true, retval); @@ -790,7 +873,10 @@ int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val) lockdep_assert_held_once(&bus->mdio_lock); - err = bus->write(bus, addr, regnum, val); + if (bus->write) + err = bus->write(bus, addr, regnum, val); + else + err = -EOPNOTSUPP; trace_mdio_access(bus, 0, addr, regnum, val, err); mdiobus_stats_acct(&bus->stats[addr], false, err); @@ -831,6 +917,105 @@ int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, } EXPORT_SYMBOL_GPL(__mdiobus_modify_changed); +static u32 mdiobus_c45_addr(int devad, u16 regnum) +{ + return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; +} + +/** + * __mdiobus_c45_read - Unlocked version of the mdiobus_c45_read function + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to read + * + * Read a MDIO bus register. Caller must hold the mdio bus lock. + * + * NOTE: MUST NOT be called from interrupt context. + */ +int __mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum) +{ + int retval; + + lockdep_assert_held_once(&bus->mdio_lock); + + if (bus->read_c45) + retval = bus->read_c45(bus, addr, devad, regnum); + else + retval = bus->read(bus, addr, mdiobus_c45_addr(devad, regnum)); + + trace_mdio_access(bus, 1, addr, regnum, retval, retval); + mdiobus_stats_acct(&bus->stats[addr], true, retval); + + return retval; +} +EXPORT_SYMBOL(__mdiobus_c45_read); + +/** + * __mdiobus_c45_write - Unlocked version of the mdiobus_write function + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to write + * @val: value to write to @regnum + * + * Write a MDIO bus register. Caller must hold the mdio bus lock. + * + * NOTE: MUST NOT be called from interrupt context. + */ +int __mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum, + u16 val) +{ + int err; + + lockdep_assert_held_once(&bus->mdio_lock); + + if (bus->write_c45) + err = bus->write_c45(bus, addr, devad, regnum, val); + else + err = bus->write(bus, addr, mdiobus_c45_addr(devad, regnum), + val); + + trace_mdio_access(bus, 0, addr, regnum, val, err); + mdiobus_stats_acct(&bus->stats[addr], false, err); + + return err; +} +EXPORT_SYMBOL(__mdiobus_c45_write); + +/** + * __mdiobus_c45_modify_changed - Unlocked version of the mdiobus_modify function + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + * + * Read, modify, and if any change, write the register value back to the + * device. Any error returns a negative number. + * + * NOTE: MUST NOT be called from interrupt context. + */ +static int __mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, + int devad, u32 regnum, u16 mask, + u16 set) +{ + int new, ret; + + ret = __mdiobus_c45_read(bus, addr, devad, regnum); + if (ret < 0) + return ret; + + new = (ret & ~mask) | set; + if (new == ret) + return 0; + + ret = __mdiobus_c45_write(bus, addr, devad, regnum, new); + + return ret < 0 ? ret : 1; +} + /** * mdiobus_read_nested - Nested version of the mdiobus_read function * @bus: the mii_bus struct @@ -879,6 +1064,56 @@ int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum) EXPORT_SYMBOL(mdiobus_read); /** + * mdiobus_c45_read - Convenience function for reading a given MII mgmt register + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to read + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum) +{ + int retval; + + mutex_lock(&bus->mdio_lock); + retval = __mdiobus_c45_read(bus, addr, devad, regnum); + mutex_unlock(&bus->mdio_lock); + + return retval; +} +EXPORT_SYMBOL(mdiobus_c45_read); + +/** + * mdiobus_c45_read_nested - Nested version of the mdiobus_c45_read function + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to read + * + * In case of nested MDIO bus access avoid lockdep false positives by + * using mutex_lock_nested(). + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int mdiobus_c45_read_nested(struct mii_bus *bus, int addr, int devad, + u32 regnum) +{ + int retval; + + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); + retval = __mdiobus_c45_read(bus, addr, devad, regnum); + mutex_unlock(&bus->mdio_lock); + + return retval; +} +EXPORT_SYMBOL(mdiobus_c45_read_nested); + +/** * mdiobus_write_nested - Nested version of the mdiobus_write function * @bus: the mii_bus struct * @addr: the phy address @@ -928,6 +1163,59 @@ int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val) EXPORT_SYMBOL(mdiobus_write); /** + * mdiobus_c45_write - Convenience function for writing a given MII mgmt register + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to write + * @val: value to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum, + u16 val) +{ + int err; + + mutex_lock(&bus->mdio_lock); + err = __mdiobus_c45_write(bus, addr, devad, regnum, val); + mutex_unlock(&bus->mdio_lock); + + return err; +} +EXPORT_SYMBOL(mdiobus_c45_write); + +/** + * mdiobus_c45_write_nested - Nested version of the mdiobus_c45_write function + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to write + * @val: value to write to @regnum + * + * In case of nested MDIO bus access avoid lockdep false positives by + * using mutex_lock_nested(). + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int mdiobus_c45_write_nested(struct mii_bus *bus, int addr, int devad, + u32 regnum, u16 val) +{ + int err; + + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); + err = __mdiobus_c45_write(bus, addr, devad, regnum, val); + mutex_unlock(&bus->mdio_lock); + + return err; +} +EXPORT_SYMBOL(mdiobus_c45_write_nested); + +/** * mdiobus_modify - Convenience function for modifying a given mdio device * register * @bus: the mii_bus struct @@ -949,6 +1237,30 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set) EXPORT_SYMBOL_GPL(mdiobus_modify); /** + * mdiobus_c45_modify - Convenience function for modifying a given mdio device + * register + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to write + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + */ +int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum, + u16 mask, u16 set) +{ + int err; + + mutex_lock(&bus->mdio_lock); + err = __mdiobus_c45_modify_changed(bus, addr, devad, regnum, + mask, set); + mutex_unlock(&bus->mdio_lock); + + return err < 0 ? err : 0; +} +EXPORT_SYMBOL_GPL(mdiobus_c45_modify); + +/** * mdiobus_modify_changed - Convenience function for modifying a given mdio * device register and returning if it changed * @bus: the mii_bus struct @@ -971,6 +1283,29 @@ int mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, EXPORT_SYMBOL_GPL(mdiobus_modify_changed); /** + * mdiobus_c45_modify_changed - Convenience function for modifying a given mdio + * device register and returning if it changed + * @bus: the mii_bus struct + * @addr: the phy address + * @devad: device address to read + * @regnum: register number to write + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + */ +int mdiobus_c45_modify_changed(struct mii_bus *bus, int devad, int addr, + u32 regnum, u16 mask, u16 set) +{ + int err; + + mutex_lock(&bus->mdio_lock); + err = __mdiobus_c45_modify_changed(bus, addr, devad, regnum, mask, set); + mutex_unlock(&bus->mdio_lock); + + return err; +} +EXPORT_SYMBOL_GPL(mdiobus_c45_modify_changed); + +/** * mdio_bus_match - determine if given MDIO driver supports the given * MDIO device * @dev: target MDIO device diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 26ce0c5defcd..d5b80c31ab91 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2088,7 +2088,8 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, const struct kszphy_type *type = phydev->drv->driver_data; unsigned long pair_mask = type->pair_mask; int retries = 20; - int pair, ret; + int ret = 0; + int pair; *finished = false; @@ -2794,13 +2795,11 @@ static void lan8814_get_rx_ts(struct kszphy_ptp_priv *ptp_priv) } while (PTP_CAP_INFO_RX_TS_CNT_GET_(reg) > 0); } -static void lan8814_handle_ptp_interrupt(struct phy_device *phydev) +static void lan8814_handle_ptp_interrupt(struct phy_device *phydev, u16 status) { struct kszphy_priv *priv = phydev->priv; struct kszphy_ptp_priv *ptp_priv = &priv->ptp_priv; - u16 status; - status = lanphy_read_page_reg(phydev, 5, PTP_TSU_INT_STS); if (status & PTP_TSU_INT_STS_PTP_TX_TS_EN_) lan8814_get_tx_ts(ptp_priv); @@ -2899,8 +2898,8 @@ static int lan8804_config_intr(struct phy_device *phydev) static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) { - int irq_status, tsu_irq_status; int ret = IRQ_NONE; + int irq_status; irq_status = phy_read(phydev, LAN8814_INTS); if (irq_status < 0) { @@ -2913,20 +2912,13 @@ static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) ret = IRQ_HANDLED; } - while (1) { - tsu_irq_status = lanphy_read_page_reg(phydev, 4, - LAN8814_INTR_STS_REG); - - if (tsu_irq_status > 0 && - (tsu_irq_status & (LAN8814_INTR_STS_REG_1588_TSU0_ | - LAN8814_INTR_STS_REG_1588_TSU1_ | - LAN8814_INTR_STS_REG_1588_TSU2_ | - LAN8814_INTR_STS_REG_1588_TSU3_))) { - lan8814_handle_ptp_interrupt(phydev); - ret = IRQ_HANDLED; - } else { + while (true) { + irq_status = lanphy_read_page_reg(phydev, 5, PTP_TSU_INT_STS); + if (!irq_status) break; - } + + lan8814_handle_ptp_interrupt(phydev, irq_status); + ret = IRQ_HANDLED; } return ret; @@ -3016,10 +3008,6 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) { struct lan8814_shared_priv *shared = phydev->shared->priv; - if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK) || - !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) - return 0; - /* Initialise shared lock for clock*/ mutex_init(&shared->shared_lock); @@ -3039,12 +3027,16 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) shared->ptp_clock = ptp_clock_register(&shared->ptp_clock_info, &phydev->mdio.dev); - if (IS_ERR_OR_NULL(shared->ptp_clock)) { + if (IS_ERR(shared->ptp_clock)) { phydev_err(phydev, "ptp_clock_register failed %lu\n", PTR_ERR(shared->ptp_clock)); return -EINVAL; } + /* Check if PHC support is missing at the configuration level */ + if (!shared->ptp_clock) + return 0; + phydev_dbg(phydev, "successfully registered ptp clock\n"); shared->phydev = phydev; diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 147d7a5a9b35..e5972b4ef6e8 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -12,6 +12,7 @@ #include <linux/mutex.h> #include <linux/phy.h> #include <linux/polynomial.h> +#include <linux/property.h> #include <linux/netdevice.h> /* PHY ID */ @@ -292,6 +293,10 @@ static int gpy_probe(struct phy_device *phydev) phydev->priv = priv; mutex_init(&priv->mbox_lock); + if (gpy_has_broken_mdint(phydev) && + !device_property_present(dev, "maxlinear,use-broken-interrupts")) + phydev->dev_flags |= PHY_F_NO_IRQ; + fw_version = phy_read(phydev, PHY_FWV); if (fw_version < 0) return fw_version; diff --git a/drivers/net/phy/ncn26000.c b/drivers/net/phy/ncn26000.c new file mode 100644 index 000000000000..5680584f659e --- /dev/null +++ b/drivers/net/phy/ncn26000.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * Driver for the onsemi 10BASE-T1S NCN26000 PHYs family. + * + * Copyright 2022 onsemi + */ +#include <linux/kernel.h> +#include <linux/bitfield.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mii.h> +#include <linux/phy.h> + +#include "mdio-open-alliance.h" + +#define PHY_ID_NCN26000 0x180FF5A1 + +#define NCN26000_REG_IRQ_CTL 16 +#define NCN26000_REG_IRQ_STATUS 17 + +// the NCN26000 maps link_ctrl to BMCR_ANENABLE +#define NCN26000_BCMR_LINK_CTRL_BIT BMCR_ANENABLE + +// the NCN26000 maps link_status to BMSR_ANEGCOMPLETE +#define NCN26000_BMSR_LINK_STATUS_BIT BMSR_ANEGCOMPLETE + +#define NCN26000_IRQ_LINKST_BIT BIT(0) +#define NCN26000_IRQ_PLCAST_BIT BIT(1) +#define NCN26000_IRQ_LJABBER_BIT BIT(2) +#define NCN26000_IRQ_RJABBER_BIT BIT(3) +#define NCN26000_IRQ_PLCAREC_BIT BIT(4) +#define NCN26000_IRQ_PHYSCOL_BIT BIT(5) +#define NCN26000_IRQ_RESET_BIT BIT(15) + +#define TO_TMR_DEFAULT 32 + +static int ncn26000_config_init(struct phy_device *phydev) +{ + /* HW bug workaround: the default value of the PLCA TO_TIMER should be + * 32, where the current version of NCN26000 reports 24. This will be + * fixed in future PHY versions. For the time being, we force the + * correct default here. + */ + return phy_write_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_TOTMR, + TO_TMR_DEFAULT); +} + +static int ncn26000_config_aneg(struct phy_device *phydev) +{ + /* Note: the NCN26000 supports only P2MP link mode. Therefore, AN is not + * supported. However, this function is invoked by phylib to enable the + * PHY, regardless of the AN support. + */ + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + phydev->mdix = ETH_TP_MDI; + + // bring up the link + return phy_write(phydev, MII_BMCR, NCN26000_BCMR_LINK_CTRL_BIT); +} + +static int ncn26000_read_status(struct phy_device *phydev) +{ + /* The NCN26000 reports NCN26000_LINK_STATUS_BIT if the link status of + * the PHY is up. It further reports the logical AND of the link status + * and the PLCA status in the BMSR_LSTATUS bit. + */ + int ret; + + /* The link state is latched low so that momentary link + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops except + * the link was already down. + */ + if (!phy_polling_mode(phydev) || !phydev->link) { + ret = phy_read(phydev, MII_BMSR); + if (ret < 0) + return ret; + else if (ret & NCN26000_BMSR_LINK_STATUS_BIT) + goto upd_link; + } + + ret = phy_read(phydev, MII_BMSR); + if (ret < 0) + return ret; + +upd_link: + // update link status + if (ret & NCN26000_BMSR_LINK_STATUS_BIT) { + phydev->link = 1; + phydev->pause = 0; + phydev->duplex = DUPLEX_HALF; + phydev->speed = SPEED_10; + } else { + phydev->link = 0; + phydev->duplex = DUPLEX_UNKNOWN; + phydev->speed = SPEED_UNKNOWN; + } + + return 0; +} + +static irqreturn_t ncn26000_handle_interrupt(struct phy_device *phydev) +{ + int ret; + + // read and aknowledge the IRQ status register + ret = phy_read(phydev, NCN26000_REG_IRQ_STATUS); + + // check only link status changes + if (ret < 0 || (ret & NCN26000_REG_IRQ_STATUS) == 0) + return IRQ_NONE; + + phy_trigger_machine(phydev); + return IRQ_HANDLED; +} + +static int ncn26000_config_intr(struct phy_device *phydev) +{ + int ret; + u16 irqe; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + // acknowledge IRQs + ret = phy_read(phydev, NCN26000_REG_IRQ_STATUS); + if (ret < 0) + return ret; + + // get link status notifications + irqe = NCN26000_IRQ_LINKST_BIT; + } else { + // disable all IRQs + irqe = 0; + } + + ret = phy_write(phydev, NCN26000_REG_IRQ_CTL, irqe); + if (ret != 0) + return ret; + + return 0; +} + +static struct phy_driver ncn26000_driver[] = { + { + PHY_ID_MATCH_MODEL(PHY_ID_NCN26000), + .name = "NCN26000", + .features = PHY_BASIC_T1S_P2MP_FEATURES, + .config_init = ncn26000_config_init, + .config_intr = ncn26000_config_intr, + .config_aneg = ncn26000_config_aneg, + .read_status = ncn26000_read_status, + .handle_interrupt = ncn26000_handle_interrupt, + .get_plca_cfg = genphy_c45_plca_get_cfg, + .set_plca_cfg = genphy_c45_plca_set_cfg, + .get_plca_status = genphy_c45_plca_get_status, + .soft_reset = genphy_soft_reset, + }, +}; + +module_phy_driver(ncn26000_driver); + +static struct mdio_device_id __maybe_unused ncn26000_tbl[] = { + { PHY_ID_MATCH_MODEL(PHY_ID_NCN26000) }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, ncn26000_tbl); + +MODULE_AUTHOR("Piergiorgio Beruto"); +MODULE_DESCRIPTION("onsemi 10BASE-T1S PHY driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index a87a4b3ffce4..9f9565a4819d 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -8,6 +8,8 @@ #include <linux/mii.h> #include <linux/phy.h> +#include "mdio-open-alliance.h" + /** * genphy_c45_baset1_able - checks if the PMA has BASE-T1 extended abilities * @phydev: target phy_device struct @@ -931,6 +933,197 @@ int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable) } EXPORT_SYMBOL_GPL(genphy_c45_fast_retrain); +/** + * genphy_c45_plca_get_cfg - get PLCA configuration from standard registers + * @phydev: target phy_device struct + * @plca_cfg: output structure to store the PLCA configuration + * + * Description: if the PHY complies to the Open Alliance TC14 10BASE-T1S PLCA + * Management Registers specifications, this function can be used to retrieve + * the current PLCA configuration from the standard registers in MMD 31. + */ +int genphy_c45_plca_get_cfg(struct phy_device *phydev, + struct phy_plca_cfg *plca_cfg) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_IDVER); + if (ret < 0) + return ret; + + if ((ret & MDIO_OATC14_PLCA_IDM) != OATC14_IDM) + return -ENODEV; + + plca_cfg->version = ret & ~MDIO_OATC14_PLCA_IDM; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_CTRL0); + if (ret < 0) + return ret; + + plca_cfg->enabled = !!(ret & MDIO_OATC14_PLCA_EN); + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_CTRL1); + if (ret < 0) + return ret; + + plca_cfg->node_cnt = (ret & MDIO_OATC14_PLCA_NCNT) >> 8; + plca_cfg->node_id = (ret & MDIO_OATC14_PLCA_ID); + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_TOTMR); + if (ret < 0) + return ret; + + plca_cfg->to_tmr = ret & MDIO_OATC14_PLCA_TOT; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_BURST); + if (ret < 0) + return ret; + + plca_cfg->burst_cnt = (ret & MDIO_OATC14_PLCA_MAXBC) >> 8; + plca_cfg->burst_tmr = (ret & MDIO_OATC14_PLCA_BTMR); + + return 0; +} +EXPORT_SYMBOL_GPL(genphy_c45_plca_get_cfg); + +/** + * genphy_c45_plca_set_cfg - set PLCA configuration using standard registers + * @phydev: target phy_device struct + * @plca_cfg: structure containing the PLCA configuration. Fields set to -1 are + * not to be changed. + * + * Description: if the PHY complies to the Open Alliance TC14 10BASE-T1S PLCA + * Management Registers specifications, this function can be used to modify + * the PLCA configuration using the standard registers in MMD 31. + */ +int genphy_c45_plca_set_cfg(struct phy_device *phydev, + const struct phy_plca_cfg *plca_cfg) +{ + u16 val = 0; + int ret; + + // PLCA IDVER is read-only + if (plca_cfg->version >= 0) + return -EINVAL; + + // first of all, disable PLCA if required + if (plca_cfg->enabled == 0) { + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_CTRL0, + MDIO_OATC14_PLCA_EN); + + if (ret < 0) + return ret; + } + + // check if we need to set the PLCA node count, node ID, or both + if (plca_cfg->node_cnt >= 0 || plca_cfg->node_id >= 0) { + /* if one between node count and node ID is -not- to be + * changed, read the register to later perform merge/purge of + * the configuration as appropriate + */ + if (plca_cfg->node_cnt < 0 || plca_cfg->node_id < 0) { + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_CTRL1); + + if (ret < 0) + return ret; + + val = ret; + } + + if (plca_cfg->node_cnt >= 0) + val = (val & ~MDIO_OATC14_PLCA_NCNT) | + (plca_cfg->node_cnt << 8); + + if (plca_cfg->node_id >= 0) + val = (val & ~MDIO_OATC14_PLCA_ID) | + (plca_cfg->node_id); + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_CTRL1, val); + + if (ret < 0) + return ret; + } + + if (plca_cfg->to_tmr >= 0) { + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_TOTMR, + plca_cfg->to_tmr); + + if (ret < 0) + return ret; + } + + // check if we need to set the PLCA burst count, burst timer, or both + if (plca_cfg->burst_cnt >= 0 || plca_cfg->burst_tmr >= 0) { + /* if one between burst count and burst timer is -not- to be + * changed, read the register to later perform merge/purge of + * the configuration as appropriate + */ + if (plca_cfg->burst_cnt < 0 || plca_cfg->burst_tmr < 0) { + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_BURST); + + if (ret < 0) + return ret; + + val = ret; + } + + if (plca_cfg->burst_cnt >= 0) + val = (val & ~MDIO_OATC14_PLCA_MAXBC) | + (plca_cfg->burst_cnt << 8); + + if (plca_cfg->burst_tmr >= 0) + val = (val & ~MDIO_OATC14_PLCA_BTMR) | + (plca_cfg->burst_tmr); + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_BURST, val); + + if (ret < 0) + return ret; + } + + // if we need to enable PLCA, do it at the end + if (plca_cfg->enabled > 0) { + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_PLCA_CTRL0, + MDIO_OATC14_PLCA_EN); + + if (ret < 0) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(genphy_c45_plca_set_cfg); + +/** + * genphy_c45_plca_get_status - get PLCA status from standard registers + * @phydev: target phy_device struct + * @plca_st: output structure to store the PLCA status + * + * Description: if the PHY complies to the Open Alliance TC14 10BASE-T1S PLCA + * Management Registers specifications, this function can be used to retrieve + * the current PLCA status information from the standard registers in MMD 31. + */ +int genphy_c45_plca_get_status(struct phy_device *phydev, + struct phy_plca_status *plca_st) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_PLCA_STATUS); + if (ret < 0) + return ret; + + plca_st->pst = !!(ret & MDIO_OATC14_PLCA_PST); + return 0; +} +EXPORT_SYMBOL_GPL(genphy_c45_plca_get_status); + struct phy_driver genphy_c45_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 5d08c627a516..a64186dc53f8 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -13,7 +13,7 @@ */ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 99, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 102, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -260,6 +260,9 @@ static const struct phy_setting settings[] = { PHY_SETTING( 10, FULL, 10baseT_Full ), PHY_SETTING( 10, HALF, 10baseT_Half ), PHY_SETTING( 10, FULL, 10baseT1L_Full ), + PHY_SETTING( 10, FULL, 10baseT1S_Full ), + PHY_SETTING( 10, HALF, 10baseT1S_Half ), + PHY_SETTING( 10, HALF, 10baseT1S_P2MP_Half ), }; #undef PHY_SETTING diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e5b6cb1a77f9..3378ca4f49b6 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -544,6 +544,198 @@ int phy_ethtool_get_stats(struct phy_device *phydev, EXPORT_SYMBOL(phy_ethtool_get_stats); /** + * phy_ethtool_get_plca_cfg - Get PLCA RS configuration + * @phydev: the phy_device struct + * @plca_cfg: where to store the retrieved configuration + * + * Retrieve the PLCA configuration from the PHY. Return 0 on success or a + * negative value if an error occurred. + */ +int phy_ethtool_get_plca_cfg(struct phy_device *phydev, + struct phy_plca_cfg *plca_cfg) +{ + int ret; + + if (!phydev->drv) { + ret = -EIO; + goto out; + } + + if (!phydev->drv->get_plca_cfg) { + ret = -EOPNOTSUPP; + goto out; + } + + mutex_lock(&phydev->lock); + ret = phydev->drv->get_plca_cfg(phydev, plca_cfg); + + mutex_unlock(&phydev->lock); +out: + return ret; +} + +/** + * plca_check_valid - Check PLCA configuration before enabling + * @phydev: the phy_device struct + * @plca_cfg: current PLCA configuration + * @extack: extack for reporting useful error messages + * + * Checks whether the PLCA and PHY configuration are consistent and it is safe + * to enable PLCA. Returns 0 on success or a negative value if the PLCA or PHY + * configuration is not consistent. + */ +static int plca_check_valid(struct phy_device *phydev, + const struct phy_plca_cfg *plca_cfg, + struct netlink_ext_ack *extack) +{ + int ret = 0; + + if (!linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, + phydev->advertising)) { + ret = -EOPNOTSUPP; + NL_SET_ERR_MSG(extack, + "Point to Multi-Point mode is not enabled"); + } else if (plca_cfg->node_id >= 255) { + NL_SET_ERR_MSG(extack, "PLCA node ID is not set"); + ret = -EINVAL; + } + + return ret; +} + +/** + * phy_ethtool_set_plca_cfg - Set PLCA RS configuration + * @phydev: the phy_device struct + * @plca_cfg: new PLCA configuration to apply + * @extack: extack for reporting useful error messages + * + * Sets the PLCA configuration in the PHY. Return 0 on success or a + * negative value if an error occurred. + */ +int phy_ethtool_set_plca_cfg(struct phy_device *phydev, + const struct phy_plca_cfg *plca_cfg, + struct netlink_ext_ack *extack) +{ + struct phy_plca_cfg *curr_plca_cfg; + int ret; + + if (!phydev->drv) { + ret = -EIO; + goto out; + } + + if (!phydev->drv->set_plca_cfg || + !phydev->drv->get_plca_cfg) { + ret = -EOPNOTSUPP; + goto out; + } + + curr_plca_cfg = kmalloc(sizeof(*curr_plca_cfg), GFP_KERNEL); + if (!curr_plca_cfg) { + ret = -ENOMEM; + goto out; + } + + mutex_lock(&phydev->lock); + + ret = phydev->drv->get_plca_cfg(phydev, curr_plca_cfg); + if (ret) + goto out_drv; + + if (curr_plca_cfg->enabled < 0 && plca_cfg->enabled >= 0) { + NL_SET_ERR_MSG(extack, + "PHY does not support changing the PLCA 'enable' attribute"); + ret = -EINVAL; + goto out_drv; + } + + if (curr_plca_cfg->node_id < 0 && plca_cfg->node_id >= 0) { + NL_SET_ERR_MSG(extack, + "PHY does not support changing the PLCA 'local node ID' attribute"); + ret = -EINVAL; + goto out_drv; + } + + if (curr_plca_cfg->node_cnt < 0 && plca_cfg->node_cnt >= 0) { + NL_SET_ERR_MSG(extack, + "PHY does not support changing the PLCA 'node count' attribute"); + ret = -EINVAL; + goto out_drv; + } + + if (curr_plca_cfg->to_tmr < 0 && plca_cfg->to_tmr >= 0) { + NL_SET_ERR_MSG(extack, + "PHY does not support changing the PLCA 'TO timer' attribute"); + ret = -EINVAL; + goto out_drv; + } + + if (curr_plca_cfg->burst_cnt < 0 && plca_cfg->burst_cnt >= 0) { + NL_SET_ERR_MSG(extack, + "PHY does not support changing the PLCA 'burst count' attribute"); + ret = -EINVAL; + goto out_drv; + } + + if (curr_plca_cfg->burst_tmr < 0 && plca_cfg->burst_tmr >= 0) { + NL_SET_ERR_MSG(extack, + "PHY does not support changing the PLCA 'burst timer' attribute"); + ret = -EINVAL; + goto out_drv; + } + + // if enabling PLCA, perform a few sanity checks + if (plca_cfg->enabled > 0) { + // allow setting node_id concurrently with enabled + if (plca_cfg->node_id >= 0) + curr_plca_cfg->node_id = plca_cfg->node_id; + + ret = plca_check_valid(phydev, curr_plca_cfg, extack); + if (ret) + goto out_drv; + } + + ret = phydev->drv->set_plca_cfg(phydev, plca_cfg); + +out_drv: + kfree(curr_plca_cfg); + mutex_unlock(&phydev->lock); +out: + return ret; +} + +/** + * phy_ethtool_get_plca_status - Get PLCA RS status information + * @phydev: the phy_device struct + * @plca_st: where to store the retrieved status information + * + * Retrieve the PLCA status information from the PHY. Return 0 on success or a + * negative value if an error occurred. + */ +int phy_ethtool_get_plca_status(struct phy_device *phydev, + struct phy_plca_status *plca_st) +{ + int ret; + + if (!phydev->drv) { + ret = -EIO; + goto out; + } + + if (!phydev->drv->get_plca_status) { + ret = -EOPNOTSUPP; + goto out; + } + + mutex_lock(&phydev->lock); + ret = phydev->drv->get_plca_status(phydev, plca_st); + + mutex_unlock(&phydev->lock); +out: + return ret; +} + +/** * phy_start_cable_test - Start a cable test * * @phydev: the phy_device struct diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 716870a4499c..9ba8f973f26f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -45,6 +45,9 @@ EXPORT_SYMBOL_GPL(phy_basic_features); __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_basic_t1_features); +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_basic_t1s_p2mp_features); + __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_gbit_features); @@ -98,6 +101,12 @@ const int phy_basic_t1_features_array[3] = { }; EXPORT_SYMBOL_GPL(phy_basic_t1_features_array); +const int phy_basic_t1s_p2mp_features_array[2] = { + ETHTOOL_LINK_MODE_TP_BIT, + ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, +}; +EXPORT_SYMBOL_GPL(phy_basic_t1s_p2mp_features_array); + const int phy_gbit_features_array[2] = { ETHTOOL_LINK_MODE_1000baseT_Half_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT, @@ -138,6 +147,11 @@ static void features_init(void) ARRAY_SIZE(phy_basic_t1_features_array), phy_basic_t1_features); + /* 10 half, P2MP, TP */ + linkmode_set_bit_array(phy_basic_t1s_p2mp_features_array, + ARRAY_SIZE(phy_basic_t1s_p2mp_features_array), + phy_basic_t1s_p2mp_features); + /* 10/100 half/full + 1000 half/full */ linkmode_set_bit_array(phy_basic_ports_array, ARRAY_SIZE(phy_basic_ports_array), @@ -932,7 +946,7 @@ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) * probe with C45 to see if we're able to get a valid PHY ID in the C45 * space, if successful, create the C45 PHY device. */ - if (!is_c45 && phy_id == 0 && bus->probe_capabilities >= MDIOBUS_C45) { + if (!is_c45 && phy_id == 0 && bus->read_c45) { r = get_phy_c45_ids(bus, addr, &c45_ids); if (!r) return phy_device_create(bus, addr, phy_id, @@ -1487,6 +1501,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, phydev->interrupts = PHY_INTERRUPT_DISABLED; + /* PHYs can request to use poll mode even though they have an + * associated interrupt line. This could be the case if they + * detect a broken interrupt handling. + */ + if (phydev->dev_flags & PHY_F_NO_IRQ) + phydev->irq = PHY_POLL; + /* Port is set to PORT_TP by default and the actual PHY driver will set * it to different value depending on the PHY configuration. If we have * the generic PHY driver we can't figure it out, thus set the old @@ -3262,6 +3283,9 @@ static const struct ethtool_phy_ops phy_ethtool_phy_ops = { .get_sset_count = phy_ethtool_get_sset_count, .get_strings = phy_ethtool_get_strings, .get_stats = phy_ethtool_get_stats, + .get_plca_cfg = phy_ethtool_get_plca_cfg, + .set_plca_cfg = phy_ethtool_set_plca_cfg, + .get_plca_status = phy_ethtool_get_plca_status, .start_cable_test = phy_start_cable_test, .start_cable_test_tdr = phy_start_cable_test_tdr, }; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 09cc65c0da93..319790221d7f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -241,12 +241,16 @@ void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps) if (caps & MAC_ASYM_PAUSE) __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, linkmodes); - if (caps & MAC_10HD) + if (caps & MAC_10HD) { __set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10baseT1S_Half_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, linkmodes); + } if (caps & MAC_10FD) { __set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, linkmodes); __set_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10baseT1S_Full_BIT, linkmodes); } if (caps & MAC_100HD) { diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 83b99d95b278..c02cad6478a8 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/acpi.h> -#include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> @@ -144,7 +142,7 @@ static const char *sm_state_to_str(unsigned short sm_state) return sm_state_strings[sm_state]; } -static const char *gpio_of_names[] = { +static const char *gpio_names[] = { "mod-def0", "los", "tx-fault", @@ -2563,7 +2561,7 @@ static void sfp_check_state(struct sfp *sfp) for (i = 0; i < GPIO_MAX; i++) if (changed & BIT(i)) - dev_dbg(sfp->dev, "%s %u -> %u\n", gpio_of_names[i], + dev_dbg(sfp->dev, "%s %u -> %u\n", gpio_names[i], !!(sfp->state & BIT(i)), !!(state & BIT(i))); state |= sfp->state & (SFP_F_TX_DISABLE | SFP_F_RATE_SELECT); @@ -2644,10 +2642,8 @@ static void sfp_cleanup(void *data) static int sfp_i2c_get(struct sfp *sfp) { - struct acpi_handle *acpi_handle; struct fwnode_handle *h; struct i2c_adapter *i2c; - struct device_node *np; int err; h = fwnode_find_reference(dev_fwnode(sfp->dev), "i2c-bus", 0); @@ -2656,16 +2652,7 @@ static int sfp_i2c_get(struct sfp *sfp) return -ENODEV; } - if (is_acpi_device_node(h)) { - acpi_handle = ACPI_HANDLE_FWNODE(h); - i2c = i2c_acpi_find_adapter_by_handle(acpi_handle); - } else if ((np = to_of_node(h)) != NULL) { - i2c = of_find_i2c_adapter_by_node(np); - } else { - err = -EINVAL; - goto put; - } - + i2c = i2c_get_adapter_by_fwnode(h); if (!i2c) { err = -EPROBE_DEFER; goto put; @@ -2696,19 +2683,11 @@ static int sfp_probe(struct platform_device *pdev) if (err < 0) return err; - sff = sfp->type = &sfp_data; - - if (pdev->dev.of_node) { - const struct of_device_id *id; + sff = device_get_match_data(sfp->dev); + if (!sff) + sff = &sfp_data; - id = of_match_node(sfp_of_match, pdev->dev.of_node); - if (WARN_ON(!id)) - return -EINVAL; - - sff = sfp->type = id->data; - } else if (!has_acpi_companion(&pdev->dev)) { - return -EINVAL; - } + sfp->type = sff; err = sfp_i2c_get(sfp); if (err) @@ -2717,7 +2696,7 @@ static int sfp_probe(struct platform_device *pdev) for (i = 0; i < GPIO_MAX; i++) if (sff->gpios & BIT(i)) { sfp->gpio[i] = devm_gpiod_get_optional(sfp->dev, - gpio_of_names[i], gpio_flags[i]); + gpio_names[i], gpio_flags[i]); if (IS_ERR(sfp->gpio[i])) return PTR_ERR(sfp->gpio[i]); } @@ -2772,7 +2751,7 @@ static int sfp_probe(struct platform_device *pdev) sfp_irq_name = devm_kasprintf(sfp->dev, GFP_KERNEL, "%s-%s", dev_name(sfp->dev), - gpio_of_names[i]); + gpio_names[i]); if (!sfp_irq_name) return -ENOMEM; diff --git a/drivers/net/thunderbolt/Kconfig b/drivers/net/thunderbolt/Kconfig new file mode 100644 index 000000000000..e127848c8cbd --- /dev/null +++ b/drivers/net/thunderbolt/Kconfig @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only +config USB4_NET + tristate "Networking over USB4 and Thunderbolt cables" + depends on USB4 && INET + help + Select this if you want to create network between two computers + over a USB4 and Thunderbolt cables. The driver supports Apple + ThunderboltIP protocol and allows communication with any host + supporting the same protocol including Windows and macOS. + + To compile this driver a module, choose M here. The module will be + called thunderbolt_net. diff --git a/drivers/net/thunderbolt/Makefile b/drivers/net/thunderbolt/Makefile new file mode 100644 index 000000000000..e81c2a4849f0 --- /dev/null +++ b/drivers/net/thunderbolt/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_USB4_NET) := thunderbolt_net.o +thunderbolt_net-objs := main.o trace.o + +# Tracepoints need to know where to find trace.h +CFLAGS_trace.o := -I$(src) diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt/main.c index 990484776f2d..26ef3706445e 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt/main.c @@ -23,6 +23,8 @@ #include <net/ip6_checksum.h> +#include "trace.h" + /* Protocol timeouts in ms */ #define TBNET_LOGIN_DELAY 4500 #define TBNET_LOGIN_TIMEOUT 500 @@ -305,6 +307,8 @@ static int tbnet_logout_request(struct tbnet *net) static void start_login(struct tbnet *net) { + netdev_dbg(net->dev, "login started\n"); + mutex_lock(&net->connection_lock); net->login_sent = false; net->login_received = false; @@ -318,6 +322,8 @@ static void stop_login(struct tbnet *net) { cancel_delayed_work_sync(&net->login_work); cancel_work_sync(&net->connected_work); + + netdev_dbg(net->dev, "login stopped\n"); } static inline unsigned int tbnet_frame_size(const struct tbnet_frame *tf) @@ -349,6 +355,8 @@ static void tbnet_free_buffers(struct tbnet_ring *ring) size = TBNET_RX_PAGE_SIZE; } + trace_tbnet_free_frame(i, tf->page, tf->frame.buffer_phy, dir); + if (tf->frame.buffer_phy) dma_unmap_page(dma_dev, tf->frame.buffer_phy, size, dir); @@ -374,6 +382,8 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) int ret, retries = TBNET_LOGOUT_RETRIES; while (send_logout && retries-- > 0) { + netdev_dbg(net->dev, "sending logout request %u\n", + retries); ret = tbnet_logout_request(net); if (ret != -ETIMEDOUT) break; @@ -400,6 +410,8 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) net->login_sent = false; net->login_received = false; + netdev_dbg(net->dev, "network traffic stopped\n"); + mutex_unlock(&net->connection_lock); } @@ -431,12 +443,15 @@ static int tbnet_handle_packet(const void *buf, size_t size, void *data) switch (pkg->hdr.type) { case TBIP_LOGIN: + netdev_dbg(net->dev, "remote login request received\n"); if (!netif_running(net->dev)) break; ret = tbnet_login_response(net, route, sequence, pkg->hdr.command_id); if (!ret) { + netdev_dbg(net->dev, "remote login response sent\n"); + mutex_lock(&net->connection_lock); net->login_received = true; net->remote_transmit_path = pkg->transmit_path; @@ -458,9 +473,12 @@ static int tbnet_handle_packet(const void *buf, size_t size, void *data) break; case TBIP_LOGOUT: + netdev_dbg(net->dev, "remote logout request received\n"); ret = tbnet_logout_response(net, route, sequence, command_id); - if (!ret) + if (!ret) { + netdev_dbg(net->dev, "remote logout response sent\n"); queue_work(system_long_wq, &net->disconnect_work); + } break; default: @@ -512,6 +530,9 @@ static int tbnet_alloc_rx_buffers(struct tbnet *net, unsigned int nbuffers) tf->frame.buffer_phy = dma_addr; tf->dev = net->dev; + trace_tbnet_alloc_rx_frame(index, tf->page, dma_addr, + DMA_FROM_DEVICE); + tb_ring_rx(ring->ring, &tf->frame); ring->prod++; @@ -588,6 +609,8 @@ static int tbnet_alloc_tx_buffers(struct tbnet *net) tf->frame.callback = tbnet_tx_callback; tf->frame.sof = TBIP_PDF_FRAME_START; tf->frame.eof = TBIP_PDF_FRAME_END; + + trace_tbnet_alloc_tx_frame(i, tf->page, dma_addr, DMA_TO_DEVICE); } ring->cons = 0; @@ -612,6 +635,8 @@ static void tbnet_connected_work(struct work_struct *work) if (!connected) return; + netdev_dbg(net->dev, "login successful, enabling paths\n"); + ret = tb_xdomain_alloc_in_hopid(net->xd, net->remote_transmit_path); if (ret != net->remote_transmit_path) { netdev_err(net->dev, "failed to allocate Rx HopID\n"); @@ -647,6 +672,8 @@ static void tbnet_connected_work(struct work_struct *work) netif_carrier_on(net->dev); netif_start_queue(net->dev); + + netdev_dbg(net->dev, "network traffic started\n"); return; err_free_tx_buffers: @@ -668,8 +695,13 @@ static void tbnet_login_work(struct work_struct *work) if (netif_carrier_ok(net->dev)) return; + netdev_dbg(net->dev, "sending login request, retries=%u\n", + net->login_retries); + ret = tbnet_login_request(net, net->login_retries % 4); if (ret) { + netdev_dbg(net->dev, "sending login request failed, ret=%d\n", + ret); if (net->login_retries++ < TBNET_LOGIN_RETRIES) { queue_delayed_work(system_long_wq, &net->login_work, delay); @@ -677,6 +709,8 @@ static void tbnet_login_work(struct work_struct *work) netdev_info(net->dev, "ThunderboltIP login timed out\n"); } } else { + netdev_dbg(net->dev, "received login reply\n"); + net->login_retries = 0; mutex_lock(&net->connection_lock); @@ -807,12 +841,16 @@ static int tbnet_poll(struct napi_struct *napi, int budget) hdr = page_address(page); if (!tbnet_check_frame(net, tf, hdr)) { + trace_tbnet_invalid_rx_ip_frame(hdr->frame_size, + hdr->frame_id, hdr->frame_index, hdr->frame_count); __free_pages(page, TBNET_RX_PAGE_ORDER); dev_kfree_skb_any(net->skb); net->skb = NULL; continue; } + trace_tbnet_rx_ip_frame(hdr->frame_size, hdr->frame_id, + hdr->frame_index, hdr->frame_count); frame_size = le32_to_cpu(hdr->frame_size); skb = net->skb; @@ -846,6 +884,7 @@ static int tbnet_poll(struct napi_struct *napi, int budget) if (last) { skb->protocol = eth_type_trans(skb, net->dev); + trace_tbnet_rx_skb(skb); napi_gro_receive(&net->napi, skb); net->skb = NULL; } @@ -965,6 +1004,8 @@ static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb, for (i = 0; i < frame_count; i++) { hdr = page_address(frames[i]->page); hdr->frame_count = cpu_to_le32(frame_count); + trace_tbnet_tx_ip_frame(hdr->frame_size, hdr->frame_id, + hdr->frame_index, hdr->frame_count); dma_sync_single_for_device(dma_dev, frames[i]->frame.buffer_phy, tbnet_frame_size(frames[i]), DMA_TO_DEVICE); @@ -1029,6 +1070,8 @@ static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb, len = le32_to_cpu(hdr->frame_size) - offset; wsum = csum_partial(dest, len, wsum); hdr->frame_count = cpu_to_le32(frame_count); + trace_tbnet_tx_ip_frame(hdr->frame_size, hdr->frame_id, + hdr->frame_index, hdr->frame_count); offset = 0; } @@ -1071,6 +1114,8 @@ static netdev_tx_t tbnet_start_xmit(struct sk_buff *skb, bool unmap = false; void *dest; + trace_tbnet_tx_skb(skb); + nframes = DIV_ROUND_UP(data_len, TBNET_MAX_PAYLOAD_SIZE); if (tbnet_available_buffers(&net->tx_ring) < nframes) { netif_stop_queue(net->dev); @@ -1177,6 +1222,7 @@ static netdev_tx_t tbnet_start_xmit(struct sk_buff *skb, net->stats.tx_packets++; net->stats.tx_bytes += skb->len; + trace_tbnet_consume_skb(skb); dev_consume_skb_any(skb); return NETDEV_TX_OK; diff --git a/drivers/net/thunderbolt/trace.c b/drivers/net/thunderbolt/trace.c new file mode 100644 index 000000000000..1b1499520a44 --- /dev/null +++ b/drivers/net/thunderbolt/trace.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tracepoints for Thunderbolt/USB4 networking driver + * + * Copyright (C) 2023, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + */ + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/drivers/net/thunderbolt/trace.h b/drivers/net/thunderbolt/trace.h new file mode 100644 index 000000000000..9626eadaebb9 --- /dev/null +++ b/drivers/net/thunderbolt/trace.h @@ -0,0 +1,141 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Tracepoints for Thunderbolt/USB4 networking driver + * + * Copyright (C) 2023, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thunderbolt_net + +#if !defined(__TRACE_THUNDERBOLT_NET_H) || defined(TRACE_HEADER_MULTI_READ) +#define __TRACE_THUNDERBOLT_NET_H + +#include <linux/dma-direction.h> +#include <linux/skbuff.h> +#include <linux/tracepoint.h> + +#define DMA_DATA_DIRECTION_NAMES \ + { DMA_BIDIRECTIONAL, "DMA_BIDIRECTIONAL" }, \ + { DMA_TO_DEVICE, "DMA_TO_DEVICE" }, \ + { DMA_FROM_DEVICE, "DMA_FROM_DEVICE" }, \ + { DMA_NONE, "DMA_NONE" } + +DECLARE_EVENT_CLASS(tbnet_frame, + TP_PROTO(unsigned int index, const void *page, dma_addr_t phys, + enum dma_data_direction dir), + TP_ARGS(index, page, phys, dir), + TP_STRUCT__entry( + __field(unsigned int, index) + __field(const void *, page) + __field(dma_addr_t, phys) + __field(enum dma_data_direction, dir) + ), + TP_fast_assign( + __entry->index = index; + __entry->page = page; + __entry->phys = phys; + __entry->dir = dir; + ), + TP_printk("index=%u page=%p phys=%pad dir=%s", + __entry->index, __entry->page, &__entry->phys, + __print_symbolic(__entry->dir, DMA_DATA_DIRECTION_NAMES)) +); + +DEFINE_EVENT(tbnet_frame, tbnet_alloc_rx_frame, + TP_PROTO(unsigned int index, const void *page, dma_addr_t phys, + enum dma_data_direction dir), + TP_ARGS(index, page, phys, dir) +); + +DEFINE_EVENT(tbnet_frame, tbnet_alloc_tx_frame, + TP_PROTO(unsigned int index, const void *page, dma_addr_t phys, + enum dma_data_direction dir), + TP_ARGS(index, page, phys, dir) +); + +DEFINE_EVENT(tbnet_frame, tbnet_free_frame, + TP_PROTO(unsigned int index, const void *page, dma_addr_t phys, + enum dma_data_direction dir), + TP_ARGS(index, page, phys, dir) +); + +DECLARE_EVENT_CLASS(tbnet_ip_frame, + TP_PROTO(__le32 size, __le16 id, __le16 index, __le32 count), + TP_ARGS(size, id, index, count), + TP_STRUCT__entry( + __field(u32, size) + __field(u16, id) + __field(u16, index) + __field(u32, count) + ), + TP_fast_assign( + __entry->size = le32_to_cpu(size); + __entry->id = le16_to_cpu(id); + __entry->index = le16_to_cpu(index); + __entry->count = le32_to_cpu(count); + ), + TP_printk("id=%u size=%u index=%u count=%u", + __entry->id, __entry->size, __entry->index, __entry->count) +); + +DEFINE_EVENT(tbnet_ip_frame, tbnet_rx_ip_frame, + TP_PROTO(__le32 size, __le16 id, __le16 index, __le32 count), + TP_ARGS(size, id, index, count) +); + +DEFINE_EVENT(tbnet_ip_frame, tbnet_invalid_rx_ip_frame, + TP_PROTO(__le32 size, __le16 id, __le16 index, __le32 count), + TP_ARGS(size, id, index, count) +); + +DEFINE_EVENT(tbnet_ip_frame, tbnet_tx_ip_frame, + TP_PROTO(__le32 size, __le16 id, __le16 index, __le32 count), + TP_ARGS(size, id, index, count) +); + +DECLARE_EVENT_CLASS(tbnet_skb, + TP_PROTO(const struct sk_buff *skb), + TP_ARGS(skb), + TP_STRUCT__entry( + __field(const void *, addr) + __field(unsigned int, len) + __field(unsigned int, data_len) + __field(unsigned int, nr_frags) + ), + TP_fast_assign( + __entry->addr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + ), + TP_printk("skb=%p len=%u data_len=%u nr_frags=%u", + __entry->addr, __entry->len, __entry->data_len, + __entry->nr_frags) +); + +DEFINE_EVENT(tbnet_skb, tbnet_rx_skb, + TP_PROTO(const struct sk_buff *skb), + TP_ARGS(skb) +); + +DEFINE_EVENT(tbnet_skb, tbnet_tx_skb, + TP_PROTO(const struct sk_buff *skb), + TP_ARGS(skb) +); + +DEFINE_EVENT(tbnet_skb, tbnet_consume_skb, + TP_PROTO(const struct sk_buff *skb), + TP_ARGS(skb) +); + +#endif /* _TRACE_THUNDERBOLT_NET_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +#include <trace/define_trace.h> diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c140edb4b648..80849d115e5d 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -747,13 +747,6 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, -/* Realtek RTL8152 Based USB 2.0 Ethernet Adapters */ -{ - USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - /* Realtek RTL8153 Based USB 3.0 Ethernet Adapters */ { USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM, @@ -761,71 +754,6 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, -/* Samsung USB Ethernet Adapters */ -{ - USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, 0xa101, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -#if IS_ENABLED(CONFIG_USB_RTL8152) -/* Linksys USB3GIGV1 Ethernet Adapter */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, -#endif - -/* Lenovo ThinkPad OneLink+ Dock (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3054, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* ThinkPad USB-C Dock (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* ThinkPad Thunderbolt 3 Dock (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3069, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* ThinkPad Thunderbolt 3 Dock Gen 2 (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3082, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* Lenovo Thinkpad USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x7205, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* Lenovo USB C to Ethernet Adapter (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x720c, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* Lenovo USB-C Travel Hub (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x7214, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - /* Lenovo Powered USB-C Travel Hub (4X90S92381, based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x721e, USB_CLASS_COMM, @@ -833,48 +761,6 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, -/* ThinkPad USB-C Dock Gen 2 (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa387, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* NVIDIA Tegra USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(NVIDIA_VENDOR_ID, 0x09ff, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* Microsoft Surface 2 dock (based on Realtek RTL8152) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07ab, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153B) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x0927, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - -/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ -{ - USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM, - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, -}, - /* Aquantia AQtion USB to 5GbE Controller (based on AQC111U) */ { USB_DEVICE_AND_INTERFACE_INFO(AQUANTIA_VENDOR_ID, 0xc101, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 23da1d9dafd1..4c5c1df5d7a4 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9500,9 +9500,8 @@ static int rtl_fw_init(struct r8152 *tp) return 0; } -u8 rtl8152_get_version(struct usb_interface *intf) +static u8 __rtl_get_hw_ver(struct usb_device *udev) { - struct usb_device *udev = interface_to_usbdev(intf); u32 ocp_data = 0; __le32 *tmp; u8 version; @@ -9571,10 +9570,19 @@ u8 rtl8152_get_version(struct usb_interface *intf) break; default: version = RTL_VER_UNKNOWN; - dev_info(&intf->dev, "Unknown version 0x%04x\n", ocp_data); + dev_info(&udev->dev, "Unknown version 0x%04x\n", ocp_data); break; } + return version; +} + +u8 rtl8152_get_version(struct usb_interface *intf) +{ + u8 version; + + version = __rtl_get_hw_ver(interface_to_usbdev(intf)); + dev_dbg(&intf->dev, "Detected version 0x%04x\n", version); return version; @@ -9618,6 +9626,9 @@ static int rtl8152_probe(struct usb_interface *intf, if (version == RTL_VER_UNKNOWN) return -ENODEV; + if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC) + return -ENODEV; + if (!rtl_vendor_mode(intf)) return -ENODEV; @@ -9814,43 +9825,35 @@ static void rtl8152_disconnect(struct usb_interface *intf) } } -#define REALTEK_USB_DEVICE(vend, prod) { \ - USB_DEVICE_INTERFACE_CLASS(vend, prod, USB_CLASS_VENDOR_SPEC), \ -}, \ -{ \ - USB_DEVICE_AND_INTERFACE_INFO(vend, prod, USB_CLASS_COMM, \ - USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), \ -} - /* table of devices that work with this driver */ static const struct usb_device_id rtl8152_table[] = { /* Realtek */ - REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8050), - REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8053), - REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152), - REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153), - REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8155), - REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8156), + { USB_DEVICE(VENDOR_ID_REALTEK, 0x8050) }, + { USB_DEVICE(VENDOR_ID_REALTEK, 0x8053) }, + { USB_DEVICE(VENDOR_ID_REALTEK, 0x8152) }, + { USB_DEVICE(VENDOR_ID_REALTEK, 0x8153) }, + { USB_DEVICE(VENDOR_ID_REALTEK, 0x8155) }, + { USB_DEVICE(VENDOR_ID_REALTEK, 0x8156) }, /* Microsoft */ - REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab), - REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6), - REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927), - REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e), - REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3069), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3082), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x720c), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7214), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x721e), - REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0xa387), - REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041), - REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff), - REALTEK_USB_DEVICE(VENDOR_ID_TPLINK, 0x0601), + { USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab) }, + { USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6) }, + { USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927) }, + { USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e) }, + { USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x304f) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x3054) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x3062) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x3069) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x3082) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x7205) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x720c) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x7214) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x721e) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0xa387) }, + { USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) }, + { USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff) }, + { USB_DEVICE(VENDOR_ID_TPLINK, 0x0601) }, {} }; @@ -9870,7 +9873,67 @@ static struct usb_driver rtl8152_driver = { .disable_hub_initiated_lpm = 1, }; -module_usb_driver(rtl8152_driver); +static int rtl8152_cfgselector_probe(struct usb_device *udev) +{ + struct usb_host_config *c; + int i, num_configs; + + /* Switch the device to vendor mode, if and only if the vendor mode + * driver supports it. + */ + if (__rtl_get_hw_ver(udev) == RTL_VER_UNKNOWN) + return 0; + + /* The vendor mode is not always config #1, so to find it out. */ + c = udev->config; + num_configs = udev->descriptor.bNumConfigurations; + for (i = 0; i < num_configs; (i++, c++)) { + struct usb_interface_descriptor *desc = NULL; + + if (!c->desc.bNumInterfaces) + continue; + desc = &c->intf_cache[0]->altsetting->desc; + if (desc->bInterfaceClass == USB_CLASS_VENDOR_SPEC) + break; + } + + if (i == num_configs) + return -ENODEV; + + if (usb_set_configuration(udev, c->desc.bConfigurationValue)) { + dev_err(&udev->dev, "Failed to set configuration %d\n", + c->desc.bConfigurationValue); + return -ENODEV; + } + + return 0; +} + +static struct usb_device_driver rtl8152_cfgselector_driver = { + .name = MODULENAME "-cfgselector", + .probe = rtl8152_cfgselector_probe, + .id_table = rtl8152_table, + .generic_subclass = 1, +}; + +static int __init rtl8152_driver_init(void) +{ + int ret; + + ret = usb_register_device_driver(&rtl8152_cfgselector_driver, THIS_MODULE); + if (ret) + return ret; + return usb_register(&rtl8152_driver); +} + +static void __exit rtl8152_driver_exit(void) +{ + usb_deregister(&rtl8152_driver); + usb_deregister_device_driver(&rtl8152_cfgselector_driver); +} + +module_init(rtl8152_driver_init); +module_exit(rtl8152_driver_exit); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 64a9a80b2309..283ffddda821 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -555,32 +555,30 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) /*-------------------------------------------------------------------------*/ -static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) +static inline int rx_process(struct usbnet *dev, struct sk_buff *skb) { if (dev->driver_info->rx_fixup && !dev->driver_info->rx_fixup (dev, skb)) { /* With RX_ASSEMBLE, rx_fixup() must update counters */ if (!(dev->driver_info->flags & FLAG_RX_ASSEMBLE)) dev->net->stats.rx_errors++; - goto done; + return -EPROTO; } // else network stack removes extra byte if we forced a short packet /* all data was already cloned from skb inside the driver */ if (dev->driver_info->flags & FLAG_MULTI_PACKET) - goto done; + return -EALREADY; if (skb->len < ETH_HLEN) { dev->net->stats.rx_errors++; dev->net->stats.rx_length_errors++; netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len); - } else { - usbnet_skb_return(dev, skb); - return; + return -EPROTO; } -done: - skb_queue_tail(&dev->done, skb); + usbnet_skb_return(dev, skb); + return 0; } /*-------------------------------------------------------------------------*/ @@ -1514,6 +1512,14 @@ err: return ret; } +static inline void usb_free_skb(struct sk_buff *skb) +{ + struct skb_data *entry = (struct skb_data *)skb->cb; + + usb_free_urb(entry->urb); + dev_kfree_skb(skb); +} + /*-------------------------------------------------------------------------*/ // tasklet (work deferred from completions, in_irq) or timer @@ -1528,15 +1534,14 @@ static void usbnet_bh (struct timer_list *t) entry = (struct skb_data *) skb->cb; switch (entry->state) { case rx_done: - entry->state = rx_cleanup; - rx_process (dev, skb); + if (rx_process(dev, skb)) + usb_free_skb(skb); continue; case tx_done: kfree(entry->urb->sg); fallthrough; case rx_cleanup: - usb_free_urb (entry->urb); - dev_kfree_skb (skb); + usb_free_skb(skb); continue; default: netdev_dbg(dev->net, "bogus skb state %d\n", entry->state); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 18b3de854aeb..a170b0075dcf 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -446,9 +446,7 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) static struct sk_buff *page_to_skb(struct virtnet_info *vi, struct receive_queue *rq, struct page *page, unsigned int offset, - unsigned int len, unsigned int truesize, - bool hdr_valid, unsigned int metasize, - unsigned int headroom) + unsigned int len, unsigned int truesize) { struct sk_buff *skb; struct virtio_net_hdr_mrg_rxbuf *hdr; @@ -466,21 +464,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, else hdr_padded_len = sizeof(struct padded_vnet_hdr); - /* If headroom is not 0, there is an offset between the beginning of the - * data and the allocated space, otherwise the data and the allocated - * space are aligned. - * - * Buffers with headroom use PAGE_SIZE as alloc size, see - * add_recvbuf_mergeable() + get_mergeable_buf_len() - */ - truesize = headroom ? PAGE_SIZE : truesize; - tailroom = truesize - headroom; - buf = p - headroom; - + buf = p; len -= hdr_len; offset += hdr_padded_len; p += hdr_padded_len; - tailroom -= hdr_padded_len + len; + tailroom = truesize - hdr_padded_len - len; shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -510,7 +498,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, if (len <= skb_tailroom(skb)) copy = len; else - copy = ETH_HLEN + metasize; + copy = ETH_HLEN; skb_put_data(skb, p, copy); len -= copy; @@ -549,19 +537,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, give_pages(rq, page); ok: - /* hdr_valid means no XDP, so we can copy the vnet header */ - if (hdr_valid) { - hdr = skb_vnet_hdr(skb); - memcpy(hdr, hdr_p, hdr_len); - } + hdr = skb_vnet_hdr(skb); + memcpy(hdr, hdr_p, hdr_len); if (page_to_free) put_page(page_to_free); - if (metasize) { - __skb_pull(skb, metasize); - skb_metadata_set(skb, metasize); - } - return skb; } @@ -570,22 +550,43 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, struct xdp_frame *xdpf) { struct virtio_net_hdr_mrg_rxbuf *hdr; - int err; + struct skb_shared_info *shinfo; + u8 nr_frags = 0; + int err, i; if (unlikely(xdpf->headroom < vi->hdr_len)) return -EOVERFLOW; - /* Make room for virtqueue hdr (also change xdpf->headroom?) */ + if (unlikely(xdp_frame_has_frags(xdpf))) { + shinfo = xdp_get_shared_info_from_frame(xdpf); + nr_frags = shinfo->nr_frags; + } + + /* In wrapping function virtnet_xdp_xmit(), we need to free + * up the pending old buffers, where we need to calculate the + * position of skb_shared_info in xdp_get_frame_len() and + * xdp_return_frame(), which will involve to xdpf->data and + * xdpf->headroom. Therefore, we need to update the value of + * headroom synchronously here. + */ + xdpf->headroom -= vi->hdr_len; xdpf->data -= vi->hdr_len; /* Zero header and leave csum up to XDP layers */ hdr = xdpf->data; memset(hdr, 0, vi->hdr_len); xdpf->len += vi->hdr_len; - sg_init_one(sq->sg, xdpf->data, xdpf->len); + sg_init_table(sq->sg, nr_frags + 1); + sg_set_buf(sq->sg, xdpf->data, xdpf->len); + for (i = 0; i < nr_frags; i++) { + skb_frag_t *frag = &shinfo->frags[i]; + + sg_set_page(&sq->sg[i + 1], skb_frag_page(frag), + skb_frag_size(frag), skb_frag_off(frag)); + } - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf), - GFP_ATOMIC); + err = virtqueue_add_outbuf(sq->vq, sq->sg, nr_frags + 1, + xdp_to_ptr(xdpf), GFP_ATOMIC); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ @@ -665,7 +666,7 @@ static int virtnet_xdp_xmit(struct net_device *dev, if (likely(is_xdp_frame(ptr))) { struct xdp_frame *frame = ptr_to_xdp(ptr); - bytes += frame->len; + bytes += xdp_get_frame_len(frame); xdp_return_frame(frame); } else { struct sk_buff *skb = ptr; @@ -924,7 +925,7 @@ static struct sk_buff *receive_big(struct net_device *dev, { struct page *page = buf; struct sk_buff *skb = - page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, true, 0, 0); + page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); stats->bytes += len - vi->hdr_len; if (unlikely(!skb)) @@ -938,6 +939,140 @@ err: return NULL; } +/* Why not use xdp_build_skb_from_frame() ? + * XDP core assumes that xdp frags are PAGE_SIZE in length, while in + * virtio-net there are 2 points that do not match its requirements: + * 1. The size of the prefilled buffer is not fixed before xdp is set. + * 2. xdp_build_skb_from_frame() does more checks that we don't need, + * like eth_type_trans() (which virtio-net does in receive_buf()). + */ +static struct sk_buff *build_skb_from_xdp_buff(struct net_device *dev, + struct virtnet_info *vi, + struct xdp_buff *xdp, + unsigned int xdp_frags_truesz) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + unsigned int headroom, data_len; + struct sk_buff *skb; + int metasize; + u8 nr_frags; + + if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { + pr_debug("Error building skb as missing reserved tailroom for xdp"); + return NULL; + } + + if (unlikely(xdp_buff_has_frags(xdp))) + nr_frags = sinfo->nr_frags; + + skb = build_skb(xdp->data_hard_start, xdp->frame_sz); + if (unlikely(!skb)) + return NULL; + + headroom = xdp->data - xdp->data_hard_start; + data_len = xdp->data_end - xdp->data; + skb_reserve(skb, headroom); + __skb_put(skb, data_len); + + metasize = xdp->data - xdp->data_meta; + metasize = metasize > 0 ? metasize : 0; + if (metasize) + skb_metadata_set(skb, metasize); + + if (unlikely(xdp_buff_has_frags(xdp))) + xdp_update_skb_shared_info(skb, nr_frags, + sinfo->xdp_frags_size, + xdp_frags_truesz, + xdp_buff_is_frag_pfmemalloc(xdp)); + + return skb; +} + +/* TODO: build xdp in big mode */ +static int virtnet_build_xdp_buff_mrg(struct net_device *dev, + struct virtnet_info *vi, + struct receive_queue *rq, + struct xdp_buff *xdp, + void *buf, + unsigned int len, + unsigned int frame_sz, + u16 *num_buf, + unsigned int *xdp_frags_truesize, + struct virtnet_rq_stats *stats) +{ + struct virtio_net_hdr_mrg_rxbuf *hdr = buf; + unsigned int headroom, tailroom, room; + unsigned int truesize, cur_frag_size; + struct skb_shared_info *shinfo; + unsigned int xdp_frags_truesz = 0; + struct page *page; + skb_frag_t *frag; + int offset; + void *ctx; + + xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq); + xdp_prepare_buff(xdp, buf - VIRTIO_XDP_HEADROOM, + VIRTIO_XDP_HEADROOM + vi->hdr_len, len - vi->hdr_len, true); + + if (*num_buf > 1) { + /* If we want to build multi-buffer xdp, we need + * to specify that the flags of xdp_buff have the + * XDP_FLAGS_HAS_FRAG bit. + */ + if (!xdp_buff_has_frags(xdp)) + xdp_buff_set_frags_flag(xdp); + + shinfo = xdp_get_shared_info_from_buff(xdp); + shinfo->nr_frags = 0; + shinfo->xdp_frags_size = 0; + } + + if ((*num_buf - 1) > MAX_SKB_FRAGS) + return -EINVAL; + + while ((--*num_buf) >= 1) { + buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx); + if (unlikely(!buf)) { + pr_debug("%s: rx error: %d buffers out of %d missing\n", + dev->name, *num_buf, + virtio16_to_cpu(vi->vdev, hdr->num_buffers)); + dev->stats.rx_length_errors++; + return -EINVAL; + } + + stats->bytes += len; + page = virt_to_head_page(buf); + offset = buf - page_address(page); + + truesize = mergeable_ctx_to_truesize(ctx); + headroom = mergeable_ctx_to_headroom(ctx); + tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + room = SKB_DATA_ALIGN(headroom + tailroom); + + cur_frag_size = truesize; + xdp_frags_truesz += cur_frag_size; + if (unlikely(len > truesize - room || cur_frag_size > PAGE_SIZE)) { + put_page(page); + pr_debug("%s: rx error: len %u exceeds truesize %lu\n", + dev->name, len, (unsigned long)(truesize - room)); + dev->stats.rx_length_errors++; + return -EINVAL; + } + + frag = &shinfo->frags[shinfo->nr_frags++]; + __skb_frag_set_page(frag, page); + skb_frag_off_set(frag, offset); + skb_frag_size_set(frag, len); + if (page_is_pfmemalloc(page)) + xdp_buff_set_frag_pfmemalloc(xdp); + + shinfo->xdp_frags_size += len; + } + + *xdp_frags_truesize = xdp_frags_truesz; + return 0; +} + static struct sk_buff *receive_mergeable(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, @@ -955,16 +1090,17 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct bpf_prog *xdp_prog; unsigned int truesize = mergeable_ctx_to_truesize(ctx); unsigned int headroom = mergeable_ctx_to_headroom(ctx); - unsigned int metasize = 0; - unsigned int frame_sz; + unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); + unsigned int frame_sz, xdp_room; int err; head_skb = NULL; stats->bytes += len - vi->hdr_len; - if (unlikely(len > truesize)) { + if (unlikely(len > truesize - room)) { pr_debug("%s: rx error: len %u exceeds truesize %lu\n", - dev->name, len, (unsigned long)ctx); + dev->name, len, (unsigned long)(truesize - room)); dev->stats.rx_length_errors++; goto err_skb; } @@ -977,11 +1113,14 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { + unsigned int xdp_frags_truesz = 0; + struct skb_shared_info *shinfo; struct xdp_frame *xdpf; struct page *xdp_page; struct xdp_buff xdp; void *data; u32 act; + int i; /* Transient failure which in theory could occur if * in-flight packets from before XDP was enabled reach @@ -990,19 +1129,23 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, if (unlikely(hdr->hdr.gso_type)) goto err_xdp; - /* Buffers with headroom use PAGE_SIZE as alloc size, - * see add_recvbuf_mergeable() + get_mergeable_buf_len() + /* Now XDP core assumes frag size is PAGE_SIZE, but buffers + * with headroom may add hole in truesize, which + * make their length exceed PAGE_SIZE. So we disabled the + * hole mechanism for xdp. See add_recvbuf_mergeable(). */ - frame_sz = headroom ? PAGE_SIZE : truesize; - - /* This happens when rx buffer size is underestimated - * or headroom is not enough because of the buffer - * was refilled before XDP is set. This should only - * happen for the first several packets, so we don't - * care much about its performance. + frame_sz = truesize; + + /* This happens when headroom is not enough because + * of the buffer was prefilled before XDP is set. + * This should only happen for the first several packets. + * In fact, vq reset can be used here to help us clean up + * the prefilled buffers, but many existing devices do not + * support it, and we don't want to bother users who are + * using xdp normally. */ - if (unlikely(num_buf > 1 || - headroom < virtnet_get_headroom(vi))) { + if (!xdp_prog->aux->xdp_has_frags && + (num_buf > 1 || headroom < virtnet_get_headroom(vi))) { /* linearize data for XDP */ xdp_page = xdp_linearize_page(rq, &num_buf, page, offset, @@ -1013,82 +1156,53 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, if (!xdp_page) goto err_xdp; offset = VIRTIO_XDP_HEADROOM; + } else if (unlikely(headroom < virtnet_get_headroom(vi))) { + xdp_room = SKB_DATA_ALIGN(VIRTIO_XDP_HEADROOM + + sizeof(struct skb_shared_info)); + if (len + xdp_room > PAGE_SIZE) + goto err_xdp; + + xdp_page = alloc_page(GFP_ATOMIC); + if (!xdp_page) + goto err_xdp; + + memcpy(page_address(xdp_page) + VIRTIO_XDP_HEADROOM, + page_address(page) + offset, len); + frame_sz = PAGE_SIZE; + offset = VIRTIO_XDP_HEADROOM; } else { xdp_page = page; } - /* Allow consuming headroom but reserve enough space to push - * the descriptor on if we get an XDP_TX return code. - */ data = page_address(xdp_page) + offset; - xdp_init_buff(&xdp, frame_sz - vi->hdr_len, &rq->xdp_rxq); - xdp_prepare_buff(&xdp, data - VIRTIO_XDP_HEADROOM + vi->hdr_len, - VIRTIO_XDP_HEADROOM, len - vi->hdr_len, true); + err = virtnet_build_xdp_buff_mrg(dev, vi, rq, &xdp, data, len, frame_sz, + &num_buf, &xdp_frags_truesz, stats); + if (unlikely(err)) + goto err_xdp_frags; act = bpf_prog_run_xdp(xdp_prog, &xdp); stats->xdp_packets++; switch (act) { case XDP_PASS: - metasize = xdp.data - xdp.data_meta; - - /* recalculate offset to account for any header - * adjustments and minus the metasize to copy the - * metadata in page_to_skb(). Note other cases do not - * build an skb and avoid using offset - */ - offset = xdp.data - page_address(xdp_page) - - vi->hdr_len - metasize; - - /* recalculate len if xdp.data, xdp.data_end or - * xdp.data_meta were adjusted - */ - len = xdp.data_end - xdp.data + vi->hdr_len + metasize; - - /* recalculate headroom if xdp.data or xdp_data_meta - * were adjusted, note that offset should always point - * to the start of the reserved bytes for virtio_net - * header which are followed by xdp.data, that means - * that offset is equal to the headroom (when buf is - * starting at the beginning of the page, otherwise - * there is a base offset inside the page) but it's used - * with a different starting point (buf start) than - * xdp.data (buf start + vnet hdr size). If xdp.data or - * data_meta were adjusted by the xdp prog then the - * headroom size has changed and so has the offset, we - * can use data_hard_start, which points at buf start + - * vnet hdr size, to calculate the new headroom and use - * it later to compute buf start in page_to_skb() - */ - headroom = xdp.data - xdp.data_hard_start - metasize; - - /* We can only create skb based on xdp_page. */ - if (unlikely(xdp_page != page)) { - rcu_read_unlock(); + if (unlikely(xdp_page != page)) put_page(page); - head_skb = page_to_skb(vi, rq, xdp_page, offset, - len, PAGE_SIZE, false, - metasize, - headroom); - return head_skb; - } - break; + head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz); + rcu_read_unlock(); + return head_skb; case XDP_TX: stats->xdp_tx++; xdpf = xdp_convert_buff_to_frame(&xdp); if (unlikely(!xdpf)) { - if (unlikely(xdp_page != page)) - put_page(xdp_page); - goto err_xdp; + netdev_dbg(dev, "convert buff to frame failed for xdp\n"); + goto err_xdp_frags; } err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); if (unlikely(!err)) { xdp_return_frame_rx_napi(xdpf); } else if (unlikely(err < 0)) { trace_xdp_exception(vi->dev, xdp_prog, act); - if (unlikely(xdp_page != page)) - put_page(xdp_page); - goto err_xdp; + goto err_xdp_frags; } *xdp_xmit |= VIRTIO_XDP_TX; if (unlikely(xdp_page != page)) @@ -1098,11 +1212,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, case XDP_REDIRECT: stats->xdp_redirects++; err = xdp_do_redirect(dev, &xdp, xdp_prog); - if (err) { - if (unlikely(xdp_page != page)) - put_page(xdp_page); - goto err_xdp; - } + if (err) + goto err_xdp_frags; *xdp_xmit |= VIRTIO_XDP_REDIR; if (unlikely(xdp_page != page)) put_page(page); @@ -1115,16 +1226,26 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, trace_xdp_exception(vi->dev, xdp_prog, act); fallthrough; case XDP_DROP: - if (unlikely(xdp_page != page)) - __free_pages(xdp_page, 0); - goto err_xdp; + goto err_xdp_frags; + } +err_xdp_frags: + if (unlikely(xdp_page != page)) + __free_pages(xdp_page, 0); + + if (xdp_buff_has_frags(&xdp)) { + shinfo = xdp_get_shared_info_from_buff(&xdp); + for (i = 0; i < shinfo->nr_frags; i++) { + xdp_page = skb_frag_page(&shinfo->frags[i]); + put_page(xdp_page); + } } + + goto err_xdp; } rcu_read_unlock(); skip_xdp: - head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog, - metasize, headroom); + head_skb = page_to_skb(vi, rq, page, offset, len, truesize); curr_skb = head_skb; if (unlikely(!curr_skb)) @@ -1146,9 +1267,12 @@ skip_xdp: page = virt_to_head_page(buf); truesize = mergeable_ctx_to_truesize(ctx); - if (unlikely(len > truesize)) { + headroom = mergeable_ctx_to_headroom(ctx); + tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + room = SKB_DATA_ALIGN(headroom + tailroom); + if (unlikely(len > truesize - room)) { pr_debug("%s: rx error: len %u exceeds truesize %lu\n", - dev->name, len, (unsigned long)ctx); + dev->name, len, (unsigned long)(truesize - room)); dev->stats.rx_length_errors++; goto err_skb; } @@ -1251,13 +1375,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); dev->stats.rx_length_errors++; - if (vi->mergeable_rx_bufs) { - put_page(virt_to_head_page(buf)); - } else if (vi->big_packets) { - give_pages(rq, buf); - } else { - put_page(virt_to_head_page(buf)); - } + virtnet_rq_free_unused_buf(rq->vq, buf); return; } @@ -1426,13 +1544,16 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, /* To avoid internal fragmentation, if there is very likely not * enough space for another buffer, add the remaining space to * the current buffer. + * XDP core assumes that frame_size of xdp_buff and the length + * of the frag are PAGE_SIZE, so we disable the hole mechanism. */ - len += hole; + if (!headroom) + len += hole; alloc_frag->offset += hole; } sg_init_one(rq->sg, buf, len); - ctx = mergeable_len_to_ctx(len, headroom); + ctx = mergeable_len_to_ctx(len + room, headroom); err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) put_page(virt_to_head_page(buf)); @@ -1608,7 +1729,7 @@ static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) } else { struct xdp_frame *frame = ptr_to_xdp(ptr); - bytes += frame->len; + bytes += xdp_get_frame_len(frame); xdp_return_frame(frame); } packets++; @@ -3080,7 +3201,9 @@ static int virtnet_restore_guest_offloads(struct virtnet_info *vi) static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { - unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr); + unsigned int room = SKB_DATA_ALIGN(VIRTIO_XDP_HEADROOM + + sizeof(struct skb_shared_info)); + unsigned int max_sz = PAGE_SIZE - room - ETH_HLEN; struct virtnet_info *vi = netdev_priv(dev); struct bpf_prog *old_prog; u16 xdp_qp = 0, curr_qp; @@ -3103,9 +3226,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return -EINVAL; } - if (dev->mtu > max_sz) { - NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP"); - netdev_warn(dev, "XDP requires MTU less than %lu\n", max_sz); + if (prog && !prog->aux->xdp_has_frags && dev->mtu > max_sz) { + NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP without frags"); + netdev_warn(dev, "single-buffer XDP requires MTU less than %u\n", max_sz); return -EINVAL; } diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index a2b374372363..1f3b89c885cc 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -51,8 +51,7 @@ struct vhost_vsock { struct hlist_node hash; struct vhost_work send_pkt_work; - spinlock_t send_pkt_list_lock; - struct list_head send_pkt_list; /* host->guest pending packets */ + struct sk_buff_head send_pkt_queue; /* host->guest pending packets */ atomic_t queued_replies; @@ -108,40 +107,31 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, vhost_disable_notify(&vsock->dev, vq); do { - struct virtio_vsock_pkt *pkt; + struct virtio_vsock_hdr *hdr; + size_t iov_len, payload_len; struct iov_iter iov_iter; + u32 flags_to_restore = 0; + struct sk_buff *skb; unsigned out, in; size_t nbytes; - size_t iov_len, payload_len; int head; - u32 flags_to_restore = 0; - spin_lock_bh(&vsock->send_pkt_list_lock); - if (list_empty(&vsock->send_pkt_list)) { - spin_unlock_bh(&vsock->send_pkt_list_lock); + skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); + + if (!skb) { vhost_enable_notify(&vsock->dev, vq); break; } - pkt = list_first_entry(&vsock->send_pkt_list, - struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - spin_unlock_bh(&vsock->send_pkt_list_lock); - head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) { - spin_lock_bh(&vsock->send_pkt_list_lock); - list_add(&pkt->list, &vsock->send_pkt_list); - spin_unlock_bh(&vsock->send_pkt_list_lock); + virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } if (head == vq->num) { - spin_lock_bh(&vsock->send_pkt_list_lock); - list_add(&pkt->list, &vsock->send_pkt_list); - spin_unlock_bh(&vsock->send_pkt_list_lock); - + virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); /* We cannot finish yet if more buffers snuck in while * re-enabling notify. */ @@ -153,26 +143,27 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, } if (out) { - virtio_transport_free_pkt(pkt); + kfree_skb(skb); vq_err(vq, "Expected 0 output buffers, got %u\n", out); break; } iov_len = iov_length(&vq->iov[out], in); - if (iov_len < sizeof(pkt->hdr)) { - virtio_transport_free_pkt(pkt); + if (iov_len < sizeof(*hdr)) { + kfree_skb(skb); vq_err(vq, "Buffer len [%zu] too small\n", iov_len); break; } iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[out], in, iov_len); - payload_len = pkt->len - pkt->off; + payload_len = skb->len; + hdr = virtio_vsock_hdr(skb); /* If the packet is greater than the space available in the * buffer, we split it using multiple buffers. */ - if (payload_len > iov_len - sizeof(pkt->hdr)) { - payload_len = iov_len - sizeof(pkt->hdr); + if (payload_len > iov_len - sizeof(*hdr)) { + payload_len = iov_len - sizeof(*hdr); /* As we are copying pieces of large packet's buffer to * small rx buffers, headers of packets in rx queue are @@ -185,31 +176,30 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, * bits set. After initialized header will be copied to * rx buffer, these required bits will be restored. */ - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) { - pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { + hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM; - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { - pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) { + hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR; } } } /* Set the correct length in the header */ - pkt->hdr.len = cpu_to_le32(payload_len); + hdr->len = cpu_to_le32(payload_len); - nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter); - if (nbytes != sizeof(pkt->hdr)) { - virtio_transport_free_pkt(pkt); + nbytes = copy_to_iter(hdr, sizeof(*hdr), &iov_iter); + if (nbytes != sizeof(*hdr)) { + kfree_skb(skb); vq_err(vq, "Faulted on copying pkt hdr\n"); break; } - nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len, - &iov_iter); + nbytes = copy_to_iter(skb->data, payload_len, &iov_iter); if (nbytes != payload_len) { - virtio_transport_free_pkt(pkt); + kfree_skb(skb); vq_err(vq, "Faulted on copying pkt buf\n"); break; } @@ -217,31 +207,28 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, /* Deliver to monitoring devices all packets that we * will transmit. */ - virtio_transport_deliver_tap_pkt(pkt); + virtio_transport_deliver_tap_pkt(skb); - vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); + vhost_add_used(vq, head, sizeof(*hdr) + payload_len); added = true; - pkt->off += payload_len; + skb_pull(skb, payload_len); total_len += payload_len; /* If we didn't send all the payload we can requeue the packet * to send it with the next available buffer. */ - if (pkt->off < pkt->len) { - pkt->hdr.flags |= cpu_to_le32(flags_to_restore); + if (skb->len > 0) { + hdr->flags |= cpu_to_le32(flags_to_restore); - /* We are queueing the same virtio_vsock_pkt to handle + /* We are queueing the same skb to handle * the remaining bytes, and we want to deliver it * to monitoring devices in the next iteration. */ - pkt->tap_delivered = false; - - spin_lock_bh(&vsock->send_pkt_list_lock); - list_add(&pkt->list, &vsock->send_pkt_list); - spin_unlock_bh(&vsock->send_pkt_list_lock); + virtio_vsock_skb_clear_tap_delivered(skb); + virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); } else { - if (pkt->reply) { + if (virtio_vsock_skb_reply(skb)) { int val; val = atomic_dec_return(&vsock->queued_replies); @@ -253,7 +240,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, restart_tx = true; } - virtio_transport_free_pkt(pkt); + consume_skb(skb); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) @@ -278,28 +265,26 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work) } static int -vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt) +vhost_transport_send_pkt(struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vhost_vsock *vsock; - int len = pkt->len; + int len = skb->len; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ - vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid)); + vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid)); if (!vsock) { rcu_read_unlock(); - virtio_transport_free_pkt(pkt); + kfree_skb(skb); return -ENODEV; } - if (pkt->reply) + if (virtio_vsock_skb_reply(skb)) atomic_inc(&vsock->queued_replies); - spin_lock_bh(&vsock->send_pkt_list_lock); - list_add_tail(&pkt->list, &vsock->send_pkt_list); - spin_unlock_bh(&vsock->send_pkt_list_lock); - + virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); vhost_work_queue(&vsock->dev, &vsock->send_pkt_work); rcu_read_unlock(); @@ -310,10 +295,8 @@ static int vhost_transport_cancel_pkt(struct vsock_sock *vsk) { struct vhost_vsock *vsock; - struct virtio_vsock_pkt *pkt, *n; int cnt = 0; int ret = -ENODEV; - LIST_HEAD(freeme); rcu_read_lock(); @@ -322,20 +305,7 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk) if (!vsock) goto out; - spin_lock_bh(&vsock->send_pkt_list_lock); - list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) { - if (pkt->vsk != vsk) - continue; - list_move(&pkt->list, &freeme); - } - spin_unlock_bh(&vsock->send_pkt_list_lock); - - list_for_each_entry_safe(pkt, n, &freeme, list) { - if (pkt->reply) - cnt++; - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } + cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue); if (cnt) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; @@ -352,12 +322,14 @@ out: return ret; } -static struct virtio_vsock_pkt * -vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, +static struct sk_buff * +vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, unsigned int out, unsigned int in) { - struct virtio_vsock_pkt *pkt; + struct virtio_vsock_hdr *hdr; struct iov_iter iov_iter; + struct sk_buff *skb; + size_t payload_len; size_t nbytes; size_t len; @@ -366,50 +338,48 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) + len = iov_length(vq->iov, out); + + /* len contains both payload and hdr */ + skb = virtio_vsock_alloc_skb(len, GFP_KERNEL); + if (!skb) return NULL; - len = iov_length(vq->iov, out); iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len); - nbytes = copy_from_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter); - if (nbytes != sizeof(pkt->hdr)) { + hdr = virtio_vsock_hdr(skb); + nbytes = copy_from_iter(hdr, sizeof(*hdr), &iov_iter); + if (nbytes != sizeof(*hdr)) { vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n", - sizeof(pkt->hdr), nbytes); - kfree(pkt); + sizeof(*hdr), nbytes); + kfree_skb(skb); return NULL; } - pkt->len = le32_to_cpu(pkt->hdr.len); + payload_len = le32_to_cpu(hdr->len); /* No payload */ - if (!pkt->len) - return pkt; + if (!payload_len) + return skb; - /* The pkt is too big */ - if (pkt->len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { - kfree(pkt); + /* The pkt is too big or the length in the header is invalid */ + if (payload_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || + payload_len + sizeof(*hdr) > len) { + kfree_skb(skb); return NULL; } - pkt->buf = kvmalloc(pkt->len, GFP_KERNEL); - if (!pkt->buf) { - kfree(pkt); - return NULL; - } + virtio_vsock_skb_rx_put(skb); - pkt->buf_len = pkt->len; - - nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter); - if (nbytes != pkt->len) { - vq_err(vq, "Expected %u byte payload, got %zu bytes\n", - pkt->len, nbytes); - virtio_transport_free_pkt(pkt); + nbytes = copy_from_iter(skb->data, payload_len, &iov_iter); + if (nbytes != payload_len) { + vq_err(vq, "Expected %zu byte payload, got %zu bytes\n", + payload_len, nbytes); + kfree_skb(skb); return NULL; } - return pkt; + return skb; } /* Is there space left for replies to rx packets? */ @@ -496,9 +466,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); - struct virtio_vsock_pkt *pkt; int head, pkts = 0, total_len = 0; unsigned int out, in; + struct sk_buff *skb; bool added = false; mutex_lock(&vq->mutex); @@ -511,6 +481,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) vhost_disable_notify(&vsock->dev, vq); do { + struct virtio_vsock_hdr *hdr; + if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue @@ -532,24 +504,26 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) break; } - pkt = vhost_vsock_alloc_pkt(vq, out, in); - if (!pkt) { + skb = vhost_vsock_alloc_skb(vq, out, in); + if (!skb) { vq_err(vq, "Faulted on pkt\n"); continue; } - total_len += sizeof(pkt->hdr) + pkt->len; + total_len += sizeof(*hdr) + skb->len; /* Deliver to monitoring devices all received packets */ - virtio_transport_deliver_tap_pkt(pkt); + virtio_transport_deliver_tap_pkt(skb); + + hdr = virtio_vsock_hdr(skb); /* Only accept correctly addressed packets */ - if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid && - le64_to_cpu(pkt->hdr.dst_cid) == + if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid && + le64_to_cpu(hdr->dst_cid) == vhost_transport_get_local_cid()) - virtio_transport_recv_pkt(&vhost_transport, pkt); + virtio_transport_recv_pkt(&vhost_transport, skb); else - virtio_transport_free_pkt(pkt); + kfree_skb(skb); vhost_add_used(vq, head, 0); added = true; @@ -693,8 +667,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) VHOST_VSOCK_WEIGHT, true, NULL); file->private_data = vsock; - spin_lock_init(&vsock->send_pkt_list_lock); - INIT_LIST_HEAD(&vsock->send_pkt_list); + skb_queue_head_init(&vsock->send_pkt_queue); vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work); return 0; @@ -760,16 +733,7 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file) vhost_vsock_flush(vsock); vhost_dev_stop(&vsock->dev); - spin_lock_bh(&vsock->send_pkt_list_lock); - while (!list_empty(&vsock->send_pkt_list)) { - struct virtio_vsock_pkt *pkt; - - pkt = list_first_entry(&vsock->send_pkt_list, - struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - virtio_transport_free_pkt(pkt); - } - spin_unlock_bh(&vsock->send_pkt_list_lock); + virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue); vhost_dev_cleanup(&vsock->dev); kfree(vsock->dev.vqs); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 5e6a876e17ba..4b12dad5a8a4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -950,6 +950,12 @@ static inline bool acpi_driver_match_device(struct device *dev, return false; } +static inline bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, + u64 rev, u64 funcs) +{ + return false; +} + static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, @@ -958,6 +964,15 @@ static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, return NULL; } +static inline union acpi_object *acpi_evaluate_dsm_typed(acpi_handle handle, + const guid_t *guid, + u64 rev, u64 func, + union acpi_object *argv4, + acpi_object_type type) +{ + return NULL; +} + static inline int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 634d37a599fa..847b97b338a1 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/linux/dsa/ksz_common.h b/include/linux/dsa/ksz_common.h new file mode 100644 index 000000000000..576a99ca698d --- /dev/null +++ b/include/linux/dsa/ksz_common.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Microchip switch tag common header + * + * Copyright (C) 2022 Microchip Technology Inc. + */ + +#ifndef _NET_DSA_KSZ_COMMON_H_ +#define _NET_DSA_KSZ_COMMON_H_ + +#include <net/dsa.h> + +/* All time stamps from the KSZ consist of 2 bits for seconds and 30 bits for + * nanoseconds. This is NOT the same as 32 bits for nanoseconds. + */ +#define KSZ_TSTAMP_SEC_MASK GENMASK(31, 30) +#define KSZ_TSTAMP_NSEC_MASK GENMASK(29, 0) + +static inline ktime_t ksz_decode_tstamp(u32 tstamp) +{ + u64 ns = FIELD_GET(KSZ_TSTAMP_SEC_MASK, tstamp) * NSEC_PER_SEC + + FIELD_GET(KSZ_TSTAMP_NSEC_MASK, tstamp); + + return ns_to_ktime(ns); +} + +struct ksz_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + +struct ksz_tagger_data { + void (*xmit_work_fn)(struct kthread_work *work); + void (*hwtstamp_set_state)(struct dsa_switch *ds, bool on); +}; + +struct ksz_skb_cb { + struct sk_buff *clone; + unsigned int ptp_type; + bool update_correction; + u32 tstamp; +}; + +#define KSZ_SKB_CB(skb) \ + ((struct ksz_skb_cb *)((skb)->cb)) + +static inline struct ksz_tagger_data * +ksz_tagger_data(struct dsa_switch *ds) +{ + return ds->tagger_data; +} + +#endif /* _NET_DSA_KSZ_COMMON_H_ */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9e0a76fc7de9..20d197693d34 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -217,6 +217,9 @@ __ethtool_get_link_ksettings(struct net_device *dev, struct kernel_ethtool_coalesce { u8 use_cqe_mode_tx; u8 use_cqe_mode_rx; + u32 tx_aggr_max_bytes; + u32 tx_aggr_max_frames; + u32 tx_aggr_time_usecs; }; /** @@ -260,7 +263,10 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL BIT(21) #define ETHTOOL_COALESCE_USE_CQE_RX BIT(22) #define ETHTOOL_COALESCE_USE_CQE_TX BIT(23) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(23, 0) +#define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) +#define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) +#define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) @@ -288,6 +294,10 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL) #define ETHTOOL_COALESCE_USE_CQE \ (ETHTOOL_COALESCE_USE_CQE_RX | ETHTOOL_COALESCE_USE_CQE_TX) +#define ETHTOOL_COALESCE_TX_AGGR \ + (ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES | \ + ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES | \ + ETHTOOL_COALESCE_TX_AGGR_TIME_USECS) #define ETHTOOL_STAT_NOT_SET (~0ULL) @@ -802,12 +812,17 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, struct phy_device; struct phy_tdr_config; +struct phy_plca_cfg; +struct phy_plca_status; /** * struct ethtool_phy_ops - Optional PHY device options * @get_sset_count: Get number of strings that @get_strings will write. * @get_strings: Return a set of strings that describe the requested objects * @get_stats: Return extended statistics about the PHY device. + * @get_plca_cfg: Return PLCA configuration. + * @set_plca_cfg: Set PLCA configuration. + * @get_plca_status: Get PLCA configuration. * @start_cable_test: Start a cable test * @start_cable_test_tdr: Start a Time Domain Reflectometry cable test * @@ -819,6 +834,13 @@ struct ethtool_phy_ops { int (*get_strings)(struct phy_device *dev, u8 *data); int (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); + int (*get_plca_cfg)(struct phy_device *dev, + struct phy_plca_cfg *plca_cfg); + int (*set_plca_cfg)(struct phy_device *dev, + const struct phy_plca_cfg *plca_cfg, + struct netlink_ext_ack *extack); + int (*get_plca_status)(struct phy_device *dev, + struct phy_plca_status *plca_st); int (*start_cable_test)(struct phy_device *phydev, struct netlink_ext_ack *extack); int (*start_cable_test_tdr)(struct phy_device *phydev, diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h index 2d9203314865..df25fffdc0ae 100644 --- a/include/linux/fsl/enetc_mdio.h +++ b/include/linux/fsl/enetc_mdio.h @@ -37,16 +37,27 @@ struct enetc_mdio_priv { #if IS_REACHABLE(CONFIG_FSL_ENETC_MDIO) -int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum); -int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value); +int enetc_mdio_read_c22(struct mii_bus *bus, int phy_id, int regnum); +int enetc_mdio_write_c22(struct mii_bus *bus, int phy_id, int regnum, + u16 value); +int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id, int devad, int regnum); +int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad, int regnum, + u16 value); struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs); #else -static inline int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +static inline int enetc_mdio_read_c22(struct mii_bus *bus, int phy_id, + int regnum) { return -EINVAL; } -static inline int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, - u16 value) +static inline int enetc_mdio_write_c22(struct mii_bus *bus, int phy_id, + int regnum, u16 value) +{ return -EINVAL; } +static inline int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id, + int devad, int regnum) +{ return -EINVAL; } +static inline int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id, + int devad, int regnum, u16 value) { return -EINVAL; } struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) { return ERR_PTR(-EINVAL); } diff --git a/include/linux/i2c.h b/include/linux/i2c.h index d84e0e99f084..500404d85141 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -965,15 +965,33 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); #endif /* I2C */ +/* must call put_device() when done with returned i2c_client device */ +struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode); + +/* must call put_device() when done with returned i2c_adapter device */ +struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode); + +/* must call i2c_put_adapter() when done with returned i2c_adapter device */ +struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode); + #if IS_ENABLED(CONFIG_OF) /* must call put_device() when done with returned i2c_client device */ -struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); +static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) +{ + return i2c_find_device_by_fwnode(of_fwnode_handle(node)); +} /* must call put_device() when done with returned i2c_adapter device */ -struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node); +static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) +{ + return i2c_find_adapter_by_fwnode(of_fwnode_handle(node)); +} /* must call i2c_put_adapter() when done with returned i2c_adapter device */ -struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); +static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node) +{ + return i2c_get_adapter_by_fwnode(of_fwnode_handle(node)); +} const struct of_device_id *i2c_of_match_device(const struct of_device_id *matches, diff --git a/include/linux/mdio-bitbang.h b/include/linux/mdio-bitbang.h index 373630fe5c28..cffabdbce075 100644 --- a/include/linux/mdio-bitbang.h +++ b/include/linux/mdio-bitbang.h @@ -38,8 +38,10 @@ struct mdiobb_ctrl { u8 op_c22_write; }; -int mdiobb_read(struct mii_bus *bus, int phy, int reg); -int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val); +int mdiobb_read_c22(struct mii_bus *bus, int phy, int reg); +int mdiobb_write_c22(struct mii_bus *bus, int phy, int reg, u16 val); +int mdiobb_read_c45(struct mii_bus *bus, int devad, int phy, int reg); +int mdiobb_write_c45(struct mii_bus *bus, int devad, int phy, int reg, u16 val); /* The returned bus is not yet registered with the phy layer. */ struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl); diff --git a/include/linux/mdio.h b/include/linux/mdio.h index f7fbbf3069e7..220f3ca8702d 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -423,6 +423,21 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); int mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); +int __mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum); +int mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum); +int mdiobus_c45_read_nested(struct mii_bus *bus, int addr, int devad, + u32 regnum); +int __mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum, + u16 val); +int mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum, + u16 val); +int mdiobus_c45_write_nested(struct mii_bus *bus, int addr, int devad, + u32 regnum, u16 val); +int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum, + u16 mask, u16 set); + +int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad, + u32 regnum, u16 mask, u16 set); static inline int mdiodev_read(struct mdio_device *mdiodev, u32 regnum) { @@ -448,11 +463,6 @@ static inline int mdiodev_modify_changed(struct mdio_device *mdiodev, mask, set); } -static inline u32 mdiobus_c45_addr(int devad, u16 regnum) -{ - return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; -} - static inline u16 mdiobus_c45_regad(u32 regnum) { return FIELD_GET(MII_REGADDR_C45_MASK, regnum); @@ -463,29 +473,19 @@ static inline u16 mdiobus_c45_devad(u32 regnum) return FIELD_GET(MII_DEVADDR_C45_MASK, regnum); } -static inline int __mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, - u16 regnum) -{ - return __mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); -} - -static inline int __mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, - u16 regnum, u16 val) +static inline int mdiodev_c45_modify(struct mdio_device *mdiodev, int devad, + u32 regnum, u16 mask, u16 set) { - return __mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), - val); + return mdiobus_c45_modify(mdiodev->bus, mdiodev->addr, devad, regnum, + mask, set); } -static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, - u16 regnum) -{ - return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); -} - -static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, - u16 regnum, u16 val) +static inline int mdiodev_c45_modify_changed(struct mdio_device *mdiodev, + int devad, u32 regnum, u16 mask, + u16 set) { - return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); + return mdiobus_c45_modify_changed(mdiodev->bus, mdiodev->addr, devad, + regnum, mask, set); } static inline int mdiodev_c45_read(struct mdio_device *mdiodev, int devad, diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 1f7c33b2f5a3..771e050883db 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -8,6 +8,8 @@ #ifndef _MICREL_PHY_H #define _MICREL_PHY_H +#define MICREL_OUI 0x0885 + #define MICREL_PHY_ID_MASK 0x00fffff0 #define PHY_ID_KSZ8873MLL 0x000e7237 diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 76ef2e4fde38..44167760ff29 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -100,6 +100,8 @@ enum { }; enum { + MLX5_REG_SBPR = 0xb001, + MLX5_REG_SBCM = 0xb002, MLX5_REG_QPTS = 0x4002, MLX5_REG_QETCR = 0x4005, MLX5_REG_QTCT = 0x400a, @@ -308,6 +310,7 @@ struct mlx5_cmd { struct workqueue_struct *wq; struct semaphore sem; struct semaphore pages_sem; + struct semaphore throttle_sem; int mode; u16 allowed_opcode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; @@ -551,10 +554,6 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, - /* Distinguish between mlx5e_probe/remove called by module init/cleanup - * and called by other flows which can already hold devlink lock - */ - MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW = 1 << 3, }; struct mlx5_adev { @@ -1200,6 +1199,11 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } +static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); +} + static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a9ee7bc59c90..0b102c651fe2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9941,7 +9941,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x5d]; + u8 reserved_at_0[0x51]; + u8 mtutc_time_adjustment_extended_range[0x1]; + u8 reserved_at_52[0xb]; u8 mcia_32dwords[0x1]; u8 out_pulse_duration_ns[0x1]; u8 npps_period[0x1]; @@ -11000,6 +11002,67 @@ struct mlx5_ifc_pbmc_reg_bits { u8 reserved_at_2e0[0x80]; }; +struct mlx5_ifc_sbpr_reg_bits { + u8 desc[0x1]; + u8 snap[0x1]; + u8 reserved_at_2[0x4]; + u8 dir[0x2]; + u8 reserved_at_8[0x14]; + u8 pool[0x4]; + + u8 infi_size[0x1]; + u8 reserved_at_21[0x7]; + u8 size[0x18]; + + u8 reserved_at_40[0x1c]; + u8 mode[0x4]; + + u8 reserved_at_60[0x8]; + u8 buff_occupancy[0x18]; + + u8 clr[0x1]; + u8 reserved_at_81[0x7]; + u8 max_buff_occupancy[0x18]; + + u8 reserved_at_a0[0x8]; + u8 ext_buff_occupancy[0x18]; +}; + +struct mlx5_ifc_sbcm_reg_bits { + u8 desc[0x1]; + u8 snap[0x1]; + u8 reserved_at_2[0x6]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 pg_buff[0x6]; + u8 reserved_at_18[0x6]; + u8 dir[0x2]; + + u8 reserved_at_20[0x1f]; + u8 exc[0x1]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x8]; + u8 buff_occupancy[0x18]; + + u8 clr[0x1]; + u8 reserved_at_a1[0x7]; + u8 max_buff_occupancy[0x18]; + + u8 reserved_at_c0[0x8]; + u8 min_buff[0x18]; + + u8 infi_max[0x1]; + u8 reserved_at_e1[0x7]; + u8 max_buff[0x18]; + + u8 reserved_at_100[0x20]; + + u8 reserved_at_120[0x1c]; + u8 pool[0x4]; +}; + struct mlx5_ifc_qtct_reg_bits { u8 reserved_at_0[0x8]; u8 port_number[0x8]; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index d81bde5a5844..38f6334f408c 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -263,6 +263,10 @@ struct netlink_callback { }; }; +#define NL_ASSET_DUMP_CTX_FITS(type_name) \ + BUILD_BUG_ON(sizeof(type_name) > \ + sizeof_field(struct netlink_callback, ctx)) + struct netlink_notify { struct net *net; u32 portid; diff --git a/include/linux/phy.h b/include/linux/phy.h index 6378c997ded5..fbeba4fee8d4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -45,6 +45,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; @@ -54,6 +55,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) +#define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) @@ -66,6 +68,7 @@ extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; +extern const int phy_basic_t1s_p2mp_features_array[2]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; @@ -364,6 +367,11 @@ struct mii_bus { int (*read)(struct mii_bus *bus, int addr, int regnum); /** @write: Perform a write transfer on the bus */ int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); + /** @read_c45: Perform a C45 read transfer on the bus */ + int (*read_c45)(struct mii_bus *bus, int addr, int devnum, int regnum); + /** @write_c45: Perform a C45 write transfer on the bus */ + int (*write_c45)(struct mii_bus *bus, int addr, int devnum, + int regnum, u16 val); /** @reset: Perform a reset of the bus */ int (*reset)(struct mii_bus *bus); @@ -411,14 +419,6 @@ struct mii_bus { /** @reset_gpiod: Reset GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; - /** @probe_capabilities: bus capabilities, used for probing */ - enum { - MDIOBUS_NO_CAP = 0, - MDIOBUS_C22, - MDIOBUS_C45, - MDIOBUS_C22_C45, - } probe_capabilities; - /** @shared_lock: protect access to the shared element */ struct mutex shared_lock; @@ -456,7 +456,7 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) } struct mii_bus *mdio_find_bus(const char *mdio_name); -struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); +struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true @@ -739,6 +739,9 @@ struct phy_device { #endif }; +/* Generic phy_device::dev_flags */ +#define PHY_F_NO_IRQ 0x80000000 + static inline struct phy_device *to_phy_device(const struct device *dev) { return container_of(to_mdio_device(dev), struct phy_device, mdio); @@ -766,6 +769,63 @@ struct phy_tdr_config { #define PHY_PAIR_ALL -1 /** + * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision + * Avoidance) Reconciliation Sublayer. + * + * @version: read-only PLCA register map version. -1 = not available. Ignored + * when setting the configuration. Format is the same as reported by the PLCA + * IDVER register (31.CA00). -1 = not available. + * @enabled: PLCA configured mode (enabled/disabled). -1 = not available / don't + * set. 0 = disabled, anything else = enabled. + * @node_id: the PLCA local node identifier. -1 = not available / don't set. + * Allowed values [0 .. 254]. 255 = node disabled. + * @node_cnt: the PLCA node count (maximum number of nodes having a TO). Only + * meaningful for the coordinator (node_id = 0). -1 = not available / don't + * set. Allowed values [1 .. 255]. + * @to_tmr: The value of the PLCA to_timer in bit-times, which determines the + * PLCA transmit opportunity window opening. See IEEE802.3 Clause 148 for + * more details. The to_timer shall be set equal over all nodes. + * -1 = not available / don't set. Allowed values [0 .. 255]. + * @burst_cnt: controls how many additional frames a node is allowed to send in + * single transmit opportunity (TO). The default value of 0 means that the + * node is allowed exactly one frame per TO. A value of 1 allows two frames + * per TO, and so on. -1 = not available / don't set. + * Allowed values [0 .. 255]. + * @burst_tmr: controls how many bit times to wait for the MAC to send a new + * frame before interrupting the burst. This value should be set to a value + * greater than the MAC inter-packet gap (which is typically 96 bits). + * -1 = not available / don't set. Allowed values [0 .. 255]. + * + * A structure containing configuration parameters for setting/getting the PLCA + * RS configuration. The driver does not need to implement all the parameters, + * but should report what is actually used. + */ +struct phy_plca_cfg { + int version; + int enabled; + int node_id; + int node_cnt; + int to_tmr; + int burst_cnt; + int burst_tmr; +}; + +/** + * struct phy_plca_status - Status of the PLCA (Physical Layer Collision + * Avoidance) Reconciliation Sublayer. + * + * @pst: The PLCA status as reported by the PST bit in the PLCA STATUS + * register(31.CA03), indicating BEACON activity. + * + * A structure containing status information of the PLCA RS configuration. + * The driver does not need to implement all the parameters, but should report + * what is actually used. + */ +struct phy_plca_status { + bool pst; +}; + +/** * struct phy_driver - Driver structure for a particular PHY type * * @mdiodrv: Data common to all MDIO devices @@ -976,6 +1036,17 @@ struct phy_driver { int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); + + /* PLCA RS interface */ + /** @get_plca_cfg: Return the current PLCA configuration */ + int (*get_plca_cfg)(struct phy_device *dev, + struct phy_plca_cfg *plca_cfg); + /** @set_plca_cfg: Set the PLCA configuration */ + int (*set_plca_cfg)(struct phy_device *dev, + const struct phy_plca_cfg *plca_cfg); + /** @get_plca_status: Return the current PLCA status info */ + int (*get_plca_status)(struct phy_device *dev, + struct phy_plca_status *plca_st); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) @@ -1674,6 +1745,12 @@ int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); +int genphy_c45_plca_get_cfg(struct phy_device *phydev, + struct phy_plca_cfg *plca_cfg); +int genphy_c45_plca_set_cfg(struct phy_device *phydev, + const struct phy_plca_cfg *plca_cfg); +int genphy_c45_plca_get_status(struct phy_device *phydev, + struct phy_plca_status *plca_st); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; @@ -1772,6 +1849,13 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); +int phy_ethtool_get_plca_cfg(struct phy_device *phydev, + struct phy_plca_cfg *plca_cfg); +int phy_ethtool_set_plca_cfg(struct phy_device *phydev, + const struct phy_plca_cfg *plca_cfg, + struct netlink_ext_ack *extack); +int phy_ethtool_get_plca_status(struct phy_device *phydev, + struct phy_plca_status *plca_st); static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 2b6ea36ad162..1b5a953c6bbc 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -10,8 +10,12 @@ #ifndef _PTP_CLASSIFY_H_ #define _PTP_CLASSIFY_H_ +#include <asm/unaligned.h> #include <linux/ip.h> +#include <linux/ktime.h> #include <linux/skbuff.h> +#include <linux/udp.h> +#include <net/checksum.h> #define PTP_CLASS_NONE 0x00 /* not a PTP event message */ #define PTP_CLASS_V1 0x01 /* protocol version 1 */ @@ -130,6 +134,69 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, } /** + * ptp_check_diff8 - Computes new checksum (when altering a 64-bit field) + * @old: old field value + * @new: new field value + * @oldsum: previous checksum + * + * This function can be used to calculate a new checksum when only a single + * field is changed. Similar as ip_vs_check_diff*() in ip_vs.h. + * + * Return: Updated checksum + */ +static inline __wsum ptp_check_diff8(__be64 old, __be64 new, __wsum oldsum) +{ + __be64 diff[2] = { ~old, new }; + + return csum_partial(diff, sizeof(diff), oldsum); +} + +/** + * ptp_header_update_correction - Update PTP header's correction field + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * @hdr: ptp header + * @correction: new correction value + * + * This updates the correction field of a PTP header and updates the UDP + * checksum (if UDP is used as transport). It is needed for hardware capable of + * one-step P2P that does not already modify the correction field of Pdelay_Req + * event messages on ingress. + */ +static inline +void ptp_header_update_correction(struct sk_buff *skb, unsigned int type, + struct ptp_header *hdr, s64 correction) +{ + __be64 correction_old; + struct udphdr *uhdr; + + /* previous correction value is required for checksum update. */ + memcpy(&correction_old, &hdr->correction, sizeof(correction_old)); + + /* write new correction value */ + put_unaligned_be64((u64)correction, &hdr->correction); + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + case PTP_CLASS_IPV6: + /* locate udp header */ + uhdr = (struct udphdr *)((char *)hdr - sizeof(struct udphdr)); + break; + default: + return; + } + + /* update checksum */ + uhdr->check = csum_fold(ptp_check_diff8(correction_old, + hdr->correction, + ~csum_unfold(uhdr->check))); + if (!uhdr->check) + uhdr->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_NONE; +} + +/** * ptp_msg_is_sync - Evaluates whether the given skb is a PTP Sync message * @skb: packet buffer * @type: type of the packet (see ptp_classify_raw()) @@ -166,5 +233,11 @@ static inline bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type) { return false; } + +static inline +void ptp_header_update_correction(struct sk_buff *skb, unsigned int type, + struct ptp_header *hdr, s64 correction) +{ +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index a3bc695bcca0..029b9e09d3ca 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -38,6 +38,14 @@ struct regmap_field; struct snd_ac97; struct sdw_slave; +/* + * regmap_mdio address encoding. IEEE 802.3ae clause 45 addresses consist of a + * device address and a register address. + */ +#define REGMAP_MDIO_C45_DEVAD_SHIFT 16 +#define REGMAP_MDIO_C45_DEVAD_MASK GENMASK(20, 16) +#define REGMAP_MDIO_C45_REGNUM_MASK GENMASK(15, 0) + /* An enum of all the supported cache types */ enum regcache_type { REGCACHE_NONE, diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index a0746d4aec20..b939bd2750a0 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -151,6 +151,8 @@ struct mtk_wed_device { void (*release_rx_buf)(struct mtk_wed_device *wed); void (*update_wo_rx_stats)(struct mtk_wed_device *wed, struct mtk_wed_wo_rx_stats *stats); + int (*reset)(struct mtk_wed_device *wed); + void (*reset_complete)(struct mtk_wed_device *wed); } wlan; #endif }; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 46040d66334a..ffe48e69b3f3 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -213,16 +213,4 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, return __u64_stats_fetch_retry(syncp, start); } -/* Obsolete interfaces */ -static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) -{ - return u64_stats_fetch_begin(syncp); -} - -static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, - unsigned int start) -{ - return u64_stats_fetch_retry(syncp, start); -} - #endif /* _LINUX_U64_STATS_SYNC_H */ diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 35d7eedb5e8e..3f9c16611306 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -7,6 +7,109 @@ #include <net/sock.h> #include <net/af_vsock.h> +#define VIRTIO_VSOCK_SKB_HEADROOM (sizeof(struct virtio_vsock_hdr)) + +struct virtio_vsock_skb_cb { + bool reply; + bool tap_delivered; +}; + +#define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb)) + +static inline struct virtio_vsock_hdr *virtio_vsock_hdr(struct sk_buff *skb) +{ + return (struct virtio_vsock_hdr *)skb->head; +} + +static inline bool virtio_vsock_skb_reply(struct sk_buff *skb) +{ + return VIRTIO_VSOCK_SKB_CB(skb)->reply; +} + +static inline void virtio_vsock_skb_set_reply(struct sk_buff *skb) +{ + VIRTIO_VSOCK_SKB_CB(skb)->reply = true; +} + +static inline bool virtio_vsock_skb_tap_delivered(struct sk_buff *skb) +{ + return VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered; +} + +static inline void virtio_vsock_skb_set_tap_delivered(struct sk_buff *skb) +{ + VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = true; +} + +static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb) +{ + VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = false; +} + +static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb) +{ + u32 len; + + len = le32_to_cpu(virtio_vsock_hdr(skb)->len); + + if (len > 0) + skb_put(skb, len); +} + +static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask) +{ + struct sk_buff *skb; + + if (size < VIRTIO_VSOCK_SKB_HEADROOM) + return NULL; + + skb = alloc_skb(size, mask); + if (!skb) + return NULL; + + skb_reserve(skb, VIRTIO_VSOCK_SKB_HEADROOM); + return skb; +} + +static inline void +virtio_vsock_skb_queue_head(struct sk_buff_head *list, struct sk_buff *skb) +{ + spin_lock_bh(&list->lock); + __skb_queue_head(list, skb); + spin_unlock_bh(&list->lock); +} + +static inline void +virtio_vsock_skb_queue_tail(struct sk_buff_head *list, struct sk_buff *skb) +{ + spin_lock_bh(&list->lock); + __skb_queue_tail(list, skb); + spin_unlock_bh(&list->lock); +} + +static inline struct sk_buff *virtio_vsock_skb_dequeue(struct sk_buff_head *list) +{ + struct sk_buff *skb; + + spin_lock_bh(&list->lock); + skb = __skb_dequeue(list); + spin_unlock_bh(&list->lock); + + return skb; +} + +static inline void virtio_vsock_skb_queue_purge(struct sk_buff_head *list) +{ + spin_lock_bh(&list->lock); + __skb_queue_purge(list); + spin_unlock_bh(&list->lock); +} + +static inline size_t virtio_vsock_skb_len(struct sk_buff *skb) +{ + return (size_t)(skb_end_pointer(skb) - skb->head); +} + #define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) @@ -35,23 +138,10 @@ struct virtio_vsock_sock { u32 last_fwd_cnt; u32 rx_bytes; u32 buf_alloc; - struct list_head rx_queue; + struct sk_buff_head rx_queue; u32 msg_count; }; -struct virtio_vsock_pkt { - struct virtio_vsock_hdr hdr; - struct list_head list; - /* socket refcnt not held, only use for cancellation */ - struct vsock_sock *vsk; - void *buf; - u32 buf_len; - u32 len; - u32 off; - bool reply; - bool tap_delivered; -}; - struct virtio_vsock_pkt_info { u32 remote_cid, remote_port; struct vsock_sock *vsk; @@ -68,7 +158,7 @@ struct virtio_transport { struct vsock_transport transport; /* Takes ownership of the packet */ - int (*send_pkt)(struct virtio_vsock_pkt *pkt); + int (*send_pkt)(struct sk_buff *skb); }; ssize_t @@ -149,11 +239,10 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk, void virtio_transport_destruct(struct vsock_sock *vsk); void virtio_transport_recv_pkt(struct virtio_transport *t, - struct virtio_vsock_pkt *pkt); -void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); -void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); + struct sk_buff *skb); +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); -void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt); - +void virtio_transport_deliver_tap_pkt(struct sk_buff *skb); +int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list); #endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 8841ab6c2de7..42207fc44660 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -19,18 +19,32 @@ struct dcb_app_type { u8 dcbx; }; +u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app); +int dcb_setrewr(struct net_device *dev, struct dcb_app *app); +int dcb_delrewr(struct net_device *dev, struct dcb_app *app); + int dcb_setapp(struct net_device *, struct dcb_app *); u8 dcb_getapp(struct net_device *, struct dcb_app *); int dcb_ieee_setapp(struct net_device *, struct dcb_app *); int dcb_ieee_delapp(struct net_device *, struct dcb_app *); u8 dcb_ieee_getapp_mask(struct net_device *, struct dcb_app *); +struct dcb_rewr_prio_pcp_map { + u16 map[IEEE_8021QAZ_MAX_TCS]; +}; + +void dcb_getrewr_prio_pcp_mask_map(const struct net_device *dev, + struct dcb_rewr_prio_pcp_map *p_map); + struct dcb_ieee_app_prio_map { u64 map[IEEE_8021QAZ_MAX_TCS]; }; void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, struct dcb_ieee_app_prio_map *p_map); +void dcb_getrewr_prio_dscp_mask_map(const struct net_device *dev, + struct dcb_ieee_app_prio_map *p_map); + struct dcb_ieee_app_dscp_map { u8 map[64]; }; @@ -113,6 +127,10 @@ struct dcbnl_rtnl_ops { /* apptrust */ int (*dcbnl_setapptrust)(struct net_device *, u8 *, int); int (*dcbnl_getapptrust)(struct net_device *, u8 *, int *); + + /* rewrite */ + int (*dcbnl_setrewr)(struct net_device *dev, struct dcb_app *app); + int (*dcbnl_delrewr)(struct net_device *dev, struct dcb_app *app); }; #endif /* __NET_DCBNL_H__ */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 6a2e4f21779f..608a0c198be8 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -146,7 +146,6 @@ struct devlink_port { initialized:1; struct delayed_work type_warn_dw; struct list_head reporter_list; - struct mutex reporters_lock; /* Protects reporter_list */ struct devlink_rate *devlink_rate; struct devlink_linecard *linecard; @@ -1647,6 +1646,8 @@ static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, return devlink_alloc_ns(ops, priv_size, &init_net, dev); } void devlink_set_features(struct devlink *devlink, u64 features); +int devl_register(struct devlink *devlink); +void devl_unregister(struct devlink *devlink); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_free(struct devlink *devlink); @@ -1685,9 +1686,9 @@ void devl_rate_nodes_destroy(struct devlink *devlink); void devlink_port_linecard_set(struct devlink_port *devlink_port, struct devlink_linecard *linecard); struct devlink_linecard * -devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, - const struct devlink_linecard_ops *ops, void *priv); -void devlink_linecard_destroy(struct devlink_linecard *linecard); +devl_linecard_create(struct devlink *devlink, unsigned int linecard_index, + const struct devlink_linecard_ops *ops, void *priv); +void devl_linecard_destroy(struct devlink_linecard *linecard); void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); @@ -1863,20 +1864,30 @@ int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, const void *value, u32 value_len); struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv); +devl_port_health_reporter_create(struct devlink_port *port, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv); struct devlink_health_reporter * devlink_port_health_reporter_create(struct devlink_port *port, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv); +struct devlink_health_reporter * +devl_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv); + +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv); + void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); +devl_health_reporter_destroy(struct devlink_health_reporter *reporter); void -devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter); +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); void * devlink_health_reporter_priv(struct devlink_health_reporter *reporter); diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 88ff7bb2bb9b..632086b2f644 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -16,7 +16,7 @@ struct dst_ops { unsigned short family; unsigned int gc_thresh; - int (*gc)(struct dst_ops *ops); + void (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*mtu)(const struct dst_entry *); diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 3e825381ac5c..780a5f6ad4a6 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -61,6 +61,16 @@ struct nft_immediate_expr { extern const struct nft_expr_ops nft_cmp_fast_ops; extern const struct nft_expr_ops nft_cmp16_fast_ops; +struct nft_ct { + enum nft_ct_keys key:8; + enum ip_conntrack_dir dir:8; + u8 len; + union { + u8 dreg; + u8 sreg; + }; +}; + struct nft_payload { enum nft_payload_bases base:8; u8 offset; @@ -140,6 +150,8 @@ void nft_rt_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_ct_get_fast_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); enum { NFT_PAYLOAD_CTX_INNER_TUN = (1 << 0), @@ -164,4 +176,8 @@ void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt, struct nft_inner_tun_ctx *ctx); +void nft_objref_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); +void nft_objref_map_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index 777ee6cbe933..71492e8276da 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -263,6 +263,51 @@ TRACE_EVENT(inet_sk_error_report, __entry->error) ); +/* + * sock send/recv msg length + */ +DECLARE_EVENT_CLASS(sock_msg_length, + + TP_PROTO(struct sock *sk, int ret, int flags), + + TP_ARGS(sk, ret, flags), + + TP_STRUCT__entry( + __field(void *, sk) + __field(__u16, family) + __field(__u16, protocol) + __field(int, ret) + __field(int, flags) + ), + + TP_fast_assign( + __entry->sk = sk; + __entry->family = sk->sk_family; + __entry->protocol = sk->sk_protocol; + __entry->ret = ret; + __entry->flags = flags; + ), + + TP_printk("sk address = %p, family = %s protocol = %s, length = %d, error = %d, flags = 0x%x", + __entry->sk, show_family_name(__entry->family), + show_inet_protocol_name(__entry->protocol), + !(__entry->flags & MSG_PEEK) ? + (__entry->ret > 0 ? __entry->ret : 0) : 0, + __entry->ret < 0 ? __entry->ret : 0, + __entry->flags) +); + +DEFINE_EVENT(sock_msg_length, sock_send_length, + TP_PROTO(struct sock *sk, int ret, int flags), + + TP_ARGS(sk, ret, flags) +); + +DEFINE_EVENT(sock_msg_length, sock_recv_length, + TP_PROTO(struct sock *sk, int ret, int flags), + + TP_ARGS(sk, ret, flags) +); #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ 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/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 99047223ab26..7e15214aa5dd 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -411,6 +411,7 @@ enum dcbnl_attrs { * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only * @DCB_ATTR_DCB_APP_TRUST_TABLE: selector trust table + * @DCB_ATTR_DCB_REWR_TABLE: rewrite configuration */ enum ieee_attrs { DCB_ATTR_IEEE_UNSPEC, @@ -425,6 +426,7 @@ enum ieee_attrs { DCB_ATTR_IEEE_QCN_STATS, DCB_ATTR_DCB_BUFFER, DCB_ATTR_DCB_APP_TRUST_TABLE, + DCB_ATTR_DCB_REWR_TABLE, __DCB_ATTR_IEEE_MAX }; #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 58e587ba0450..6389953c32cf 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1183,7 +1183,7 @@ struct ethtool_rxnfc { __u32 rule_cnt; __u32 rss_context; }; - __u32 rule_locs[0]; + __u32 rule_locs[]; }; @@ -1741,6 +1741,9 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT = 96, ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT = 97, ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT = 98, + ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, + ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, + ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5799a9db034e..83557cae0b87 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -52,6 +52,9 @@ enum { ETHTOOL_MSG_PSE_GET, ETHTOOL_MSG_PSE_SET, ETHTOOL_MSG_RSS_GET, + ETHTOOL_MSG_PLCA_GET_CFG, + ETHTOOL_MSG_PLCA_SET_CFG, + ETHTOOL_MSG_PLCA_GET_STATUS, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -99,6 +102,9 @@ enum { ETHTOOL_MSG_MODULE_NTF, ETHTOOL_MSG_PSE_GET_REPLY, ETHTOOL_MSG_RSS_GET_REPLY, + ETHTOOL_MSG_PLCA_GET_CFG_REPLY, + ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, + ETHTOOL_MSG_PLCA_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -400,6 +406,9 @@ enum { ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, /* u32 */ ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, /* u8 */ ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, /* u8 */ + ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ + ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ + ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, @@ -894,6 +903,25 @@ enum { ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), }; +/* PLCA */ + +enum { + ETHTOOL_A_PLCA_UNSPEC, + ETHTOOL_A_PLCA_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PLCA_VERSION, /* u16 */ + ETHTOOL_A_PLCA_ENABLED, /* u8 */ + ETHTOOL_A_PLCA_STATUS, /* u8 */ + ETHTOOL_A_PLCA_NODE_CNT, /* u32 */ + ETHTOOL_A_PLCA_NODE_ID, /* u32 */ + ETHTOOL_A_PLCA_TO_TMR, /* u32 */ + ETHTOOL_A_PLCA_BURST_CNT, /* u32 */ + ETHTOOL_A_PLCA_BURST_TMR, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_PLCA_CNT, + ETHTOOL_A_PLCA_MAX = (__ETHTOOL_A_PLCA_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h index ac4de376f0ce..8f72b24fefb3 100644 --- a/include/uapi/linux/ioam6.h +++ b/include/uapi/linux/ioam6.h @@ -127,7 +127,7 @@ struct ioam6_trace_hdr { #endif #define IOAM6_TRACE_DATA_SIZE_MAX 244 - __u8 data[0]; + __u8 data[]; } __attribute__((packed)); #endif /* _UAPI_LINUX_IOAM6_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index cfa844da1ce6..ff677f3a6cad 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -98,6 +98,13 @@ enum nft_verdicts { * @NFT_MSG_GETFLOWTABLE: get flow table (enum nft_flowtable_attributes) * @NFT_MSG_DELFLOWTABLE: delete flow table (enum nft_flowtable_attributes) * @NFT_MSG_GETRULE_RESET: get rules and reset stateful expressions (enum nft_obj_attributes) + * @NFT_MSG_DESTROYTABLE: destroy a table (enum nft_table_attributes) + * @NFT_MSG_DESTROYCHAIN: destroy a chain (enum nft_chain_attributes) + * @NFT_MSG_DESTROYRULE: destroy a rule (enum nft_rule_attributes) + * @NFT_MSG_DESTROYSET: destroy a set (enum nft_set_attributes) + * @NFT_MSG_DESTROYSETELEM: destroy a set element (enum nft_set_elem_attributes) + * @NFT_MSG_DESTROYOBJ: destroy a stateful object (enum nft_object_attributes) + * @NFT_MSG_DESTROYFLOWTABLE: destroy flow table (enum nft_flowtable_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -126,6 +133,13 @@ enum nf_tables_msg_types { NFT_MSG_GETFLOWTABLE, NFT_MSG_DELFLOWTABLE, NFT_MSG_GETRULE_RESET, + NFT_MSG_DESTROYTABLE, + NFT_MSG_DESTROYCHAIN, + NFT_MSG_DESTROYRULE, + NFT_MSG_DESTROYSET, + NFT_MSG_DESTROYSETELEM, + NFT_MSG_DESTROYOBJ, + NFT_MSG_DESTROYFLOWTABLE, NFT_MSG_MAX, }; diff --git a/include/uapi/linux/rpl.h b/include/uapi/linux/rpl.h index 708adddf9f13..7c8970e5b84b 100644 --- a/include/uapi/linux/rpl.h +++ b/include/uapi/linux/rpl.h @@ -37,8 +37,8 @@ struct ipv6_rpl_sr_hdr { #endif union { - struct in6_addr addr[0]; - __u8 data[0]; + __DECLARE_FLEX_ARRAY(struct in6_addr, addr); + __DECLARE_FLEX_ARRAY(__u8, data); } segments; } __attribute__((packed)); diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index eb2747d58a81..25a0af57dd5e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -635,6 +635,7 @@ enum { TCA_INGRESS_BLOCK, TCA_EGRESS_BLOCK, TCA_DUMP_FLAGS, + TCA_EXT_WARN_MSG, __TCA_MAX }; 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 ecca9366c7a6..bf384b3346d6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5309,7 +5309,6 @@ 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 dbef0b0967ae..ba62f98d3c59 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1404,9 +1404,11 @@ 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); } @@ -1752,11 +1754,13 @@ 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; @@ -7622,6 +7626,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[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; @@ -7646,7 +7651,7 @@ 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"); @@ -8781,21 +8786,22 @@ 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 */ @@ -9237,9 +9243,9 @@ 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; @@ -12958,6 +12964,13 @@ 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 */ @@ -13069,79 +13082,74 @@ 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, @@ -13156,7 +13164,7 @@ 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) && @@ -13165,15 +13173,10 @@ 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, @@ -13239,12 +13242,20 @@ 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 @@ -13286,7 +13297,7 @@ 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 f47274de012b..c3f008ac3e42 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/Makefile b/net/Makefile index 6a62e5b27378..0914bea9c335 100644 --- a/net/Makefile +++ b/net/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ +obj-$(CONFIG_NET_DEVLINK) += devlink/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_ATALK) += appletalk/ obj-$(CONFIG_X25) += x25/ diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 748be7253248..1f2c1d7b90e2 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -533,10 +533,6 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_namelen) goto err; - ret = -EINVAL; - if (unlikely(msg->msg_iter.nr_segs == 0) || - unlikely(msg->msg_iter.iov->iov_base == NULL)) - goto err; noblock = msg->msg_flags & MSG_DONTWAIT; timeo = sock_sndtimeo(sk, noblock); diff --git a/net/core/Makefile b/net/core/Makefile index 5857cec87b83..10edd66a8a37 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o -obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o diff --git a/net/core/dev.c b/net/core/dev.c index b76fb37b381e..cf78f35bc0b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1840,7 +1840,7 @@ EXPORT_SYMBOL(register_netdevice_notifier_net); * @nb: notifier * * Unregister a notifier previously registered by - * register_netdevice_notifier(). The notifier is unlinked into the + * register_netdevice_notifier_net(). The notifier is unlinked from the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * diff --git a/net/core/dst.c b/net/core/dst.c index 6d2dd03dafa8..31c08a3386d3 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -82,12 +82,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, if (ops->gc && !(flags & DST_NOCOUNT) && - dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) { - pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); - return NULL; - } - } + dst_entries_get_fast(ops) > ops->gc_thresh) + ops->gc(ops); dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) diff --git a/net/core/filter.c b/net/core/filter.c index 43cc1fe58a2c..7a2b67893afd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4128,9 +4128,13 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { * bpf_redirect_info to actually enqueue the frame into a map type-specific * bulk queue structure. * - * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(), - * which will flush all the different bulk queues, thus completing the - * redirect. + * 3. Before exiting its NAPI poll loop, the driver will call + * xdp_do_flush(), which will flush all the different bulk queues, + * thus completing the redirect. Note that xdp_do_flush() must be + * called before napi_complete_done() in the driver, as the + * XDP_REDIRECT logic relies on being inside a single NAPI instance + * through to the xdp_do_flush() call for RCU protection of all + * in-kernel data structures. */ /* * Pointers to the map entries will be kept around for this whole sequence of @@ -4618,7 +4622,8 @@ 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) { @@ -4656,6 +4661,8 @@ 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/net/core/skbuff.c b/net/core/skbuff.c index 4a0eb5593275..4e73ab3482b8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -386,8 +386,6 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc - * This means that if @frag_size is not zero, then @data must be backed - * by a page fragment, not kmalloc() or vmalloc() */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { @@ -406,7 +404,7 @@ EXPORT_SYMBOL(build_skb); * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller - * @frag_size: size of data, or 0 if head was kmalloced + * @frag_size: size of data */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) @@ -428,7 +426,7 @@ EXPORT_SYMBOL(build_skb_around); /** * __napi_build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of data, or 0 if head was kmalloced + * @frag_size: size of data * * Version of __build_skb() that uses NAPI percpu caches to obtain * skbuff_head instead of inplace allocation. @@ -452,7 +450,7 @@ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) /** * napi_build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of data, or 0 if head was kmalloced + * @frag_size: size of data * * Version of __napi_build_skb() that takes care of skb->head_frag * and skb->pfmemalloc when the data is a page or page fragment. @@ -932,6 +930,21 @@ void __kfree_skb(struct sk_buff *skb) } EXPORT_SYMBOL(__kfree_skb); +static __always_inline +bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +{ + if (unlikely(!skb_unref(skb))) + return false; + + DEBUG_NET_WARN_ON_ONCE(reason <= 0 || reason >= SKB_DROP_REASON_MAX); + + if (reason == SKB_CONSUMED) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, __builtin_return_address(0), reason); + return true; +} + /** * kfree_skb_reason - free an sk_buff with special reason * @skb: buffer to free @@ -944,28 +957,59 @@ EXPORT_SYMBOL(__kfree_skb); void __fix_address kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { - if (unlikely(!skb_unref(skb))) + if (__kfree_skb_reason(skb, reason)) + __kfree_skb(skb); +} +EXPORT_SYMBOL(kfree_skb_reason); + +#define KFREE_SKB_BULK_SIZE 16 + +struct skb_free_array { + unsigned int skb_count; + void *skb_array[KFREE_SKB_BULK_SIZE]; +}; + +static void kfree_skb_add_bulk(struct sk_buff *skb, + struct skb_free_array *sa, + enum skb_drop_reason reason) +{ + /* if SKB is a clone, don't handle this case */ + if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { + __kfree_skb(skb); return; + } - DEBUG_NET_WARN_ON_ONCE(reason <= 0 || reason >= SKB_DROP_REASON_MAX); + skb_release_all(skb, reason); + sa->skb_array[sa->skb_count++] = skb; - if (reason == SKB_CONSUMED) - trace_consume_skb(skb); - else - trace_kfree_skb(skb, __builtin_return_address(0), reason); - __kfree_skb(skb); + if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { + kmem_cache_free_bulk(skbuff_head_cache, KFREE_SKB_BULK_SIZE, + sa->skb_array); + sa->skb_count = 0; + } } -EXPORT_SYMBOL(kfree_skb_reason); -void kfree_skb_list_reason(struct sk_buff *segs, - enum skb_drop_reason reason) +void __fix_address +kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) { + struct skb_free_array sa; + + sa.skb_count = 0; + while (segs) { struct sk_buff *next = segs->next; - kfree_skb_reason(segs, reason); + skb_mark_not_on_list(segs); + + if (__kfree_skb_reason(segs, reason)) + kfree_skb_add_bulk(segs, &sa, reason); + segs = next; } + + if (sa.skb_count) + kmem_cache_free_bulk(skbuff_head_cache, sa.skb_count, + sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 5b1ce656baa1..e7b98162c632 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -643,11 +643,6 @@ static __net_init int sysctl_core_net_init(struct net *net) for (tmp = tbl; tmp->procname; tmp++) tmp->data += (char *)net - (char *)&init_net; - - /* Don't export any sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) { - tbl[0].procname = NULL; - } } net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index f9949e051f49..c0c438128575 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -178,6 +178,7 @@ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { }; static LIST_HEAD(dcb_app_list); +static LIST_HEAD(dcb_rewr_list); static DEFINE_SPINLOCK(dcb_lock); static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) @@ -1099,11 +1100,46 @@ out: return err; } +/* Set or delete APP table or rewrite table entries. The APP struct is validated + * and the appropriate callback function is called. + */ +static int dcbnl_app_table_setdel(struct nlattr *attr, + struct net_device *netdev, + int (*setdel)(struct net_device *dev, + struct dcb_app *app)) +{ + struct dcb_app *app_data; + enum ieee_attrs_app type; + struct nlattr *attr_itr; + int rem, err; + + nla_for_each_nested(attr_itr, attr, rem) { + type = nla_type(attr_itr); + + if (!dcbnl_app_attr_type_validate(type)) + continue; + + if (nla_len(attr_itr) < sizeof(struct dcb_app)) + return -ERANGE; + + app_data = nla_data(attr_itr); + + if (!dcbnl_app_selector_validate(type, app_data->selector)) + return -EINVAL; + + err = setdel(netdev, app_data); + if (err) + return err; + } + + return 0; +} + /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; - struct nlattr *ieee, *app; + struct nlattr *ieee, *app, *rewr; struct dcb_app_type *itr; int dcbx; int err; @@ -1206,6 +1242,27 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); + rewr = nla_nest_start(skb, DCB_ATTR_DCB_REWR_TABLE); + if (!rewr) + return -EMSGSIZE; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == netdev->ifindex) { + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); + if (err) { + spin_unlock_bh(&dcb_lock); + nla_nest_cancel(skb, rewr); + return -EMSGSIZE; + } + } + } + + spin_unlock_bh(&dcb_lock); + nla_nest_end(skb, rewr); + if (ops->dcbnl_getapptrust) { err = dcbnl_getapptrust(netdev, skb); if (err) @@ -1567,37 +1624,20 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, goto err; } - if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { - struct nlattr *attr; - int rem; - - nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { - enum ieee_attrs_app type = nla_type(attr); - struct dcb_app *app_data; - - if (!dcbnl_app_attr_type_validate(type)) - continue; - - if (nla_len(attr) < sizeof(struct dcb_app)) { - err = -ERANGE; - goto err; - } - - app_data = nla_data(attr); - - if (!dcbnl_app_selector_validate(type, - app_data->selector)) { - err = -EINVAL; - goto err; - } + if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], + netdev, + ops->dcbnl_setrewr ?: dcb_setrewr); + if (err) + goto err; + } - if (ops->ieee_setapp) - err = ops->ieee_setapp(netdev, app_data); - else - err = dcb_ieee_setapp(netdev, app_data); - if (err) - goto err; - } + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], + netdev, ops->ieee_setapp ?: + dcb_ieee_setapp); + if (err) + goto err; } if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { @@ -1684,31 +1724,19 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, return err; if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { - struct nlattr *attr; - int rem; - - nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { - enum ieee_attrs_app type = nla_type(attr); - struct dcb_app *app_data; - - if (!dcbnl_app_attr_type_validate(type)) - continue; - - app_data = nla_data(attr); - - if (!dcbnl_app_selector_validate(type, - app_data->selector)) { - err = -EINVAL; - goto err; - } + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], + netdev, ops->ieee_delapp ?: + dcb_ieee_delapp); + if (err) + goto err; + } - if (ops->ieee_delapp) - err = ops->ieee_delapp(netdev, app_data); - else - err = dcb_ieee_delapp(netdev, app_data); - if (err) - goto err; - } + if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], + netdev, + ops->dcbnl_delrewr ?: dcb_delrewr); + if (err) + goto err; } err: @@ -1939,6 +1967,22 @@ out: return ret; } +static struct dcb_app_type *dcb_rewr_lookup(const struct dcb_app *app, + int ifindex, int proto) +{ + struct dcb_app_type *itr; + + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->app.selector == app->selector && + itr->app.priority == app->priority && + itr->ifindex == ifindex && + ((proto == -1) || itr->app.protocol == proto)) + return itr; + } + + return NULL; +} + static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, int ifindex, int prio) { @@ -1955,7 +1999,8 @@ static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, return NULL; } -static int dcb_app_add(const struct dcb_app *app, int ifindex) +static int dcb_app_add(struct list_head *list, const struct dcb_app *app, + int ifindex) { struct dcb_app_type *entry; @@ -1965,7 +2010,7 @@ static int dcb_app_add(const struct dcb_app *app, int ifindex) memcpy(&entry->app, app, sizeof(*app)); entry->ifindex = ifindex; - list_add(&entry->list, &dcb_app_list); + list_add(&entry->list, list); return 0; } @@ -2028,7 +2073,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) } /* App type does not exist add new application type */ if (new->priority) - err = dcb_app_add(new, dev->ifindex); + err = dcb_app_add(&dcb_app_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); if (!err) @@ -2061,6 +2106,63 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) } EXPORT_SYMBOL(dcb_ieee_getapp_mask); +/* Get protocol value from rewrite entry. */ +u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u16 proto = 0; + + spin_lock_bh(&dcb_lock); + itr = dcb_rewr_lookup(app, dev->ifindex, -1); + if (itr) + proto = itr->app.protocol; + spin_unlock_bh(&dcb_lock); + + return proto; +} +EXPORT_SYMBOL(dcb_getrewr); + + /* Add rewrite entry to the rewrite list. */ +int dcb_setrewr(struct net_device *dev, struct dcb_app *new) +{ + int err; + + spin_lock_bh(&dcb_lock); + /* Search for existing match and abort if found. */ + if (dcb_rewr_lookup(new, dev->ifindex, new->protocol)) { + err = -EEXIST; + goto out; + } + + err = dcb_app_add(&dcb_rewr_list, new, dev->ifindex); +out: + spin_unlock_bh(&dcb_lock); + + return err; +} +EXPORT_SYMBOL(dcb_setrewr); + +/* Delete rewrite entry from the rewrite list. */ +int dcb_delrewr(struct net_device *dev, struct dcb_app *del) +{ + struct dcb_app_type *itr; + int err = -ENOENT; + + spin_lock_bh(&dcb_lock); + /* Search for existing match and remove it. */ + itr = dcb_rewr_lookup(del, dev->ifindex, del->protocol); + if (itr) { + list_del(&itr->list); + kfree(itr); + err = 0; + } + + spin_unlock_bh(&dcb_lock); + + return err; +} +EXPORT_SYMBOL(dcb_delrewr); + /** * dcb_ieee_setapp - add IEEE dcb application data to app list * @dev: network interface @@ -2088,7 +2190,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) goto out; } - err = dcb_app_add(new, dev->ifindex); + err = dcb_app_add(&dcb_app_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); if (!err) @@ -2130,6 +2232,58 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) } EXPORT_SYMBOL(dcb_ieee_delapp); +/* dcb_getrewr_prio_pcp_mask_map - For a given device, find mapping from + * priorities to the PCP and DEI values assigned to that priority. + */ +void dcb_getrewr_prio_pcp_mask_map(const struct net_device *dev, + struct dcb_rewr_prio_pcp_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 prio; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == DCB_APP_SEL_PCP && + itr->app.protocol < 16 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) { + prio = itr->app.priority; + p_map->map[prio] |= 1 << itr->app.protocol; + } + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_getrewr_prio_pcp_mask_map); + +/* dcb_getrewr_prio_dscp_mask_map - For a given device, find mapping from + * priorities to the DSCP values assigned to that priority. + */ +void dcb_getrewr_prio_dscp_mask_map(const struct net_device *dev, + struct dcb_ieee_app_prio_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 prio; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && + itr->app.protocol < 64 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) { + prio = itr->app.priority; + p_map->map[prio] |= 1ULL << itr->app.protocol; + } + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_getrewr_prio_dscp_mask_map); + /* * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from * priorities to the DSCP values assigned to that priority. Initialize p_map diff --git a/net/devlink/Makefile b/net/devlink/Makefile new file mode 100644 index 000000000000..1b1eeac59cb3 --- /dev/null +++ b/net/devlink/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := leftover.o core.o netlink.o diff --git a/net/devlink/core.c b/net/devlink/core.c new file mode 100644 index 000000000000..6c0e2fc57e45 --- /dev/null +++ b/net/devlink/core.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + */ + +#include <net/genetlink.h> + +#include "devl_internal.h" + +DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); + +void *devlink_priv(struct devlink *devlink) +{ + return &devlink->priv; +} +EXPORT_SYMBOL_GPL(devlink_priv); + +struct devlink *priv_to_devlink(void *priv) +{ + return container_of(priv, struct devlink, priv); +} +EXPORT_SYMBOL_GPL(priv_to_devlink); + +struct device *devlink_to_dev(const struct devlink *devlink) +{ + return devlink->dev; +} +EXPORT_SYMBOL_GPL(devlink_to_dev); + +struct net *devlink_net(const struct devlink *devlink) +{ + return read_pnet(&devlink->_net); +} +EXPORT_SYMBOL_GPL(devlink_net); + +void devl_assert_locked(struct devlink *devlink) +{ + lockdep_assert_held(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_assert_locked); + +#ifdef CONFIG_LOCKDEP +/* For use in conjunction with LOCKDEP only e.g. rcu_dereference_protected() */ +bool devl_lock_is_held(struct devlink *devlink) +{ + return lockdep_is_held(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_lock_is_held); +#endif + +void devl_lock(struct devlink *devlink) +{ + mutex_lock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_lock); + +int devl_trylock(struct devlink *devlink) +{ + return mutex_trylock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_trylock); + +void devl_unlock(struct devlink *devlink) +{ + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devl_unlock); + +/** + * devlink_try_get() - try to obtain a reference on a devlink instance + * @devlink: instance to reference + * + * Obtain a reference on a devlink instance. A reference on a devlink instance + * only implies that it's safe to take the instance lock. It does not imply + * that the instance is registered, use devl_is_registered() after taking + * the instance lock to check registration status. + */ +struct devlink *__must_check devlink_try_get(struct devlink *devlink) +{ + if (refcount_inc_not_zero(&devlink->refcount)) + return devlink; + return NULL; +} + +static void devlink_release(struct work_struct *work) +{ + struct devlink *devlink; + + devlink = container_of(to_rcu_work(work), struct devlink, rwork); + + mutex_destroy(&devlink->lock); + lockdep_unregister_key(&devlink->lock_key); + kfree(devlink); +} + +void devlink_put(struct devlink *devlink) +{ + if (refcount_dec_and_test(&devlink->refcount)) + queue_rcu_work(system_wq, &devlink->rwork); +} + +struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp) +{ + struct devlink *devlink = NULL; + + rcu_read_lock(); +retry: + devlink = xa_find(&devlinks, indexp, ULONG_MAX, DEVLINK_REGISTERED); + if (!devlink) + goto unlock; + + if (!devlink_try_get(devlink)) + goto next; + if (!net_eq(devlink_net(devlink), net)) { + devlink_put(devlink); + goto next; + } +unlock: + rcu_read_unlock(); + return devlink; + +next: + (*indexp)++; + goto retry; +} + +/** + * devlink_set_features - Set devlink supported features + * + * @devlink: devlink + * @features: devlink support features + * + * This interface allows us to set reload ops separatelly from + * the devlink_alloc. + */ +void devlink_set_features(struct devlink *devlink, u64 features) +{ + WARN_ON(features & DEVLINK_F_RELOAD && + !devlink_reload_supported(devlink->ops)); + devlink->features = features; +} +EXPORT_SYMBOL_GPL(devlink_set_features); + +/** + * devl_register - Register devlink instance + * @devlink: devlink + */ +int devl_register(struct devlink *devlink) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + devl_assert_locked(devlink); + + xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); + devlink_notify_register(devlink); + + return 0; +} +EXPORT_SYMBOL_GPL(devl_register); + +void devlink_register(struct devlink *devlink) +{ + devl_lock(devlink); + devl_register(devlink); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_register); + +/** + * devl_unregister - Unregister devlink instance + * @devlink: devlink + */ +void devl_unregister(struct devlink *devlink) +{ + ASSERT_DEVLINK_REGISTERED(devlink); + devl_assert_locked(devlink); + + devlink_notify_unregister(devlink); + xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); +} +EXPORT_SYMBOL_GPL(devl_unregister); + +void devlink_unregister(struct devlink *devlink) +{ + devl_lock(devlink); + devl_unregister(devlink); + devl_unlock(devlink); +} +EXPORT_SYMBOL_GPL(devlink_unregister); + +/** + * devlink_alloc_ns - Allocate new devlink instance resources + * in specific namespace + * + * @ops: ops + * @priv_size: size of user private data + * @net: net namespace + * @dev: parent device + * + * Allocate new devlink instance resources, including devlink index + * and name. + */ +struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, + size_t priv_size, struct net *net, + struct device *dev) +{ + struct devlink *devlink; + static u32 last_id; + int ret; + + WARN_ON(!ops || !dev); + if (!devlink_reload_actions_valid(ops)) + return NULL; + + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + if (!devlink) + return NULL; + + ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, + &last_id, GFP_KERNEL); + if (ret < 0) + goto err_xa_alloc; + + devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; + ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + if (ret) + goto err_register_netdevice_notifier; + + devlink->dev = dev; + devlink->ops = ops; + xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); + xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); + write_pnet(&devlink->_net, net); + INIT_LIST_HEAD(&devlink->rate_list); + INIT_LIST_HEAD(&devlink->linecard_list); + INIT_LIST_HEAD(&devlink->sb_list); + INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); + INIT_LIST_HEAD(&devlink->resource_list); + INIT_LIST_HEAD(&devlink->param_list); + INIT_LIST_HEAD(&devlink->region_list); + INIT_LIST_HEAD(&devlink->reporter_list); + INIT_LIST_HEAD(&devlink->trap_list); + INIT_LIST_HEAD(&devlink->trap_group_list); + INIT_LIST_HEAD(&devlink->trap_policer_list); + INIT_RCU_WORK(&devlink->rwork, devlink_release); + lockdep_register_key(&devlink->lock_key); + mutex_init(&devlink->lock); + lockdep_set_class(&devlink->lock, &devlink->lock_key); + refcount_set(&devlink->refcount, 1); + + return devlink; + +err_register_netdevice_notifier: + xa_erase(&devlinks, devlink->index); +err_xa_alloc: + kfree(devlink); + return NULL; +} +EXPORT_SYMBOL_GPL(devlink_alloc_ns); + +/** + * devlink_free - Free devlink instance resources + * + * @devlink: devlink + */ +void devlink_free(struct devlink *devlink) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + WARN_ON(!list_empty(&devlink->trap_policer_list)); + WARN_ON(!list_empty(&devlink->trap_group_list)); + WARN_ON(!list_empty(&devlink->trap_list)); + WARN_ON(!list_empty(&devlink->reporter_list)); + WARN_ON(!list_empty(&devlink->region_list)); + WARN_ON(!list_empty(&devlink->param_list)); + WARN_ON(!list_empty(&devlink->resource_list)); + WARN_ON(!list_empty(&devlink->dpipe_table_list)); + WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->rate_list)); + WARN_ON(!list_empty(&devlink->linecard_list)); + WARN_ON(!xa_empty(&devlink->ports)); + + xa_destroy(&devlink->snapshot_ids); + xa_destroy(&devlink->ports); + + WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), + &devlink->netdevice_nb)); + + xa_erase(&devlinks, devlink->index); + + devlink_put(devlink); +} +EXPORT_SYMBOL_GPL(devlink_free); + +static void __net_exit devlink_pernet_pre_exit(struct net *net) +{ + struct devlink *devlink; + u32 actions_performed; + unsigned long index; + int err; + + /* In case network namespace is getting destroyed, reload + * all devlink instances from this namespace into init_net. + */ + devlinks_xa_for_each_registered_get(net, index, devlink) { + WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); + devl_lock(devlink); + err = 0; + if (devl_is_registered(devlink)) + err = devlink_reload(devlink, &init_net, + DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_LIMIT_UNSPEC, + &actions_performed, NULL); + devl_unlock(devlink); + devlink_put(devlink); + + if (err && err != -EOPNOTSUPP) + pr_warn("Failed to reload devlink instance into init_net\n"); + } +} + +static struct pernet_operations devlink_pernet_ops __net_initdata = { + .pre_exit = devlink_pernet_pre_exit, +}; + +static int __init devlink_init(void) +{ + int err; + + err = genl_register_family(&devlink_nl_family); + if (err) + goto out; + err = register_pernet_subsys(&devlink_pernet_ops); + +out: + WARN_ON(err); + return err; +} + +subsys_initcall(devlink_init); diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h new file mode 100644 index 000000000000..1aa1a9549549 --- /dev/null +++ b/net/devlink/devl_internal.h @@ -0,0 +1,192 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + */ + +#include <linux/mutex.h> +#include <linux/netdevice.h> +#include <linux/notifier.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/xarray.h> +#include <net/devlink.h> +#include <net/net_namespace.h> + +#define DEVLINK_REGISTERED XA_MARK_1 + +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + +struct devlink { + u32 index; + struct xarray ports; + struct list_head rate_list; + struct list_head sb_list; + struct list_head dpipe_table_list; + struct list_head resource_list; + struct list_head param_list; + struct list_head region_list; + struct list_head reporter_list; + struct devlink_dpipe_headers *dpipe_headers; + struct list_head trap_list; + struct list_head trap_group_list; + struct list_head trap_policer_list; + struct list_head linecard_list; + const struct devlink_ops *ops; + u64 features; + struct xarray snapshot_ids; + struct devlink_dev_stats stats; + struct device *dev; + possible_net_t _net; + /* Serializes access to devlink instance specific objects such as + * port, sb, dpipe, resource, params, region, traps and more. + */ + struct mutex lock; + struct lock_class_key lock_key; + u8 reload_failed:1; + refcount_t refcount; + struct rcu_work rwork; + struct notifier_block netdevice_nb; + char priv[] __aligned(NETDEV_ALIGN); +}; + +extern struct xarray devlinks; +extern struct genl_family devlink_nl_family; + +/* devlink instances are open to the access from the user space after + * devlink_register() call. Such logical barrier allows us to have certain + * expectations related to locking. + * + * Before *_register() - we are in initialization stage and no parallel + * access possible to the devlink instance. All drivers perform that phase + * by implicitly holding device_lock. + * + * After *_register() - users and driver can access devlink instance at + * the same time. + */ +#define ASSERT_DEVLINK_REGISTERED(d) \ + WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) +#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ + WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) + +/* Iterate over devlink pointers which were possible to get reference to. + * devlink_put() needs to be called for each iterated devlink pointer + * in loop body in order to release the reference. + */ +#define devlinks_xa_for_each_registered_get(net, index, devlink) \ + for (index = 0; (devlink = devlinks_xa_find_get(net, &index)); index++) + +struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp); + +static inline bool devl_is_registered(struct devlink *devlink) +{ + devl_assert_locked(devlink); + return xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); +} + +/* Netlink */ +#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) +#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) +#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) +#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) +#define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) + +enum devlink_multicast_groups { + DEVLINK_MCGRP_CONFIG, +}; + +/* state held across netlink dumps */ +struct devlink_nl_dump_state { + unsigned long instance; + int idx; + union { + /* DEVLINK_CMD_REGION_READ */ + struct { + u64 start_offset; + }; + /* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET */ + struct { + u64 dump_ts; + }; + }; +}; + +struct devlink_gen_cmd { + int (*dump_one)(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb); +}; + +extern const struct genl_small_ops devlink_nl_ops[56]; + +struct devlink * +devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs); + +void devlink_notify_unregister(struct devlink *devlink); +void devlink_notify_register(struct devlink *devlink); + +int devlink_nl_instance_iter_dump(struct sk_buff *msg, + struct netlink_callback *cb); + +static inline struct devlink_nl_dump_state * +devlink_dump_state(struct netlink_callback *cb) +{ + NL_ASSET_DUMP_CTX_FITS(struct devlink_nl_dump_state); + + return (struct devlink_nl_dump_state *)cb->ctx; +} + +/* gen cmds */ +extern const struct devlink_gen_cmd devl_gen_inst; +extern const struct devlink_gen_cmd devl_gen_port; +extern const struct devlink_gen_cmd devl_gen_sb; +extern const struct devlink_gen_cmd devl_gen_sb_pool; +extern const struct devlink_gen_cmd devl_gen_sb_port_pool; +extern const struct devlink_gen_cmd devl_gen_sb_tc_pool_bind; +extern const struct devlink_gen_cmd devl_gen_selftests; +extern const struct devlink_gen_cmd devl_gen_param; +extern const struct devlink_gen_cmd devl_gen_region; +extern const struct devlink_gen_cmd devl_gen_info; +extern const struct devlink_gen_cmd devl_gen_health_reporter; +extern const struct devlink_gen_cmd devl_gen_trap; +extern const struct devlink_gen_cmd devl_gen_trap_group; +extern const struct devlink_gen_cmd devl_gen_trap_policer; +extern const struct devlink_gen_cmd devl_gen_linecard; + +/* Ports */ +int devlink_port_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr); + +struct devlink_port * +devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info); + +/* Reload */ +bool devlink_reload_actions_valid(const struct devlink_ops *ops); +int devlink_reload(struct devlink *devlink, struct net *dest_net, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack); + +static inline bool devlink_reload_supported(const struct devlink_ops *ops) +{ + return ops->reload_down && ops->reload_up; +} + +/* Line cards */ +struct devlink_linecard; + +struct devlink_linecard * +devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info); + +/* Rates */ +extern const struct devlink_gen_cmd devl_gen_rate_get; + +struct devlink_rate * +devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info); +struct devlink_rate * +devlink_rate_node_get_from_info(struct devlink *devlink, + struct genl_info *info); diff --git a/net/core/devlink.c b/net/devlink/leftover.c index 032d6d0a5ce6..8eab95cae917 100644 --- a/net/core/devlink.c +++ b/net/devlink/leftover.c @@ -31,58 +31,12 @@ #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> -#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ - (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) - -struct devlink_dev_stats { - u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; -}; - -struct devlink { - u32 index; - struct xarray ports; - struct list_head rate_list; - struct list_head sb_list; - struct list_head dpipe_table_list; - struct list_head resource_list; - struct list_head param_list; - struct list_head region_list; - struct list_head reporter_list; - struct mutex reporters_lock; /* protects reporter_list */ - struct devlink_dpipe_headers *dpipe_headers; - struct list_head trap_list; - struct list_head trap_group_list; - struct list_head trap_policer_list; - struct list_head linecard_list; - struct mutex linecards_lock; /* protects linecard_list */ - const struct devlink_ops *ops; - u64 features; - struct xarray snapshot_ids; - struct devlink_dev_stats stats; - struct device *dev; - possible_net_t _net; - /* Serializes access to devlink instance specific objects such as - * port, sb, dpipe, resource, params, region, traps and more. - */ - struct mutex lock; - struct lock_class_key lock_key; - u8 reload_failed:1; - refcount_t refcount; - struct completion comp; - struct rcu_head rcu; - struct notifier_block netdevice_nb; - char priv[] __aligned(NETDEV_ALIGN); -}; - -struct devlink_linecard_ops; -struct devlink_linecard_type; +#include "devl_internal.h" struct devlink_linecard { struct list_head list; struct devlink *devlink; unsigned int index; - refcount_t refcount; const struct devlink_linecard_ops *ops; void *priv; enum devlink_linecard_state state; @@ -122,24 +76,6 @@ struct devlink_resource { void *occ_get_priv; }; -void *devlink_priv(struct devlink *devlink) -{ - return &devlink->priv; -} -EXPORT_SYMBOL_GPL(devlink_priv); - -struct devlink *priv_to_devlink(void *priv) -{ - return container_of(priv, struct devlink, priv); -} -EXPORT_SYMBOL_GPL(priv_to_devlink); - -struct device *devlink_to_dev(const struct devlink *devlink) -{ - return devlink->dev; -} -EXPORT_SYMBOL_GPL(devlink_to_dev); - static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { { .name = "destination mac", @@ -211,172 +147,6 @@ static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, }; -static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); -#define DEVLINK_REGISTERED XA_MARK_1 -#define DEVLINK_UNREGISTERING XA_MARK_2 - -/* devlink instances are open to the access from the user space after - * devlink_register() call. Such logical barrier allows us to have certain - * expectations related to locking. - * - * Before *_register() - we are in initialization stage and no parallel - * access possible to the devlink instance. All drivers perform that phase - * by implicitly holding device_lock. - * - * After *_register() - users and driver can access devlink instance at - * the same time. - */ -#define ASSERT_DEVLINK_REGISTERED(d) \ - WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) -#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ - WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) - -struct net *devlink_net(const struct devlink *devlink) -{ - return read_pnet(&devlink->_net); -} -EXPORT_SYMBOL_GPL(devlink_net); - -static void __devlink_put_rcu(struct rcu_head *head) -{ - struct devlink *devlink = container_of(head, struct devlink, rcu); - - complete(&devlink->comp); -} - -void devlink_put(struct devlink *devlink) -{ - if (refcount_dec_and_test(&devlink->refcount)) - /* Make sure unregister operation that may await the completion - * is unblocked only after all users are after the end of - * RCU grace period. - */ - call_rcu(&devlink->rcu, __devlink_put_rcu); -} - -struct devlink *__must_check devlink_try_get(struct devlink *devlink) -{ - if (refcount_inc_not_zero(&devlink->refcount)) - return devlink; - return NULL; -} - -void devl_assert_locked(struct devlink *devlink) -{ - lockdep_assert_held(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_assert_locked); - -#ifdef CONFIG_LOCKDEP -/* For use in conjunction with LOCKDEP only e.g. rcu_dereference_protected() */ -bool devl_lock_is_held(struct devlink *devlink) -{ - return lockdep_is_held(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_lock_is_held); -#endif - -void devl_lock(struct devlink *devlink) -{ - mutex_lock(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_lock); - -int devl_trylock(struct devlink *devlink) -{ - return mutex_trylock(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_trylock); - -void devl_unlock(struct devlink *devlink) -{ - mutex_unlock(&devlink->lock); -} -EXPORT_SYMBOL_GPL(devl_unlock); - -static struct devlink * -devlinks_xa_find_get(struct net *net, unsigned long *indexp, xa_mark_t filter, - void * (*xa_find_fn)(struct xarray *, unsigned long *, - unsigned long, xa_mark_t)) -{ - struct devlink *devlink; - - rcu_read_lock(); -retry: - devlink = xa_find_fn(&devlinks, indexp, ULONG_MAX, DEVLINK_REGISTERED); - if (!devlink) - goto unlock; - - /* In case devlink_unregister() was already called and "unregistering" - * mark was set, do not allow to get a devlink reference here. - * This prevents live-lock of devlink_unregister() wait for completion. - */ - if (xa_get_mark(&devlinks, *indexp, DEVLINK_UNREGISTERING)) - goto retry; - - /* For a possible retry, the xa_find_after() should be always used */ - xa_find_fn = xa_find_after; - if (!devlink_try_get(devlink)) - goto retry; - if (!net_eq(devlink_net(devlink), net)) { - devlink_put(devlink); - goto retry; - } -unlock: - rcu_read_unlock(); - return devlink; -} - -static struct devlink *devlinks_xa_find_get_first(struct net *net, - unsigned long *indexp, - xa_mark_t filter) -{ - return devlinks_xa_find_get(net, indexp, filter, xa_find); -} - -static struct devlink *devlinks_xa_find_get_next(struct net *net, - unsigned long *indexp, - xa_mark_t filter) -{ - return devlinks_xa_find_get(net, indexp, filter, xa_find_after); -} - -/* Iterate over devlink pointers which were possible to get reference to. - * devlink_put() needs to be called for each iterated devlink pointer - * in loop body in order to release the reference. - */ -#define devlinks_xa_for_each_get(net, index, devlink, filter) \ - for (index = 0, \ - devlink = devlinks_xa_find_get_first(net, &index, filter); \ - devlink; devlink = devlinks_xa_find_get_next(net, &index, filter)) - -#define devlinks_xa_for_each_registered_get(net, index, devlink) \ - devlinks_xa_for_each_get(net, index, devlink, DEVLINK_REGISTERED) - -static struct devlink *devlink_get_from_attrs(struct net *net, - struct nlattr **attrs) -{ - struct devlink *devlink; - unsigned long index; - char *busname; - char *devname; - - if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) - return ERR_PTR(-EINVAL); - - busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); - devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); - - devlinks_xa_for_each_registered_get(net, index, devlink) { - if (strcmp(devlink->dev->bus->name, busname) == 0 && - strcmp(dev_name(devlink->dev), devname) == 0) - return devlink; - devlink_put(devlink); - } - - return ERR_PTR(-ENODEV); -} - #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ @@ -405,8 +175,8 @@ static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, return ERR_PTR(-EINVAL); } -static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, - struct genl_info *info) +struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, + struct genl_info *info) { return devlink_port_get_from_attrs(devlink, info->attrs); } @@ -466,13 +236,13 @@ devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) return devlink_rate_node_get_by_name(devlink, rate_node_name); } -static struct devlink_rate * +struct devlink_rate * devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_rate_node_get_from_attrs(devlink, info->attrs); } -static struct devlink_rate * +struct devlink_rate * devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) { struct nlattr **attrs = info->attrs; @@ -511,11 +281,7 @@ devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]); struct devlink_linecard *linecard; - mutex_lock(&devlink->linecards_lock); linecard = devlink_linecard_get_by_index(devlink, linecard_index); - if (linecard) - refcount_inc(&linecard->refcount); - mutex_unlock(&devlink->linecards_lock); if (!linecard) return ERR_PTR(-ENODEV); return linecard; @@ -523,20 +289,12 @@ devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) return ERR_PTR(-EINVAL); } -static struct devlink_linecard * +struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_linecard_get_from_attrs(devlink, info->attrs); } -static void devlink_linecard_put(struct devlink_linecard *linecard) -{ - if (refcount_dec_and_test(&linecard->refcount)) { - mutex_destroy(&linecard->state_lock); - kfree(linecard); - } -} - struct devlink_sb { struct list_head list; unsigned int index; @@ -838,95 +596,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) -#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) -#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) -#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) -#define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) - -static int devlink_nl_pre_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info) -{ - struct devlink_linecard *linecard; - struct devlink_port *devlink_port; - struct devlink *devlink; - int err; - - devlink = devlink_get_from_attrs(genl_info_net(info), info->attrs); - if (IS_ERR(devlink)) - return PTR_ERR(devlink); - devl_lock(devlink); - info->user_ptr[0] = devlink; - if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { - devlink_port = devlink_port_get_from_info(devlink, info); - if (IS_ERR(devlink_port)) { - err = PTR_ERR(devlink_port); - goto unlock; - } - info->user_ptr[1] = devlink_port; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { - devlink_port = devlink_port_get_from_info(devlink, info); - if (!IS_ERR(devlink_port)) - info->user_ptr[1] = devlink_port; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { - struct devlink_rate *devlink_rate; - - devlink_rate = devlink_rate_get_from_info(devlink, info); - if (IS_ERR(devlink_rate)) { - err = PTR_ERR(devlink_rate); - goto unlock; - } - info->user_ptr[1] = devlink_rate; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { - struct devlink_rate *rate_node; - - rate_node = devlink_rate_node_get_from_info(devlink, info); - if (IS_ERR(rate_node)) { - err = PTR_ERR(rate_node); - goto unlock; - } - info->user_ptr[1] = rate_node; - } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { - linecard = devlink_linecard_get_from_info(devlink, info); - if (IS_ERR(linecard)) { - err = PTR_ERR(linecard); - goto unlock; - } - info->user_ptr[1] = linecard; - } - return 0; - -unlock: - devl_unlock(devlink); - devlink_put(devlink); - return err; -} - -static void devlink_nl_post_doit(const struct genl_split_ops *ops, - struct sk_buff *skb, struct genl_info *info) -{ - struct devlink_linecard *linecard; - struct devlink *devlink; - - devlink = info->user_ptr[0]; - if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { - linecard = info->user_ptr[1]; - devlink_linecard_put(linecard); - } - devl_unlock(devlink); - devlink_put(devlink); -} - -static struct genl_family devlink_nl_family; - -enum devlink_multicast_groups { - DEVLINK_MCGRP_CONFIG, -}; - -static const struct genl_multicast_group devlink_nl_mcgrps[] = { - [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, -}; - static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) { if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) @@ -1537,47 +1206,40 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } -static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_rate_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_rate *devlink_rate; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; int idx = 0; int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(devlink_rate, &devlink->rate_list, list) { - enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; - u32 id = NETLINK_CB(cb->skb).portid; + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; + u32 id = NETLINK_CB(cb->skb).portid; - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, NULL); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + if (idx < state->idx) { idx++; + continue; } - devl_unlock(devlink); - devlink_put(devlink); + err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, NULL); + if (err) { + state->idx = idx; + break; + } + idx++; } -out: - if (err != -EMSGSIZE) - return err; - cb->args[0] = idx; - return msg->len; + return err; } +const struct devlink_gen_cmd devl_gen_rate_get = { + .dump_one = devlink_nl_cmd_rate_get_dump_one, +}; + static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -1632,38 +1294,19 @@ static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (idx < start) { - idx++; - devlink_put(devlink); - continue; - } - - devl_lock(devlink); - err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); - devl_unlock(devlink); - devlink_put(devlink); - - if (err) - goto out; - idx++; - } -out: - cb->args[0] = idx; - return msg->len; + return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); } +const struct devlink_gen_cmd devl_gen_inst = { + .dump_one = devlink_nl_cmd_get_dump_one, +}; + static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -1686,43 +1329,40 @@ static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_port *devlink_port; - unsigned long index, port_index; - int start = cb->args[0]; + unsigned long port_index; int idx = 0; - int err; + int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - xa_for_each(&devlink->ports, port_index, devlink_port) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_port_fill(msg, devlink_port, - DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->extack); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + xa_for_each(&devlink->ports, port_index, devlink_port) { + if (idx < state->idx) { idx++; + continue; + } + err = devlink_nl_port_fill(msg, devlink_port, + DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->extack); + if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); - devlink_put(devlink); + idx++; } -out: - cb->args[0] = idx; - return msg->len; + + return err; } +const struct devlink_gen_cmd devl_gen_port = { + .dump_one = devlink_nl_cmd_port_get_dump_one, +}; + static int devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type port_type) @@ -2465,46 +2105,42 @@ static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_linecard_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int devlink_nl_cmd_linecard_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_linecard *linecard; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; int idx = 0; - int err; + int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - mutex_lock(&devlink->linecards_lock); - list_for_each_entry(linecard, &devlink->linecard_list, list) { - if (idx < start) { - idx++; - continue; - } - mutex_lock(&linecard->state_lock); - err = devlink_nl_linecard_fill(msg, devlink, linecard, - DEVLINK_CMD_LINECARD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, - cb->extack); - mutex_unlock(&linecard->state_lock); - if (err) { - mutex_unlock(&devlink->linecards_lock); - devlink_put(devlink); - goto out; - } + list_for_each_entry(linecard, &devlink->linecard_list, list) { + if (idx < state->idx) { idx++; + continue; + } + mutex_lock(&linecard->state_lock); + err = devlink_nl_linecard_fill(msg, devlink, linecard, + DEVLINK_CMD_LINECARD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + cb->extack); + mutex_unlock(&linecard->state_lock); + if (err) { + state->idx = idx; + break; } - mutex_unlock(&devlink->linecards_lock); - devlink_put(devlink); + idx++; } -out: - cb->args[0] = idx; - return msg->len; + + return err; } +const struct devlink_gen_cmd devl_gen_linecard = { + .dump_one = devlink_nl_cmd_linecard_get_dump_one, +}; + static struct devlink_linecard_type * devlink_linecard_type_lookup(struct devlink_linecard *linecard, const char *type) @@ -2727,43 +2363,39 @@ static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_sb_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; int idx = 0; - int err; + int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_sb_fill(msg, devlink, devlink_sb, - DEVLINK_CMD_SB_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + if (idx < state->idx) { idx++; + continue; + } + err = devlink_nl_sb_fill(msg, devlink, devlink_sb, + DEVLINK_CMD_SB_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); - devlink_put(devlink); + idx++; } -out: - cb->args[0] = idx; - return msg->len; + + return err; } +const struct devlink_gen_cmd devl_gen_sb = { + .dump_one = devlink_nl_cmd_sb_get_dump_one, +}; + static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, u16 pool_index, enum devlink_command cmd, @@ -2869,46 +2501,39 @@ static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, return 0; } -static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_sb_pool_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; - int idx = 0; int err = 0; + int idx = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (!devlink->ops->sb_pool_get) - goto retry; + if (!devlink->ops->sb_pool_get) + return 0; - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - err = __sb_pool_get_dumpit(msg, start, &idx, devlink, - devlink_sb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + err = __sb_pool_get_dumpit(msg, state->idx, &idx, + devlink, devlink_sb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); -retry: - devlink_put(devlink); } -out: - if (err != -EMSGSIZE) - return err; - cb->args[0] = idx; - return msg->len; + return err; } +const struct devlink_gen_cmd devl_gen_sb_pool = { + .dump_one = devlink_nl_cmd_sb_pool_get_dump_one, +}; + static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, @@ -3084,46 +2709,39 @@ static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, return 0; } -static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_sb_port_pool_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; int idx = 0; int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (!devlink->ops->sb_port_pool_get) - goto retry; - - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - err = __sb_port_pool_get_dumpit(msg, start, &idx, - devlink, devlink_sb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + if (!devlink->ops->sb_port_pool_get) + return 0; + + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + err = __sb_port_pool_get_dumpit(msg, state->idx, &idx, + devlink, devlink_sb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); -retry: - devlink_put(devlink); } -out: - if (err != -EMSGSIZE) - return err; - cb->args[0] = idx; - return msg->len; + return err; } +const struct devlink_gen_cmd devl_gen_sb_port_pool = { + .dump_one = devlink_nl_cmd_sb_port_pool_get_dump_one, +}; + static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 pool_index, u32 threshold, @@ -3327,47 +2945,38 @@ static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, } static int -devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +devlink_nl_cmd_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; - int start = cb->args[0]; - unsigned long index; int idx = 0; int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (!devlink->ops->sb_tc_pool_bind_get) - goto retry; + if (!devlink->ops->sb_tc_pool_bind_get) + return 0; - devl_lock(devlink); - list_for_each_entry(devlink_sb, &devlink->sb_list, list) { - err = __sb_tc_pool_bind_get_dumpit(msg, start, &idx, - devlink, - devlink_sb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + list_for_each_entry(devlink_sb, &devlink->sb_list, list) { + err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx, + devlink, devlink_sb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); -retry: - devlink_put(devlink); } -out: - if (err != -EMSGSIZE) - return err; - cb->args[0] = idx; - return msg->len; + return err; } +const struct devlink_gen_cmd devl_gen_sb_tc_pool_bind = { + .dump_one = devlink_nl_cmd_sb_tc_pool_bind_get_dump_one, +}; + static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, @@ -4653,11 +4262,6 @@ static void devlink_ns_change_notify(struct devlink *devlink, devlink_notify(devlink, DEVLINK_CMD_DEL); } -static bool devlink_reload_supported(const struct devlink_ops *ops) -{ - return ops->reload_down && ops->reload_up; -} - static void devlink_reload_failed_set(struct devlink *devlink, bool reload_failed) { @@ -4725,9 +4329,10 @@ void devlink_remote_reload_actions_performed(struct devlink *devlink, } EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); -static int devlink_reload(struct devlink *devlink, struct net *dest_net, - enum devlink_reload_action action, enum devlink_reload_limit limit, - u32 *actions_performed, struct netlink_ext_ack *extack) +int devlink_reload(struct devlink *devlink, struct net *dest_net, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) { u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; struct net *curr_net; @@ -5190,41 +4795,24 @@ static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_selftests_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (idx < start || !devlink->ops->selftest_check) - goto inc; - - devl_lock(devlink); - err = devlink_nl_selftests_fill(msg, devlink, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - devl_unlock(devlink); - if (err) { - devlink_put(devlink); - break; - } -inc: - idx++; - devlink_put(devlink); - } - - if (err != -EMSGSIZE) - return err; + if (!devlink->ops->selftest_check) + return 0; - cb->args[0] = idx; - return msg->len; + return devlink_nl_selftests_fill(msg, devlink, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); } +const struct devlink_gen_cmd devl_gen_selftests = { + .dump_one = devlink_nl_cmd_selftests_get_dump_one, +}; + static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, enum devlink_selftest_status test_status) { @@ -5654,7 +5242,13 @@ static void devlink_param_notify(struct devlink *devlink, WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL && cmd != DEVLINK_CMD_PORT_PARAM_NEW && cmd != DEVLINK_CMD_PORT_PARAM_DEL); - ASSERT_DEVLINK_REGISTERED(devlink); + + /* devlink_notify_register() / devlink_notify_unregister() + * will replay the notifications if the params are added/removed + * outside of the lifetime of the instance. + */ + if (!devl_is_registered(devlink)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -5670,48 +5264,41 @@ static void devlink_param_notify(struct devlink *devlink, msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } -static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_param_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_param_item *param_item; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; int idx = 0; int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(param_item, &devlink->param_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_param_fill(msg, devlink, 0, param_item, - DEVLINK_CMD_PARAM_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err == -EOPNOTSUPP) { - err = 0; - } else if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + list_for_each_entry(param_item, &devlink->param_list, list) { + if (idx < state->idx) { idx++; + continue; + } + err = devlink_nl_param_fill(msg, devlink, 0, param_item, + DEVLINK_CMD_PARAM_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); - devlink_put(devlink); + idx++; } -out: - if (err != -EMSGSIZE) - return err; - cb->args[0] = idx; - return msg->len; + return err; } +const struct devlink_gen_cmd devl_gen_param = { + .dump_one = devlink_nl_cmd_param_get_dump_one, +}; + static int devlink_param_type_get_from_info(struct genl_info *info, enum devlink_param_type *param_type) @@ -6375,21 +5962,20 @@ out: return err; } -static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg, - struct netlink_callback *cb, - struct devlink *devlink, - int *idx, - int start) +static int +devlink_nl_cmd_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_region *region; struct devlink_port *port; unsigned long port_index; - int err = 0; + int idx = 0; + int err; - devl_lock(devlink); list_for_each_entry(region, &devlink->region_list, list) { - if (*idx < start) { - (*idx)++; + if (idx < state->idx) { + idx++; continue; } err = devlink_nl_region_fill(msg, devlink, @@ -6397,43 +5983,28 @@ static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, region); - if (err) - goto out; - (*idx)++; + if (err) { + state->idx = idx; + return err; + } + idx++; } xa_for_each(&devlink->ports, port_index, port) { - err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx, - start); - if (err) - goto out; + err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx, + state->idx); + if (err) { + state->idx = idx; + return err; + } } -out: - devl_unlock(devlink); - return err; + return 0; } -static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) -{ - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink, - &idx, start); - devlink_put(devlink); - if (err) - goto out; - } -out: - cb->args[0] = idx; - return msg->len; -} +const struct devlink_gen_cmd devl_gen_region = { + .dump_one = devlink_nl_cmd_region_get_dump_one, +}; static int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info) @@ -6716,6 +6287,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->attrs; @@ -6729,14 +6301,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, void *hdr; int err; - start_offset = *((u64 *)&cb->args[0]); + start_offset = state->start_offset; - devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); + devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs); if (IS_ERR(devlink)) return PTR_ERR(devlink); - devl_lock(devlink); - if (!attrs[DEVLINK_ATTR_REGION_NAME]) { NL_SET_ERR_MSG(cb->extack, "No region name provided"); err = -EINVAL; @@ -6868,7 +6438,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; } - *((u64 *)&cb->args[0]) = ret_offset; + state->start_offset = ret_offset; nla_nest_end(skb, chunks_attr); genlmsg_end(skb, hdr); @@ -7064,43 +6634,25 @@ static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; - int idx = 0; - int err = 0; - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - if (idx < start) - goto inc; - - devl_lock(devlink); - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - devl_unlock(devlink); - if (err == -EOPNOTSUPP) - err = 0; - else if (err) { - devlink_put(devlink); - break; - } -inc: - idx++; - devlink_put(devlink); - } - - if (err != -EMSGSIZE) - return err; + int err; - cb->args[0] = idx; - return msg->len; + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + if (err == -EOPNOTSUPP) + err = 0; + return err; } +const struct devlink_gen_cmd devl_gen_info = { + .dump_one = devlink_nl_cmd_info_get_dump_one, +}; + struct devlink_fmsg_item { struct list_head list; int attrtype; @@ -7666,7 +7218,8 @@ static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, struct netlink_callback *cb, enum devlink_command cmd) { - int index = cb->args[0]; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); + int index = state->idx; int tmp_index = index; void *hdr; int err; @@ -7682,7 +7235,7 @@ static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, if ((err && err != -EMSGSIZE) || tmp_index == index) goto nla_put_failure; - cb->args[0] = index; + state->idx = index; genlmsg_end(skb, hdr); return skb->len; @@ -7708,7 +7261,6 @@ struct devlink_health_reporter { u64 error_count; u64 recovery_count; u64 last_recovery_ts; - refcount_t refcount; }; void * @@ -7720,12 +7272,10 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); static struct devlink_health_reporter * __devlink_health_reporter_find_by_name(struct list_head *reporter_list, - struct mutex *list_lock, const char *reporter_name) { struct devlink_health_reporter *reporter; - lockdep_assert_held(list_lock); list_for_each_entry(reporter, reporter_list, list) if (!strcmp(reporter->ops->name, reporter_name)) return reporter; @@ -7737,7 +7287,6 @@ devlink_health_reporter_find_by_name(struct devlink *devlink, const char *reporter_name) { return __devlink_health_reporter_find_by_name(&devlink->reporter_list, - &devlink->reporters_lock, reporter_name); } @@ -7746,7 +7295,6 @@ devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port, const char *reporter_name) { return __devlink_health_reporter_find_by_name(&devlink_port->reporter_list, - &devlink_port->reporters_lock, reporter_name); } @@ -7771,13 +7319,12 @@ __devlink_health_reporter_create(struct devlink *devlink, reporter->auto_recover = !!ops->recover; reporter->auto_dump = !!ops->dump; mutex_init(&reporter->dump_lock); - refcount_set(&reporter->refcount, 1); return reporter; } /** - * devlink_port_health_reporter_create - create devlink health reporter for - * specified port instance + * devl_port_health_reporter_create - create devlink health reporter for + * specified port instance * * @port: devlink_port which should contain the new reporter * @ops: ops @@ -7785,34 +7332,47 @@ __devlink_health_reporter_create(struct devlink *devlink, * @priv: priv */ struct devlink_health_reporter * -devlink_port_health_reporter_create(struct devlink_port *port, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv) +devl_port_health_reporter_create(struct devlink_port *port, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; - mutex_lock(&port->reporters_lock); + devl_assert_locked(port->devlink); + if (__devlink_health_reporter_find_by_name(&port->reporter_list, - &port->reporters_lock, ops->name)) { - reporter = ERR_PTR(-EEXIST); - goto unlock; - } + ops->name)) + return ERR_PTR(-EEXIST); reporter = __devlink_health_reporter_create(port->devlink, ops, graceful_period, priv); if (IS_ERR(reporter)) - goto unlock; + return reporter; reporter->devlink_port = port; list_add_tail(&reporter->list, &port->reporter_list); -unlock: - mutex_unlock(&port->reporters_lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devl_port_health_reporter_create); + +struct devlink_health_reporter * +devlink_port_health_reporter_create(struct devlink_port *port, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + struct devlink *devlink = port->devlink; + + devl_lock(devlink); + reporter = devl_port_health_reporter_create(port, ops, + graceful_period, priv); + devl_unlock(devlink); return reporter; } EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create); /** - * devlink_health_reporter_create - create devlink health reporter + * devl_health_reporter_create - create devlink health reporter * * @devlink: devlink * @ops: ops @@ -7820,26 +7380,38 @@ EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create); * @priv: priv */ struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, void *priv) +devl_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; - mutex_lock(&devlink->reporters_lock); - if (devlink_health_reporter_find_by_name(devlink, ops->name)) { - reporter = ERR_PTR(-EEXIST); - goto unlock; - } + devl_assert_locked(devlink); + + if (devlink_health_reporter_find_by_name(devlink, ops->name)) + return ERR_PTR(-EEXIST); reporter = __devlink_health_reporter_create(devlink, ops, graceful_period, priv); if (IS_ERR(reporter)) - goto unlock; + return reporter; list_add_tail(&reporter->list, &devlink->reporter_list); -unlock: - mutex_unlock(&devlink->reporters_lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devl_health_reporter_create); + +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + + devl_lock(devlink); + reporter = devl_health_reporter_create(devlink, ops, + graceful_period, priv); + devl_unlock(devlink); return reporter; } EXPORT_SYMBOL_GPL(devlink_health_reporter_create); @@ -7853,51 +7425,31 @@ devlink_health_reporter_free(struct devlink_health_reporter *reporter) kfree(reporter); } -static void -devlink_health_reporter_put(struct devlink_health_reporter *reporter) -{ - if (refcount_dec_and_test(&reporter->refcount)) - devlink_health_reporter_free(reporter); -} - -static void -__devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ - list_del(&reporter->list); - devlink_health_reporter_put(reporter); -} - /** - * devlink_health_reporter_destroy - destroy devlink health reporter + * devl_health_reporter_destroy - destroy devlink health reporter * * @reporter: devlink health reporter to destroy */ void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +devl_health_reporter_destroy(struct devlink_health_reporter *reporter) { - struct mutex *lock = &reporter->devlink->reporters_lock; + devl_assert_locked(reporter->devlink); - mutex_lock(lock); - __devlink_health_reporter_destroy(reporter); - mutex_unlock(lock); + list_del(&reporter->list); + devlink_health_reporter_free(reporter); } -EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); +EXPORT_SYMBOL_GPL(devl_health_reporter_destroy); -/** - * devlink_port_health_reporter_destroy - destroy devlink port health reporter - * - * @reporter: devlink health reporter to destroy - */ void -devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter) +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) { - struct mutex *lock = &reporter->devlink_port->reporters_lock; + struct devlink *devlink = reporter->devlink; - mutex_lock(lock); - __devlink_health_reporter_destroy(reporter); - mutex_unlock(lock); + devl_lock(devlink); + devl_health_reporter_destroy(reporter); + devl_unlock(devlink); } -EXPORT_SYMBOL_GPL(devlink_port_health_reporter_destroy); +EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); static int devlink_nl_health_reporter_fill(struct sk_buff *msg, @@ -8128,7 +7680,6 @@ static struct devlink_health_reporter * devlink_health_reporter_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { - struct devlink_health_reporter *reporter; struct devlink_port *devlink_port; char *reporter_name; @@ -8137,21 +7688,12 @@ devlink_health_reporter_get_from_attrs(struct devlink *devlink, reporter_name = nla_data(attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); devlink_port = devlink_port_get_from_attrs(devlink, attrs); - if (IS_ERR(devlink_port)) { - mutex_lock(&devlink->reporters_lock); - reporter = devlink_health_reporter_find_by_name(devlink, reporter_name); - if (reporter) - refcount_inc(&reporter->refcount); - mutex_unlock(&devlink->reporters_lock); - } else { - mutex_lock(&devlink_port->reporters_lock); - reporter = devlink_port_health_reporter_find_by_name(devlink_port, reporter_name); - if (reporter) - refcount_inc(&reporter->refcount); - mutex_unlock(&devlink_port->reporters_lock); - } - - return reporter; + if (IS_ERR(devlink_port)) + return devlink_health_reporter_find_by_name(devlink, + reporter_name); + else + return devlink_port_health_reporter_find_by_name(devlink_port, + reporter_name); } static struct devlink_health_reporter * @@ -8169,9 +7711,10 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb) struct nlattr **attrs = info->attrs; struct devlink *devlink; - devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); + devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs); if (IS_ERR(devlink)) return NULL; + devl_unlock(devlink); reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); devlink_put(devlink); @@ -8209,10 +7752,8 @@ static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOMEM; - goto out; - } + if (!msg) + return -ENOMEM; err = devlink_nl_health_reporter_fill(msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, @@ -8220,89 +7761,72 @@ static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, 0); if (err) { nlmsg_free(msg); - goto out; + return err; } - err = genlmsg_reply(msg, info); -out: - devlink_health_reporter_put(reporter); - return err; + return genlmsg_reply(msg, info); } static int -devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +devlink_nl_cmd_health_reporter_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_health_reporter *reporter; - unsigned long index, port_index; struct devlink_port *port; - struct devlink *devlink; - int start = cb->args[0]; + unsigned long port_index; int idx = 0; int err; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - mutex_lock(&devlink->reporters_lock); - list_for_each_entry(reporter, &devlink->reporter_list, - list) { - if (idx < start) { + list_for_each_entry(reporter, &devlink->reporter_list, list) { + if (idx < state->idx) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill(msg, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + state->idx = idx; + return err; + } + idx++; + } + xa_for_each(&devlink->ports, port_index, port) { + list_for_each_entry(reporter, &port->reporter_list, list) { + if (idx < state->idx) { idx++; continue; } - err = devlink_nl_health_reporter_fill( - msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI); + err = devlink_nl_health_reporter_fill(msg, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); if (err) { - mutex_unlock(&devlink->reporters_lock); - devlink_put(devlink); - goto out; + state->idx = idx; + return err; } idx++; } - mutex_unlock(&devlink->reporters_lock); - devlink_put(devlink); - } - - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - xa_for_each(&devlink->ports, port_index, port) { - mutex_lock(&port->reporters_lock); - list_for_each_entry(reporter, &port->reporter_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_health_reporter_fill( - msg, reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { - mutex_unlock(&port->reporters_lock); - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } - idx++; - } - mutex_unlock(&port->reporters_lock); - } - devl_unlock(devlink); - devlink_put(devlink); } -out: - cb->args[0] = idx; - return msg->len; + + return 0; } +const struct devlink_gen_cmd devl_gen_health_reporter = { + .dump_one = devlink_nl_cmd_health_reporter_get_dump_one, +}; + static int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; - int err; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) @@ -8310,15 +7834,12 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, if (!reporter->ops->recover && (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || - info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) { - err = -EOPNOTSUPP; - goto out; - } + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) + return -EOPNOTSUPP; + if (!reporter->ops->dump && - info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) { - err = -EOPNOTSUPP; - goto out; - } + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) + return -EOPNOTSUPP; if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) reporter->graceful_period = @@ -8332,11 +7853,7 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, reporter->auto_dump = nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]); - devlink_health_reporter_put(reporter); return 0; -out: - devlink_health_reporter_put(reporter); - return err; } static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, @@ -8344,16 +7861,12 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; - int err; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; - err = devlink_health_reporter_recover(reporter, NULL, info->extack); - - devlink_health_reporter_put(reporter); - return err; + return devlink_health_reporter_recover(reporter, NULL, info->extack); } static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, @@ -8368,62 +7881,52 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (!reporter) return -EINVAL; - if (!reporter->ops->diagnose) { - devlink_health_reporter_put(reporter); + if (!reporter->ops->diagnose) return -EOPNOTSUPP; - } fmsg = devlink_fmsg_alloc(); - if (!fmsg) { - devlink_health_reporter_put(reporter); + if (!fmsg) return -ENOMEM; - } err = devlink_fmsg_obj_nest_start(fmsg); if (err) - goto out; + return err; err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) - goto out; + return err; err = devlink_fmsg_obj_nest_end(fmsg); if (err) - goto out; - - err = devlink_fmsg_snd(fmsg, info, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); + return err; -out: - devlink_fmsg_free(fmsg); - devlink_health_reporter_put(reporter); - return err; + return devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); } static int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_health_reporter *reporter; - u64 start = cb->args[0]; int err; reporter = devlink_health_reporter_get_from_cb(cb); if (!reporter) return -EINVAL; - if (!reporter->ops->dump) { - err = -EOPNOTSUPP; - goto out; - } + if (!reporter->ops->dump) + return -EOPNOTSUPP; + mutex_lock(&reporter->dump_lock); - if (!start) { + if (!state->idx) { err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) goto unlock; - cb->args[1] = reporter->dump_ts; + state->dump_ts = reporter->dump_ts; } - if (!reporter->dump_fmsg || cb->args[1] != reporter->dump_ts) { + if (!reporter->dump_fmsg || state->dump_ts != reporter->dump_ts) { NL_SET_ERR_MSG_MOD(cb->extack, "Dump trampled, please retry"); err = -EAGAIN; goto unlock; @@ -8433,8 +7936,6 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET); unlock: mutex_unlock(&reporter->dump_lock); -out: - devlink_health_reporter_put(reporter); return err; } @@ -8449,15 +7950,12 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, if (!reporter) return -EINVAL; - if (!reporter->ops->dump) { - devlink_health_reporter_put(reporter); + if (!reporter->ops->dump) return -EOPNOTSUPP; - } mutex_lock(&reporter->dump_lock); devlink_health_dump_clear(reporter); mutex_unlock(&reporter->dump_lock); - devlink_health_reporter_put(reporter); return 0; } @@ -8466,21 +7964,15 @@ static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; - int err; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; - if (!reporter->ops->test) { - devlink_health_reporter_put(reporter); + if (!reporter->ops->test) return -EOPNOTSUPP; - } - - err = reporter->ops->test(reporter, info->extack); - devlink_health_reporter_put(reporter); - return err; + return reporter->ops->test(reporter, info->extack); } struct devlink_stats { @@ -8814,43 +8306,39 @@ err_trap_fill: return err; } -static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) { + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_item *trap_item; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; int idx = 0; - int err; + int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(trap_item, &devlink->trap_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_trap_fill(msg, devlink, trap_item, - DEVLINK_CMD_TRAP_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (idx < state->idx) { idx++; + continue; + } + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); - devlink_put(devlink); + idx++; } -out: - cb->args[0] = idx; - return msg->len; + + return err; } +const struct devlink_gen_cmd devl_gen_trap = { + .dump_one = devlink_nl_cmd_trap_get_dump_one, +}; + static int __devlink_trap_action_set(struct devlink *devlink, struct devlink_trap_item *trap_item, enum devlink_trap_action trap_action, @@ -9029,46 +8517,41 @@ err_trap_group_fill: return err; } -static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_trap_group_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { - enum devlink_command cmd = DEVLINK_CMD_TRAP_GROUP_NEW; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_group_item *group_item; - u32 portid = NETLINK_CB(cb->skb).portid; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; int idx = 0; - int err; + int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(group_item, &devlink->trap_group_list, - list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_trap_group_fill(msg, devlink, - group_item, cmd, - portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + + list_for_each_entry(group_item, &devlink->trap_group_list, list) { + if (idx < state->idx) { idx++; + continue; } - devl_unlock(devlink); - devlink_put(devlink); + err = devlink_nl_trap_group_fill(msg, devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + state->idx = idx; + break; + } + idx++; } -out: - cb->args[0] = idx; - return msg->len; + + return err; } +const struct devlink_gen_cmd devl_gen_trap_group = { + .dump_one = devlink_nl_cmd_trap_group_get_dump_one, +}; + static int __devlink_trap_group_action_set(struct devlink *devlink, struct devlink_trap_group_item *group_item, @@ -9144,6 +8627,7 @@ static int devlink_trap_group_set(struct devlink *devlink, struct netlink_ext_ack *extack = info->extack; const struct devlink_trap_policer *policer; struct nlattr **attrs = info->attrs; + u32 policer_id; int err; if (!attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) @@ -9152,17 +8636,11 @@ static int devlink_trap_group_set(struct devlink *devlink, if (!devlink->ops->trap_group_set) return -EOPNOTSUPP; - policer_item = group_item->policer_item; - if (attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) { - u32 policer_id; - - policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); - policer_item = devlink_trap_policer_item_lookup(devlink, - policer_id); - if (policer_id && !policer_item) { - NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); - return -ENOENT; - } + policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); + policer_item = devlink_trap_policer_item_lookup(devlink, policer_id); + if (policer_id && !policer_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap policer"); + return -ENOENT; } policer = policer_item ? policer_item->policer : NULL; @@ -9333,46 +8811,40 @@ err_trap_policer_fill: return err; } -static int devlink_nl_cmd_trap_policer_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +static int +devlink_nl_cmd_trap_policer_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) { - enum devlink_command cmd = DEVLINK_CMD_TRAP_POLICER_NEW; + struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_policer_item *policer_item; - u32 portid = NETLINK_CB(cb->skb).portid; - struct devlink *devlink; - int start = cb->args[0]; - unsigned long index; int idx = 0; - int err; + int err = 0; - devlinks_xa_for_each_registered_get(sock_net(msg->sk), index, devlink) { - devl_lock(devlink); - list_for_each_entry(policer_item, &devlink->trap_policer_list, - list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_trap_policer_fill(msg, devlink, - policer_item, cmd, - portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); - if (err) { - devl_unlock(devlink); - devlink_put(devlink); - goto out; - } + list_for_each_entry(policer_item, &devlink->trap_policer_list, list) { + if (idx < state->idx) { idx++; + continue; + } + err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + state->idx = idx; + break; } - devl_unlock(devlink); - devlink_put(devlink); + idx++; } -out: - cb->args[0] = idx; - return msg->len; + + return err; } +const struct devlink_gen_cmd devl_gen_trap_policer = { + .dump_one = devlink_nl_cmd_trap_policer_get_dump_one, +}; + static int devlink_trap_policer_set(struct devlink *devlink, struct devlink_trap_policer_item *policer_item, @@ -9445,88 +8917,19 @@ static int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, return devlink_trap_policer_set(devlink, policer_item, info); } -static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { - [DEVLINK_ATTR_UNSPEC] = { .strict_start_type = - DEVLINK_ATTR_TRAP_POLICER_ID }, - [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, - DEVLINK_PORT_TYPE_IB), - [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, - DEVLINK_ESWITCH_MODE_SWITCHDEV), - [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, - [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, - [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, - [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, - [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, - [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = - NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), - [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, - [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_ACTION_MAX), - [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), - [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, - [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG }, -}; - -static const struct genl_small_ops devlink_nl_ops[] = { +const struct genl_small_ops devlink_nl_ops[56] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_get_doit, - .dumpit = devlink_nl_cmd_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PORT_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_port_get_doit, - .dumpit = devlink_nl_cmd_port_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, @@ -9540,7 +8943,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_RATE_GET, .doit = devlink_nl_cmd_rate_get_doit, - .dumpit = devlink_nl_cmd_rate_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, /* can be retrieved by unprivileged users */ }, @@ -9588,7 +8991,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_LINECARD_GET, .doit = devlink_nl_cmd_linecard_get_doit, - .dumpit = devlink_nl_cmd_linecard_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD, /* can be retrieved by unprivileged users */ }, @@ -9602,14 +9005,14 @@ static const struct genl_small_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_get_doit, - .dumpit = devlink_nl_cmd_sb_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_POOL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_pool_get_doit, - .dumpit = devlink_nl_cmd_sb_pool_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { @@ -9622,7 +9025,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_port_pool_get_doit, - .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, @@ -9637,7 +9040,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, - .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, @@ -9718,7 +9121,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_PARAM_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_param_get_doit, - .dumpit = devlink_nl_cmd_param_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { @@ -9746,7 +9149,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_REGION_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_region_get_doit, - .dumpit = devlink_nl_cmd_region_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .flags = GENL_ADMIN_PERM, }, { @@ -9772,14 +9175,14 @@ static const struct genl_small_ops devlink_nl_ops[] = { .cmd = DEVLINK_CMD_INFO_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_info_get_doit, - .dumpit = devlink_nl_cmd_info_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_get_doit, - .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, /* can be retrieved by unprivileged users */ }, @@ -9834,7 +9237,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_TRAP_GET, .doit = devlink_nl_cmd_trap_get_doit, - .dumpit = devlink_nl_cmd_trap_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { @@ -9845,7 +9248,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_TRAP_GROUP_GET, .doit = devlink_nl_cmd_trap_group_get_doit, - .dumpit = devlink_nl_cmd_trap_group_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { @@ -9856,7 +9259,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_TRAP_POLICER_GET, .doit = devlink_nl_cmd_trap_policer_get_doit, - .dumpit = devlink_nl_cmd_trap_policer_get_dumpit, + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { @@ -9867,7 +9270,7 @@ static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_SELFTESTS_GET, .doit = devlink_nl_cmd_selftests_get_doit, - .dumpit = devlink_nl_cmd_selftests_get_dumpit + .dumpit = devlink_nl_instance_iter_dump, /* can be retrieved by unprivileged users */ }, { @@ -9875,26 +9278,10 @@ static const struct genl_small_ops devlink_nl_ops[] = { .doit = devlink_nl_cmd_selftests_run, .flags = GENL_ADMIN_PERM, }, + /* -- No new ops here! Use split ops going forward! -- */ }; -static struct genl_family devlink_nl_family __ro_after_init = { - .name = DEVLINK_GENL_NAME, - .version = DEVLINK_GENL_VERSION, - .maxattr = DEVLINK_ATTR_MAX, - .policy = devlink_nl_policy, - .netnsok = true, - .parallel_ops = true, - .pre_doit = devlink_nl_pre_doit, - .post_doit = devlink_nl_post_doit, - .module = THIS_MODULE, - .small_ops = devlink_nl_ops, - .n_small_ops = ARRAY_SIZE(devlink_nl_ops), - .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, - .mcgrps = devlink_nl_mcgrps, - .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), -}; - -static bool devlink_reload_actions_valid(const struct devlink_ops *ops) +bool devlink_reload_actions_valid(const struct devlink_ops *ops) { const struct devlink_reload_combination *comb; int i; @@ -9923,100 +9310,6 @@ static bool devlink_reload_actions_valid(const struct devlink_ops *ops) return true; } -/** - * devlink_set_features - Set devlink supported features - * - * @devlink: devlink - * @features: devlink support features - * - * This interface allows us to set reload ops separatelly from - * the devlink_alloc. - */ -void devlink_set_features(struct devlink *devlink, u64 features) -{ - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - WARN_ON(features & DEVLINK_F_RELOAD && - !devlink_reload_supported(devlink->ops)); - devlink->features = features; -} -EXPORT_SYMBOL_GPL(devlink_set_features); - -static int devlink_netdevice_event(struct notifier_block *nb, - unsigned long event, void *ptr); - -/** - * devlink_alloc_ns - Allocate new devlink instance resources - * in specific namespace - * - * @ops: ops - * @priv_size: size of user private data - * @net: net namespace - * @dev: parent device - * - * Allocate new devlink instance resources, including devlink index - * and name. - */ -struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, - size_t priv_size, struct net *net, - struct device *dev) -{ - struct devlink *devlink; - static u32 last_id; - int ret; - - WARN_ON(!ops || !dev); - if (!devlink_reload_actions_valid(ops)) - return NULL; - - devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); - if (!devlink) - return NULL; - - ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, - &last_id, GFP_KERNEL); - if (ret < 0) - goto err_xa_alloc; - - devlink->netdevice_nb.notifier_call = devlink_netdevice_event; - ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); - if (ret) - goto err_register_netdevice_notifier; - - devlink->dev = dev; - devlink->ops = ops; - xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); - xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); - write_pnet(&devlink->_net, net); - INIT_LIST_HEAD(&devlink->rate_list); - INIT_LIST_HEAD(&devlink->linecard_list); - INIT_LIST_HEAD(&devlink->sb_list); - INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); - INIT_LIST_HEAD(&devlink->resource_list); - INIT_LIST_HEAD(&devlink->param_list); - INIT_LIST_HEAD(&devlink->region_list); - INIT_LIST_HEAD(&devlink->reporter_list); - INIT_LIST_HEAD(&devlink->trap_list); - INIT_LIST_HEAD(&devlink->trap_group_list); - INIT_LIST_HEAD(&devlink->trap_policer_list); - lockdep_register_key(&devlink->lock_key); - mutex_init(&devlink->lock); - lockdep_set_class(&devlink->lock, &devlink->lock_key); - mutex_init(&devlink->reporters_lock); - mutex_init(&devlink->linecards_lock); - refcount_set(&devlink->refcount, 1); - init_completion(&devlink->comp); - - return devlink; - -err_register_netdevice_notifier: - xa_erase(&devlinks, devlink->index); -err_xa_alloc: - kfree(devlink); - return NULL; -} -EXPORT_SYMBOL_GPL(devlink_alloc_ns); - static void devlink_trap_policer_notify(struct devlink *devlink, const struct devlink_trap_policer_item *policer_item, @@ -10029,7 +9322,7 @@ static void devlink_trap_notify(struct devlink *devlink, const struct devlink_trap_item *trap_item, enum devlink_command cmd); -static void devlink_notify_register(struct devlink *devlink) +void devlink_notify_register(struct devlink *devlink) { struct devlink_trap_policer_item *policer_item; struct devlink_trap_group_item *group_item; @@ -10070,7 +9363,7 @@ static void devlink_notify_register(struct devlink *devlink) DEVLINK_CMD_PARAM_NEW); } -static void devlink_notify_unregister(struct devlink *devlink) +void devlink_notify_unregister(struct devlink *devlink) { struct devlink_trap_policer_item *policer_item; struct devlink_trap_group_item *group_item; @@ -10107,79 +9400,6 @@ static void devlink_notify_unregister(struct devlink *devlink) devlink_notify(devlink, DEVLINK_CMD_DEL); } -/** - * devlink_register - Register devlink instance - * - * @devlink: devlink - */ -void devlink_register(struct devlink *devlink) -{ - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - /* Make sure that we are in .probe() routine */ - - xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); - devlink_notify_register(devlink); -} -EXPORT_SYMBOL_GPL(devlink_register); - -/** - * devlink_unregister - Unregister devlink instance - * - * @devlink: devlink - */ -void devlink_unregister(struct devlink *devlink) -{ - ASSERT_DEVLINK_REGISTERED(devlink); - /* Make sure that we are in .remove() routine */ - - xa_set_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING); - devlink_put(devlink); - wait_for_completion(&devlink->comp); - - devlink_notify_unregister(devlink); - xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); - xa_clear_mark(&devlinks, devlink->index, DEVLINK_UNREGISTERING); -} -EXPORT_SYMBOL_GPL(devlink_unregister); - -/** - * devlink_free - Free devlink instance resources - * - * @devlink: devlink - */ -void devlink_free(struct devlink *devlink) -{ - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - - mutex_destroy(&devlink->linecards_lock); - mutex_destroy(&devlink->reporters_lock); - mutex_destroy(&devlink->lock); - lockdep_unregister_key(&devlink->lock_key); - WARN_ON(!list_empty(&devlink->trap_policer_list)); - WARN_ON(!list_empty(&devlink->trap_group_list)); - WARN_ON(!list_empty(&devlink->trap_list)); - WARN_ON(!list_empty(&devlink->reporter_list)); - WARN_ON(!list_empty(&devlink->region_list)); - WARN_ON(!list_empty(&devlink->param_list)); - WARN_ON(!list_empty(&devlink->resource_list)); - WARN_ON(!list_empty(&devlink->dpipe_table_list)); - WARN_ON(!list_empty(&devlink->sb_list)); - WARN_ON(!list_empty(&devlink->rate_list)); - WARN_ON(!list_empty(&devlink->linecard_list)); - WARN_ON(!xa_empty(&devlink->ports)); - - xa_destroy(&devlink->snapshot_ids); - xa_destroy(&devlink->ports); - - WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), - &devlink->netdevice_nb)); - - xa_erase(&devlinks, devlink->index); - - kfree(devlink); -} -EXPORT_SYMBOL_GPL(devlink_free); - static void devlink_port_type_warn(struct work_struct *work) { WARN(true, "Type was not set for devlink port."); @@ -10279,12 +9499,9 @@ int devl_port_register(struct devlink *devlink, devlink_port->index = port_index; spin_lock_init(&devlink_port->type_lock); INIT_LIST_HEAD(&devlink_port->reporter_list); - mutex_init(&devlink_port->reporters_lock); err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL); - if (err) { - mutex_destroy(&devlink_port->reporters_lock); + if (err) return err; - } INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); @@ -10335,7 +9552,6 @@ void devl_port_unregister(struct devlink_port *devlink_port) devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); xa_erase(&devlink_port->devlink->ports, devlink_port->index); WARN_ON(!list_empty(&devlink_port->reporter_list)); - mutex_destroy(&devlink_port->reporters_lock); devlink_port->registered = false; } EXPORT_SYMBOL_GPL(devl_port_unregister); @@ -10480,8 +9696,8 @@ void devlink_port_type_clear(struct devlink_port *devlink_port) } EXPORT_SYMBOL_GPL(devlink_port_type_clear); -static int devlink_netdevice_event(struct notifier_block *nb, - unsigned long event, void *ptr) +int devlink_port_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct devlink_port *devlink_port = netdev->devlink_port; @@ -10911,7 +10127,7 @@ static void devlink_linecard_types_fini(struct devlink_linecard *linecard) } /** - * devlink_linecard_create - Create devlink linecard + * devl_linecard_create - Create devlink linecard * * @devlink: devlink * @linecard_index: driver-specific numerical identifier of the linecard @@ -10924,8 +10140,8 @@ static void devlink_linecard_types_fini(struct devlink_linecard *linecard) * Return: Line card structure or an ERR_PTR() encoded error code. */ struct devlink_linecard * -devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, - const struct devlink_linecard_ops *ops, void *priv) +devl_linecard_create(struct devlink *devlink, unsigned int linecard_index, + const struct devlink_linecard_ops *ops, void *priv) { struct devlink_linecard *linecard; int err; @@ -10934,17 +10150,12 @@ devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, !ops->types_count || !ops->types_get)) return ERR_PTR(-EINVAL); - mutex_lock(&devlink->linecards_lock); - if (devlink_linecard_index_exists(devlink, linecard_index)) { - mutex_unlock(&devlink->linecards_lock); + if (devlink_linecard_index_exists(devlink, linecard_index)) return ERR_PTR(-EEXIST); - } linecard = kzalloc(sizeof(*linecard), GFP_KERNEL); - if (!linecard) { - mutex_unlock(&devlink->linecards_lock); + if (!linecard) return ERR_PTR(-ENOMEM); - } linecard->devlink = devlink; linecard->index = linecard_index; @@ -10957,35 +10168,29 @@ devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, if (err) { mutex_destroy(&linecard->state_lock); kfree(linecard); - mutex_unlock(&devlink->linecards_lock); return ERR_PTR(err); } list_add_tail(&linecard->list, &devlink->linecard_list); - refcount_set(&linecard->refcount, 1); - mutex_unlock(&devlink->linecards_lock); devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); return linecard; } -EXPORT_SYMBOL_GPL(devlink_linecard_create); +EXPORT_SYMBOL_GPL(devl_linecard_create); /** - * devlink_linecard_destroy - Destroy devlink linecard + * devl_linecard_destroy - Destroy devlink linecard * * @linecard: devlink linecard */ -void devlink_linecard_destroy(struct devlink_linecard *linecard) +void devl_linecard_destroy(struct devlink_linecard *linecard) { - struct devlink *devlink = linecard->devlink; - devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); - mutex_lock(&devlink->linecards_lock); list_del(&linecard->list); devlink_linecard_types_fini(linecard); - mutex_unlock(&devlink->linecards_lock); - devlink_linecard_put(linecard); + mutex_destroy(&linecard->state_lock); + kfree(linecard); } -EXPORT_SYMBOL_GPL(devlink_linecard_destroy); +EXPORT_SYMBOL_GPL(devl_linecard_destroy); /** * devlink_linecard_provision_set - Set provisioning on linecard @@ -11604,8 +10809,6 @@ int devlink_params_register(struct devlink *devlink, const struct devlink_param *param = params; int i, err; - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - for (i = 0; i < params_count; i++, param++) { err = devlink_param_register(devlink, param); if (err) @@ -11636,8 +10839,6 @@ void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *param = params; int i; - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - for (i = 0; i < params_count; i++, param++) devlink_param_unregister(devlink, param); } @@ -11657,8 +10858,6 @@ int devlink_param_register(struct devlink *devlink, { struct devlink_param_item *param_item; - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - WARN_ON(devlink_param_verify(param)); WARN_ON(devlink_param_find_by_name(&devlink->param_list, param->name)); @@ -11674,6 +10873,7 @@ int devlink_param_register(struct devlink *devlink, param_item->param = param; list_add_tail(¶m_item->list, &devlink->param_list); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); return 0; } EXPORT_SYMBOL_GPL(devlink_param_register); @@ -11688,11 +10888,10 @@ void devlink_param_unregister(struct devlink *devlink, { struct devlink_param_item *param_item; - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - param_item = devlink_param_find_by_name(&devlink->param_list, param->name); WARN_ON(!param_item); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_DEL); list_del(¶m_item->list); kfree(param_item); } @@ -11752,8 +10951,6 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, { struct devlink_param_item *param_item; - ASSERT_DEVLINK_NOT_REGISTERED(devlink); - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); if (!param_item) return -EINVAL; @@ -11767,6 +10964,8 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, else param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; + + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); return 0; } EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); @@ -12921,7 +12120,8 @@ void devlink_compat_running_version(struct devlink *devlink, return; devl_lock(devlink); - __devlink_compat_running_version(devlink, buf, len); + if (devl_is_registered(devlink)) + __devlink_compat_running_version(devlink, buf, len); devl_unlock(devlink); } @@ -12930,20 +12130,28 @@ int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) struct devlink_flash_update_params params = {}; int ret; - if (!devlink->ops->flash_update) - return -EOPNOTSUPP; + devl_lock(devlink); + if (!devl_is_registered(devlink)) { + ret = -ENODEV; + goto out_unlock; + } + + if (!devlink->ops->flash_update) { + ret = -EOPNOTSUPP; + goto out_unlock; + } ret = request_firmware(¶ms.fw, file_name, devlink->dev); if (ret) - return ret; + goto out_unlock; - devl_lock(devlink); devlink_flash_update_begin_notify(devlink); ret = devlink->ops->flash_update(devlink, ¶ms, NULL); devlink_flash_update_end_notify(devlink); - devl_unlock(devlink); release_firmware(params.fw); +out_unlock: + devl_unlock(devlink); return ret; } @@ -12983,47 +12191,3 @@ int devlink_compat_switch_id_get(struct net_device *dev, return 0; } - -static void __net_exit devlink_pernet_pre_exit(struct net *net) -{ - struct devlink *devlink; - u32 actions_performed; - unsigned long index; - int err; - - /* In case network namespace is getting destroyed, reload - * all devlink instances from this namespace into init_net. - */ - devlinks_xa_for_each_registered_get(net, index, devlink) { - WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); - mutex_lock(&devlink->lock); - err = devlink_reload(devlink, &init_net, - DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_LIMIT_UNSPEC, - &actions_performed, NULL); - mutex_unlock(&devlink->lock); - if (err && err != -EOPNOTSUPP) - pr_warn("Failed to reload devlink instance into init_net\n"); - devlink_put(devlink); - } -} - -static struct pernet_operations devlink_pernet_ops __net_initdata = { - .pre_exit = devlink_pernet_pre_exit, -}; - -static int __init devlink_init(void) -{ - int err; - - err = genl_register_family(&devlink_nl_family); - if (err) - goto out; - err = register_pernet_subsys(&devlink_pernet_ops); - -out: - WARN_ON(err); - return err; -} - -subsys_initcall(devlink_init); diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c new file mode 100644 index 000000000000..3f44633af01c --- /dev/null +++ b/net/devlink/netlink.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + */ + +#include <net/genetlink.h> +#include <net/sock.h> + +#include "devl_internal.h" + +static const struct genl_multicast_group devlink_nl_mcgrps[] = { + [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, +}; + +static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_UNSPEC] = { .strict_start_type = + DEVLINK_ATTR_TRAP_POLICER_ID }, + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, + DEVLINK_PORT_TYPE_IB), + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, + [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, + DEVLINK_ESWITCH_MODE_SWITCHDEV), + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, + [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, + [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, + [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, + [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = + NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, + [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, + [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_ACTION_MAX), + [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), + [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG }, +}; + +struct devlink * +devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs) +{ + struct devlink *devlink; + unsigned long index; + char *busname; + char *devname; + + if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) + return ERR_PTR(-EINVAL); + + busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); + devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); + + devlinks_xa_for_each_registered_get(net, index, devlink) { + devl_lock(devlink); + if (devl_is_registered(devlink) && + strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0) + return devlink; + devl_unlock(devlink); + devlink_put(devlink); + } + + return ERR_PTR(-ENODEV); +} + +static int devlink_nl_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + struct devlink_linecard *linecard; + struct devlink_port *devlink_port; + struct devlink *devlink; + int err; + + devlink = devlink_get_from_attrs_lock(genl_info_net(info), info->attrs); + if (IS_ERR(devlink)) + return PTR_ERR(devlink); + + info->user_ptr[0] = devlink; + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { + devlink_port = devlink_port_get_from_info(devlink, info); + if (IS_ERR(devlink_port)) { + err = PTR_ERR(devlink_port); + goto unlock; + } + info->user_ptr[1] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { + devlink_port = devlink_port_get_from_info(devlink, info); + if (!IS_ERR(devlink_port)) + info->user_ptr[1] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { + struct devlink_rate *devlink_rate; + + devlink_rate = devlink_rate_get_from_info(devlink, info); + if (IS_ERR(devlink_rate)) { + err = PTR_ERR(devlink_rate); + goto unlock; + } + info->user_ptr[1] = devlink_rate; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { + struct devlink_rate *rate_node; + + rate_node = devlink_rate_node_get_from_info(devlink, info); + if (IS_ERR(rate_node)) { + err = PTR_ERR(rate_node); + goto unlock; + } + info->user_ptr[1] = rate_node; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) { + linecard = devlink_linecard_get_from_info(devlink, info); + if (IS_ERR(linecard)) { + err = PTR_ERR(linecard); + goto unlock; + } + info->user_ptr[1] = linecard; + } + return 0; + +unlock: + devl_unlock(devlink); + devlink_put(devlink); + return err; +} + +static void devlink_nl_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink; + + devlink = info->user_ptr[0]; + devl_unlock(devlink); + devlink_put(devlink); +} + +static const struct devlink_gen_cmd *devl_gen_cmds[] = { + [DEVLINK_CMD_GET] = &devl_gen_inst, + [DEVLINK_CMD_PORT_GET] = &devl_gen_port, + [DEVLINK_CMD_SB_GET] = &devl_gen_sb, + [DEVLINK_CMD_SB_POOL_GET] = &devl_gen_sb_pool, + [DEVLINK_CMD_SB_PORT_POOL_GET] = &devl_gen_sb_port_pool, + [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = &devl_gen_sb_tc_pool_bind, + [DEVLINK_CMD_PARAM_GET] = &devl_gen_param, + [DEVLINK_CMD_REGION_GET] = &devl_gen_region, + [DEVLINK_CMD_INFO_GET] = &devl_gen_info, + [DEVLINK_CMD_HEALTH_REPORTER_GET] = &devl_gen_health_reporter, + [DEVLINK_CMD_RATE_GET] = &devl_gen_rate_get, + [DEVLINK_CMD_TRAP_GET] = &devl_gen_trap, + [DEVLINK_CMD_TRAP_GROUP_GET] = &devl_gen_trap_group, + [DEVLINK_CMD_TRAP_POLICER_GET] = &devl_gen_trap_policer, + [DEVLINK_CMD_LINECARD_GET] = &devl_gen_linecard, + [DEVLINK_CMD_SELFTESTS_GET] = &devl_gen_selftests, +}; + +int devlink_nl_instance_iter_dump(struct sk_buff *msg, + struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct devlink_nl_dump_state *state = devlink_dump_state(cb); + const struct devlink_gen_cmd *cmd; + struct devlink *devlink; + int err = 0; + + cmd = devl_gen_cmds[info->op.cmd]; + + while ((devlink = devlinks_xa_find_get(sock_net(msg->sk), + &state->instance))) { + devl_lock(devlink); + + if (devl_is_registered(devlink)) + err = cmd->dump_one(msg, devlink, cb); + else + err = 0; + + devl_unlock(devlink); + devlink_put(devlink); + + if (err) + break; + + state->instance++; + + /* restart sub-object walk for the next instance */ + state->idx = 0; + } + + if (err != -EMSGSIZE) + return err; + return msg->len; +} + +struct genl_family devlink_nl_family __ro_after_init = { + .name = DEVLINK_GENL_NAME, + .version = DEVLINK_GENL_VERSION, + .maxattr = DEVLINK_ATTR_MAX, + .policy = devlink_nl_policy, + .netnsok = true, + .parallel_ops = true, + .pre_doit = devlink_nl_pre_doit, + .post_doit = devlink_nl_post_doit, + .module = THIS_MODULE, + .small_ops = devlink_nl_ops, + .n_small_ops = ARRAY_SIZE(devlink_nl_ops), + .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, + .mcgrps = devlink_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), +}; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 080e5c369f5b..694478fe07d6 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -4,8 +4,10 @@ * Copyright (c) 2017 Microchip Technology */ +#include <linux/dsa/ksz_common.h> #include <linux/etherdevice.h> #include <linux/list.h> +#include <linux/ptp_classify.h> #include <net/dsa.h> #include "tag.h" @@ -16,9 +18,71 @@ #define LAN937X_NAME "lan937x" /* Typically only one byte is used for tail tag. */ +#define KSZ_PTP_TAG_LEN 4 #define KSZ_EGRESS_TAG_LEN 1 #define KSZ_INGRESS_TAG_LEN 1 +#define KSZ_HWTS_EN 0 + +struct ksz_tagger_private { + struct ksz_tagger_data data; /* Must be first */ + unsigned long state; + struct kthread_worker *xmit_worker; +}; + +static struct ksz_tagger_private * +ksz_tagger_private(struct dsa_switch *ds) +{ + return ds->tagger_data; +} + +static void ksz_hwtstamp_set_state(struct dsa_switch *ds, bool on) +{ + struct ksz_tagger_private *priv = ksz_tagger_private(ds); + + if (on) + set_bit(KSZ_HWTS_EN, &priv->state); + else + clear_bit(KSZ_HWTS_EN, &priv->state); +} + +static void ksz_disconnect(struct dsa_switch *ds) +{ + struct ksz_tagger_private *priv = ds->tagger_data; + + kthread_destroy_worker(priv->xmit_worker); + kfree(priv); + ds->tagger_data = NULL; +} + +static int ksz_connect(struct dsa_switch *ds) +{ + struct ksz_tagger_data *tagger_data; + struct kthread_worker *xmit_worker; + struct ksz_tagger_private *priv; + int ret; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", + ds->dst->index, ds->index); + if (IS_ERR(xmit_worker)) { + ret = PTR_ERR(xmit_worker); + kfree(priv); + return ret; + } + + priv->xmit_worker = xmit_worker; + /* Export functions for switch driver use */ + tagger_data = &priv->data; + tagger_data->hwtstamp_set_state = ksz_hwtstamp_set_state; + ds->tagger_data = priv; + + return 0; +} + static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, struct net_device *dev, unsigned int port, unsigned int len) @@ -92,17 +156,20 @@ DSA_TAG_DRIVER(ksz8795_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME); /* - * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS. + * For Ingress (Host -> KSZ9477), 2/6 bytes are added before FCS. * --------------------------------------------------------------------------- - * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|tag1(1byte)| + * FCS(4bytes) * --------------------------------------------------------------------------- + * ts : time stamp (Present only if PTP is enabled in the Hardware) * tag0 : Prioritization (not used now) * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) * - * For Egress (KSZ9477 -> Host), 1 byte is added before FCS. + * For Egress (KSZ9477 -> Host), 1/5 bytes is added before FCS. * --------------------------------------------------------------------------- - * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- + * ts : time stamp (Present only if bit 7 of tag0 is set) * tag0 : zero-based value represents port * (eg, 0x00=port1, 0x02=port3, 0x06=port7) */ @@ -114,6 +181,91 @@ MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME); #define KSZ9477_TAIL_TAG_OVERRIDE BIT(9) #define KSZ9477_TAIL_TAG_LOOKUP BIT(10) +static void ksz_rcv_timestamp(struct sk_buff *skb, u8 *tag) +{ + u8 *tstamp_raw = tag - KSZ_PTP_TAG_LEN; + ktime_t tstamp; + + tstamp = ksz_decode_tstamp(get_unaligned_be32(tstamp_raw)); + KSZ_SKB_CB(skb)->tstamp = tstamp; +} + +/* Time stamp tag *needs* to be inserted if PTP is enabled in hardware. + * Regardless of Whether it is a PTP frame or not. + */ +static void ksz_xmit_timestamp(struct dsa_port *dp, struct sk_buff *skb) +{ + struct ksz_tagger_private *priv; + struct ptp_header *ptp_hdr; + unsigned int ptp_type; + u32 tstamp_raw = 0; + s64 correction; + + priv = ksz_tagger_private(dp->ds); + + if (!test_bit(KSZ_HWTS_EN, &priv->state)) + return; + + if (!KSZ_SKB_CB(skb)->update_correction) + goto output_tag; + + ptp_type = KSZ_SKB_CB(skb)->ptp_type; + + ptp_hdr = ptp_parse_header(skb, ptp_type); + if (!ptp_hdr) + goto output_tag; + + correction = (s64)get_unaligned_be64(&ptp_hdr->correction); + + if (correction < 0) { + struct timespec64 ts; + + ts = ns_to_timespec64(-correction >> 16); + tstamp_raw = ((ts.tv_sec & 3) << 30) | ts.tv_nsec; + + /* Set correction field to 0 and update UDP checksum */ + ptp_header_update_correction(skb, ptp_type, ptp_hdr, 0); + } + +output_tag: + put_unaligned_be32(tstamp_raw, skb_put(skb, KSZ_PTP_TAG_LEN)); +} + +/* Defer transmit if waiting for egress time stamp is required. */ +static struct sk_buff *ksz_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) +{ + struct ksz_tagger_data *tagger_data = ksz_tagger_data(dp->ds); + struct ksz_tagger_private *priv = ksz_tagger_private(dp->ds); + void (*xmit_work_fn)(struct kthread_work *work); + struct sk_buff *clone = KSZ_SKB_CB(skb)->clone; + struct ksz_deferred_xmit_work *xmit_work; + struct kthread_worker *xmit_worker; + + if (!clone) + return skb; /* no deferred xmit for this packet */ + + xmit_work_fn = tagger_data->xmit_work_fn; + xmit_worker = priv->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + kthread_init_work(&xmit_work->work, xmit_work_fn); + /* Increase refcount so the kfree_skb in dsa_slave_xmit + * won't really free the packet. + */ + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(xmit_worker, &xmit_work->work); + + return NULL; +} + static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -126,6 +278,8 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, return NULL; /* Tag encoding */ + ksz_xmit_timestamp(dp, skb); + tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -136,7 +290,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, *tag = cpu_to_be16(val); - return skb; + return ksz_defer_xmit(dp, skb); } static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) @@ -147,8 +301,10 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) unsigned int len = KSZ_EGRESS_TAG_LEN; /* Extra 4-bytes PTP timestamp */ - if (tag[0] & KSZ9477_PTP_TAG_INDICATION) - len += KSZ9477_PTP_TAG_LEN; + if (tag[0] & KSZ9477_PTP_TAG_INDICATION) { + ksz_rcv_timestamp(skb, tag); + len += KSZ_PTP_TAG_LEN; + } return ksz_common_rcv(skb, dev, port, len); } @@ -158,7 +314,9 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9477, .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, - .needed_tailroom = KSZ9477_INGRESS_TAG_LEN, + .connect = ksz_connect, + .disconnect = ksz_disconnect, + .needed_tailroom = KSZ9477_INGRESS_TAG_LEN + KSZ_PTP_TAG_LEN, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); @@ -178,6 +336,8 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, return NULL; /* Tag encoding */ + ksz_xmit_timestamp(dp, skb); + tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(skb); @@ -186,7 +346,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, if (is_link_local_ether_addr(addr)) *tag |= KSZ9893_TAIL_TAG_OVERRIDE; - return skb; + return ksz_defer_xmit(dp, skb); } static const struct dsa_device_ops ksz9893_netdev_ops = { @@ -194,23 +354,28 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9893, .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, - .needed_tailroom = KSZ_INGRESS_TAG_LEN, + .connect = ksz_connect, + .disconnect = ksz_disconnect, + .needed_tailroom = KSZ_INGRESS_TAG_LEN + KSZ_PTP_TAG_LEN, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893, KSZ9893_NAME); -/* For xmit, 2 bytes are added before FCS. +/* For xmit, 2/6 bytes are added before FCS. * --------------------------------------------------------------------------- - * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|tag1(1byte)| + * FCS(4bytes) * --------------------------------------------------------------------------- + * ts : time stamp (Present only if PTP is enabled in the Hardware) * tag0 : represents tag override, lookup and valid * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x80=port8) * - * For rcv, 1 byte is added before FCS. + * For rcv, 1/5 bytes is added before FCS. * --------------------------------------------------------------------------- - * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- + * ts : time stamp (Present only if bit 7 of tag0 is set) * tag0 : zero-based value represents port * (eg, 0x00=port1, 0x02=port3, 0x07=port8) */ @@ -232,6 +397,8 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) return NULL; + ksz_xmit_timestamp(dp, skb); + tag = skb_put(skb, LAN937X_EGRESS_TAG_LEN); val = BIT(dp->index); @@ -244,7 +411,7 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb, put_unaligned_be16(val, tag); - return skb; + return ksz_defer_xmit(dp, skb); } static const struct dsa_device_ops lan937x_netdev_ops = { @@ -252,7 +419,9 @@ static const struct dsa_device_ops lan937x_netdev_ops = { .proto = DSA_TAG_PROTO_LAN937X, .xmit = lan937x_xmit, .rcv = ksz9477_rcv, - .needed_tailroom = LAN937X_EGRESS_TAG_LEN, + .connect = ksz_connect, + .disconnect = ksz_disconnect, + .needed_tailroom = LAN937X_EGRESS_TAG_LEN + KSZ_PTP_TAG_LEN, }; DSA_TAG_DRIVER(lan937x_netdev_ops); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 228f13df2e18..563864c1bf5a 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o \ - pse-pd.o + pse-pd.o plca.o diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 487bdf345541..e405b47f7eed 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -105,7 +105,10 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _RATE_SAMPLE_INTERVAL */ nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_TX */ - nla_total_size(sizeof(u8)); /* _USE_CQE_MODE_RX */ + nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ + nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -180,7 +183,13 @@ static int coalesce_fill_reply(struct sk_buff *skb, coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, kcoal->use_cqe_mode_tx, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, - kcoal->use_cqe_mode_rx, supported)) + kcoal->use_cqe_mode_rx, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, + kcoal->tx_aggr_max_bytes, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, + kcoal->tx_aggr_max_frames, supported) || + coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, + kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; return 0; @@ -227,6 +236,9 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, }; int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) @@ -321,6 +333,12 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX], &mod); ethnl_update_u8(&kernel_coalesce.use_cqe_mode_rx, tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX], &mod); + ethnl_update_u32(&kernel_coalesce.tx_aggr_max_bytes, + tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES], &mod); + ethnl_update_u32(&kernel_coalesce.tx_aggr_max_frames, + tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES], &mod); + ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, + tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); ret = 0; if (!mod) goto out_ops; diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6f399afc2ff2..5fb19050991e 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -208,6 +208,9 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(800000, DR8_2, Full), __DEFINE_LINK_MODE_NAME(800000, SR8, Full), __DEFINE_LINK_MODE_NAME(800000, VR8, Full), + __DEFINE_LINK_MODE_NAME(10, T1S, Full), + __DEFINE_LINK_MODE_NAME(10, T1S, Half), + __DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -244,6 +247,8 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_X 1 #define __LINK_MODE_LANES_FX 1 #define __LINK_MODE_LANES_T1L 1 +#define __LINK_MODE_LANES_T1S 1 +#define __LINK_MODE_LANES_T1S_P2MP 1 #define __LINK_MODE_LANES_VR8 8 #define __LINK_MODE_LANES_DR8_2 8 @@ -366,6 +371,9 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full), __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full), __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full), + __DEFINE_LINK_MODE_PARAMS(10, T1S, Full), + __DEFINE_LINK_MODE_PARAMS(10, T1S, Half), + __DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index aee98be6237f..9f924875bba9 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -288,6 +288,8 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, + [ETHTOOL_MSG_PLCA_GET_CFG] = ðnl_plca_cfg_request_ops, + [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -603,6 +605,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, + [ETHTOOL_MSG_PLCA_NTF] = ðnl_plca_cfg_request_ops, }; /* default notification handler */ @@ -696,6 +699,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_PLCA_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -1047,6 +1051,31 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PLCA_GET_CFG, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_plca_get_cfg_policy, + .maxattr = ARRAY_SIZE(ethnl_plca_get_cfg_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_PLCA_SET_CFG, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_plca_cfg, + .policy = ethnl_plca_set_cfg_policy, + .maxattr = ARRAY_SIZE(ethnl_plca_set_cfg_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_PLCA_GET_STATUS, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_plca_get_status_policy, + .maxattr = ARRAY_SIZE(ethnl_plca_get_status_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3753787ba233..f271266f6e28 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -347,6 +347,8 @@ extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct ethnl_request_ops ethnl_module_request_ops; extern const struct ethnl_request_ops ethnl_pse_request_ops; extern const struct ethnl_request_ops ethnl_rss_request_ops; +extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; +extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -388,6 +390,9 @@ extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MO extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; +extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; +extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; +extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); @@ -408,6 +413,7 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_set_fec(struct sk_buff *skb, struct genl_info *info); int ethnl_set_module(struct sk_buff *skb, struct genl_info *info); int ethnl_set_pse(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_plca_cfg(struct sk_buff *skb, struct genl_info *info); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c new file mode 100644 index 000000000000..be7404dc9ef2 --- /dev/null +++ b/net/ethtool/plca.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/phy.h> +#include <linux/ethtool_netlink.h> + +#include "netlink.h" +#include "common.h" + +struct plca_req_info { + struct ethnl_req_info base; +}; + +struct plca_reply_data { + struct ethnl_reply_data base; + struct phy_plca_cfg plca_cfg; + struct phy_plca_status plca_st; +}; + +// Helpers ------------------------------------------------------------------ // + +#define PLCA_REPDATA(__reply_base) \ + container_of(__reply_base, struct plca_reply_data, base) + +static void plca_update_sint(int *dst, const struct nlattr *attr, + bool *mod) +{ + if (!attr) + return; + + *dst = nla_get_u32(attr); + *mod = true; +} + +// PLCA get configuration message ------------------------------------------- // + +const struct nla_policy ethnl_plca_get_cfg_policy[] = { + [ETHTOOL_A_PLCA_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct plca_reply_data *data = PLCA_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_phy_ops *ops; + int ret; + + // check that the PHY device is available and connected + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out; + } + + // note: rtnl_lock is held already by ethnl_default_doit + ops = ethtool_phy_ops; + if (!ops || !ops->get_plca_cfg) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out; + + memset(&data->plca_cfg, 0xff, + sizeof_field(struct plca_reply_data, plca_cfg)); + + ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg); + ethnl_ops_complete(dev); + +out: + return ret; +} + +static int plca_get_cfg_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u16)) + /* _VERSION */ + nla_total_size(sizeof(u8)) + /* _ENABLED */ + nla_total_size(sizeof(u32)) + /* _NODE_CNT */ + nla_total_size(sizeof(u32)) + /* _NODE_ID */ + nla_total_size(sizeof(u32)) + /* _TO_TIMER */ + nla_total_size(sizeof(u32)) + /* _BURST_COUNT */ + nla_total_size(sizeof(u32)); /* _BURST_TIMER */ +} + +static int plca_get_cfg_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct plca_reply_data *data = PLCA_REPDATA(reply_base); + const struct phy_plca_cfg *plca = &data->plca_cfg; + + if ((plca->version >= 0 && + nla_put_u16(skb, ETHTOOL_A_PLCA_VERSION, plca->version)) || + (plca->enabled >= 0 && + nla_put_u8(skb, ETHTOOL_A_PLCA_ENABLED, !!plca->enabled)) || + (plca->node_id >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_ID, plca->node_id)) || + (plca->node_cnt >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_CNT, plca->node_cnt)) || + (plca->to_tmr >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_TO_TMR, plca->to_tmr)) || + (plca->burst_cnt >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_CNT, plca->burst_cnt)) || + (plca->burst_tmr >= 0 && + nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_TMR, plca->burst_tmr))) + return -EMSGSIZE; + + return 0; +}; + +const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { + .request_cmd = ETHTOOL_MSG_PLCA_GET_CFG, + .reply_cmd = ETHTOOL_MSG_PLCA_GET_CFG_REPLY, + .hdr_attr = ETHTOOL_A_PLCA_HEADER, + .req_info_size = sizeof(struct plca_req_info), + .reply_data_size = sizeof(struct plca_reply_data), + + .prepare_data = plca_get_cfg_prepare_data, + .reply_size = plca_get_cfg_reply_size, + .fill_reply = plca_get_cfg_fill_reply, +}; + +// PLCA set configuration message ------------------------------------------- // + +const struct nla_policy ethnl_plca_set_cfg_policy[] = { + [ETHTOOL_A_PLCA_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), + [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), + [ETHTOOL_A_PLCA_TO_TMR] = NLA_POLICY_MAX(NLA_U32, 255), + [ETHTOOL_A_PLCA_BURST_CNT] = NLA_POLICY_MAX(NLA_U32, 255), + [ETHTOOL_A_PLCA_BURST_TMR] = NLA_POLICY_MAX(NLA_U32, 255), +}; + +int ethnl_set_plca_cfg(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + const struct ethtool_phy_ops *ops; + struct phy_plca_cfg plca_cfg; + struct net_device *dev; + bool mod = false; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_PLCA_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + dev = req_info.dev; + + rtnl_lock(); + + // check that the PHY device is available and connected + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + + ops = ethtool_phy_ops; + if (!ops || !ops->set_plca_cfg) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + memset(&plca_cfg, 0xff, sizeof(plca_cfg)); + plca_update_sint(&plca_cfg.enabled, tb[ETHTOOL_A_PLCA_ENABLED], &mod); + plca_update_sint(&plca_cfg.node_id, tb[ETHTOOL_A_PLCA_NODE_ID], &mod); + plca_update_sint(&plca_cfg.node_cnt, tb[ETHTOOL_A_PLCA_NODE_CNT], &mod); + plca_update_sint(&plca_cfg.to_tmr, tb[ETHTOOL_A_PLCA_TO_TMR], &mod); + plca_update_sint(&plca_cfg.burst_cnt, tb[ETHTOOL_A_PLCA_BURST_CNT], + &mod); + plca_update_sint(&plca_cfg.burst_tmr, tb[ETHTOOL_A_PLCA_BURST_TMR], + &mod); + + ret = 0; + if (!mod) + goto out_ops; + + ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack); + if (ret < 0) + goto out_ops; + + ethtool_notify(dev, ETHTOOL_MSG_PLCA_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info); + + return ret; +} + +// PLCA get status message -------------------------------------------------- // + +const struct nla_policy ethnl_plca_get_status_policy[] = { + [ETHTOOL_A_PLCA_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct plca_reply_data *data = PLCA_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_phy_ops *ops; + int ret; + + // check that the PHY device is available and connected + if (!dev->phydev) { + ret = -EOPNOTSUPP; + goto out; + } + + // note: rtnl_lock is held already by ethnl_default_doit + ops = ethtool_phy_ops; + if (!ops || !ops->get_plca_status) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out; + + memset(&data->plca_st, 0xff, + sizeof_field(struct plca_reply_data, plca_st)); + + ret = ops->get_plca_status(dev->phydev, &data->plca_st); + ethnl_ops_complete(dev); +out: + return ret; +} + +static int plca_get_status_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u8)); /* _STATUS */ +} + +static int plca_get_status_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct plca_reply_data *data = PLCA_REPDATA(reply_base); + const u8 status = data->plca_st.pst; + + if (nla_put_u8(skb, ETHTOOL_A_PLCA_STATUS, !!status)) + return -EMSGSIZE; + + return 0; +}; + +const struct ethnl_request_ops ethnl_plca_status_request_ops = { + .request_cmd = ETHTOOL_MSG_PLCA_GET_STATUS, + .reply_cmd = ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, + .hdr_attr = ETHTOOL_A_PLCA_HEADER, + .req_info_size = sizeof(struct plca_req_info), + .reply_data_size = sizeof(struct plca_reply_data), + + .prepare_data = plca_get_status_prepare_data, + .reply_size = plca_get_status_reply_size, + .fill_reply = plca_get_status_fill_reply, +}; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index f58d73888638..7a13dd7f546b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1008,17 +1008,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, u32 index; if (port) { - head = &hinfo->bhash[inet_bhashfn(net, port, - hinfo->bhash_size)]; - tb = inet_csk(sk)->icsk_bind_hash; - spin_lock_bh(&head->lock); - if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL, NULL); - spin_unlock_bh(&head->lock); - return 0; - } - spin_unlock(&head->lock); - /* No definite answer... Walk to established hash table */ + local_bh_disable(); ret = check_established(death_row, sk, port, NULL); local_bh_enable(); return ret; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index aab384126f61..f71a7e9a7de6 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -259,20 +259,6 @@ config IP_NF_MANGLE To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_CLUSTERIP - tristate "CLUSTERIP target support" - depends on IP_NF_MANGLE - depends on NF_CONNTRACK - depends on NETFILTER_ADVANCED - select NF_CONNTRACK_MARK - select NETFILTER_FAMILY_ARP - help - The CLUSTERIP target allows you to build load-balancing clusters of - network servers without having a dedicated load-balancing - router/server/switch. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_ECN tristate "ECN target support" depends on IP_NF_MANGLE diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 93bad1184251..5a26f9de1ab9 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o # targets -obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_SYNPROXY) += ipt_SYNPROXY.o diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c deleted file mode 100644 index b3cc416ed292..000000000000 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ /dev/null @@ -1,929 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Cluster IP hashmark target - * (C) 2003-2004 by Harald Welte <laforge@netfilter.org> - * based on ideas of Fabio Olive Leite <olive@unixforge.org> - * - * Development of this code funded by SuSE Linux AG, https://www.suse.com/ - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/proc_fs.h> -#include <linux/jhash.h> -#include <linux/bitops.h> -#include <linux/skbuff.h> -#include <linux/slab.h> -#include <linux/ip.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/icmp.h> -#include <linux/if_arp.h> -#include <linux/seq_file.h> -#include <linux/refcount.h> -#include <linux/netfilter_arp.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_CLUSTERIP.h> -#include <net/netfilter/nf_conntrack.h> -#include <net/net_namespace.h> -#include <net/netns/generic.h> -#include <net/checksum.h> -#include <net/ip.h> - -#define CLUSTERIP_VERSION "0.8" - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("Xtables: CLUSTERIP target"); - -struct clusterip_config { - struct list_head list; /* list of all configs */ - refcount_t refcount; /* reference count */ - refcount_t entries; /* number of entries/rules - * referencing us */ - - __be32 clusterip; /* the IP address */ - u_int8_t clustermac[ETH_ALEN]; /* the MAC address */ - int ifindex; /* device ifindex */ - u_int16_t num_total_nodes; /* total number of nodes */ - unsigned long local_nodes; /* node number array */ - -#ifdef CONFIG_PROC_FS - struct proc_dir_entry *pde; /* proc dir entry */ -#endif - enum clusterip_hashmode hash_mode; /* which hashing mode */ - u_int32_t hash_initval; /* hash initialization */ - struct rcu_head rcu; /* for call_rcu */ - struct net *net; /* netns for pernet list */ - char ifname[IFNAMSIZ]; /* device ifname */ -}; - -#ifdef CONFIG_PROC_FS -static const struct proc_ops clusterip_proc_ops; -#endif - -struct clusterip_net { - struct list_head configs; - /* lock protects the configs list */ - spinlock_t lock; - - bool clusterip_deprecated_warning; -#ifdef CONFIG_PROC_FS - struct proc_dir_entry *procdir; - /* mutex protects the config->pde*/ - struct mutex mutex; -#endif - unsigned int hook_users; -}; - -static unsigned int clusterip_arp_mangle(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); - -static const struct nf_hook_ops cip_arp_ops = { - .hook = clusterip_arp_mangle, - .pf = NFPROTO_ARP, - .hooknum = NF_ARP_OUT, - .priority = -1 -}; - -static unsigned int clusterip_net_id __read_mostly; -static inline struct clusterip_net *clusterip_pernet(struct net *net) -{ - return net_generic(net, clusterip_net_id); -} - -static inline void -clusterip_config_get(struct clusterip_config *c) -{ - refcount_inc(&c->refcount); -} - -static void clusterip_config_rcu_free(struct rcu_head *head) -{ - struct clusterip_config *config; - struct net_device *dev; - - config = container_of(head, struct clusterip_config, rcu); - dev = dev_get_by_name(config->net, config->ifname); - if (dev) { - dev_mc_del(dev, config->clustermac); - dev_put(dev); - } - kfree(config); -} - -static inline void -clusterip_config_put(struct clusterip_config *c) -{ - if (refcount_dec_and_test(&c->refcount)) - call_rcu(&c->rcu, clusterip_config_rcu_free); -} - -/* decrease the count of entries using/referencing this config. If last - * entry(rule) is removed, remove the config from lists, but don't free it - * yet, since proc-files could still be holding references */ -static inline void -clusterip_config_entry_put(struct clusterip_config *c) -{ - struct clusterip_net *cn = clusterip_pernet(c->net); - - local_bh_disable(); - if (refcount_dec_and_lock(&c->entries, &cn->lock)) { - list_del_rcu(&c->list); - spin_unlock(&cn->lock); - local_bh_enable(); - /* In case anyone still accesses the file, the open/close - * functions are also incrementing the refcount on their own, - * so it's safe to remove the entry even if it's in use. */ -#ifdef CONFIG_PROC_FS - mutex_lock(&cn->mutex); - if (cn->procdir) - proc_remove(c->pde); - mutex_unlock(&cn->mutex); -#endif - return; - } - local_bh_enable(); -} - -static struct clusterip_config * -__clusterip_config_find(struct net *net, __be32 clusterip) -{ - struct clusterip_config *c; - struct clusterip_net *cn = clusterip_pernet(net); - - list_for_each_entry_rcu(c, &cn->configs, list) { - if (c->clusterip == clusterip) - return c; - } - - return NULL; -} - -static inline struct clusterip_config * -clusterip_config_find_get(struct net *net, __be32 clusterip, int entry) -{ - struct clusterip_config *c; - - rcu_read_lock_bh(); - c = __clusterip_config_find(net, clusterip); - if (c) { -#ifdef CONFIG_PROC_FS - if (!c->pde) - c = NULL; - else -#endif - if (unlikely(!refcount_inc_not_zero(&c->refcount))) - c = NULL; - else if (entry) { - if (unlikely(!refcount_inc_not_zero(&c->entries))) { - clusterip_config_put(c); - c = NULL; - } - } - } - rcu_read_unlock_bh(); - - return c; -} - -static void -clusterip_config_init_nodelist(struct clusterip_config *c, - const struct ipt_clusterip_tgt_info *i) -{ - int n; - - for (n = 0; n < i->num_local_nodes; n++) - set_bit(i->local_nodes[n] - 1, &c->local_nodes); -} - -static int -clusterip_netdev_event(struct notifier_block *this, unsigned long event, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct net *net = dev_net(dev); - struct clusterip_net *cn = clusterip_pernet(net); - struct clusterip_config *c; - - spin_lock_bh(&cn->lock); - list_for_each_entry_rcu(c, &cn->configs, list) { - switch (event) { - case NETDEV_REGISTER: - if (!strcmp(dev->name, c->ifname)) { - c->ifindex = dev->ifindex; - dev_mc_add(dev, c->clustermac); - } - break; - case NETDEV_UNREGISTER: - if (dev->ifindex == c->ifindex) { - dev_mc_del(dev, c->clustermac); - c->ifindex = -1; - } - break; - case NETDEV_CHANGENAME: - if (!strcmp(dev->name, c->ifname)) { - c->ifindex = dev->ifindex; - dev_mc_add(dev, c->clustermac); - } else if (dev->ifindex == c->ifindex) { - dev_mc_del(dev, c->clustermac); - c->ifindex = -1; - } - break; - } - } - spin_unlock_bh(&cn->lock); - - return NOTIFY_DONE; -} - -static struct clusterip_config * -clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, - __be32 ip, const char *iniface) -{ - struct clusterip_net *cn = clusterip_pernet(net); - struct clusterip_config *c; - struct net_device *dev; - int err; - - if (iniface[0] == '\0') { - pr_info("Please specify an interface name\n"); - return ERR_PTR(-EINVAL); - } - - c = kzalloc(sizeof(*c), GFP_ATOMIC); - if (!c) - return ERR_PTR(-ENOMEM); - - dev = dev_get_by_name(net, iniface); - if (!dev) { - pr_info("no such interface %s\n", iniface); - kfree(c); - return ERR_PTR(-ENOENT); - } - c->ifindex = dev->ifindex; - strcpy(c->ifname, dev->name); - memcpy(&c->clustermac, &i->clustermac, ETH_ALEN); - dev_mc_add(dev, c->clustermac); - dev_put(dev); - - c->clusterip = ip; - c->num_total_nodes = i->num_total_nodes; - clusterip_config_init_nodelist(c, i); - c->hash_mode = i->hash_mode; - c->hash_initval = i->hash_initval; - c->net = net; - refcount_set(&c->refcount, 1); - - spin_lock_bh(&cn->lock); - if (__clusterip_config_find(net, ip)) { - err = -EBUSY; - goto out_config_put; - } - - list_add_rcu(&c->list, &cn->configs); - spin_unlock_bh(&cn->lock); - -#ifdef CONFIG_PROC_FS - { - char buffer[16]; - - /* create proc dir entry */ - sprintf(buffer, "%pI4", &ip); - mutex_lock(&cn->mutex); - c->pde = proc_create_data(buffer, 0600, - cn->procdir, - &clusterip_proc_ops, c); - mutex_unlock(&cn->mutex); - if (!c->pde) { - err = -ENOMEM; - goto err; - } - } -#endif - - refcount_set(&c->entries, 1); - return c; - -#ifdef CONFIG_PROC_FS -err: -#endif - spin_lock_bh(&cn->lock); - list_del_rcu(&c->list); -out_config_put: - spin_unlock_bh(&cn->lock); - clusterip_config_put(c); - return ERR_PTR(err); -} - -#ifdef CONFIG_PROC_FS -static int -clusterip_add_node(struct clusterip_config *c, u_int16_t nodenum) -{ - - if (nodenum == 0 || - nodenum > c->num_total_nodes) - return 1; - - /* check if we already have this number in our bitfield */ - if (test_and_set_bit(nodenum - 1, &c->local_nodes)) - return 1; - - return 0; -} - -static bool -clusterip_del_node(struct clusterip_config *c, u_int16_t nodenum) -{ - if (nodenum == 0 || - nodenum > c->num_total_nodes) - return true; - - if (test_and_clear_bit(nodenum - 1, &c->local_nodes)) - return false; - - return true; -} -#endif - -static inline u_int32_t -clusterip_hashfn(const struct sk_buff *skb, - const struct clusterip_config *config) -{ - const struct iphdr *iph = ip_hdr(skb); - unsigned long hashval; - u_int16_t sport = 0, dport = 0; - int poff; - - poff = proto_ports_offset(iph->protocol); - if (poff >= 0) { - const u_int16_t *ports; - u16 _ports[2]; - - ports = skb_header_pointer(skb, iph->ihl * 4 + poff, 4, _ports); - if (ports) { - sport = ports[0]; - dport = ports[1]; - } - } else { - net_info_ratelimited("unknown protocol %u\n", iph->protocol); - } - - switch (config->hash_mode) { - case CLUSTERIP_HASHMODE_SIP: - hashval = jhash_1word(ntohl(iph->saddr), - config->hash_initval); - break; - case CLUSTERIP_HASHMODE_SIP_SPT: - hashval = jhash_2words(ntohl(iph->saddr), sport, - config->hash_initval); - break; - case CLUSTERIP_HASHMODE_SIP_SPT_DPT: - hashval = jhash_3words(ntohl(iph->saddr), sport, dport, - config->hash_initval); - break; - default: - /* to make gcc happy */ - hashval = 0; - /* This cannot happen, unless the check function wasn't called - * at rule load time */ - pr_info("unknown mode %u\n", config->hash_mode); - BUG(); - break; - } - - /* node numbers are 1..n, not 0..n */ - return reciprocal_scale(hashval, config->num_total_nodes) + 1; -} - -static inline int -clusterip_responsible(const struct clusterip_config *config, u_int32_t hash) -{ - return test_bit(hash - 1, &config->local_nodes); -} - -/*********************************************************************** - * IPTABLES TARGET - ***********************************************************************/ - -static unsigned int -clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - u_int32_t hash; - - /* don't need to clusterip_config_get() here, since refcount - * is only decremented by destroy() - and ip_tables guarantees - * that the ->target() function isn't called after ->destroy() */ - - ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) - return NF_DROP; - - /* special case: ICMP error handling. conntrack distinguishes between - * error messages (RELATED) and information requests (see below) */ - if (ip_hdr(skb)->protocol == IPPROTO_ICMP && - (ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)) - return XT_CONTINUE; - - /* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO, - * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here - * on, which all have an ID field [relevant for hashing]. */ - - hash = clusterip_hashfn(skb, cipinfo->config); - - switch (ctinfo) { - case IP_CT_NEW: - WRITE_ONCE(ct->mark, hash); - break; - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - /* FIXME: we don't handle expectations at the moment. - * They can arrive on a different node than - * the master connection (e.g. FTP passive mode) */ - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED_REPLY: - break; - default: /* Prevent gcc warnings */ - break; - } - -#ifdef DEBUG - nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); -#endif - pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); - if (!clusterip_responsible(cipinfo->config, hash)) { - pr_debug("not responsible\n"); - return NF_DROP; - } - pr_debug("responsible\n"); - - /* despite being received via linklayer multicast, this is - * actually a unicast IP packet. TCP doesn't like PACKET_MULTICAST */ - skb->pkt_type = PACKET_HOST; - - return XT_CONTINUE; -} - -static int clusterip_tg_check(const struct xt_tgchk_param *par) -{ - struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; - struct clusterip_net *cn = clusterip_pernet(par->net); - const struct ipt_entry *e = par->entryinfo; - struct clusterip_config *config; - int ret, i; - - if (par->nft_compat) { - pr_err("cannot use CLUSTERIP target from nftables compat\n"); - return -EOPNOTSUPP; - } - - if (cn->hook_users == UINT_MAX) - return -EOVERFLOW; - - if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP && - cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT && - cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) { - pr_info("unknown mode %u\n", cipinfo->hash_mode); - return -EINVAL; - - } - if (e->ip.dmsk.s_addr != htonl(0xffffffff) || - e->ip.dst.s_addr == 0) { - pr_info("Please specify destination IP\n"); - return -EINVAL; - } - if (cipinfo->num_local_nodes > ARRAY_SIZE(cipinfo->local_nodes)) { - pr_info("bad num_local_nodes %u\n", cipinfo->num_local_nodes); - return -EINVAL; - } - for (i = 0; i < cipinfo->num_local_nodes; i++) { - if (cipinfo->local_nodes[i] - 1 >= - sizeof(config->local_nodes) * 8) { - pr_info("bad local_nodes[%d] %u\n", - i, cipinfo->local_nodes[i]); - return -EINVAL; - } - } - - config = clusterip_config_find_get(par->net, e->ip.dst.s_addr, 1); - if (!config) { - if (!(cipinfo->flags & CLUSTERIP_FLAG_NEW)) { - pr_info("no config found for %pI4, need 'new'\n", - &e->ip.dst.s_addr); - return -EINVAL; - } else { - config = clusterip_config_init(par->net, cipinfo, - e->ip.dst.s_addr, - e->ip.iniface); - if (IS_ERR(config)) - return PTR_ERR(config); - } - } else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN)) { - clusterip_config_entry_put(config); - clusterip_config_put(config); - return -EINVAL; - } - - ret = nf_ct_netns_get(par->net, par->family); - if (ret < 0) { - pr_info("cannot load conntrack support for proto=%u\n", - par->family); - clusterip_config_entry_put(config); - clusterip_config_put(config); - return ret; - } - - if (cn->hook_users == 0) { - ret = nf_register_net_hook(par->net, &cip_arp_ops); - - if (ret < 0) { - clusterip_config_entry_put(config); - clusterip_config_put(config); - nf_ct_netns_put(par->net, par->family); - return ret; - } - } - - cn->hook_users++; - - if (!cn->clusterip_deprecated_warning) { - pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " - "use xt_cluster instead\n"); - cn->clusterip_deprecated_warning = true; - } - - cipinfo->config = config; - return ret; -} - -/* drop reference count of cluster config when rule is deleted */ -static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) -{ - const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; - struct clusterip_net *cn = clusterip_pernet(par->net); - - /* if no more entries are referencing the config, remove it - * from the list and destroy the proc entry */ - clusterip_config_entry_put(cipinfo->config); - - clusterip_config_put(cipinfo->config); - - nf_ct_netns_put(par->net, par->family); - cn->hook_users--; - - if (cn->hook_users == 0) - nf_unregister_net_hook(par->net, &cip_arp_ops); -} - -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT -struct compat_ipt_clusterip_tgt_info -{ - u_int32_t flags; - u_int8_t clustermac[6]; - u_int16_t num_total_nodes; - u_int16_t num_local_nodes; - u_int16_t local_nodes[CLUSTERIP_MAX_NODES]; - u_int32_t hash_mode; - u_int32_t hash_initval; - compat_uptr_t config; -}; -#endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ - -static struct xt_target clusterip_tg_reg __read_mostly = { - .name = "CLUSTERIP", - .family = NFPROTO_IPV4, - .target = clusterip_tg, - .checkentry = clusterip_tg_check, - .destroy = clusterip_tg_destroy, - .targetsize = sizeof(struct ipt_clusterip_tgt_info), - .usersize = offsetof(struct ipt_clusterip_tgt_info, config), -#ifdef CONFIG_NETFILTER_XTABLES_COMPAT - .compatsize = sizeof(struct compat_ipt_clusterip_tgt_info), -#endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ - .me = THIS_MODULE -}; - - -/*********************************************************************** - * ARP MANGLING CODE - ***********************************************************************/ - -/* hardcoded for 48bit ethernet and 32bit ipv4 addresses */ -struct arp_payload { - u_int8_t src_hw[ETH_ALEN]; - __be32 src_ip; - u_int8_t dst_hw[ETH_ALEN]; - __be32 dst_ip; -} __packed; - -#ifdef DEBUG -static void arp_print(struct arp_payload *payload) -{ -#define HBUFFERLEN 30 - char hbuffer[HBUFFERLEN]; - int j, k; - - for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < ETH_ALEN; j++) { - hbuffer[k++] = hex_asc_hi(payload->src_hw[j]); - hbuffer[k++] = hex_asc_lo(payload->src_hw[j]); - hbuffer[k++] = ':'; - } - hbuffer[--k] = '\0'; - - pr_debug("src %pI4@%s, dst %pI4\n", - &payload->src_ip, hbuffer, &payload->dst_ip); -} -#endif - -static unsigned int -clusterip_arp_mangle(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct arphdr *arp = arp_hdr(skb); - struct arp_payload *payload; - struct clusterip_config *c; - struct net *net = state->net; - - /* we don't care about non-ethernet and non-ipv4 ARP */ - if (arp->ar_hrd != htons(ARPHRD_ETHER) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) - return NF_ACCEPT; - - /* we only want to mangle arp requests and replies */ - if (arp->ar_op != htons(ARPOP_REPLY) && - arp->ar_op != htons(ARPOP_REQUEST)) - return NF_ACCEPT; - - payload = (void *)(arp+1); - - /* if there is no clusterip configuration for the arp reply's - * source ip, we don't want to mangle it */ - c = clusterip_config_find_get(net, payload->src_ip, 0); - if (!c) - return NF_ACCEPT; - - /* normally the linux kernel always replies to arp queries of - * addresses on different interfacs. However, in the CLUSTERIP case - * this wouldn't work, since we didn't subscribe the mcast group on - * other interfaces */ - if (c->ifindex != state->out->ifindex) { - pr_debug("not mangling arp reply on different interface: cip'%d'-skb'%d'\n", - c->ifindex, state->out->ifindex); - clusterip_config_put(c); - return NF_ACCEPT; - } - - /* mangle reply hardware address */ - memcpy(payload->src_hw, c->clustermac, arp->ar_hln); - -#ifdef DEBUG - pr_debug("mangled arp reply: "); - arp_print(payload); -#endif - - clusterip_config_put(c); - - return NF_ACCEPT; -} - -/*********************************************************************** - * PROC DIR HANDLING - ***********************************************************************/ - -#ifdef CONFIG_PROC_FS - -struct clusterip_seq_position { - unsigned int pos; /* position */ - unsigned int weight; /* number of bits set == size */ - unsigned int bit; /* current bit */ - unsigned long val; /* current value */ -}; - -static void *clusterip_seq_start(struct seq_file *s, loff_t *pos) -{ - struct clusterip_config *c = s->private; - unsigned int weight; - u_int32_t local_nodes; - struct clusterip_seq_position *idx; - - /* FIXME: possible race */ - local_nodes = c->local_nodes; - weight = hweight32(local_nodes); - if (*pos >= weight) - return NULL; - - idx = kmalloc(sizeof(struct clusterip_seq_position), GFP_KERNEL); - if (!idx) - return ERR_PTR(-ENOMEM); - - idx->pos = *pos; - idx->weight = weight; - idx->bit = ffs(local_nodes); - idx->val = local_nodes; - clear_bit(idx->bit - 1, &idx->val); - - return idx; -} - -static void *clusterip_seq_next(struct seq_file *s, void *v, loff_t *pos) -{ - struct clusterip_seq_position *idx = v; - - *pos = ++idx->pos; - if (*pos >= idx->weight) { - kfree(v); - return NULL; - } - idx->bit = ffs(idx->val); - clear_bit(idx->bit - 1, &idx->val); - return idx; -} - -static void clusterip_seq_stop(struct seq_file *s, void *v) -{ - if (!IS_ERR(v)) - kfree(v); -} - -static int clusterip_seq_show(struct seq_file *s, void *v) -{ - struct clusterip_seq_position *idx = v; - - if (idx->pos != 0) - seq_putc(s, ','); - - seq_printf(s, "%u", idx->bit); - - if (idx->pos == idx->weight - 1) - seq_putc(s, '\n'); - - return 0; -} - -static const struct seq_operations clusterip_seq_ops = { - .start = clusterip_seq_start, - .next = clusterip_seq_next, - .stop = clusterip_seq_stop, - .show = clusterip_seq_show, -}; - -static int clusterip_proc_open(struct inode *inode, struct file *file) -{ - int ret = seq_open(file, &clusterip_seq_ops); - - if (!ret) { - struct seq_file *sf = file->private_data; - struct clusterip_config *c = pde_data(inode); - - sf->private = c; - - clusterip_config_get(c); - } - - return ret; -} - -static int clusterip_proc_release(struct inode *inode, struct file *file) -{ - struct clusterip_config *c = pde_data(inode); - int ret; - - ret = seq_release(inode, file); - - if (!ret) - clusterip_config_put(c); - - return ret; -} - -static ssize_t clusterip_proc_write(struct file *file, const char __user *input, - size_t size, loff_t *ofs) -{ - struct clusterip_config *c = pde_data(file_inode(file)); -#define PROC_WRITELEN 10 - char buffer[PROC_WRITELEN+1]; - unsigned long nodenum; - int rc; - - if (size > PROC_WRITELEN) - return -EIO; - if (copy_from_user(buffer, input, size)) - return -EFAULT; - buffer[size] = 0; - - if (*buffer == '+') { - rc = kstrtoul(buffer+1, 10, &nodenum); - if (rc) - return rc; - if (clusterip_add_node(c, nodenum)) - return -ENOMEM; - } else if (*buffer == '-') { - rc = kstrtoul(buffer+1, 10, &nodenum); - if (rc) - return rc; - if (clusterip_del_node(c, nodenum)) - return -ENOENT; - } else - return -EIO; - - return size; -} - -static const struct proc_ops clusterip_proc_ops = { - .proc_open = clusterip_proc_open, - .proc_read = seq_read, - .proc_write = clusterip_proc_write, - .proc_lseek = seq_lseek, - .proc_release = clusterip_proc_release, -}; - -#endif /* CONFIG_PROC_FS */ - -static int clusterip_net_init(struct net *net) -{ - struct clusterip_net *cn = clusterip_pernet(net); - - INIT_LIST_HEAD(&cn->configs); - - spin_lock_init(&cn->lock); - -#ifdef CONFIG_PROC_FS - cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net); - if (!cn->procdir) { - pr_err("Unable to proc dir entry\n"); - return -ENOMEM; - } - mutex_init(&cn->mutex); -#endif /* CONFIG_PROC_FS */ - - return 0; -} - -static void clusterip_net_exit(struct net *net) -{ -#ifdef CONFIG_PROC_FS - struct clusterip_net *cn = clusterip_pernet(net); - - mutex_lock(&cn->mutex); - proc_remove(cn->procdir); - cn->procdir = NULL; - mutex_unlock(&cn->mutex); -#endif -} - -static struct pernet_operations clusterip_net_ops = { - .init = clusterip_net_init, - .exit = clusterip_net_exit, - .id = &clusterip_net_id, - .size = sizeof(struct clusterip_net), -}; - -static struct notifier_block cip_netdev_notifier = { - .notifier_call = clusterip_netdev_event -}; - -static int __init clusterip_tg_init(void) -{ - int ret; - - ret = register_pernet_subsys(&clusterip_net_ops); - if (ret < 0) - return ret; - - ret = xt_register_target(&clusterip_tg_reg); - if (ret < 0) - goto cleanup_subsys; - - ret = register_netdevice_notifier(&cip_netdev_notifier); - if (ret < 0) - goto unregister_target; - - pr_info("ClusterIP Version %s loaded successfully\n", - CLUSTERIP_VERSION); - - return 0; - -unregister_target: - xt_unregister_target(&clusterip_tg_reg); -cleanup_subsys: - unregister_pernet_subsys(&clusterip_net_ops); - return ret; -} - -static void __exit clusterip_tg_exit(void) -{ - pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION); - - unregister_netdevice_notifier(&cip_netdev_notifier); - xt_unregister_target(&clusterip_tg_reg); - unregister_pernet_subsys(&clusterip_net_ops); - - /* Wait for completion of call_rcu()'s (clusterip_config_rcu_free) */ - rcu_barrier(); -} - -module_init(clusterip_tg_init); -module_exit(clusterip_tg_exit); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e74e0361fd92..76889ceeead9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -91,7 +91,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static int ip6_dst_gc(struct dst_ops *ops); +static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -3284,23 +3284,17 @@ out: return dst; } -static int ip6_dst_gc(struct dst_ops *ops) +static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; - int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; unsigned int val; int entries; - entries = dst_entries_get_fast(ops); - if (entries > rt_max_size) - entries = dst_entries_get_slow(ops); - - if (time_after(rt_last_gc + rt_min_interval, jiffies) && - entries <= rt_max_size) + if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); @@ -3310,7 +3304,6 @@ static int ip6_dst_gc(struct dst_ops *ops) out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); - return entries > rt_max_size; } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, @@ -6512,7 +6505,7 @@ static int __net_init ip6_route_net_init(struct net *net) #endif net->ipv6.sysctl.flush_delay = 0; - net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index ff691d9f4a04..b1c028df686e 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -13,7 +13,7 @@ #include <net/rpl.h> struct rpl_iptunnel_encap { - struct ipv6_rpl_sr_hdr srh[0]; + DECLARE_FLEX_ARRAY(struct ipv6_rpl_sr_hdr, srh); }; struct rpl_lwt { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 5ded85e2c374..b30cea2fbf3f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1594,8 +1594,7 @@ mp_rst: TCPOLEN_MPTCP_PRIO, opts->backup, TCPOPT_NOP); - MPTCP_INC_STATS(sock_net((const struct sock *)tp), - MPTCP_MIB_MPPRIOTX); + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPPRIOTX); } mp_capable_done: diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2ea7eae43bdb..b5505b8167f9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1143,7 +1143,7 @@ void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ss if (!tcp_rtx_and_write_queues_empty(ssk)) { subflow->stale = 1; __mptcp_retransmit_pending_data(sk); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_SUBFLOWSTALE); + MPTCP_INC_STATS(net, MPTCP_MIB_SUBFLOWSTALE); } unlock_sock_fast(ssk, slow); @@ -1903,8 +1903,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) } if (token) - return mptcp_userspace_pm_set_flags(sock_net(skb->sk), - token, &addr, &remote, bkup); + return mptcp_userspace_pm_set_flags(net, token, &addr, &remote, bkup); spin_lock_bh(&pernet->lock); entry = __lookup_addr(pernet, &addr.addr, lookup_by_id); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8cd6cc67c2c5..1ff2efbab29e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -923,9 +923,8 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - struct sock *sk = (struct sock *)msk; - sock_owned_by_me(sk); + msk_owned_by_me(msk); mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->data_avail)) @@ -1408,7 +1407,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) u64 linger_time; long tout = 0; - sock_owned_by_me(sk); + msk_owned_by_me(msk); if (__mptcp_check_fallback(msk)) { if (!msk->first) @@ -1890,7 +1889,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) u32 time, advmss = 1; u64 rtt_us, mstamp; - sock_owned_by_me(sk); + msk_owned_by_me(msk); if (copied <= 0) return; @@ -2217,7 +2216,7 @@ static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) struct mptcp_subflow_context *subflow; int min_stale_count = INT_MAX; - sock_owned_by_me((const struct sock *)msk); + msk_owned_by_me(msk); if (__mptcp_check_fallback(msk)) return NULL; @@ -2724,8 +2723,8 @@ static int mptcp_init_sock(struct sock *sk) mptcp_ca_reset(sk); sk_sockets_allocated_inc(sk); - sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); - sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + sk->sk_rcvbuf = READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]); + sk->sk_sndbuf = READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]); return 0; } @@ -2892,6 +2891,12 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk) return EPOLLIN | EPOLLRDNORM; } +static void mptcp_listen_inuse_dec(struct sock *sk) +{ + if (inet_sk_state_load(sk) == TCP_LISTEN) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); +} + bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; @@ -2901,6 +2906,7 @@ bool __mptcp_close(struct sock *sk, long timeout) sk->sk_shutdown = SHUTDOWN_MASK; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { + mptcp_listen_inuse_dec(sk); inet_sk_state_store(sk, TCP_CLOSE); goto cleanup; } @@ -3001,6 +3007,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) if (msk->fastopening) return 0; + mptcp_listen_inuse_dec(sk); inet_sk_state_store(sk, TCP_CLOSE); mptcp_stop_timer(sk); @@ -3639,12 +3646,13 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct sock *sk = sock->sk; struct socket *ssock; int err; pr_debug("msk=%p", msk); - lock_sock(sock->sk); + lock_sock(sk); ssock = __mptcp_nmpc_socket(msk); if (!ssock) { err = -EINVAL; @@ -3652,18 +3660,20 @@ static int mptcp_listen(struct socket *sock, int backlog) } mptcp_token_destroy(msk); - inet_sk_state_store(sock->sk, TCP_LISTEN); - sock_set_flag(sock->sk, SOCK_RCU_FREE); + inet_sk_state_store(sk, TCP_LISTEN); + sock_set_flag(sk, SOCK_RCU_FREE); err = ssock->ops->listen(ssock, backlog); - inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); - if (!err) - mptcp_copy_inaddrs(sock->sk, ssock->sk); + inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); + if (!err) { + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + mptcp_copy_inaddrs(sk, ssock->sk); + } mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); unlock: - release_sock(sock->sk); + release_sock(sk); return err; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 601469249da8..61fd8eabfca2 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -755,7 +755,7 @@ static inline void mptcp_token_init_request(struct request_sock *req) int mptcp_token_new_request(struct request_sock *req); void mptcp_token_destroy_request(struct request_sock *req); -int mptcp_token_new_connect(struct sock *sk); +int mptcp_token_new_connect(struct sock *ssk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); bool mptcp_token_exists(u32 token); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index d4b1e6ec1b36..582ed93bcc8a 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -18,7 +18,7 @@ static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { - sock_owned_by_me((const struct sock *)msk); + msk_owned_by_me(msk); if (likely(!__mptcp_check_fallback(msk))) return NULL; diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 65430f314a68..5bb924534387 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -134,7 +134,7 @@ int mptcp_token_new_request(struct request_sock *req) /** * mptcp_token_new_connect - create new key/idsn/token for subflow - * @sk: the socket that will initiate a connection + * @ssk: the socket that will initiate a connection * * This function is called when a new outgoing mptcp connection is * initiated. @@ -148,11 +148,12 @@ int mptcp_token_new_request(struct request_sock *req) * * returns 0 on success. */ -int mptcp_token_new_connect(struct sock *sk) +int mptcp_token_new_connect(struct sock *ssk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); int retries = MPTCP_TOKEN_MAX_RETRIES; + struct sock *sk = subflow->conn; struct token_bucket *bucket; again: @@ -169,12 +170,13 @@ again: } pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", - sk, subflow->local_key, subflow->token, subflow->idsn); + ssk, subflow->local_key, subflow->token, subflow->idsn); WRITE_ONCE(msk->token, subflow->token); __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); bucket->chain_len++; spin_unlock_bh(&bucket->lock); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); return 0; } @@ -190,8 +192,10 @@ void mptcp_token_accept(struct mptcp_subflow_request_sock *req, struct mptcp_sock *msk) { struct mptcp_subflow_request_sock *pos; + struct sock *sk = (struct sock *)msk; struct token_bucket *bucket; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); bucket = token_bucket(req->token); spin_lock_bh(&bucket->lock); @@ -370,12 +374,14 @@ void mptcp_token_destroy_request(struct request_sock *req) */ void mptcp_token_destroy(struct mptcp_sock *msk) { + struct sock *sk = (struct sock *)msk; struct token_bucket *bucket; struct mptcp_sock *pos; if (sk_unhashed((struct sock *)msk)) return; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); bucket = token_bucket(msk->token); spin_lock_bh(&bucket->lock); pos = __token_lookup_msk(bucket, msk->token); diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index 5d984bec1cd8..0758865ab658 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -57,6 +57,9 @@ static struct mptcp_sock *build_msk(struct kunit *test) KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); refcount_set(&((struct sock *)msk)->sk_refcnt, 1); sock_net_set((struct sock *)msk, &init_net); + + /* be sure the token helpers can dereference sk->sk_prot */ + ((struct sock *)msk)->sk_prot = &tcp_prot; return msk; } diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 3754eb06fb41..ba2a6b5e93d9 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -98,6 +98,12 @@ nf_tables-objs += nft_set_pipapo_avx2.o endif endif +ifdef CONFIG_NFT_CT +ifdef CONFIG_RETPOLINE +nf_tables-objs += nft_ct_fast.o +endif +endif + obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 496c4920505b..c00858344f02 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -514,7 +514,6 @@ EXPORT_SYMBOL_GPL(nf_ct_get_id); static void clean_from_lists(struct nf_conn *ct) { - pr_debug("clean_from_lists(%p)\n", ct); hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode); @@ -582,7 +581,6 @@ void nf_ct_destroy(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; - pr_debug("%s(%p)\n", __func__, ct); WARN_ON(refcount_read(&nfct->use) != 0); if (unlikely(nf_ct_is_template(ct))) { @@ -603,7 +601,6 @@ void nf_ct_destroy(struct nf_conntrack *nfct) if (ct->master) nf_ct_put(ct->master); - pr_debug("%s: returning ct=%p to slab\n", __func__, ct); nf_conntrack_free(ct); } EXPORT_SYMBOL(nf_ct_destroy); @@ -786,8 +783,6 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; - rcu_read_lock(); - h = ____nf_conntrack_find(net, zone, tuple, hash); if (h) { /* We have a candidate that matches the tuple we're interested @@ -799,7 +794,7 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, smp_acquire__after_ctrl_dep(); if (likely(nf_ct_key_equal(h, tuple, zone, net))) - goto found; + return h; /* TYPESAFE_BY_RCU recycled the candidate */ nf_ct_put(ct); @@ -807,8 +802,6 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, h = NULL; } -found: - rcu_read_unlock(); return h; } @@ -820,16 +813,21 @@ nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); struct nf_conntrack_tuple_hash *thash; + rcu_read_lock(); + thash = __nf_conntrack_find_get(net, zone, tuple, hash_conntrack_raw(tuple, zone_id, net)); if (thash) - return thash; + goto out_unlock; rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); if (rid != zone_id) - return __nf_conntrack_find_get(net, zone, tuple, - hash_conntrack_raw(tuple, rid, net)); + thash = __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, rid, net)); + +out_unlock: + rcu_read_unlock(); return thash; } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); @@ -1210,7 +1208,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) goto dying; } - pr_debug("Confirming conntrack %p\n", ct); /* We have to check the DYING flag after unlink to prevent * a race against nf_ct_get_next_corpse() possibly called from * user context, else we insert an already 'dead' hash, blocking @@ -1721,10 +1718,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_zone tmp; struct nf_conntrack_net *cnet; - if (!nf_ct_invert_tuple(&repl_tuple, tuple)) { - pr_debug("Can't invert tuple.\n"); + if (!nf_ct_invert_tuple(&repl_tuple, tuple)) return NULL; - } zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC, @@ -1764,8 +1759,6 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, spin_lock_bh(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple); if (exp) { - pr_debug("expectation arrives ct=%p exp=%p\n", - ct, exp); /* Welcome, Mr. Bond. We've been expecting you... */ __set_bit(IPS_EXPECTED_BIT, &ct->status); /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ @@ -1829,10 +1822,8 @@ resolve_normal_ct(struct nf_conn *tmpl, if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, - &tuple)) { - pr_debug("Can't get tuple\n"); + &tuple)) return 0; - } /* look for tuple match */ zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); @@ -1864,17 +1855,15 @@ resolve_normal_ct(struct nf_conn *tmpl, if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) { ctinfo = IP_CT_ESTABLISHED_REPLY; } else { + unsigned long status = READ_ONCE(ct->status); + /* Once we've had two way comms, always ESTABLISHED. */ - if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { - pr_debug("normal packet for %p\n", ct); + if (likely(status & IPS_SEEN_REPLY)) ctinfo = IP_CT_ESTABLISHED; - } else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) { - pr_debug("related packet for %p\n", ct); + else if (status & IPS_EXPECTED) ctinfo = IP_CT_RELATED; - } else { - pr_debug("new packet for %p\n", ct); + else ctinfo = IP_CT_NEW; - } } nf_ct_set(skb, ct, ctinfo); return 0; @@ -1988,7 +1977,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) /* rcu_read_lock()ed by nf_hook_thresh */ dataoff = get_l4proto(skb, skb_network_offset(skb), state->pf, &protonum); if (dataoff <= 0) { - pr_debug("not prepared to track yet or error occurred\n"); NF_CT_STAT_INC_ATOMIC(state->net, invalid); ret = NF_ACCEPT; goto out; @@ -2027,7 +2015,6 @@ repeat: if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ - pr_debug("nf_conntrack_in: Can't track with proto module\n"); nf_ct_put(ct); skb->_nfct = 0; /* Special case: TCP tracker reports an attempt to reopen a @@ -2066,7 +2053,6 @@ void nf_conntrack_alter_reply(struct nf_conn *ct, /* Should be unconfirmed, so not in hash table yet */ WARN_ON(nf_ct_is_confirmed(ct)); - pr_debug("Altering reply tuple of %p to ", ct); nf_ct_dump_tuple(newreply); ct->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1286ae7d4609..90672e293e57 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3866,7 +3866,7 @@ static int __init ctnetlink_init(void) { int ret; - BUILD_BUG_ON(sizeof(struct ctnetlink_list_dump_ctx) > sizeof_field(struct netlink_callback, ctx)); + NL_ASSET_DUMP_CTX_FITS(struct ctnetlink_list_dump_ctx); ret = nfnetlink_subsys_register(&ctnl_subsys); if (ret < 0) { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index ccef340be575..c928ff63b10e 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -284,16 +284,11 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) /* We only do TCP and SCTP at the moment: is there a better way? */ if (tuple.dst.protonum != IPPROTO_TCP && - tuple.dst.protonum != IPPROTO_SCTP) { - pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); + tuple.dst.protonum != IPPROTO_SCTP) return -ENOPROTOOPT; - } - if ((unsigned int)*len < sizeof(struct sockaddr_in)) { - pr_debug("SO_ORIGINAL_DST: len %d not %zu\n", - *len, sizeof(struct sockaddr_in)); + if ((unsigned int)*len < sizeof(struct sockaddr_in)) return -EINVAL; - } h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); if (h) { @@ -307,17 +302,12 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) .tuple.dst.u3.ip; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); - pr_debug("SO_ORIGINAL_DST: %pI4 %u\n", - &sin.sin_addr.s_addr, ntohs(sin.sin_port)); nf_ct_put(ct); if (copy_to_user(user, &sin, sizeof(sin)) != 0) return -EFAULT; else return 0; } - pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n", - &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port), - &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port)); return -ENOENT; } @@ -360,12 +350,8 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) return -EINVAL; h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); - if (!h) { - pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", - &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), - &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + if (!h) return -ENOENT; - } ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index d88b92a8ffca..dbdfcc6cd2aa 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -168,7 +168,8 @@ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ static int do_basic_checks(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - unsigned long *map) + unsigned long *map, + const struct nf_hook_state *state) { u_int32_t offset, count; struct sctp_chunkhdr _sch, *sch; @@ -177,8 +178,6 @@ static int do_basic_checks(struct nf_conn *ct, flag = 0; for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { - pr_debug("Chunk Num: %d Type: %d\n", count, sch->type); - if (sch->type == SCTP_CID_INIT || sch->type == SCTP_CID_INIT_ACK || sch->type == SCTP_CID_SHUTDOWN_COMPLETE) @@ -193,7 +192,9 @@ static int do_basic_checks(struct nf_conn *ct, sch->type == SCTP_CID_COOKIE_ECHO || flag) && count != 0) || !sch->length) { - pr_debug("Basic checks failed\n"); + nf_ct_l4proto_log_invalid(skb, ct, state, + "%s failed. chunk num %d, type %d, len %d flag %d\n", + __func__, count, sch->type, sch->length, flag); return 1; } @@ -201,7 +202,6 @@ static int do_basic_checks(struct nf_conn *ct, set_bit(sch->type, map); } - pr_debug("Basic checks passed\n"); return count == 0; } @@ -211,69 +211,51 @@ static int sctp_new_state(enum ip_conntrack_dir dir, { int i; - pr_debug("Chunk type: %d\n", chunk_type); - switch (chunk_type) { case SCTP_CID_INIT: - pr_debug("SCTP_CID_INIT\n"); i = 0; break; case SCTP_CID_INIT_ACK: - pr_debug("SCTP_CID_INIT_ACK\n"); i = 1; break; case SCTP_CID_ABORT: - pr_debug("SCTP_CID_ABORT\n"); i = 2; break; case SCTP_CID_SHUTDOWN: - pr_debug("SCTP_CID_SHUTDOWN\n"); i = 3; break; case SCTP_CID_SHUTDOWN_ACK: - pr_debug("SCTP_CID_SHUTDOWN_ACK\n"); i = 4; break; case SCTP_CID_ERROR: - pr_debug("SCTP_CID_ERROR\n"); i = 5; break; case SCTP_CID_COOKIE_ECHO: - pr_debug("SCTP_CID_COOKIE_ECHO\n"); i = 6; break; case SCTP_CID_COOKIE_ACK: - pr_debug("SCTP_CID_COOKIE_ACK\n"); i = 7; break; case SCTP_CID_SHUTDOWN_COMPLETE: - pr_debug("SCTP_CID_SHUTDOWN_COMPLETE\n"); i = 8; break; case SCTP_CID_HEARTBEAT: - pr_debug("SCTP_CID_HEARTBEAT"); i = 9; break; case SCTP_CID_HEARTBEAT_ACK: - pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; case SCTP_CID_DATA: case SCTP_CID_SACK: - pr_debug("SCTP_CID_DATA/SACK"); i = 11; break; default: /* Other chunks like DATA or SACK do not change the state */ - pr_debug("Unknown chunk type, Will stay in %s\n", - sctp_conntrack_names[cur_state]); + pr_debug("Unknown chunk type %d, Will stay in %s\n", + chunk_type, sctp_conntrack_names[cur_state]); return cur_state; } - pr_debug("dir: %d cur_state: %s chunk_type: %d new_state: %s\n", - dir, sctp_conntrack_names[cur_state], chunk_type, - sctp_conntrack_names[sctp_conntracks[dir][i][cur_state]]); - return sctp_conntracks[dir][i][cur_state]; } @@ -392,7 +374,7 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (sh == NULL) goto out; - if (do_basic_checks(ct, skb, dataoff, map) != 0) + if (do_basic_checks(ct, skb, dataoff, map, state) != 0) goto out; if (!nf_ct_is_confirmed(ct)) { @@ -414,7 +396,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, !test_bit(SCTP_CID_HEARTBEAT, map) && !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); + nf_ct_l4proto_log_invalid(skb, ct, state, + "verification tag check failed %x vs %x for dir %d", + sh->vtag, ct->proto.sctp.vtag[dir], dir); goto out; } } @@ -488,9 +472,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* Invalid */ if (new_state == SCTP_CONNTRACK_MAX) { - pr_debug("nf_conntrack_sctp: Invalid dir=%i ctype=%u " - "conntrack=%u\n", - dir, sch->type, old_state); + nf_ct_l4proto_log_invalid(skb, ct, state, + "Invalid, old_state %d, dir %d, type %d", + old_state, dir, sch->type); + goto out_unlock; } @@ -536,7 +521,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && dir == IP_CT_DIR_REPLY && new_state == SCTP_CONNTRACK_ESTABLISHED) { - pr_debug("Setting assured bit\n"); set_bit(IPS_ASSURED_BIT, &ct->status); nf_conntrack_event_cache(IPCT_ASSURED, ct); } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3ac1af6f59fc..16ee5ebe1ce1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -930,7 +930,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); - struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; enum nf_ct_tcp_action res; @@ -954,7 +953,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, dir = CTINFO2DIR(ctinfo); index = get_conntrack_index(th); new_state = tcp_conntracks[dir][index][old_state]; - tuple = &ct->tuplehash[dir].tuple; switch (new_state) { case TCP_CONNTRACK_SYN_SENT: @@ -1232,13 +1230,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; - pr_debug("tcp_conntracks: "); - nf_ct_dump_tuple(tuple); - pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n", - (th->syn ? 1 : 0), (th->ack ? 1 : 0), - (th->fin ? 1 : 0), (th->rst ? 1 : 0), - old_state, new_state); - ct->proto.tcp.state = new_state; if (old_state != new_state && new_state == TCP_CONNTRACK_FIN_WAIT) diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 3b516cffc779..6b9206635b24 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -88,6 +88,7 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, const struct nf_hook_state *state) { unsigned int *timeouts; + unsigned long status; if (udp_error(skb, dataoff, state)) return -NF_ACCEPT; @@ -96,26 +97,27 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, if (!timeouts) timeouts = udp_get_timeouts(nf_ct_net(ct)); - if (!nf_ct_is_confirmed(ct)) + status = READ_ONCE(ct->status); + if ((status & IPS_CONFIRMED) == 0) ct->proto.udp.stream_ts = 2 * HZ + jiffies; /* If we've seen traffic both ways, this is some kind of UDP * stream. Set Assured. */ - if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (status & IPS_SEEN_REPLY_BIT) { unsigned long extra = timeouts[UDP_CT_UNREPLIED]; bool stream = false; /* Still active after two seconds? Extend timeout. */ if (time_after(jiffies, ct->proto.udp.stream_ts)) { extra = timeouts[UDP_CT_REPLIED]; - stream = true; + stream = (status & IPS_ASSURED) == 0; } nf_ct_refresh_acct(ct, ctinfo, skb, extra); /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ - if (unlikely((ct->status & IPS_NAT_CLASH))) + if (unlikely((status & IPS_NAT_CLASH))) return NF_ACCEPT; /* Also, more likely to be important, and not a probe */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8c09e4d12ac1..974b95dece1d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1401,6 +1401,10 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, } if (IS_ERR(table)) { + if (PTR_ERR(table) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYTABLE) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(table); } @@ -2639,6 +2643,10 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, chain = nft_chain_lookup(net, table, attr, genmask); } if (IS_ERR(chain)) { + if (PTR_ERR(chain) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); } @@ -3716,6 +3724,10 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { + if (PTR_ERR(rule) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) + return 0; + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } @@ -3729,6 +3741,10 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_RULE_HANDLE]) { rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { + if (PTR_ERR(rule) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) + return 0; + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); } @@ -4808,6 +4824,10 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, } if (IS_ERR(set)) { + if (PTR_ERR(set) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSET) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(set); } @@ -6690,6 +6710,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); + if (err == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM) + continue; + if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; @@ -7334,6 +7358,10 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, } if (IS_ERR(obj)) { + if (PTR_ERR(obj) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYOBJ) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(obj); } @@ -7964,6 +7992,10 @@ static int nf_tables_delflowtable(struct sk_buff *skb, } if (IS_ERR(flowtable)) { + if (PTR_ERR(flowtable) == -ENOENT && + NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYFLOWTABLE) + return 0; + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(flowtable); } @@ -8373,6 +8405,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, + [NFT_MSG_DESTROYTABLE] = { + .call = nf_tables_deltable, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_TABLE_MAX, + .policy = nft_table_policy, + }, [NFT_MSG_NEWCHAIN] = { .call = nf_tables_newchain, .type = NFNL_CB_BATCH, @@ -8391,6 +8429,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, + [NFT_MSG_DESTROYCHAIN] = { + .call = nf_tables_delchain, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_CHAIN_MAX, + .policy = nft_chain_policy, + }, [NFT_MSG_NEWRULE] = { .call = nf_tables_newrule, .type = NFNL_CB_BATCH, @@ -8415,6 +8459,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, + [NFT_MSG_DESTROYRULE] = { + .call = nf_tables_delrule, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_RULE_MAX, + .policy = nft_rule_policy, + }, [NFT_MSG_NEWSET] = { .call = nf_tables_newset, .type = NFNL_CB_BATCH, @@ -8433,6 +8483,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, + [NFT_MSG_DESTROYSET] = { + .call = nf_tables_delset, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_SET_MAX, + .policy = nft_set_policy, + }, [NFT_MSG_NEWSETELEM] = { .call = nf_tables_newsetelem, .type = NFNL_CB_BATCH, @@ -8451,6 +8507,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, + [NFT_MSG_DESTROYSETELEM] = { + .call = nf_tables_delsetelem, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_SET_ELEM_LIST_MAX, + .policy = nft_set_elem_list_policy, + }, [NFT_MSG_GETGEN] = { .call = nf_tables_getgen, .type = NFNL_CB_RCU, @@ -8473,6 +8535,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, + [NFT_MSG_DESTROYOBJ] = { + .call = nf_tables_delobj, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_OBJ_MAX, + .policy = nft_obj_policy, + }, [NFT_MSG_GETOBJ_RESET] = { .call = nf_tables_getobj, .type = NFNL_CB_RCU, @@ -8497,6 +8565,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, + [NFT_MSG_DESTROYFLOWTABLE] = { + .call = nf_tables_delflowtable, + .type = NFNL_CB_BATCH, + .attr_count = NFTA_FLOWTABLE_MAX, + .policy = nft_flowtable_policy, + }, }; static int nf_tables_validate(struct net *net) @@ -8590,6 +8664,7 @@ static void nft_commit_release(struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_DELTABLE: + case NFT_MSG_DESTROYTABLE: nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: @@ -8597,23 +8672,29 @@ static void nft_commit_release(struct nft_trans *trans) kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: + case NFT_MSG_DESTROYSET: nft_set_destroy(&trans->ctx, nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: + case NFT_MSG_DESTROYSETELEM: nf_tables_set_elem_destroy(&trans->ctx, nft_trans_elem_set(trans), nft_trans_elem(trans).priv); break; case NFT_MSG_DELOBJ: + case NFT_MSG_DESTROYOBJ: nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: + case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else @@ -9065,8 +9146,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELTABLE: + case NFT_MSG_DESTROYTABLE: list_del_rcu(&trans->ctx.table->list); - nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); + nf_tables_table_notify(&trans->ctx, trans->msg_type); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { @@ -9081,8 +9163,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } break; case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: nft_chain_del(trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN); + nf_tables_chain_notify(&trans->ctx, trans->msg_type); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, trans->ctx.chain); @@ -9098,10 +9181,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: list_del_rcu(&nft_trans_rule(trans)->list); nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), - NFT_MSG_DELRULE); + trans->msg_type); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); @@ -9129,9 +9213,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSET: + case NFT_MSG_DESTROYSET: list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), - NFT_MSG_DELSET, GFP_KERNEL); + trans->msg_type, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; @@ -9143,11 +9228,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: + case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_DELSETELEM); + trans->msg_type); nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) { atomic_dec(&te->set->nelems); @@ -9169,9 +9255,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } break; case NFT_MSG_DELOBJ: + case NFT_MSG_DESTROYOBJ: nft_obj_del(nft_trans_obj(trans)); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), - NFT_MSG_DELOBJ); + trans->msg_type); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { @@ -9193,11 +9280,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELFLOWTABLE: + case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), - NFT_MSG_DELFLOWTABLE); + trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { @@ -9205,7 +9293,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list, - NFT_MSG_DELFLOWTABLE); + trans->msg_type); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); } @@ -9301,6 +9389,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELTABLE: + case NFT_MSG_DESTROYTABLE: nft_clear(trans->ctx.net, trans->ctx.table); nft_trans_destroy(trans); break; @@ -9322,6 +9411,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELCHAIN: + case NFT_MSG_DESTROYCHAIN: trans->ctx.table->use++; nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); @@ -9336,6 +9426,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: + case NFT_MSG_DESTROYRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); @@ -9357,6 +9448,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: + case NFT_MSG_DESTROYSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); nft_trans_destroy(trans); @@ -9372,6 +9464,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) atomic_dec(&te->set->nelems); break; case NFT_MSG_DELSETELEM: + case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; nft_setelem_data_activate(net, te->set, &te->elem); @@ -9391,6 +9484,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELOBJ: + case NFT_MSG_DESTROYOBJ: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); @@ -9407,6 +9501,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELFLOWTABLE: + case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 709a736c301c..6ecd0ba2e546 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -21,6 +21,26 @@ #include <net/netfilter/nf_log.h> #include <net/netfilter/nft_meta.h> +#if defined(CONFIG_RETPOLINE) && defined(CONFIG_X86) + +static struct static_key_false nf_tables_skip_direct_calls; + +static bool nf_skip_indirect_calls(void) +{ + return static_branch_likely(&nf_tables_skip_direct_calls); +} + +static void __init nf_skip_indirect_calls_enable(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_RETPOLINE)) + static_branch_enable(&nf_tables_skip_direct_calls); +} +#else +static inline bool nf_skip_indirect_calls(void) { return false; } + +static inline void nf_skip_indirect_calls_enable(void) { } +#endif + static noinline void __nft_trace_packet(struct nft_traceinfo *info, const struct nft_chain *chain, enum nft_trace_types type) @@ -193,7 +213,12 @@ static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_pktinfo *pkt) { #ifdef CONFIG_RETPOLINE - unsigned long e = (unsigned long)expr->ops->eval; + unsigned long e; + + if (nf_skip_indirect_calls()) + goto indirect_call; + + e = (unsigned long)expr->ops->eval; #define X(e, fun) \ do { if ((e) == (unsigned long)(fun)) \ return fun(expr, regs, pkt); } while (0) @@ -203,13 +228,19 @@ static void expr_call_ops_eval(const struct nft_expr *expr, X(e, nft_counter_eval); X(e, nft_meta_get_eval); X(e, nft_lookup_eval); +#if IS_ENABLED(CONFIG_NFT_CT) + X(e, nft_ct_get_fast_eval); +#endif X(e, nft_range_eval); X(e, nft_immediate_eval); X(e, nft_byteorder_eval); X(e, nft_dynset_eval); X(e, nft_rt_get_eval); X(e, nft_bitwise_eval); + X(e, nft_objref_eval); + X(e, nft_objref_map_eval); #undef X +indirect_call: #endif /* CONFIG_RETPOLINE */ expr->ops->eval(expr, regs, pkt); } @@ -369,6 +400,8 @@ int __init nf_tables_core_module_init(void) goto err; } + nf_skip_indirect_calls_enable(); + return 0; err: diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index c68e2151defe..b9c84499438b 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -12,7 +12,7 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_tuple.h> @@ -23,16 +23,6 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> -struct nft_ct { - enum nft_ct_keys key:8; - enum ip_conntrack_dir dir:8; - u8 len; - union { - u8 dreg; - u8 sreg; - }; -}; - struct nft_ct_helper_obj { struct nf_conntrack_helper *helper4; struct nf_conntrack_helper *helper6; @@ -759,6 +749,18 @@ static bool nft_ct_set_reduce(struct nft_regs_track *track, return false; } +#ifdef CONFIG_RETPOLINE +static const struct nft_expr_ops nft_ct_get_fast_ops = { + .type = &nft_ct_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), + .eval = nft_ct_get_fast_eval, + .init = nft_ct_get_init, + .destroy = nft_ct_get_destroy, + .dump = nft_ct_get_dump, + .reduce = nft_ct_set_reduce, +}; +#endif + static const struct nft_expr_ops nft_ct_set_ops = { .type = &nft_ct_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), @@ -791,8 +793,21 @@ nft_ct_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_CT_DREG] && tb[NFTA_CT_SREG]) return ERR_PTR(-EINVAL); - if (tb[NFTA_CT_DREG]) + if (tb[NFTA_CT_DREG]) { +#ifdef CONFIG_RETPOLINE + u32 k = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); + + switch (k) { + case NFT_CT_STATE: + case NFT_CT_DIRECTION: + case NFT_CT_STATUS: + case NFT_CT_MARK: + case NFT_CT_SECMARK: + return &nft_ct_get_fast_ops; + } +#endif return &nft_ct_get_ops; + } if (tb[NFTA_CT_SREG]) { #ifdef CONFIG_NF_CONNTRACK_ZONES diff --git a/net/netfilter/nft_ct_fast.c b/net/netfilter/nft_ct_fast.c new file mode 100644 index 000000000000..89983b0613fa --- /dev/null +++ b/net/netfilter/nft_ct_fast.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +#if IS_ENABLED(CONFIG_NFT_CT) +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_conntrack.h> + +void nft_ct_get_fast_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_ct *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + unsigned int state; + + ct = nf_ct_get(pkt->skb, &ctinfo); + if (!ct) { + regs->verdict.code = NFT_BREAK; + return; + } + + switch (priv->key) { + case NFT_CT_STATE: + if (ct) + state = NF_CT_STATE_BIT(ctinfo); + else if (ctinfo == IP_CT_UNTRACKED) + state = NF_CT_STATE_UNTRACKED_BIT; + else + state = NF_CT_STATE_INVALID_BIT; + *dest = state; + return; + case NFT_CT_DIRECTION: + nft_reg_store8(dest, CTINFO2DIR(ctinfo)); + return; + case NFT_CT_STATUS: + *dest = ct->status; + return; +#ifdef CONFIG_NF_CONNTRACK_MARK + case NFT_CT_MARK: + *dest = ct->mark; + return; +#endif +#ifdef CONFIG_NF_CONNTRACK_SECMARK + case NFT_CT_SECMARK: + *dest = ct->secmark; + return; +#endif + default: + WARN_ON_ONCE(1); + regs->verdict.code = NFT_BREAK; + break; + } +} +EXPORT_SYMBOL_GPL(nft_ct_get_fast_eval); +#endif diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 7b01aa2ef653..cb37169608ba 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -13,9 +13,9 @@ #define nft_objref_priv(expr) *((struct nft_object **)nft_expr_priv(expr)) -static void nft_objref_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_objref_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { struct nft_object *obj = nft_objref_priv(expr); @@ -100,9 +100,9 @@ struct nft_objref_map { struct nft_set_binding binding; }; -static void nft_objref_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_objref_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { struct nft_objref_map *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 5b3c0ac495be..cd09ef49df22 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1582,7 +1582,7 @@ errout: static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], u32 portid, u32 seq, u16 flags, int event, int bind, - int ref) + int ref, struct netlink_ext_ack *extack) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -1606,7 +1606,12 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], nla_nest_end(skb, nest); + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1625,7 +1630,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, - 0, 1) <= 0) { + 0, 1, NULL) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; @@ -1799,7 +1804,7 @@ tcf_reoffload_del_notify(struct net *net, struct tc_action *action) if (!skb) return -ENOBUFS; - if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1) <= 0) { + if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1, NULL) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1886,7 +1891,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, - 0, 2) <= 0) { + 0, 2, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); return -EINVAL; @@ -1965,7 +1970,7 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, - RTM_NEWACTION, 0, 0) <= 0) { + RTM_NEWACTION, 0, 0, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 668130f08903..5b4a95e8a1ee 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -488,7 +488,8 @@ static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block, #endif static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, - u32 seq, u16 flags, int event, bool unicast); + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack); static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create, @@ -521,7 +522,7 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, */ if (is_first_reference && !by_act) tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + RTM_NEWCHAIN, false, NULL); return chain; @@ -1817,7 +1818,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, u32 portid, u32 seq, u16 flags, int event, - bool terse_dump, bool rtnl_held) + bool terse_dump, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1857,7 +1859,13 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) goto nla_put_failure; } + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto nla_put_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1871,7 +1879,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, int event, bool unicast, - bool rtnl_held) + bool rtnl_held, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1883,7 +1891,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event, - false, rtnl_held) <= 0) { + false, rtnl_held, extack) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1912,7 +1920,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER, - false, rtnl_held) <= 0) { + false, rtnl_held, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); kfree_skb(skb); return -EINVAL; @@ -1938,14 +1946,15 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct tcf_block *block, struct Qdisc *q, u32 parent, struct nlmsghdr *n, - struct tcf_chain *chain, int event) + struct tcf_chain *chain, int event, + struct netlink_ext_ack *extack) { struct tcf_proto *tp; for (tp = tcf_get_next_proto(chain, NULL); tp; tp = tcf_get_next_proto(chain, tp)) - tfilter_notify(net, oskb, n, tp, block, - q, parent, NULL, event, false, true); + tfilter_notify(net, oskb, n, tp, block, q, parent, NULL, + event, false, true, extack); } static void tfilter_put(struct tcf_proto *tp, void *fh) @@ -2156,7 +2165,7 @@ replay: flags, extack); if (err == 0) { tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_NEWTFILTER, false, rtnl_held); + RTM_NEWTFILTER, false, rtnl_held, extack); tfilter_put(tp, fh); /* q pointer is NULL for shared blocks */ if (q) @@ -2284,7 +2293,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (prio == 0) { tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, extack); tcf_chain_flush(chain, rtnl_held); err = 0; goto errout; @@ -2308,7 +2317,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, tcf_proto_put(tp, rtnl_held, NULL); tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_DELTFILTER, false, rtnl_held); + RTM_DELTFILTER, false, rtnl_held, extack); err = 0; goto errout; } @@ -2452,7 +2461,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -ENOENT; } else { err = tfilter_notify(net, skb, n, tp, block, q, parent, - fh, RTM_NEWTFILTER, true, rtnl_held); + fh, RTM_NEWTFILTER, true, rtnl_held, NULL); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); } @@ -2490,7 +2499,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER, a->terse_dump, true); + RTM_NEWTFILTER, a->terse_dump, true, NULL); } static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, @@ -2524,7 +2533,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER, false, true) <= 0) + RTM_NEWTFILTER, false, true, NULL) <= 0) goto errout; cb->args[1] = 1; } @@ -2667,7 +2676,8 @@ static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, void *tmplt_priv, u32 chain_index, struct net *net, struct sk_buff *skb, struct tcf_block *block, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) { unsigned char *b = skb_tail_pointer(skb); const struct tcf_proto_ops *ops; @@ -2704,7 +2714,12 @@ static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, goto nla_put_failure; } + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -2714,7 +2729,8 @@ nla_put_failure: } static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, - u32 seq, u16 flags, int event, bool unicast) + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct tcf_block *block = chain->block; @@ -2728,7 +2744,7 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, chain->index, net, skb, block, portid, - seq, flags, event) <= 0) { + seq, flags, event, extack) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -2756,7 +2772,7 @@ static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, return -ENOBUFS; if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb, - block, portid, seq, flags, RTM_DELCHAIN) <= 0) { + block, portid, seq, flags, RTM_DELCHAIN, NULL) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -2908,11 +2924,11 @@ replay: } tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + RTM_NEWCHAIN, false, extack); break; case RTM_DELCHAIN: tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, extack); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain, true); /* In case the chain was successfully deleted, put a reference @@ -2922,7 +2938,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_flags, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true, extack); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; @@ -3022,7 +3038,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) chain->index, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWCHAIN); + RTM_NEWCHAIN, NULL); if (err <= 0) break; index++; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 72d2c204d5f3..c14018a8052c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -902,7 +902,8 @@ static void qdisc_offload_graft_root(struct net_device *dev, } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) { struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; @@ -970,7 +971,12 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -991,7 +997,8 @@ static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) static int qdisc_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new) + struct Qdisc *old, struct Qdisc *new, + struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1002,12 +1009,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, - 0, RTM_DELQDISC) < 0) + 0, RTM_DELQDISC, extack) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, - old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) + old ? NLM_F_REPLACE : 0, RTM_NEWQDISC, extack) < 0) goto err_out; } @@ -1022,10 +1029,11 @@ err_out: static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, - struct Qdisc *old, struct Qdisc *new) + struct Qdisc *old, struct Qdisc *new, + struct netlink_ext_ack *extack) { if (new || old) - qdisc_notify(net, skb, n, clid, old, new); + qdisc_notify(net, skb, n, clid, old, new, extack); if (old) qdisc_put(old); @@ -1105,12 +1113,12 @@ skip: qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); - notify_and_destroy(net, skb, n, classid, old, new); + notify_and_destroy(net, skb, n, classid, old, new, extack); if (new && new->ops->attach) new->ops->attach(new); } else { - notify_and_destroy(net, skb, n, classid, old, new); + notify_and_destroy(net, skb, n, classid, old, new, extack); } if (dev->flags & IFF_UP) @@ -1141,7 +1149,7 @@ skip: err = cops->graft(parent, cl, new, &old, extack); if (err) return err; - notify_and_destroy(net, skb, n, classid, old, new); + notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; } @@ -1509,7 +1517,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, if (err != 0) return err; } else { - qdisc_notify(net, skb, n, clid, NULL, q); + qdisc_notify(net, skb, n, clid, NULL, q, NULL); } return 0; } @@ -1648,7 +1656,7 @@ replay: } err = qdisc_change(q, tca, extack); if (err == 0) - qdisc_notify(net, skb, n, clid, NULL, q); + qdisc_notify(net, skb, n, clid, NULL, q, extack); return err; create_n_graft: @@ -1715,7 +1723,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWQDISC) <= 0) + RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } @@ -1737,7 +1745,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWQDISC) <= 0) + RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } @@ -1810,8 +1818,8 @@ done: ************************************************/ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, - unsigned long cl, - u32 portid, u32 seq, u16 flags, int event) + unsigned long cl, u32 portid, u32 seq, u16 flags, + int event, struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1846,7 +1854,12 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1857,7 +1870,7 @@ nla_put_failure: static int tclass_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, - unsigned long cl, int event) + unsigned long cl, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1866,7 +1879,7 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) { + if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event, extack) < 0) { kfree_skb(skb); return -EINVAL; } @@ -1893,7 +1906,7 @@ static int tclass_del_notify(struct net *net, return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, - RTM_DELTCLASS) < 0) { + RTM_DELTCLASS, extack) < 0) { kfree_skb(skb); return -EINVAL; } @@ -2100,7 +2113,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, tc_bind_tclass(q, portid, clid, 0); goto out; case RTM_GETTCLASS: - err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS); + err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS, extack); goto out; default: err = -EINVAL; @@ -2118,7 +2131,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, if (cops->change) err = cops->change(q, clid, portid, tca, &new_cl, extack); if (err == 0) { - tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS); + tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS, extack); /* We just create a new class, need to do reverse binding. */ if (cl != new_cl) tc_bind_tclass(q, portid, clid, new_cl); @@ -2140,7 +2153,7 @@ static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTCLASS); + RTM_NEWTCLASS, NULL); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, diff --git a/net/socket.c b/net/socket.c index 888cd618a968..77626e4d9690 100644 --- a/net/socket.c +++ b/net/socket.c @@ -106,6 +106,7 @@ #include <net/busy_poll.h> #include <linux/errqueue.h> #include <linux/ptp_clock_kernel.h> +#include <trace/events/sock.h> #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -709,12 +710,22 @@ INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, size_t)); INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, size_t)); + +static noinline void call_trace_sock_send_length(struct sock *sk, int ret, + int flags) +{ + trace_sock_send_length(sk, ret, 0); +} + static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg, inet_sendmsg, sock, msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); + + if (trace_sock_send_length_enabled()) + call_trace_sock_send_length(sock->sk, ret, 0); return ret; } @@ -989,12 +1000,21 @@ INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, size_t, int)); INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, size_t, int)); + +static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int flags) +{ + trace_sock_recv_length(sk, ret, flags); +} + static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { - return INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg, - inet_recvmsg, sock, msg, msg_data_left(msg), - flags); + int ret = INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg, + inet_recvmsg, sock, msg, + msg_data_left(msg), flags); + if (trace_sock_recv_length_enabled()) + call_trace_sock_recv_length(sock->sk, ret, flags); + return ret; } /** @@ -1044,6 +1064,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, { struct socket *sock; int flags; + int ret; sock = file->private_data; @@ -1051,7 +1072,11 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */ flags |= more; - return kernel_sendpage(sock, page, offset, size, flags); + ret = kernel_sendpage(sock, page, offset, size, flags); + + if (trace_sock_send_length_enabled()) + call_trace_sock_send_length(sock->sk, ret, 0); + return ret; } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f0c2293f1d3b..009616fa0256 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -807,23 +807,23 @@ static int unix_count_nr_fds(struct sock *sk) static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; + unsigned char s_state; struct unix_sock *u; - int nr_fds; + int nr_fds = 0; if (sk) { + s_state = READ_ONCE(sk->sk_state); u = unix_sk(sk); - if (sock->type == SOCK_DGRAM) { - nr_fds = atomic_read(&u->scm_stat.nr_fds); - goto out_print; - } - unix_state_lock(sk); - if (sk->sk_state != TCP_LISTEN) + /* SOCK_STREAM and SOCK_SEQPACKET sockets never change their + * sk_state after switching to TCP_ESTABLISHED or TCP_LISTEN. + * SOCK_DGRAM is ordinary. So, no lock is needed. + */ + if (sock->type == SOCK_DGRAM || s_state == TCP_ESTABLISHED) nr_fds = atomic_read(&u->scm_stat.nr_fds); - else + else if (s_state == TCP_LISTEN) nr_fds = unix_count_nr_fds(sk); - unix_state_unlock(sk); -out_print: + seq_printf(m, "scm_fds: %u\n", nr_fds); } } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index d593d5b6d4b1..19aea7cba26e 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1861,8 +1861,9 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, written = transport->stream_enqueue(vsk, msg, len - total_written); } + if (written < 0) { - err = -ENOMEM; + err = written; goto out_err; } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index ad64f403536a..28b5a8e8e094 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -42,8 +42,7 @@ struct virtio_vsock { bool tx_run; struct work_struct send_pkt_work; - spinlock_t send_pkt_list_lock; - struct list_head send_pkt_list; + struct sk_buff_head send_pkt_queue; atomic_t queued_replies; @@ -101,41 +100,31 @@ virtio_transport_send_pkt_work(struct work_struct *work) vq = vsock->vqs[VSOCK_VQ_TX]; for (;;) { - struct virtio_vsock_pkt *pkt; struct scatterlist hdr, buf, *sgs[2]; int ret, in_sg = 0, out_sg = 0; + struct sk_buff *skb; bool reply; - spin_lock_bh(&vsock->send_pkt_list_lock); - if (list_empty(&vsock->send_pkt_list)) { - spin_unlock_bh(&vsock->send_pkt_list_lock); + skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); + if (!skb) break; - } - - pkt = list_first_entry(&vsock->send_pkt_list, - struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - spin_unlock_bh(&vsock->send_pkt_list_lock); - virtio_transport_deliver_tap_pkt(pkt); + virtio_transport_deliver_tap_pkt(skb); + reply = virtio_vsock_skb_reply(skb); - reply = pkt->reply; - - sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); + sg_init_one(&hdr, virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb))); sgs[out_sg++] = &hdr; - if (pkt->buf) { - sg_init_one(&buf, pkt->buf, pkt->len); + if (skb->len > 0) { + sg_init_one(&buf, skb->data, skb->len); sgs[out_sg++] = &buf; } - ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL); + ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL); /* Usually this means that there is no more space available in * the vq */ if (ret < 0) { - spin_lock_bh(&vsock->send_pkt_list_lock); - list_add(&pkt->list, &vsock->send_pkt_list); - spin_unlock_bh(&vsock->send_pkt_list_lock); + virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } @@ -164,32 +153,32 @@ out: } static int -virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) +virtio_transport_send_pkt(struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr; struct virtio_vsock *vsock; - int len = pkt->len; + int len = skb->len; + + hdr = virtio_vsock_hdr(skb); rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); if (!vsock) { - virtio_transport_free_pkt(pkt); + kfree_skb(skb); len = -ENODEV; goto out_rcu; } - if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) { - virtio_transport_free_pkt(pkt); + if (le64_to_cpu(hdr->dst_cid) == vsock->guest_cid) { + kfree_skb(skb); len = -ENODEV; goto out_rcu; } - if (pkt->reply) + if (virtio_vsock_skb_reply(skb)) atomic_inc(&vsock->queued_replies); - spin_lock_bh(&vsock->send_pkt_list_lock); - list_add_tail(&pkt->list, &vsock->send_pkt_list); - spin_unlock_bh(&vsock->send_pkt_list_lock); - + virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); out_rcu: @@ -201,9 +190,7 @@ static int virtio_transport_cancel_pkt(struct vsock_sock *vsk) { struct virtio_vsock *vsock; - struct virtio_vsock_pkt *pkt, *n; int cnt = 0, ret; - LIST_HEAD(freeme); rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); @@ -212,20 +199,7 @@ virtio_transport_cancel_pkt(struct vsock_sock *vsk) goto out_rcu; } - spin_lock_bh(&vsock->send_pkt_list_lock); - list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) { - if (pkt->vsk != vsk) - continue; - list_move(&pkt->list, &freeme); - } - spin_unlock_bh(&vsock->send_pkt_list_lock); - - list_for_each_entry_safe(pkt, n, &freeme, list) { - if (pkt->reply) - cnt++; - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } + cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue); if (cnt) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; @@ -246,38 +220,28 @@ out_rcu: static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) { - int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; - struct virtio_vsock_pkt *pkt; - struct scatterlist hdr, buf, *sgs[2]; + int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM; + struct scatterlist pkt, *p; struct virtqueue *vq; + struct sk_buff *skb; int ret; vq = vsock->vqs[VSOCK_VQ_RX]; do { - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) + skb = virtio_vsock_alloc_skb(total_len, GFP_KERNEL); + if (!skb) break; - pkt->buf = kmalloc(buf_len, GFP_KERNEL); - if (!pkt->buf) { - virtio_transport_free_pkt(pkt); + memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM); + sg_init_one(&pkt, virtio_vsock_hdr(skb), total_len); + p = &pkt; + ret = virtqueue_add_sgs(vq, &p, 0, 1, skb, GFP_KERNEL); + if (ret < 0) { + kfree_skb(skb); break; } - pkt->buf_len = buf_len; - pkt->len = buf_len; - - sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); - sgs[0] = &hdr; - - sg_init_one(&buf, pkt->buf, buf_len); - sgs[1] = &buf; - ret = virtqueue_add_sgs(vq, sgs, 0, 2, pkt, GFP_KERNEL); - if (ret) { - virtio_transport_free_pkt(pkt); - break; - } vsock->rx_buf_nr++; } while (vq->num_free); if (vsock->rx_buf_nr > vsock->rx_buf_max_nr) @@ -299,12 +263,12 @@ static void virtio_transport_tx_work(struct work_struct *work) goto out; do { - struct virtio_vsock_pkt *pkt; + struct sk_buff *skb; unsigned int len; virtqueue_disable_cb(vq); - while ((pkt = virtqueue_get_buf(vq, &len)) != NULL) { - virtio_transport_free_pkt(pkt); + while ((skb = virtqueue_get_buf(vq, &len)) != NULL) { + consume_skb(skb); added = true; } } while (!virtqueue_enable_cb(vq)); @@ -529,7 +493,7 @@ static void virtio_transport_rx_work(struct work_struct *work) do { virtqueue_disable_cb(vq); for (;;) { - struct virtio_vsock_pkt *pkt; + struct sk_buff *skb; unsigned int len; if (!virtio_transport_more_replies(vsock)) { @@ -540,23 +504,22 @@ static void virtio_transport_rx_work(struct work_struct *work) goto out; } - pkt = virtqueue_get_buf(vq, &len); - if (!pkt) { + skb = virtqueue_get_buf(vq, &len); + if (!skb) break; - } vsock->rx_buf_nr--; /* Drop short/long packets */ - if (unlikely(len < sizeof(pkt->hdr) || - len > sizeof(pkt->hdr) + pkt->len)) { - virtio_transport_free_pkt(pkt); + if (unlikely(len < sizeof(struct virtio_vsock_hdr) || + len > virtio_vsock_skb_len(skb))) { + kfree_skb(skb); continue; } - pkt->len = len - sizeof(pkt->hdr); - virtio_transport_deliver_tap_pkt(pkt); - virtio_transport_recv_pkt(&virtio_transport, pkt); + virtio_vsock_skb_rx_put(skb); + virtio_transport_deliver_tap_pkt(skb); + virtio_transport_recv_pkt(&virtio_transport, skb); } } while (!virtqueue_enable_cb(vq)); @@ -610,7 +573,7 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) static void virtio_vsock_vqs_del(struct virtio_vsock *vsock) { struct virtio_device *vdev = vsock->vdev; - struct virtio_vsock_pkt *pkt; + struct sk_buff *skb; /* Reset all connected sockets when the VQs disappear */ vsock_for_each_connected_socket(&virtio_transport.transport, @@ -637,23 +600,16 @@ static void virtio_vsock_vqs_del(struct virtio_vsock *vsock) virtio_reset_device(vdev); mutex_lock(&vsock->rx_lock); - while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) - virtio_transport_free_pkt(pkt); + while ((skb = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) + kfree_skb(skb); mutex_unlock(&vsock->rx_lock); mutex_lock(&vsock->tx_lock); - while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX]))) - virtio_transport_free_pkt(pkt); + while ((skb = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX]))) + kfree_skb(skb); mutex_unlock(&vsock->tx_lock); - spin_lock_bh(&vsock->send_pkt_list_lock); - while (!list_empty(&vsock->send_pkt_list)) { - pkt = list_first_entry(&vsock->send_pkt_list, - struct virtio_vsock_pkt, list); - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } - spin_unlock_bh(&vsock->send_pkt_list_lock); + virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue); /* Delete virtqueues and flush outstanding callbacks if any */ vdev->config->del_vqs(vdev); @@ -690,8 +646,7 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_init(&vsock->tx_lock); mutex_init(&vsock->rx_lock); mutex_init(&vsock->event_lock); - spin_lock_init(&vsock->send_pkt_list_lock); - INIT_LIST_HEAD(&vsock->send_pkt_list); + skb_queue_head_init(&vsock->send_pkt_queue); INIT_WORK(&vsock->rx_work, virtio_transport_rx_work); INIT_WORK(&vsock->tx_work, virtio_transport_tx_work); INIT_WORK(&vsock->event_work, virtio_transport_event_work); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a9980e9b9304..a1581c77cf84 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -37,53 +37,56 @@ virtio_transport_get_ops(struct vsock_sock *vsk) return container_of(t, struct virtio_transport, transport); } -static struct virtio_vsock_pkt * -virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, +/* Returns a new packet on success, otherwise returns NULL. + * + * If NULL is returned, errp is set to a negative errno. + */ +static struct sk_buff * +virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, size_t len, u32 src_cid, u32 src_port, u32 dst_cid, u32 dst_port) { - struct virtio_vsock_pkt *pkt; + const size_t skb_len = VIRTIO_VSOCK_SKB_HEADROOM + len; + struct virtio_vsock_hdr *hdr; + struct sk_buff *skb; + void *payload; int err; - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) + skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL); + if (!skb) return NULL; - pkt->hdr.type = cpu_to_le16(info->type); - pkt->hdr.op = cpu_to_le16(info->op); - pkt->hdr.src_cid = cpu_to_le64(src_cid); - pkt->hdr.dst_cid = cpu_to_le64(dst_cid); - pkt->hdr.src_port = cpu_to_le32(src_port); - pkt->hdr.dst_port = cpu_to_le32(dst_port); - pkt->hdr.flags = cpu_to_le32(info->flags); - pkt->len = len; - pkt->hdr.len = cpu_to_le32(len); - pkt->reply = info->reply; - pkt->vsk = info->vsk; + hdr = virtio_vsock_hdr(skb); + hdr->type = cpu_to_le16(info->type); + hdr->op = cpu_to_le16(info->op); + hdr->src_cid = cpu_to_le64(src_cid); + hdr->dst_cid = cpu_to_le64(dst_cid); + hdr->src_port = cpu_to_le32(src_port); + hdr->dst_port = cpu_to_le32(dst_port); + hdr->flags = cpu_to_le32(info->flags); + hdr->len = cpu_to_le32(len); if (info->msg && len > 0) { - pkt->buf = kmalloc(len, GFP_KERNEL); - if (!pkt->buf) - goto out_pkt; - - pkt->buf_len = len; - - err = memcpy_from_msg(pkt->buf, info->msg, len); + payload = skb_put(skb, len); + err = memcpy_from_msg(payload, info->msg, len); if (err) goto out; if (msg_data_left(info->msg) == 0 && info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) { - pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); + hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); if (info->msg->msg_flags & MSG_EOR) - pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } } + if (info->reply) + virtio_vsock_skb_set_reply(skb); + trace_virtio_transport_alloc_pkt(src_cid, src_port, dst_cid, dst_port, len, @@ -91,19 +94,18 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, info->op, info->flags); - return pkt; + return skb; out: - kfree(pkt->buf); -out_pkt: - kfree(pkt); + kfree_skb(skb); return NULL; } /* Packet capture */ static struct sk_buff *virtio_transport_build_skb(void *opaque) { - struct virtio_vsock_pkt *pkt = opaque; + struct virtio_vsock_hdr *pkt_hdr; + struct sk_buff *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; size_t payload_len; @@ -113,10 +115,11 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) * the payload length from the header and the buffer pointer taking * care of the offset in the original packet. */ - payload_len = le32_to_cpu(pkt->hdr.len); - payload_buf = pkt->buf + pkt->off; + pkt_hdr = virtio_vsock_hdr(pkt); + payload_len = pkt->len; + payload_buf = pkt->data; - skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len, + skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; @@ -124,16 +127,16 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) hdr = skb_put(skb, sizeof(*hdr)); /* pkt->hdr is little-endian so no need to byteswap here */ - hdr->src_cid = pkt->hdr.src_cid; - hdr->src_port = pkt->hdr.src_port; - hdr->dst_cid = pkt->hdr.dst_cid; - hdr->dst_port = pkt->hdr.dst_port; + hdr->src_cid = pkt_hdr->src_cid; + hdr->src_port = pkt_hdr->src_port; + hdr->dst_cid = pkt_hdr->dst_cid; + hdr->dst_port = pkt_hdr->dst_port; hdr->transport = cpu_to_le16(AF_VSOCK_TRANSPORT_VIRTIO); - hdr->len = cpu_to_le16(sizeof(pkt->hdr)); + hdr->len = cpu_to_le16(sizeof(*pkt_hdr)); memset(hdr->reserved, 0, sizeof(hdr->reserved)); - switch (le16_to_cpu(pkt->hdr.op)) { + switch (le16_to_cpu(pkt_hdr->op)) { case VIRTIO_VSOCK_OP_REQUEST: case VIRTIO_VSOCK_OP_RESPONSE: hdr->op = cpu_to_le16(AF_VSOCK_OP_CONNECT); @@ -154,7 +157,7 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) break; } - skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); + skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr)); if (payload_len) { skb_put_data(skb, payload_buf, payload_len); @@ -163,13 +166,13 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) return skb; } -void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) +void virtio_transport_deliver_tap_pkt(struct sk_buff *skb) { - if (pkt->tap_delivered) + if (virtio_vsock_skb_tap_delivered(skb)) return; - vsock_deliver_tap(virtio_transport_build_skb, pkt); - pkt->tap_delivered = true; + vsock_deliver_tap(virtio_transport_build_skb, skb); + virtio_vsock_skb_set_tap_delivered(skb); } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); @@ -192,8 +195,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, u32 src_cid, src_port, dst_cid, dst_port; const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; - struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; + struct sk_buff *skb; info->type = virtio_transport_get_type(sk_vsock(vsk)); @@ -224,42 +227,47 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) return pkt_len; - pkt = virtio_transport_alloc_pkt(info, pkt_len, + skb = virtio_transport_alloc_skb(info, pkt_len, src_cid, src_port, dst_cid, dst_port); - if (!pkt) { + if (!skb) { virtio_transport_put_credit(vvs, pkt_len); return -ENOMEM; } - virtio_transport_inc_tx_pkt(vvs, pkt); + virtio_transport_inc_tx_pkt(vvs, skb); - return t_ops->send_pkt(pkt); + return t_ops->send_pkt(skb); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { - if (vvs->rx_bytes + pkt->len > vvs->buf_alloc) + if (vvs->rx_bytes + skb->len > vvs->buf_alloc) return false; - vvs->rx_bytes += pkt->len; + vvs->rx_bytes += skb->len; return true; } static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { - vvs->rx_bytes -= pkt->len; - vvs->fwd_cnt += pkt->len; + int len; + + len = skb_headroom(skb) - sizeof(struct virtio_vsock_hdr) - skb->len; + vvs->rx_bytes -= len; + vvs->fwd_cnt += len; } -void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); + spin_lock_bh(&vvs->rx_lock); vvs->last_fwd_cnt = vvs->fwd_cnt; - pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); - pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); + hdr->fwd_cnt = cpu_to_le32(vvs->fwd_cnt); + hdr->buf_alloc = cpu_to_le32(vvs->buf_alloc); spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); @@ -303,29 +311,29 @@ virtio_transport_stream_do_peek(struct vsock_sock *vsk, size_t len) { struct virtio_vsock_sock *vvs = vsk->trans; - struct virtio_vsock_pkt *pkt; size_t bytes, total = 0, off; + struct sk_buff *skb, *tmp; int err = -EFAULT; spin_lock_bh(&vvs->rx_lock); - list_for_each_entry(pkt, &vvs->rx_queue, list) { - off = pkt->off; + skb_queue_walk_safe(&vvs->rx_queue, skb, tmp) { + off = 0; if (total == len) break; - while (total < len && off < pkt->len) { + while (total < len && off < skb->len) { bytes = len - total; - if (bytes > pkt->len - off) - bytes = pkt->len - off; + if (bytes > skb->len - off) + bytes = skb->len - off; /* sk_lock is held by caller so no one else can dequeue. * Unlock rx_lock since memcpy_to_msg() may sleep. */ spin_unlock_bh(&vvs->rx_lock); - err = memcpy_to_msg(msg, pkt->buf + off, bytes); + err = memcpy_to_msg(msg, skb->data + off, bytes); if (err) goto out; @@ -352,37 +360,38 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, size_t len) { struct virtio_vsock_sock *vvs = vsk->trans; - struct virtio_vsock_pkt *pkt; size_t bytes, total = 0; - u32 free_space; + struct sk_buff *skb; int err = -EFAULT; + u32 free_space; spin_lock_bh(&vvs->rx_lock); - while (total < len && !list_empty(&vvs->rx_queue)) { - pkt = list_first_entry(&vvs->rx_queue, - struct virtio_vsock_pkt, list); + while (total < len && !skb_queue_empty(&vvs->rx_queue)) { + skb = __skb_dequeue(&vvs->rx_queue); bytes = len - total; - if (bytes > pkt->len - pkt->off) - bytes = pkt->len - pkt->off; + if (bytes > skb->len) + bytes = skb->len; /* sk_lock is held by caller so no one else can dequeue. * Unlock rx_lock since memcpy_to_msg() may sleep. */ spin_unlock_bh(&vvs->rx_lock); - err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes); + err = memcpy_to_msg(msg, skb->data, bytes); if (err) goto out; spin_lock_bh(&vvs->rx_lock); total += bytes; - pkt->off += bytes; - if (pkt->off == pkt->len) { - virtio_transport_dec_rx_pkt(vvs, pkt); - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); + skb_pull(skb, bytes); + + if (skb->len == 0) { + virtio_transport_dec_rx_pkt(vvs, skb); + consume_skb(skb); + } else { + __skb_queue_head(&vvs->rx_queue, skb); } } @@ -414,10 +423,10 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, int flags) { struct virtio_vsock_sock *vvs = vsk->trans; - struct virtio_vsock_pkt *pkt; int dequeued_len = 0; size_t user_buf_len = msg_data_left(msg); bool msg_ready = false; + struct sk_buff *skb; spin_lock_bh(&vvs->rx_lock); @@ -427,13 +436,18 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, } while (!msg_ready) { - pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); + struct virtio_vsock_hdr *hdr; + + skb = __skb_dequeue(&vvs->rx_queue); + if (!skb) + break; + hdr = virtio_vsock_hdr(skb); if (dequeued_len >= 0) { size_t pkt_len; size_t bytes_to_copy; - pkt_len = (size_t)le32_to_cpu(pkt->hdr.len); + pkt_len = (size_t)le32_to_cpu(hdr->len); bytes_to_copy = min(user_buf_len, pkt_len); if (bytes_to_copy) { @@ -444,7 +458,7 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, */ spin_unlock_bh(&vvs->rx_lock); - err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); + err = memcpy_to_msg(msg, skb->data, bytes_to_copy); if (err) { /* Copy of message failed. Rest of * fragments will be freed without copy. @@ -452,6 +466,7 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, dequeued_len = err; } else { user_buf_len -= bytes_to_copy; + skb_pull(skb, bytes_to_copy); } spin_lock_bh(&vvs->rx_lock); @@ -461,17 +476,16 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, dequeued_len += pkt_len; } - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) { + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { msg_ready = true; vvs->msg_count--; - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) msg->msg_flags |= MSG_EOR; } - virtio_transport_dec_rx_pkt(vvs, pkt); - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); + virtio_transport_dec_rx_pkt(vvs, skb); + kfree_skb(skb); } spin_unlock_bh(&vvs->rx_lock); @@ -609,7 +623,7 @@ int virtio_transport_do_socket_init(struct vsock_sock *vsk, spin_lock_init(&vvs->rx_lock); spin_lock_init(&vvs->tx_lock); - INIT_LIST_HEAD(&vvs->rx_queue); + skb_queue_head_init(&vvs->rx_queue); return 0; } @@ -806,16 +820,16 @@ void virtio_transport_destruct(struct vsock_sock *vsk) EXPORT_SYMBOL_GPL(virtio_transport_destruct); static int virtio_transport_reset(struct vsock_sock *vsk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, - .reply = !!pkt, + .reply = !!skb, .vsk = vsk, }; /* Send RST only if the original pkt is not a RST pkt */ - if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + if (skb && le16_to_cpu(virtio_vsock_hdr(skb)->op) == VIRTIO_VSOCK_OP_RST) return 0; return virtio_transport_send_pkt_info(vsk, &info); @@ -825,29 +839,30 @@ static int virtio_transport_reset(struct vsock_sock *vsk, * attempt was made to connect to a socket that does not exist. */ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { - struct virtio_vsock_pkt *reply; + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, - .type = le16_to_cpu(pkt->hdr.type), + .type = le16_to_cpu(hdr->type), .reply = true, }; + struct sk_buff *reply; /* Send RST only if the original pkt is not a RST pkt */ - if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + if (le16_to_cpu(hdr->op) == VIRTIO_VSOCK_OP_RST) return 0; - reply = virtio_transport_alloc_pkt(&info, 0, - le64_to_cpu(pkt->hdr.dst_cid), - le32_to_cpu(pkt->hdr.dst_port), - le64_to_cpu(pkt->hdr.src_cid), - le32_to_cpu(pkt->hdr.src_port)); + reply = virtio_transport_alloc_skb(&info, 0, + le64_to_cpu(hdr->dst_cid), + le32_to_cpu(hdr->dst_port), + le64_to_cpu(hdr->src_cid), + le32_to_cpu(hdr->src_port)); if (!reply) return -ENOMEM; if (!t) { - virtio_transport_free_pkt(reply); + kfree_skb(reply); return -ENOTCONN; } @@ -858,16 +873,11 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, static void virtio_transport_remove_sock(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; - struct virtio_vsock_pkt *pkt, *tmp; /* We don't need to take rx_lock, as the socket is closing and we are * removing it. */ - list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) { - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } - + __skb_queue_purge(&vvs->rx_queue); vsock_remove_sock(vsk); } @@ -981,13 +991,14 @@ EXPORT_SYMBOL_GPL(virtio_transport_release); static int virtio_transport_recv_connecting(struct sock *sk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); - int err; int skerr; + int err; - switch (le16_to_cpu(pkt->hdr.op)) { + switch (le16_to_cpu(hdr->op)) { case VIRTIO_VSOCK_OP_RESPONSE: sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; @@ -1008,7 +1019,7 @@ virtio_transport_recv_connecting(struct sock *sk, return 0; destroy: - virtio_transport_reset(vsk, pkt); + virtio_transport_reset(vsk, skb); sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; sk_error_report(sk); @@ -1017,34 +1028,37 @@ destroy: static void virtio_transport_recv_enqueue(struct vsock_sock *vsk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { struct virtio_vsock_sock *vvs = vsk->trans; bool can_enqueue, free_pkt = false; + struct virtio_vsock_hdr *hdr; + u32 len; - pkt->len = le32_to_cpu(pkt->hdr.len); - pkt->off = 0; + hdr = virtio_vsock_hdr(skb); + len = le32_to_cpu(hdr->len); spin_lock_bh(&vvs->rx_lock); - can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt); + can_enqueue = virtio_transport_inc_rx_pkt(vvs, skb); if (!can_enqueue) { free_pkt = true; goto out; } - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) vvs->msg_count++; /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small * payload. */ - if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) { - struct virtio_vsock_pkt *last_pkt; + if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue)) { + struct virtio_vsock_hdr *last_hdr; + struct sk_buff *last_skb; - last_pkt = list_last_entry(&vvs->rx_queue, - struct virtio_vsock_pkt, list); + last_skb = skb_peek_tail(&vvs->rx_queue); + last_hdr = virtio_vsock_hdr(last_skb); /* If there is space in the last packet queued, we copy the * new packet in its buffer. We avoid this if the last packet @@ -1052,35 +1066,35 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, * delimiter of SEQPACKET message, so 'pkt' is the first packet * of a new message. */ - if ((pkt->len <= last_pkt->buf_len - last_pkt->len) && - !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM)) { - memcpy(last_pkt->buf + last_pkt->len, pkt->buf, - pkt->len); - last_pkt->len += pkt->len; + if (skb->len < skb_tailroom(last_skb) && + !(le32_to_cpu(last_hdr->flags) & VIRTIO_VSOCK_SEQ_EOM)) { + memcpy(skb_put(last_skb, skb->len), skb->data, skb->len); free_pkt = true; - last_pkt->hdr.flags |= pkt->hdr.flags; + last_hdr->flags |= hdr->flags; + last_hdr->len = cpu_to_le32(last_skb->len); goto out; } } - list_add_tail(&pkt->list, &vvs->rx_queue); + __skb_queue_tail(&vvs->rx_queue, skb); out: spin_unlock_bh(&vvs->rx_lock); if (free_pkt) - virtio_transport_free_pkt(pkt); + kfree_skb(skb); } static int virtio_transport_recv_connected(struct sock *sk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); int err = 0; - switch (le16_to_cpu(pkt->hdr.op)) { + switch (le16_to_cpu(hdr->op)) { case VIRTIO_VSOCK_OP_RW: - virtio_transport_recv_enqueue(vsk, pkt); + virtio_transport_recv_enqueue(vsk, skb); vsock_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_REQUEST: @@ -1090,18 +1104,17 @@ virtio_transport_recv_connected(struct sock *sk, sk->sk_write_space(sk); break; case VIRTIO_VSOCK_OP_SHUTDOWN: - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV) + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SHUTDOWN_RCV) vsk->peer_shutdown |= RCV_SHUTDOWN; - if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && vsock_stream_has_data(vsk) <= 0 && !sock_flag(sk, SOCK_DONE)) { (void)virtio_transport_reset(vsk, NULL); - virtio_transport_do_close(vsk, true); } - if (le32_to_cpu(pkt->hdr.flags)) + if (le32_to_cpu(virtio_vsock_hdr(skb)->flags)) sk->sk_state_change(sk); break; case VIRTIO_VSOCK_OP_RST: @@ -1112,28 +1125,30 @@ virtio_transport_recv_connected(struct sock *sk, break; } - virtio_transport_free_pkt(pkt); + kfree_skb(skb); return err; } static void virtio_transport_recv_disconnecting(struct sock *sk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); - if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + if (le16_to_cpu(hdr->op) == VIRTIO_VSOCK_OP_RST) virtio_transport_do_close(vsk, true); } static int virtio_transport_send_response(struct vsock_sock *vsk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RESPONSE, - .remote_cid = le64_to_cpu(pkt->hdr.src_cid), - .remote_port = le32_to_cpu(pkt->hdr.src_port), + .remote_cid = le64_to_cpu(hdr->src_cid), + .remote_port = le32_to_cpu(hdr->src_port), .reply = true, .vsk = vsk, }; @@ -1142,8 +1157,9 @@ virtio_transport_send_response(struct vsock_sock *vsk, } static bool virtio_transport_space_update(struct sock *sk, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); struct virtio_vsock_sock *vvs = vsk->trans; bool space_available; @@ -1158,8 +1174,8 @@ static bool virtio_transport_space_update(struct sock *sk, /* buf_alloc and fwd_cnt is always included in the hdr */ spin_lock_bh(&vvs->tx_lock); - vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc); - vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt); + vvs->peer_buf_alloc = le32_to_cpu(hdr->buf_alloc); + vvs->peer_fwd_cnt = le32_to_cpu(hdr->fwd_cnt); space_available = virtio_transport_has_space(vsk); spin_unlock_bh(&vvs->tx_lock); return space_available; @@ -1167,27 +1183,28 @@ static bool virtio_transport_space_update(struct sock *sk, /* Handle server socket */ static int -virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, +virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, struct virtio_transport *t) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); struct vsock_sock *vchild; struct sock *child; int ret; - if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset_no_sock(t, pkt); + if (le16_to_cpu(hdr->op) != VIRTIO_VSOCK_OP_REQUEST) { + virtio_transport_reset_no_sock(t, skb); return -EINVAL; } if (sk_acceptq_is_full(sk)) { - virtio_transport_reset_no_sock(t, pkt); + virtio_transport_reset_no_sock(t, skb); return -ENOMEM; } child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset_no_sock(t, pkt); + virtio_transport_reset_no_sock(t, skb); return -ENOMEM; } @@ -1198,10 +1215,10 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, child->sk_state = TCP_ESTABLISHED; vchild = vsock_sk(child); - vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid), - le32_to_cpu(pkt->hdr.dst_port)); - vsock_addr_init(&vchild->remote_addr, le64_to_cpu(pkt->hdr.src_cid), - le32_to_cpu(pkt->hdr.src_port)); + vsock_addr_init(&vchild->local_addr, le64_to_cpu(hdr->dst_cid), + le32_to_cpu(hdr->dst_port)); + vsock_addr_init(&vchild->remote_addr, le64_to_cpu(hdr->src_cid), + le32_to_cpu(hdr->src_port)); ret = vsock_assign_transport(vchild, vsk); /* Transport assigned (looking at remote_addr) must be the same @@ -1209,17 +1226,17 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset_no_sock(t, pkt); + virtio_transport_reset_no_sock(t, skb); sock_put(child); return ret; } - if (virtio_transport_space_update(child, pkt)) + if (virtio_transport_space_update(child, skb)) child->sk_write_space(child); vsock_insert_connected(vchild); vsock_enqueue_accept(sk, child); - virtio_transport_send_response(vchild, pkt); + virtio_transport_send_response(vchild, skb); release_sock(child); @@ -1237,29 +1254,30 @@ static bool virtio_transport_valid_type(u16 type) * lock. */ void virtio_transport_recv_pkt(struct virtio_transport *t, - struct virtio_vsock_pkt *pkt) + struct sk_buff *skb) { + struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct sockaddr_vm src, dst; struct vsock_sock *vsk; struct sock *sk; bool space_available; - vsock_addr_init(&src, le64_to_cpu(pkt->hdr.src_cid), - le32_to_cpu(pkt->hdr.src_port)); - vsock_addr_init(&dst, le64_to_cpu(pkt->hdr.dst_cid), - le32_to_cpu(pkt->hdr.dst_port)); + vsock_addr_init(&src, le64_to_cpu(hdr->src_cid), + le32_to_cpu(hdr->src_port)); + vsock_addr_init(&dst, le64_to_cpu(hdr->dst_cid), + le32_to_cpu(hdr->dst_port)); trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port, dst.svm_cid, dst.svm_port, - le32_to_cpu(pkt->hdr.len), - le16_to_cpu(pkt->hdr.type), - le16_to_cpu(pkt->hdr.op), - le32_to_cpu(pkt->hdr.flags), - le32_to_cpu(pkt->hdr.buf_alloc), - le32_to_cpu(pkt->hdr.fwd_cnt)); - - if (!virtio_transport_valid_type(le16_to_cpu(pkt->hdr.type))) { - (void)virtio_transport_reset_no_sock(t, pkt); + le32_to_cpu(hdr->len), + le16_to_cpu(hdr->type), + le16_to_cpu(hdr->op), + le32_to_cpu(hdr->flags), + le32_to_cpu(hdr->buf_alloc), + le32_to_cpu(hdr->fwd_cnt)); + + if (!virtio_transport_valid_type(le16_to_cpu(hdr->type))) { + (void)virtio_transport_reset_no_sock(t, skb); goto free_pkt; } @@ -1270,13 +1288,13 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, if (!sk) { sk = vsock_find_bound_socket(&dst); if (!sk) { - (void)virtio_transport_reset_no_sock(t, pkt); + (void)virtio_transport_reset_no_sock(t, skb); goto free_pkt; } } - if (virtio_transport_get_type(sk) != le16_to_cpu(pkt->hdr.type)) { - (void)virtio_transport_reset_no_sock(t, pkt); + if (virtio_transport_get_type(sk) != le16_to_cpu(hdr->type)) { + (void)virtio_transport_reset_no_sock(t, skb); sock_put(sk); goto free_pkt; } @@ -1287,13 +1305,13 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, /* Check if sk has been closed before lock_sock */ if (sock_flag(sk, SOCK_DONE)) { - (void)virtio_transport_reset_no_sock(t, pkt); + (void)virtio_transport_reset_no_sock(t, skb); release_sock(sk); sock_put(sk); goto free_pkt; } - space_available = virtio_transport_space_update(sk, pkt); + space_available = virtio_transport_space_update(sk, skb); /* Update CID in case it has changed after a transport reset event */ if (vsk->local_addr.svm_cid != VMADDR_CID_ANY) @@ -1304,23 +1322,23 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, switch (sk->sk_state) { case TCP_LISTEN: - virtio_transport_recv_listen(sk, pkt, t); - virtio_transport_free_pkt(pkt); + virtio_transport_recv_listen(sk, skb, t); + kfree_skb(skb); break; case TCP_SYN_SENT: - virtio_transport_recv_connecting(sk, pkt); - virtio_transport_free_pkt(pkt); + virtio_transport_recv_connecting(sk, skb); + kfree_skb(skb); break; case TCP_ESTABLISHED: - virtio_transport_recv_connected(sk, pkt); + virtio_transport_recv_connected(sk, skb); break; case TCP_CLOSING: - virtio_transport_recv_disconnecting(sk, pkt); - virtio_transport_free_pkt(pkt); + virtio_transport_recv_disconnecting(sk, skb); + kfree_skb(skb); break; default: - (void)virtio_transport_reset_no_sock(t, pkt); - virtio_transport_free_pkt(pkt); + (void)virtio_transport_reset_no_sock(t, skb); + kfree_skb(skb); break; } @@ -1333,16 +1351,42 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, return; free_pkt: - virtio_transport_free_pkt(pkt); + kfree_skb(skb); } EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt); -void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt) +/* Remove skbs found in a queue that have a vsk that matches. + * + * Each skb is freed. + * + * Returns the count of skbs that were reply packets. + */ +int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *queue) { - kvfree(pkt->buf); - kfree(pkt); + struct sk_buff_head freeme; + struct sk_buff *skb, *tmp; + int cnt = 0; + + skb_queue_head_init(&freeme); + + spin_lock_bh(&queue->lock); + skb_queue_walk_safe(queue, skb, tmp) { + if (vsock_sk(skb->sk) != vsk) + continue; + + __skb_unlink(skb, queue); + __skb_queue_tail(&freeme, skb); + + if (virtio_vsock_skb_reply(skb)) + cnt++; + } + spin_unlock_bh(&queue->lock); + + __skb_queue_purge(&freeme); + + return cnt; } -EXPORT_SYMBOL_GPL(virtio_transport_free_pkt); +EXPORT_SYMBOL_GPL(virtio_transport_purge_skbs); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Asias He"); diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 169a8cf65b39..671e03240fc5 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -16,7 +16,7 @@ struct vsock_loopback { struct workqueue_struct *workqueue; spinlock_t pkt_list_lock; /* protects pkt_list */ - struct list_head pkt_list; + struct sk_buff_head pkt_queue; struct work_struct pkt_work; }; @@ -27,13 +27,13 @@ static u32 vsock_loopback_get_local_cid(void) return VMADDR_CID_LOCAL; } -static int vsock_loopback_send_pkt(struct virtio_vsock_pkt *pkt) +static int vsock_loopback_send_pkt(struct sk_buff *skb) { struct vsock_loopback *vsock = &the_vsock_loopback; - int len = pkt->len; + int len = skb->len; spin_lock_bh(&vsock->pkt_list_lock); - list_add_tail(&pkt->list, &vsock->pkt_list); + skb_queue_tail(&vsock->pkt_queue, skb); spin_unlock_bh(&vsock->pkt_list_lock); queue_work(vsock->workqueue, &vsock->pkt_work); @@ -44,21 +44,8 @@ static int vsock_loopback_send_pkt(struct virtio_vsock_pkt *pkt) static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) { struct vsock_loopback *vsock = &the_vsock_loopback; - struct virtio_vsock_pkt *pkt, *n; - LIST_HEAD(freeme); - spin_lock_bh(&vsock->pkt_list_lock); - list_for_each_entry_safe(pkt, n, &vsock->pkt_list, list) { - if (pkt->vsk != vsk) - continue; - list_move(&pkt->list, &freeme); - } - spin_unlock_bh(&vsock->pkt_list_lock); - - list_for_each_entry_safe(pkt, n, &freeme, list) { - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } + virtio_transport_purge_skbs(vsk, &vsock->pkt_queue); return 0; } @@ -121,20 +108,18 @@ static void vsock_loopback_work(struct work_struct *work) { struct vsock_loopback *vsock = container_of(work, struct vsock_loopback, pkt_work); - LIST_HEAD(pkts); + struct sk_buff_head pkts; + struct sk_buff *skb; + + skb_queue_head_init(&pkts); spin_lock_bh(&vsock->pkt_list_lock); - list_splice_init(&vsock->pkt_list, &pkts); + skb_queue_splice_init(&vsock->pkt_queue, &pkts); spin_unlock_bh(&vsock->pkt_list_lock); - while (!list_empty(&pkts)) { - struct virtio_vsock_pkt *pkt; - - pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - - virtio_transport_deliver_tap_pkt(pkt); - virtio_transport_recv_pkt(&loopback_transport, pkt); + while ((skb = __skb_dequeue(&pkts))) { + virtio_transport_deliver_tap_pkt(skb); + virtio_transport_recv_pkt(&loopback_transport, skb); } } @@ -148,7 +133,7 @@ static int __init vsock_loopback_init(void) return -ENOMEM; spin_lock_init(&vsock->pkt_list_lock); - INIT_LIST_HEAD(&vsock->pkt_list); + skb_queue_head_init(&vsock->pkt_queue); INIT_WORK(&vsock->pkt_work, vsock_loopback_work); ret = vsock_core_register(&loopback_transport.transport, @@ -166,19 +151,13 @@ out_wq: static void __exit vsock_loopback_exit(void) { struct vsock_loopback *vsock = &the_vsock_loopback; - struct virtio_vsock_pkt *pkt; vsock_core_unregister(&loopback_transport.transport); flush_work(&vsock->pkt_work); spin_lock_bh(&vsock->pkt_list_lock); - while (!list_empty(&vsock->pkt_list)) { - pkt = list_first_entry(&vsock->pkt_list, - struct virtio_vsock_pkt, list); - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } + virtio_vsock_skb_queue_purge(&vsock->pkt_queue); spin_unlock_bh(&vsock->pkt_list_lock); destroy_workqueue(vsock->workqueue); 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 f610e184ce02..ab20ecc5acce 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -293,3 +293,6 @@ 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 3fc3e54b19aa..96e8371f5c2a 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -27,6 +27,7 @@ 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 + $? )) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3007e98a6d64..47314f0b3006 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -75,14 +75,60 @@ TEST_GEN_PROGS += so_incoming_cpu TEST_PROGS += sctp_vrf.sh TEST_GEN_FILES += sctp_hello TEST_GEN_FILES += csum +TEST_GEN_FILES += nat6to4.o TEST_FILES := settings include ../lib.mk -include bpf/Makefile - $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +# Rules to generate bpf obj nat6to4.o +CLANG ?= clang +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +BPFDIR := $(abspath ../../../lib/bpf) +APIDIR := $(abspath ../../../include/uapi) + +CCINCLUDE += -I../bpf +CCINCLUDE += -I../../../../usr/include/ +CCINCLUDE += -I$(SCRATCH_DIR)/include + +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + +MAKE_DIRS := $(BUILD_DIR)/libbpf +$(MAKE_DIRS): + mkdir -p $@ + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + +$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + $(APIDIR)/linux/bpf.h \ + | $(BUILD_DIR)/libbpf + $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + EXTRA_CFLAGS='-g -O0' \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers + +EXTRA_CLEAN := $(SCRATCH_DIR) diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile deleted file mode 100644 index 4abaf16d2077..000000000000 --- a/tools/testing/selftests/net/bpf/Makefile +++ /dev/null @@ -1,51 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -CLANG ?= clang -SCRATCH_DIR := $(OUTPUT)/tools -BUILD_DIR := $(SCRATCH_DIR)/build -BPFDIR := $(abspath ../../../lib/bpf) -APIDIR := $(abspath ../../../include/uapi) - -CCINCLUDE += -I../../bpf -CCINCLUDE += -I../../../../../usr/include/ -CCINCLUDE += -I$(SCRATCH_DIR)/include - -BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a - -MAKE_DIRS := $(BUILD_DIR)/libbpf $(OUTPUT)/bpf -$(MAKE_DIRS): - mkdir -p $@ - -TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o -all: $(TEST_CUSTOM_PROGS) - -# Get Clang's default includes on this system, as opposed to those seen by -# '-target bpf'. This fixes "missing" files on some architectures/distros, -# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. -# -# Use '-idirafter': Don't interfere with include mechanics except where the -# build would have failed anyways. -define get_sys_includes -$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ - | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ -$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') -endef - -ifneq ($(CROSS_COMPILE),) -CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) -endif - -CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) - -$(TEST_CUSTOM_PROGS): $(OUTPUT)/%.o: %.c $(BPFOBJ) | $(MAKE_DIRS) - $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ - -$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ - $(APIDIR)/linux/bpf.h \ - | $(BUILD_DIR)/libbpf - $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ - EXTRA_CFLAGS='-g -O0' \ - DESTDIR=$(SCRATCH_DIR) prefix= all install_headers - -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) - diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 24bcd7b9bdb2..ef628b16fe9b 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -17,6 +17,11 @@ flush_pids() sleep 1.1 ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null + + for _ in $(seq 10); do + [ -z "$(ip netns pids "${ns}")" ] && break + sleep 0.1 + done } cleanup() @@ -37,15 +42,20 @@ if [ $? -ne 0 ];then exit $ksft_skip fi +get_msk_inuse() +{ + ip netns exec $ns cat /proc/net/protocols | awk '$1~/^MPTCP$/{print $3}' +} + __chk_nr() { - local condition="$1" + local command="$1" local expected=$2 local msg nr shift 2 msg=$* - nr=$(ss -inmHMN $ns | $condition) + nr=$(eval $command) printf "%-50s" "$msg" if [ $nr != $expected ]; then @@ -57,9 +67,17 @@ __chk_nr() test_cnt=$((test_cnt+1)) } +__chk_msk_nr() +{ + local condition=$1 + shift 1 + + __chk_nr "ss -inmHMN $ns | $condition" $* +} + chk_msk_nr() { - __chk_nr "grep -c token:" $* + __chk_msk_nr "grep -c token:" $* } wait_msk_nr() @@ -97,12 +115,12 @@ wait_msk_nr() chk_msk_fallback_nr() { - __chk_nr "grep -c fallback" $* + __chk_msk_nr "grep -c fallback" $* } chk_msk_remote_key_nr() { - __chk_nr "grep -c remote_key" $* + __chk_msk_nr "grep -c remote_key" $* } __chk_listen() @@ -142,6 +160,26 @@ chk_msk_listen() nr=$(ss -Ml $filter | wc -l) } +chk_msk_inuse() +{ + local expected=$1 + local listen_nr + + shift 1 + + listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) + expected=$((expected + listen_nr)) + + for _ in $(seq 10); do + if [ $(get_msk_inuse) -eq $expected ];then + break + fi + sleep 0.1 + done + + __chk_nr get_msk_inuse $expected $* +} + # $1: ns, $2: port wait_local_port_listen() { @@ -195,8 +233,10 @@ wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" +chk_msk_inuse 2 "....chk 2 msk in use" flush_pids +chk_msk_inuse 0 "....chk 0 msk in use after flush" echo "a" | \ timeout ${timeout_test} \ @@ -211,8 +251,11 @@ echo "b" | \ 127.0.0.1 >/dev/null & wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" +chk_msk_inuse 1 "....chk 1 msk in use" flush_pids +chk_msk_inuse 0 "....chk 0 msk in use after flush" + NR_CLIENTS=100 for I in `seq 1 $NR_CLIENTS`; do echo "a" | \ @@ -232,6 +275,9 @@ for I in `seq 1 $NR_CLIENTS`; do done wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use" flush_pids +chk_msk_inuse 0 "....chk 0 msk in use after flush" + exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 8a8266957bc5..b25a31445ded 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -627,7 +627,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, char rbuf[8192]; ssize_t len; - if (fds.events == 0) + if (fds.events == 0 || quit) break; switch (poll(&fds, 1, poll_timeout)) { @@ -733,7 +733,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd, } /* leave some time for late join/announce */ - if (cfg_remove) + if (cfg_remove && !quit) usleep(cfg_wait); return 0; diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/nat6to4.c index ac54c36b25fc..ac54c36b25fc 100644 --- a/tools/testing/selftests/net/bpf/nat6to4.c +++ b/tools/testing/selftests/net/nat6to4.c diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index c9c4b9d65839..0a6359bed0b9 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -40,8 +40,8 @@ run_one() { ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact - tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action - tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file nat6to4.o section schedcls/egress4/snat4 direct-action echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & @@ -88,8 +88,8 @@ if [ ! -f ${BPF_FILE} ]; then exit -1 fi -if [ ! -f bpf/nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" +if [ ! -f nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" exit -1 fi diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index f8293c6910c9..43a254f0e14d 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only -all: test +all: test vsock_perf test: vsock_test vsock_diag_test vsock_test: vsock_test.o timeout.o control.o util.o vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o +vsock_perf: vsock_perf.o CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 4d5045e7d2c3..84ee217ba8ee 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -35,3 +35,37 @@ Invoke test binaries in both directions as follows: --control-port=$GUEST_IP \ --control-port=1234 \ --peer-cid=3 + +vsock_perf utility +------------------- +'vsock_perf' is a simple tool to measure vsock performance. It works in +sender/receiver modes: sender connect to peer at the specified port and +starts data transmission to the receiver. After data processing is done, +it prints several metrics(see below). + +Usage: +# run as sender +# connect to CID 2, port 1234, send 1G of data, tx buf size is 1M +./vsock_perf --sender 2 --port 1234 --bytes 1G --buf-size 1M + +Output: +tx performance: A Gbits/s + +Output explanation: +A is calculated as "number of bits to send" / "time in tx loop" + +# run as receiver +# listen port 1234, rx buf size is 1M, socket buf size is 1G, SO_RCVLOWAT is 64K +./vsock_perf --port 1234 --buf-size 1M --vsk-size 1G --rcvlowat 64K + +Output: +rx performance: A Gbits/s +total in 'read()': B sec +POLLIN wakeups: C +average in 'read()': D ns + +Output explanation: +A is calculated as "number of received bits" / "time in rx loop". +B is time, spent in 'read()' system call(excluding 'poll()') +C is number of 'poll()' wake ups with POLLIN bit set. +D is B / C, e.g. average amount of time, spent in single 'read()'. diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c index 4874872fc5a3..d2deb4b15b94 100644 --- a/tools/testing/vsock/control.c +++ b/tools/testing/vsock/control.c @@ -141,6 +141,34 @@ void control_writeln(const char *str) timeout_end(); } +void control_writeulong(unsigned long value) +{ + char str[32]; + + if (snprintf(str, sizeof(str), "%lu", value) >= sizeof(str)) { + perror("snprintf"); + exit(EXIT_FAILURE); + } + + control_writeln(str); +} + +unsigned long control_readulong(void) +{ + unsigned long value; + char *str; + + str = control_readln(); + + if (!str) + exit(EXIT_FAILURE); + + value = strtoul(str, NULL, 10); + free(str); + + return value; +} + /* Return the next line from the control socket (without the trailing newline). * * The program terminates if a timeout occurs. diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h index 51814b4f9ac1..c1f77fdb2c7a 100644 --- a/tools/testing/vsock/control.h +++ b/tools/testing/vsock/control.h @@ -9,7 +9,9 @@ void control_init(const char *control_host, const char *control_port, void control_cleanup(void); void control_writeln(const char *str); char *control_readln(void); +unsigned long control_readulong(void); void control_expectln(const char *str); bool control_cmpln(char *line, const char *str, bool fail); +void control_writeulong(unsigned long value); #endif /* CONTROL_H */ diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 2acbb7703c6a..01b636d3039a 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -395,3 +395,16 @@ void skip_test(struct test_case *test_cases, size_t test_cases_len, test_cases[test_id].skip = true; } + +unsigned long hash_djb2(const void *data, size_t len) +{ + unsigned long hash = 5381; + int i = 0; + + while (i < len) { + hash = ((hash << 5) + hash) + ((unsigned char *)data)[i]; + i++; + } + + return hash; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index a3375ad2fb7f..fb99208a95ea 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -49,4 +49,5 @@ void run_tests(const struct test_case *test_cases, void list_tests(const struct test_case *test_cases); void skip_test(struct test_case *test_cases, size_t test_cases_len, const char *test_id_str); +unsigned long hash_djb2(const void *data, size_t len); #endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_perf.c b/tools/testing/vsock/vsock_perf.c new file mode 100644 index 000000000000..a72520338f84 --- /dev/null +++ b/tools/testing/vsock/vsock_perf.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock_perf - benchmark utility for vsock. + * + * Copyright (C) 2022 SberDevices. + * + * Author: Arseniy Krasnov <AVKrasnov@sberdevices.ru> + */ +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <time.h> +#include <stdint.h> +#include <poll.h> +#include <sys/socket.h> +#include <linux/vm_sockets.h> + +#define DEFAULT_BUF_SIZE_BYTES (128 * 1024) +#define DEFAULT_TO_SEND_BYTES (64 * 1024) +#define DEFAULT_VSOCK_BUF_BYTES (256 * 1024) +#define DEFAULT_RCVLOWAT_BYTES 1 +#define DEFAULT_PORT 1234 + +#define BYTES_PER_GB (1024 * 1024 * 1024ULL) +#define NSEC_PER_SEC (1000000000ULL) + +static unsigned int port = DEFAULT_PORT; +static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES; +static unsigned long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES; + +static void error(const char *s) +{ + perror(s); + exit(EXIT_FAILURE); +} + +static time_t current_nsec(void) +{ + struct timespec ts; + + if (clock_gettime(CLOCK_REALTIME, &ts)) + error("clock_gettime"); + + return (ts.tv_sec * NSEC_PER_SEC) + ts.tv_nsec; +} + +/* From lib/cmdline.c. */ +static unsigned long memparse(const char *ptr) +{ + char *endptr; + + unsigned long long ret = strtoull(ptr, &endptr, 0); + + switch (*endptr) { + case 'E': + case 'e': + ret <<= 10; + case 'P': + case 'p': + ret <<= 10; + case 'T': + case 't': + ret <<= 10; + case 'G': + case 'g': + ret <<= 10; + case 'M': + case 'm': + ret <<= 10; + case 'K': + case 'k': + ret <<= 10; + endptr++; + default: + break; + } + + return ret; +} + +static void vsock_increase_buf_size(int fd) +{ + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + &vsock_buf_bytes, sizeof(vsock_buf_bytes))) + error("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + &vsock_buf_bytes, sizeof(vsock_buf_bytes))) + error("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); +} + +static int vsock_connect(unsigned int cid, unsigned int port) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (fd < 0) { + perror("socket"); + return -1; + } + + if (connect(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("connect"); + close(fd); + return -1; + } + + return fd; +} + +static float get_gbps(unsigned long bits, time_t ns_delta) +{ + return ((float)bits / 1000000000ULL) / + ((float)ns_delta / NSEC_PER_SEC); +} + +static void run_receiver(unsigned long rcvlowat_bytes) +{ + unsigned int read_cnt; + time_t rx_begin_ns; + time_t in_read_ns; + size_t total_recv; + int client_fd; + char *data; + int fd; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = VMADDR_CID_ANY, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + + socklen_t clientaddr_len = sizeof(clientaddr.svm); + + printf("Run as receiver\n"); + printf("Listen port %u\n", port); + printf("RX buffer %lu bytes\n", buf_size_bytes); + printf("vsock buffer %lu bytes\n", vsock_buf_bytes); + printf("SO_RCVLOWAT %lu bytes\n", rcvlowat_bytes); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (fd < 0) + error("socket"); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) + error("bind"); + + if (listen(fd, 1) < 0) + error("listen"); + + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + + if (client_fd < 0) + error("accept"); + + vsock_increase_buf_size(client_fd); + + if (setsockopt(client_fd, SOL_SOCKET, SO_RCVLOWAT, + &rcvlowat_bytes, + sizeof(rcvlowat_bytes))) + error("setsockopt(SO_RCVLOWAT)"); + + data = malloc(buf_size_bytes); + + if (!data) { + fprintf(stderr, "'malloc()' failed\n"); + exit(EXIT_FAILURE); + } + + read_cnt = 0; + in_read_ns = 0; + total_recv = 0; + rx_begin_ns = current_nsec(); + + while (1) { + struct pollfd fds = { 0 }; + + fds.fd = client_fd; + fds.events = POLLIN | POLLERR | + POLLHUP | POLLRDHUP; + + if (poll(&fds, 1, -1) < 0) + error("poll"); + + if (fds.revents & POLLERR) { + fprintf(stderr, "'poll()' error\n"); + exit(EXIT_FAILURE); + } + + if (fds.revents & POLLIN) { + ssize_t bytes_read; + time_t t; + + t = current_nsec(); + bytes_read = read(fds.fd, data, buf_size_bytes); + in_read_ns += (current_nsec() - t); + read_cnt++; + + if (!bytes_read) + break; + + if (bytes_read < 0) { + perror("read"); + exit(EXIT_FAILURE); + } + + total_recv += bytes_read; + } + + if (fds.revents & (POLLHUP | POLLRDHUP)) + break; + } + + printf("total bytes received: %zu\n", total_recv); + printf("rx performance: %f Gbits/s\n", + get_gbps(total_recv * 8, current_nsec() - rx_begin_ns)); + printf("total time in 'read()': %f sec\n", (float)in_read_ns / NSEC_PER_SEC); + printf("average time in 'read()': %f ns\n", (float)in_read_ns / read_cnt); + printf("POLLIN wakeups: %i\n", read_cnt); + + free(data); + close(client_fd); + close(fd); +} + +static void run_sender(int peer_cid, unsigned long to_send_bytes) +{ + time_t tx_begin_ns; + time_t tx_total_ns; + size_t total_send; + void *data; + int fd; + + printf("Run as sender\n"); + printf("Connect to %i:%u\n", peer_cid, port); + printf("Send %lu bytes\n", to_send_bytes); + printf("TX buffer %lu bytes\n", buf_size_bytes); + + fd = vsock_connect(peer_cid, port); + + if (fd < 0) + exit(EXIT_FAILURE); + + data = malloc(buf_size_bytes); + + if (!data) { + fprintf(stderr, "'malloc()' failed\n"); + exit(EXIT_FAILURE); + } + + memset(data, 0, buf_size_bytes); + total_send = 0; + tx_begin_ns = current_nsec(); + + while (total_send < to_send_bytes) { + ssize_t sent; + + sent = write(fd, data, buf_size_bytes); + + if (sent <= 0) + error("write"); + + total_send += sent; + } + + tx_total_ns = current_nsec() - tx_begin_ns; + + printf("total bytes sent: %zu\n", total_send); + printf("tx performance: %f Gbits/s\n", + get_gbps(total_send * 8, tx_total_ns)); + printf("total time in 'write()': %f sec\n", + (float)tx_total_ns / NSEC_PER_SEC); + + close(fd); + free(data); +} + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "help", + .has_arg = no_argument, + .val = 'H', + }, + { + .name = "sender", + .has_arg = required_argument, + .val = 'S', + }, + { + .name = "port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "bytes", + .has_arg = required_argument, + .val = 'M', + }, + { + .name = "buf-size", + .has_arg = required_argument, + .val = 'B', + }, + { + .name = "vsk-size", + .has_arg = required_argument, + .val = 'V', + }, + { + .name = "rcvlowat", + .has_arg = required_argument, + .val = 'R', + }, + {}, +}; + +static void usage(void) +{ + printf("Usage: ./vsock_perf [--help] [options]\n" + "\n" + "This is benchmarking utility, to test vsock performance.\n" + "It runs in two modes: sender or receiver. In sender mode, it\n" + "connects to the specified CID and starts data transmission.\n" + "\n" + "Options:\n" + " --help This message\n" + " --sender <cid> Sender mode (receiver default)\n" + " <cid> of the receiver to connect to\n" + " --port <port> Port (default %d)\n" + " --bytes <bytes>KMG Bytes to send (default %d)\n" + " --buf-size <bytes>KMG Data buffer size (default %d). In sender mode\n" + " it is the buffer size, passed to 'write()'. In\n" + " receiver mode it is the buffer size passed to 'read()'.\n" + " --vsk-size <bytes>KMG Socket buffer size (default %d)\n" + " --rcvlowat <bytes>KMG SO_RCVLOWAT value (default %d)\n" + "\n", DEFAULT_PORT, DEFAULT_TO_SEND_BYTES, + DEFAULT_BUF_SIZE_BYTES, DEFAULT_VSOCK_BUF_BYTES, + DEFAULT_RCVLOWAT_BYTES); + exit(EXIT_FAILURE); +} + +static long strtolx(const char *arg) +{ + long value; + char *end; + + value = strtol(arg, &end, 10); + + if (end != arg + strlen(arg)) + usage(); + + return value; +} + +int main(int argc, char **argv) +{ + unsigned long to_send_bytes = DEFAULT_TO_SEND_BYTES; + unsigned long rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES; + int peer_cid = -1; + bool sender = false; + + while (1) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'V': /* Peer buffer size. */ + vsock_buf_bytes = memparse(optarg); + break; + case 'R': /* SO_RCVLOWAT value. */ + rcvlowat_bytes = memparse(optarg); + break; + case 'P': /* Port to connect to. */ + port = strtolx(optarg); + break; + case 'M': /* Bytes to send. */ + to_send_bytes = memparse(optarg); + break; + case 'B': /* Size of rx/tx buffer. */ + buf_size_bytes = memparse(optarg); + break; + case 'S': /* Sender mode. CID to connect to. */ + peer_cid = strtolx(optarg); + sender = true; + break; + case 'H': /* Help. */ + usage(); + break; + default: + usage(); + } + } + + if (!sender) + run_receiver(rcvlowat_bytes); + else + run_sender(peer_cid, to_send_bytes); + + return 0; +} diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index bb6d691cb30d..67e9f9df3a8c 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -284,10 +284,14 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) close(fd); } -#define MESSAGES_CNT 7 -#define MSG_EOR_IDX (MESSAGES_CNT / 2) +#define SOCK_BUF_SIZE (2 * 1024 * 1024) +#define MAX_MSG_SIZE (32 * 1024) + static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { + unsigned long curr_hash; + int page_size; + int msg_count; int fd; fd = vsock_seqpacket_connect(opts->peer_cid, 1234); @@ -296,18 +300,79 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) exit(EXIT_FAILURE); } - /* Send several messages, one with MSG_EOR flag */ - for (int i = 0; i < MESSAGES_CNT; i++) - send_byte(fd, 1, (i == MSG_EOR_IDX) ? MSG_EOR : 0); + /* Wait, until receiver sets buffer size. */ + control_expectln("SRVREADY"); + + curr_hash = 0; + page_size = getpagesize(); + msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE; + + for (int i = 0; i < msg_count; i++) { + ssize_t send_size; + size_t buf_size; + int flags; + void *buf; + + /* Use "small" buffers and "big" buffers. */ + if (i & 1) + buf_size = page_size + + (rand() % (MAX_MSG_SIZE - page_size)); + else + buf_size = 1 + (rand() % page_size); + + buf = malloc(buf_size); + + if (!buf) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + memset(buf, rand() & 0xff, buf_size); + /* Set at least one MSG_EOR + some random. */ + if (i == (msg_count / 2) || (rand() & 1)) { + flags = MSG_EOR; + curr_hash++; + } else { + flags = 0; + } + + send_size = send(fd, buf, buf_size, flags); + + if (send_size < 0) { + perror("send"); + exit(EXIT_FAILURE); + } + + if (send_size != buf_size) { + fprintf(stderr, "Invalid send size\n"); + exit(EXIT_FAILURE); + } + + /* + * Hash sum is computed at both client and server in + * the same way: + * H += hash('message data') + * Such hash "controls" both data integrity and message + * bounds. After data exchange, both sums are compared + * using control socket, and if message bounds wasn't + * broken - two values must be equal. + */ + curr_hash += hash_djb2(buf, buf_size); + free(buf); + } control_writeln("SENDDONE"); + control_writeulong(curr_hash); close(fd); } static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) { + unsigned long sock_buf_size; + unsigned long remote_hash; + unsigned long curr_hash; int fd; - char buf[16]; + char buf[MAX_MSG_SIZE]; struct msghdr msg = {0}; struct iovec iov = {0}; @@ -317,25 +382,57 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) exit(EXIT_FAILURE); } + sock_buf_size = SOCK_BUF_SIZE; + + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + &sock_buf_size, sizeof(sock_buf_size))) { + perror("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + exit(EXIT_FAILURE); + } + + if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + &sock_buf_size, sizeof(sock_buf_size))) { + perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + exit(EXIT_FAILURE); + } + + /* Ready to receive data. */ + control_writeln("SRVREADY"); + /* Wait, until peer sends whole data. */ control_expectln("SENDDONE"); iov.iov_base = buf; iov.iov_len = sizeof(buf); msg.msg_iov = &iov; msg.msg_iovlen = 1; - for (int i = 0; i < MESSAGES_CNT; i++) { - if (recvmsg(fd, &msg, 0) != 1) { - perror("message bound violated"); - exit(EXIT_FAILURE); - } + curr_hash = 0; + + while (1) { + ssize_t recv_size; - if ((i == MSG_EOR_IDX) ^ !!(msg.msg_flags & MSG_EOR)) { - perror("MSG_EOR"); + recv_size = recvmsg(fd, &msg, 0); + + if (!recv_size) + break; + + if (recv_size < 0) { + perror("recvmsg"); exit(EXIT_FAILURE); } + + if (msg.msg_flags & MSG_EOR) + curr_hash++; + + curr_hash += hash_djb2(msg.msg_iov[0].iov_base, recv_size); } close(fd); + remote_hash = control_readulong(); + + if (curr_hash != remote_hash) { + fprintf(stderr, "Message bounds broken\n"); + exit(EXIT_FAILURE); + } } #define MESSAGE_TRUNC_SZ 32 @@ -427,7 +524,7 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts) tv.tv_usec = 0; if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (void *)&tv, sizeof(tv)) == -1) { - perror("setsockopt 'SO_RCVTIMEO'"); + perror("setsockopt(SO_RCVTIMEO)"); exit(EXIT_FAILURE); } @@ -472,6 +569,70 @@ static void test_seqpacket_timeout_server(const struct test_opts *opts) close(fd); } +static void test_seqpacket_bigmsg_client(const struct test_opts *opts) +{ + unsigned long sock_buf_size; + ssize_t send_size; + socklen_t len; + void *data; + int fd; + + len = sizeof(sock_buf_size); + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (getsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + &sock_buf_size, &len)) { + perror("getsockopt"); + exit(EXIT_FAILURE); + } + + sock_buf_size++; + + data = malloc(sock_buf_size); + if (!data) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + send_size = send(fd, data, sock_buf_size, 0); + if (send_size != -1) { + fprintf(stderr, "expected 'send(2)' failure, got %zi\n", + send_size); + exit(EXIT_FAILURE); + } + + if (errno != EMSGSIZE) { + fprintf(stderr, "expected EMSGSIZE in 'errno', got %i\n", + errno); + exit(EXIT_FAILURE); + } + + control_writeln("CLISENT"); + + free(data); + close(fd); +} + +static void test_seqpacket_bigmsg_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("CLISENT"); + + close(fd); +} + #define BUF_PATTERN_1 'a' #define BUF_PATTERN_2 'b' @@ -644,7 +805,7 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, &lowat_val, sizeof(lowat_val))) { - perror("setsockopt"); + perror("setsockopt(SO_RCVLOWAT)"); exit(EXIT_FAILURE); } @@ -754,6 +915,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_poll_rcvlowat_client, .run_server = test_stream_poll_rcvlowat_server, }, + { + .name = "SOCK_SEQPACKET big message", + .run_client = test_seqpacket_bigmsg_client, + .run_server = test_seqpacket_bigmsg_server, + }, {}, }; @@ -837,6 +1003,7 @@ int main(int argc, char **argv) .peer_cid = VMADDR_CID_ANY, }; + srand(time(NULL)); init_signals(); for (;;) { |