diff options
793 files changed, 27113 insertions, 8290 deletions
diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst index 0e7c1d946e83..c9856b927055 100644 --- a/Documentation/bpf/bpf_devel_QA.rst +++ b/Documentation/bpf/bpf_devel_QA.rst @@ -106,9 +106,9 @@ into the bpf-next tree will make their way into net-next tree. net and net-next are both run by David S. Miller. From there, they will go into the kernel mainline tree run by Linus Torvalds. To read up on the process of net and net-next being merged into the mainline tree, see -the `netdev FAQ`_ under: +the :ref:`netdev-FAQ` + - `Documentation/networking/netdev-FAQ.txt`_ Occasionally, to prevent merge conflicts, we might send pull requests to other trees (e.g. tracing) with a small subset of the patches, but @@ -125,8 +125,8 @@ request):: Q: How do I indicate which tree (bpf vs. bpf-next) my patch should be applied to? --------------------------------------------------------------------------------- -A: The process is the very same as described in the `netdev FAQ`_, so -please read up on it. The subject line must indicate whether the +A: The process is the very same as described in the :ref:`netdev-FAQ`, +so please read up on it. The subject line must indicate whether the patch is a fix or rather "next-like" content in order to let the maintainers know whether it is targeted at bpf or bpf-next. @@ -184,7 +184,7 @@ ii) run extensive BPF test suite and Once the BPF pull request was accepted by David S. Miller, then the patches end up in net or net-next tree, respectively, and make their way from there further into mainline. Again, see the -`netdev FAQ`_ for additional information e.g. on how often they are +:ref:`netdev-FAQ` for additional information e.g. on how often they are merged to mainline. Q: How long do I need to wait for feedback on my BPF patches? @@ -208,7 +208,7 @@ Q: Are patches applied to bpf-next when the merge window is open? ----------------------------------------------------------------- A: For the time when the merge window is open, bpf-next will not be processed. This is roughly analogous to net-next patch processing, -so feel free to read up on the `netdev FAQ`_ about further details. +so feel free to read up on the :ref:`netdev-FAQ` about further details. During those two weeks of merge window, we might ask you to resend your patch series once bpf-next is open again. Once Linus released @@ -372,7 +372,7 @@ netdev kernel mailing list in Cc and ask for the fix to be queued up: netdev@vger.kernel.org The process in general is the same as on netdev itself, see also the -`netdev FAQ`_ document. +:ref:`netdev-FAQ`. Q: Do you also backport to kernels not currently maintained as stable? ---------------------------------------------------------------------- @@ -388,9 +388,7 @@ Q: The BPF patch I am about to submit needs to go to stable as well What should I do? A: The same rules apply as with netdev patch submissions in general, see -`netdev FAQ`_ under: - - `Documentation/networking/netdev-FAQ.txt`_ +the :ref:`netdev-FAQ`. Never add "``Cc: stable@vger.kernel.org``" to the patch description, but ask the BPF maintainers to queue the patches instead. This can be done @@ -630,8 +628,7 @@ when: .. Links .. _Documentation/process/: https://www.kernel.org/doc/html/latest/process/ .. _MAINTAINERS: ../../MAINTAINERS -.. _Documentation/networking/netdev-FAQ.txt: ../networking/netdev-FAQ.txt -.. _netdev FAQ: ../networking/netdev-FAQ.txt +.. _netdev-FAQ: ../networking/netdev-FAQ.rst .. _samples/bpf/: ../../samples/bpf/ .. _selftests: ../../tools/testing/selftests/bpf/ .. _Documentation/dev-tools/kselftest.rst: diff --git a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt index dfe287a5d6f2..b58843f29591 100644 --- a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt +++ b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt @@ -13,14 +13,17 @@ MDIO multiplexer node: Every non-ethernet PHY requires a compatible so that it could be probed based on this compatible string. +Optional properties: +- clocks: phandle of the core clock which drives the mdio block. + Additional information regarding generic multiplexer properties can be found at- Documentation/devicetree/bindings/net/mdio-mux.txt for example: - mdio_mux_iproc: mdio-mux@6602023c { + mdio_mux_iproc: mdio-mux@66020000 { compatible = "brcm,mdio-mux-iproc"; - reg = <0x6602023c 0x14>; + reg = <0x66020000 0x250>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt index fe38847d8e26..ae5c07e96ad5 100644 --- a/Documentation/devicetree/bindings/net/can/xilinx_can.txt +++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt @@ -2,20 +2,26 @@ Xilinx Axi CAN/Zynq CANPS controller Device Tree Bindings --------------------------------------------------------- Required properties: -- compatible : Should be "xlnx,zynq-can-1.0" for Zynq CAN - controllers and "xlnx,axi-can-1.00.a" for Axi CAN - controllers. -- reg : Physical base address and size of the Axi CAN/Zynq - CANPS registers map. +- compatible : Should be: + - "xlnx,zynq-can-1.0" for Zynq CAN controllers + - "xlnx,axi-can-1.00.a" for Axi CAN controllers + - "xlnx,canfd-1.0" for CAN FD controllers +- reg : Physical base address and size of the controller + registers map. - interrupts : Property with a value describing the interrupt number. - interrupt-parent : Must be core interrupt controller -- clock-names : List of input clock names - "can_clk", "pclk" - (For CANPS), "can_clk" , "s_axi_aclk"(For AXI CAN) +- clock-names : List of input clock names + - "can_clk", "pclk" (For CANPS), + - "can_clk", "s_axi_aclk" (For AXI CAN and CAN FD). (See clock bindings for details). - clocks : Clock phandles (see clock bindings for details). -- tx-fifo-depth : Can Tx fifo depth. -- rx-fifo-depth : Can Rx fifo depth. +- tx-fifo-depth : Can Tx fifo depth (Zynq, Axi CAN). +- rx-fifo-depth : Can Rx fifo depth (Zynq, Axi CAN, CAN FD in + sequential Rx mode). +- tx-mailbox-count : Can Tx mailbox buffer count (CAN FD). +- rx-mailbox-count : Can Rx mailbox buffer count (CAN FD in mailbox Rx + mode). Example: @@ -42,3 +48,14 @@ For Axi CAN Dts file: tx-fifo-depth = <0x40>; rx-fifo-depth = <0x40>; }; +For CAN FD Dts file: + canfd_0: canfd@40000000 { + compatible = "xlnx,canfd-1.0"; + clocks = <&clkc 0>, <&clkc 1>; + clock-names = "can_clk", "s_axi_aclk"; + reg = <0x40000000 0x2000>; + interrupt-parent = <&intc>; + interrupts = <0 59 1>; + tx-mailbox-count = <0x20>; + rx-fifo-depth = <0x20>; + }; diff --git a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt index 0ea18a53cc29..824c0e23c544 100644 --- a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt +++ b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt @@ -10,12 +10,25 @@ device the slave device is attached to. Required properties: - compatible: should contain one of the following: * "qcom,qca6174-bt" + * "qcom,wcn3990-bt" + +Optional properties for compatible string qcom,qca6174-bt: -Optional properties: - enable-gpios: gpio specifier used to enable chip - clocks: clock provided to the controller (SUSCLK_32KHZ) -Example: +Required properties for compatible string qcom,wcn3990-bt: + + - vddio-supply: VDD_IO supply regulator handle. + - vddxo-supply: VDD_XO supply regulator handle. + - vddrf-supply: VDD_RF supply regulator handle. + - vddch0-supply: VDD_CH0 supply regulator handle. + +Optional properties for compatible string qcom,wcn3990-bt: + + - max-speed: see Documentation/devicetree/bindings/serial/slave-device.txt + +Examples: serial@7570000 { label = "BT-UART"; @@ -28,3 +41,15 @@ serial@7570000 { clocks = <&divclk4>; }; }; + +serial@898000 { + bluetooth { + compatible = "qcom,wcn3990-bt"; + + vddio-supply = <&vreg_s4a_1p8>; + vddxo-supply = <&vreg_l7a_1p8>; + vddrf-supply = <&vreg_l17a_1p3>; + vddch0-supply = <&vreg_l25a_3p3>; + max-speed = <3200000>; + }; +}; diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt index 252a05c5d976..c8c4b00ecb94 100644 --- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt +++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt @@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of the node is not important. The content of the node is defined in dwc3.txt. Phy documentation is provided in the following places: -Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt +Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY +Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt - Type-C PHY Example device nodes: diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 1e5153ed8990..02a323c43261 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -138,8 +138,6 @@ multiqueue.txt - HOWTO for multiqueue network device support. netconsole.txt - The network console module netconsole.ko: configuration and notes. -netdev-FAQ.txt - - FAQ describing how to submit net changes to netdev mailing list. netdev-features.txt - Network interface features API description. netdevices.txt diff --git a/Documentation/networking/can_ucan_protocol.rst b/Documentation/networking/can_ucan_protocol.rst new file mode 100644 index 000000000000..4cef88d24fc7 --- /dev/null +++ b/Documentation/networking/can_ucan_protocol.rst @@ -0,0 +1,332 @@ +================= +The UCAN Protocol +================= + +UCAN is the protocol used by the microcontroller-based USB-CAN +adapter that is integrated on System-on-Modules from Theobroma Systems +and that is also available as a standalone USB stick. + +The UCAN protocol has been designed to be hardware-independent. +It is modeled closely after how Linux represents CAN devices +internally. All multi-byte integers are encoded as Little Endian. + +All structures mentioned in this document are defined in +``drivers/net/can/usb/ucan.c``. + +USB Endpoints +============= + +UCAN devices use three USB endpoints: + +CONTROL endpoint + The driver sends device management commands on this endpoint + +IN endpoint + The device sends CAN data frames and CAN error frames + +OUT endpoint + The driver sends CAN data frames on the out endpoint + + +CONTROL Messages +================ + +UCAN devices are configured using vendor requests on the control pipe. + +To support multiple CAN interfaces in a single USB device all +configuration commands target the corresponding interface in the USB +descriptor. + +The driver uses ``ucan_ctrl_command_in/out`` and +``ucan_device_request_in`` to deliver commands to the device. + +Setup Packet +------------ + +================= ===================================================== +``bmRequestType`` Direction | Vendor | (Interface or Device) +``bRequest`` Command Number +``wValue`` Subcommand Number (16 Bit) or 0 if not used +``wIndex`` USB Interface Index (0 for device commands) +``wLength`` * Host to Device - Number of bytes to transmit + * Device to Host - Maximum Number of bytes to + receive. If the device send less. Commom ZLP + semantics are used. +================= ===================================================== + +Error Handling +-------------- + +The device indicates failed control commands by stalling the +pipe. + +Device Commands +--------------- + +UCAN_DEVICE_GET_FW_STRING +~~~~~~~~~~~~~~~~~~~~~~~~~ + +*Dev2Host; optional* + +Request the device firmware string. + + +Interface Commands +------------------ + +UCAN_COMMAND_START +~~~~~~~~~~~~~~~~~~ + +*Host2Dev; mandatory* + +Bring the CAN interface up. + +Payload Format + ``ucan_ctl_payload_t.cmd_start`` + +==== ============================ +mode or mask of ``UCAN_MODE_*`` +==== ============================ + +UCAN_COMMAND_STOP +~~~~~~~~~~~~~~~~~~ + +*Host2Dev; mandatory* + +Stop the CAN interface + +Payload Format + *empty* + +UCAN_COMMAND_RESET +~~~~~~~~~~~~~~~~~~ + +*Host2Dev; mandatory* + +Reset the CAN controller (including error counters) + +Payload Format + *empty* + +UCAN_COMMAND_GET +~~~~~~~~~~~~~~~~ + +*Host2Dev; mandatory* + +Get Information from the Device + +Subcommands +^^^^^^^^^^^ + +UCAN_COMMAND_GET_INFO + Request the device information structure ``ucan_ctl_payload_t.device_info``. + + See the ``device_info`` field for details, and + ``uapi/linux/can/netlink.h`` for an explanation of the + ``can_bittiming fields``. + + Payload Format + ``ucan_ctl_payload_t.device_info`` + +UCAN_COMMAND_GET_PROTOCOL_VERSION + + Request the device protocol version + ``ucan_ctl_payload_t.protocol_version``. The current protocol version is 3. + + Payload Format + ``ucan_ctl_payload_t.protocol_version`` + +.. note:: Devices that do not implement this command use the old + protocol version 1 + +UCAN_COMMAND_SET_BITTIMING +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +*Host2Dev; mandatory* + +Setup bittiming by sending the the structure +``ucan_ctl_payload_t.cmd_set_bittiming`` (see ``struct bittiming`` for +details) + +Payload Format + ``ucan_ctl_payload_t.cmd_set_bittiming``. + +UCAN_SLEEP/WAKE +~~~~~~~~~~~~~~~ + +*Host2Dev; optional* + +Configure sleep and wake modes. Not yet supported by the driver. + +UCAN_FILTER +~~~~~~~~~~~ + +*Host2Dev; optional* + +Setup hardware CAN filters. Not yet supported by the driver. + +Allowed interface commands +-------------------------- + +================== =================== ================== +Legal Device State Command New Device State +================== =================== ================== +stopped SET_BITTIMING stopped +stopped START started +started STOP or RESET stopped +stopped STOP or RESET stopped +started RESTART started +any GET *no change* +================== =================== ================== + +IN Message Format +================= + +A data packet on the USB IN endpoint contains one or more +``ucan_message_in`` values. If multiple messages are batched in a USB +data packet, the ``len`` field can be used to jump to the next +``ucan_message_in`` value (take care to sanity-check the ``len`` value +against the actual data size). + +.. _can_ucan_in_message_len: + +``len`` field +------------- + +Each ``ucan_message_in`` must be aligned to a 4-byte boundary (relative +to the start of the start of the data buffer). That means that there +may be padding bytes between multiple ``ucan_message_in`` values: + +.. code:: + + +----------------------------+ < 0 + | | + | struct ucan_message_in | + | | + +----------------------------+ < len + [padding] + +----------------------------+ < round_up(len, 4) + | | + | struct ucan_message_in | + | | + +----------------------------+ + [...] + +``type`` field +-------------- + +The ``type`` field specifies the type of the message. + +UCAN_IN_RX +~~~~~~~~~~ + +``subtype`` + zero + +Data received from the CAN bus (ID + payload). + +UCAN_IN_TX_COMPLETE +~~~~~~~~~~~~~~~~~~~ + +``subtype`` + zero + +The CAN device has sent a message to the CAN bus. It answers with a +list of of tuples <echo-ids, flags>. + +The echo-id identifies the frame from (echos the id from a previous +UCAN_OUT_TX message). The flag indicates the result of the +transmission. Whereas a set Bit 0 indicates success. All other bits +are reserved and set to zero. + +Flow Control +------------ + +When receiving CAN messages there is no flow control on the USB +buffer. The driver has to handle inbound message quickly enough to +avoid drops. I case the device buffer overflow the condition is +reported by sending corresponding error frames (see +:ref:`can_ucan_error_handling`) + + +OUT Message Format +================== + +A data packet on the USB OUT endpoint contains one or more ``struct +ucan_message_out`` values. If multiple messages are batched into one +data packet, the device uses the ``len`` field to jump to the next +ucan_message_out value. Each ucan_message_out must be aligned to 4 +bytes (relative to the start of the data buffer). The mechanism is +same as described in :ref:`can_ucan_in_message_len`. + +.. code:: + + +----------------------------+ < 0 + | | + | struct ucan_message_out | + | | + +----------------------------+ < len + [padding] + +----------------------------+ < round_up(len, 4) + | | + | struct ucan_message_out | + | | + +----------------------------+ + [...] + +``type`` field +-------------- + +In protocol version 3 only ``UCAN_OUT_TX`` is defined, others are used +only by legacy devices (protocol version 1). + +UCAN_OUT_TX +~~~~~~~~~~~ +``subtype`` + echo id to be replied within a CAN_IN_TX_COMPLETE message + +Transmit a CAN frame. (parameters: ``id``, ``data``) + +Flow Control +------------ + +When the device outbound buffers are full it starts sending *NAKs* on +the *OUT* pipe until more buffers are available. The driver stops the +queue when a certain threshold of out packets are incomplete. + +.. _can_ucan_error_handling: + +CAN Error Handling +================== + +If error reporting is turned on the device encodes errors into CAN +error frames (see ``uapi/linux/can/error.h``) and sends it using the +IN endpoint. The driver updates its error statistics and forwards +it. + +Although UCAN devices can suppress error frames completely, in Linux +the driver is always interested. Hence, the device is always started with +the ``UCAN_MODE_BERR_REPORT`` set. Filtering those messages for the +user space is done by the driver. + +Bus OFF +------- + +- The device does not recover from bus of automatically. +- Bus OFF is indicated by an error frame (see ``uapi/linux/can/error.h``) +- Bus OFF recovery is started by ``UCAN_COMMAND_RESTART`` +- Once Bus OFF recover is completed the device sends an error frame + indicating that it is on ERROR-ACTIVE state. +- During Bus OFF no frames are sent by the device. +- During Bus OFF transmission requests from the host are completed + immediately with the success bit left unset. + +Example Conversation +==================== + +#) Device is connected to USB +#) Host sends command ``UCAN_COMMAND_RESET``, subcmd 0 +#) Host sends command ``UCAN_COMMAND_GET``, subcmd ``UCAN_COMMAND_GET_INFO`` +#) Device sends ``UCAN_IN_DEVICE_INFO`` +#) Host sends command ``UCAN_OUT_SET_BITTIMING`` +#) Host sends command ``UCAN_COMMAND_START``, subcmd 0, mode ``UCAN_MODE_BERR_REPORT`` diff --git a/Documentation/networking/dpaa2/overview.rst b/Documentation/networking/dpaa2/overview.rst index 79fede4447d6..d638b5a8aadd 100644 --- a/Documentation/networking/dpaa2/overview.rst +++ b/Documentation/networking/dpaa2/overview.rst @@ -1,5 +1,6 @@ .. include:: <isonum.txt> +========================================================= DPAA2 (Data Path Acceleration Architecture Gen2) Overview ========================================================= diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index f0ae9b65dfba..fcd710f2cc7a 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -6,9 +6,11 @@ Contents: .. toctree:: :maxdepth: 2 + netdev-FAQ af_xdp batman-adv can + can_ucan_protocol dpaa2/index e100 e1000 diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 77c37fb0b6a6..e74515ecaa9c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -81,6 +81,15 @@ fib_multipath_hash_policy - INTEGER 0 - Layer 3 1 - Layer 4 +ip_forward_update_priority - INTEGER + Whether to update SKB priority from "TOS" field in IPv4 header after it + is forwarded. The new SKB priority is mapped from TOS field value + according to an rt_tos2priority table (see e.g. man tc-prio). + Default: 1 (Update priority.) + Possible values: + 0 - Do not update priority. + 1 - Update priority. + route/max_size - INTEGER Maximum number of routes allowed in the kernel. Increase this when using large numbers of interfaces and/or routes. diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst new file mode 100644 index 000000000000..0ac5fa77f501 --- /dev/null +++ b/Documentation/networking/netdev-FAQ.rst @@ -0,0 +1,259 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _netdev-FAQ: + +========== +netdev FAQ +========== + +Q: What is netdev? +------------------ +A: It is a mailing list for all network-related Linux stuff. This +includes anything found under net/ (i.e. core code like IPv6) and +drivers/net (i.e. hardware specific drivers) in the Linux source tree. + +Note that some subsystems (e.g. wireless drivers) which have a high +volume of traffic have their own specific mailing lists. + +The netdev list is managed (like many other Linux mailing lists) through +VGER (http://vger.kernel.org/) and archives can be found below: + +- http://marc.info/?l=linux-netdev +- http://www.spinics.net/lists/netdev/ + +Aside from subsystems like that mentioned above, all network-related +Linux development (i.e. RFC, review, comments, etc.) takes place on +netdev. + +Q: How do the changes posted to netdev make their way into Linux? +----------------------------------------------------------------- +A: There are always two trees (git repositories) in play. Both are +driven by David Miller, the main network maintainer. There is the +``net`` tree, and the ``net-next`` tree. As you can probably guess from +the names, the ``net`` tree is for fixes to existing code already in the +mainline tree from Linus, and ``net-next`` is where the new code goes +for the future release. You can find the trees here: + +- https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git +- https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git + +Q: How often do changes from these trees make it to the mainline Linus tree? +---------------------------------------------------------------------------- +A: To understand this, you need to know a bit of background information on +the cadence of Linux development. Each new release starts off with a +two week "merge window" where the main maintainers feed their new stuff +to Linus for merging into the mainline tree. After the two weeks, the +merge window is closed, and it is called/tagged ``-rc1``. No new +features get mainlined after this -- only fixes to the rc1 content are +expected. After roughly a week of collecting fixes to the rc1 content, +rc2 is released. This repeats on a roughly weekly basis until rc7 +(typically; sometimes rc6 if things are quiet, or rc8 if things are in a +state of churn), and a week after the last vX.Y-rcN was done, the +official vX.Y is released. + +Relating that to netdev: At the beginning of the 2-week merge window, +the ``net-next`` tree will be closed - no new changes/features. The +accumulated new content of the past ~10 weeks will be passed onto +mainline/Linus via a pull request for vX.Y -- at the same time, the +``net`` tree will start accumulating fixes for this pulled content +relating to vX.Y + +An announcement indicating when ``net-next`` has been closed is usually +sent to netdev, but knowing the above, you can predict that in advance. + +IMPORTANT: Do not send new ``net-next`` content to netdev during the +period during which ``net-next`` tree is closed. + +Shortly after the two weeks have passed (and vX.Y-rc1 is released), the +tree for ``net-next`` reopens to collect content for the next (vX.Y+1) +release. + +If you aren't subscribed to netdev and/or are simply unsure if +``net-next`` has re-opened yet, simply check the ``net-next`` git +repository link above for any new networking-related commits. You may +also check the following website for the current status: + + http://vger.kernel.org/~davem/net-next.html + +The ``net`` tree continues to collect fixes for the vX.Y content, and is +fed back to Linus at regular (~weekly) intervals. Meaning that the +focus for ``net`` is on stabilization and bug fixes. + +Finally, the vX.Y gets released, and the whole cycle starts over. + +Q: So where are we now in this cycle? + +Load the mainline (Linus) page here: + + https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +and note the top of the "tags" section. If it is rc1, it is early in +the dev cycle. If it was tagged rc7 a week ago, then a release is +probably imminent. + +Q: How do I indicate which tree (net vs. net-next) my patch should be in? +------------------------------------------------------------------------- +A: Firstly, think whether you have a bug fix or new "next-like" content. +Then once decided, assuming that you use git, use the prefix flag, i.e. +:: + + git format-patch --subject-prefix='PATCH net-next' start..finish + +Use ``net`` instead of ``net-next`` (always lower case) in the above for +bug-fix ``net`` content. If you don't use git, then note the only magic +in the above is just the subject text of the outgoing e-mail, and you +can manually change it yourself with whatever MUA you are comfortable +with. + +Q: I sent a patch and I'm wondering what happened to it? +-------------------------------------------------------- +Q: How can I tell whether it got merged? +A: Start by looking at the main patchworks queue for netdev: + + http://patchwork.ozlabs.org/project/netdev/list/ + +The "State" field will tell you exactly where things are at with your +patch. + +Q: The above only says "Under Review". How can I find out more? +---------------------------------------------------------------- +A: Generally speaking, the patches get triaged quickly (in less than +48h). So be patient. Asking the maintainer for status updates on your +patch is a good way to ensure your patch is ignored or pushed to the +bottom of the priority list. + +Q: I submitted multiple versions of the patch series +---------------------------------------------------- +Q: should I directly update patchwork for the previous versions of these +patch series? +A: No, please don't interfere with the patch status on patchwork, leave +it to the maintainer to figure out what is the most recent and current +version that should be applied. If there is any doubt, the maintainer +will reply and ask what should be done. + +Q: How can I tell what patches are queued up for backporting to the various stable releases? +-------------------------------------------------------------------------------------------- +A: Normally Greg Kroah-Hartman collects stable commits himself, but for +networking, Dave collects up patches he deems critical for the +networking subsystem, and then hands them off to Greg. + +There is a patchworks queue that you can see here: + + http://patchwork.ozlabs.org/bundle/davem/stable/?state=* + +It contains the patches which Dave has selected, but not yet handed off +to Greg. If Greg already has the patch, then it will be here: + + https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git + +A quick way to find whether the patch is in this stable-queue is to +simply clone the repo, and then git grep the mainline commit ID, e.g. +:: + + stable-queue$ git grep -l 284041ef21fdf2e + releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch + releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch + releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch + stable/stable-queue$ + +Q: I see a network patch and I think it should be backported to stable. +----------------------------------------------------------------------- +Q: Should I request it via stable@vger.kernel.org like the references in +the kernel's Documentation/process/stable-kernel-rules.rst file say? +A: No, not for networking. Check the stable queues as per above first +to see if it is already queued. If not, then send a mail to netdev, +listing the upstream commit ID and why you think it should be a stable +candidate. + +Before you jump to go do the above, do note that the normal stable rules +in :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>` +still apply. So you need to explicitly indicate why it is a critical +fix and exactly what users are impacted. In addition, you need to +convince yourself that you *really* think it has been overlooked, +vs. having been considered and rejected. + +Generally speaking, the longer it has had a chance to "soak" in +mainline, the better the odds that it is an OK candidate for stable. So +scrambling to request a commit be added the day after it appears should +be avoided. + +Q: I have created a network patch and I think it should be backported to stable. +-------------------------------------------------------------------------------- +Q: Should I add a Cc: stable@vger.kernel.org like the references in the +kernel's Documentation/ directory say? +A: No. See above answer. In short, if you think it really belongs in +stable, then ensure you write a decent commit log that describes who +gets impacted by the bug fix and how it manifests itself, and when the +bug was introduced. If you do that properly, then the commit will get +handled appropriately and most likely get put in the patchworks stable +queue if it really warrants it. + +If you think there is some valid information relating to it being in +stable that does *not* belong in the commit log, then use the three dash +marker line as described in +:ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>` +to temporarily embed that information into the patch that you send. + +Q: Are all networking bug fixes backported to all stable releases? +------------------------------------------------------------------ +A: Due to capacity, Dave could only take care of the backports for the +last two stable releases. For earlier stable releases, each stable +branch maintainer is supposed to take care of them. If you find any +patch is missing from an earlier stable branch, please notify +stable@vger.kernel.org with either a commit ID or a formal patch +backported, and CC Dave and other relevant networking developers. + +Q: Is the comment style convention different for the networking content? +------------------------------------------------------------------------ +A: Yes, in a largely trivial way. Instead of this:: + + /* + * foobar blah blah blah + * another line of text + */ + +it is requested that you make it look like this:: + + /* foobar blah blah blah + * another line of text + */ + +Q: I am working in existing code that has the former comment style and not the latter. +-------------------------------------------------------------------------------------- +Q: Should I submit new code in the former style or the latter? +A: Make it the latter style, so that eventually all code in the domain +of netdev is of this format. + +Q: I found a bug that might have possible security implications or similar. +--------------------------------------------------------------------------- +Q: Should I mail the main netdev maintainer off-list?** +A: No. The current netdev maintainer has consistently requested that +people use the mailing lists and not reach out directly. If you aren't +OK with that, then perhaps consider mailing security@kernel.org or +reading about http://oss-security.openwall.org/wiki/mailing-lists/distros +as possible alternative mechanisms. + +Q: What level of testing is expected before I submit my change? +--------------------------------------------------------------- +A: If your changes are against ``net-next``, the expectation is that you +have tested by layering your changes on top of ``net-next``. Ideally +you will have done run-time testing specific to your change, but at a +minimum, your changes should survive an ``allyesconfig`` and an +``allmodconfig`` build without new warnings or failures. + +Q: Any other tips to help ensure my net/net-next patch gets OK'd? +----------------------------------------------------------------- +A: Attention to detail. Re-read your own work as if you were the +reviewer. You can start with using ``checkpatch.pl``, perhaps even with +the ``--strict`` flag. But do not be mindlessly robotic in doing so. +If your change is a bug fix, make sure your commit log indicates the +end-user visible symptom, the underlying reason as to why it happens, +and then if necessary, explain why the fix proposed is the best way to +get things done. Don't mangle whitespace, and as is common, don't +mis-indent function arguments that span multiple lines. If it is your +first patch, mail it to yourself so you can test apply it to an +unpatched tree to confirm infrastructure didn't mangle it. + +Finally, go back and read +:ref:`Documentation/process/submitting-patches.rst <submittingpatches>` +to be sure you are not repeating some common mistake documented there. diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt deleted file mode 100644 index fa951b820b25..000000000000 --- a/Documentation/networking/netdev-FAQ.txt +++ /dev/null @@ -1,244 +0,0 @@ - -Information you need to know about netdev ------------------------------------------ - -Q: What is netdev? - -A: It is a mailing list for all network-related Linux stuff. This includes - anything found under net/ (i.e. core code like IPv6) and drivers/net - (i.e. hardware specific drivers) in the Linux source tree. - - Note that some subsystems (e.g. wireless drivers) which have a high volume - of traffic have their own specific mailing lists. - - The netdev list is managed (like many other Linux mailing lists) through - VGER ( http://vger.kernel.org/ ) and archives can be found below: - - http://marc.info/?l=linux-netdev - http://www.spinics.net/lists/netdev/ - - Aside from subsystems like that mentioned above, all network-related Linux - development (i.e. RFC, review, comments, etc.) takes place on netdev. - -Q: How do the changes posted to netdev make their way into Linux? - -A: There are always two trees (git repositories) in play. Both are driven - by David Miller, the main network maintainer. There is the "net" tree, - and the "net-next" tree. As you can probably guess from the names, the - net tree is for fixes to existing code already in the mainline tree from - Linus, and net-next is where the new code goes for the future release. - You can find the trees here: - - https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git - https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git - -Q: How often do changes from these trees make it to the mainline Linus tree? - -A: To understand this, you need to know a bit of background information - on the cadence of Linux development. Each new release starts off with - a two week "merge window" where the main maintainers feed their new - stuff to Linus for merging into the mainline tree. After the two weeks, - the merge window is closed, and it is called/tagged "-rc1". No new - features get mainlined after this -- only fixes to the rc1 content - are expected. After roughly a week of collecting fixes to the rc1 - content, rc2 is released. This repeats on a roughly weekly basis - until rc7 (typically; sometimes rc6 if things are quiet, or rc8 if - things are in a state of churn), and a week after the last vX.Y-rcN - was done, the official "vX.Y" is released. - - Relating that to netdev: At the beginning of the 2-week merge window, - the net-next tree will be closed - no new changes/features. The - accumulated new content of the past ~10 weeks will be passed onto - mainline/Linus via a pull request for vX.Y -- at the same time, - the "net" tree will start accumulating fixes for this pulled content - relating to vX.Y - - An announcement indicating when net-next has been closed is usually - sent to netdev, but knowing the above, you can predict that in advance. - - IMPORTANT: Do not send new net-next content to netdev during the - period during which net-next tree is closed. - - Shortly after the two weeks have passed (and vX.Y-rc1 is released), the - tree for net-next reopens to collect content for the next (vX.Y+1) release. - - If you aren't subscribed to netdev and/or are simply unsure if net-next - has re-opened yet, simply check the net-next git repository link above for - any new networking-related commits. You may also check the following - website for the current status: - - http://vger.kernel.org/~davem/net-next.html - - The "net" tree continues to collect fixes for the vX.Y content, and - is fed back to Linus at regular (~weekly) intervals. Meaning that the - focus for "net" is on stabilization and bugfixes. - - Finally, the vX.Y gets released, and the whole cycle starts over. - -Q: So where are we now in this cycle? - -A: Load the mainline (Linus) page here: - - https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git - - and note the top of the "tags" section. If it is rc1, it is early - in the dev cycle. If it was tagged rc7 a week ago, then a release - is probably imminent. - -Q: How do I indicate which tree (net vs. net-next) my patch should be in? - -A: Firstly, think whether you have a bug fix or new "next-like" content. - Then once decided, assuming that you use git, use the prefix flag, i.e. - - git format-patch --subject-prefix='PATCH net-next' start..finish - - Use "net" instead of "net-next" (always lower case) in the above for - bug-fix net content. If you don't use git, then note the only magic in - the above is just the subject text of the outgoing e-mail, and you can - manually change it yourself with whatever MUA you are comfortable with. - -Q: I sent a patch and I'm wondering what happened to it. How can I tell - whether it got merged? - -A: Start by looking at the main patchworks queue for netdev: - - http://patchwork.ozlabs.org/project/netdev/list/ - - The "State" field will tell you exactly where things are at with - your patch. - -Q: The above only says "Under Review". How can I find out more? - -A: Generally speaking, the patches get triaged quickly (in less than 48h). - So be patient. Asking the maintainer for status updates on your - patch is a good way to ensure your patch is ignored or pushed to - the bottom of the priority list. - -Q: I submitted multiple versions of the patch series, should I directly update - patchwork for the previous versions of these patch series? - -A: No, please don't interfere with the patch status on patchwork, leave it to - the maintainer to figure out what is the most recent and current version that - should be applied. If there is any doubt, the maintainer will reply and ask - what should be done. - -Q: How can I tell what patches are queued up for backporting to the - various stable releases? - -A: Normally Greg Kroah-Hartman collects stable commits himself, but - for networking, Dave collects up patches he deems critical for the - networking subsystem, and then hands them off to Greg. - - There is a patchworks queue that you can see here: - http://patchwork.ozlabs.org/bundle/davem/stable/?state=* - - It contains the patches which Dave has selected, but not yet handed - off to Greg. If Greg already has the patch, then it will be here: - https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git - - A quick way to find whether the patch is in this stable-queue is - to simply clone the repo, and then git grep the mainline commit ID, e.g. - - stable-queue$ git grep -l 284041ef21fdf2e - releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch - releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch - releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch - stable/stable-queue$ - -Q: I see a network patch and I think it should be backported to stable. - Should I request it via "stable@vger.kernel.org" like the references in - the kernel's Documentation/process/stable-kernel-rules.rst file say? - -A: No, not for networking. Check the stable queues as per above 1st to see - if it is already queued. If not, then send a mail to netdev, listing - the upstream commit ID and why you think it should be a stable candidate. - - Before you jump to go do the above, do note that the normal stable rules - in Documentation/process/stable-kernel-rules.rst still apply. So you need to - explicitly indicate why it is a critical fix and exactly what users are - impacted. In addition, you need to convince yourself that you _really_ - think it has been overlooked, vs. having been considered and rejected. - - Generally speaking, the longer it has had a chance to "soak" in mainline, - the better the odds that it is an OK candidate for stable. So scrambling - to request a commit be added the day after it appears should be avoided. - -Q: I have created a network patch and I think it should be backported to - stable. Should I add a "Cc: stable@vger.kernel.org" like the references - in the kernel's Documentation/ directory say? - -A: No. See above answer. In short, if you think it really belongs in - stable, then ensure you write a decent commit log that describes who - gets impacted by the bugfix and how it manifests itself, and when the - bug was introduced. If you do that properly, then the commit will - get handled appropriately and most likely get put in the patchworks - stable queue if it really warrants it. - - If you think there is some valid information relating to it being in - stable that does _not_ belong in the commit log, then use the three - dash marker line as described in Documentation/process/submitting-patches.rst to - temporarily embed that information into the patch that you send. - -Q: Are all networking bug fixes backported to all stable releases? - -A: Due to capacity, Dave could only take care of the backports for the last - 2 stable releases. For earlier stable releases, each stable branch maintainer - is supposed to take care of them. If you find any patch is missing from an - earlier stable branch, please notify stable@vger.kernel.org with either a - commit ID or a formal patch backported, and CC Dave and other relevant - networking developers. - -Q: Someone said that the comment style and coding convention is different - for the networking content. Is this true? - -A: Yes, in a largely trivial way. Instead of this: - - /* - * foobar blah blah blah - * another line of text - */ - - it is requested that you make it look like this: - - /* foobar blah blah blah - * another line of text - */ - -Q: I am working in existing code that has the former comment style and not the - latter. Should I submit new code in the former style or the latter? - -A: Make it the latter style, so that eventually all code in the domain of - netdev is of this format. - -Q: I found a bug that might have possible security implications or similar. - Should I mail the main netdev maintainer off-list? - -A: No. The current netdev maintainer has consistently requested that people - use the mailing lists and not reach out directly. If you aren't OK with - that, then perhaps consider mailing "security@kernel.org" or reading about - http://oss-security.openwall.org/wiki/mailing-lists/distros - as possible alternative mechanisms. - -Q: What level of testing is expected before I submit my change? - -A: If your changes are against net-next, the expectation is that you - have tested by layering your changes on top of net-next. Ideally you - will have done run-time testing specific to your change, but at a - minimum, your changes should survive an "allyesconfig" and an - "allmodconfig" build without new warnings or failures. - -Q: Any other tips to help ensure my net/net-next patch gets OK'd? - -A: Attention to detail. Re-read your own work as if you were the - reviewer. You can start with using checkpatch.pl, perhaps even - with the "--strict" flag. But do not be mindlessly robotic in - doing so. If your change is a bug-fix, make sure your commit log - indicates the end-user visible symptom, the underlying reason as - to why it happens, and then if necessary, explain why the fix proposed - is the best way to get things done. Don't mangle whitespace, and as - is common, don't mis-indent function arguments that span multiple lines. - If it is your first patch, mail it to yourself so you can test apply - it to an unpatched tree to confirm infrastructure didn't mangle it. - - Finally, go back and read Documentation/process/submitting-patches.rst to be - sure you are not repeating some common mistake documented there. diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst index 36a2dded525b..0de6f6145cc6 100644 --- a/Documentation/process/stable-kernel-rules.rst +++ b/Documentation/process/stable-kernel-rules.rst @@ -37,7 +37,7 @@ Procedure for submitting patches to the -stable tree - If the patch covers files in net/ or drivers/net please follow netdev stable submission guidelines as described in - Documentation/networking/netdev-FAQ.txt + :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>` - Security patches should not be handled (solely) by the -stable review process but should follow the procedures in :ref:`Documentation/admin-guide/security-bugs.rst <securitybugs>`. diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index 908bb55be407..c0917107b90a 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -611,6 +611,7 @@ which stable kernel versions should receive your fix. This is the preferred method for indicating a bug fixed by the patch. See :ref:`describe_changes` for more details. +.. _the_canonical_patch_format: 14) The canonical patch format ------------------------------ diff --git a/MAINTAINERS b/MAINTAINERS index fce04d747a1a..82f277462349 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5444,6 +5444,7 @@ F: drivers/iommu/exynos-iommu.c EZchip NPS platform support M: Vineet Gupta <vgupta@synopsys.com> +M: Ofer Levi <oferle@mellanox.com> S: Supported F: arch/arc/plat-eznps F: arch/arc/boot/dts/eznps.dts @@ -7095,6 +7096,7 @@ F: include/uapi/linux/input.h F: include/uapi/linux/input-event-codes.h F: include/linux/input/ F: Documentation/devicetree/bindings/input/ +F: Documentation/devicetree/bindings/serio/ F: Documentation/input/ INPUT MULTITOUCH (MT) PROTOCOL @@ -7984,7 +7986,7 @@ F: lib/test_kmod.c F: tools/testing/selftests/kmod/ KPROBES -M: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> +M: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> @@ -9074,7 +9076,7 @@ S: Maintained F: drivers/usb/mtu3/ MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES -M: Peter Senna Tschudin <peter.senna@collabora.com> +M: Peter Senna Tschudin <peter.senna@gmail.com> M: Martin Donnelly <martin.donnelly@ge.com> M: Martyn Welch <martyn.welch@collabora.co.uk> S: Maintained @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc8 NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 6e921754c8fc..c210a25dd6da 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, struct rusage32 __user *, ur) { - unsigned int status = 0; struct rusage r; - long err = kernel_wait4(pid, &status, options, &r); + long err = kernel_wait4(pid, ustatus, options, &r); if (err <= 0) return err; - if (put_user(status, ustatus)) - return -EFAULT; if (!ur) return err; if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime)) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 9cf59fc60eab..5151d81476a1 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -50,6 +50,9 @@ config ARC select HAVE_KERNEL_LZMA select ARCH_HAS_PTE_SPECIAL +config ARCH_HAS_CACHE_LINE_SIZE + def_bool y + config MIGHT_HAVE_PCI bool diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 8486f328cc5d..ff7d3232764a 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -48,7 +48,9 @@ }) /* Largest line length for either L1 or L2 is 128 bytes */ -#define ARCH_DMA_MINALIGN 128 +#define SMP_CACHE_BYTES 128 +#define cache_line_size() SMP_CACHE_BYTES +#define ARCH_DMA_MINALIGN SMP_CACHE_BYTES extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index d5da2115d78a..03d6bb0f4e13 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -17,8 +17,11 @@ #ifndef __ASM_ARC_UDELAY_H #define __ASM_ARC_UDELAY_H +#include <asm-generic/types.h> #include <asm/param.h> /* HZ */ +extern unsigned long loops_per_jiffy; + static inline void __delay(unsigned long loops) { __asm__ __volatile__( diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 9dbe645ee127..25c631942500 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm) void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, unsigned long pfn) { - unsigned int paddr = pfn << PAGE_SHIFT; + phys_addr_t paddr = pfn << PAGE_SHIFT; u_vaddr &= PAGE_MASK; @@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long u_vaddr) { /* TBD: do we really need to clear the kernel mapping */ - __flush_dcache_page(page_address(page), u_vaddr); - __flush_dcache_page(page_address(page), page_address(page)); + __flush_dcache_page((phys_addr_t)page_address(page), u_vaddr); + __flush_dcache_page((phys_addr_t)page_address(page), + (phys_addr_t)page_address(page)); } @@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void) } } + /* + * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger + * or equal to any cache line length. + */ + BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES, + "SMP_CACHE_BYTES must be >= any cache line length"); + if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES)) + panic("L2 Cache line [%d] > kernel Config [%d]\n", + l2_line_sz, SMP_CACHE_BYTES); + /* Note that SLC disable not formally supported till HS 3.0 */ if (is_isa_arcv2() && l2_line_sz && !slc_enable) arc_slc_disable(); diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 8c1071840979..ec47e6079f5d 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } +/* + * Cache operations depending on function and direction argument, inspired by + * https://lkml.org/lkml/2018/5/18/979 + * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20] + * dma-mapping: provide a generic dma-noncoherent implementation)" + * + * | map == for_device | unmap == for_cpu + * |---------------------------------------------------------------- + * TO_DEV | writeback writeback | none none + * FROM_DEV | invalidate invalidate | invalidate* invalidate* + * BIDIR | writeback+inv writeback+inv | invalidate invalidate + * + * [*] needed for CPU speculative prefetches + * + * NOTE: we don't check the validity of direction argument as it is done in + * upper layer functions (in include/linux/dma-mapping.h) + */ + void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_wback(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + dma_cache_wback(paddr, size); + break; + + case DMA_FROM_DEVICE: + dma_cache_inv(paddr, size); + break; + + case DMA_BIDIRECTIONAL: + dma_cache_wback_inv(paddr, size); + break; + + default: + break; + } } void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_inv(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + break; + + /* FROM_DEVICE invalidate needed if speculative CPU prefetch only */ + case DMA_FROM_DEVICE: + case DMA_BIDIRECTIONAL: + dma_cache_inv(paddr, size); + break; + + default: + break; + } } diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index 0c7d11022d0f..4f6a1673b3a6 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -21,6 +21,7 @@ #error "Incorrect ctop.h include" #endif +#include <linux/types.h> #include <soc/nps/common.h> /* core auxiliary registers */ @@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst { }; /* AUX registers definition */ +struct nps_host_reg_aux_dpc { + union { + struct { + u32 ien:1, men:1, hen:1, reserved:29; + }; + u32 value; + }; +}; + struct nps_host_reg_aux_udmc { union { struct { diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c index 2388de3d09ef..ed0077ef666e 100644 --- a/arch/arc/plat-eznps/mtm.c +++ b/arch/arc/plat-eznps/mtm.c @@ -15,6 +15,8 @@ */ #include <linux/smp.h> +#include <linux/init.h> +#include <linux/kernel.h> #include <linux/io.h> #include <linux/log2.h> #include <asm/arcregs.h> @@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu) /* Verify and set the value of the mtm hs counter */ static int __init set_mtm_hs_ctr(char *ctr_str) { - long hs_ctr; + int hs_ctr; int ret; - ret = kstrtol(ctr_str, 0, &hs_ctr); + ret = kstrtoint(ctr_str, 0, &hs_ctr); if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) { pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n", diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi index 19a075aee19e..f14df0baf2ab 100644 --- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi @@ -692,7 +692,7 @@ dsa,member = <0 0>; eeprom-length = <512>; interrupt-parent = <&gpio6>; - interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index bdf73cbcec3a..e7c3c563ff8f 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -159,13 +159,7 @@ dais = <&mcbsp2_port>, <&mcbsp3_port>; }; -}; - -&dss { - status = "okay"; -}; -&gpio6 { pwm8: dmtimer-pwm-8 { pinctrl-names = "default"; pinctrl-0 = <&vibrator_direction_pin>; @@ -192,7 +186,10 @@ pwm-names = "enable", "direction"; direction-duty-cycle-ns = <10000000>; }; +}; +&dss { + status = "okay"; }; &dsi1 { diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 106a1466518d..746565a876dc 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -48,6 +48,7 @@ saved_pc .req lr * from those features make this path too inefficient. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts @@ -78,6 +79,7 @@ fast_work_pending: * call. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 @@ -255,7 +257,7 @@ local_restart: tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls? bne __sys_trace - invoke_syscall tbl, scno, r10, ret_fast_syscall + invoke_syscall tbl, scno, r10, __ret_fast_syscall add r1, sp, #S_OFF 2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 225d1c58d2de..d9c299133111 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = { static int __init gate_vma_init(void) { + vma_init(&gate_vma, NULL); gate_vma.vm_page_prot = PAGE_READONLY_EXEC; return 0; } diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 39aef4876ed4..04b2f22c2739 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -212,7 +212,7 @@ static DEFINE_MUTEX(ecard_mutex); */ static void ecard_init_pgtables(struct mm_struct *mm) { - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC); /* We want to set up the page tables for the following mapping: * Virtual Physical @@ -237,9 +237,6 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); - vma.vm_flags = VM_EXEC; - vma.vm_mm = mm; - flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE); flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE); } diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index 4057197048dc..1a406a76c86a 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -482,9 +482,9 @@ status = "disabled"; }; - mdio_mux_iproc: mdio-mux@6602023c { + mdio_mux_iproc: mdio-mux@66020000 { compatible = "brcm,mdio-mux-iproc"; - reg = <0x6602023c 0x14>; + reg = <0x66020000 0x250>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index b203152ad67c..a70e8ddbd66f 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -278,9 +278,9 @@ #include "stingray-pinctrl.dtsi" - mdio_mux_iproc: mdio-mux@2023c { + mdio_mux_iproc: mdio-mux@20000 { compatible = "brcm,mdio-mux-iproc"; - reg = <0x0002023c 0x14>; + reg = <0x00020000 0x250>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index a56a408e9bf7..4664c33e0763 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -80,4 +80,5 @@ ptp_timer0: ptp-timer@1afe000 { compatible = "fsl,fman-ptp-timer"; reg = <0x0 0x1afe000 0x0 0x1000>; interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 7cf0b1aa6ea8..8a10f1d7199a 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req) err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } - if (walk.nbytes) - pmull_gcm_encrypt_block(iv, iv, NULL, + if (walk.nbytes) { + kernel_neon_begin(); + pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc, num_rounds(&ctx->aes_key)); + kernel_neon_end(); + } + } else { __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, num_rounds(&ctx->aes_key)); diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index ffdaea7954bb..0ad1cf233470 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); /* * The ASID allocator will either invalidate the ASID or mark diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f24892a40d2c..c6d80743f4ed 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void update_cpu_capabilities(u16 scope_mask) { - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); __update_cpu_capabilities(arm64_errata, scope_mask, "enabling workaround for"); + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); } static int __enable_cpu_capability(void *arg) @@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void __init enable_cpu_capabilities(u16 scope_mask) { - __enable_cpu_capabilities(arm64_features, scope_mask); __enable_cpu_capabilities(arm64_errata, scope_mask); + __enable_cpu_capabilities(arm64_features, scope_mask); } /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ecc6818191df..192b3ba07075 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; pte_t orig_pte = huge_ptep_get(ptep); bool valid = pte_valid(orig_pte); unsigned long i, saddr = addr; @@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm, orig_pte = pte_mkdirty(orig_pte); } - if (valid) + if (valid) { + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, saddr, addr); + } return orig_pte; } @@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325cfb3b858a..9abf8a1e7b25 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -611,11 +611,13 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Make sure we chose the upper bound of sizeof(struct page) - * correctly. + * correctly when sizing the VMEMMAP array. */ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); +#endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 44f0ac0df308..516355a774bf 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -115,12 +115,11 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned flush_tlb_all(); } else { /* - * XXX fix me: flush_tlb_range() should take an mm pointer instead of a - * vma pointer. + * flush_tlb_range() takes a vma instead of a mm pointer because + * some architectures want the vm_flags for ITLB/DTLB flush. */ - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); - vma.vm_mm = tlb->mm; /* flush the address range from the tlb: */ flush_tlb_range(&vma, start, end); /* now flush the virt. page-table area mapping the address range: */ diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 3b38c717008a..46bff1661836 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("smpl_buf @%p\n", smpl_buf)); /* allocate vma */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { DPRINT(("Cannot allocate vma\n")); goto error_kmem; } - INIT_LIST_HEAD(&vma->anon_vma_chain); /* * partially initialize the vma for the sampling buffer */ - vma->vm_mm = mm; vma->vm_file = get_file(filp); vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ @@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t return 0; error: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); error_kmem: pfm_rvfree(smpl_buf, size); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 18278b448530..3b85c3ecac38 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -114,10 +114,9 @@ ia64_init_addr_space (void) * the problem. When the process attempts to write to the register backing store * for the first time, it will get a SEGFAULT in this case. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; + vma_set_anonymous(vma); vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; @@ -125,7 +124,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -133,10 +132,9 @@ ia64_init_addr_space (void) /* map NaT-page at address zero to speed up speculative dereferencing of NULL: */ if (!(current->personality & MMAP_PAGE_ZERO)) { - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; + vma_set_anonymous(vma); vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | @@ -144,7 +142,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -277,7 +275,7 @@ static struct vm_area_struct gate_vma; static int __init gate_vma_init(void) { - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 10a405d593df..c782b10ddf50 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init); void ath79_ddr_wb_flush(u32 reg) { - void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg; + void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4); /* Flush the DDR write buffer. */ __raw_writel(0x1, flush_reg); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 8c9cbf13d32a..6054d49e608e 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; - - /* - * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" - * Enable ExternalSync for sync instruction to take effect - */ - set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 0bc270806ec5..ae461d91cd1f 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -681,8 +681,6 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) -/* ExternalSync */ -#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -2767,7 +2765,6 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) -__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 9632436d74d7..c2e94cf5ecda 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, phys_addr_t size = resource_size(rsrc); *start = fixup_bigphys_addr(rsrc->start, size); - *end = rsrc->start + size; + *end = rsrc->start + size - 1; } diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 2ea575cb3401..fb96206de317 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -243,6 +243,7 @@ endif cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 +cpu-as-$(CONFIG_E500) += -Wa,-me500 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi index 6b124f73f67a..9b6cf9149937 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi @@ -100,4 +100,5 @@ ptp_timer0: ptp-timer@4fe000 { compatible = "fsl,fman-ptp-timer"; reg = <0x4fe000 0x1000>; interrupts = <96 2 0 0>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi index b80aaf5f00a1..e95c11ff0417 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi @@ -100,4 +100,5 @@ ptp_timer1: ptp-timer@5fe000 { compatible = "fsl,fman-ptp-timer"; reg = <0x5fe000 0x1000>; interrupts = <97 2 0 0>; + clocks = <&clockgen 3 1>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi index d3720fdde26c..d62b36c5a329 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi @@ -105,4 +105,5 @@ ptp_timer0: ptp-timer@4fe000 { compatible = "fsl,fman-ptp-timer"; reg = <0x4fe000 0x1000>; interrupts = <96 2 0 0>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi index ae34c204a5bc..310232460500 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi @@ -105,4 +105,5 @@ ptp_timer1: ptp-timer@5fe000 { compatible = "fsl,fman-ptp-timer"; reg = <0x5fe000 0x1000>; interrupts = <97 2 0 0>; + clocks = <&clockgen 3 1>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi index 02f2755842cc..c90702b04a53 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi @@ -93,4 +93,5 @@ ptp_timer0: ptp-timer@4fe000 { compatible = "fsl,fman-ptp-timer"; reg = <0x4fe000 0x1000>; interrupts = <96 2 0 0>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 896efa559996..b2f89b621b15 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif @@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) { int c; - c = atomic_dec_if_positive(&mm->context.copros); - - /* Detect imbalance between add and remove */ - WARN_ON(c < 0); - /* - * Need to broadcast a global flush of the full mm before - * decrementing active_cpus count, as the next TLBI may be - * local and the nMMU and/or PSL need to be cleaned up. - * Should be rare enough so that it's acceptable. + * When removing the last copro, we need to broadcast a global + * flush of the full mm, as the next TLBI may be local and the + * nMMU and/or PSL need to be cleaned up. + * + * Both the 'copros' and 'active_cpus' counts are looked at in + * flush_all_mm() to determine the scope (local/global) of the + * TLBIs, so we need to flush first before decrementing + * 'copros'. If this API is used by several callers for the + * same context, it can lead to over-flushing. It's hopefully + * not common enough to be a problem. * * Skip on hash, as we don't know how to do the proper flush * for the time being. Invalidations will remain global if - * used on hash. + * used on hash. Note that we can't drop 'copros' either, as + * it could make some invalidations local with no flush + * in-between. */ - if (c == 0 && radix_enabled()) { + if (radix_enabled()) { flush_all_mm(mm); - dec_mm_active_cpus(mm); + + c = atomic_dec_if_positive(&mm->context.copros); + /* Detect imbalance between add and remove */ + WARN_ON(c < 0); + + if (c == 0) + dec_mm_active_cpus(mm); } } #else diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index e734f6e45abc..689306118b48 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -144,7 +144,9 @@ power9_restore_additional_sprs: mtspr SPRN_MMCR1, r4 ld r3, STOP_MMCR2(r13) + ld r4, PACA_SPRG_VDSO(r13) mtspr SPRN_MMCR2, r3 + mtspr SPRN_SPRG3, r4 blr /* diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fe9733ffffaa..471aac313b89 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -42,6 +42,8 @@ #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include "../../../drivers/pci/pci.h" + /* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pcibios_setup_device(dev); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d066e37551ec..8c456fa691a5 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, /* This only handles v2 IOMMU type, v1 is handled via ioctl() */ return H_TOO_HARD; - if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa))) + if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa))) return H_HARDWARE; if (mm_iommu_mapped_inc(mem)) diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 925fc316a104..5b298f5a1a14 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (!mem) return H_TOO_HARD; - if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa))) + if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift, + &hpa))) return H_HARDWARE; pua = (void *) vmalloc_to_phys(pua); @@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K); if (mem) - prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0; + prereg = mm_iommu_ua_to_hpa_rm(mem, ua, + IOMMU_PAGE_SHIFT_4K, &tces) == 0; } if (!prereg) { diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index abb43646927a..a4ca57612558 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -19,6 +19,7 @@ #include <linux/hugetlb.h> #include <linux/swap.h> #include <asm/mmu_context.h> +#include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); @@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t { struct rcu_head rcu; unsigned long used; atomic64_t mapped; + unsigned int pageshift; u64 ua; /* userspace address */ u64 entries; /* number of entries in hpas[] */ u64 *hpas; /* vmalloc'ed */ @@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, { struct mm_iommu_table_group_mem_t *mem; long i, j, ret = 0, locked_entries = 0; + unsigned int pageshift; + unsigned long flags; struct page *page = NULL; mutex_lock(&mem_list_mutex); @@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, goto unlock_exit; } + /* + * For a starting point for a maximum page size calculation + * we use @ua and @entries natural alignment to allow IOMMU pages + * smaller than huge pages but still bigger than PAGE_SIZE. + */ + mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT)); mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0]))); if (!mem->hpas) { kfree(mem); @@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, } } populate: + pageshift = PAGE_SHIFT; + if (PageCompound(page)) { + pte_t *pte; + struct page *head = compound_head(page); + unsigned int compshift = compound_order(head); + + local_irq_save(flags); /* disables as well */ + pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift); + local_irq_restore(flags); + + /* Double check it is still the same pinned page */ + if (pte && pte_page(*pte) == head && + pageshift == compshift) + pageshift = max_t(unsigned int, pageshift, + PAGE_SHIFT); + } + mem->pageshift = min(mem->pageshift, pageshift); mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } @@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, EXPORT_SYMBOL_GPL(mm_iommu_find); long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; u64 *va = &mem->hpas[entry]; @@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + *hpa = *va | (ua & ~PAGE_MASK); return 0; @@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa); long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; void *va = &mem->hpas[entry]; @@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + pa = (void *) vmalloc_to_phys(va); if (!pa) return -EFAULT; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 380cbf9a40d9..c0a9bcd28356 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u64 imm64; u8 *func; u32 true_cond; + u32 tmp_idx; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -637,11 +638,7 @@ emit_clear: case BPF_STX | BPF_XADD | BPF_W: /* Get EA into TMP_REG_1 */ PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not word-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); + tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); /* add value from src_reg into this */ @@ -649,32 +646,16 @@ emit_clear: /* store result back */ PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); - /* otherwise, let's try once more */ - PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - /* exit if the store was not successful */ - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not doubleword-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4)); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); - PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); + tmp_idx = ctx->idx * 4; PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5bd0eb6681bc..70b2e1e0f23c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -46,6 +46,7 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" #define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */ #define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */ @@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; pdn = pci_get_pdn(pdev); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 139f0af6c3d9..8a4868a3964b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -71,6 +71,7 @@ #include <asm/security_features.h> #include "pseries.h" +#include "../../../../drivers/pci/pci.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; @@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 47166ad2a669..196978733e64 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, { int nr, dotted; unsigned long first_adr; - unsigned long inst, last_inst = 0; + unsigned int inst, last_inst = 0; unsigned char val[4]; dotted = 0; @@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %.8lx", adr, inst); + printf(REG" %.8x", adr, inst); printf("\t"); dump_func(inst, adr); printf("\n"); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e44bb2b2873e..8a1863d9ed53 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -140,7 +140,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_GCC_PLUGINS + select HAVE_GCC_PLUGINS if BROKEN select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index ac67828da201..410b263ef5c8 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h +generic-y += msi.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h diff --git a/arch/sparc/include/asm/msi.h b/arch/sparc/include/asm/msi.h deleted file mode 100644 index 3c17c1074431..000000000000 --- a/arch/sparc/include/asm/msi.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * msi.h: Defines specific to the MBus - Sbus - Interface. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be) - */ - -#ifndef _SPARC_MSI_H -#define _SPARC_MSI_H - -/* - * Locations of MSI Registers. - */ -#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ - -/* - * Useful bits in the MSI Registers. - */ -#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ - - -static inline void msi_set_sync(void) -{ - __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" - "andn %%g3, %2, %%g3\n\t" - "sta %%g3, [%0] %1\n\t" : : - "r" (MSI_MBUS_ARBEN), - "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); -} - -#endif /* !(_SPARC_MSI_H) */ diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 2ef8cfa9677e..f0eba72aa1ad 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -814,7 +814,7 @@ static void __init get_tick_patch(void) } } -static void init_tick_ops(struct sparc64_tick_ops *ops) +static void __init init_tick_ops(struct sparc64_tick_ops *ops) { unsigned long freq, quotient, tick; diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 1d70c3f6d986..be9cb0065179 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -37,7 +37,6 @@ #include <asm/mbus.h> #include <asm/page.h> #include <asm/asi.h> -#include <asm/msi.h> #include <asm/smp.h> #include <asm/io.h> @@ -116,6 +115,25 @@ static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp) set_pte((pte_t *)ctxp, pte); } +/* + * Locations of MSI Registers. + */ +#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ + +/* + * Useful bits in the MSI Registers. + */ +#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ + +static void msi_set_sync(void) +{ + __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" + "andn %%g3, %2, %%g3\n\t" + "sta %%g3, [%0] %1\n\t" : : + "r" (MSI_MBUS_ARBEN), + "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); +} + void pmd_set(pmd_t *pmdp, pte_t *ptep) { unsigned long ptp; /* Physical address, shifted right by 4 */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f1dbb4ee19d7..887d3a7bb646 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -63,7 +63,7 @@ config X86 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 - select ARCH_HAS_UACCESS_MCSAFE if X86_64 + select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fa42f895fdde..169c2feda14a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -106,9 +106,13 @@ define cmd_check_data_rel done endef +# We need to run two commands under "if_changed", so merge them into a +# single invocation. +quiet_cmd_check-and-link-vmlinux = LD $@ + cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) + $(obj)/vmlinux: $(vmlinux-objs-y) FORCE - $(call if_changed,check_data_rel) - $(call if_changed,ld) + $(call if_changed,check-and-link-vmlinux) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 8c5107545251..9e2157371491 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,3 +1,4 @@ +#include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" #include "../string.h" @@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data); extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); +static unsigned long find_trampoline_placement(void) +{ + unsigned long bios_start, ebda_start; + unsigned long trampoline_start; + struct boot_e820_entry *entry; + int i; + + /* + * Find a suitable spot for the trampoline. + * This code is based on reserve_bios_regions(). + */ + + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; + + if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) + bios_start = BIOS_START_MAX; + + if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) + bios_start = ebda_start; + + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Find the first usable memory region under bios_start. */ + for (i = boot_params->e820_entries - 1; i >= 0; i--) { + entry = &boot_params->e820_table[i]; + + /* Skip all entries above bios_start. */ + if (bios_start <= entry->addr) + continue; + + /* Skip non-RAM entries. */ + if (entry->type != E820_TYPE_RAM) + continue; + + /* Adjust bios_start to the end of the entry if needed. */ + if (bios_start > entry->addr + entry->size) + bios_start = entry->addr + entry->size; + + /* Keep bios_start page-aligned. */ + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Skip the entry if it's too small. */ + if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr) + continue; + + break; + } + + /* Place the trampoline just below the end of low memory */ + return bios_start - TRAMPOLINE_32BIT_SIZE; +} + struct paging_config paging_prepare(void *rmode) { struct paging_config paging_config = {}; - unsigned long bios_start, ebda_start; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ boot_params = rmode; @@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode) paging_config.l5_required = 1; } - /* - * Find a suitable spot for the trampoline. - * This code is based on reserve_bios_regions(). - */ - - ebda_start = *(unsigned short *)0x40e << 4; - bios_start = *(unsigned short *)0x413 << 10; - - if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) - bios_start = BIOS_START_MAX; - - if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) - bios_start = ebda_start; - - /* Place the trampoline just below the end of low memory, aligned to 4k */ - paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE; - paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE); + paging_config.trampoline_start = find_trampoline_placement(); trampoline_32bit = (unsigned long *)paging_config.trampoline_start; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 73a522d53b53..8ae7ffda8f98 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -981,7 +981,7 @@ ENTRY(\sym) call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit .endif END(\sym) .endm @@ -1222,7 +1222,6 @@ END(paranoid_exit) /* * Save all registers in pt_regs, and switch GS if needed. - * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) UNWIND_HINT_FUNC @@ -1269,7 +1268,6 @@ ENTRY(error_entry) * for these here too. */ .Lerror_kernelspace: - incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) je .Lerror_bad_iret @@ -1303,28 +1301,20 @@ ENTRY(error_entry) /* * Pretend that the exception came from user mode: set up pt_regs - * as if we faulted immediately after IRET and clear EBX so that - * error_exit knows that we will be returning to user mode. + * as if we faulted immediately after IRET. */ mov %rsp, %rdi call fixup_bad_iret mov %rax, %rsp - decl %ebx jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) - -/* - * On entry, EBX is a "return to kernel mode" flag: - * 1: already in kernel mode, don't need SWAPGS - * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode - */ ENTRY(error_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - testl %ebx, %ebx - jnz retint_kernel + testb $3, CS(%rsp) + jz retint_kernel jmp retint_user END(error_exit) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 4b98101209a1..d50bb4dc0650 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) { struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); struct perf_event *event = pcpu->event; - struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event *hwc; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; @@ -602,6 +602,10 @@ fail: return 0; } + if (WARN_ON_ONCE(!event)) + goto fail; + + hwc = &event->hw; msr = hwc->config_base; buf = ibs_data.regs; rdmsrl(msr, *buf); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 707b2a96e516..86f0c15dcc2d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); + + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8a10a045b57b..8dbba77e0518 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu) ds->bts_buffer_base = (unsigned long) cea; ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL); ds->bts_index = ds->bts_buffer_base; - max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE); - ds->bts_absolute_maximum = ds->bts_buffer_base + max; - ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16); + max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; + ds->bts_absolute_maximum = ds->bts_buffer_base + + max * BTS_RECORD_SIZE; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - + (max / 16) * BTS_RECORD_SIZE; return 0; } @@ -1184,16 +1186,20 @@ static void setup_pebs_sample_data(struct perf_event *event, } /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happend between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + /* * We use the interrupt regs as a base because the PEBS record does not * contain a full regs set, specifically it seems to lack segment * descriptors, which get used by things like user_mode(). * * In the simple case fix up only the IP for PERF_SAMPLE_IP. - * - * We must however always use BP,SP from iregs for the unwinder to stay - * sane; the record BP,SP can point into thin air when the record is - * from a previous PMI context or an (I)RET happend between the record - * and PMI. */ *regs = *iregs; @@ -1212,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->si = pebs->si; regs->di = pebs->di; - /* - * Per the above; only set BP,SP if we don't need callchains. - * - * XXX: does this make sense? - */ - if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { - regs->bp = pebs->bp; - regs->sp = pebs->sp; - } + regs->bp = pebs->bp; + regs->sp = pebs->sp; #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index c9e1e0bef3c3..e17ab885b1e9 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -28,7 +28,7 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 3 +#define UNCORE_EXTRA_PCI_DEV_MAX 4 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 87dc0263a2e1..51d7c117e3c7 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void) enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, + BDX_PCI_QPI_PORT2_FILTER, HSWEP_PCI_PCU_3, }; @@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { }, { /* QPI Port 0 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), }, { /* QPI Port 1 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* QPI Port 2 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + BDX_PCI_QPI_PORT2_FILTER), }, { /* PCU.3 (for Capability registers) */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index c356098b6fb9..4d4015ddcf26 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,8 +7,6 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H -#include <asm/nospec-branch.h> - #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 9ef5ee03d2d7..159622ee0674 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -43,7 +43,7 @@ asm (".pushsection .text;" "push %rdx;" "mov $0x1,%eax;" "xor %edx,%edx;" - "lock cmpxchg %dl,(%rdi);" + LOCK_PREFIX "cmpxchg %dl,(%rdi);" "cmp $0x1,%al;" "jne .slowpath;" "pop %rdx;" diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 62acb613114b..a9d637bc301d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len) unsigned long ret; __uaccess_begin(); - ret = memcpy_mcsafe(to, from, len); + /* + * Note, __memcpy_mcsafe() is explicitly used since it can + * handle exceptions / faults. memcpy_mcsafe() may fall back to + * memcpy() which lacks this handling. + */ + ret = __memcpy_mcsafe(to, from, len); __uaccess_end(); return ret; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2aabd4cb0e3f..adbda5847b14 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,6 +573,9 @@ static u32 skx_deadline_rev(void) case 0x04: return 0x02000014; } + if (boot_cpu_data.x86_stepping > 4) + return 0; + return ~0U; } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5d0de79fdab0..ec00d1ff5098 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -240,6 +240,7 @@ #include <asm/olpc.h> #include <asm/paravirt.h> #include <asm/reboot.h> +#include <asm/nospec-branch.h> #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) extern int (*console_blank_hook)(int); @@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; apm_bios_call_asm(call->func, call->ebx, call->ecx, &call->eax, &call->ebx, &call->ecx, &call->edx, &call->esi); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); @@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, &call->eax); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c102ad51025e..8c50754c09c1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2165,9 +2165,6 @@ static ssize_t store_int_with_restart(struct device *s, if (check_interval == old_check_interval) return ret; - if (check_interval < 1) - check_interval = 1; - mutex_lock(&mce_sysfs_mutex); mce_restart(); mutex_unlock(&mce_sysfs_mutex); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d594690d8b95..6b8f11521c41 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = (void *)__get_free_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e30da9a2430c..5d8e317c2b04 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7893,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + vmx->nested.vpid02 = allocate_vpid(); + vmx->nested.vmxon = true; return 0; @@ -8480,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - gva_t vmcs_gva; + unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; + gva_t gva; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, &vmcs_gva)) + if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, vmcs_gva, - (void *)&to_vmx(vcpu)->nested.current_vmptr, - sizeof(u64), &e)) { + if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, + sizeof(gpa_t), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } @@ -10370,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) { + if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, kvm_vcpu_apicv_active(&vmx->vcpu)); - vmx->nested.vpid02 = allocate_vpid(); - } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -10391,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: - free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 55799873ebe5..8f6cc71e0848 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* sub esp,STACK_SIZE */ EMIT2_off32(0x81, 0xEC, STACK_SIZE); - /* sub ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16); + /* sub ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12); /* xor ebx,ebx */ EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX)); @@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) /* mov edx,dword ptr [ebp+off]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1])); - /* add ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16); + /* add ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12); /* mov ebx,dword ptr [ebp-12]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 77873ce700ae..5f2eb3231607 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; - if (sev_active()) + if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO) flags |= _PAGE_ENC; pfn = md->phys_addr >> PAGE_SHIFT; diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 744afdc18cf3..56c44d865f7b 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) if (!FIXADDR_USER_START) return 0; - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/block/bio.c b/block/bio.c index 67eff5eddc49..047c5dca6d90 100644 --- a/block/bio.c +++ b/block/bio.c @@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page, EXPORT_SYMBOL(bio_add_page); /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins as many pages from *iter and appends them to @bio's bvec array. The + * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. + * For multi-segment *iter, this function only adds pages from the + * the next non-empty segment of the iov iterator. */ -int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { - unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - size_t offset, diff; + size_t offset; ssize_t size; size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; - nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; + idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; /* * Deep magic below: We need to walk the pinned pages backwards @@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) bio->bi_iter.bi_size += size; bio->bi_vcnt += nr_pages; - diff = (nr_pages * PAGE_SIZE - offset) - size; - while (nr_pages--) { - bv[nr_pages].bv_page = pages[nr_pages]; - bv[nr_pages].bv_len = PAGE_SIZE; - bv[nr_pages].bv_offset = 0; + while (idx--) { + bv[idx].bv_page = pages[idx]; + bv[idx].bv_len = PAGE_SIZE; + bv[idx].bv_offset = 0; } bv[0].bv_offset += offset; bv[0].bv_len -= offset; - if (diff) - bv[bio->bi_vcnt - 1].bv_len -= diff; + bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size; iov_iter_advance(iter, size); return 0; } + +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + * The function tries, but does not guarantee, to pin as many pages as + * fit into the bio, or are requested in *iter, whatever is smaller. + * If MM encounters an error pinning the requested pages, it stops. + * Error is returned only if 0 pages could be pinned. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short orig_vcnt = bio->bi_vcnt; + + do { + int ret = __bio_iov_iter_get_pages(bio, iter); + + if (unlikely(ret)) + return bio->bi_vcnt > orig_vcnt ? 0 : ret; + + } while (iov_iter_count(iter) && !bio_full(bio)); + + return 0; +} EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) @@ -1866,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); + bio->bi_iter.bi_done = 0; if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); diff --git a/block/blk-core.c b/block/blk-core.c index f84a9b7b6f5a..ee33590f54eb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2155,11 +2155,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) if (part->policy && op_is_write(bio_op(bio))) { char b[BDEVNAME_SIZE]; - printk(KERN_ERR + WARN_ONCE(1, "generic_make_request: Trying to write " "to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); - return true; + /* Older lvm-tools actually trigger this */ + return false; } return false; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 09b2ee6694fb..3de0836163c2 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -271,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * test and set the bit before assining ->rqs[]. */ rq = tags->rqs[bitnr]; - if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) + if (rq && blk_mq_request_started(rq)) iter_data->fn(rq, iter_data->data, reserved); return true; diff --git a/block/blk-mq.c b/block/blk-mq.c index 95919268564b..654b0dc7e001 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq) bool shared = false; int cpu; - if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) != - MQ_RQ_IN_FLIGHT) + if (!blk_mq_mark_complete(rq)) return; - if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index c166f424871c..b053179e0bc5 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1071,7 +1071,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock, struct af_alg_ctx *ctx = ask->private; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; if (!ctx->more || ctx->used) diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index f8fecfec5df9..9706613eecf9 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -879,6 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev) #define LPSS_GPIODEF0_DMA_LLP BIT(13) static DEFINE_MUTEX(lpss_iosf_mutex); +static bool lpss_iosf_d3_entered; static void lpss_iosf_enter_d3_state(void) { @@ -921,6 +922,9 @@ static void lpss_iosf_enter_d3_state(void) iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE, LPSS_IOSF_GPIODEF0, value1, mask1); + + lpss_iosf_d3_entered = true; + exit: mutex_unlock(&lpss_iosf_mutex); } @@ -935,6 +939,11 @@ static void lpss_iosf_exit_d3_state(void) mutex_lock(&lpss_iosf_mutex); + if (!lpss_iosf_d3_entered) + goto exit; + + lpss_iosf_d3_entered = false; + iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE, LPSS_IOSF_GPIODEF0, value1, mask1); @@ -944,13 +953,13 @@ static void lpss_iosf_exit_d3_state(void) iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE, LPSS_IOSF_PMCSR, value2, mask2); +exit: mutex_unlock(&lpss_iosf_mutex); } -static int acpi_lpss_suspend(struct device *dev, bool runtime) +static int acpi_lpss_suspend(struct device *dev, bool wakeup) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); - bool wakeup = runtime || device_may_wakeup(dev); int ret; if (pdata->dev_desc->flags & LPSS_SAVE_CTX) @@ -963,14 +972,14 @@ static int acpi_lpss_suspend(struct device *dev, bool runtime) * wrong status for devices being about to be powered off. See * lpss_iosf_enter_d3_state() for further information. */ - if ((runtime || !pm_suspend_via_firmware()) && + if (acpi_target_system_state() == ACPI_STATE_S0 && lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_enter_d3_state(); return ret; } -static int acpi_lpss_resume(struct device *dev, bool runtime) +static int acpi_lpss_resume(struct device *dev) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; @@ -979,8 +988,7 @@ static int acpi_lpss_resume(struct device *dev, bool runtime) * This call is kept first to be in symmetry with * acpi_lpss_runtime_suspend() one. */ - if ((runtime || !pm_resume_via_firmware()) && - lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) + if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_exit_d3_state(); ret = acpi_dev_resume(dev); @@ -1004,12 +1012,12 @@ static int acpi_lpss_suspend_late(struct device *dev) return 0; ret = pm_generic_suspend_late(dev); - return ret ? ret : acpi_lpss_suspend(dev, false); + return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev)); } static int acpi_lpss_resume_early(struct device *dev) { - int ret = acpi_lpss_resume(dev, false); + int ret = acpi_lpss_resume(dev); return ret ? ret : pm_generic_resume_early(dev); } @@ -1024,7 +1032,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev) static int acpi_lpss_runtime_resume(struct device *dev) { - int ret = acpi_lpss_resume(dev, true); + int ret = acpi_lpss_resume(dev); return ret ? ret : pm_generic_runtime_resume(dev); } diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index bc5f05906bd1..44f35ab3347d 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -497,6 +497,18 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) status = acpi_ps_create_op(walk_state, aml_op_start, &op); if (ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by + * executing it as a control method. However, if we encounter + * an error while loading the table, we need to keep trying to + * load the table rather than aborting the table load. Set the + * status to AE_OK to proceed with the table load. + */ + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status == AE_ALREADY_EXISTS) { + status = AE_OK; + } if (status == AE_CTRL_PARSE_CONTINUE) { continue; } @@ -694,6 +706,25 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) acpi_ps_next_parse_state(walk_state, op, status); if (status == AE_CTRL_PENDING) { status = AE_OK; + } else + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status != AE_CTRL_TRANSFER + && ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL flag means that we are currently + * loading a table by executing it as a control method. + * However, if we encounter an error while loading the table, + * we need to keep trying to load the table rather than + * aborting the table load (setting the status to AE_OK + * continues the table load). If we get a failure at this + * point, it means that the dispatcher got an error while + * processing Op (most likely an AML operand error) or a + * control method was called from module level and the + * dispatcher returned AE_CTRL_TRANSFER. In the latter case, + * leave the status alone, there's nothing wrong with it. + */ + status = AE_OK; } } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 1435d7281c66..6ebcd65d64b6 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -434,14 +434,6 @@ re_probe: goto probe_failed; } - /* - * Ensure devices are listed in devices_kset in correct order - * It's important to move Dev to the end of devices_kset before - * calling .probe, because it could be recursive and parent Dev - * should always go first - */ - devices_kset_move_last(dev); - if (dev->bus->probe) { ret = dev->bus->probe(dev); if (ret) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index e07401d3901d..3863c00372bb 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -112,12 +112,16 @@ struct nbd_device { struct task_struct *task_setup; }; +#define NBD_CMD_REQUEUED 1 + struct nbd_cmd { struct nbd_device *nbd; + struct mutex lock; int index; int cookie; - struct completion send_complete; blk_status_t status; + unsigned long flags; + u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd) return disk_to_dev(nbd->disk); } +static void nbd_requeue_cmd(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) + blk_mq_requeue_request(req, true); +} + +#define NBD_COOKIE_BITS 32 + +static u64 nbd_cmd_handle(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + u32 tag = blk_mq_unique_tag(req); + u64 cookie = cmd->cmd_cookie; + + return (cookie << NBD_COOKIE_BITS) | tag; +} + +static u32 nbd_handle_to_tag(u64 handle) +{ + return (u32)handle; +} + +static u32 nbd_handle_to_cookie(u64 handle) +{ + return (u32)(handle >> NBD_COOKIE_BITS); +} + static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { @@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } config = nbd->config; + if (!mutex_trylock(&cmd->lock)) + return BLK_EH_RESET_TIMER; + if (config->num_connections > 1) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", @@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - blk_mq_requeue_request(req, true); + mutex_unlock(&cmd->lock); + nbd_requeue_cmd(cmd); nbd_config_put(nbd); return BLK_EH_DONE; } @@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } set_bit(NBD_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; + mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); done: @@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) struct iov_iter from; unsigned long size = blk_rq_bytes(req); struct bio *bio; + u64 handle; u32 type; u32 nbd_cmd_flags = 0; - u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); @@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) goto send_pages; } iov_iter_advance(&from, sent); + } else { + cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; @@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); } - memcpy(request.handle, &tag, sizeof(tag)); + handle = nbd_cmd_handle(cmd); + memcpy(request.handle, &handle, sizeof(handle)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), @@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; } + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -541,6 +583,7 @@ send_pages: */ nsock->pending = req; nsock->sent = sent; + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), @@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; + u64 handle; u16 hwq; u32 tag; struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; struct iov_iter to; + int ret = 0; reply.magic = 0; iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); @@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-EPROTO); } - memcpy(&tag, reply.handle, sizeof(u32)); - + memcpy(&handle, reply.handle, sizeof(handle)); + tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], @@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-ENOENT); } cmd = blk_mq_rq_to_pdu(req); + + mutex_lock(&cmd->lock); + if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { + dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", + req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); + ret = -ENOENT; + goto out; + } + if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", + req); + ret = -ENOENT; + goto out; + } if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); @@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (nbd_disconnected(config) || config->num_connections <= 1) { cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } - return ERR_PTR(-EIO); + ret = -EIO; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", req, bvec.bv_len); } - } else { - /* See the comment in nbd_queue_rq. */ - wait_for_completion(&cmd->send_complete); } - return cmd; +out: + mutex_unlock(&cmd->lock); + return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) @@ -805,7 +864,7 @@ again: */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; goto out; } @@ -818,7 +877,7 @@ again: dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; } out: @@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ - init_completion(&cmd->send_complete); + mutex_lock(&cmd->lock); + clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In @@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_IOERR; else if (!ret) ret = BLK_STS_OK; - complete(&cmd->send_complete); + mutex_unlock(&cmd->lock); return ret; } @@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; + cmd->flags = 0; + mutex_init(&cmd->lock); return 0; } diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig index f3c643a0473c..5f953ca8ac5b 100644 --- a/drivers/bluetooth/Kconfig +++ b/drivers/bluetooth/Kconfig @@ -159,6 +159,7 @@ config BT_HCIUART_LL config BT_HCIUART_3WIRE bool "Three-wire UART (H5) protocol support" depends on BT_HCIUART + depends on BT_HCIUART_SERDEV help The HCI Three-wire UART Transport Layer makes it possible to user the Bluetooth HCI over a serial port interface. The HCI diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c index ab090a313a5f..0588639b899a 100644 --- a/drivers/bluetooth/bfusb.c +++ b/drivers/bluetooth/bfusb.c @@ -490,7 +490,7 @@ static int bfusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb) count = skb->len; /* Max HCI frame size seems to be 1511 + 1 */ - nskb = bt_skb_alloc(count + 32, GFP_ATOMIC); + nskb = bt_skb_alloc(count + 32, GFP_KERNEL); if (!nskb) { BT_ERR("Can't allocate memory for new packet"); return -ENOMEM; diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c index 82437a69f99c..cc6e56223656 100644 --- a/drivers/bluetooth/bluecard_cs.c +++ b/drivers/bluetooth/bluecard_cs.c @@ -565,7 +565,7 @@ static int bluecard_hci_set_baud_rate(struct hci_dev *hdev, int baud) /* Ericsson baud rate command */ unsigned char cmd[] = { HCI_COMMAND_PKT, 0x09, 0xfc, 0x01, 0x03 }; - skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_ATOMIC); + skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_KERNEL); if (!skb) { BT_ERR("Can't allocate mem for new packet"); return -1; diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c index c6f7cc57db14..d1c2adf08576 100644 --- a/drivers/bluetooth/bpa10x.c +++ b/drivers/bluetooth/bpa10x.c @@ -289,7 +289,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb) skb->dev = (void *) hdev; - urb = usb_alloc_urb(0, GFP_ATOMIC); + urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) return -ENOMEM; @@ -298,7 +298,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb) switch (hci_skb_pkt_type(skb)) { case HCI_COMMAND_PKT: - dr = kmalloc(sizeof(*dr), GFP_ATOMIC); + dr = kmalloc(sizeof(*dr), GFP_KERNEL); if (!dr) { usb_free_urb(urb); return -ENOMEM; @@ -343,7 +343,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb) usb_anchor_urb(urb, &data->tx_anchor); - err = usb_submit_urb(urb, GFP_ATOMIC); + err = usb_submit_urb(urb, GFP_KERNEL); if (err < 0) { bt_dev_err(hdev, "urb %p submission failed", urb); kfree(urb->setup_packet); diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 888bac49a87b..fb3d03928460 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -718,7 +718,7 @@ static int btmrvl_sdio_card_to_host(struct btmrvl_private *priv) } /* Allocate buffer */ - skb = bt_skb_alloc(num_blocks * blksz + BTSDIO_DMA_ALIGN, GFP_ATOMIC); + skb = bt_skb_alloc(num_blocks * blksz + BTSDIO_DMA_ALIGN, GFP_KERNEL); if (!skb) { BT_ERR("No free skb"); ret = -ENOMEM; diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 8219816c54a0..488f5e7521dd 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -27,7 +27,7 @@ #define VERSION "0.1" -static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version) +int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version) { struct sk_buff *skb; struct edl_event_hdr *edl; @@ -35,36 +35,35 @@ static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version) char cmd; int err = 0; - BT_DBG("%s: ROME Patch Version Request", hdev->name); + bt_dev_dbg(hdev, "QCA Version Request"); cmd = EDL_PATCH_VER_REQ_CMD; skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN, &cmd, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); - BT_ERR("%s: Failed to read version of ROME (%d)", hdev->name, - err); + bt_dev_err(hdev, "Reading QCA version information failed (%d)", + err); return err; } if (skb->len != sizeof(*edl) + sizeof(*ver)) { - BT_ERR("%s: Version size mismatch len %d", hdev->name, - skb->len); + bt_dev_err(hdev, "QCA Version size mismatch len %d", skb->len); err = -EILSEQ; goto out; } edl = (struct edl_event_hdr *)(skb->data); if (!edl) { - BT_ERR("%s: TLV with no header", hdev->name); + bt_dev_err(hdev, "QCA TLV with no header"); err = -EILSEQ; goto out; } if (edl->cresp != EDL_CMD_REQ_RES_EVT || edl->rtype != EDL_APP_VER_RES_EVT) { - BT_ERR("%s: Wrong packet received %d %d", hdev->name, - edl->cresp, edl->rtype); + bt_dev_err(hdev, "QCA Wrong packet received %d %d", edl->cresp, + edl->rtype); err = -EIO; goto out; } @@ -76,30 +75,35 @@ static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version) BT_DBG("%s: ROM :0x%08x", hdev->name, le16_to_cpu(ver->rome_ver)); BT_DBG("%s: SOC :0x%08x", hdev->name, le32_to_cpu(ver->soc_id)); - /* ROME chipset version can be decided by patch and SoC + /* QCA chipset version can be decided by patch and SoC * version, combination with upper 2 bytes from SoC * and lower 2 bytes from patch will be used. */ - *rome_version = (le32_to_cpu(ver->soc_id) << 16) | + *soc_version = (le32_to_cpu(ver->soc_id) << 16) | (le16_to_cpu(ver->rome_ver) & 0x0000ffff); + if (*soc_version == 0) + err = -EILSEQ; out: kfree_skb(skb); + if (err) + bt_dev_err(hdev, "QCA Failed to get version (%d)", err); return err; } +EXPORT_SYMBOL_GPL(qca_read_soc_version); -static int rome_reset(struct hci_dev *hdev) +static int qca_send_reset(struct hci_dev *hdev) { struct sk_buff *skb; int err; - BT_DBG("%s: ROME HCI_RESET", hdev->name); + bt_dev_dbg(hdev, "QCA HCI_RESET"); skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); - BT_ERR("%s: Reset failed (%d)", hdev->name, err); + bt_dev_err(hdev, "QCA Reset failed (%d)", err); return err; } @@ -108,7 +112,7 @@ static int rome_reset(struct hci_dev *hdev) return 0; } -static void rome_tlv_check_data(struct rome_config *config, +static void qca_tlv_check_data(struct rome_config *config, const struct firmware *fw) { const u8 *data; @@ -207,7 +211,7 @@ static void rome_tlv_check_data(struct rome_config *config, } } -static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size, +static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, const u8 *data, enum rome_tlv_dnld_mode mode) { struct sk_buff *skb; @@ -228,19 +232,19 @@ static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); - BT_ERR("%s: Failed to send TLV segment (%d)", hdev->name, err); + bt_dev_err(hdev, "QCA Failed to send TLV segment (%d)", err); return err; } if (skb->len != sizeof(*edl) + sizeof(*tlv_resp)) { - BT_ERR("%s: TLV response size mismatch", hdev->name); + bt_dev_err(hdev, "QCA TLV response size mismatch"); err = -EILSEQ; goto out; } edl = (struct edl_event_hdr *)(skb->data); if (!edl) { - BT_ERR("%s: TLV with no header", hdev->name); + bt_dev_err(hdev, "TLV with no header"); err = -EILSEQ; goto out; } @@ -249,8 +253,8 @@ static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size, if (edl->cresp != EDL_CMD_REQ_RES_EVT || edl->rtype != EDL_TVL_DNLD_RES_EVT || tlv_resp->result != 0x00) { - BT_ERR("%s: TLV with error stat 0x%x rtype 0x%x (0x%x)", - hdev->name, edl->cresp, edl->rtype, tlv_resp->result); + bt_dev_err(hdev, "QCA TLV with error stat 0x%x rtype 0x%x (0x%x)", + edl->cresp, edl->rtype, tlv_resp->result); err = -EIO; } @@ -260,23 +264,23 @@ out: return err; } -static int rome_download_firmware(struct hci_dev *hdev, +static int qca_download_firmware(struct hci_dev *hdev, struct rome_config *config) { const struct firmware *fw; const u8 *segment; int ret, remain, i = 0; - bt_dev_info(hdev, "ROME Downloading %s", config->fwname); + bt_dev_info(hdev, "QCA Downloading %s", config->fwname); ret = request_firmware(&fw, config->fwname, &hdev->dev); if (ret) { - BT_ERR("%s: Failed to request file: %s (%d)", hdev->name, - config->fwname, ret); + bt_dev_err(hdev, "QCA Failed to request file: %s (%d)", + config->fwname, ret); return ret; } - rome_tlv_check_data(config, fw); + qca_tlv_check_data(config, fw); segment = fw->data; remain = fw->size; @@ -290,7 +294,7 @@ static int rome_download_firmware(struct hci_dev *hdev, if (!remain || segsize < MAX_SIZE_PER_TLV_SEGMENT) config->dnld_mode = ROME_SKIP_EVT_NONE; - ret = rome_tlv_send_segment(hdev, segsize, segment, + ret = qca_tlv_send_segment(hdev, segsize, segment, config->dnld_mode); if (ret) break; @@ -317,8 +321,7 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) HCI_VENDOR_PKT, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); - BT_ERR("%s: Change address command failed (%d)", - hdev->name, err); + bt_dev_err(hdev, "QCA Change address command failed (%d)", err); return err; } @@ -328,57 +331,65 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) } EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome); -int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate) +int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, + enum qca_btsoc_type soc_type, u32 soc_ver) { - u32 rome_ver = 0; struct rome_config config; int err; + u8 rom_ver; - BT_DBG("%s: ROME setup on UART", hdev->name); + bt_dev_dbg(hdev, "QCA setup on UART"); config.user_baud_rate = baudrate; - /* Get ROME version information */ - err = rome_patch_ver_req(hdev, &rome_ver); - if (err < 0 || rome_ver == 0) { - BT_ERR("%s: Failed to get version 0x%x", hdev->name, err); - return err; - } - - bt_dev_info(hdev, "ROME controller version 0x%08x", rome_ver); - /* Download rampatch file */ config.type = TLV_TYPE_PATCH; - snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin", - rome_ver); - err = rome_download_firmware(hdev, &config); + if (soc_type == QCA_WCN3990) { + /* Firmware files to download are based on ROM version. + * ROM version is derived from last two bytes of soc_ver. + */ + rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | + (soc_ver & 0x0000000f); + snprintf(config.fwname, sizeof(config.fwname), + "qca/crbtfw%02x.tlv", rom_ver); + } else { + snprintf(config.fwname, sizeof(config.fwname), + "qca/rampatch_%08x.bin", soc_ver); + } + + err = qca_download_firmware(hdev, &config); if (err < 0) { - BT_ERR("%s: Failed to download patch (%d)", hdev->name, err); + bt_dev_err(hdev, "QCA Failed to download patch (%d)", err); return err; } /* Download NVM configuration */ config.type = TLV_TYPE_NVM; - snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin", - rome_ver); - err = rome_download_firmware(hdev, &config); + if (soc_type == QCA_WCN3990) + snprintf(config.fwname, sizeof(config.fwname), + "qca/crnv%02x.bin", rom_ver); + else + snprintf(config.fwname, sizeof(config.fwname), + "qca/nvm_%08x.bin", soc_ver); + + err = qca_download_firmware(hdev, &config); if (err < 0) { - BT_ERR("%s: Failed to download NVM (%d)", hdev->name, err); + bt_dev_err(hdev, "QCA Failed to download NVM (%d)", err); return err; } /* Perform HCI reset */ - err = rome_reset(hdev); + err = qca_send_reset(hdev); if (err < 0) { - BT_ERR("%s: Failed to run HCI_RESET (%d)", hdev->name, err); + bt_dev_err(hdev, "QCA Failed to run HCI_RESET (%d)", err); return err; } - bt_dev_info(hdev, "ROME setup on UART is completed"); + bt_dev_info(hdev, "QCA setup on UART is completed"); return 0; } -EXPORT_SYMBOL_GPL(qca_uart_setup_rome); +EXPORT_SYMBOL_GPL(qca_uart_setup); MODULE_AUTHOR("Ben Young Tae Kim <ytkim@qca.qualcomm.com>"); MODULE_DESCRIPTION("Bluetooth support for Qualcomm Atheros family ver " VERSION); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index 13d77fd873b6..0c01f375fe83 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -37,6 +37,9 @@ #define EDL_TAG_ID_HCI (17) #define EDL_TAG_ID_DEEP_SLEEP (27) +#define QCA_WCN3990_POWERON_PULSE 0xFC +#define QCA_WCN3990_POWEROFF_PULSE 0xC0 + enum qca_bardrate { QCA_BAUDRATE_115200 = 0, QCA_BAUDRATE_57600, @@ -124,10 +127,19 @@ struct tlv_type_hdr { __u8 data[0]; } __packed; +enum qca_btsoc_type { + QCA_INVALID = -1, + QCA_AR3002, + QCA_ROME, + QCA_WCN3990 +}; + #if IS_ENABLED(CONFIG_BT_QCA) int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr); -int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate); +int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, + enum qca_btsoc_type soc_type, u32 soc_ver); +int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version); #else @@ -136,7 +148,13 @@ static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdad return -EOPNOTSUPP; } -static inline int qca_uart_setup_rome(struct hci_dev *hdev, int speed) +static inline int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, + enum qca_btsoc_type soc_type, u32 soc_ver) +{ + return -EOPNOTSUPP; +} + +static inline int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version) { return -EOPNOTSUPP; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 437f080deaab..7f9ea8e4c1b2 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -34,9 +34,12 @@ #define RTL_ROM_LMP_8821A 0x8821 #define RTL_ROM_LMP_8761A 0x8761 #define RTL_ROM_LMP_8822B 0x8822 +#define RTL_CONFIG_MAGIC 0x8723ab55 #define IC_MATCH_FL_LMPSUBV (1 << 0) #define IC_MATCH_FL_HCIREV (1 << 1) +#define IC_MATCH_FL_HCIVER (1 << 2) +#define IC_MATCH_FL_HCIBUS (1 << 3) #define IC_INFO(lmps, hcir) \ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV, \ .lmp_subver = (lmps), \ @@ -46,49 +49,130 @@ struct id_table { __u16 match_flags; __u16 lmp_subver; __u16 hci_rev; + __u8 hci_ver; + __u8 hci_bus; bool config_needed; + bool has_rom_version; char *fw_name; char *cfg_name; }; +struct btrtl_device_info { + const struct id_table *ic_info; + u8 rom_version; + u8 *fw_data; + int fw_len; + u8 *cfg_data; + int cfg_len; +}; + static const struct id_table ic_id_table[] = { + { IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8723A, 0x0, + .config_needed = false, + .has_rom_version = false, + .fw_name = "rtl_bt/rtl8723a_fw.bin", + .cfg_name = NULL }, + + { IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_3499, 0x0, + .config_needed = false, + .has_rom_version = false, + .fw_name = "rtl_bt/rtl8723a_fw.bin", + .cfg_name = NULL }, + + /* 8723BS */ + { .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV | + IC_MATCH_FL_HCIVER | IC_MATCH_FL_HCIBUS, + .lmp_subver = RTL_ROM_LMP_8723B, + .hci_rev = 0xb, + .hci_ver = 6, + .hci_bus = HCI_UART, + .config_needed = true, + .has_rom_version = true, + .fw_name = "rtl_bt/rtl8723bs_fw.bin", + .cfg_name = "rtl_bt/rtl8723bs_config" }, + /* 8723B */ { IC_INFO(RTL_ROM_LMP_8723B, 0xb), .config_needed = false, + .has_rom_version = true, .fw_name = "rtl_bt/rtl8723b_fw.bin", - .cfg_name = "rtl_bt/rtl8723b_config.bin" }, + .cfg_name = "rtl_bt/rtl8723b_config" }, /* 8723D */ { IC_INFO(RTL_ROM_LMP_8723B, 0xd), .config_needed = true, + .has_rom_version = true, .fw_name = "rtl_bt/rtl8723d_fw.bin", - .cfg_name = "rtl_bt/rtl8723d_config.bin" }, + .cfg_name = "rtl_bt/rtl8723d_config" }, + + /* 8723DS */ + { .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV | + IC_MATCH_FL_HCIVER | IC_MATCH_FL_HCIBUS, + .lmp_subver = RTL_ROM_LMP_8723B, + .hci_rev = 0xd, + .hci_ver = 8, + .hci_bus = HCI_UART, + .config_needed = true, + .has_rom_version = true, + .fw_name = "rtl_bt/rtl8723ds_fw.bin", + .cfg_name = "rtl_bt/rtl8723ds_config" }, /* 8821A */ { IC_INFO(RTL_ROM_LMP_8821A, 0xa), .config_needed = false, + .has_rom_version = true, .fw_name = "rtl_bt/rtl8821a_fw.bin", - .cfg_name = "rtl_bt/rtl8821a_config.bin" }, + .cfg_name = "rtl_bt/rtl8821a_config" }, /* 8821C */ { IC_INFO(RTL_ROM_LMP_8821A, 0xc), .config_needed = false, + .has_rom_version = true, .fw_name = "rtl_bt/rtl8821c_fw.bin", - .cfg_name = "rtl_bt/rtl8821c_config.bin" }, + .cfg_name = "rtl_bt/rtl8821c_config" }, /* 8761A */ { IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0, .config_needed = false, + .has_rom_version = true, .fw_name = "rtl_bt/rtl8761a_fw.bin", - .cfg_name = "rtl_bt/rtl8761a_config.bin" }, + .cfg_name = "rtl_bt/rtl8761a_config" }, /* 8822B */ { IC_INFO(RTL_ROM_LMP_8822B, 0xb), .config_needed = true, + .has_rom_version = true, .fw_name = "rtl_bt/rtl8822b_fw.bin", - .cfg_name = "rtl_bt/rtl8822b_config.bin" }, + .cfg_name = "rtl_bt/rtl8822b_config" }, }; +static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev, + u8 hci_ver, u8 hci_bus) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) { + if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) && + (ic_id_table[i].lmp_subver != lmp_subver)) + continue; + if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) && + (ic_id_table[i].hci_rev != hci_rev)) + continue; + if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIVER) && + (ic_id_table[i].hci_ver != hci_ver)) + continue; + if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIBUS) && + (ic_id_table[i].hci_bus != hci_bus)) + continue; + + break; + } + if (i >= ARRAY_SIZE(ic_id_table)) + return NULL; + + return &ic_id_table[i]; +} + static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) { struct rtl_rom_version_evt *rom_version; @@ -97,20 +181,20 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) /* Read RTL ROM version command */ skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s: Read ROM version failed (%ld)", - hdev->name, PTR_ERR(skb)); + rtl_dev_err(hdev, "Read ROM version failed (%ld)\n", + PTR_ERR(skb)); return PTR_ERR(skb); } if (skb->len != sizeof(*rom_version)) { - BT_ERR("%s: RTL version event length mismatch", hdev->name); + rtl_dev_err(hdev, "RTL version event length mismatch\n"); kfree_skb(skb); return -EIO; } rom_version = (struct rtl_rom_version_evt *)skb->data; - bt_dev_info(hdev, "rom_version status=%x version=%x", - rom_version->status, rom_version->version); + rtl_dev_info(hdev, "rom_version status=%x version=%x\n", + rom_version->status, rom_version->version); *version = rom_version->version; @@ -118,16 +202,16 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) return 0; } -static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, - const struct firmware *fw, +static int rtlbt_parse_firmware(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev, unsigned char **_buf) { const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 }; struct rtl_epatch_header *epatch_info; unsigned char *buf; - int i, ret, len; + int i, len; size_t min_size; - u8 opcode, length, data, rom_version = 0; + u8 opcode, length, data; int project_id = -1; const unsigned char *fwptr, *chip_id_base; const unsigned char *patch_length_base, *patch_offset_base; @@ -146,17 +230,13 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, { RTL_ROM_LMP_8821A, 10 }, /* 8821C */ }; - ret = rtl_read_rom_version(hdev, &rom_version); - if (ret) - return ret; - min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3; - if (fw->size < min_size) + if (btrtl_dev->fw_len < min_size) return -EINVAL; - fwptr = fw->data + fw->size - sizeof(extension_sig); + fwptr = btrtl_dev->fw_data + btrtl_dev->fw_len - sizeof(extension_sig); if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) { - BT_ERR("%s: extension section signature mismatch", hdev->name); + rtl_dev_err(hdev, "extension section signature mismatch\n"); return -EINVAL; } @@ -166,7 +246,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, * Once we have that, we double-check that that project_id is suitable * for the hardware we are working with. */ - while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) { + while (fwptr >= btrtl_dev->fw_data + (sizeof(*epatch_info) + 3)) { opcode = *--fwptr; length = *--fwptr; data = *--fwptr; @@ -177,8 +257,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, break; if (length == 0) { - BT_ERR("%s: found instruction with length 0", - hdev->name); + rtl_dev_err(hdev, "found instruction with length 0\n"); return -EINVAL; } @@ -191,7 +270,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, } if (project_id < 0) { - BT_ERR("%s: failed to find version instruction", hdev->name); + rtl_dev_err(hdev, "failed to find version instruction\n"); return -EINVAL; } @@ -202,19 +281,21 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, } if (i >= ARRAY_SIZE(project_id_to_lmp_subver)) { - BT_ERR("%s: unknown project id %d", hdev->name, project_id); + rtl_dev_err(hdev, "unknown project id %d\n", project_id); return -EINVAL; } - if (lmp_subver != project_id_to_lmp_subver[i].lmp_subver) { - BT_ERR("%s: firmware is for %x but this is a %x", hdev->name, - project_id_to_lmp_subver[i].lmp_subver, lmp_subver); + if (btrtl_dev->ic_info->lmp_subver != + project_id_to_lmp_subver[i].lmp_subver) { + rtl_dev_err(hdev, "firmware is for %x but this is a %x\n", + project_id_to_lmp_subver[i].lmp_subver, + btrtl_dev->ic_info->lmp_subver); return -EINVAL; } - epatch_info = (struct rtl_epatch_header *)fw->data; + epatch_info = (struct rtl_epatch_header *)btrtl_dev->fw_data; if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) { - BT_ERR("%s: bad EPATCH signature", hdev->name); + rtl_dev_err(hdev, "bad EPATCH signature\n"); return -EINVAL; } @@ -229,16 +310,16 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, * Find the right patch for this chip. */ min_size += 8 * num_patches; - if (fw->size < min_size) + if (btrtl_dev->fw_len < min_size) return -EINVAL; - chip_id_base = fw->data + sizeof(struct rtl_epatch_header); + chip_id_base = btrtl_dev->fw_data + sizeof(struct rtl_epatch_header); patch_length_base = chip_id_base + (sizeof(u16) * num_patches); patch_offset_base = patch_length_base + (sizeof(u16) * num_patches); for (i = 0; i < num_patches; i++) { u16 chip_id = get_unaligned_le16(chip_id_base + (i * sizeof(u16))); - if (chip_id == rom_version + 1) { + if (chip_id == btrtl_dev->rom_version + 1) { patch_length = get_unaligned_le16(patch_length_base + (i * sizeof(u16))); patch_offset = get_unaligned_le32(patch_offset_base + @@ -248,21 +329,22 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, } if (!patch_offset) { - BT_ERR("%s: didn't find patch for chip id %d", - hdev->name, rom_version); + rtl_dev_err(hdev, "didn't find patch for chip id %d", + btrtl_dev->rom_version); return -EINVAL; } BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i); min_size = patch_offset + patch_length; - if (fw->size < min_size) + if (btrtl_dev->fw_len < min_size) return -EINVAL; /* Copy the firmware into a new buffer and write the version at * the end. */ len = patch_length; - buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL); + buf = kmemdup(btrtl_dev->fw_data + patch_offset, patch_length, + GFP_KERNEL); if (!buf) return -ENOMEM; @@ -301,15 +383,14 @@ static int rtl_download_firmware(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s: download fw command failed (%ld)", - hdev->name, PTR_ERR(skb)); + rtl_dev_err(hdev, "download fw command failed (%ld)\n", + PTR_ERR(skb)); ret = -PTR_ERR(skb); goto out; } if (skb->len != sizeof(struct rtl_download_response)) { - BT_ERR("%s: download fw event length mismatch", - hdev->name); + rtl_dev_err(hdev, "download fw event length mismatch\n"); kfree_skb(skb); ret = -EIO; goto out; @@ -324,12 +405,12 @@ out: return ret; } -static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff) +static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff) { const struct firmware *fw; int ret; - bt_dev_info(hdev, "rtl: loading %s", name); + rtl_dev_info(hdev, "rtl: loading %s\n", name); ret = request_firmware(&fw, name, &hdev->dev); if (ret < 0) return ret; @@ -343,96 +424,37 @@ static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff) return ret; } -static int btrtl_setup_rtl8723a(struct hci_dev *hdev) +static int btrtl_setup_rtl8723a(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev) { - const struct firmware *fw; - int ret; - - bt_dev_info(hdev, "rtl: loading rtl_bt/rtl8723a_fw.bin"); - ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &hdev->dev); - if (ret < 0) { - BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name); - return ret; - } - - if (fw->size < 8) { - ret = -EINVAL; - goto out; - } + if (btrtl_dev->fw_len < 8) + return -EINVAL; /* Check that the firmware doesn't have the epatch signature * (which is only for RTL8723B and newer). */ - if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) { - BT_ERR("%s: unexpected EPATCH signature!", hdev->name); - ret = -EINVAL; - goto out; + if (!memcmp(btrtl_dev->fw_data, RTL_EPATCH_SIGNATURE, 8)) { + rtl_dev_err(hdev, "unexpected EPATCH signature!\n"); + return -EINVAL; } - ret = rtl_download_firmware(hdev, fw->data, fw->size); - -out: - release_firmware(fw); - return ret; + return rtl_download_firmware(hdev, btrtl_dev->fw_data, + btrtl_dev->fw_len); } -static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev, - u16 lmp_subver) +static int btrtl_setup_rtl8723b(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev) { unsigned char *fw_data = NULL; - const struct firmware *fw; int ret; - int cfg_sz; - u8 *cfg_buff = NULL; u8 *tbuff; - char *cfg_name = NULL; - char *fw_name = NULL; - int i; - for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) { - if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) && - (ic_id_table[i].lmp_subver != lmp_subver)) - continue; - if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) && - (ic_id_table[i].hci_rev != hci_rev)) - continue; - - break; - } - - if (i >= ARRAY_SIZE(ic_id_table)) { - BT_ERR("%s: unknown IC info, lmp subver %04x, hci rev %04x", - hdev->name, lmp_subver, hci_rev); - return -EINVAL; - } - - cfg_name = ic_id_table[i].cfg_name; - - if (cfg_name) { - cfg_sz = rtl_load_config(hdev, cfg_name, &cfg_buff); - if (cfg_sz < 0) { - cfg_sz = 0; - if (ic_id_table[i].config_needed) - BT_ERR("Necessary config file %s not found\n", - cfg_name); - } - } else - cfg_sz = 0; - - fw_name = ic_id_table[i].fw_name; - bt_dev_info(hdev, "rtl: loading %s", fw_name); - ret = request_firmware(&fw, fw_name, &hdev->dev); - if (ret < 0) { - BT_ERR("%s: Failed to load %s", hdev->name, fw_name); - goto err_req_fw; - } - - ret = rtlbt_parse_firmware(hdev, lmp_subver, fw, &fw_data); + ret = rtlbt_parse_firmware(hdev, btrtl_dev, &fw_data); if (ret < 0) goto out; - if (cfg_sz) { - tbuff = kzalloc(ret + cfg_sz, GFP_KERNEL); + if (btrtl_dev->cfg_len > 0) { + tbuff = kzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL); if (!tbuff) { ret = -ENOMEM; goto out; @@ -441,22 +463,18 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev, memcpy(tbuff, fw_data, ret); kfree(fw_data); - memcpy(tbuff + ret, cfg_buff, cfg_sz); - ret += cfg_sz; + memcpy(tbuff + ret, btrtl_dev->cfg_data, btrtl_dev->cfg_len); + ret += btrtl_dev->cfg_len; fw_data = tbuff; } - bt_dev_info(hdev, "cfg_sz %d, total size %d", cfg_sz, ret); + rtl_dev_info(hdev, "cfg_sz %d, total sz %d\n", btrtl_dev->cfg_len, ret); ret = rtl_download_firmware(hdev, fw_data, ret); out: - release_firmware(fw); kfree(fw_data); -err_req_fw: - if (cfg_sz) - kfree(cfg_buff); return ret; } @@ -467,14 +485,13 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev) skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)", - hdev->name, PTR_ERR(skb)); + rtl_dev_err(hdev, "HCI_OP_READ_LOCAL_VERSION failed (%ld)\n", + PTR_ERR(skb)); return skb; } if (skb->len != sizeof(struct hci_rp_read_local_version)) { - BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch", - hdev->name); + rtl_dev_err(hdev, "HCI_OP_READ_LOCAL_VERSION event length mismatch\n"); kfree_skb(skb); return ERR_PTR(-EIO); } @@ -482,49 +499,264 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev) return skb; } -int btrtl_setup_realtek(struct hci_dev *hdev) +void btrtl_free(struct btrtl_device_info *btrtl_dev) { + kfree(btrtl_dev->fw_data); + kfree(btrtl_dev->cfg_data); + kfree(btrtl_dev); +} +EXPORT_SYMBOL_GPL(btrtl_free); + +struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, + const char *postfix) +{ + struct btrtl_device_info *btrtl_dev; struct sk_buff *skb; struct hci_rp_read_local_version *resp; + char cfg_name[40]; u16 hci_rev, lmp_subver; + u8 hci_ver; + int ret; + + btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL); + if (!btrtl_dev) { + ret = -ENOMEM; + goto err_alloc; + } skb = btrtl_read_local_version(hdev); - if (IS_ERR(skb)) - return -PTR_ERR(skb); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + goto err_free; + } resp = (struct hci_rp_read_local_version *)skb->data; - bt_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x " - "lmp_ver=%02x lmp_subver=%04x", - resp->hci_ver, resp->hci_rev, - resp->lmp_ver, resp->lmp_subver); + rtl_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x lmp_subver=%04x\n", + resp->hci_ver, resp->hci_rev, + resp->lmp_ver, resp->lmp_subver); + hci_ver = resp->hci_ver; hci_rev = le16_to_cpu(resp->hci_rev); lmp_subver = le16_to_cpu(resp->lmp_subver); kfree_skb(skb); + btrtl_dev->ic_info = btrtl_match_ic(lmp_subver, hci_rev, hci_ver, + hdev->bus); + + if (!btrtl_dev->ic_info) { + rtl_dev_err(hdev, "rtl: unknown IC info, lmp subver %04x, hci rev %04x, hci ver %04x", + lmp_subver, hci_rev, hci_ver); + ret = -EINVAL; + goto err_free; + } + + if (btrtl_dev->ic_info->has_rom_version) { + ret = rtl_read_rom_version(hdev, &btrtl_dev->rom_version); + if (ret) + goto err_free; + } + + btrtl_dev->fw_len = rtl_load_file(hdev, btrtl_dev->ic_info->fw_name, + &btrtl_dev->fw_data); + if (btrtl_dev->fw_len < 0) { + rtl_dev_err(hdev, "firmware file %s not found\n", + btrtl_dev->ic_info->fw_name); + ret = btrtl_dev->fw_len; + goto err_free; + } + + if (btrtl_dev->ic_info->cfg_name) { + if (postfix) { + snprintf(cfg_name, sizeof(cfg_name), "%s-%s.bin", + btrtl_dev->ic_info->cfg_name, postfix); + } else { + snprintf(cfg_name, sizeof(cfg_name), "%s.bin", + btrtl_dev->ic_info->cfg_name); + } + btrtl_dev->cfg_len = rtl_load_file(hdev, cfg_name, + &btrtl_dev->cfg_data); + if (btrtl_dev->ic_info->config_needed && + btrtl_dev->cfg_len <= 0) { + rtl_dev_err(hdev, "mandatory config file %s not found\n", + btrtl_dev->ic_info->cfg_name); + ret = btrtl_dev->cfg_len; + goto err_free; + } + } + + return btrtl_dev; + +err_free: + btrtl_free(btrtl_dev); +err_alloc: + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(btrtl_initialize); + +int btrtl_download_firmware(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev) +{ /* Match a set of subver values that correspond to stock firmware, * which is not compatible with standard btusb. * If matched, upload an alternative firmware that does conform to * standard btusb. Once that firmware is uploaded, the subver changes * to a different value. */ - switch (lmp_subver) { + switch (btrtl_dev->ic_info->lmp_subver) { case RTL_ROM_LMP_8723A: case RTL_ROM_LMP_3499: - return btrtl_setup_rtl8723a(hdev); + return btrtl_setup_rtl8723a(hdev, btrtl_dev); case RTL_ROM_LMP_8723B: case RTL_ROM_LMP_8821A: case RTL_ROM_LMP_8761A: case RTL_ROM_LMP_8822B: - return btrtl_setup_rtl8723b(hdev, hci_rev, lmp_subver); + return btrtl_setup_rtl8723b(hdev, btrtl_dev); default: - bt_dev_info(hdev, "rtl: assuming no firmware upload needed"); + rtl_dev_info(hdev, "rtl: assuming no firmware upload needed\n"); return 0; } } +EXPORT_SYMBOL_GPL(btrtl_download_firmware); + +int btrtl_setup_realtek(struct hci_dev *hdev) +{ + struct btrtl_device_info *btrtl_dev; + int ret; + + btrtl_dev = btrtl_initialize(hdev, NULL); + if (IS_ERR(btrtl_dev)) + return PTR_ERR(btrtl_dev); + + ret = btrtl_download_firmware(hdev, btrtl_dev); + + btrtl_free(btrtl_dev); + + return ret; +} EXPORT_SYMBOL_GPL(btrtl_setup_realtek); +static unsigned int btrtl_convert_baudrate(u32 device_baudrate) +{ + switch (device_baudrate) { + case 0x0252a00a: + return 230400; + + case 0x05f75004: + return 921600; + + case 0x00005004: + return 1000000; + + case 0x04928002: + case 0x01128002: + return 1500000; + + case 0x00005002: + return 2000000; + + case 0x0000b001: + return 2500000; + + case 0x04928001: + return 3000000; + + case 0x052a6001: + return 3500000; + + case 0x00005001: + return 4000000; + + case 0x0252c014: + default: + return 115200; + } +} + +int btrtl_get_uart_settings(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev, + unsigned int *controller_baudrate, + u32 *device_baudrate, bool *flow_control) +{ + struct rtl_vendor_config *config; + struct rtl_vendor_config_entry *entry; + int i, total_data_len; + bool found = false; + + total_data_len = btrtl_dev->cfg_len - sizeof(*config); + if (total_data_len <= 0) { + rtl_dev_warn(hdev, "no config loaded\n"); + return -EINVAL; + } + + config = (struct rtl_vendor_config *)btrtl_dev->cfg_data; + if (le32_to_cpu(config->signature) != RTL_CONFIG_MAGIC) { + rtl_dev_err(hdev, "invalid config magic\n"); + return -EINVAL; + } + + if (total_data_len < le16_to_cpu(config->total_len)) { + rtl_dev_err(hdev, "config is too short\n"); + return -EINVAL; + } + + for (i = 0; i < total_data_len; ) { + entry = ((void *)config->entry) + i; + + switch (le16_to_cpu(entry->offset)) { + case 0xc: + if (entry->len < sizeof(*device_baudrate)) { + rtl_dev_err(hdev, "invalid UART config entry\n"); + return -EINVAL; + } + + *device_baudrate = get_unaligned_le32(entry->data); + *controller_baudrate = btrtl_convert_baudrate( + *device_baudrate); + + if (entry->len >= 13) + *flow_control = !!(entry->data[12] & BIT(2)); + else + *flow_control = false; + + found = true; + break; + + default: + rtl_dev_dbg(hdev, "skipping config entry 0x%x (len %u)\n", + le16_to_cpu(entry->offset), entry->len); + break; + }; + + i += sizeof(*entry) + entry->len; + } + + if (!found) { + rtl_dev_err(hdev, "no UART config entry found\n"); + return -ENOENT; + } + + rtl_dev_dbg(hdev, "device baudrate = 0x%08x\n", *device_baudrate); + rtl_dev_dbg(hdev, "controller baudrate = %u\n", *controller_baudrate); + rtl_dev_dbg(hdev, "flow control %d\n", *flow_control); + + return 0; +} +EXPORT_SYMBOL_GPL(btrtl_get_uart_settings); + MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>"); MODULE_DESCRIPTION("Bluetooth support for Realtek devices ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); +MODULE_FIRMWARE("rtl_bt/rtl8723a_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8723b_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8723b_config.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8723bs_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8723bs_config.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8723ds_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8723ds_config.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8761a_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8761a_config.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8821a_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8821a_config.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8822b_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8822b_config.bin"); diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h index 38ffe4890cd1..f5e36f3993a8 100644 --- a/drivers/bluetooth/btrtl.h +++ b/drivers/bluetooth/btrtl.h @@ -17,6 +17,13 @@ #define RTL_FRAG_LEN 252 +#define rtl_dev_err(dev, fmt, ...) bt_dev_err(dev, "RTL: " fmt, ##__VA_ARGS__) +#define rtl_dev_warn(dev, fmt, ...) bt_dev_warn(dev, "RTL: " fmt, ##__VA_ARGS__) +#define rtl_dev_info(dev, fmt, ...) bt_dev_info(dev, "RTL: " fmt, ##__VA_ARGS__) +#define rtl_dev_dbg(dev, fmt, ...) bt_dev_dbg(dev, "RTL: " fmt, ##__VA_ARGS__) + +struct btrtl_device_info; + struct rtl_download_cmd { __u8 index; __u8 data[RTL_FRAG_LEN]; @@ -38,15 +45,61 @@ struct rtl_epatch_header { __le16 num_patches; } __packed; +struct rtl_vendor_config_entry { + __le16 offset; + __u8 len; + __u8 data[0]; +} __packed; + +struct rtl_vendor_config { + __le32 signature; + __le16 total_len; + struct rtl_vendor_config_entry entry[0]; +} __packed; + #if IS_ENABLED(CONFIG_BT_RTL) +struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, + const char *postfix); +void btrtl_free(struct btrtl_device_info *btrtl_dev); +int btrtl_download_firmware(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev); int btrtl_setup_realtek(struct hci_dev *hdev); +int btrtl_get_uart_settings(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev, + unsigned int *controller_baudrate, + u32 *device_baudrate, bool *flow_control); #else +static inline struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, + const char *postfix) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void btrtl_free(struct btrtl_device_info *btrtl_dev) +{ +} + +static inline int btrtl_download_firmware(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev) +{ + return -EOPNOTSUPP; +} + static inline int btrtl_setup_realtek(struct hci_dev *hdev) { return -EOPNOTSUPP; } +static inline int btrtl_get_uart_settings(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev, + unsigned int *controller_baudrate, + u32 *device_baudrate, + bool *flow_control) +{ + return -ENOENT; +} + #endif diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index f73a27ea28cc..cd2e5cf14ea5 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -374,6 +374,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x7392, 0xa611), .driver_info = BTUSB_REALTEK }, /* Additional Realtek 8723DE Bluetooth devices */ + { USB_DEVICE(0x0bda, 0xb009), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x2ff8, 0xb011), .driver_info = BTUSB_REALTEK }, /* Additional Realtek 8821AE Bluetooth devices */ @@ -509,9 +510,10 @@ static inline void btusb_free_frags(struct btusb_data *data) static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count) { struct sk_buff *skb; + unsigned long flags; int err = 0; - spin_lock(&data->rxlock); + spin_lock_irqsave(&data->rxlock, flags); skb = data->evt_skb; while (count) { @@ -556,7 +558,7 @@ static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count) } data->evt_skb = skb; - spin_unlock(&data->rxlock); + spin_unlock_irqrestore(&data->rxlock, flags); return err; } @@ -564,9 +566,10 @@ static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count) static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count) { struct sk_buff *skb; + unsigned long flags; int err = 0; - spin_lock(&data->rxlock); + spin_lock_irqsave(&data->rxlock, flags); skb = data->acl_skb; while (count) { @@ -613,7 +616,7 @@ static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count) } data->acl_skb = skb; - spin_unlock(&data->rxlock); + spin_unlock_irqrestore(&data->rxlock, flags); return err; } @@ -621,9 +624,10 @@ static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count) static int btusb_recv_isoc(struct btusb_data *data, void *buffer, int count) { struct sk_buff *skb; + unsigned long flags; int err = 0; - spin_lock(&data->rxlock); + spin_lock_irqsave(&data->rxlock, flags); skb = data->sco_skb; while (count) { @@ -668,7 +672,7 @@ static int btusb_recv_isoc(struct btusb_data *data, void *buffer, int count) } data->sco_skb = skb; - spin_unlock(&data->rxlock); + spin_unlock_irqrestore(&data->rxlock, flags); return err; } @@ -1066,6 +1070,7 @@ static void btusb_tx_complete(struct urb *urb) struct sk_buff *skb = urb->context; struct hci_dev *hdev = (struct hci_dev *)skb->dev; struct btusb_data *data = hci_get_drvdata(hdev); + unsigned long flags; BT_DBG("%s urb %p status %d count %d", hdev->name, urb, urb->status, urb->actual_length); @@ -1079,9 +1084,9 @@ static void btusb_tx_complete(struct urb *urb) hdev->stat.err_tx++; done: - spin_lock(&data->txlock); + spin_lock_irqsave(&data->txlock, flags); data->tx_in_flight--; - spin_unlock(&data->txlock); + spin_unlock_irqrestore(&data->txlock, flags); kfree(urb->setup_packet); @@ -1593,13 +1598,13 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev, ret = request_firmware(&fw, fwname, &hdev->dev); if (ret < 0) { if (ret == -EINVAL) { - BT_ERR("%s Intel firmware file request failed (%d)", - hdev->name, ret); + bt_dev_err(hdev, "Intel firmware file request failed (%d)", + ret); return NULL; } - BT_ERR("%s failed to open Intel firmware file: %s(%d)", - hdev->name, fwname, ret); + bt_dev_err(hdev, "failed to open Intel firmware file: %s (%d)", + fwname, ret); /* If the correct firmware patch file is not found, use the * default firmware patch file instead @@ -1607,8 +1612,8 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev, snprintf(fwname, sizeof(fwname), "intel/ibt-hw-%x.%x.bseq", ver->hw_platform, ver->hw_variant); if (request_firmware(&fw, fwname, &hdev->dev) < 0) { - BT_ERR("%s failed to open default Intel fw file: %s", - hdev->name, fwname); + bt_dev_err(hdev, "failed to open default fw file: %s", + fwname); return NULL; } } @@ -1637,7 +1642,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev, * process. */ if (remain > HCI_COMMAND_HDR_SIZE && *fw_ptr[0] != 0x01) { - BT_ERR("%s Intel fw corrupted: invalid cmd read", hdev->name); + bt_dev_err(hdev, "Intel fw corrupted: invalid cmd read"); return -EINVAL; } (*fw_ptr)++; @@ -1651,7 +1656,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev, * of command parameter. If not, the firmware file is corrupted. */ if (remain < cmd->plen) { - BT_ERR("%s Intel fw corrupted: invalid cmd len", hdev->name); + bt_dev_err(hdev, "Intel fw corrupted: invalid cmd len"); return -EFAULT; } @@ -1684,8 +1689,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev, remain -= sizeof(*evt); if (remain < evt->plen) { - BT_ERR("%s Intel fw corrupted: invalid evt len", - hdev->name); + bt_dev_err(hdev, "Intel fw corrupted: invalid evt len"); return -EFAULT; } @@ -1699,15 +1703,15 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev, * file is corrupted. */ if (!evt || !evt_param || remain < 0) { - BT_ERR("%s Intel fw corrupted: invalid evt read", hdev->name); + bt_dev_err(hdev, "Intel fw corrupted: invalid evt read"); return -EFAULT; } skb = __hci_cmd_sync_ev(hdev, le16_to_cpu(cmd->opcode), cmd->plen, cmd_param, evt->evt, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s sending Intel patch command (0x%4.4x) failed (%ld)", - hdev->name, cmd->opcode, PTR_ERR(skb)); + bt_dev_err(hdev, "sending Intel patch command (0x%4.4x) failed (%ld)", + cmd->opcode, PTR_ERR(skb)); return PTR_ERR(skb); } @@ -1716,15 +1720,15 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev, * the contents of the event. */ if (skb->len != evt->plen) { - BT_ERR("%s mismatch event length (opcode 0x%4.4x)", hdev->name, - le16_to_cpu(cmd->opcode)); + bt_dev_err(hdev, "mismatch event length (opcode 0x%4.4x)", + le16_to_cpu(cmd->opcode)); kfree_skb(skb); return -EFAULT; } if (memcmp(skb->data, evt_param, evt->plen)) { - BT_ERR("%s mismatch event parameter (opcode 0x%4.4x)", - hdev->name, le16_to_cpu(cmd->opcode)); + bt_dev_err(hdev, "mismatch event parameter (opcode 0x%4.4x)", + le16_to_cpu(cmd->opcode)); kfree_skb(skb); return -EFAULT; } @@ -1753,8 +1757,8 @@ static int btusb_setup_intel(struct hci_dev *hdev) */ skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s sending initial HCI reset command failed (%ld)", - hdev->name, PTR_ERR(skb)); + bt_dev_err(hdev, "sending initial HCI reset command failed (%ld)", + PTR_ERR(skb)); return PTR_ERR(skb); } kfree_skb(skb); @@ -1890,7 +1894,7 @@ static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode) struct hci_event_hdr *hdr; struct hci_ev_cmd_complete *evt; - skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC); + skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -2084,8 +2088,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * for now only accept this single value. */ if (ver.hw_platform != 0x37) { - BT_ERR("%s: Unsupported Intel hardware platform (%u)", - hdev->name, ver.hw_platform); + bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)", + ver.hw_platform); return -EINVAL; } @@ -2104,8 +2108,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) case 0x14: /* QnJ, IcP */ break; default: - BT_ERR("%s: Unsupported Intel hardware variant (%u)", - hdev->name, ver.hw_variant); + bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)", + ver.hw_variant); return -EINVAL; } @@ -2134,8 +2138,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * choice is to return an error and abort the device initialization. */ if (ver.fw_variant != 0x06) { - BT_ERR("%s: Unsupported Intel firmware variant (%u)", - hdev->name, ver.fw_variant); + bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)", + ver.fw_variant); return -ENODEV; } @@ -2151,8 +2155,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * that this bootloader does not send them, then abort the setup. */ if (params.limited_cce != 0x00) { - BT_ERR("%s: Unsupported Intel firmware loading method (%u)", - hdev->name, params.limited_cce); + bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)", + params.limited_cce); return -EINVAL; } @@ -2202,14 +2206,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) le16_to_cpu(ver.fw_revision)); break; default: - BT_ERR("%s: Unsupported Intel firmware naming", hdev->name); + bt_dev_err(hdev, "Unsupported Intel firmware naming"); return -EINVAL; } err = request_firmware(&fw, fwname, &hdev->dev); if (err < 0) { - BT_ERR("%s: Failed to load Intel firmware file (%d)", - hdev->name, err); + bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", err); return err; } @@ -2235,13 +2238,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) le16_to_cpu(ver.fw_revision)); break; default: - BT_ERR("%s: Unsupported Intel firmware naming", hdev->name); + bt_dev_err(hdev, "Unsupported Intel firmware naming"); return -EINVAL; } if (fw->size < 644) { - BT_ERR("%s: Invalid size of firmware file (%zu)", - hdev->name, fw->size); + bt_dev_err(hdev, "Invalid size of firmware file (%zu)", + fw->size); err = -EBADF; goto done; } @@ -2272,18 +2275,18 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) TASK_INTERRUPTIBLE, msecs_to_jiffies(5000)); if (err == -EINTR) { - BT_ERR("%s: Firmware loading interrupted", hdev->name); + bt_dev_err(hdev, "Firmware loading interrupted"); goto done; } if (err) { - BT_ERR("%s: Firmware loading timeout", hdev->name); + bt_dev_err(hdev, "Firmware loading timeout"); err = -ETIMEDOUT; goto done; } if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) { - BT_ERR("%s: Firmware loading failed", hdev->name); + bt_dev_err(hdev, "Firmware loading failed"); err = -ENOEXEC; goto done; } @@ -2322,12 +2325,12 @@ done: msecs_to_jiffies(1000)); if (err == -EINTR) { - BT_ERR("%s: Device boot interrupted", hdev->name); + bt_dev_err(hdev, "Device boot interrupted"); return -EINTR; } if (err) { - BT_ERR("%s: Device boot timeout", hdev->name); + bt_dev_err(hdev, "Device boot timeout"); return -ETIMEDOUT; } @@ -2364,6 +2367,22 @@ static int btusb_shutdown_intel(struct hci_dev *hdev) struct sk_buff *skb; long ret; + /* In the shutdown sequence where Bluetooth is turned off followed + * by WiFi being turned off, turning WiFi back on causes issue with + * the RF calibration. + * + * To ensure that any RF activity has been stopped, issue HCI Reset + * command to clear all ongoing activity including advertising, + * scanning etc. + */ + skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + bt_dev_err(hdev, "HCI reset during shutdown failed"); + return ret; + } + kfree_skb(skb); + /* Some platforms have an issue with BT LED when the interface is * down or BT radio is turned off, which takes 5 seconds to BT LED * goes off. This command turns off the BT LED immediately. @@ -2371,8 +2390,7 @@ static int btusb_shutdown_intel(struct hci_dev *hdev) skb = __hci_cmd_sync(hdev, 0xfc3f, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { ret = PTR_ERR(skb); - BT_ERR("%s: turning off Intel device LED failed (%ld)", - hdev->name, ret); + bt_dev_err(hdev, "turning off Intel device LED failed"); return ret; } kfree_skb(skb); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 6a8d0d06aba7..63c0dcbc4914 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -21,13 +21,18 @@ * */ -#include <linux/kernel.h> +#include <linux/acpi.h> #include <linux/errno.h> +#include <linux/gpio/consumer.h> +#include <linux/kernel.h> +#include <linux/mod_devicetable.h> +#include <linux/serdev.h> #include <linux/skbuff.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include "btrtl.h" #include "hci_uart.h" #define HCI_3WIRE_ACK_PKT 0 @@ -65,6 +70,9 @@ enum { }; struct h5 { + /* Must be the first member, hci_serdev.c expects this. */ + struct hci_uart serdev_hu; + struct sk_buff_head unack; /* Unack'ed packets queue */ struct sk_buff_head rel; /* Reliable packets queue */ struct sk_buff_head unrel; /* Unreliable packets queue */ @@ -95,6 +103,19 @@ struct h5 { H5_SLEEPING, H5_WAKING_UP, } sleep; + + const struct h5_vnd *vnd; + const char *id; + + struct gpio_desc *enable_gpio; + struct gpio_desc *device_wake_gpio; +}; + +struct h5_vnd { + int (*setup)(struct h5 *h5); + void (*open)(struct h5 *h5); + void (*close)(struct h5 *h5); + const struct acpi_gpio_mapping *acpi_gpio_map; }; static void h5_reset_rx(struct h5 *h5); @@ -193,9 +214,13 @@ static int h5_open(struct hci_uart *hu) BT_DBG("hu %p", hu); - h5 = kzalloc(sizeof(*h5), GFP_KERNEL); - if (!h5) - return -ENOMEM; + if (hu->serdev) { + h5 = serdev_device_get_drvdata(hu->serdev); + } else { + h5 = kzalloc(sizeof(*h5), GFP_KERNEL); + if (!h5) + return -ENOMEM; + } hu->priv = h5; h5->hu = hu; @@ -210,6 +235,9 @@ static int h5_open(struct hci_uart *hu) h5->tx_win = H5_TX_WIN_MAX; + if (h5->vnd && h5->vnd->open) + h5->vnd->open(h5); + set_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags); /* Send initial sync request */ @@ -229,7 +257,21 @@ static int h5_close(struct hci_uart *hu) skb_queue_purge(&h5->rel); skb_queue_purge(&h5->unrel); - kfree(h5); + if (h5->vnd && h5->vnd->close) + h5->vnd->close(h5); + + if (!hu->serdev) + kfree(h5); + + return 0; +} + +static int h5_setup(struct hci_uart *hu) +{ + struct h5 *h5 = hu->priv; + + if (h5->vnd && h5->vnd->setup) + return h5->vnd->setup(h5); return 0; } @@ -744,18 +786,168 @@ static const struct hci_uart_proto h5p = { .name = "Three-wire (H5)", .open = h5_open, .close = h5_close, + .setup = h5_setup, .recv = h5_recv, .enqueue = h5_enqueue, .dequeue = h5_dequeue, .flush = h5_flush, }; +static int h5_serdev_probe(struct serdev_device *serdev) +{ + const struct acpi_device_id *match; + struct device *dev = &serdev->dev; + struct h5 *h5; + + h5 = devm_kzalloc(dev, sizeof(*h5), GFP_KERNEL); + if (!h5) + return -ENOMEM; + + set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.flags); + + h5->hu = &h5->serdev_hu; + h5->serdev_hu.serdev = serdev; + serdev_device_set_drvdata(serdev, h5); + + if (has_acpi_companion(dev)) { + match = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!match) + return -ENODEV; + + h5->vnd = (const struct h5_vnd *)match->driver_data; + h5->id = (char *)match->id; + + if (h5->vnd->acpi_gpio_map) + devm_acpi_dev_add_driver_gpios(dev, + h5->vnd->acpi_gpio_map); + } + + h5->enable_gpio = devm_gpiod_get_optional(dev, "enable", GPIOD_OUT_LOW); + if (IS_ERR(h5->enable_gpio)) + return PTR_ERR(h5->enable_gpio); + + h5->device_wake_gpio = devm_gpiod_get_optional(dev, "device-wake", + GPIOD_OUT_LOW); + if (IS_ERR(h5->device_wake_gpio)) + return PTR_ERR(h5->device_wake_gpio); + + return hci_uart_register_device(&h5->serdev_hu, &h5p); +} + +static void h5_serdev_remove(struct serdev_device *serdev) +{ + struct h5 *h5 = serdev_device_get_drvdata(serdev); + + hci_uart_unregister_device(&h5->serdev_hu); +} + +static int h5_btrtl_setup(struct h5 *h5) +{ + struct btrtl_device_info *btrtl_dev; + struct sk_buff *skb; + __le32 baudrate_data; + u32 device_baudrate; + unsigned int controller_baudrate; + bool flow_control; + int err; + + btrtl_dev = btrtl_initialize(h5->hu->hdev, h5->id); + if (IS_ERR(btrtl_dev)) + return PTR_ERR(btrtl_dev); + + err = btrtl_get_uart_settings(h5->hu->hdev, btrtl_dev, + &controller_baudrate, &device_baudrate, + &flow_control); + if (err) + goto out_free; + + baudrate_data = cpu_to_le32(device_baudrate); + skb = __hci_cmd_sync(h5->hu->hdev, 0xfc17, sizeof(baudrate_data), + &baudrate_data, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + rtl_dev_err(h5->hu->hdev, "set baud rate command failed\n"); + err = PTR_ERR(skb); + goto out_free; + } else { + kfree_skb(skb); + } + /* Give the device some time to set up the new baudrate. */ + usleep_range(10000, 20000); + + serdev_device_set_baudrate(h5->hu->serdev, controller_baudrate); + serdev_device_set_flow_control(h5->hu->serdev, flow_control); + + err = btrtl_download_firmware(h5->hu->hdev, btrtl_dev); + /* Give the device some time before the hci-core sends it a reset */ + usleep_range(10000, 20000); + +out_free: + btrtl_free(btrtl_dev); + + return err; +} + +static void h5_btrtl_open(struct h5 *h5) +{ + /* Devices always start with these fixed parameters */ + serdev_device_set_flow_control(h5->hu->serdev, false); + serdev_device_set_parity(h5->hu->serdev, SERDEV_PARITY_EVEN); + serdev_device_set_baudrate(h5->hu->serdev, 115200); + + /* The controller needs up to 500ms to wakeup */ + gpiod_set_value_cansleep(h5->enable_gpio, 1); + gpiod_set_value_cansleep(h5->device_wake_gpio, 1); + msleep(500); +} + +static void h5_btrtl_close(struct h5 *h5) +{ + gpiod_set_value_cansleep(h5->device_wake_gpio, 0); + gpiod_set_value_cansleep(h5->enable_gpio, 0); +} + +static const struct acpi_gpio_params btrtl_device_wake_gpios = { 0, 0, false }; +static const struct acpi_gpio_params btrtl_enable_gpios = { 1, 0, false }; +static const struct acpi_gpio_params btrtl_host_wake_gpios = { 2, 0, false }; +static const struct acpi_gpio_mapping acpi_btrtl_gpios[] = { + { "device-wake-gpios", &btrtl_device_wake_gpios, 1 }, + { "enable-gpios", &btrtl_enable_gpios, 1 }, + { "host-wake-gpios", &btrtl_host_wake_gpios, 1 }, + {}, +}; + +static struct h5_vnd rtl_vnd = { + .setup = h5_btrtl_setup, + .open = h5_btrtl_open, + .close = h5_btrtl_close, + .acpi_gpio_map = acpi_btrtl_gpios, +}; + +#ifdef CONFIG_ACPI +static const struct acpi_device_id h5_acpi_match[] = { + { "OBDA8723", (kernel_ulong_t)&rtl_vnd }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, h5_acpi_match); +#endif + +static struct serdev_device_driver h5_serdev_driver = { + .probe = h5_serdev_probe, + .remove = h5_serdev_remove, + .driver = { + .name = "hci_uart_h5", + .acpi_match_table = ACPI_PTR(h5_acpi_match), + }, +}; + int __init h5_init(void) { + serdev_device_driver_register(&h5_serdev_driver); return hci_uart_register_proto(&h5p); } int __exit h5_deinit(void) { + serdev_device_driver_unregister(&h5_serdev_driver); return hci_uart_unregister_proto(&h5p); } diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 7c166e3b308b..46ace321bf60 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -458,7 +458,7 @@ static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode) struct hci_event_hdr *hdr; struct hci_ev_cmd_complete *evt; - skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC); + skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_KERNEL); if (!skb) return -ENOMEM; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 51790dd02afb..e182f6019f68 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -5,7 +5,7 @@ * protocol extension to H4. * * Copyright (C) 2007 Texas Instruments, Inc. - * Copyright (c) 2010, 2012 The Linux Foundation. All rights reserved. + * Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved. * * Acknowledgements: * This file is based on hci_ll.c, which was... @@ -31,9 +31,14 @@ #include <linux/kernel.h> #include <linux/clk.h> #include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/device.h> #include <linux/gpio/consumer.h> #include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/regulator/consumer.h> #include <linux/serdev.h> #include <net/bluetooth/bluetooth.h> @@ -119,12 +124,51 @@ struct qca_data { u64 votes_off; }; +enum qca_speed_type { + QCA_INIT_SPEED = 1, + QCA_OPER_SPEED +}; + +/* + * Voltage regulator information required for configuring the + * QCA Bluetooth chipset + */ +struct qca_vreg { + const char *name; + unsigned int min_uV; + unsigned int max_uV; + unsigned int load_uA; +}; + +struct qca_vreg_data { + enum qca_btsoc_type soc_type; + struct qca_vreg *vregs; + size_t num_vregs; +}; + +/* + * Platform data for the QCA Bluetooth power driver. + */ +struct qca_power { + struct device *dev; + const struct qca_vreg_data *vreg_data; + struct regulator_bulk_data *vreg_bulk; + bool vregs_on; +}; + struct qca_serdev { struct hci_uart serdev_hu; struct gpio_desc *bt_en; struct clk *susclk; + enum qca_btsoc_type btsoc_type; + struct qca_power *bt_power; + u32 init_speed; + u32 oper_speed; }; +static int qca_power_setup(struct hci_uart *hu, bool on); +static void qca_power_shutdown(struct hci_dev *hdev); + static void __serial_clock_on(struct tty_struct *tty) { /* TODO: Some chipset requires to enable UART clock on client @@ -402,10 +446,11 @@ static int qca_open(struct hci_uart *hu) { struct qca_serdev *qcadev; struct qca_data *qca; + int ret; BT_DBG("hu %p qca_open", hu); - qca = kzalloc(sizeof(struct qca_data), GFP_ATOMIC); + qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL); if (!qca) return -ENOMEM; @@ -453,19 +498,32 @@ static int qca_open(struct hci_uart *hu) hu->priv = qca; - timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0); - qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS; - - timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0); - qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS; - if (hu->serdev) { serdev_device_open(hu->serdev); qcadev = serdev_device_get_drvdata(hu->serdev); - gpiod_set_value_cansleep(qcadev->bt_en, 1); + if (qcadev->btsoc_type != QCA_WCN3990) { + gpiod_set_value_cansleep(qcadev->bt_en, 1); + } else { + hu->init_speed = qcadev->init_speed; + hu->oper_speed = qcadev->oper_speed; + ret = qca_power_setup(hu, true); + if (ret) { + destroy_workqueue(qca->workqueue); + kfree_skb(qca->rx_skb); + hu->priv = NULL; + kfree(qca); + return ret; + } + } } + timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0); + qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS; + + timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0); + qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS; + BT_DBG("HCI_UART_QCA open, tx_idle_delay=%u, wake_retrans=%u", qca->tx_idle_delay, qca->wake_retrans); @@ -549,10 +607,13 @@ static int qca_close(struct hci_uart *hu) qca->hu = NULL; if (hu->serdev) { - serdev_device_close(hu->serdev); - qcadev = serdev_device_get_drvdata(hu->serdev); - gpiod_set_value_cansleep(qcadev->bt_en, 0); + if (qcadev->btsoc_type == QCA_WCN3990) + qca_power_shutdown(hu->hdev); + else + gpiod_set_value_cansleep(qcadev->bt_en, 0); + + serdev_device_close(hu->serdev); } kfree_skb(qca->rx_skb); @@ -872,6 +933,8 @@ static uint8_t qca_get_baudrate_value(int speed) return QCA_BAUDRATE_2000000; case 3000000: return QCA_BAUDRATE_3000000; + case 3200000: + return QCA_BAUDRATE_3200000; case 3500000: return QCA_BAUDRATE_3500000; default: @@ -884,19 +947,27 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate) struct hci_uart *hu = hci_get_drvdata(hdev); struct qca_data *qca = hu->priv; struct sk_buff *skb; + struct qca_serdev *qcadev; u8 cmd[] = { 0x01, 0x48, 0xFC, 0x01, 0x00 }; - if (baudrate > QCA_BAUDRATE_3000000) + if (baudrate > QCA_BAUDRATE_3200000) return -EINVAL; cmd[4] = baudrate; - skb = bt_skb_alloc(sizeof(cmd), GFP_ATOMIC); + skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL); if (!skb) { bt_dev_err(hdev, "Failed to allocate baudrate packet"); return -ENOMEM; } + /* Disabling hardware flow control is mandatory while + * sending change baudrate request to wcn3990 SoC. + */ + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qcadev->btsoc_type == QCA_WCN3990) + hci_uart_set_flow_control(hu, true); + /* Assign commands to change baudrate and packet type. */ skb_put_data(skb, cmd, sizeof(cmd)); hci_skb_pkt_type(skb) = HCI_COMMAND_PKT; @@ -912,6 +983,9 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate) schedule_timeout(msecs_to_jiffies(BAUDRATE_SETTLE_TIMEOUT_MS)); set_current_state(TASK_RUNNING); + if (qcadev->btsoc_type == QCA_WCN3990) + hci_uart_set_flow_control(hu, false); + return 0; } @@ -923,50 +997,195 @@ static inline void host_set_baudrate(struct hci_uart *hu, unsigned int speed) hci_uart_set_baudrate(hu, speed); } +static int qca_send_power_pulse(struct hci_dev *hdev, u8 cmd) +{ + struct hci_uart *hu = hci_get_drvdata(hdev); + struct qca_data *qca = hu->priv; + struct sk_buff *skb; + + /* These power pulses are single byte command which are sent + * at required baudrate to wcn3990. On wcn3990, we have an external + * circuit at Tx pin which decodes the pulse sent at specific baudrate. + * For example, wcn3990 supports RF COEX antenna for both Wi-Fi/BT + * and also we use the same power inputs to turn on and off for + * Wi-Fi/BT. Powering up the power sources will not enable BT, until + * we send a power on pulse at 115200 bps. This algorithm will help to + * save power. Disabling hardware flow control is mandatory while + * sending power pulses to SoC. + */ + bt_dev_dbg(hdev, "sending power pulse %02x to SoC", cmd); + + skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hci_uart_set_flow_control(hu, true); + + skb_put_u8(skb, cmd); + hci_skb_pkt_type(skb) = HCI_COMMAND_PKT; + + skb_queue_tail(&qca->txq, skb); + hci_uart_tx_wakeup(hu); + + /* Wait for 100 uS for SoC to settle down */ + usleep_range(100, 200); + hci_uart_set_flow_control(hu, false); + + return 0; +} + +static unsigned int qca_get_speed(struct hci_uart *hu, + enum qca_speed_type speed_type) +{ + unsigned int speed = 0; + + if (speed_type == QCA_INIT_SPEED) { + if (hu->init_speed) + speed = hu->init_speed; + else if (hu->proto->init_speed) + speed = hu->proto->init_speed; + } else { + if (hu->oper_speed) + speed = hu->oper_speed; + else if (hu->proto->oper_speed) + speed = hu->proto->oper_speed; + } + + return speed; +} + +static int qca_check_speeds(struct hci_uart *hu) +{ + struct qca_serdev *qcadev; + + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qcadev->btsoc_type == QCA_WCN3990) { + if (!qca_get_speed(hu, QCA_INIT_SPEED) && + !qca_get_speed(hu, QCA_OPER_SPEED)) + return -EINVAL; + } else { + if (!qca_get_speed(hu, QCA_INIT_SPEED) || + !qca_get_speed(hu, QCA_OPER_SPEED)) + return -EINVAL; + } + + return 0; +} + +static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) +{ + unsigned int speed, qca_baudrate; + int ret; + + if (speed_type == QCA_INIT_SPEED) { + speed = qca_get_speed(hu, QCA_INIT_SPEED); + if (speed) + host_set_baudrate(hu, speed); + } else { + speed = qca_get_speed(hu, QCA_OPER_SPEED); + if (!speed) + return 0; + + qca_baudrate = qca_get_baudrate_value(speed); + bt_dev_dbg(hu->hdev, "Set UART speed to %d", speed); + ret = qca_set_baudrate(hu->hdev, qca_baudrate); + if (ret) + return ret; + + host_set_baudrate(hu, speed); + } + + return 0; +} + +static int qca_wcn3990_init(struct hci_uart *hu) +{ + struct hci_dev *hdev = hu->hdev; + int ret; + + /* Forcefully enable wcn3990 to enter in to boot mode. */ + host_set_baudrate(hu, 2400); + ret = qca_send_power_pulse(hdev, QCA_WCN3990_POWEROFF_PULSE); + if (ret) + return ret; + + qca_set_speed(hu, QCA_INIT_SPEED); + ret = qca_send_power_pulse(hdev, QCA_WCN3990_POWERON_PULSE); + if (ret) + return ret; + + /* Wait for 100 ms for SoC to boot */ + msleep(100); + + /* Now the device is in ready state to communicate with host. + * To sync host with device we need to reopen port. + * Without this, we will have RTS and CTS synchronization + * issues. + */ + serdev_device_close(hu->serdev); + ret = serdev_device_open(hu->serdev); + if (ret) { + bt_dev_err(hu->hdev, "failed to open port"); + return ret; + } + + hci_uart_set_flow_control(hu, false); + + return 0; +} + static int qca_setup(struct hci_uart *hu) { struct hci_dev *hdev = hu->hdev; struct qca_data *qca = hu->priv; unsigned int speed, qca_baudrate = QCA_BAUDRATE_115200; + struct qca_serdev *qcadev; int ret; + int soc_ver = 0; + + qcadev = serdev_device_get_drvdata(hu->serdev); - bt_dev_info(hdev, "ROME setup"); + ret = qca_check_speeds(hu); + if (ret) + return ret; /* Patch downloading has to be done without IBS mode */ clear_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags); - /* Setup initial baudrate */ - speed = 0; - if (hu->init_speed) - speed = hu->init_speed; - else if (hu->proto->init_speed) - speed = hu->proto->init_speed; + if (qcadev->btsoc_type == QCA_WCN3990) { + bt_dev_info(hdev, "setting up wcn3990"); + ret = qca_wcn3990_init(hu); + if (ret) + return ret; - if (speed) - host_set_baudrate(hu, speed); + ret = qca_read_soc_version(hdev, &soc_ver); + if (ret) + return ret; + } else { + bt_dev_info(hdev, "ROME setup"); + qca_set_speed(hu, QCA_INIT_SPEED); + } /* Setup user speed if needed */ - speed = 0; - if (hu->oper_speed) - speed = hu->oper_speed; - else if (hu->proto->oper_speed) - speed = hu->proto->oper_speed; - + speed = qca_get_speed(hu, QCA_OPER_SPEED); if (speed) { + ret = qca_set_speed(hu, QCA_OPER_SPEED); + if (ret) + return ret; + qca_baudrate = qca_get_baudrate_value(speed); + } - bt_dev_info(hdev, "Set UART speed to %d", speed); - ret = qca_set_baudrate(hdev, qca_baudrate); - if (ret) { - bt_dev_err(hdev, "Failed to change the baud rate (%d)", - ret); + if (qcadev->btsoc_type != QCA_WCN3990) { + /* Get QCA version information */ + ret = qca_read_soc_version(hdev, &soc_ver); + if (ret) return ret; - } - host_set_baudrate(hu, speed); } + bt_dev_info(hdev, "QCA controller version 0x%08x", soc_ver); /* Setup patch / NVM configurations */ - ret = qca_uart_setup_rome(hdev, qca_baudrate); + ret = qca_uart_setup(hdev, qca_baudrate, qcadev->btsoc_type, soc_ver); if (!ret) { set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags); qca_debugfs_init(hdev); @@ -1002,9 +1221,123 @@ static struct hci_uart_proto qca_proto = { .dequeue = qca_dequeue, }; +static const struct qca_vreg_data qca_soc_data = { + .soc_type = QCA_WCN3990, + .vregs = (struct qca_vreg []) { + { "vddio", 1800000, 1900000, 15000 }, + { "vddxo", 1800000, 1900000, 80000 }, + { "vddrf", 1300000, 1350000, 300000 }, + { "vddch0", 3300000, 3400000, 450000 }, + }, + .num_vregs = 4, +}; + +static void qca_power_shutdown(struct hci_dev *hdev) +{ + struct hci_uart *hu = hci_get_drvdata(hdev); + + host_set_baudrate(hu, 2400); + qca_send_power_pulse(hdev, QCA_WCN3990_POWEROFF_PULSE); + qca_power_setup(hu, false); +} + +static int qca_enable_regulator(struct qca_vreg vregs, + struct regulator *regulator) +{ + int ret; + + ret = regulator_set_voltage(regulator, vregs.min_uV, + vregs.max_uV); + if (ret) + return ret; + + if (vregs.load_uA) + ret = regulator_set_load(regulator, + vregs.load_uA); + + if (ret) + return ret; + + return regulator_enable(regulator); + +} + +static void qca_disable_regulator(struct qca_vreg vregs, + struct regulator *regulator) +{ + regulator_disable(regulator); + regulator_set_voltage(regulator, 0, vregs.max_uV); + if (vregs.load_uA) + regulator_set_load(regulator, 0); + +} + +static int qca_power_setup(struct hci_uart *hu, bool on) +{ + struct qca_vreg *vregs; + struct regulator_bulk_data *vreg_bulk; + struct qca_serdev *qcadev; + int i, num_vregs, ret = 0; + + qcadev = serdev_device_get_drvdata(hu->serdev); + if (!qcadev || !qcadev->bt_power || !qcadev->bt_power->vreg_data || + !qcadev->bt_power->vreg_bulk) + return -EINVAL; + + vregs = qcadev->bt_power->vreg_data->vregs; + vreg_bulk = qcadev->bt_power->vreg_bulk; + num_vregs = qcadev->bt_power->vreg_data->num_vregs; + BT_DBG("on: %d", on); + if (on && !qcadev->bt_power->vregs_on) { + for (i = 0; i < num_vregs; i++) { + ret = qca_enable_regulator(vregs[i], + vreg_bulk[i].consumer); + if (ret) + break; + } + + if (ret) { + BT_ERR("failed to enable regulator:%s", vregs[i].name); + /* turn off regulators which are enabled */ + for (i = i - 1; i >= 0; i--) + qca_disable_regulator(vregs[i], + vreg_bulk[i].consumer); + } else { + qcadev->bt_power->vregs_on = true; + } + } else if (!on && qcadev->bt_power->vregs_on) { + /* turn off regulator in reverse order */ + i = qcadev->bt_power->vreg_data->num_vregs - 1; + for ( ; i >= 0; i--) + qca_disable_regulator(vregs[i], vreg_bulk[i].consumer); + + qcadev->bt_power->vregs_on = false; + } + + return ret; +} + +static int qca_init_regulators(struct qca_power *qca, + const struct qca_vreg *vregs, size_t num_vregs) +{ + int i; + + qca->vreg_bulk = devm_kzalloc(qca->dev, num_vregs * + sizeof(struct regulator_bulk_data), + GFP_KERNEL); + if (!qca->vreg_bulk) + return -ENOMEM; + + for (i = 0; i < num_vregs; i++) + qca->vreg_bulk[i].supply = vregs[i].name; + + return devm_regulator_bulk_get(qca->dev, num_vregs, qca->vreg_bulk); +} + static int qca_serdev_probe(struct serdev_device *serdev) { struct qca_serdev *qcadev; + const struct qca_vreg_data *data; int err; qcadev = devm_kzalloc(&serdev->dev, sizeof(*qcadev), GFP_KERNEL); @@ -1012,47 +1345,84 @@ static int qca_serdev_probe(struct serdev_device *serdev) return -ENOMEM; qcadev->serdev_hu.serdev = serdev; + data = of_device_get_match_data(&serdev->dev); serdev_device_set_drvdata(serdev, qcadev); + if (data && data->soc_type == QCA_WCN3990) { + qcadev->btsoc_type = QCA_WCN3990; + qcadev->bt_power = devm_kzalloc(&serdev->dev, + sizeof(struct qca_power), + GFP_KERNEL); + if (!qcadev->bt_power) + return -ENOMEM; + + qcadev->bt_power->dev = &serdev->dev; + qcadev->bt_power->vreg_data = data; + err = qca_init_regulators(qcadev->bt_power, data->vregs, + data->num_vregs); + if (err) { + BT_ERR("Failed to init regulators:%d", err); + goto out; + } - qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable", - GPIOD_OUT_LOW); - if (IS_ERR(qcadev->bt_en)) { - dev_err(&serdev->dev, "failed to acquire enable gpio\n"); - return PTR_ERR(qcadev->bt_en); - } + qcadev->bt_power->vregs_on = false; - qcadev->susclk = devm_clk_get(&serdev->dev, NULL); - if (IS_ERR(qcadev->susclk)) { - dev_err(&serdev->dev, "failed to acquire clk\n"); - return PTR_ERR(qcadev->susclk); - } + device_property_read_u32(&serdev->dev, "max-speed", + &qcadev->oper_speed); + if (!qcadev->oper_speed) + BT_DBG("UART will pick default operating speed"); - err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ); - if (err) - return err; + err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto); + if (err) { + BT_ERR("wcn3990 serdev registration failed"); + goto out; + } + } else { + qcadev->btsoc_type = QCA_ROME; + qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable", + GPIOD_OUT_LOW); + if (IS_ERR(qcadev->bt_en)) { + dev_err(&serdev->dev, "failed to acquire enable gpio\n"); + return PTR_ERR(qcadev->bt_en); + } - err = clk_prepare_enable(qcadev->susclk); - if (err) - return err; + qcadev->susclk = devm_clk_get(&serdev->dev, NULL); + if (IS_ERR(qcadev->susclk)) { + dev_err(&serdev->dev, "failed to acquire clk\n"); + return PTR_ERR(qcadev->susclk); + } - err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto); - if (err) - clk_disable_unprepare(qcadev->susclk); + err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ); + if (err) + return err; + + err = clk_prepare_enable(qcadev->susclk); + if (err) + return err; + + err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto); + if (err) + clk_disable_unprepare(qcadev->susclk); + } + +out: return err; - return err; } static void qca_serdev_remove(struct serdev_device *serdev) { struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); - hci_uart_unregister_device(&qcadev->serdev_hu); + if (qcadev->btsoc_type == QCA_WCN3990) + qca_power_shutdown(qcadev->serdev_hu.hdev); + else + clk_disable_unprepare(qcadev->susclk); - clk_disable_unprepare(qcadev->susclk); + hci_uart_unregister_device(&qcadev->serdev_hu); } static const struct of_device_id qca_bluetooth_of_match[] = { { .compatible = "qcom,qca6174-bt" }, + { .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); diff --git a/drivers/char/mem.c b/drivers/char/mem.c index ffeb60d3434c..df66a9dd0aae 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma) #endif if (vma->vm_flags & VM_SHARED) return shmem_zero_setup(vma); + vma_set_anonymous(vma); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index cd888d4ee605..bd449ad52442 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1895,14 +1895,22 @@ static int write_pool(struct entropy_store *r, const char __user *buffer, size_t count) { size_t bytes; - __u32 buf[16]; + __u32 t, buf[16]; const char __user *p = buffer; while (count > 0) { + int b, i = 0; + bytes = min(count, sizeof(buf)); if (copy_from_user(&buf, p, bytes)) return -EFAULT; + for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) { + if (!arch_get_random_int(&t)) + break; + buf[i] ^= t; + } + count -= bytes; p += bytes; diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c index 38b366b00c57..7b70a074095d 100644 --- a/drivers/clk/clk-aspeed.c +++ b/drivers/clk/clk-aspeed.c @@ -24,7 +24,7 @@ #define ASPEED_MPLL_PARAM 0x20 #define ASPEED_HPLL_PARAM 0x24 #define AST2500_HPLL_BYPASS_EN BIT(20) -#define AST2400_HPLL_STRAPPED BIT(18) +#define AST2400_HPLL_PROGRAMMED BIT(18) #define AST2400_HPLL_BYPASS_EN BIT(17) #define ASPEED_MISC_CTRL 0x2c #define UART_DIV13_EN BIT(12) @@ -91,8 +91,8 @@ static const struct aspeed_gate_data aspeed_gates[] = { [ASPEED_CLK_GATE_GCLK] = { 1, 7, "gclk-gate", NULL, 0 }, /* 2D engine */ [ASPEED_CLK_GATE_MCLK] = { 2, -1, "mclk-gate", "mpll", CLK_IS_CRITICAL }, /* SDRAM */ [ASPEED_CLK_GATE_VCLK] = { 3, 6, "vclk-gate", NULL, 0 }, /* Video Capture */ - [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", 0 }, /* PCIe/PCI */ - [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, 0 }, /* DAC */ + [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", CLK_IS_CRITICAL }, /* PCIe/PCI */ + [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, CLK_IS_CRITICAL }, /* DAC */ [ASPEED_CLK_GATE_REFCLK] = { 6, -1, "refclk-gate", "clkin", CLK_IS_CRITICAL }, [ASPEED_CLK_GATE_USBPORT2CLK] = { 7, 3, "usb-port2-gate", NULL, 0 }, /* USB2.0 Host port 2 */ [ASPEED_CLK_GATE_LCLK] = { 8, 5, "lclk-gate", NULL, 0 }, /* LPC */ @@ -212,9 +212,22 @@ static int aspeed_clk_is_enabled(struct clk_hw *hw) { struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); u32 clk = BIT(gate->clock_idx); + u32 rst = BIT(gate->reset_idx); u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk; u32 reg; + /* + * If the IP is in reset, treat the clock as not enabled, + * this happens with some clocks such as the USB one when + * coming from cold reset. Without this, aspeed_clk_enable() + * will fail to lift the reset. + */ + if (gate->reset_idx >= 0) { + regmap_read(gate->map, ASPEED_RESET_CTRL, ®); + if (reg & rst) + return 0; + } + regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®); return ((reg & clk) == enval) ? 1 : 0; @@ -565,29 +578,45 @@ builtin_platform_driver(aspeed_clk_driver); static void __init aspeed_ast2400_cc(struct regmap *map) { struct clk_hw *hw; - u32 val, freq, div; + u32 val, div, clkin, hpll; + const u16 hpll_rates[][4] = { + {384, 360, 336, 408}, + {400, 375, 350, 425}, + }; + int rate; /* * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by * strapping */ regmap_read(map, ASPEED_STRAP, &val); - if (val & CLKIN_25MHZ_EN) - freq = 25000000; - else if (val & AST2400_CLK_SOURCE_SEL) - freq = 48000000; - else - freq = 24000000; - hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq); - pr_debug("clkin @%u MHz\n", freq / 1000000); + rate = (val >> 8) & 3; + if (val & CLKIN_25MHZ_EN) { + clkin = 25000000; + hpll = hpll_rates[1][rate]; + } else if (val & AST2400_CLK_SOURCE_SEL) { + clkin = 48000000; + hpll = hpll_rates[0][rate]; + } else { + clkin = 24000000; + hpll = hpll_rates[0][rate]; + } + hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin); + pr_debug("clkin @%u MHz\n", clkin / 1000000); /* * High-speed PLL clock derived from the crystal. This the CPU clock, - * and we assume that it is enabled + * and we assume that it is enabled. It can be configured through the + * HPLL_PARAM register, or set to a specified frequency by strapping. */ regmap_read(map, ASPEED_HPLL_PARAM, &val); - WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured"); - aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val); + if (val & AST2400_HPLL_PROGRAMMED) + hw = aspeed_ast2400_calc_pll("hpll", val); + else + hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0, + hpll * 1000000); + + aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw; /* * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9760b526ca31..e2ed078abd90 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -24,7 +24,6 @@ #include <linux/pm_runtime.h> #include <linux/sched.h> #include <linux/clkdev.h> -#include <linux/stringify.h> #include "clk.h" @@ -2559,7 +2558,7 @@ static const struct { unsigned long flag; const char *name; } clk_flags[] = { -#define ENTRY(f) { f, __stringify(f) } +#define ENTRY(f) { f, #f } ENTRY(CLK_SET_RATE_GATE), ENTRY(CLK_SET_PARENT_GATE), ENTRY(CLK_SET_RATE_PARENT), diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c index 58f546e04807..e4cf96ba704e 100644 --- a/drivers/clk/meson/clk-audio-divider.c +++ b/drivers/clk/meson/clk-audio-divider.c @@ -51,7 +51,7 @@ static unsigned long audio_divider_recalc_rate(struct clk_hw *hw, struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk); unsigned long divider; - divider = meson_parm_read(clk->map, &adiv->div); + divider = meson_parm_read(clk->map, &adiv->div) + 1; return DIV_ROUND_UP_ULL((u64)parent_rate, divider); } diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 240658404367..177fffb9ebef 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -498,6 +498,7 @@ static struct clk_regmap gxbb_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c index 6860bd5a37c5..44e4e27eddad 100644 --- a/drivers/clk/mvebu/armada-37xx-periph.c +++ b/drivers/clk/mvebu/armada-37xx-periph.c @@ -35,6 +35,7 @@ #define CLK_SEL 0x10 #define CLK_DIS 0x14 +#define ARMADA_37XX_DVFS_LOAD_1 1 #define LOAD_LEVEL_NR 4 #define ARMADA_37XX_NB_L0L1 0x18 @@ -507,6 +508,40 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate, return -EINVAL; } +/* + * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz + * respectively) to L0 frequency (1.2 Ghz) requires a significant + * amount of time to let VDD stabilize to the appropriate + * voltage. This amount of time is large enough that it cannot be + * covered by the hardware countdown register. Due to this, the CPU + * might start operating at L0 before the voltage is stabilized, + * leading to CPU stalls. + * + * To work around this problem, we prevent switching directly from the + * L2/L3 frequencies to the L0 frequency, and instead switch to the L1 + * frequency in-between. The sequence therefore becomes: + * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ) + * 2. Sleep 20ms for stabling VDD voltage + * 3. Then switch from L1(600MHZ) to L0(1200Mhz). + */ +static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base) +{ + unsigned int cur_level; + + if (rate != 1200 * 1000 * 1000) + return; + + regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level); + cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK; + if (cur_level <= ARMADA_37XX_DVFS_LOAD_1) + return; + + regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD, + ARMADA_37XX_NB_CPU_LOAD_MASK, + ARMADA_37XX_DVFS_LOAD_1); + msleep(20); +} + static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -537,6 +572,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, */ reg = ARMADA_37XX_NB_CPU_LOAD; mask = ARMADA_37XX_NB_CPU_LOAD_MASK; + + clk_pm_cpu_set_rate_wa(rate, base); + regmap_update_bits(base, reg, mask, load_level); return rate; diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index 9f35b3fe1d97..ff8d66fd94e6 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -2781,6 +2781,7 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = { static struct clk_branch gcc_ufs_tx_symbol_0_clk = { .halt_reg = 0x75018, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x75018, .enable_mask = BIT(0), diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c index 1a25ee4f3658..4b20d1b67a1b 100644 --- a/drivers/clk/qcom/mmcc-msm8996.c +++ b/drivers/clk/qcom/mmcc-msm8996.c @@ -2910,6 +2910,7 @@ static struct gdsc mmagic_bimc_gdsc = { .name = "mmagic_bimc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = ALWAYS_ON, }; static struct gdsc mmagic_video_gdsc = { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 3c3971256130..d4ed0022b0dd 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -311,12 +311,20 @@ static DEFINE_MUTEX(intel_pstate_limits_lock); #ifdef CONFIG_ACPI -static bool intel_pstate_get_ppc_enable_status(void) +static bool intel_pstate_acpi_pm_profile_server(void) { if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER || acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER) return true; + return false; +} + +static bool intel_pstate_get_ppc_enable_status(void) +{ + if (intel_pstate_acpi_pm_profile_server()) + return true; + return acpi_ppc; } @@ -459,6 +467,11 @@ static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *pol static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) { } + +static inline bool intel_pstate_acpi_pm_profile_server(void) +{ + return false; +} #endif static inline void update_turbo_state(void) @@ -1841,7 +1854,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_hwp_enable(cpu); id = x86_match_cpu(intel_pstate_hwp_boost_ids); - if (id) + if (id && intel_pstate_acpi_pm_profile_server()) hwp_boost = true; } diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index 29389accf3e9..efc9a7ae4857 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -183,6 +183,7 @@ static struct platform_driver qcom_cpufreq_kryo_driver = { static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = { { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, + {} }; /* diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 1c6cbda56afe..09d823d36d3a 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -266,6 +266,8 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key, return; } + count -= initial; + if (initial) asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */ : "+S"(input), "+D"(output) @@ -273,7 +275,7 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key, asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */ : "+S"(input), "+D"(output) - : "d"(control_word), "b"(key), "c"(count - initial)); + : "d"(control_word), "b"(key), "c"(count)); } static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, @@ -284,6 +286,8 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, if (count < cbc_fetch_blocks) return cbc_crypt(input, output, key, iv, control_word, count); + count -= initial; + if (initial) asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */ : "+S" (input), "+D" (output), "+a" (iv) @@ -291,7 +295,7 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */ : "+S" (input), "+D" (output), "+a" (iv) - : "d" (control_word), "b" (key), "c" (count-initial)); + : "d" (control_word), "b" (key), "c" (count)); return iv; } diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index d3cf9502e7e7..58faeb1cef63 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -181,7 +181,11 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node); fwspec.param_count = 2; fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET; - fwspec.param[1] = IRQ_TYPE_NONE; + /* + * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH + * temporarily. Anyway, ->irq_set_type() will override it later. + */ + fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH; return irq_create_fwspec_mapping(&fwspec); } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 28d968088131..53a14ee8ad6d 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -64,7 +64,8 @@ static void of_gpio_flags_quirks(struct device_node *np, * Note that active low is the default. */ if (IS_ENABLED(CONFIG_REGULATOR) && - (of_device_is_compatible(np, "reg-fixed-voltage") || + (of_device_is_compatible(np, "regulator-fixed") || + of_device_is_compatible(np, "reg-fixed-voltage") || of_device_is_compatible(np, "regulator-gpio"))) { /* * The regulator GPIO handles are specified such that the diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 73021b388e12..dd3ff2f2cdce 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -429,6 +429,18 @@ static void adv7511_hpd_work(struct work_struct *work) else status = connector_status_disconnected; + /* + * The bridge resets its registers on unplug. So when we get a plug + * event and we're already supposed to be powered, cycle the bridge to + * restore its state. + */ + if (status == connector_status_connected && + adv7511->connector.status == connector_status_disconnected && + adv7511->powered) { + regcache_mark_dirty(adv7511->regmap); + adv7511_power_on(adv7511); + } + if (adv7511->connector.status != status) { adv7511->connector.status = status; if (status == connector_status_disconnected) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 130da5195f3b..81e32199d3ef 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1510,8 +1510,9 @@ int drm_atomic_helper_async_check(struct drm_device *dev, { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; - struct drm_plane *plane; - struct drm_plane_state *old_plane_state, *new_plane_state; + struct drm_plane *plane = NULL; + struct drm_plane_state *old_plane_state = NULL; + struct drm_plane_state *new_plane_state = NULL; const struct drm_plane_helper_funcs *funcs; int i, n_planes = 0; @@ -1527,7 +1528,8 @@ int drm_atomic_helper_async_check(struct drm_device *dev, if (n_planes != 1) return -EINVAL; - if (!new_plane_state->crtc) + if (!new_plane_state->crtc || + old_plane_state->crtc != new_plane_state->crtc) return -EINVAL; funcs = plane->helper_private; diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c index 3c4000facb36..f973d287696a 100644 --- a/drivers/gpu/drm/drm_context.c +++ b/drivers/gpu/drm/drm_context.c @@ -372,7 +372,7 @@ int drm_legacy_addctx(struct drm_device *dev, void *data, ctx->handle = drm_legacy_ctxbitmap_next(dev); } DRM_DEBUG("%d\n", ctx->handle); - if (ctx->handle == -1) { + if (ctx->handle < 0) { DRM_DEBUG("Not enough free contexts.\n"); /* Should this return -EBUSY instead? */ return -ENOMEM; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 50c73c0a20b9..d638c0fb3418 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -553,24 +553,13 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, /* Clone the lessor file to create a new file for us */ DRM_DEBUG_LEASE("Allocating lease file\n"); - path_get(&lessor_file->f_path); - lessee_file = alloc_file(&lessor_file->f_path, - lessor_file->f_mode, - fops_get(lessor_file->f_inode->i_fop)); - + lessee_file = filp_clone_open(lessor_file); if (IS_ERR(lessee_file)) { ret = PTR_ERR(lessee_file); goto out_lessee; } - /* Initialize the new file for DRM */ - DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open); - ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file); - if (ret) - goto out_lessee_file; - lessee_priv = lessee_file->private_data; - /* Change the file to a master one */ drm_master_put(&lessee_priv->master); lessee_priv->master = lessee; @@ -588,9 +577,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n"); return 0; -out_lessee_file: - fput(lessee_file); - out_lessee: drm_master_put(&lessee); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 52f3b91d14fd..71e1aa54f774 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -652,6 +652,7 @@ enum intel_sbi_destination { #define QUIRK_BACKLIGHT_PRESENT (1<<3) #define QUIRK_PIN_SWIZZLED_PAGES (1<<5) #define QUIRK_INCREASE_T12_DELAY (1<<6) +#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7) struct intel_fbdev; struct intel_fbc_work; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f4a8598a2d39..fed26d6e4e27 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1782,15 +1782,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state) I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp); } -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder) +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder); uint32_t val = I915_READ(reg); val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC); val |= TRANS_DDI_PORT_NONE; I915_WRITE(reg, val); + + if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME && + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { + DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n"); + /* Quirk time at 100ms for reliable operation */ + msleep(100); + } } int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2cc6faa1daa8..dec0d60921bf 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5809,7 +5809,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_ddi_set_vc_payload_alloc(intel_crtc->config, false); if (!transcoder_is_dsi(cpu_transcoder)) - intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder); + intel_ddi_disable_transcoder_func(old_crtc_state); if (INTEL_GEN(dev_priv) >= 9) skylake_scaler_disable(intel_crtc); @@ -14646,6 +14646,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev) DRM_INFO("Applying T12 delay quirk\n"); } +/* + * GeminiLake NUC HDMI outputs require additional off time + * this allows the onboard retimer to correctly sync to signal + */ +static void quirk_increase_ddi_disabled_time(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + + dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME; + DRM_INFO("Applying Increase DDI Disabled quirk\n"); +} + struct intel_quirk { int device; int subsystem_vendor; @@ -14732,6 +14744,13 @@ static struct intel_quirk intel_quirks[] = { /* Toshiba Satellite P50-C-18C */ { 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay }, + + /* GeminiLake NUC */ + { 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + /* ASRock ITX*/ + { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, }; static void intel_init_quirks(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0361130500a6..b8eefbffc77d 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1388,8 +1388,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc, void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port); bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe); void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state); -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder); +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state); void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state); void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state); struct intel_encoder * diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 56dd7a9a8e25..dd5312b02a8d 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -612,6 +612,9 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) return PTR_ERR(imx_ldb->regmap); } + /* disable LDB by resetting the control register to POR default */ + regmap_write(imx_ldb->regmap, IOMUXC_GPR2, 0); + imx_ldb->dev = dev; if (of_id) @@ -652,14 +655,14 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) if (ret || i < 0 || i > 1) return -EINVAL; + if (!of_device_is_available(child)) + continue; + if (dual && i > 0) { dev_warn(dev, "dual-channel mode, ignoring second output\n"); continue; } - if (!of_device_is_available(child)) - continue; - channel = &imx_ldb->channel[i]; channel->ldb = imx_ldb; channel->chno = i; diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 1d34619eb3fe..a951ec75d01f 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -320,6 +320,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_state->x_scaling[0] = VC4_SCALING_TPZ; if (vc4_state->y_scaling[0] == VC4_SCALING_NONE) vc4_state->y_scaling[0] = VC4_SCALING_TPZ; + } else { + vc4_state->x_scaling[1] = VC4_SCALING_NONE; + vc4_state->y_scaling[1] = VC4_SCALING_NONE; } vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index caa05b0702e1..5450a2db1219 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -339,7 +339,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg, break; case V4L2_MBUS_BT656: csicfg->ext_vsync = 0; - if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field)) + if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field) || + mbus_fmt->field == V4L2_FIELD_ALTERNATE) csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED; else csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE; diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index 75d6ab177055..7379043711df 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -237,12 +237,16 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) /* * It's not always possible to have 1 to 2 ratio when d=7, so fall back * to minimal possible clkh in this case. + * + * Note: + * CLKH is not allowed to be 0, in this case I2C clock is not generated + * at all */ - if (clk >= clkl + d) { + if (clk > clkl + d) { clkh = clk - clkl - d; clkl -= d; } else { - clkh = 0; + clkh = 1; clkl = clk - (d << 1); } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 0207e194f84b..498c5e891649 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -368,6 +368,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx, goto err_desc; } + reinit_completion(&dma->cmd_complete); txdesc->callback = i2c_imx_dma_callback; txdesc->callback_param = i2c_imx; if (dma_submit_error(dmaengine_submit(txdesc))) { @@ -622,7 +623,6 @@ static int i2c_imx_dma_write(struct imx_i2c_struct *i2c_imx, * The first byte must be transmitted by the CPU. */ imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR); - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -681,7 +681,6 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, if (result) return result; - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -1010,7 +1009,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl, "gpio"); rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN); - rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH); + rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER || PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) { diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 5e310efd9446..3c1c817f6968 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -32,6 +32,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include <linux/slab.h> /* register offsets */ @@ -111,8 +112,9 @@ #define ID_ARBLOST (1 << 3) #define ID_NACK (1 << 4) /* persistent flags */ +#define ID_P_NO_RXDMA (1 << 30) /* HW forbids RXDMA sometimes */ #define ID_P_PM_BLOCKED (1 << 31) -#define ID_P_MASK ID_P_PM_BLOCKED +#define ID_P_MASK (ID_P_PM_BLOCKED | ID_P_NO_RXDMA) enum rcar_i2c_type { I2C_RCAR_GEN1, @@ -141,6 +143,8 @@ struct rcar_i2c_priv { struct dma_chan *dma_rx; struct scatterlist sg; enum dma_data_direction dma_direction; + + struct reset_control *rstc; }; #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) @@ -370,6 +374,11 @@ static void rcar_i2c_dma_unmap(struct rcar_i2c_priv *priv) dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg), sg_dma_len(&priv->sg), priv->dma_direction); + /* Gen3 can only do one RXDMA per transfer and we just completed it */ + if (priv->devtype == I2C_RCAR_GEN3 && + priv->dma_direction == DMA_FROM_DEVICE) + priv->flags |= ID_P_NO_RXDMA; + priv->dma_direction = DMA_NONE; } @@ -407,8 +416,9 @@ static void rcar_i2c_dma(struct rcar_i2c_priv *priv) unsigned char *buf; int len; - /* Do not use DMA if it's not available or for messages < 8 bytes */ - if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE)) + /* Do various checks to see if DMA is feasible at all */ + if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) || + (read && priv->flags & ID_P_NO_RXDMA)) return; if (read) { @@ -739,6 +749,25 @@ static void rcar_i2c_release_dma(struct rcar_i2c_priv *priv) } } +/* I2C is a special case, we need to poll the status of a reset */ +static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv) +{ + int i, ret; + + ret = reset_control_reset(priv->rstc); + if (ret) + return ret; + + for (i = 0; i < LOOP_TIMEOUT; i++) { + ret = reset_control_status(priv->rstc); + if (ret == 0) + return 0; + udelay(1); + } + + return -ETIMEDOUT; +} + static int rcar_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) @@ -750,6 +779,16 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, pm_runtime_get_sync(dev); + /* Gen3 needs a reset before allowing RXDMA once */ + if (priv->devtype == I2C_RCAR_GEN3) { + priv->flags |= ID_P_NO_RXDMA; + if (!IS_ERR(priv->rstc)) { + ret = rcar_i2c_do_reset(priv); + if (ret == 0) + priv->flags &= ~ID_P_NO_RXDMA; + } + } + rcar_i2c_init(priv); ret = rcar_i2c_bus_barrier(priv); @@ -920,6 +959,15 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put; + if (priv->devtype == I2C_RCAR_GEN3) { + priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (!IS_ERR(priv->rstc)) { + ret = reset_control_status(priv->rstc); + if (ret < 0) + priv->rstc = ERR_PTR(-ENOTSUPP); + } + } + /* Stay always active when multi-master to keep arbitration working */ if (of_property_read_bool(dev->of_node, "multi-master")) priv->flags |= ID_P_PM_BLOCKED; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 301285c54603..15c95aaa484c 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -624,7 +624,7 @@ static int i2c_check_addr_busy(struct i2c_adapter *adapter, int addr) static void i2c_adapter_lock_bus(struct i2c_adapter *adapter, unsigned int flags) { - rt_mutex_lock(&adapter->bus_lock); + rt_mutex_lock_nested(&adapter->bus_lock, i2c_adapter_depth(adapter)); } /** diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 300ab4b672e4..29646aa6132e 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -144,7 +144,7 @@ static void i2c_mux_lock_bus(struct i2c_adapter *adapter, unsigned int flags) struct i2c_mux_priv *priv = adapter->algo_data; struct i2c_adapter *parent = priv->muxc->parent; - rt_mutex_lock(&parent->mux_lock); + rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter)); if (!(flags & I2C_LOCK_ROOT_ADAPTER)) return; i2c_lock_bus(parent, flags); @@ -181,7 +181,7 @@ static void i2c_parent_lock_bus(struct i2c_adapter *adapter, struct i2c_mux_priv *priv = adapter->algo_data; struct i2c_adapter *parent = priv->muxc->parent; - rt_mutex_lock(&parent->mux_lock); + rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter)); i2c_lock_bus(parent, flags); } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index cc06e8404e9b..583d3a10b940 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1984,15 +1984,64 @@ static int modify_qp(struct ib_uverbs_file *file, goto release_qp; } - if ((cmd->base.attr_mask & IB_QP_AV) && - !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { - ret = -EINVAL; - goto release_qp; + if ((cmd->base.attr_mask & IB_QP_AV)) { + if (!rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { + ret = -EINVAL; + goto release_qp; + } + + if (cmd->base.attr_mask & IB_QP_STATE && + cmd->base.qp_state == IB_QPS_RTR) { + /* We are in INIT->RTR TRANSITION (if we are not, + * this transition will be rejected in subsequent checks). + * In the INIT->RTR transition, we cannot have IB_QP_PORT set, + * but the IB_QP_STATE flag is required. + * + * Since kernel 3.14 (commit dbf727de7440), the uverbs driver, + * when IB_QP_AV is set, has required inclusion of a valid + * port number in the primary AV. (AVs are created and handled + * differently for infiniband and ethernet (RoCE) ports). + * + * Check the port number included in the primary AV against + * the port number in the qp struct, which was set (and saved) + * in the RST->INIT transition. + */ + if (cmd->base.dest.port_num != qp->real_qp->port) { + ret = -EINVAL; + goto release_qp; + } + } else { + /* We are in SQD->SQD. (If we are not, this transition will + * be rejected later in the verbs layer checks). + * Check for both IB_QP_PORT and IB_QP_AV, these can be set + * together in the SQD->SQD transition. + * + * If only IP_QP_AV was set, add in IB_QP_PORT as well (the + * verbs layer driver does not track primary port changes + * resulting from path migration. Thus, in SQD, if the primary + * AV is modified, the primary port should also be modified). + * + * Note that in this transition, the IB_QP_STATE flag + * is not allowed. + */ + if (((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT)) + == (IB_QP_AV | IB_QP_PORT)) && + cmd->base.port_num != cmd->base.dest.port_num) { + ret = -EINVAL; + goto release_qp; + } + if ((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT)) + == IB_QP_AV) { + cmd->base.attr_mask |= IB_QP_PORT; + cmd->base.port_num = cmd->base.dest.port_num; + } + } } if ((cmd->base.attr_mask & IB_QP_ALT_PATH) && (!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) || - !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) { + !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num) || + cmd->base.alt_port_num != cmd->base.alt_dest.port_num)) { ret = -EINVAL; goto release_qp; } diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 1f9cd7d8b7ad..f5ae24865355 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1346,6 +1346,8 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0611", 0 }, { "ELAN0612", 0 }, { "ELAN0618", 0 }, + { "ELAN061D", 0 }, + { "ELAN0622", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index b353d494ad40..136f6e7bf797 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -527,6 +527,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), }, }, + { + /* Lenovo LaVie Z */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), + }, + }, { } }; diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index 72a271b98873..ebb3fa2e1d00 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -2220,7 +2220,7 @@ hfc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct hfc_pci *card; struct _hfc_map *m = (struct _hfc_map *)ent->driver_data; - card = kzalloc(sizeof(struct hfc_pci), GFP_ATOMIC); + card = kzalloc(sizeof(struct hfc_pci), GFP_KERNEL); if (!card) { printk(KERN_ERR "No kmem for HFC card\n"); return err; diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index 89d9ba8ed535..2b317cb63d06 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -1084,7 +1084,7 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } - card = kzalloc(sizeof(struct tiger_hw), GFP_ATOMIC); + card = kzalloc(sizeof(struct tiger_hw), GFP_KERNEL); if (!card) { pr_info("No kmem for Netjet\n"); return err; diff --git a/drivers/isdn/hisax/callc.c b/drivers/isdn/hisax/callc.c index 5f43783039d4..9ee06328784c 100644 --- a/drivers/isdn/hisax/callc.c +++ b/drivers/isdn/hisax/callc.c @@ -1012,7 +1012,7 @@ dummy_pstack(struct PStack *st, int pr, void *arg) { static int init_PStack(struct PStack **stp) { - *stp = kmalloc(sizeof(struct PStack), GFP_ATOMIC); + *stp = kmalloc(sizeof(struct PStack), GFP_KERNEL); if (!*stp) return -ENOMEM; (*stp)->next = NULL; diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c index fcc9c46127b4..b12e6cae26c2 100644 --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -1029,7 +1029,7 @@ static int hisax_cs_new(int cardnr, char *id, struct IsdnCard *card, *cs_out = NULL; - cs = kzalloc(sizeof(struct IsdnCardState), GFP_ATOMIC); + cs = kzalloc(sizeof(struct IsdnCardState), GFP_KERNEL); if (!cs) { printk(KERN_WARNING "HiSax: No memory for IsdnCardState(card %d)\n", @@ -1059,12 +1059,12 @@ static int hisax_cs_new(int cardnr, char *id, struct IsdnCard *card, "HiSax: Card Type %d out of range\n", card->typ); goto outf_cs; } - if (!(cs->dlog = kmalloc(MAX_DLOG_SPACE, GFP_ATOMIC))) { + if (!(cs->dlog = kmalloc(MAX_DLOG_SPACE, GFP_KERNEL))) { printk(KERN_WARNING "HiSax: No memory for dlog(card %d)\n", cardnr + 1); goto outf_cs; } - if (!(cs->status_buf = kmalloc(HISAX_STATUS_BUFSIZE, GFP_ATOMIC))) { + if (!(cs->status_buf = kmalloc(HISAX_STATUS_BUFSIZE, GFP_KERNEL))) { printk(KERN_WARNING "HiSax: No memory for status_buf(card %d)\n", cardnr + 1); @@ -1123,7 +1123,7 @@ static int hisax_cs_setup(int cardnr, struct IsdnCard *card, { int ret; - if (!(cs->rcvbuf = kmalloc(MAX_DFRAME_LEN_L1, GFP_ATOMIC))) { + if (!(cs->rcvbuf = kmalloc(MAX_DFRAME_LEN_L1, GFP_KERNEL))) { printk(KERN_WARNING "HiSax: No memory for isac rcvbuf\n"); ll_unload(cs); goto outf_cs; diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c index edb35a5c57ea..a99fc0ced7a7 100644 --- a/drivers/media/platform/vsp1/vsp1_drm.c +++ b/drivers/media/platform/vsp1/vsp1_drm.c @@ -728,9 +728,6 @@ EXPORT_SYMBOL_GPL(vsp1_du_setup_lif); */ void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index) { - struct vsp1_device *vsp1 = dev_get_drvdata(dev); - - mutex_lock(&vsp1->drm->lock); } EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin); @@ -846,6 +843,7 @@ void vsp1_du_atomic_flush(struct device *dev, unsigned int pipe_index, drm_pipe->crc = cfg->crc; + mutex_lock(&vsp1->drm->lock); vsp1_du_pipeline_setup_inputs(vsp1, pipe); vsp1_du_pipeline_configure(pipe); mutex_unlock(&vsp1->drm->lock); diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fcfab6635f9c..81b150e5dfdb 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -174,6 +174,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog) rcu_assign_pointer(raw->progs, new_array); bpf_prog_array_free(old_array); + bpf_prog_put(prog); unlock: mutex_unlock(&ir_raw_handler_lock); return ret; diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c index 2e0066b1a31c..e7948908e78c 100644 --- a/drivers/media/rc/rc-ir-raw.c +++ b/drivers/media/rc/rc-ir-raw.c @@ -30,13 +30,13 @@ static int ir_raw_event_thread(void *data) while (kfifo_out(&raw->kfifo, &ev, 1)) { if (is_timing_event(ev)) { if (ev.duration == 0) - dev_err(&dev->dev, "nonsensical timing event of duration 0"); + dev_warn_once(&dev->dev, "nonsensical timing event of duration 0"); if (is_timing_event(raw->prev_ev) && !is_transition(&ev, &raw->prev_ev)) - dev_err(&dev->dev, "two consecutive events of type %s", - TO_STR(ev.pulse)); + dev_warn_once(&dev->dev, "two consecutive events of type %s", + TO_STR(ev.pulse)); if (raw->prev_ev.reset && ev.pulse == 0) - dev_err(&dev->dev, "timing event after reset should be pulse"); + dev_warn_once(&dev->dev, "timing event after reset should be pulse"); } list_for_each_entry(handler, &ir_raw_handler_list, list) if (dev->enabled_protocols & diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 2e222d9ee01f..ca68e1d2b2f9 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -679,6 +679,14 @@ static void ir_timer_repeat(struct timer_list *t) spin_unlock_irqrestore(&dev->keylock, flags); } +static unsigned int repeat_period(int protocol) +{ + if (protocol >= ARRAY_SIZE(protocols)) + return 100; + + return protocols[protocol].repeat_period; +} + /** * rc_repeat() - signals that a key is still pressed * @dev: the struct rc_dev descriptor of the device @@ -691,7 +699,7 @@ void rc_repeat(struct rc_dev *dev) { unsigned long flags; unsigned int timeout = nsecs_to_jiffies(dev->timeout) + - msecs_to_jiffies(protocols[dev->last_protocol].repeat_period); + msecs_to_jiffies(repeat_period(dev->last_protocol)); struct lirc_scancode sc = { .scancode = dev->last_scancode, .rc_proto = dev->last_protocol, .keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED, @@ -803,7 +811,7 @@ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u32 scancode, if (dev->keypressed) { dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) + - msecs_to_jiffies(protocols[protocol].repeat_period); + msecs_to_jiffies(repeat_period(protocol)); mod_timer(&dev->timer_keyup, dev->keyup_jiffies); } spin_unlock_irqrestore(&dev->keylock, flags); diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c index 753b1a698fc4..6b16946f9b05 100644 --- a/drivers/misc/cxl/api.c +++ b/drivers/misc/cxl/api.c @@ -103,15 +103,15 @@ static struct file *cxl_getfile(const char *name, d_instantiate(path.dentry, inode); file = alloc_file(&path, OPEN_FMODE(flags), fops); - if (IS_ERR(file)) - goto err_dput; + if (IS_ERR(file)) { + path_put(&path); + goto err_fs; + } file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; return file; -err_dput: - path_put(&path); err_inode: iput(inode); err_fs: diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 75f781c11e89..de4e6e5bf304 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -293,9 +293,10 @@ static void mxcmci_swap_buffers(struct mmc_data *data) int i; for_each_sg(data->sg, sg, data->sg_len, i) { - void *buf = kmap_atomic(sg_page(sg) + sg->offset; + void *buf = kmap_atomic(sg_page(sg) + sg->offset); buffer_swap32(buf, sg->length); kunmap_atomic(buf); + } } #else static inline void mxcmci_swap_buffers(struct mmc_data *data) {} diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9a2ea3c1f949..a764a83f99da 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1717,6 +1717,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_upper_unlink; } + bond->nest_level = dev_get_nest_level(bond_dev) + 1; + /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ @@ -1764,7 +1766,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); - bond->nest_level = dev_get_nest_level(bond_dev); netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n", slave_dev->name, @@ -3415,6 +3416,13 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +static int bond_get_nest_level(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + return bond->nest_level; +} + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3423,7 +3431,7 @@ static void bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; - spin_lock(&bond->stats_lock); + spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev)); memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); @@ -4228,6 +4236,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, + .ndo_get_lock_subclass = bond_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, @@ -4726,6 +4735,7 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->nest_level = SINGLE_DEPTH_NESTING; netdev_lockdep_set_classes(bond_dev); list_add_tail(&bond->bond_list, &bn->dev_list); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 98663c50ded0..4d5d01cb8141 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option) static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { - if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) { - netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", - newval->string); - /* disable arp monitoring */ - bond->params.arp_interval = 0; - /* set miimon to default value */ - bond->params.miimon = BOND_DEFAULT_MIIMON; - netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", - bond->params.miimon); + if (!bond_mode_uses_arp(newval->value)) { + if (bond->params.arp_interval) { + netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", + newval->string); + /* disable arp monitoring */ + bond->params.arp_interval = 0; + } + + if (!bond->params.miimon) { + /* set miimon to default value */ + bond->params.miimon = BOND_DEFAULT_MIIMON; + netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", + bond->params.miimon); + } } if (newval->value == BOND_MODE_ALB) diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index d4dd4da23997..da636a22c542 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -73,7 +73,7 @@ MODULE_PARM_DESC(msgobj15_eff, "Extended 29-bit frames for message object 15 " static int i82527_compat; module_param(i82527_compat, int, 0444); -MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 comptibility mode " +MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 compatibility mode " "without using additional functions"); /* diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 3c71f1cb205f..49163570a63a 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -649,8 +649,7 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; - *cf = skb_put(skb, sizeof(struct can_frame)); - memset(*cf, 0, sizeof(struct can_frame)); + *cf = skb_put_zero(skb, sizeof(struct can_frame)); return skb; } @@ -678,8 +677,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; - *cfd = skb_put(skb, sizeof(struct canfd_frame)); - memset(*cfd, 0, sizeof(struct canfd_frame)); + *cfd = skb_put_zero(skb, sizeof(struct canfd_frame)); return skb; } @@ -703,7 +701,8 @@ EXPORT_SYMBOL_GPL(alloc_can_err_skb); /* * Allocate and setup space for the CAN network device */ -struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) +struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, + unsigned int txqs, unsigned int rxqs) { struct net_device *dev; struct can_priv *priv; @@ -715,7 +714,8 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) else size = sizeof_priv; - dev = alloc_netdev(size, "can%d", NET_NAME_UNKNOWN, can_setup); + dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup, + txqs, rxqs); if (!dev) return NULL; @@ -734,7 +734,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) return dev; } -EXPORT_SYMBOL_GPL(alloc_candev); +EXPORT_SYMBOL_GPL(alloc_candev_mqs); /* * Free space of the CAN network device diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index d53a45bf2a72..8e972ef08637 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1,24 +1,13 @@ -/* - * flexcan.c - FLEXCAN CAN controller driver - * - * Copyright (c) 2005-2006 Varma Electronics Oy - * Copyright (c) 2009 Sascha Hauer, Pengutronix - * Copyright (c) 2010-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> - * Copyright (c) 2014 David Jander, Protonic Holland - * - * Based on code originally by Andrey Volkov <avolkov@varma-el.com> - * - * LICENCE: - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0 +// +// flexcan.c - FLEXCAN CAN controller driver +// +// Copyright (c) 2005-2006 Varma Electronics Oy +// Copyright (c) 2009 Sascha Hauer, Pengutronix +// Copyright (c) 2010-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> +// Copyright (c) 2014 David Jander, Protonic Holland +// +// Based on code originally by Andrey Volkov <avolkov@varma-el.com> #include <linux/netdevice.h> #include <linux/can.h> @@ -523,7 +512,7 @@ static int flexcan_get_berr_counter(const struct net_device *dev, return err; } -static int flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev) { const struct flexcan_priv *priv = netdev_priv(dev); struct can_frame *cf = (struct can_frame *)skb->data; diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index adfdb66a486e..02042cb09bd2 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1684,7 +1684,7 @@ static int ican3_stop(struct net_device *ndev) return 0; } -static int ican3_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t ican3_xmit(struct sk_buff *skb, struct net_device *ndev) { struct ican3_dev *mod = netdev_priv(ndev); struct can_frame *cf = (struct can_frame *)skb->data; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b397a33f3d32..9b449400376b 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv) int err; err = pm_runtime_get_sync(priv->device); - if (err) + if (err < 0) { pm_runtime_put_noidle(priv->device); + return err; + } - return err; + return 0; } static void m_can_clk_stop(struct m_can_priv *priv) @@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev) } else { /* Version 3.1.x or 3.2.x */ - cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE); + cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE | + CCCR_NISO); /* Only 3.2.x has NISO Bit implemented */ if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) @@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev) priv->can.clock.freq = clk_get_rate(cclk); priv->mram_base = mram_addr; - m_can_of_parse_mram(priv, mram_config_vals); - platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); @@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev) goto clk_disable; } + m_can_of_parse_mram(priv, mram_config_vals); + devm_can_led_init(dev); of_can_transceiver(dev); @@ -1687,8 +1690,6 @@ failed_ret: return ret; } -/* TODO: runtime PM with power down or sleep mode */ - static __maybe_unused int m_can_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); @@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - m_can_init_ram(priv); - priv->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { @@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev) if (ret) return ret; + m_can_init_ram(priv); m_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index c7427bdd3a4b..2949a381a94d 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev, return 0; } cdm = of_iomap(np_cdm, 0); + if (!cdm) { + of_node_put(np_cdm); + dev_err(&ofdev->dev, "can't map clock node!\n"); + return 0; + } if (in_8(&cdm->ipb_clk_sel) & 0x1) freq *= 2; diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index ed8561d4a90f..5696d7e80751 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -486,7 +486,7 @@ int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv, if (msg_size <= 0) break; - msg_ptr += msg_size; + msg_ptr += ALIGN(msg_size, 4); } if (msg_size < 0) diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index b9e28578bc7b..c458d5fdc8d3 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2"); #define PCIEFD_REG_SYS_VER1 0x0040 /* version reg #1 */ #define PCIEFD_REG_SYS_VER2 0x0044 /* version reg #2 */ +#define PCIEFD_FW_VERSION(x, y, z) (((u32)(x) << 24) | \ + ((u32)(y) << 16) | \ + ((u32)(z) << 8)) + /* System Control Registers Bits */ #define PCIEFD_SYS_CTL_TS_RST 0x00000001 /* timestamp clock */ #define PCIEFD_SYS_CTL_CLK_EN 0x00000002 /* system clock */ @@ -170,9 +174,6 @@ struct pciefd_page { u32 size; }; -#define CANFD_IRQ_SET 0x00000001 -#define CANFD_TX_PATH_SET 0x00000002 - /* CAN-FD channel object */ struct pciefd_board; struct pciefd_can { @@ -414,7 +415,7 @@ static int pciefd_pre_cmd(struct peak_canfd_priv *ucan) break; /* going into operational mode: setup IRQ handler */ - err = request_irq(priv->board->pci_dev->irq, + err = request_irq(priv->ucan.ndev->irq, pciefd_irq_handler, IRQF_SHARED, PCIEFD_DRV_NAME, @@ -487,15 +488,18 @@ static int pciefd_post_cmd(struct peak_canfd_priv *ucan) /* controller now in reset mode: */ + /* disable IRQ for this CAN */ + pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT, + PCIEFD_REG_CAN_RX_CTL_CLR); + /* stop and reset DMA addresses in Tx/Rx engines */ pciefd_can_clear_tx_dma(priv); pciefd_can_clear_rx_dma(priv); - /* disable IRQ for this CAN */ - pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT, - PCIEFD_REG_CAN_RX_CTL_CLR); + /* wait for above commands to complete (read cycle) */ + (void)pciefd_sys_readreg(priv->board, PCIEFD_REG_SYS_VER1); - free_irq(priv->board->pci_dev->irq, priv); + free_irq(priv->ucan.ndev->irq, priv); ucan->can.state = CAN_STATE_STOPPED; @@ -634,7 +638,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd) GFP_KERNEL); if (!priv->tx_dma_vaddr) { dev_err(&pciefd->pci_dev->dev, - "Tx dmaim_alloc_coherent(%u) failure\n", + "Tx dmam_alloc_coherent(%u) failure\n", PCIEFD_TX_DMA_SIZE); goto err_free_candev; } @@ -687,7 +691,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd) pciefd->can[pciefd->can_count] = priv; dev_info(&pciefd->pci_dev->dev, "%s at reg_base=0x%p irq=%d\n", - ndev->name, priv->reg_base, pciefd->pci_dev->irq); + ndev->name, priv->reg_base, ndev->irq); return 0; @@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev, "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count, hw_ver_major, hw_ver_minor, hw_ver_sub); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + /* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and + * 64-bit logical addresses: this workaround forces usage of 32-bit + * DMA addresses only when such a fw is detected. + */ + if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) < + PCIEFD_FW_VERSION(3, 3, 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + dev_warn(&pdev->dev, + "warning: can't set DMA mask %llxh (err %d)\n", + DMA_BIT_MASK(32), err); + } +#endif + /* stop system clock */ pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN, PCIEFD_REG_SYS_CTL_CLR); diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 5adc95c922ee..a97b81d1d0da 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -608,7 +608,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) writeb(0x00, cfg_base + PITA_GPIOICR); /* Toggle reset */ writeb(0x05, cfg_base + PITA_MISC + 3); - mdelay(5); + usleep_range(5000, 6000); /* Leave parport mux mode */ writeb(0x04, cfg_base + PITA_MISC + 3); diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c index 485b19c9ae47..b8c39ede7cd5 100644 --- a/drivers/net/can/sja1000/peak_pcmcia.c +++ b/drivers/net/can/sja1000/peak_pcmcia.c @@ -530,7 +530,7 @@ static int pcan_add_channels(struct pcan_pccard *card) pcan_write_reg(card, PCC_CCR, ccr); /* wait 2ms before unresetting channels */ - mdelay(2); + usleep_range(2000, 3000); ccr &= ~PCC_CCR_RST_ALL; pcan_write_reg(card, PCC_CCR, ccr); diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 1ac2090a1721..093fc9a529f0 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -409,7 +409,7 @@ static int sun4ican_set_mode(struct net_device *dev, enum can_mode mode) * xx xx xx xx ff ll 00 11 22 33 44 55 66 77 * [ can_id ] [flags] [len] [can data (up to 8 bytes] */ -static int sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct sun4ican_priv *priv = netdev_priv(dev); struct can_frame *cf = (struct can_frame *)skb->data; diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index c36f4bdcbf4f..750d04d9e2ae 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -1,6 +1,12 @@ menu "CAN USB interfaces" depends on USB +config CAN_8DEV_USB + tristate "8 devices USB2CAN interface" + ---help--- + This driver supports the USB2CAN interface + from 8 devices (http://www.8devices.com). + config CAN_EMS_USB tristate "EMS CPC-USB/ARM7 CAN/USB interface" ---help--- @@ -26,7 +32,7 @@ config CAN_KVASER_USB tristate "Kvaser CAN/USB interface" ---help--- This driver adds support for Kvaser CAN/USB devices like Kvaser - Leaf Light and Kvaser USBcan II. + Leaf Light, Kvaser USBcan II and Kvaser Memorator Pro 5xHS. The driver provides support for the following devices: - Kvaser Leaf Light @@ -55,12 +61,30 @@ config CAN_KVASER_USB - Kvaser Memorator HS/HS - Kvaser Memorator HS/LS - Scania VCI2 (if you have the Kvaser logo on top) + - Kvaser BlackBird v2 + - Kvaser Leaf Pro HS v2 + - Kvaser Hybrid 2xCAN/LIN + - Kvaser Hybrid Pro 2xCAN/LIN + - Kvaser Memorator 2xHS v2 + - Kvaser Memorator Pro 2xHS v2 + - Kvaser Memorator Pro 5xHS + - Kvaser USBcan Light 4xHS + - Kvaser USBcan Pro 2xHS v2 + - Kvaser USBcan Pro 5xHS + - ATI Memorator Pro 2xHS v2 + - ATI USBcan Pro 2xHS v2 If unsure, say N. To compile this driver as a module, choose M here: the module will be called kvaser_usb. +config CAN_MCBA_USB + tristate "Microchip CAN BUS Analyzer interface" + ---help--- + This driver supports the CAN BUS Analyzer interface + from Microchip (http://www.microchip.com/development-tools/). + config CAN_PEAK_USB tristate "PEAK PCAN-USB/USB Pro interfaces for CAN 2.0b/CAN-FD" ---help--- @@ -77,16 +101,26 @@ config CAN_PEAK_USB (see also http://www.peak-system.com). -config CAN_8DEV_USB - tristate "8 devices USB2CAN interface" - ---help--- - This driver supports the USB2CAN interface - from 8 devices (http://www.8devices.com). - config CAN_MCBA_USB tristate "Microchip CAN BUS Analyzer interface" ---help--- This driver supports the CAN BUS Analyzer interface from Microchip (http://www.microchip.com/development-tools/). +config CAN_UCAN + tristate "Theobroma Systems UCAN interface" + ---help--- + This driver supports the Theobroma Systems + UCAN USB-CAN interface. + + The UCAN driver supports the microcontroller-based USB/CAN + adapters from Theobroma Systems. There are two form-factors + that run essentially the same firmware: + + * Seal: standalone USB stick + https://www.theobroma-systems.com/seal) + * Mule: integrated on the PCB of various System-on-Modules + from Theobroma Systems like the A31-µQ7 and the RK3399-Q7 + (https://www.theobroma-systems.com/rk3399-q7) + endmenu diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile index 49ac7b99ba32..aa0f17c0b2ed 100644 --- a/drivers/net/can/usb/Makefile +++ b/drivers/net/can/usb/Makefile @@ -3,10 +3,11 @@ # Makefile for the Linux Controller Area Network USB drivers. # +obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o obj-$(CONFIG_CAN_EMS_USB) += ems_usb.o obj-$(CONFIG_CAN_ESD_USB2) += esd_usb2.o obj-$(CONFIG_CAN_GS_USB) += gs_usb.o -obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o -obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/ -obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o +obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb/ obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o +obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/ +obj-$(CONFIG_CAN_UCAN) += ucan.o diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 12ff0020ecd6..b7dfd4109d24 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -1072,6 +1072,7 @@ static void ems_usb_disconnect(struct usb_interface *intf) usb_free_urb(dev->intr_urb); kfree(dev->intr_in_buffer); + kfree(dev->tx_msg_buffer); } } diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c deleted file mode 100644 index daed57d3d209..000000000000 --- a/drivers/net/can/usb/kvaser_usb.c +++ /dev/null @@ -1,2085 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * Parts of this driver are based on the following: - * - Kvaser linux leaf driver (version 4.78) - * - CAN driver for esd CAN-USB/2 - * - Kvaser linux usbcanII driver (version 5.3) - * - * Copyright (C) 2002-2006 KVASER AB, Sweden. All rights reserved. - * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh - * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be> - * Copyright (C) 2015 Valeo S.A. - */ - -#include <linux/spinlock.h> -#include <linux/kernel.h> -#include <linux/completion.h> -#include <linux/module.h> -#include <linux/netdevice.h> -#include <linux/usb.h> - -#include <linux/can.h> -#include <linux/can/dev.h> -#include <linux/can/error.h> - -#define MAX_RX_URBS 4 -#define START_TIMEOUT 1000 /* msecs */ -#define STOP_TIMEOUT 1000 /* msecs */ -#define USB_SEND_TIMEOUT 1000 /* msecs */ -#define USB_RECV_TIMEOUT 1000 /* msecs */ -#define RX_BUFFER_SIZE 3072 -#define CAN_USB_CLOCK 8000000 -#define MAX_NET_DEVICES 3 -#define MAX_USBCAN_NET_DEVICES 2 - -/* Kvaser Leaf USB devices */ -#define KVASER_VENDOR_ID 0x0bfd -#define USB_LEAF_DEVEL_PRODUCT_ID 10 -#define USB_LEAF_LITE_PRODUCT_ID 11 -#define USB_LEAF_PRO_PRODUCT_ID 12 -#define USB_LEAF_SPRO_PRODUCT_ID 14 -#define USB_LEAF_PRO_LS_PRODUCT_ID 15 -#define USB_LEAF_PRO_SWC_PRODUCT_ID 16 -#define USB_LEAF_PRO_LIN_PRODUCT_ID 17 -#define USB_LEAF_SPRO_LS_PRODUCT_ID 18 -#define USB_LEAF_SPRO_SWC_PRODUCT_ID 19 -#define USB_MEMO2_DEVEL_PRODUCT_ID 22 -#define USB_MEMO2_HSHS_PRODUCT_ID 23 -#define USB_UPRO_HSHS_PRODUCT_ID 24 -#define USB_LEAF_LITE_GI_PRODUCT_ID 25 -#define USB_LEAF_PRO_OBDII_PRODUCT_ID 26 -#define USB_MEMO2_HSLS_PRODUCT_ID 27 -#define USB_LEAF_LITE_CH_PRODUCT_ID 28 -#define USB_BLACKBIRD_SPRO_PRODUCT_ID 29 -#define USB_OEM_MERCURY_PRODUCT_ID 34 -#define USB_OEM_LEAF_PRODUCT_ID 35 -#define USB_CAN_R_PRODUCT_ID 39 -#define USB_LEAF_LITE_V2_PRODUCT_ID 288 -#define USB_MINI_PCIE_HS_PRODUCT_ID 289 -#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290 -#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID 291 -#define USB_MINI_PCIE_2HS_PRODUCT_ID 292 - -static inline bool kvaser_is_leaf(const struct usb_device_id *id) -{ - return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID && - id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID; -} - -/* Kvaser USBCan-II devices */ -#define USB_USBCAN_REVB_PRODUCT_ID 2 -#define USB_VCI2_PRODUCT_ID 3 -#define USB_USBCAN2_PRODUCT_ID 4 -#define USB_MEMORATOR_PRODUCT_ID 5 - -static inline bool kvaser_is_usbcan(const struct usb_device_id *id) -{ - return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID && - id->idProduct <= USB_MEMORATOR_PRODUCT_ID; -} - -/* USB devices features */ -#define KVASER_HAS_SILENT_MODE BIT(0) -#define KVASER_HAS_TXRX_ERRORS BIT(1) - -/* Message header size */ -#define MSG_HEADER_LEN 2 - -/* Can message flags */ -#define MSG_FLAG_ERROR_FRAME BIT(0) -#define MSG_FLAG_OVERRUN BIT(1) -#define MSG_FLAG_NERR BIT(2) -#define MSG_FLAG_WAKEUP BIT(3) -#define MSG_FLAG_REMOTE_FRAME BIT(4) -#define MSG_FLAG_RESERVED BIT(5) -#define MSG_FLAG_TX_ACK BIT(6) -#define MSG_FLAG_TX_REQUEST BIT(7) - -/* Can states (M16C CxSTRH register) */ -#define M16C_STATE_BUS_RESET BIT(0) -#define M16C_STATE_BUS_ERROR BIT(4) -#define M16C_STATE_BUS_PASSIVE BIT(5) -#define M16C_STATE_BUS_OFF BIT(6) - -/* Can msg ids */ -#define CMD_RX_STD_MESSAGE 12 -#define CMD_TX_STD_MESSAGE 13 -#define CMD_RX_EXT_MESSAGE 14 -#define CMD_TX_EXT_MESSAGE 15 -#define CMD_SET_BUS_PARAMS 16 -#define CMD_GET_BUS_PARAMS 17 -#define CMD_GET_BUS_PARAMS_REPLY 18 -#define CMD_GET_CHIP_STATE 19 -#define CMD_CHIP_STATE_EVENT 20 -#define CMD_SET_CTRL_MODE 21 -#define CMD_GET_CTRL_MODE 22 -#define CMD_GET_CTRL_MODE_REPLY 23 -#define CMD_RESET_CHIP 24 -#define CMD_RESET_CARD 25 -#define CMD_START_CHIP 26 -#define CMD_START_CHIP_REPLY 27 -#define CMD_STOP_CHIP 28 -#define CMD_STOP_CHIP_REPLY 29 - -#define CMD_LEAF_GET_CARD_INFO2 32 -#define CMD_USBCAN_RESET_CLOCK 32 -#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT 33 - -#define CMD_GET_CARD_INFO 34 -#define CMD_GET_CARD_INFO_REPLY 35 -#define CMD_GET_SOFTWARE_INFO 38 -#define CMD_GET_SOFTWARE_INFO_REPLY 39 -#define CMD_ERROR_EVENT 45 -#define CMD_FLUSH_QUEUE 48 -#define CMD_RESET_ERROR_COUNTER 49 -#define CMD_TX_ACKNOWLEDGE 50 -#define CMD_CAN_ERROR_EVENT 51 -#define CMD_FLUSH_QUEUE_REPLY 68 - -#define CMD_LEAF_USB_THROTTLE 77 -#define CMD_LEAF_LOG_MESSAGE 106 - -/* error factors */ -#define M16C_EF_ACKE BIT(0) -#define M16C_EF_CRCE BIT(1) -#define M16C_EF_FORME BIT(2) -#define M16C_EF_STFE BIT(3) -#define M16C_EF_BITE0 BIT(4) -#define M16C_EF_BITE1 BIT(5) -#define M16C_EF_RCVE BIT(6) -#define M16C_EF_TRE BIT(7) - -/* Only Leaf-based devices can report M16C error factors, - * thus define our own error status flags for USBCANII - */ -#define USBCAN_ERROR_STATE_NONE 0 -#define USBCAN_ERROR_STATE_TX_ERROR BIT(0) -#define USBCAN_ERROR_STATE_RX_ERROR BIT(1) -#define USBCAN_ERROR_STATE_BUSERROR BIT(2) - -/* bittiming parameters */ -#define KVASER_USB_TSEG1_MIN 1 -#define KVASER_USB_TSEG1_MAX 16 -#define KVASER_USB_TSEG2_MIN 1 -#define KVASER_USB_TSEG2_MAX 8 -#define KVASER_USB_SJW_MAX 4 -#define KVASER_USB_BRP_MIN 1 -#define KVASER_USB_BRP_MAX 64 -#define KVASER_USB_BRP_INC 1 - -/* ctrl modes */ -#define KVASER_CTRL_MODE_NORMAL 1 -#define KVASER_CTRL_MODE_SILENT 2 -#define KVASER_CTRL_MODE_SELFRECEPTION 3 -#define KVASER_CTRL_MODE_OFF 4 - -/* Extended CAN identifier flag */ -#define KVASER_EXTENDED_FRAME BIT(31) - -/* Kvaser USB CAN dongles are divided into two major families: - * - Leaf: Based on Renesas M32C, running firmware labeled as 'filo' - * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios' - */ -enum kvaser_usb_family { - KVASER_LEAF, - KVASER_USBCAN, -}; - -struct kvaser_msg_simple { - u8 tid; - u8 channel; -} __packed; - -struct kvaser_msg_cardinfo { - u8 tid; - u8 nchannels; - union { - struct { - __le32 serial_number; - __le32 padding; - } __packed leaf0; - struct { - __le32 serial_number_low; - __le32 serial_number_high; - } __packed usbcan0; - } __packed; - __le32 clock_resolution; - __le32 mfgdate; - u8 ean[8]; - u8 hw_revision; - union { - struct { - u8 usb_hs_mode; - } __packed leaf1; - struct { - u8 padding; - } __packed usbcan1; - } __packed; - __le16 padding; -} __packed; - -struct kvaser_msg_cardinfo2 { - u8 tid; - u8 reserved; - u8 pcb_id[24]; - __le32 oem_unlock_code; -} __packed; - -struct leaf_msg_softinfo { - u8 tid; - u8 padding0; - __le32 sw_options; - __le32 fw_version; - __le16 max_outstanding_tx; - __le16 padding1[9]; -} __packed; - -struct usbcan_msg_softinfo { - u8 tid; - u8 fw_name[5]; - __le16 max_outstanding_tx; - u8 padding[6]; - __le32 fw_version; - __le16 checksum; - __le16 sw_options; -} __packed; - -struct kvaser_msg_busparams { - u8 tid; - u8 channel; - __le32 bitrate; - u8 tseg1; - u8 tseg2; - u8 sjw; - u8 no_samp; -} __packed; - -struct kvaser_msg_tx_can { - u8 channel; - u8 tid; - u8 msg[14]; - union { - struct { - u8 padding; - u8 flags; - } __packed leaf; - struct { - u8 flags; - u8 padding; - } __packed usbcan; - } __packed; -} __packed; - -struct kvaser_msg_rx_can_header { - u8 channel; - u8 flag; -} __packed; - -struct leaf_msg_rx_can { - u8 channel; - u8 flag; - - __le16 time[3]; - u8 msg[14]; -} __packed; - -struct usbcan_msg_rx_can { - u8 channel; - u8 flag; - - u8 msg[14]; - __le16 time; -} __packed; - -struct leaf_msg_chip_state_event { - u8 tid; - u8 channel; - - __le16 time[3]; - u8 tx_errors_count; - u8 rx_errors_count; - - u8 status; - u8 padding[3]; -} __packed; - -struct usbcan_msg_chip_state_event { - u8 tid; - u8 channel; - - u8 tx_errors_count; - u8 rx_errors_count; - __le16 time; - - u8 status; - u8 padding[3]; -} __packed; - -struct kvaser_msg_tx_acknowledge_header { - u8 channel; - u8 tid; -} __packed; - -struct leaf_msg_tx_acknowledge { - u8 channel; - u8 tid; - - __le16 time[3]; - u8 flags; - u8 time_offset; -} __packed; - -struct usbcan_msg_tx_acknowledge { - u8 channel; - u8 tid; - - __le16 time; - __le16 padding; -} __packed; - -struct leaf_msg_error_event { - u8 tid; - u8 flags; - __le16 time[3]; - u8 channel; - u8 padding; - u8 tx_errors_count; - u8 rx_errors_count; - u8 status; - u8 error_factor; -} __packed; - -struct usbcan_msg_error_event { - u8 tid; - u8 padding; - u8 tx_errors_count_ch0; - u8 rx_errors_count_ch0; - u8 tx_errors_count_ch1; - u8 rx_errors_count_ch1; - u8 status_ch0; - u8 status_ch1; - __le16 time; -} __packed; - -struct kvaser_msg_ctrl_mode { - u8 tid; - u8 channel; - u8 ctrl_mode; - u8 padding[3]; -} __packed; - -struct kvaser_msg_flush_queue { - u8 tid; - u8 channel; - u8 flags; - u8 padding[3]; -} __packed; - -struct leaf_msg_log_message { - u8 channel; - u8 flags; - __le16 time[3]; - u8 dlc; - u8 time_offset; - __le32 id; - u8 data[8]; -} __packed; - -struct kvaser_msg { - u8 len; - u8 id; - union { - struct kvaser_msg_simple simple; - struct kvaser_msg_cardinfo cardinfo; - struct kvaser_msg_cardinfo2 cardinfo2; - struct kvaser_msg_busparams busparams; - - struct kvaser_msg_rx_can_header rx_can_header; - struct kvaser_msg_tx_acknowledge_header tx_acknowledge_header; - - union { - struct leaf_msg_softinfo softinfo; - struct leaf_msg_rx_can rx_can; - struct leaf_msg_chip_state_event chip_state_event; - struct leaf_msg_tx_acknowledge tx_acknowledge; - struct leaf_msg_error_event error_event; - struct leaf_msg_log_message log_message; - } __packed leaf; - - union { - struct usbcan_msg_softinfo softinfo; - struct usbcan_msg_rx_can rx_can; - struct usbcan_msg_chip_state_event chip_state_event; - struct usbcan_msg_tx_acknowledge tx_acknowledge; - struct usbcan_msg_error_event error_event; - } __packed usbcan; - - struct kvaser_msg_tx_can tx_can; - struct kvaser_msg_ctrl_mode ctrl_mode; - struct kvaser_msg_flush_queue flush_queue; - } u; -} __packed; - -/* Summary of a kvaser error event, for a unified Leaf/Usbcan error - * handling. Some discrepancies between the two families exist: - * - * - USBCAN firmware does not report M16C "error factors" - * - USBCAN controllers has difficulties reporting if the raised error - * event is for ch0 or ch1. They leave such arbitration to the OS - * driver by letting it compare error counters with previous values - * and decide the error event's channel. Thus for USBCAN, the channel - * field is only advisory. - */ -struct kvaser_usb_error_summary { - u8 channel, status, txerr, rxerr; - union { - struct { - u8 error_factor; - } leaf; - struct { - u8 other_ch_status; - u8 error_state; - } usbcan; - }; -}; - -/* Context for an outstanding, not yet ACKed, transmission */ -struct kvaser_usb_tx_urb_context { - struct kvaser_usb_net_priv *priv; - u32 echo_index; - int dlc; -}; - -struct kvaser_usb { - struct usb_device *udev; - struct kvaser_usb_net_priv *nets[MAX_NET_DEVICES]; - - struct usb_endpoint_descriptor *bulk_in, *bulk_out; - struct usb_anchor rx_submitted; - - /* @max_tx_urbs: Firmware-reported maximum number of outstanding, - * not yet ACKed, transmissions on this device. This value is - * also used as a sentinel for marking free tx contexts. - */ - u32 fw_version; - unsigned int nchannels; - unsigned int max_tx_urbs; - enum kvaser_usb_family family; - - bool rxinitdone; - void *rxbuf[MAX_RX_URBS]; - dma_addr_t rxbuf_dma[MAX_RX_URBS]; -}; - -struct kvaser_usb_net_priv { - struct can_priv can; - struct can_berr_counter bec; - - struct kvaser_usb *dev; - struct net_device *netdev; - int channel; - - struct completion start_comp, stop_comp; - struct usb_anchor tx_submitted; - - spinlock_t tx_contexts_lock; - int active_tx_contexts; - struct kvaser_usb_tx_urb_context tx_contexts[]; -}; - -static const struct usb_device_id kvaser_usb_table[] = { - /* Leaf family IDs */ - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS | - KVASER_HAS_SILENT_MODE }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) }, - - /* USBCANII family IDs */ - { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID), - .driver_info = KVASER_HAS_TXRX_ERRORS }, - - { } -}; -MODULE_DEVICE_TABLE(usb, kvaser_usb_table); - -static inline int kvaser_usb_send_msg(const struct kvaser_usb *dev, - struct kvaser_msg *msg) -{ - int actual_len; - - return usb_bulk_msg(dev->udev, - usb_sndbulkpipe(dev->udev, - dev->bulk_out->bEndpointAddress), - msg, msg->len, &actual_len, - USB_SEND_TIMEOUT); -} - -static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id, - struct kvaser_msg *msg) -{ - struct kvaser_msg *tmp; - void *buf; - int actual_len; - int err; - int pos; - unsigned long to = jiffies + msecs_to_jiffies(USB_RECV_TIMEOUT); - - buf = kzalloc(RX_BUFFER_SIZE, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - do { - err = usb_bulk_msg(dev->udev, - usb_rcvbulkpipe(dev->udev, - dev->bulk_in->bEndpointAddress), - buf, RX_BUFFER_SIZE, &actual_len, - USB_RECV_TIMEOUT); - if (err < 0) - goto end; - - pos = 0; - while (pos <= actual_len - MSG_HEADER_LEN) { - tmp = buf + pos; - - /* Handle messages crossing the USB endpoint max packet - * size boundary. Check kvaser_usb_read_bulk_callback() - * for further details. - */ - if (tmp->len == 0) { - pos = round_up(pos, le16_to_cpu(dev->bulk_in-> - wMaxPacketSize)); - continue; - } - - if (pos + tmp->len > actual_len) { - dev_err_ratelimited(dev->udev->dev.parent, - "Format error\n"); - break; - } - - if (tmp->id == id) { - memcpy(msg, tmp, tmp->len); - goto end; - } - - pos += tmp->len; - } - } while (time_before(jiffies, to)); - - err = -EINVAL; - -end: - kfree(buf); - - return err; -} - -static int kvaser_usb_send_simple_msg(const struct kvaser_usb *dev, - u8 msg_id, int channel) -{ - struct kvaser_msg *msg; - int rc; - - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->id = msg_id; - msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_simple); - msg->u.simple.channel = channel; - msg->u.simple.tid = 0xff; - - rc = kvaser_usb_send_msg(dev, msg); - - kfree(msg); - return rc; -} - -static int kvaser_usb_get_software_info(struct kvaser_usb *dev) -{ - struct kvaser_msg msg; - int err; - - err = kvaser_usb_send_simple_msg(dev, CMD_GET_SOFTWARE_INFO, 0); - if (err) - return err; - - err = kvaser_usb_wait_msg(dev, CMD_GET_SOFTWARE_INFO_REPLY, &msg); - if (err) - return err; - - switch (dev->family) { - case KVASER_LEAF: - dev->fw_version = le32_to_cpu(msg.u.leaf.softinfo.fw_version); - dev->max_tx_urbs = - le16_to_cpu(msg.u.leaf.softinfo.max_outstanding_tx); - break; - case KVASER_USBCAN: - dev->fw_version = le32_to_cpu(msg.u.usbcan.softinfo.fw_version); - dev->max_tx_urbs = - le16_to_cpu(msg.u.usbcan.softinfo.max_outstanding_tx); - break; - } - - return 0; -} - -static int kvaser_usb_get_card_info(struct kvaser_usb *dev) -{ - struct kvaser_msg msg; - int err; - - err = kvaser_usb_send_simple_msg(dev, CMD_GET_CARD_INFO, 0); - if (err) - return err; - - err = kvaser_usb_wait_msg(dev, CMD_GET_CARD_INFO_REPLY, &msg); - if (err) - return err; - - dev->nchannels = msg.u.cardinfo.nchannels; - if ((dev->nchannels > MAX_NET_DEVICES) || - (dev->family == KVASER_USBCAN && - dev->nchannels > MAX_USBCAN_NET_DEVICES)) - return -EINVAL; - - return 0; -} - -static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - struct net_device_stats *stats; - struct kvaser_usb_tx_urb_context *context; - struct kvaser_usb_net_priv *priv; - struct sk_buff *skb; - struct can_frame *cf; - unsigned long flags; - u8 channel, tid; - - channel = msg->u.tx_acknowledge_header.channel; - tid = msg->u.tx_acknowledge_header.tid; - - if (channel >= dev->nchannels) { - dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", channel); - return; - } - - priv = dev->nets[channel]; - - if (!netif_device_present(priv->netdev)) - return; - - stats = &priv->netdev->stats; - - context = &priv->tx_contexts[tid % dev->max_tx_urbs]; - - /* Sometimes the state change doesn't come after a bus-off event */ - if (priv->can.restart_ms && - (priv->can.state >= CAN_STATE_BUS_OFF)) { - skb = alloc_can_err_skb(priv->netdev, &cf); - if (skb) { - cf->can_id |= CAN_ERR_RESTARTED; - - stats->rx_packets++; - stats->rx_bytes += cf->can_dlc; - netif_rx(skb); - } else { - netdev_err(priv->netdev, - "No memory left for err_skb\n"); - } - - priv->can.can_stats.restarts++; - netif_carrier_on(priv->netdev); - - priv->can.state = CAN_STATE_ERROR_ACTIVE; - } - - stats->tx_packets++; - stats->tx_bytes += context->dlc; - - spin_lock_irqsave(&priv->tx_contexts_lock, flags); - - can_get_echo_skb(priv->netdev, context->echo_index); - context->echo_index = dev->max_tx_urbs; - --priv->active_tx_contexts; - netif_wake_queue(priv->netdev); - - spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); -} - -static void kvaser_usb_simple_msg_callback(struct urb *urb) -{ - struct net_device *netdev = urb->context; - - kfree(urb->transfer_buffer); - - if (urb->status) - netdev_warn(netdev, "urb status received: %d\n", - urb->status); -} - -static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv, - u8 msg_id) -{ - struct kvaser_usb *dev = priv->dev; - struct net_device *netdev = priv->netdev; - struct kvaser_msg *msg; - struct urb *urb; - void *buf; - int err; - - urb = usb_alloc_urb(0, GFP_ATOMIC); - if (!urb) - return -ENOMEM; - - buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC); - if (!buf) { - usb_free_urb(urb); - return -ENOMEM; - } - - msg = (struct kvaser_msg *)buf; - msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_simple); - msg->id = msg_id; - msg->u.simple.channel = priv->channel; - - usb_fill_bulk_urb(urb, dev->udev, - usb_sndbulkpipe(dev->udev, - dev->bulk_out->bEndpointAddress), - buf, msg->len, - kvaser_usb_simple_msg_callback, netdev); - usb_anchor_urb(urb, &priv->tx_submitted); - - err = usb_submit_urb(urb, GFP_ATOMIC); - if (err) { - netdev_err(netdev, "Error transmitting URB\n"); - usb_unanchor_urb(urb); - kfree(buf); - usb_free_urb(urb); - return err; - } - - usb_free_urb(urb); - - return 0; -} - -static void kvaser_usb_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, - const struct kvaser_usb_error_summary *es, - struct can_frame *cf) -{ - struct kvaser_usb *dev = priv->dev; - struct net_device_stats *stats = &priv->netdev->stats; - enum can_state cur_state, new_state, tx_state, rx_state; - - netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status); - - new_state = cur_state = priv->can.state; - - if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) - new_state = CAN_STATE_BUS_OFF; - else if (es->status & M16C_STATE_BUS_PASSIVE) - new_state = CAN_STATE_ERROR_PASSIVE; - else if (es->status & M16C_STATE_BUS_ERROR) { - /* Guard against spurious error events after a busoff */ - if (cur_state < CAN_STATE_BUS_OFF) { - if ((es->txerr >= 128) || (es->rxerr >= 128)) - new_state = CAN_STATE_ERROR_PASSIVE; - else if ((es->txerr >= 96) || (es->rxerr >= 96)) - new_state = CAN_STATE_ERROR_WARNING; - else if (cur_state > CAN_STATE_ERROR_ACTIVE) - new_state = CAN_STATE_ERROR_ACTIVE; - } - } - - if (!es->status) - new_state = CAN_STATE_ERROR_ACTIVE; - - if (new_state != cur_state) { - tx_state = (es->txerr >= es->rxerr) ? new_state : 0; - rx_state = (es->txerr <= es->rxerr) ? new_state : 0; - - can_change_state(priv->netdev, cf, tx_state, rx_state); - } - - if (priv->can.restart_ms && - (cur_state >= CAN_STATE_BUS_OFF) && - (new_state < CAN_STATE_BUS_OFF)) { - priv->can.can_stats.restarts++; - } - - switch (dev->family) { - case KVASER_LEAF: - if (es->leaf.error_factor) { - priv->can.can_stats.bus_error++; - stats->rx_errors++; - } - break; - case KVASER_USBCAN: - if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR) - stats->tx_errors++; - if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR) - stats->rx_errors++; - if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) { - priv->can.can_stats.bus_error++; - } - break; - } - - priv->bec.txerr = es->txerr; - priv->bec.rxerr = es->rxerr; -} - -static void kvaser_usb_rx_error(const struct kvaser_usb *dev, - const struct kvaser_usb_error_summary *es) -{ - struct can_frame *cf, tmp_cf = { .can_id = CAN_ERR_FLAG, .can_dlc = CAN_ERR_DLC }; - struct sk_buff *skb; - struct net_device_stats *stats; - struct kvaser_usb_net_priv *priv; - enum can_state old_state, new_state; - - if (es->channel >= dev->nchannels) { - dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", es->channel); - return; - } - - priv = dev->nets[es->channel]; - stats = &priv->netdev->stats; - - /* Update all of the can interface's state and error counters before - * trying any memory allocation that can actually fail with -ENOMEM. - * - * We send a temporary stack-allocated error can frame to - * can_change_state() for the very same reason. - * - * TODO: Split can_change_state() responsibility between updating the - * can interface's state and counters, and the setting up of can error - * frame ID and data to userspace. Remove stack allocation afterwards. - */ - old_state = priv->can.state; - kvaser_usb_rx_error_update_can_state(priv, es, &tmp_cf); - new_state = priv->can.state; - - skb = alloc_can_err_skb(priv->netdev, &cf); - if (!skb) { - stats->rx_dropped++; - return; - } - memcpy(cf, &tmp_cf, sizeof(*cf)); - - if (new_state != old_state) { - if (es->status & - (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { - if (!priv->can.restart_ms) - kvaser_usb_simple_msg_async(priv, CMD_STOP_CHIP); - netif_carrier_off(priv->netdev); - } - - if (priv->can.restart_ms && - (old_state >= CAN_STATE_BUS_OFF) && - (new_state < CAN_STATE_BUS_OFF)) { - cf->can_id |= CAN_ERR_RESTARTED; - netif_carrier_on(priv->netdev); - } - } - - switch (dev->family) { - case KVASER_LEAF: - if (es->leaf.error_factor) { - cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT; - - if (es->leaf.error_factor & M16C_EF_ACKE) - cf->data[3] = CAN_ERR_PROT_LOC_ACK; - if (es->leaf.error_factor & M16C_EF_CRCE) - cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ; - if (es->leaf.error_factor & M16C_EF_FORME) - cf->data[2] |= CAN_ERR_PROT_FORM; - if (es->leaf.error_factor & M16C_EF_STFE) - cf->data[2] |= CAN_ERR_PROT_STUFF; - if (es->leaf.error_factor & M16C_EF_BITE0) - cf->data[2] |= CAN_ERR_PROT_BIT0; - if (es->leaf.error_factor & M16C_EF_BITE1) - cf->data[2] |= CAN_ERR_PROT_BIT1; - if (es->leaf.error_factor & M16C_EF_TRE) - cf->data[2] |= CAN_ERR_PROT_TX; - } - break; - case KVASER_USBCAN: - if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) { - cf->can_id |= CAN_ERR_BUSERROR; - } - break; - } - - cf->data[6] = es->txerr; - cf->data[7] = es->rxerr; - - stats->rx_packets++; - stats->rx_bytes += cf->can_dlc; - netif_rx(skb); -} - -/* For USBCAN, report error to userspace iff the channels's errors counter - * has changed, or we're the only channel seeing a bus error state. - */ -static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev, - struct kvaser_usb_error_summary *es) -{ - struct kvaser_usb_net_priv *priv; - int channel; - bool report_error; - - channel = es->channel; - if (channel >= dev->nchannels) { - dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", channel); - return; - } - - priv = dev->nets[channel]; - report_error = false; - - if (es->txerr != priv->bec.txerr) { - es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR; - report_error = true; - } - if (es->rxerr != priv->bec.rxerr) { - es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR; - report_error = true; - } - if ((es->status & M16C_STATE_BUS_ERROR) && - !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) { - es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR; - report_error = true; - } - - if (report_error) - kvaser_usb_rx_error(dev, es); -} - -static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - struct kvaser_usb_error_summary es = { }; - - switch (msg->id) { - /* Sometimes errors are sent as unsolicited chip state events */ - case CMD_CHIP_STATE_EVENT: - es.channel = msg->u.usbcan.chip_state_event.channel; - es.status = msg->u.usbcan.chip_state_event.status; - es.txerr = msg->u.usbcan.chip_state_event.tx_errors_count; - es.rxerr = msg->u.usbcan.chip_state_event.rx_errors_count; - kvaser_usbcan_conditionally_rx_error(dev, &es); - break; - - case CMD_CAN_ERROR_EVENT: - es.channel = 0; - es.status = msg->u.usbcan.error_event.status_ch0; - es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch0; - es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch0; - es.usbcan.other_ch_status = - msg->u.usbcan.error_event.status_ch1; - kvaser_usbcan_conditionally_rx_error(dev, &es); - - /* The USBCAN firmware supports up to 2 channels. - * Now that ch0 was checked, check if ch1 has any errors. - */ - if (dev->nchannels == MAX_USBCAN_NET_DEVICES) { - es.channel = 1; - es.status = msg->u.usbcan.error_event.status_ch1; - es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch1; - es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch1; - es.usbcan.other_ch_status = - msg->u.usbcan.error_event.status_ch0; - kvaser_usbcan_conditionally_rx_error(dev, &es); - } - break; - - default: - dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n", - msg->id); - } -} - -static void kvaser_leaf_rx_error(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - struct kvaser_usb_error_summary es = { }; - - switch (msg->id) { - case CMD_CAN_ERROR_EVENT: - es.channel = msg->u.leaf.error_event.channel; - es.status = msg->u.leaf.error_event.status; - es.txerr = msg->u.leaf.error_event.tx_errors_count; - es.rxerr = msg->u.leaf.error_event.rx_errors_count; - es.leaf.error_factor = msg->u.leaf.error_event.error_factor; - break; - case CMD_LEAF_LOG_MESSAGE: - es.channel = msg->u.leaf.log_message.channel; - es.status = msg->u.leaf.log_message.data[0]; - es.txerr = msg->u.leaf.log_message.data[2]; - es.rxerr = msg->u.leaf.log_message.data[3]; - es.leaf.error_factor = msg->u.leaf.log_message.data[1]; - break; - case CMD_CHIP_STATE_EVENT: - es.channel = msg->u.leaf.chip_state_event.channel; - es.status = msg->u.leaf.chip_state_event.status; - es.txerr = msg->u.leaf.chip_state_event.tx_errors_count; - es.rxerr = msg->u.leaf.chip_state_event.rx_errors_count; - es.leaf.error_factor = 0; - break; - default: - dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n", - msg->id); - return; - } - - kvaser_usb_rx_error(dev, &es); -} - -static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, - const struct kvaser_msg *msg) -{ - struct can_frame *cf; - struct sk_buff *skb; - struct net_device_stats *stats = &priv->netdev->stats; - - if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | - MSG_FLAG_NERR)) { - netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n", - msg->u.rx_can_header.flag); - - stats->rx_errors++; - return; - } - - if (msg->u.rx_can_header.flag & MSG_FLAG_OVERRUN) { - stats->rx_over_errors++; - stats->rx_errors++; - - skb = alloc_can_err_skb(priv->netdev, &cf); - if (!skb) { - stats->rx_dropped++; - return; - } - - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; - - stats->rx_packets++; - stats->rx_bytes += cf->can_dlc; - netif_rx(skb); - } -} - -static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - struct kvaser_usb_net_priv *priv; - struct can_frame *cf; - struct sk_buff *skb; - struct net_device_stats *stats; - u8 channel = msg->u.rx_can_header.channel; - const u8 *rx_msg = NULL; /* GCC */ - - if (channel >= dev->nchannels) { - dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", channel); - return; - } - - priv = dev->nets[channel]; - stats = &priv->netdev->stats; - - if ((msg->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) && - (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE)) { - kvaser_leaf_rx_error(dev, msg); - return; - } else if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | - MSG_FLAG_NERR | - MSG_FLAG_OVERRUN)) { - kvaser_usb_rx_can_err(priv, msg); - return; - } else if (msg->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) { - netdev_warn(priv->netdev, - "Unhandled frame (flags: 0x%02x)", - msg->u.rx_can_header.flag); - return; - } - - switch (dev->family) { - case KVASER_LEAF: - rx_msg = msg->u.leaf.rx_can.msg; - break; - case KVASER_USBCAN: - rx_msg = msg->u.usbcan.rx_can.msg; - break; - } - - skb = alloc_can_skb(priv->netdev, &cf); - if (!skb) { - stats->rx_dropped++; - return; - } - - if (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE) { - cf->can_id = le32_to_cpu(msg->u.leaf.log_message.id); - if (cf->can_id & KVASER_EXTENDED_FRAME) - cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG; - else - cf->can_id &= CAN_SFF_MASK; - - cf->can_dlc = get_can_dlc(msg->u.leaf.log_message.dlc); - - if (msg->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME) - cf->can_id |= CAN_RTR_FLAG; - else - memcpy(cf->data, &msg->u.leaf.log_message.data, - cf->can_dlc); - } else { - cf->can_id = ((rx_msg[0] & 0x1f) << 6) | (rx_msg[1] & 0x3f); - - if (msg->id == CMD_RX_EXT_MESSAGE) { - cf->can_id <<= 18; - cf->can_id |= ((rx_msg[2] & 0x0f) << 14) | - ((rx_msg[3] & 0xff) << 6) | - (rx_msg[4] & 0x3f); - cf->can_id |= CAN_EFF_FLAG; - } - - cf->can_dlc = get_can_dlc(rx_msg[5]); - - if (msg->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME) - cf->can_id |= CAN_RTR_FLAG; - else - memcpy(cf->data, &rx_msg[6], - cf->can_dlc); - } - - stats->rx_packets++; - stats->rx_bytes += cf->can_dlc; - netif_rx(skb); -} - -static void kvaser_usb_start_chip_reply(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - struct kvaser_usb_net_priv *priv; - u8 channel = msg->u.simple.channel; - - if (channel >= dev->nchannels) { - dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", channel); - return; - } - - priv = dev->nets[channel]; - - if (completion_done(&priv->start_comp) && - netif_queue_stopped(priv->netdev)) { - netif_wake_queue(priv->netdev); - } else { - netif_start_queue(priv->netdev); - complete(&priv->start_comp); - } -} - -static void kvaser_usb_stop_chip_reply(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - struct kvaser_usb_net_priv *priv; - u8 channel = msg->u.simple.channel; - - if (channel >= dev->nchannels) { - dev_err(dev->udev->dev.parent, - "Invalid channel number (%d)\n", channel); - return; - } - - priv = dev->nets[channel]; - - complete(&priv->stop_comp); -} - -static void kvaser_usb_handle_message(const struct kvaser_usb *dev, - const struct kvaser_msg *msg) -{ - switch (msg->id) { - case CMD_START_CHIP_REPLY: - kvaser_usb_start_chip_reply(dev, msg); - break; - - case CMD_STOP_CHIP_REPLY: - kvaser_usb_stop_chip_reply(dev, msg); - break; - - case CMD_RX_STD_MESSAGE: - case CMD_RX_EXT_MESSAGE: - kvaser_usb_rx_can_msg(dev, msg); - break; - - case CMD_LEAF_LOG_MESSAGE: - if (dev->family != KVASER_LEAF) - goto warn; - kvaser_usb_rx_can_msg(dev, msg); - break; - - case CMD_CHIP_STATE_EVENT: - case CMD_CAN_ERROR_EVENT: - if (dev->family == KVASER_LEAF) - kvaser_leaf_rx_error(dev, msg); - else - kvaser_usbcan_rx_error(dev, msg); - break; - - case CMD_TX_ACKNOWLEDGE: - kvaser_usb_tx_acknowledge(dev, msg); - break; - - /* Ignored messages */ - case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: - if (dev->family != KVASER_USBCAN) - goto warn; - break; - - case CMD_FLUSH_QUEUE_REPLY: - if (dev->family != KVASER_LEAF) - goto warn; - break; - - default: -warn: dev_warn(dev->udev->dev.parent, - "Unhandled message (%d)\n", msg->id); - break; - } -} - -static void kvaser_usb_read_bulk_callback(struct urb *urb) -{ - struct kvaser_usb *dev = urb->context; - struct kvaser_msg *msg; - int pos = 0; - int err, i; - - switch (urb->status) { - case 0: - break; - case -ENOENT: - case -EPIPE: - case -EPROTO: - case -ESHUTDOWN: - return; - default: - dev_info(dev->udev->dev.parent, "Rx URB aborted (%d)\n", - urb->status); - goto resubmit_urb; - } - - while (pos <= (int)(urb->actual_length - MSG_HEADER_LEN)) { - msg = urb->transfer_buffer + pos; - - /* The Kvaser firmware can only read and write messages that - * does not cross the USB's endpoint wMaxPacketSize boundary. - * If a follow-up command crosses such boundary, firmware puts - * a placeholder zero-length command in its place then aligns - * the real command to the next max packet size. - * - * Handle such cases or we're going to miss a significant - * number of events in case of a heavy rx load on the bus. - */ - if (msg->len == 0) { - pos = round_up(pos, le16_to_cpu(dev->bulk_in-> - wMaxPacketSize)); - continue; - } - - if (pos + msg->len > urb->actual_length) { - dev_err_ratelimited(dev->udev->dev.parent, - "Format error\n"); - break; - } - - kvaser_usb_handle_message(dev, msg); - pos += msg->len; - } - -resubmit_urb: - usb_fill_bulk_urb(urb, dev->udev, - usb_rcvbulkpipe(dev->udev, - dev->bulk_in->bEndpointAddress), - urb->transfer_buffer, RX_BUFFER_SIZE, - kvaser_usb_read_bulk_callback, dev); - - err = usb_submit_urb(urb, GFP_ATOMIC); - if (err == -ENODEV) { - for (i = 0; i < dev->nchannels; i++) { - if (!dev->nets[i]) - continue; - - netif_device_detach(dev->nets[i]->netdev); - } - } else if (err) { - dev_err(dev->udev->dev.parent, - "Failed resubmitting read bulk urb: %d\n", err); - } - - return; -} - -static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev) -{ - int i, err = 0; - - if (dev->rxinitdone) - return 0; - - for (i = 0; i < MAX_RX_URBS; i++) { - struct urb *urb = NULL; - u8 *buf = NULL; - dma_addr_t buf_dma; - - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) { - err = -ENOMEM; - break; - } - - buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, - GFP_KERNEL, &buf_dma); - if (!buf) { - dev_warn(dev->udev->dev.parent, - "No memory left for USB buffer\n"); - usb_free_urb(urb); - err = -ENOMEM; - break; - } - - usb_fill_bulk_urb(urb, dev->udev, - usb_rcvbulkpipe(dev->udev, - dev->bulk_in->bEndpointAddress), - buf, RX_BUFFER_SIZE, - kvaser_usb_read_bulk_callback, - dev); - urb->transfer_dma = buf_dma; - urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - usb_anchor_urb(urb, &dev->rx_submitted); - - err = usb_submit_urb(urb, GFP_KERNEL); - if (err) { - usb_unanchor_urb(urb); - usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf, - buf_dma); - usb_free_urb(urb); - break; - } - - dev->rxbuf[i] = buf; - dev->rxbuf_dma[i] = buf_dma; - - usb_free_urb(urb); - } - - if (i == 0) { - dev_warn(dev->udev->dev.parent, - "Cannot setup read URBs, error %d\n", err); - return err; - } else if (i < MAX_RX_URBS) { - dev_warn(dev->udev->dev.parent, - "RX performances may be slow\n"); - } - - dev->rxinitdone = true; - - return 0; -} - -static int kvaser_usb_set_opt_mode(const struct kvaser_usb_net_priv *priv) -{ - struct kvaser_msg *msg; - int rc; - - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->id = CMD_SET_CTRL_MODE; - msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_ctrl_mode); - msg->u.ctrl_mode.tid = 0xff; - msg->u.ctrl_mode.channel = priv->channel; - - if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) - msg->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT; - else - msg->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL; - - rc = kvaser_usb_send_msg(priv->dev, msg); - - kfree(msg); - return rc; -} - -static int kvaser_usb_start_chip(struct kvaser_usb_net_priv *priv) -{ - int err; - - init_completion(&priv->start_comp); - - err = kvaser_usb_send_simple_msg(priv->dev, CMD_START_CHIP, - priv->channel); - if (err) - return err; - - if (!wait_for_completion_timeout(&priv->start_comp, - msecs_to_jiffies(START_TIMEOUT))) - return -ETIMEDOUT; - - return 0; -} - -static int kvaser_usb_open(struct net_device *netdev) -{ - struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct kvaser_usb *dev = priv->dev; - int err; - - err = open_candev(netdev); - if (err) - return err; - - err = kvaser_usb_setup_rx_urbs(dev); - if (err) - goto error; - - err = kvaser_usb_set_opt_mode(priv); - if (err) - goto error; - - err = kvaser_usb_start_chip(priv); - if (err) { - netdev_warn(netdev, "Cannot start device, error %d\n", err); - goto error; - } - - priv->can.state = CAN_STATE_ERROR_ACTIVE; - - return 0; - -error: - close_candev(netdev); - return err; -} - -static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv) -{ - int i, max_tx_urbs; - - max_tx_urbs = priv->dev->max_tx_urbs; - - priv->active_tx_contexts = 0; - for (i = 0; i < max_tx_urbs; i++) - priv->tx_contexts[i].echo_index = max_tx_urbs; -} - -/* This method might sleep. Do not call it in the atomic context - * of URB completions. - */ -static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) -{ - usb_kill_anchored_urbs(&priv->tx_submitted); - kvaser_usb_reset_tx_urb_contexts(priv); -} - -static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev) -{ - int i; - - usb_kill_anchored_urbs(&dev->rx_submitted); - - for (i = 0; i < MAX_RX_URBS; i++) - usb_free_coherent(dev->udev, RX_BUFFER_SIZE, - dev->rxbuf[i], - dev->rxbuf_dma[i]); - - for (i = 0; i < dev->nchannels; i++) { - struct kvaser_usb_net_priv *priv = dev->nets[i]; - - if (priv) - kvaser_usb_unlink_tx_urbs(priv); - } -} - -static int kvaser_usb_stop_chip(struct kvaser_usb_net_priv *priv) -{ - int err; - - init_completion(&priv->stop_comp); - - err = kvaser_usb_send_simple_msg(priv->dev, CMD_STOP_CHIP, - priv->channel); - if (err) - return err; - - if (!wait_for_completion_timeout(&priv->stop_comp, - msecs_to_jiffies(STOP_TIMEOUT))) - return -ETIMEDOUT; - - return 0; -} - -static int kvaser_usb_flush_queue(struct kvaser_usb_net_priv *priv) -{ - struct kvaser_msg *msg; - int rc; - - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->id = CMD_FLUSH_QUEUE; - msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_flush_queue); - msg->u.flush_queue.channel = priv->channel; - msg->u.flush_queue.flags = 0x00; - - rc = kvaser_usb_send_msg(priv->dev, msg); - - kfree(msg); - return rc; -} - -static int kvaser_usb_close(struct net_device *netdev) -{ - struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct kvaser_usb *dev = priv->dev; - int err; - - netif_stop_queue(netdev); - - err = kvaser_usb_flush_queue(priv); - if (err) - netdev_warn(netdev, "Cannot flush queue, error %d\n", err); - - err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel); - if (err) - netdev_warn(netdev, "Cannot reset card, error %d\n", err); - - err = kvaser_usb_stop_chip(priv); - if (err) - netdev_warn(netdev, "Cannot stop device, error %d\n", err); - - /* reset tx contexts */ - kvaser_usb_unlink_tx_urbs(priv); - - priv->can.state = CAN_STATE_STOPPED; - close_candev(priv->netdev); - - return 0; -} - -static void kvaser_usb_write_bulk_callback(struct urb *urb) -{ - struct kvaser_usb_tx_urb_context *context = urb->context; - struct kvaser_usb_net_priv *priv; - struct net_device *netdev; - - if (WARN_ON(!context)) - return; - - priv = context->priv; - netdev = priv->netdev; - - kfree(urb->transfer_buffer); - - if (!netif_device_present(netdev)) - return; - - if (urb->status) - netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status); -} - -static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, - struct net_device *netdev) -{ - struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct kvaser_usb *dev = priv->dev; - struct net_device_stats *stats = &netdev->stats; - struct can_frame *cf = (struct can_frame *)skb->data; - struct kvaser_usb_tx_urb_context *context = NULL; - struct urb *urb; - void *buf; - struct kvaser_msg *msg; - int i, err, ret = NETDEV_TX_OK; - u8 *msg_tx_can_flags = NULL; /* GCC */ - unsigned long flags; - - if (can_dropped_invalid_skb(netdev, skb)) - return NETDEV_TX_OK; - - urb = usb_alloc_urb(0, GFP_ATOMIC); - if (!urb) { - stats->tx_dropped++; - dev_kfree_skb(skb); - return NETDEV_TX_OK; - } - - buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC); - if (!buf) { - stats->tx_dropped++; - dev_kfree_skb(skb); - goto freeurb; - } - - msg = buf; - msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_tx_can); - msg->u.tx_can.channel = priv->channel; - - switch (dev->family) { - case KVASER_LEAF: - msg_tx_can_flags = &msg->u.tx_can.leaf.flags; - break; - case KVASER_USBCAN: - msg_tx_can_flags = &msg->u.tx_can.usbcan.flags; - break; - } - - *msg_tx_can_flags = 0; - - if (cf->can_id & CAN_EFF_FLAG) { - msg->id = CMD_TX_EXT_MESSAGE; - msg->u.tx_can.msg[0] = (cf->can_id >> 24) & 0x1f; - msg->u.tx_can.msg[1] = (cf->can_id >> 18) & 0x3f; - msg->u.tx_can.msg[2] = (cf->can_id >> 14) & 0x0f; - msg->u.tx_can.msg[3] = (cf->can_id >> 6) & 0xff; - msg->u.tx_can.msg[4] = cf->can_id & 0x3f; - } else { - msg->id = CMD_TX_STD_MESSAGE; - msg->u.tx_can.msg[0] = (cf->can_id >> 6) & 0x1f; - msg->u.tx_can.msg[1] = cf->can_id & 0x3f; - } - - msg->u.tx_can.msg[5] = cf->can_dlc; - memcpy(&msg->u.tx_can.msg[6], cf->data, cf->can_dlc); - - if (cf->can_id & CAN_RTR_FLAG) - *msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME; - - spin_lock_irqsave(&priv->tx_contexts_lock, flags); - for (i = 0; i < dev->max_tx_urbs; i++) { - if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) { - context = &priv->tx_contexts[i]; - - context->echo_index = i; - can_put_echo_skb(skb, netdev, context->echo_index); - ++priv->active_tx_contexts; - if (priv->active_tx_contexts >= dev->max_tx_urbs) - netif_stop_queue(netdev); - - break; - } - } - spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); - - /* This should never happen; it implies a flow control bug */ - if (!context) { - netdev_warn(netdev, "cannot find free context\n"); - - kfree(buf); - ret = NETDEV_TX_BUSY; - goto freeurb; - } - - context->priv = priv; - context->dlc = cf->can_dlc; - - msg->u.tx_can.tid = context->echo_index; - - usb_fill_bulk_urb(urb, dev->udev, - usb_sndbulkpipe(dev->udev, - dev->bulk_out->bEndpointAddress), - buf, msg->len, - kvaser_usb_write_bulk_callback, context); - usb_anchor_urb(urb, &priv->tx_submitted); - - err = usb_submit_urb(urb, GFP_ATOMIC); - if (unlikely(err)) { - spin_lock_irqsave(&priv->tx_contexts_lock, flags); - - can_free_echo_skb(netdev, context->echo_index); - context->echo_index = dev->max_tx_urbs; - --priv->active_tx_contexts; - netif_wake_queue(netdev); - - spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); - - usb_unanchor_urb(urb); - kfree(buf); - - stats->tx_dropped++; - - if (err == -ENODEV) - netif_device_detach(netdev); - else - netdev_warn(netdev, "Failed tx_urb %d\n", err); - - goto freeurb; - } - - ret = NETDEV_TX_OK; - -freeurb: - usb_free_urb(urb); - return ret; -} - -static const struct net_device_ops kvaser_usb_netdev_ops = { - .ndo_open = kvaser_usb_open, - .ndo_stop = kvaser_usb_close, - .ndo_start_xmit = kvaser_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, -}; - -static const struct can_bittiming_const kvaser_usb_bittiming_const = { - .name = "kvaser_usb", - .tseg1_min = KVASER_USB_TSEG1_MIN, - .tseg1_max = KVASER_USB_TSEG1_MAX, - .tseg2_min = KVASER_USB_TSEG2_MIN, - .tseg2_max = KVASER_USB_TSEG2_MAX, - .sjw_max = KVASER_USB_SJW_MAX, - .brp_min = KVASER_USB_BRP_MIN, - .brp_max = KVASER_USB_BRP_MAX, - .brp_inc = KVASER_USB_BRP_INC, -}; - -static int kvaser_usb_set_bittiming(struct net_device *netdev) -{ - struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct can_bittiming *bt = &priv->can.bittiming; - struct kvaser_usb *dev = priv->dev; - struct kvaser_msg *msg; - int rc; - - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->id = CMD_SET_BUS_PARAMS; - msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_busparams); - msg->u.busparams.channel = priv->channel; - msg->u.busparams.tid = 0xff; - msg->u.busparams.bitrate = cpu_to_le32(bt->bitrate); - msg->u.busparams.sjw = bt->sjw; - msg->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1; - msg->u.busparams.tseg2 = bt->phase_seg2; - - if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) - msg->u.busparams.no_samp = 3; - else - msg->u.busparams.no_samp = 1; - - rc = kvaser_usb_send_msg(dev, msg); - - kfree(msg); - return rc; -} - -static int kvaser_usb_set_mode(struct net_device *netdev, - enum can_mode mode) -{ - struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - int err; - - switch (mode) { - case CAN_MODE_START: - err = kvaser_usb_simple_msg_async(priv, CMD_START_CHIP); - if (err) - return err; - break; - default: - return -EOPNOTSUPP; - } - - return 0; -} - -static int kvaser_usb_get_berr_counter(const struct net_device *netdev, - struct can_berr_counter *bec) -{ - struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - - *bec = priv->bec; - - return 0; -} - -static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev) -{ - int i; - - for (i = 0; i < dev->nchannels; i++) { - if (!dev->nets[i]) - continue; - - unregister_candev(dev->nets[i]->netdev); - } - - kvaser_usb_unlink_all_urbs(dev); - - for (i = 0; i < dev->nchannels; i++) { - if (!dev->nets[i]) - continue; - - free_candev(dev->nets[i]->netdev); - } -} - -static int kvaser_usb_init_one(struct usb_interface *intf, - const struct usb_device_id *id, int channel) -{ - struct kvaser_usb *dev = usb_get_intfdata(intf); - struct net_device *netdev; - struct kvaser_usb_net_priv *priv; - int err; - - err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel); - if (err) - return err; - - netdev = alloc_candev(sizeof(*priv) + - dev->max_tx_urbs * sizeof(*priv->tx_contexts), - dev->max_tx_urbs); - if (!netdev) { - dev_err(&intf->dev, "Cannot alloc candev\n"); - return -ENOMEM; - } - - priv = netdev_priv(netdev); - - init_usb_anchor(&priv->tx_submitted); - init_completion(&priv->start_comp); - init_completion(&priv->stop_comp); - - priv->dev = dev; - priv->netdev = netdev; - priv->channel = channel; - - spin_lock_init(&priv->tx_contexts_lock); - kvaser_usb_reset_tx_urb_contexts(priv); - - priv->can.state = CAN_STATE_STOPPED; - priv->can.clock.freq = CAN_USB_CLOCK; - priv->can.bittiming_const = &kvaser_usb_bittiming_const; - priv->can.do_set_bittiming = kvaser_usb_set_bittiming; - priv->can.do_set_mode = kvaser_usb_set_mode; - if (id->driver_info & KVASER_HAS_TXRX_ERRORS) - priv->can.do_get_berr_counter = kvaser_usb_get_berr_counter; - priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES; - if (id->driver_info & KVASER_HAS_SILENT_MODE) - priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY; - - netdev->flags |= IFF_ECHO; - - netdev->netdev_ops = &kvaser_usb_netdev_ops; - - SET_NETDEV_DEV(netdev, &intf->dev); - netdev->dev_id = channel; - - dev->nets[channel] = priv; - - err = register_candev(netdev); - if (err) { - dev_err(&intf->dev, "Failed to register can device\n"); - free_candev(netdev); - dev->nets[channel] = NULL; - return err; - } - - netdev_dbg(netdev, "device registered\n"); - - return 0; -} - -static int kvaser_usb_get_endpoints(const struct usb_interface *intf, - struct usb_endpoint_descriptor **in, - struct usb_endpoint_descriptor **out) -{ - const struct usb_host_interface *iface_desc; - struct usb_endpoint_descriptor *endpoint; - int i; - - iface_desc = &intf->altsetting[0]; - - for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { - endpoint = &iface_desc->endpoint[i].desc; - - if (!*in && usb_endpoint_is_bulk_in(endpoint)) - *in = endpoint; - - if (!*out && usb_endpoint_is_bulk_out(endpoint)) - *out = endpoint; - - /* use first bulk endpoint for in and out */ - if (*in && *out) - return 0; - } - - return -ENODEV; -} - -static int kvaser_usb_probe(struct usb_interface *intf, - const struct usb_device_id *id) -{ - struct kvaser_usb *dev; - int err = -ENOMEM; - int i, retry = 3; - - dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL); - if (!dev) - return -ENOMEM; - - if (kvaser_is_leaf(id)) { - dev->family = KVASER_LEAF; - } else if (kvaser_is_usbcan(id)) { - dev->family = KVASER_USBCAN; - } else { - dev_err(&intf->dev, - "Product ID (%d) does not belong to any known Kvaser USB family", - id->idProduct); - return -ENODEV; - } - - err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out); - if (err) { - dev_err(&intf->dev, "Cannot get usb endpoint(s)"); - return err; - } - - dev->udev = interface_to_usbdev(intf); - - init_usb_anchor(&dev->rx_submitted); - - usb_set_intfdata(intf, dev); - - /* On some x86 laptops, plugging a Kvaser device again after - * an unplug makes the firmware always ignore the very first - * command. For such a case, provide some room for retries - * instead of completely exiting the driver. - */ - do { - err = kvaser_usb_get_software_info(dev); - } while (--retry && err == -ETIMEDOUT); - - if (err) { - dev_err(&intf->dev, - "Cannot get software infos, error %d\n", err); - return err; - } - - dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n", - ((dev->fw_version >> 24) & 0xff), - ((dev->fw_version >> 16) & 0xff), - (dev->fw_version & 0xffff)); - - dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs); - - err = kvaser_usb_get_card_info(dev); - if (err) { - dev_err(&intf->dev, - "Cannot get card infos, error %d\n", err); - return err; - } - - for (i = 0; i < dev->nchannels; i++) { - err = kvaser_usb_init_one(intf, id, i); - if (err) { - kvaser_usb_remove_interfaces(dev); - return err; - } - } - - return 0; -} - -static void kvaser_usb_disconnect(struct usb_interface *intf) -{ - struct kvaser_usb *dev = usb_get_intfdata(intf); - - usb_set_intfdata(intf, NULL); - - if (!dev) - return; - - kvaser_usb_remove_interfaces(dev); -} - -static struct usb_driver kvaser_usb_driver = { - .name = "kvaser_usb", - .probe = kvaser_usb_probe, - .disconnect = kvaser_usb_disconnect, - .id_table = kvaser_usb_table, -}; - -module_usb_driver(kvaser_usb_driver); - -MODULE_AUTHOR("Olivier Sobrie <olivier@sobrie.be>"); -MODULE_DESCRIPTION("CAN driver for Kvaser CAN/USB devices"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/usb/kvaser_usb/Makefile b/drivers/net/can/usb/kvaser_usb/Makefile new file mode 100644 index 000000000000..9f41ddab6a5a --- /dev/null +++ b/drivers/net/can/usb/kvaser_usb/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o +kvaser_usb-y = kvaser_usb_core.o kvaser_usb_leaf.o kvaser_usb_hydra.o diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h new file mode 100644 index 000000000000..390b6bde883c --- /dev/null +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -0,0 +1,188 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Parts of this driver are based on the following: + * - Kvaser linux leaf driver (version 4.78) + * - CAN driver for esd CAN-USB/2 + * - Kvaser linux usbcanII driver (version 5.3) + * - Kvaser linux mhydra driver (version 5.24) + * + * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved. + * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh + * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be> + * Copyright (C) 2015 Valeo S.A. + */ + +#ifndef KVASER_USB_H +#define KVASER_USB_H + +/* Kvaser USB CAN dongles are divided into three major platforms: + * - Hydra: Running firmware labeled as 'mhydra' + * - Leaf: Based on Renesas M32C or Freescale i.MX28, running firmware labeled + * as 'filo' + * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios' + */ + +#include <linux/completion.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/usb.h> + +#include <linux/can.h> +#include <linux/can/dev.h> + +#define KVASER_USB_MAX_RX_URBS 4 +#define KVASER_USB_MAX_TX_URBS 128 +#define KVASER_USB_TIMEOUT 1000 /* msecs */ +#define KVASER_USB_RX_BUFFER_SIZE 3072 +#define KVASER_USB_MAX_NET_DEVICES 5 + +/* USB devices features */ +#define KVASER_USB_HAS_SILENT_MODE BIT(0) +#define KVASER_USB_HAS_TXRX_ERRORS BIT(1) + +/* Device capabilities */ +#define KVASER_USB_CAP_BERR_CAP 0x01 +#define KVASER_USB_CAP_EXT_CAP 0x02 +#define KVASER_USB_HYDRA_CAP_EXT_CMD 0x04 + +struct kvaser_usb_dev_cfg; + +enum kvaser_usb_leaf_family { + KVASER_LEAF, + KVASER_USBCAN, +}; + +#define KVASER_USB_HYDRA_MAX_CMD_LEN 128 +struct kvaser_usb_dev_card_data_hydra { + u8 channel_to_he[KVASER_USB_MAX_NET_DEVICES]; + u8 sysdbg_he; + spinlock_t transid_lock; /* lock for transid */ + u16 transid; + /* lock for usb_rx_leftover and usb_rx_leftover_len */ + spinlock_t usb_rx_leftover_lock; + u8 usb_rx_leftover[KVASER_USB_HYDRA_MAX_CMD_LEN]; + u8 usb_rx_leftover_len; +}; +struct kvaser_usb_dev_card_data { + u32 ctrlmode_supported; + u32 capabilities; + union { + struct { + enum kvaser_usb_leaf_family family; + } leaf; + struct kvaser_usb_dev_card_data_hydra hydra; + }; +}; + +/* Context for an outstanding, not yet ACKed, transmission */ +struct kvaser_usb_tx_urb_context { + struct kvaser_usb_net_priv *priv; + u32 echo_index; + int dlc; +}; + +struct kvaser_usb { + struct usb_device *udev; + struct usb_interface *intf; + struct kvaser_usb_net_priv *nets[KVASER_USB_MAX_NET_DEVICES]; + const struct kvaser_usb_dev_ops *ops; + const struct kvaser_usb_dev_cfg *cfg; + + struct usb_endpoint_descriptor *bulk_in, *bulk_out; + struct usb_anchor rx_submitted; + + /* @max_tx_urbs: Firmware-reported maximum number of outstanding, + * not yet ACKed, transmissions on this device. This value is + * also used as a sentinel for marking free tx contexts. + */ + u32 fw_version; + unsigned int nchannels; + unsigned int max_tx_urbs; + struct kvaser_usb_dev_card_data card_data; + + bool rxinitdone; + void *rxbuf[KVASER_USB_MAX_RX_URBS]; + dma_addr_t rxbuf_dma[KVASER_USB_MAX_RX_URBS]; +}; + +struct kvaser_usb_net_priv { + struct can_priv can; + struct can_berr_counter bec; + + struct kvaser_usb *dev; + struct net_device *netdev; + int channel; + + struct completion start_comp, stop_comp, flush_comp; + struct usb_anchor tx_submitted; + + spinlock_t tx_contexts_lock; /* lock for active_tx_contexts */ + int active_tx_contexts; + struct kvaser_usb_tx_urb_context tx_contexts[]; +}; + +/** + * struct kvaser_usb_dev_ops - Device specific functions + * @dev_set_mode: used for can.do_set_mode + * @dev_set_bittiming: used for can.do_set_bittiming + * @dev_set_data_bittiming: used for can.do_set_data_bittiming + * @dev_get_berr_counter: used for can.do_get_berr_counter + * + * @dev_setup_endpoints: setup USB in and out endpoints + * @dev_init_card: initialize card + * @dev_get_software_info: get software info + * @dev_get_software_details: get software details + * @dev_get_card_info: get card info + * @dev_get_capabilities: discover device capabilities + * + * @dev_set_opt_mode: set ctrlmod + * @dev_start_chip: start the CAN controller + * @dev_stop_chip: stop the CAN controller + * @dev_reset_chip: reset the CAN controller + * @dev_flush_queue: flush outstanding CAN messages + * @dev_read_bulk_callback: handle incoming commands + * @dev_frame_to_cmd: translate struct can_frame into device command + */ +struct kvaser_usb_dev_ops { + int (*dev_set_mode)(struct net_device *netdev, enum can_mode mode); + int (*dev_set_bittiming)(struct net_device *netdev); + int (*dev_set_data_bittiming)(struct net_device *netdev); + int (*dev_get_berr_counter)(const struct net_device *netdev, + struct can_berr_counter *bec); + int (*dev_setup_endpoints)(struct kvaser_usb *dev); + int (*dev_init_card)(struct kvaser_usb *dev); + int (*dev_get_software_info)(struct kvaser_usb *dev); + int (*dev_get_software_details)(struct kvaser_usb *dev); + int (*dev_get_card_info)(struct kvaser_usb *dev); + int (*dev_get_capabilities)(struct kvaser_usb *dev); + int (*dev_set_opt_mode)(const struct kvaser_usb_net_priv *priv); + int (*dev_start_chip)(struct kvaser_usb_net_priv *priv); + int (*dev_stop_chip)(struct kvaser_usb_net_priv *priv); + int (*dev_reset_chip)(struct kvaser_usb *dev, int channel); + int (*dev_flush_queue)(struct kvaser_usb_net_priv *priv); + void (*dev_read_bulk_callback)(struct kvaser_usb *dev, void *buf, + int len); + void *(*dev_frame_to_cmd)(const struct kvaser_usb_net_priv *priv, + const struct sk_buff *skb, int *frame_len, + int *cmd_len, u16 transid); +}; + +struct kvaser_usb_dev_cfg { + const struct can_clock clock; + const unsigned int timestamp_freq; + const struct can_bittiming_const * const bittiming_const; + const struct can_bittiming_const * const data_bittiming_const; +}; + +extern const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops; +extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops; + +int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len, + int *actual_len); + +int kvaser_usb_send_cmd(const struct kvaser_usb *dev, void *cmd, int len); + +int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd, + int len); + +int kvaser_usb_can_rx_over_error(struct net_device *netdev); +#endif /* KVASER_USB_H */ diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c new file mode 100644 index 000000000000..b939a4c10b84 --- /dev/null +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -0,0 +1,835 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Parts of this driver are based on the following: + * - Kvaser linux leaf driver (version 4.78) + * - CAN driver for esd CAN-USB/2 + * - Kvaser linux usbcanII driver (version 5.3) + * - Kvaser linux mhydra driver (version 5.24) + * + * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved. + * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh + * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be> + * Copyright (C) 2015 Valeo S.A. + */ + +#include <linux/completion.h> +#include <linux/device.h> +#include <linux/gfp.h> +#include <linux/if.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/usb.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> +#include <linux/can/netlink.h> + +#include "kvaser_usb.h" + +/* Kvaser USB vendor id. */ +#define KVASER_VENDOR_ID 0x0bfd + +/* Kvaser Leaf USB devices product ids */ +#define USB_LEAF_DEVEL_PRODUCT_ID 10 +#define USB_LEAF_LITE_PRODUCT_ID 11 +#define USB_LEAF_PRO_PRODUCT_ID 12 +#define USB_LEAF_SPRO_PRODUCT_ID 14 +#define USB_LEAF_PRO_LS_PRODUCT_ID 15 +#define USB_LEAF_PRO_SWC_PRODUCT_ID 16 +#define USB_LEAF_PRO_LIN_PRODUCT_ID 17 +#define USB_LEAF_SPRO_LS_PRODUCT_ID 18 +#define USB_LEAF_SPRO_SWC_PRODUCT_ID 19 +#define USB_MEMO2_DEVEL_PRODUCT_ID 22 +#define USB_MEMO2_HSHS_PRODUCT_ID 23 +#define USB_UPRO_HSHS_PRODUCT_ID 24 +#define USB_LEAF_LITE_GI_PRODUCT_ID 25 +#define USB_LEAF_PRO_OBDII_PRODUCT_ID 26 +#define USB_MEMO2_HSLS_PRODUCT_ID 27 +#define USB_LEAF_LITE_CH_PRODUCT_ID 28 +#define USB_BLACKBIRD_SPRO_PRODUCT_ID 29 +#define USB_OEM_MERCURY_PRODUCT_ID 34 +#define USB_OEM_LEAF_PRODUCT_ID 35 +#define USB_CAN_R_PRODUCT_ID 39 +#define USB_LEAF_LITE_V2_PRODUCT_ID 288 +#define USB_MINI_PCIE_HS_PRODUCT_ID 289 +#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290 +#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID 291 +#define USB_MINI_PCIE_2HS_PRODUCT_ID 292 + +/* Kvaser USBCan-II devices product ids */ +#define USB_USBCAN_REVB_PRODUCT_ID 2 +#define USB_VCI2_PRODUCT_ID 3 +#define USB_USBCAN2_PRODUCT_ID 4 +#define USB_MEMORATOR_PRODUCT_ID 5 + +/* Kvaser Minihydra USB devices product ids */ +#define USB_BLACKBIRD_V2_PRODUCT_ID 258 +#define USB_MEMO_PRO_5HS_PRODUCT_ID 260 +#define USB_USBCAN_PRO_5HS_PRODUCT_ID 261 +#define USB_USBCAN_LIGHT_4HS_PRODUCT_ID 262 +#define USB_LEAF_PRO_HS_V2_PRODUCT_ID 263 +#define USB_USBCAN_PRO_2HS_V2_PRODUCT_ID 264 +#define USB_MEMO_2HS_PRODUCT_ID 265 +#define USB_MEMO_PRO_2HS_V2_PRODUCT_ID 266 +#define USB_HYBRID_CANLIN_PRODUCT_ID 267 +#define USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID 268 +#define USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID 269 +#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID 270 + +static inline bool kvaser_is_leaf(const struct usb_device_id *id) +{ + return (id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID && + id->idProduct <= USB_CAN_R_PRODUCT_ID) || + (id->idProduct >= USB_LEAF_LITE_V2_PRODUCT_ID && + id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID); +} + +static inline bool kvaser_is_usbcan(const struct usb_device_id *id) +{ + return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID && + id->idProduct <= USB_MEMORATOR_PRODUCT_ID; +} + +static inline bool kvaser_is_hydra(const struct usb_device_id *id) +{ + return id->idProduct >= USB_BLACKBIRD_V2_PRODUCT_ID && + id->idProduct <= USB_HYBRID_PRO_CANLIN_PRODUCT_ID; +} + +static const struct usb_device_id kvaser_usb_table[] = { + /* Leaf USB product IDs */ + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS | + KVASER_USB_HAS_SILENT_MODE }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) }, + + /* USBCANII USB product IDs */ + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID), + .driver_info = KVASER_USB_HAS_TXRX_ERRORS }, + + /* Minihydra USB product IDs */ + { USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_5HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_5HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_4HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_HS_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) }, + { } +}; +MODULE_DEVICE_TABLE(usb, kvaser_usb_table); + +int kvaser_usb_send_cmd(const struct kvaser_usb *dev, void *cmd, int len) +{ + int actual_len; /* Not used */ + + return usb_bulk_msg(dev->udev, + usb_sndbulkpipe(dev->udev, + dev->bulk_out->bEndpointAddress), + cmd, len, &actual_len, KVASER_USB_TIMEOUT); +} + +int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len, + int *actual_len) +{ + return usb_bulk_msg(dev->udev, + usb_rcvbulkpipe(dev->udev, + dev->bulk_in->bEndpointAddress), + cmd, len, actual_len, KVASER_USB_TIMEOUT); +} + +static void kvaser_usb_send_cmd_callback(struct urb *urb) +{ + struct net_device *netdev = urb->context; + + kfree(urb->transfer_buffer); + + if (urb->status) + netdev_warn(netdev, "urb status received: %d\n", urb->status); +} + +int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd, + int len) +{ + struct kvaser_usb *dev = priv->dev; + struct net_device *netdev = priv->netdev; + struct urb *urb; + int err; + + urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!urb) + return -ENOMEM; + + usb_fill_bulk_urb(urb, dev->udev, + usb_sndbulkpipe(dev->udev, + dev->bulk_out->bEndpointAddress), + cmd, len, kvaser_usb_send_cmd_callback, netdev); + usb_anchor_urb(urb, &priv->tx_submitted); + + err = usb_submit_urb(urb, GFP_ATOMIC); + if (err) { + netdev_err(netdev, "Error transmitting URB\n"); + usb_unanchor_urb(urb); + } + usb_free_urb(urb); + + return 0; +} + +int kvaser_usb_can_rx_over_error(struct net_device *netdev) +{ + struct net_device_stats *stats = &netdev->stats; + struct can_frame *cf; + struct sk_buff *skb; + + stats->rx_over_errors++; + stats->rx_errors++; + + skb = alloc_can_err_skb(netdev, &cf); + if (!skb) { + stats->rx_dropped++; + netdev_warn(netdev, "No memory left for err_skb\n"); + return -ENOMEM; + } + + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + + return 0; +} + +static void kvaser_usb_read_bulk_callback(struct urb *urb) +{ + struct kvaser_usb *dev = urb->context; + int err; + unsigned int i; + + switch (urb->status) { + case 0: + break; + case -ENOENT: + case -EPIPE: + case -EPROTO: + case -ESHUTDOWN: + return; + default: + dev_info(&dev->intf->dev, "Rx URB aborted (%d)\n", urb->status); + goto resubmit_urb; + } + + dev->ops->dev_read_bulk_callback(dev, urb->transfer_buffer, + urb->actual_length); + +resubmit_urb: + usb_fill_bulk_urb(urb, dev->udev, + usb_rcvbulkpipe(dev->udev, + dev->bulk_in->bEndpointAddress), + urb->transfer_buffer, KVASER_USB_RX_BUFFER_SIZE, + kvaser_usb_read_bulk_callback, dev); + + err = usb_submit_urb(urb, GFP_ATOMIC); + if (err == -ENODEV) { + for (i = 0; i < dev->nchannels; i++) { + if (!dev->nets[i]) + continue; + + netif_device_detach(dev->nets[i]->netdev); + } + } else if (err) { + dev_err(&dev->intf->dev, + "Failed resubmitting read bulk urb: %d\n", err); + } +} + +static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev) +{ + int i, err = 0; + + if (dev->rxinitdone) + return 0; + + for (i = 0; i < KVASER_USB_MAX_RX_URBS; i++) { + struct urb *urb = NULL; + u8 *buf = NULL; + dma_addr_t buf_dma; + + urb = usb_alloc_urb(0, GFP_KERNEL); + if (!urb) { + err = -ENOMEM; + break; + } + + buf = usb_alloc_coherent(dev->udev, KVASER_USB_RX_BUFFER_SIZE, + GFP_KERNEL, &buf_dma); + if (!buf) { + dev_warn(&dev->intf->dev, + "No memory left for USB buffer\n"); + usb_free_urb(urb); + err = -ENOMEM; + break; + } + + usb_fill_bulk_urb(urb, dev->udev, + usb_rcvbulkpipe + (dev->udev, + dev->bulk_in->bEndpointAddress), + buf, KVASER_USB_RX_BUFFER_SIZE, + kvaser_usb_read_bulk_callback, dev); + urb->transfer_dma = buf_dma; + urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + usb_anchor_urb(urb, &dev->rx_submitted); + + err = usb_submit_urb(urb, GFP_KERNEL); + if (err) { + usb_unanchor_urb(urb); + usb_free_coherent(dev->udev, + KVASER_USB_RX_BUFFER_SIZE, buf, + buf_dma); + usb_free_urb(urb); + break; + } + + dev->rxbuf[i] = buf; + dev->rxbuf_dma[i] = buf_dma; + + usb_free_urb(urb); + } + + if (i == 0) { + dev_warn(&dev->intf->dev, "Cannot setup read URBs, error %d\n", + err); + return err; + } else if (i < KVASER_USB_MAX_RX_URBS) { + dev_warn(&dev->intf->dev, "RX performances may be slow\n"); + } + + dev->rxinitdone = true; + + return 0; +} + +static int kvaser_usb_open(struct net_device *netdev) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct kvaser_usb *dev = priv->dev; + int err; + + err = open_candev(netdev); + if (err) + return err; + + err = kvaser_usb_setup_rx_urbs(dev); + if (err) + goto error; + + err = dev->ops->dev_set_opt_mode(priv); + if (err) + goto error; + + err = dev->ops->dev_start_chip(priv); + if (err) { + netdev_warn(netdev, "Cannot start device, error %d\n", err); + goto error; + } + + priv->can.state = CAN_STATE_ERROR_ACTIVE; + + return 0; + +error: + close_candev(netdev); + return err; +} + +static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv) +{ + int i, max_tx_urbs; + + max_tx_urbs = priv->dev->max_tx_urbs; + + priv->active_tx_contexts = 0; + for (i = 0; i < max_tx_urbs; i++) + priv->tx_contexts[i].echo_index = max_tx_urbs; +} + +/* This method might sleep. Do not call it in the atomic context + * of URB completions. + */ +static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) +{ + usb_kill_anchored_urbs(&priv->tx_submitted); + kvaser_usb_reset_tx_urb_contexts(priv); +} + +static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev) +{ + int i; + + usb_kill_anchored_urbs(&dev->rx_submitted); + + for (i = 0; i < KVASER_USB_MAX_RX_URBS; i++) + usb_free_coherent(dev->udev, KVASER_USB_RX_BUFFER_SIZE, + dev->rxbuf[i], dev->rxbuf_dma[i]); + + for (i = 0; i < dev->nchannels; i++) { + struct kvaser_usb_net_priv *priv = dev->nets[i]; + + if (priv) + kvaser_usb_unlink_tx_urbs(priv); + } +} + +static int kvaser_usb_close(struct net_device *netdev) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct kvaser_usb *dev = priv->dev; + int err; + + netif_stop_queue(netdev); + + err = dev->ops->dev_flush_queue(priv); + if (err) + netdev_warn(netdev, "Cannot flush queue, error %d\n", err); + + if (dev->ops->dev_reset_chip) { + err = dev->ops->dev_reset_chip(dev, priv->channel); + if (err) + netdev_warn(netdev, "Cannot reset card, error %d\n", + err); + } + + err = dev->ops->dev_stop_chip(priv); + if (err) + netdev_warn(netdev, "Cannot stop device, error %d\n", err); + + /* reset tx contexts */ + kvaser_usb_unlink_tx_urbs(priv); + + priv->can.state = CAN_STATE_STOPPED; + close_candev(priv->netdev); + + return 0; +} + +static void kvaser_usb_write_bulk_callback(struct urb *urb) +{ + struct kvaser_usb_tx_urb_context *context = urb->context; + struct kvaser_usb_net_priv *priv; + struct net_device *netdev; + + if (WARN_ON(!context)) + return; + + priv = context->priv; + netdev = priv->netdev; + + kfree(urb->transfer_buffer); + + if (!netif_device_present(netdev)) + return; + + if (urb->status) + netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status); +} + +static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct kvaser_usb *dev = priv->dev; + struct net_device_stats *stats = &netdev->stats; + struct kvaser_usb_tx_urb_context *context = NULL; + struct urb *urb; + void *buf; + int cmd_len = 0; + int err, ret = NETDEV_TX_OK; + unsigned int i; + unsigned long flags; + + if (can_dropped_invalid_skb(netdev, skb)) + return NETDEV_TX_OK; + + urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!urb) { + stats->tx_dropped++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + spin_lock_irqsave(&priv->tx_contexts_lock, flags); + for (i = 0; i < dev->max_tx_urbs; i++) { + if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) { + context = &priv->tx_contexts[i]; + + context->echo_index = i; + can_put_echo_skb(skb, netdev, context->echo_index); + ++priv->active_tx_contexts; + if (priv->active_tx_contexts >= (int)dev->max_tx_urbs) + netif_stop_queue(netdev); + + break; + } + } + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); + + /* This should never happen; it implies a flow control bug */ + if (!context) { + netdev_warn(netdev, "cannot find free context\n"); + + ret = NETDEV_TX_BUSY; + goto freeurb; + } + + buf = dev->ops->dev_frame_to_cmd(priv, skb, &context->dlc, &cmd_len, + context->echo_index); + if (!buf) { + stats->tx_dropped++; + dev_kfree_skb(skb); + spin_lock_irqsave(&priv->tx_contexts_lock, flags); + + can_free_echo_skb(netdev, context->echo_index); + context->echo_index = dev->max_tx_urbs; + --priv->active_tx_contexts; + netif_wake_queue(netdev); + + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); + goto freeurb; + } + + context->priv = priv; + + usb_fill_bulk_urb(urb, dev->udev, + usb_sndbulkpipe(dev->udev, + dev->bulk_out->bEndpointAddress), + buf, cmd_len, kvaser_usb_write_bulk_callback, + context); + usb_anchor_urb(urb, &priv->tx_submitted); + + err = usb_submit_urb(urb, GFP_ATOMIC); + if (unlikely(err)) { + spin_lock_irqsave(&priv->tx_contexts_lock, flags); + + can_free_echo_skb(netdev, context->echo_index); + context->echo_index = dev->max_tx_urbs; + --priv->active_tx_contexts; + netif_wake_queue(netdev); + + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); + + usb_unanchor_urb(urb); + kfree(buf); + + stats->tx_dropped++; + + if (err == -ENODEV) + netif_device_detach(netdev); + else + netdev_warn(netdev, "Failed tx_urb %d\n", err); + + goto freeurb; + } + + ret = NETDEV_TX_OK; + +freeurb: + usb_free_urb(urb); + return ret; +} + +static const struct net_device_ops kvaser_usb_netdev_ops = { + .ndo_open = kvaser_usb_open, + .ndo_stop = kvaser_usb_close, + .ndo_start_xmit = kvaser_usb_start_xmit, + .ndo_change_mtu = can_change_mtu, +}; + +static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev) +{ + int i; + + for (i = 0; i < dev->nchannels; i++) { + if (!dev->nets[i]) + continue; + + unregister_candev(dev->nets[i]->netdev); + } + + kvaser_usb_unlink_all_urbs(dev); + + for (i = 0; i < dev->nchannels; i++) { + if (!dev->nets[i]) + continue; + + free_candev(dev->nets[i]->netdev); + } +} + +static int kvaser_usb_init_one(struct kvaser_usb *dev, + const struct usb_device_id *id, int channel) +{ + struct net_device *netdev; + struct kvaser_usb_net_priv *priv; + int err; + + if (dev->ops->dev_reset_chip) { + err = dev->ops->dev_reset_chip(dev, channel); + if (err) + return err; + } + + netdev = alloc_candev(sizeof(*priv) + + dev->max_tx_urbs * sizeof(*priv->tx_contexts), + dev->max_tx_urbs); + if (!netdev) { + dev_err(&dev->intf->dev, "Cannot alloc candev\n"); + return -ENOMEM; + } + + priv = netdev_priv(netdev); + + init_usb_anchor(&priv->tx_submitted); + init_completion(&priv->start_comp); + init_completion(&priv->stop_comp); + priv->can.ctrlmode_supported = 0; + + priv->dev = dev; + priv->netdev = netdev; + priv->channel = channel; + + spin_lock_init(&priv->tx_contexts_lock); + kvaser_usb_reset_tx_urb_contexts(priv); + + priv->can.state = CAN_STATE_STOPPED; + priv->can.clock.freq = dev->cfg->clock.freq; + priv->can.bittiming_const = dev->cfg->bittiming_const; + priv->can.do_set_bittiming = dev->ops->dev_set_bittiming; + priv->can.do_set_mode = dev->ops->dev_set_mode; + if ((id->driver_info & KVASER_USB_HAS_TXRX_ERRORS) || + (priv->dev->card_data.capabilities & KVASER_USB_CAP_BERR_CAP)) + priv->can.do_get_berr_counter = dev->ops->dev_get_berr_counter; + if (id->driver_info & KVASER_USB_HAS_SILENT_MODE) + priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY; + + priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported; + + if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) { + priv->can.data_bittiming_const = dev->cfg->data_bittiming_const; + priv->can.do_set_data_bittiming = + dev->ops->dev_set_data_bittiming; + } + + netdev->flags |= IFF_ECHO; + + netdev->netdev_ops = &kvaser_usb_netdev_ops; + + SET_NETDEV_DEV(netdev, &dev->intf->dev); + netdev->dev_id = channel; + + dev->nets[channel] = priv; + + err = register_candev(netdev); + if (err) { + dev_err(&dev->intf->dev, "Failed to register CAN device\n"); + free_candev(netdev); + dev->nets[channel] = NULL; + return err; + } + + netdev_dbg(netdev, "device registered\n"); + + return 0; +} + +static int kvaser_usb_probe(struct usb_interface *intf, + const struct usb_device_id *id) +{ + struct kvaser_usb *dev; + int err; + int i; + + dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + if (kvaser_is_leaf(id)) { + dev->card_data.leaf.family = KVASER_LEAF; + dev->ops = &kvaser_usb_leaf_dev_ops; + } else if (kvaser_is_usbcan(id)) { + dev->card_data.leaf.family = KVASER_USBCAN; + dev->ops = &kvaser_usb_leaf_dev_ops; + } else if (kvaser_is_hydra(id)) { + dev->ops = &kvaser_usb_hydra_dev_ops; + } else { + dev_err(&intf->dev, + "Product ID (%d) is not a supported Kvaser USB device\n", + id->idProduct); + return -ENODEV; + } + + dev->intf = intf; + + err = dev->ops->dev_setup_endpoints(dev); + if (err) { + dev_err(&intf->dev, "Cannot get usb endpoint(s)"); + return err; + } + + dev->udev = interface_to_usbdev(intf); + + init_usb_anchor(&dev->rx_submitted); + + usb_set_intfdata(intf, dev); + + dev->card_data.ctrlmode_supported = 0; + dev->card_data.capabilities = 0; + err = dev->ops->dev_init_card(dev); + if (err) { + dev_err(&intf->dev, + "Failed to initialize card, error %d\n", err); + return err; + } + + err = dev->ops->dev_get_software_info(dev); + if (err) { + dev_err(&intf->dev, + "Cannot get software info, error %d\n", err); + return err; + } + + if (dev->ops->dev_get_software_details) { + err = dev->ops->dev_get_software_details(dev); + if (err) { + dev_err(&intf->dev, + "Cannot get software details, error %d\n", err); + return err; + } + } + + if (WARN_ON(!dev->cfg)) + return -ENODEV; + + dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n", + ((dev->fw_version >> 24) & 0xff), + ((dev->fw_version >> 16) & 0xff), + (dev->fw_version & 0xffff)); + + dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs); + + err = dev->ops->dev_get_card_info(dev); + if (err) { + dev_err(&intf->dev, "Cannot get card info, error %d\n", err); + return err; + } + + if (dev->ops->dev_get_capabilities) { + err = dev->ops->dev_get_capabilities(dev); + if (err) { + dev_err(&intf->dev, + "Cannot get capabilities, error %d\n", err); + kvaser_usb_remove_interfaces(dev); + return err; + } + } + + for (i = 0; i < dev->nchannels; i++) { + err = kvaser_usb_init_one(dev, id, i); + if (err) { + kvaser_usb_remove_interfaces(dev); + return err; + } + } + + return 0; +} + +static void kvaser_usb_disconnect(struct usb_interface *intf) +{ + struct kvaser_usb *dev = usb_get_intfdata(intf); + + usb_set_intfdata(intf, NULL); + + if (!dev) + return; + + kvaser_usb_remove_interfaces(dev); +} + +static struct usb_driver kvaser_usb_driver = { + .name = "kvaser_usb", + .probe = kvaser_usb_probe, + .disconnect = kvaser_usb_disconnect, + .id_table = kvaser_usb_table, +}; + +module_usb_driver(kvaser_usb_driver); + +MODULE_AUTHOR("Olivier Sobrie <olivier@sobrie.be>"); +MODULE_AUTHOR("Kvaser AB <support@kvaser.com>"); +MODULE_DESCRIPTION("CAN driver for Kvaser CAN/USB devices"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c new file mode 100644 index 000000000000..c084bae5ec0a --- /dev/null +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -0,0 +1,2028 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Parts of this driver are based on the following: + * - Kvaser linux mhydra driver (version 5.24) + * - CAN driver for esd CAN-USB/2 + * + * Copyright (C) 2018 KVASER AB, Sweden. All rights reserved. + * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh + * + * Known issues: + * - Transition from CAN_STATE_ERROR_WARNING to CAN_STATE_ERROR_ACTIVE is only + * reported after a call to do_get_berr_counter(), since firmware does not + * distinguish between ERROR_WARNING and ERROR_ACTIVE. + * - Hardware timestamps are not set for CAN Tx frames. + */ + +#include <linux/completion.h> +#include <linux/device.h> +#include <linux/gfp.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/usb.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> +#include <linux/can/netlink.h> + +#include "kvaser_usb.h" + +/* Forward declarations */ +static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan; +static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc; + +#define KVASER_USB_HYDRA_BULK_EP_IN_ADDR 0x82 +#define KVASER_USB_HYDRA_BULK_EP_OUT_ADDR 0x02 + +#define KVASER_USB_HYDRA_MAX_TRANSID 0xff +#define KVASER_USB_HYDRA_MIN_TRANSID 0x01 + +/* Minihydra command IDs */ +#define CMD_SET_BUSPARAMS_REQ 16 +#define CMD_GET_CHIP_STATE_REQ 19 +#define CMD_CHIP_STATE_EVENT 20 +#define CMD_SET_DRIVERMODE_REQ 21 +#define CMD_START_CHIP_REQ 26 +#define CMD_START_CHIP_RESP 27 +#define CMD_STOP_CHIP_REQ 28 +#define CMD_STOP_CHIP_RESP 29 +#define CMD_TX_CAN_MESSAGE 33 +#define CMD_GET_CARD_INFO_REQ 34 +#define CMD_GET_CARD_INFO_RESP 35 +#define CMD_GET_SOFTWARE_INFO_REQ 38 +#define CMD_GET_SOFTWARE_INFO_RESP 39 +#define CMD_ERROR_EVENT 45 +#define CMD_FLUSH_QUEUE 48 +#define CMD_TX_ACKNOWLEDGE 50 +#define CMD_FLUSH_QUEUE_RESP 66 +#define CMD_SET_BUSPARAMS_FD_REQ 69 +#define CMD_SET_BUSPARAMS_FD_RESP 70 +#define CMD_SET_BUSPARAMS_RESP 85 +#define CMD_GET_CAPABILITIES_REQ 95 +#define CMD_GET_CAPABILITIES_RESP 96 +#define CMD_RX_MESSAGE 106 +#define CMD_MAP_CHANNEL_REQ 200 +#define CMD_MAP_CHANNEL_RESP 201 +#define CMD_GET_SOFTWARE_DETAILS_REQ 202 +#define CMD_GET_SOFTWARE_DETAILS_RESP 203 +#define CMD_EXTENDED 255 + +/* Minihydra extended command IDs */ +#define CMD_TX_CAN_MESSAGE_FD 224 +#define CMD_TX_ACKNOWLEDGE_FD 225 +#define CMD_RX_MESSAGE_FD 226 + +/* Hydra commands are handled by different threads in firmware. + * The threads are denoted hydra entity (HE). Each HE got a unique 6-bit + * address. The address is used in hydra commands to get/set source and + * destination HE. There are two predefined HE addresses, the remaining + * addresses are different between devices and firmware versions. Hence, we need + * to enumerate the addresses (see kvaser_usb_hydra_map_channel()). + */ + +/* Well-known HE addresses */ +#define KVASER_USB_HYDRA_HE_ADDRESS_ROUTER 0x00 +#define KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL 0x3e + +#define KVASER_USB_HYDRA_TRANSID_CANHE 0x40 +#define KVASER_USB_HYDRA_TRANSID_SYSDBG 0x61 + +struct kvaser_cmd_map_ch_req { + char name[16]; + u8 channel; + u8 reserved[11]; +} __packed; + +struct kvaser_cmd_map_ch_res { + u8 he_addr; + u8 channel; + u8 reserved[26]; +} __packed; + +struct kvaser_cmd_card_info { + __le32 serial_number; + __le32 clock_res; + __le32 mfg_date; + __le32 ean[2]; + u8 hw_version; + u8 usb_mode; + u8 hw_type; + u8 reserved0; + u8 nchannels; + u8 reserved1[3]; +} __packed; + +struct kvaser_cmd_sw_info { + u8 reserved0[8]; + __le16 max_outstanding_tx; + u8 reserved1[18]; +} __packed; + +struct kvaser_cmd_sw_detail_req { + u8 use_ext_cmd; + u8 reserved[27]; +} __packed; + +/* Software detail flags */ +#define KVASER_USB_HYDRA_SW_FLAG_FW_BETA BIT(2) +#define KVASER_USB_HYDRA_SW_FLAG_FW_BAD BIT(4) +#define KVASER_USB_HYDRA_SW_FLAG_FREQ_80M BIT(5) +#define KVASER_USB_HYDRA_SW_FLAG_EXT_CMD BIT(9) +#define KVASER_USB_HYDRA_SW_FLAG_CANFD BIT(10) +#define KVASER_USB_HYDRA_SW_FLAG_NONISO BIT(11) +#define KVASER_USB_HYDRA_SW_FLAG_EXT_CAP BIT(12) +struct kvaser_cmd_sw_detail_res { + __le32 sw_flags; + __le32 sw_version; + __le32 sw_name; + __le32 ean[2]; + __le32 max_bitrate; + u8 reserved[4]; +} __packed; + +/* Sub commands for cap_req and cap_res */ +#define KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE 0x02 +#define KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT 0x05 +#define KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT 0x06 +struct kvaser_cmd_cap_req { + __le16 cap_cmd; + u8 reserved[26]; +} __packed; + +/* Status codes for cap_res */ +#define KVASER_USB_HYDRA_CAP_STAT_OK 0x00 +#define KVASER_USB_HYDRA_CAP_STAT_NOT_IMPL 0x01 +#define KVASER_USB_HYDRA_CAP_STAT_UNAVAIL 0x02 +struct kvaser_cmd_cap_res { + __le16 cap_cmd; + __le16 status; + __le32 mask; + __le32 value; + u8 reserved[16]; +} __packed; + +/* CMD_ERROR_EVENT error codes */ +#define KVASER_USB_HYDRA_ERROR_EVENT_CAN 0x01 +#define KVASER_USB_HYDRA_ERROR_EVENT_PARAM 0x09 +struct kvaser_cmd_error_event { + __le16 timestamp[3]; + u8 reserved; + u8 error_code; + __le16 info1; + __le16 info2; +} __packed; + +/* Chip state status flags. Used for chip_state_event and err_frame_data. */ +#define KVASER_USB_HYDRA_BUS_ERR_ACT 0x00 +#define KVASER_USB_HYDRA_BUS_ERR_PASS BIT(5) +#define KVASER_USB_HYDRA_BUS_BUS_OFF BIT(6) +struct kvaser_cmd_chip_state_event { + __le16 timestamp[3]; + u8 tx_err_counter; + u8 rx_err_counter; + u8 bus_status; + u8 reserved[19]; +} __packed; + +/* Busparam modes */ +#define KVASER_USB_HYDRA_BUS_MODE_CAN 0x00 +#define KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO 0x01 +#define KVASER_USB_HYDRA_BUS_MODE_NONISO 0x02 +struct kvaser_cmd_set_busparams { + __le32 bitrate; + u8 tseg1; + u8 tseg2; + u8 sjw; + u8 nsamples; + u8 reserved0[4]; + __le32 bitrate_d; + u8 tseg1_d; + u8 tseg2_d; + u8 sjw_d; + u8 nsamples_d; + u8 canfd_mode; + u8 reserved1[7]; +} __packed; + +/* Ctrl modes */ +#define KVASER_USB_HYDRA_CTRLMODE_NORMAL 0x01 +#define KVASER_USB_HYDRA_CTRLMODE_LISTEN 0x02 +struct kvaser_cmd_set_ctrlmode { + u8 mode; + u8 reserved[27]; +} __packed; + +struct kvaser_err_frame_data { + u8 bus_status; + u8 reserved0; + u8 tx_err_counter; + u8 rx_err_counter; + u8 reserved1[4]; +} __packed; + +struct kvaser_cmd_rx_can { + u8 cmd_len; + u8 cmd_no; + u8 channel; + u8 flags; + __le16 timestamp[3]; + u8 dlc; + u8 padding; + __le32 id; + union { + u8 data[8]; + struct kvaser_err_frame_data err_frame_data; + }; +} __packed; + +/* Extended CAN ID flag. Used in rx_can and tx_can */ +#define KVASER_USB_HYDRA_EXTENDED_FRAME_ID BIT(31) +struct kvaser_cmd_tx_can { + __le32 id; + u8 data[8]; + u8 dlc; + u8 flags; + __le16 transid; + u8 channel; + u8 reserved[11]; +} __packed; + +struct kvaser_cmd_header { + u8 cmd_no; + /* The destination HE address is stored in 0..5 of he_addr. + * The upper part of source HE address is stored in 6..7 of he_addr, and + * the lower part is stored in 12..15 of transid. + */ + u8 he_addr; + __le16 transid; +} __packed; + +struct kvaser_cmd { + struct kvaser_cmd_header header; + union { + struct kvaser_cmd_map_ch_req map_ch_req; + struct kvaser_cmd_map_ch_res map_ch_res; + + struct kvaser_cmd_card_info card_info; + struct kvaser_cmd_sw_info sw_info; + struct kvaser_cmd_sw_detail_req sw_detail_req; + struct kvaser_cmd_sw_detail_res sw_detail_res; + + struct kvaser_cmd_cap_req cap_req; + struct kvaser_cmd_cap_res cap_res; + + struct kvaser_cmd_error_event error_event; + + struct kvaser_cmd_set_busparams set_busparams_req; + + struct kvaser_cmd_chip_state_event chip_state_event; + + struct kvaser_cmd_set_ctrlmode set_ctrlmode; + + struct kvaser_cmd_rx_can rx_can; + struct kvaser_cmd_tx_can tx_can; + } __packed; +} __packed; + +/* CAN frame flags. Used in rx_can, ext_rx_can, tx_can and ext_tx_can */ +#define KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME BIT(0) +#define KVASER_USB_HYDRA_CF_FLAG_OVERRUN BIT(1) +#define KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME BIT(4) +#define KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID BIT(5) +/* CAN frame flags. Used in ext_rx_can and ext_tx_can */ +#define KVASER_USB_HYDRA_CF_FLAG_OSM_NACK BIT(12) +#define KVASER_USB_HYDRA_CF_FLAG_ABL BIT(13) +#define KVASER_USB_HYDRA_CF_FLAG_FDF BIT(16) +#define KVASER_USB_HYDRA_CF_FLAG_BRS BIT(17) +#define KVASER_USB_HYDRA_CF_FLAG_ESI BIT(18) + +/* KCAN packet header macros. Used in ext_rx_can and ext_tx_can */ +#define KVASER_USB_KCAN_DATA_DLC_BITS 4 +#define KVASER_USB_KCAN_DATA_DLC_SHIFT 8 +#define KVASER_USB_KCAN_DATA_DLC_MASK \ + GENMASK(KVASER_USB_KCAN_DATA_DLC_BITS - 1 + \ + KVASER_USB_KCAN_DATA_DLC_SHIFT, \ + KVASER_USB_KCAN_DATA_DLC_SHIFT) + +#define KVASER_USB_KCAN_DATA_BRS BIT(14) +#define KVASER_USB_KCAN_DATA_FDF BIT(15) +#define KVASER_USB_KCAN_DATA_OSM BIT(16) +#define KVASER_USB_KCAN_DATA_AREQ BIT(31) +#define KVASER_USB_KCAN_DATA_SRR BIT(31) +#define KVASER_USB_KCAN_DATA_RTR BIT(29) +#define KVASER_USB_KCAN_DATA_IDE BIT(30) +struct kvaser_cmd_ext_rx_can { + __le32 flags; + __le32 id; + __le32 kcan_id; + __le32 kcan_header; + __le64 timestamp; + union { + u8 kcan_payload[64]; + struct kvaser_err_frame_data err_frame_data; + }; +} __packed; + +struct kvaser_cmd_ext_tx_can { + __le32 flags; + __le32 id; + __le32 kcan_id; + __le32 kcan_header; + u8 databytes; + u8 dlc; + u8 reserved[6]; + u8 kcan_payload[64]; +} __packed; + +struct kvaser_cmd_ext_tx_ack { + __le32 flags; + u8 reserved0[4]; + __le64 timestamp; + u8 reserved1[8]; +} __packed; + +/* struct for extended commands (CMD_EXTENDED) */ +struct kvaser_cmd_ext { + struct kvaser_cmd_header header; + __le16 len; + u8 cmd_no_ext; + u8 reserved; + + union { + struct kvaser_cmd_ext_rx_can rx_can; + struct kvaser_cmd_ext_tx_can tx_can; + struct kvaser_cmd_ext_tx_ack tx_ack; + } __packed; +} __packed; + +static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = { + .name = "kvaser_usb_kcan", + .tseg1_min = 1, + .tseg1_max = 255, + .tseg2_min = 1, + .tseg2_max = 32, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 4096, + .brp_inc = 1, +}; + +static const struct can_bittiming_const kvaser_usb_hydra_flexc_bittiming_c = { + .name = "kvaser_usb_flex", + .tseg1_min = 4, + .tseg1_max = 16, + .tseg2_min = 2, + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 256, + .brp_inc = 1, +}; + +#define KVASER_USB_HYDRA_TRANSID_BITS 12 +#define KVASER_USB_HYDRA_TRANSID_MASK \ + GENMASK(KVASER_USB_HYDRA_TRANSID_BITS - 1, 0) +#define KVASER_USB_HYDRA_HE_ADDR_SRC_MASK GENMASK(7, 6) +#define KVASER_USB_HYDRA_HE_ADDR_DEST_MASK GENMASK(5, 0) +#define KVASER_USB_HYDRA_HE_ADDR_SRC_BITS 2 +static inline u16 kvaser_usb_hydra_get_cmd_transid(const struct kvaser_cmd *cmd) +{ + return le16_to_cpu(cmd->header.transid) & KVASER_USB_HYDRA_TRANSID_MASK; +} + +static inline void kvaser_usb_hydra_set_cmd_transid(struct kvaser_cmd *cmd, + u16 transid) +{ + cmd->header.transid = + cpu_to_le16(transid & KVASER_USB_HYDRA_TRANSID_MASK); +} + +static inline u8 kvaser_usb_hydra_get_cmd_src_he(const struct kvaser_cmd *cmd) +{ + return (cmd->header.he_addr & KVASER_USB_HYDRA_HE_ADDR_SRC_MASK) >> + KVASER_USB_HYDRA_HE_ADDR_SRC_BITS | + le16_to_cpu(cmd->header.transid) >> + KVASER_USB_HYDRA_TRANSID_BITS; +} + +static inline void kvaser_usb_hydra_set_cmd_dest_he(struct kvaser_cmd *cmd, + u8 dest_he) +{ + cmd->header.he_addr = + (cmd->header.he_addr & KVASER_USB_HYDRA_HE_ADDR_SRC_MASK) | + (dest_he & KVASER_USB_HYDRA_HE_ADDR_DEST_MASK); +} + +static u8 kvaser_usb_hydra_channel_from_cmd(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + int i; + u8 channel = 0xff; + u8 src_he = kvaser_usb_hydra_get_cmd_src_he(cmd); + + for (i = 0; i < KVASER_USB_MAX_NET_DEVICES; i++) { + if (dev->card_data.hydra.channel_to_he[i] == src_he) { + channel = i; + break; + } + } + + return channel; +} + +static u16 kvaser_usb_hydra_get_next_transid(struct kvaser_usb *dev) +{ + unsigned long flags; + u16 transid; + struct kvaser_usb_dev_card_data_hydra *card_data = + &dev->card_data.hydra; + + spin_lock_irqsave(&card_data->transid_lock, flags); + transid = card_data->transid; + if (transid >= KVASER_USB_HYDRA_MAX_TRANSID) + transid = KVASER_USB_HYDRA_MIN_TRANSID; + else + transid++; + card_data->transid = transid; + spin_unlock_irqrestore(&card_data->transid_lock, flags); + + return transid; +} + +static size_t kvaser_usb_hydra_cmd_size(struct kvaser_cmd *cmd) +{ + size_t ret; + + if (cmd->header.cmd_no == CMD_EXTENDED) + ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len); + else + ret = sizeof(struct kvaser_cmd); + + return ret; +} + +static struct kvaser_usb_net_priv * +kvaser_usb_hydra_net_priv_from_cmd(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv = NULL; + u8 channel = kvaser_usb_hydra_channel_from_cmd(dev, cmd); + + if (channel >= dev->nchannels) + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + else + priv = dev->nets[channel]; + + return priv; +} + +static ktime_t +kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg, + const struct kvaser_cmd *cmd) +{ + u64 ticks; + + if (cmd->header.cmd_no == CMD_EXTENDED) { + struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd; + + ticks = le64_to_cpu(cmd_ext->rx_can.timestamp); + } else { + ticks = le16_to_cpu(cmd->rx_can.timestamp[0]); + ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[1])) << 16; + ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[2])) << 32; + } + + return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq)); +} + +static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, + u8 cmd_no, int channel) +{ + struct kvaser_cmd *cmd; + int err; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = cmd_no; + if (channel < 0) { + kvaser_usb_hydra_set_cmd_dest_he + (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL); + } else { + if (channel >= KVASER_USB_MAX_NET_DEVICES) { + dev_err(&dev->intf->dev, "channel (%d) out of range.\n", + channel); + err = -EINVAL; + goto end; + } + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[channel]); + } + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + if (err) + goto end; + +end: + kfree(cmd); + + return err; +} + +static int +kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv, + u8 cmd_no) +{ + struct kvaser_cmd *cmd; + struct kvaser_usb *dev = priv->dev; + int err; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = cmd_no; + + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + + err = kvaser_usb_send_cmd_async(priv, cmd, + kvaser_usb_hydra_cmd_size(cmd)); + if (err) + kfree(cmd); + + return err; +} + +/* This function is used for synchronously waiting on hydra control commands. + * Note: Compared to kvaser_usb_hydra_read_bulk_callback(), we never need to + * handle partial hydra commands. Since hydra control commands are always + * non-extended commands. + */ +static int kvaser_usb_hydra_wait_cmd(const struct kvaser_usb *dev, u8 cmd_no, + struct kvaser_cmd *cmd) +{ + void *buf; + int err; + unsigned long timeout = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT); + + if (cmd->header.cmd_no == CMD_EXTENDED) { + dev_err(&dev->intf->dev, "Wait for CMD_EXTENDED not allowed\n"); + return -EINVAL; + } + + buf = kzalloc(KVASER_USB_RX_BUFFER_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + do { + int actual_len = 0; + int pos = 0; + + err = kvaser_usb_recv_cmd(dev, buf, KVASER_USB_RX_BUFFER_SIZE, + &actual_len); + if (err < 0) + goto end; + + while (pos < actual_len) { + struct kvaser_cmd *tmp_cmd; + size_t cmd_len; + + tmp_cmd = buf + pos; + cmd_len = kvaser_usb_hydra_cmd_size(tmp_cmd); + if (pos + cmd_len > actual_len) { + dev_err_ratelimited(&dev->intf->dev, + "Format error\n"); + break; + } + + if (tmp_cmd->header.cmd_no == cmd_no) { + memcpy(cmd, tmp_cmd, cmd_len); + goto end; + } + pos += cmd_len; + } + } while (time_before(jiffies, timeout)); + + err = -EINVAL; + +end: + kfree(buf); + + return err; +} + +static int kvaser_usb_hydra_map_channel_resp(struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + u8 he, channel; + u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd); + struct kvaser_usb_dev_card_data_hydra *card_data = + &dev->card_data.hydra; + + if (transid > 0x007f || transid < 0x0040) { + dev_err(&dev->intf->dev, + "CMD_MAP_CHANNEL_RESP, invalid transid: 0x%x\n", + transid); + return -EINVAL; + } + + switch (transid) { + case KVASER_USB_HYDRA_TRANSID_CANHE: + case KVASER_USB_HYDRA_TRANSID_CANHE + 1: + case KVASER_USB_HYDRA_TRANSID_CANHE + 2: + case KVASER_USB_HYDRA_TRANSID_CANHE + 3: + case KVASER_USB_HYDRA_TRANSID_CANHE + 4: + channel = transid & 0x000f; + he = cmd->map_ch_res.he_addr; + card_data->channel_to_he[channel] = he; + break; + case KVASER_USB_HYDRA_TRANSID_SYSDBG: + card_data->sysdbg_he = cmd->map_ch_res.he_addr; + break; + default: + dev_warn(&dev->intf->dev, + "Unknown CMD_MAP_CHANNEL_RESP transid=0x%x\n", + transid); + break; + } + + return 0; +} + +static int kvaser_usb_hydra_map_channel(struct kvaser_usb *dev, u16 transid, + u8 channel, const char *name) +{ + struct kvaser_cmd *cmd; + int err; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + strcpy(cmd->map_ch_req.name, name); + cmd->header.cmd_no = CMD_MAP_CHANNEL_REQ; + kvaser_usb_hydra_set_cmd_dest_he + (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ROUTER); + cmd->map_ch_req.channel = channel; + + kvaser_usb_hydra_set_cmd_transid(cmd, transid); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + if (err) + goto end; + + err = kvaser_usb_hydra_wait_cmd(dev, CMD_MAP_CHANNEL_RESP, cmd); + if (err) + goto end; + + err = kvaser_usb_hydra_map_channel_resp(dev, cmd); + if (err) + goto end; + +end: + kfree(cmd); + + return err; +} + +static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev, + u16 cap_cmd_req, u16 *status) +{ + struct kvaser_usb_dev_card_data *card_data = &dev->card_data; + struct kvaser_cmd *cmd; + u32 value = 0; + u32 mask = 0; + u16 cap_cmd_res; + int err; + int i; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = CMD_GET_CAPABILITIES_REQ; + cmd->cap_req.cap_cmd = cpu_to_le16(cap_cmd_req); + + kvaser_usb_hydra_set_cmd_dest_he(cmd, card_data->hydra.sysdbg_he); + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + if (err) + goto end; + + err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CAPABILITIES_RESP, cmd); + if (err) + goto end; + + *status = le16_to_cpu(cmd->cap_res.status); + + if (*status != KVASER_USB_HYDRA_CAP_STAT_OK) + goto end; + + cap_cmd_res = le16_to_cpu(cmd->cap_res.cap_cmd); + switch (cap_cmd_res) { + case KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE: + case KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT: + case KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT: + value = le32_to_cpu(cmd->cap_res.value); + mask = le32_to_cpu(cmd->cap_res.mask); + break; + default: + dev_warn(&dev->intf->dev, "Unknown capability command %u\n", + cap_cmd_res); + break; + } + + for (i = 0; i < dev->nchannels; i++) { + if (BIT(i) & (value & mask)) { + switch (cap_cmd_res) { + case KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE: + card_data->ctrlmode_supported |= + CAN_CTRLMODE_LISTENONLY; + break; + case KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT: + card_data->capabilities |= + KVASER_USB_CAP_BERR_CAP; + break; + case KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT: + card_data->ctrlmode_supported |= + CAN_CTRLMODE_ONE_SHOT; + break; + } + } + } + +end: + kfree(cmd); + + return err; +} + +static void kvaser_usb_hydra_start_chip_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + if (completion_done(&priv->start_comp) && + netif_queue_stopped(priv->netdev)) { + netif_wake_queue(priv->netdev); + } else { + netif_start_queue(priv->netdev); + complete(&priv->start_comp); + } +} + +static void kvaser_usb_hydra_stop_chip_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + complete(&priv->stop_comp); +} + +static void kvaser_usb_hydra_flush_queue_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + complete(&priv->flush_comp); +} + +static void +kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv, + u8 bus_status, + const struct can_berr_counter *bec, + enum can_state *new_state) +{ + if (bus_status & KVASER_USB_HYDRA_BUS_BUS_OFF) { + *new_state = CAN_STATE_BUS_OFF; + } else if (bus_status & KVASER_USB_HYDRA_BUS_ERR_PASS) { + *new_state = CAN_STATE_ERROR_PASSIVE; + } else if (bus_status == KVASER_USB_HYDRA_BUS_ERR_ACT) { + if (bec->txerr >= 128 || bec->rxerr >= 128) { + netdev_warn(priv->netdev, + "ERR_ACTIVE but err tx=%u or rx=%u >=128\n", + bec->txerr, bec->rxerr); + *new_state = CAN_STATE_ERROR_PASSIVE; + } else if (bec->txerr >= 96 || bec->rxerr >= 96) { + *new_state = CAN_STATE_ERROR_WARNING; + } else { + *new_state = CAN_STATE_ERROR_ACTIVE; + } + } +} + +static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv, + u8 bus_status, + const struct can_berr_counter *bec) +{ + struct net_device *netdev = priv->netdev; + struct can_frame *cf; + struct sk_buff *skb; + struct net_device_stats *stats; + enum can_state new_state, old_state; + + old_state = priv->can.state; + + kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, bec, + &new_state); + + if (new_state == old_state) + return; + + /* Ignore state change if previous state was STOPPED and the new state + * is BUS_OFF. Firmware always report this as BUS_OFF, since firmware + * does not distinguish between BUS_OFF and STOPPED. + */ + if (old_state == CAN_STATE_STOPPED && new_state == CAN_STATE_BUS_OFF) + return; + + skb = alloc_can_err_skb(netdev, &cf); + if (skb) { + enum can_state tx_state, rx_state; + + tx_state = (bec->txerr >= bec->rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + rx_state = (bec->txerr <= bec->rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + can_change_state(netdev, cf, tx_state, rx_state); + } + + if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) { + if (!priv->can.restart_ms) + kvaser_usb_hydra_send_simple_cmd_async + (priv, CMD_STOP_CHIP_REQ); + + can_bus_off(netdev); + } + + if (!skb) { + netdev_warn(netdev, "No memory left for err_skb\n"); + return; + } + + if (priv->can.restart_ms && + old_state >= CAN_STATE_BUS_OFF && + new_state < CAN_STATE_BUS_OFF) + priv->can.can_stats.restarts++; + + cf->data[6] = bec->txerr; + cf->data[7] = bec->rxerr; + + stats = &netdev->stats; + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); +} + +static void kvaser_usb_hydra_state_event(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + struct can_berr_counter bec; + u8 bus_status; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + bus_status = cmd->chip_state_event.bus_status; + bec.txerr = cmd->chip_state_event.tx_err_counter; + bec.rxerr = cmd->chip_state_event.rx_err_counter; + + kvaser_usb_hydra_update_state(priv, bus_status, &bec); + priv->bec.txerr = bec.txerr; + priv->bec.rxerr = bec.rxerr; +} + +static void kvaser_usb_hydra_error_event_parameter(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + /* info1 will contain the offending cmd_no */ + switch (le16_to_cpu(cmd->error_event.info1)) { + case CMD_START_CHIP_REQ: + dev_warn(&dev->intf->dev, + "CMD_START_CHIP_REQ error in parameter\n"); + break; + + case CMD_STOP_CHIP_REQ: + dev_warn(&dev->intf->dev, + "CMD_STOP_CHIP_REQ error in parameter\n"); + break; + + case CMD_FLUSH_QUEUE: + dev_warn(&dev->intf->dev, + "CMD_FLUSH_QUEUE error in parameter\n"); + break; + + case CMD_SET_BUSPARAMS_REQ: + dev_warn(&dev->intf->dev, + "Set bittiming failed. Error in parameter\n"); + break; + + case CMD_SET_BUSPARAMS_FD_REQ: + dev_warn(&dev->intf->dev, + "Set data bittiming failed. Error in parameter\n"); + break; + + default: + dev_warn(&dev->intf->dev, + "Unhandled parameter error event cmd_no (%u)\n", + le16_to_cpu(cmd->error_event.info1)); + break; + } +} + +static void kvaser_usb_hydra_error_event(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + switch (cmd->error_event.error_code) { + case KVASER_USB_HYDRA_ERROR_EVENT_PARAM: + kvaser_usb_hydra_error_event_parameter(dev, cmd); + break; + + case KVASER_USB_HYDRA_ERROR_EVENT_CAN: + /* Wrong channel mapping?! This should never happen! + * info1 will contain the offending cmd_no + */ + dev_err(&dev->intf->dev, + "Received CAN error event for cmd_no (%u)\n", + le16_to_cpu(cmd->error_event.info1)); + break; + + default: + dev_warn(&dev->intf->dev, + "Unhandled error event (%d)\n", + cmd->error_event.error_code); + break; + } +} + +static void +kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv, + const struct kvaser_err_frame_data *err_frame_data, + ktime_t hwtstamp) +{ + struct net_device *netdev = priv->netdev; + struct net_device_stats *stats = &netdev->stats; + struct can_frame *cf; + struct sk_buff *skb; + struct skb_shared_hwtstamps *shhwtstamps; + struct can_berr_counter bec; + enum can_state new_state, old_state; + u8 bus_status; + + priv->can.can_stats.bus_error++; + stats->rx_errors++; + + bus_status = err_frame_data->bus_status; + bec.txerr = err_frame_data->tx_err_counter; + bec.rxerr = err_frame_data->rx_err_counter; + + old_state = priv->can.state; + kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, &bec, + &new_state); + + skb = alloc_can_err_skb(netdev, &cf); + + if (new_state != old_state) { + if (skb) { + enum can_state tx_state, rx_state; + + tx_state = (bec.txerr >= bec.rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + rx_state = (bec.txerr <= bec.rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + + can_change_state(netdev, cf, tx_state, rx_state); + } + + if (new_state == CAN_STATE_BUS_OFF) { + if (!priv->can.restart_ms) + kvaser_usb_hydra_send_simple_cmd_async + (priv, CMD_STOP_CHIP_REQ); + + can_bus_off(netdev); + } + + if (priv->can.restart_ms && + old_state >= CAN_STATE_BUS_OFF && + new_state < CAN_STATE_BUS_OFF) + cf->can_id |= CAN_ERR_RESTARTED; + } + + if (!skb) { + stats->rx_dropped++; + netdev_warn(netdev, "No memory left for err_skb\n"); + return; + } + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = hwtstamp; + + cf->can_id |= CAN_ERR_BUSERROR; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + + priv->bec.txerr = bec.txerr; + priv->bec.rxerr = bec.rxerr; +} + +static void kvaser_usb_hydra_one_shot_fail(struct kvaser_usb_net_priv *priv, + const struct kvaser_cmd_ext *cmd) +{ + struct net_device *netdev = priv->netdev; + struct net_device_stats *stats = &netdev->stats; + struct can_frame *cf; + struct sk_buff *skb; + u32 flags; + + skb = alloc_can_err_skb(netdev, &cf); + if (!skb) { + stats->rx_dropped++; + netdev_warn(netdev, "No memory left for err_skb\n"); + return; + } + + cf->can_id |= CAN_ERR_BUSERROR; + flags = le32_to_cpu(cmd->tx_ack.flags); + + if (flags & KVASER_USB_HYDRA_CF_FLAG_OSM_NACK) + cf->can_id |= CAN_ERR_ACK; + if (flags & KVASER_USB_HYDRA_CF_FLAG_ABL) { + cf->can_id |= CAN_ERR_LOSTARB; + priv->can.can_stats.arbitration_lost++; + } + + stats->tx_errors++; + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); +} + +static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_tx_urb_context *context; + struct kvaser_usb_net_priv *priv; + unsigned long irq_flags; + bool one_shot_fail = false; + u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd); + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + if (!netif_device_present(priv->netdev)) + return; + + if (cmd->header.cmd_no == CMD_EXTENDED) { + struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd; + u32 flags = le32_to_cpu(cmd_ext->tx_ack.flags); + + if (flags & (KVASER_USB_HYDRA_CF_FLAG_OSM_NACK | + KVASER_USB_HYDRA_CF_FLAG_ABL)) { + kvaser_usb_hydra_one_shot_fail(priv, cmd_ext); + one_shot_fail = true; + } + } + + context = &priv->tx_contexts[transid % dev->max_tx_urbs]; + if (!one_shot_fail) { + struct net_device_stats *stats = &priv->netdev->stats; + + stats->tx_packets++; + stats->tx_bytes += can_dlc2len(context->dlc); + } + + spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags); + + can_get_echo_skb(priv->netdev, context->echo_index); + context->echo_index = dev->max_tx_urbs; + --priv->active_tx_contexts; + netif_wake_queue(priv->netdev); + + spin_unlock_irqrestore(&priv->tx_contexts_lock, irq_flags); +} + +static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv = NULL; + struct can_frame *cf; + struct sk_buff *skb; + struct skb_shared_hwtstamps *shhwtstamps; + struct net_device_stats *stats; + u8 flags; + ktime_t hwtstamp; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + stats = &priv->netdev->stats; + + flags = cmd->rx_can.flags; + hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, cmd); + + if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) { + kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data, + hwtstamp); + return; + } + + skb = alloc_can_skb(priv->netdev, &cf); + if (!skb) { + stats->rx_dropped++; + return; + } + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = hwtstamp; + + cf->can_id = le32_to_cpu(cmd->rx_can.id); + + if (cf->can_id & KVASER_USB_HYDRA_EXTENDED_FRAME_ID) { + cf->can_id &= CAN_EFF_MASK; + cf->can_id |= CAN_EFF_FLAG; + } else { + cf->can_id &= CAN_SFF_MASK; + } + + if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN) + kvaser_usb_can_rx_over_error(priv->netdev); + + cf->can_dlc = get_can_dlc(cmd->rx_can.dlc); + + if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME) + cf->can_id |= CAN_RTR_FLAG; + else + memcpy(cf->data, cmd->rx_can.data, cf->can_dlc); + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); +} + +static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev, + const struct kvaser_cmd_ext *cmd) +{ + struct kvaser_cmd *std_cmd = (struct kvaser_cmd *)cmd; + struct kvaser_usb_net_priv *priv; + struct canfd_frame *cf; + struct sk_buff *skb; + struct skb_shared_hwtstamps *shhwtstamps; + struct net_device_stats *stats; + u32 flags; + u8 dlc; + u32 kcan_header; + ktime_t hwtstamp; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, std_cmd); + if (!priv) + return; + + stats = &priv->netdev->stats; + + kcan_header = le32_to_cpu(cmd->rx_can.kcan_header); + dlc = (kcan_header & KVASER_USB_KCAN_DATA_DLC_MASK) >> + KVASER_USB_KCAN_DATA_DLC_SHIFT; + + flags = le32_to_cpu(cmd->rx_can.flags); + hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, std_cmd); + + if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) { + kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data, + hwtstamp); + return; + } + + if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) + skb = alloc_canfd_skb(priv->netdev, &cf); + else + skb = alloc_can_skb(priv->netdev, (struct can_frame **)&cf); + + if (!skb) { + stats->rx_dropped++; + return; + } + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = hwtstamp; + + cf->can_id = le32_to_cpu(cmd->rx_can.id); + + if (flags & KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID) { + cf->can_id &= CAN_EFF_MASK; + cf->can_id |= CAN_EFF_FLAG; + } else { + cf->can_id &= CAN_SFF_MASK; + } + + if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN) + kvaser_usb_can_rx_over_error(priv->netdev); + + if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) { + cf->len = can_dlc2len(get_canfd_dlc(dlc)); + if (flags & KVASER_USB_HYDRA_CF_FLAG_BRS) + cf->flags |= CANFD_BRS; + if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI) + cf->flags |= CANFD_ESI; + } else { + cf->len = get_can_dlc(dlc); + } + + if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME) + cf->can_id |= CAN_RTR_FLAG; + else + memcpy(cf->data, cmd->rx_can.kcan_payload, cf->len); + + stats->rx_packets++; + stats->rx_bytes += cf->len; + netif_rx(skb); +} + +static void kvaser_usb_hydra_handle_cmd_std(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + switch (cmd->header.cmd_no) { + case CMD_START_CHIP_RESP: + kvaser_usb_hydra_start_chip_reply(dev, cmd); + break; + + case CMD_STOP_CHIP_RESP: + kvaser_usb_hydra_stop_chip_reply(dev, cmd); + break; + + case CMD_FLUSH_QUEUE_RESP: + kvaser_usb_hydra_flush_queue_reply(dev, cmd); + break; + + case CMD_CHIP_STATE_EVENT: + kvaser_usb_hydra_state_event(dev, cmd); + break; + + case CMD_ERROR_EVENT: + kvaser_usb_hydra_error_event(dev, cmd); + break; + + case CMD_TX_ACKNOWLEDGE: + kvaser_usb_hydra_tx_acknowledge(dev, cmd); + break; + + case CMD_RX_MESSAGE: + kvaser_usb_hydra_rx_msg_std(dev, cmd); + break; + + /* Ignored commands */ + case CMD_SET_BUSPARAMS_RESP: + case CMD_SET_BUSPARAMS_FD_RESP: + break; + + default: + dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", + cmd->header.cmd_no); + break; + } +} + +static void kvaser_usb_hydra_handle_cmd_ext(const struct kvaser_usb *dev, + const struct kvaser_cmd_ext *cmd) +{ + switch (cmd->cmd_no_ext) { + case CMD_TX_ACKNOWLEDGE_FD: + kvaser_usb_hydra_tx_acknowledge(dev, (struct kvaser_cmd *)cmd); + break; + + case CMD_RX_MESSAGE_FD: + kvaser_usb_hydra_rx_msg_ext(dev, cmd); + break; + + default: + dev_warn(&dev->intf->dev, "Unhandled extended command (%d)\n", + cmd->header.cmd_no); + break; + } +} + +static void kvaser_usb_hydra_handle_cmd(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + if (cmd->header.cmd_no == CMD_EXTENDED) + kvaser_usb_hydra_handle_cmd_ext + (dev, (struct kvaser_cmd_ext *)cmd); + else + kvaser_usb_hydra_handle_cmd_std(dev, cmd); +} + +static void * +kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv, + const struct sk_buff *skb, int *frame_len, + int *cmd_len, u16 transid) +{ + struct kvaser_usb *dev = priv->dev; + struct kvaser_cmd_ext *cmd; + struct canfd_frame *cf = (struct canfd_frame *)skb->data; + u8 dlc = can_len2dlc(cf->len); + u8 nbr_of_bytes = cf->len; + u32 flags; + u32 id; + u32 kcan_id; + u32 kcan_header; + + *frame_len = nbr_of_bytes; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd_ext), GFP_ATOMIC); + if (!cmd) + return NULL; + + kvaser_usb_hydra_set_cmd_dest_he + ((struct kvaser_cmd *)cmd, + dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid((struct kvaser_cmd *)cmd, transid); + + cmd->header.cmd_no = CMD_EXTENDED; + cmd->cmd_no_ext = CMD_TX_CAN_MESSAGE_FD; + + *cmd_len = ALIGN(sizeof(struct kvaser_cmd_ext) - + sizeof(cmd->tx_can.kcan_payload) + nbr_of_bytes, + 8); + + cmd->len = cpu_to_le16(*cmd_len); + + cmd->tx_can.databytes = nbr_of_bytes; + cmd->tx_can.dlc = dlc; + + if (cf->can_id & CAN_EFF_FLAG) { + id = cf->can_id & CAN_EFF_MASK; + flags = KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID; + kcan_id = (cf->can_id & CAN_EFF_MASK) | + KVASER_USB_KCAN_DATA_IDE | KVASER_USB_KCAN_DATA_SRR; + } else { + id = cf->can_id & CAN_SFF_MASK; + flags = 0; + kcan_id = cf->can_id & CAN_SFF_MASK; + } + + if (cf->can_id & CAN_ERR_FLAG) + flags |= KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME; + + kcan_header = ((dlc << KVASER_USB_KCAN_DATA_DLC_SHIFT) & + KVASER_USB_KCAN_DATA_DLC_MASK) | + KVASER_USB_KCAN_DATA_AREQ | + (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT ? + KVASER_USB_KCAN_DATA_OSM : 0); + + if (can_is_canfd_skb(skb)) { + kcan_header |= KVASER_USB_KCAN_DATA_FDF | + (cf->flags & CANFD_BRS ? + KVASER_USB_KCAN_DATA_BRS : 0); + } else { + if (cf->can_id & CAN_RTR_FLAG) { + kcan_id |= KVASER_USB_KCAN_DATA_RTR; + cmd->tx_can.databytes = 0; + flags |= KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME; + } + } + + cmd->tx_can.kcan_id = cpu_to_le32(kcan_id); + cmd->tx_can.id = cpu_to_le32(id); + cmd->tx_can.flags = cpu_to_le32(flags); + cmd->tx_can.kcan_header = cpu_to_le32(kcan_header); + + memcpy(cmd->tx_can.kcan_payload, cf->data, nbr_of_bytes); + + return cmd; +} + +static void * +kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv, + const struct sk_buff *skb, int *frame_len, + int *cmd_len, u16 transid) +{ + struct kvaser_usb *dev = priv->dev; + struct kvaser_cmd *cmd; + struct can_frame *cf = (struct can_frame *)skb->data; + u32 flags; + u32 id; + + *frame_len = cf->can_dlc; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC); + if (!cmd) + return NULL; + + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid(cmd, transid); + + cmd->header.cmd_no = CMD_TX_CAN_MESSAGE; + + *cmd_len = ALIGN(sizeof(struct kvaser_cmd), 8); + + if (cf->can_id & CAN_EFF_FLAG) { + id = (cf->can_id & CAN_EFF_MASK); + id |= KVASER_USB_HYDRA_EXTENDED_FRAME_ID; + } else { + id = cf->can_id & CAN_SFF_MASK; + } + + cmd->tx_can.dlc = cf->can_dlc; + + flags = (cf->can_id & CAN_EFF_FLAG ? + KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID : 0); + + if (cf->can_id & CAN_RTR_FLAG) + flags |= KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME; + + flags |= (cf->can_id & CAN_ERR_FLAG ? + KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME : 0); + + cmd->tx_can.id = cpu_to_le32(id); + cmd->tx_can.flags = flags; + + memcpy(cmd->tx_can.data, cf->data, *frame_len); + + return cmd; +} + +static int kvaser_usb_hydra_set_mode(struct net_device *netdev, + enum can_mode mode) +{ + int err = 0; + + switch (mode) { + case CAN_MODE_START: + /* CAN controller automatically recovers from BUS_OFF */ + break; + default: + err = -EOPNOTSUPP; + } + + return err; +} + +static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev) +{ + struct kvaser_cmd *cmd; + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct can_bittiming *bt = &priv->can.bittiming; + struct kvaser_usb *dev = priv->dev; + int tseg1 = bt->prop_seg + bt->phase_seg1; + int tseg2 = bt->phase_seg2; + int sjw = bt->sjw; + int err; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ; + cmd->set_busparams_req.bitrate = cpu_to_le32(bt->bitrate); + cmd->set_busparams_req.sjw = (u8)sjw; + cmd->set_busparams_req.tseg1 = (u8)tseg1; + cmd->set_busparams_req.tseg2 = (u8)tseg2; + cmd->set_busparams_req.nsamples = 1; + + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + + kfree(cmd); + + return err; +} + +static int kvaser_usb_hydra_set_data_bittiming(struct net_device *netdev) +{ + struct kvaser_cmd *cmd; + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct can_bittiming *dbt = &priv->can.data_bittiming; + struct kvaser_usb *dev = priv->dev; + int tseg1 = dbt->prop_seg + dbt->phase_seg1; + int tseg2 = dbt->phase_seg2; + int sjw = dbt->sjw; + int err; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ; + cmd->set_busparams_req.bitrate_d = cpu_to_le32(dbt->bitrate); + cmd->set_busparams_req.sjw_d = (u8)sjw; + cmd->set_busparams_req.tseg1_d = (u8)tseg1; + cmd->set_busparams_req.tseg2_d = (u8)tseg2; + cmd->set_busparams_req.nsamples_d = 1; + + if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { + if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) + cmd->set_busparams_req.canfd_mode = + KVASER_USB_HYDRA_BUS_MODE_NONISO; + else + cmd->set_busparams_req.canfd_mode = + KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO; + } + + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + + kfree(cmd); + + return err; +} + +static int kvaser_usb_hydra_get_berr_counter(const struct net_device *netdev, + struct can_berr_counter *bec) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + int err; + + err = kvaser_usb_hydra_send_simple_cmd(priv->dev, + CMD_GET_CHIP_STATE_REQ, + priv->channel); + if (err) + return err; + + *bec = priv->bec; + + return 0; +} + +static int kvaser_usb_hydra_setup_endpoints(struct kvaser_usb *dev) +{ + const struct usb_host_interface *iface_desc; + struct usb_endpoint_descriptor *ep; + int i; + + iface_desc = &dev->intf->altsetting[0]; + + for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { + ep = &iface_desc->endpoint[i].desc; + + if (!dev->bulk_in && usb_endpoint_is_bulk_in(ep) && + ep->bEndpointAddress == KVASER_USB_HYDRA_BULK_EP_IN_ADDR) + dev->bulk_in = ep; + + if (!dev->bulk_out && usb_endpoint_is_bulk_out(ep) && + ep->bEndpointAddress == KVASER_USB_HYDRA_BULK_EP_OUT_ADDR) + dev->bulk_out = ep; + + if (dev->bulk_in && dev->bulk_out) + return 0; + } + + return -ENODEV; +} + +static int kvaser_usb_hydra_init_card(struct kvaser_usb *dev) +{ + int err; + unsigned int i; + struct kvaser_usb_dev_card_data_hydra *card_data = + &dev->card_data.hydra; + + card_data->transid = KVASER_USB_HYDRA_MIN_TRANSID; + spin_lock_init(&card_data->transid_lock); + + memset(card_data->usb_rx_leftover, 0, KVASER_USB_HYDRA_MAX_CMD_LEN); + card_data->usb_rx_leftover_len = 0; + spin_lock_init(&card_data->usb_rx_leftover_lock); + + memset(card_data->channel_to_he, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL, + sizeof(card_data->channel_to_he)); + card_data->sysdbg_he = 0; + + for (i = 0; i < KVASER_USB_MAX_NET_DEVICES; i++) { + err = kvaser_usb_hydra_map_channel + (dev, + (KVASER_USB_HYDRA_TRANSID_CANHE | i), + i, "CAN"); + if (err) { + dev_err(&dev->intf->dev, + "CMD_MAP_CHANNEL_REQ failed for CAN%u\n", i); + return err; + } + } + + err = kvaser_usb_hydra_map_channel(dev, KVASER_USB_HYDRA_TRANSID_SYSDBG, + 0, "SYSDBG"); + if (err) { + dev_err(&dev->intf->dev, + "CMD_MAP_CHANNEL_REQ failed for SYSDBG\n"); + return err; + } + + return 0; +} + +static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev) +{ + struct kvaser_cmd cmd; + int err; + + err = kvaser_usb_hydra_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO_REQ, + -1); + if (err) + return err; + + memset(&cmd, 0, sizeof(struct kvaser_cmd)); + err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_RESP, &cmd); + if (err) + return err; + + dev->max_tx_urbs = min_t(unsigned int, KVASER_USB_MAX_TX_URBS, + le16_to_cpu(cmd.sw_info.max_outstanding_tx)); + + return 0; +} + +static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) +{ + struct kvaser_cmd *cmd; + int err; + u32 flags; + struct kvaser_usb_dev_card_data *card_data = &dev->card_data; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = CMD_GET_SOFTWARE_DETAILS_REQ; + cmd->sw_detail_req.use_ext_cmd = 1; + kvaser_usb_hydra_set_cmd_dest_he + (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL); + + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + if (err) + goto end; + + err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_SOFTWARE_DETAILS_RESP, + cmd); + if (err) + goto end; + + dev->fw_version = le32_to_cpu(cmd->sw_detail_res.sw_version); + flags = le32_to_cpu(cmd->sw_detail_res.sw_flags); + + if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BAD) { + dev_err(&dev->intf->dev, + "Bad firmware, device refuse to run!\n"); + err = -EINVAL; + goto end; + } + + if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BETA) + dev_info(&dev->intf->dev, "Beta firmware in use\n"); + + if (flags & KVASER_USB_HYDRA_SW_FLAG_EXT_CAP) + card_data->capabilities |= KVASER_USB_CAP_EXT_CAP; + + if (flags & KVASER_USB_HYDRA_SW_FLAG_EXT_CMD) + card_data->capabilities |= KVASER_USB_HYDRA_CAP_EXT_CMD; + + if (flags & KVASER_USB_HYDRA_SW_FLAG_CANFD) + card_data->ctrlmode_supported |= CAN_CTRLMODE_FD; + + if (flags & KVASER_USB_HYDRA_SW_FLAG_NONISO) + card_data->ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO; + + if (flags & KVASER_USB_HYDRA_SW_FLAG_FREQ_80M) + dev->cfg = &kvaser_usb_hydra_dev_cfg_kcan; + else + dev->cfg = &kvaser_usb_hydra_dev_cfg_flexc; + +end: + kfree(cmd); + + return err; +} + +static int kvaser_usb_hydra_get_card_info(struct kvaser_usb *dev) +{ + struct kvaser_cmd cmd; + int err; + + err = kvaser_usb_hydra_send_simple_cmd(dev, CMD_GET_CARD_INFO_REQ, -1); + if (err) + return err; + + memset(&cmd, 0, sizeof(struct kvaser_cmd)); + err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CARD_INFO_RESP, &cmd); + if (err) + return err; + + dev->nchannels = cmd.card_info.nchannels; + if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES) + return -EINVAL; + + return 0; +} + +static int kvaser_usb_hydra_get_capabilities(struct kvaser_usb *dev) +{ + int err; + u16 status; + + if (!(dev->card_data.capabilities & KVASER_USB_CAP_EXT_CAP)) { + dev_info(&dev->intf->dev, + "No extended capability support. Upgrade your device.\n"); + return 0; + } + + err = kvaser_usb_hydra_get_single_capability + (dev, + KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE, + &status); + if (err) + return err; + if (status) + dev_info(&dev->intf->dev, + "KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE failed %u\n", + status); + + err = kvaser_usb_hydra_get_single_capability + (dev, + KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT, + &status); + if (err) + return err; + if (status) + dev_info(&dev->intf->dev, + "KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT failed %u\n", + status); + + err = kvaser_usb_hydra_get_single_capability + (dev, KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT, + &status); + if (err) + return err; + if (status) + dev_info(&dev->intf->dev, + "KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT failed %u\n", + status); + + return 0; +} + +static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) +{ + struct kvaser_usb *dev = priv->dev; + struct kvaser_cmd *cmd; + int err; + + if ((priv->can.ctrlmode & + (CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO)) == + CAN_CTRLMODE_FD_NON_ISO) { + netdev_warn(priv->netdev, + "CTRLMODE_FD shall be on if CTRLMODE_FD_NON_ISO is on\n"); + return -EINVAL; + } + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = CMD_SET_DRIVERMODE_REQ; + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_LISTEN; + else + cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_NORMAL; + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + kfree(cmd); + + return err; +} + +static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv) +{ + int err; + + init_completion(&priv->start_comp); + + err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ, + priv->channel); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->start_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return 0; +} + +static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv) +{ + int err; + + init_completion(&priv->stop_comp); + + /* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT + * see comment in kvaser_usb_hydra_update_state() + */ + priv->can.state = CAN_STATE_STOPPED; + + err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_STOP_CHIP_REQ, + priv->channel); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->stop_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return 0; +} + +static int kvaser_usb_hydra_flush_queue(struct kvaser_usb_net_priv *priv) +{ + int err; + + init_completion(&priv->flush_comp); + + err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_FLUSH_QUEUE, + priv->channel); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->flush_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return 0; +} + +/* A single extended hydra command can be transmitted in multiple transfers + * We have to buffer partial hydra commands, and handle them on next callback. + */ +static void kvaser_usb_hydra_read_bulk_callback(struct kvaser_usb *dev, + void *buf, int len) +{ + unsigned long irq_flags; + struct kvaser_cmd *cmd; + int pos = 0; + size_t cmd_len; + struct kvaser_usb_dev_card_data_hydra *card_data = + &dev->card_data.hydra; + int usb_rx_leftover_len; + spinlock_t *usb_rx_leftover_lock = &card_data->usb_rx_leftover_lock; + + spin_lock_irqsave(usb_rx_leftover_lock, irq_flags); + usb_rx_leftover_len = card_data->usb_rx_leftover_len; + if (usb_rx_leftover_len) { + int remaining_bytes; + + cmd = (struct kvaser_cmd *)card_data->usb_rx_leftover; + + cmd_len = kvaser_usb_hydra_cmd_size(cmd); + + remaining_bytes = min_t(unsigned int, len, + cmd_len - usb_rx_leftover_len); + /* Make sure we do not overflow usb_rx_leftover */ + if (remaining_bytes + usb_rx_leftover_len > + KVASER_USB_HYDRA_MAX_CMD_LEN) { + dev_err(&dev->intf->dev, "Format error\n"); + spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags); + return; + } + + memcpy(card_data->usb_rx_leftover + usb_rx_leftover_len, buf, + remaining_bytes); + pos += remaining_bytes; + + if (remaining_bytes + usb_rx_leftover_len == cmd_len) { + kvaser_usb_hydra_handle_cmd(dev, cmd); + usb_rx_leftover_len = 0; + } else { + /* Command still not complete */ + usb_rx_leftover_len += remaining_bytes; + } + card_data->usb_rx_leftover_len = usb_rx_leftover_len; + } + spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags); + + while (pos < len) { + cmd = buf + pos; + + cmd_len = kvaser_usb_hydra_cmd_size(cmd); + + if (pos + cmd_len > len) { + /* We got first part of a command */ + int leftover_bytes; + + leftover_bytes = len - pos; + /* Make sure we do not overflow usb_rx_leftover */ + if (leftover_bytes > KVASER_USB_HYDRA_MAX_CMD_LEN) { + dev_err(&dev->intf->dev, "Format error\n"); + return; + } + spin_lock_irqsave(usb_rx_leftover_lock, irq_flags); + memcpy(card_data->usb_rx_leftover, buf + pos, + leftover_bytes); + card_data->usb_rx_leftover_len = leftover_bytes; + spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags); + break; + } + + kvaser_usb_hydra_handle_cmd(dev, cmd); + pos += cmd_len; + } +} + +static void * +kvaser_usb_hydra_frame_to_cmd(const struct kvaser_usb_net_priv *priv, + const struct sk_buff *skb, int *frame_len, + int *cmd_len, u16 transid) +{ + void *buf; + + if (priv->dev->card_data.capabilities & KVASER_USB_HYDRA_CAP_EXT_CMD) + buf = kvaser_usb_hydra_frame_to_cmd_ext(priv, skb, frame_len, + cmd_len, transid); + else + buf = kvaser_usb_hydra_frame_to_cmd_std(priv, skb, frame_len, + cmd_len, transid); + + return buf; +} + +const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops = { + .dev_set_mode = kvaser_usb_hydra_set_mode, + .dev_set_bittiming = kvaser_usb_hydra_set_bittiming, + .dev_set_data_bittiming = kvaser_usb_hydra_set_data_bittiming, + .dev_get_berr_counter = kvaser_usb_hydra_get_berr_counter, + .dev_setup_endpoints = kvaser_usb_hydra_setup_endpoints, + .dev_init_card = kvaser_usb_hydra_init_card, + .dev_get_software_info = kvaser_usb_hydra_get_software_info, + .dev_get_software_details = kvaser_usb_hydra_get_software_details, + .dev_get_card_info = kvaser_usb_hydra_get_card_info, + .dev_get_capabilities = kvaser_usb_hydra_get_capabilities, + .dev_set_opt_mode = kvaser_usb_hydra_set_opt_mode, + .dev_start_chip = kvaser_usb_hydra_start_chip, + .dev_stop_chip = kvaser_usb_hydra_stop_chip, + .dev_reset_chip = NULL, + .dev_flush_queue = kvaser_usb_hydra_flush_queue, + .dev_read_bulk_callback = kvaser_usb_hydra_read_bulk_callback, + .dev_frame_to_cmd = kvaser_usb_hydra_frame_to_cmd, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan = { + .clock = { + .freq = 80000000, + }, + .timestamp_freq = 80, + .bittiming_const = &kvaser_usb_hydra_kcan_bittiming_c, + .data_bittiming_const = &kvaser_usb_hydra_kcan_bittiming_c, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc = { + .clock = { + .freq = 24000000, + }, + .timestamp_freq = 1, + .bittiming_const = &kvaser_usb_hydra_flexc_bittiming_c, +}; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c new file mode 100644 index 000000000000..07d2f3aa2c02 --- /dev/null +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -0,0 +1,1358 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Parts of this driver are based on the following: + * - Kvaser linux leaf driver (version 4.78) + * - CAN driver for esd CAN-USB/2 + * - Kvaser linux usbcanII driver (version 5.3) + * + * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved. + * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh + * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be> + * Copyright (C) 2015 Valeo S.A. + */ + +#include <linux/completion.h> +#include <linux/device.h> +#include <linux/gfp.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/usb.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> +#include <linux/can/netlink.h> + +#include "kvaser_usb.h" + +/* Forward declaration */ +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg; + +#define CAN_USB_CLOCK 8000000 +#define MAX_USBCAN_NET_DEVICES 2 + +/* Command header size */ +#define CMD_HEADER_LEN 2 + +/* Kvaser CAN message flags */ +#define MSG_FLAG_ERROR_FRAME BIT(0) +#define MSG_FLAG_OVERRUN BIT(1) +#define MSG_FLAG_NERR BIT(2) +#define MSG_FLAG_WAKEUP BIT(3) +#define MSG_FLAG_REMOTE_FRAME BIT(4) +#define MSG_FLAG_RESERVED BIT(5) +#define MSG_FLAG_TX_ACK BIT(6) +#define MSG_FLAG_TX_REQUEST BIT(7) + +/* CAN states (M16C CxSTRH register) */ +#define M16C_STATE_BUS_RESET BIT(0) +#define M16C_STATE_BUS_ERROR BIT(4) +#define M16C_STATE_BUS_PASSIVE BIT(5) +#define M16C_STATE_BUS_OFF BIT(6) + +/* Leaf/usbcan command ids */ +#define CMD_RX_STD_MESSAGE 12 +#define CMD_TX_STD_MESSAGE 13 +#define CMD_RX_EXT_MESSAGE 14 +#define CMD_TX_EXT_MESSAGE 15 +#define CMD_SET_BUS_PARAMS 16 +#define CMD_CHIP_STATE_EVENT 20 +#define CMD_SET_CTRL_MODE 21 +#define CMD_RESET_CHIP 24 +#define CMD_START_CHIP 26 +#define CMD_START_CHIP_REPLY 27 +#define CMD_STOP_CHIP 28 +#define CMD_STOP_CHIP_REPLY 29 + +#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT 33 + +#define CMD_GET_CARD_INFO 34 +#define CMD_GET_CARD_INFO_REPLY 35 +#define CMD_GET_SOFTWARE_INFO 38 +#define CMD_GET_SOFTWARE_INFO_REPLY 39 +#define CMD_FLUSH_QUEUE 48 +#define CMD_TX_ACKNOWLEDGE 50 +#define CMD_CAN_ERROR_EVENT 51 +#define CMD_FLUSH_QUEUE_REPLY 68 + +#define CMD_LEAF_LOG_MESSAGE 106 + +/* error factors */ +#define M16C_EF_ACKE BIT(0) +#define M16C_EF_CRCE BIT(1) +#define M16C_EF_FORME BIT(2) +#define M16C_EF_STFE BIT(3) +#define M16C_EF_BITE0 BIT(4) +#define M16C_EF_BITE1 BIT(5) +#define M16C_EF_RCVE BIT(6) +#define M16C_EF_TRE BIT(7) + +/* Only Leaf-based devices can report M16C error factors, + * thus define our own error status flags for USBCANII + */ +#define USBCAN_ERROR_STATE_NONE 0 +#define USBCAN_ERROR_STATE_TX_ERROR BIT(0) +#define USBCAN_ERROR_STATE_RX_ERROR BIT(1) +#define USBCAN_ERROR_STATE_BUSERROR BIT(2) + +/* bittiming parameters */ +#define KVASER_USB_TSEG1_MIN 1 +#define KVASER_USB_TSEG1_MAX 16 +#define KVASER_USB_TSEG2_MIN 1 +#define KVASER_USB_TSEG2_MAX 8 +#define KVASER_USB_SJW_MAX 4 +#define KVASER_USB_BRP_MIN 1 +#define KVASER_USB_BRP_MAX 64 +#define KVASER_USB_BRP_INC 1 + +/* ctrl modes */ +#define KVASER_CTRL_MODE_NORMAL 1 +#define KVASER_CTRL_MODE_SILENT 2 +#define KVASER_CTRL_MODE_SELFRECEPTION 3 +#define KVASER_CTRL_MODE_OFF 4 + +/* Extended CAN identifier flag */ +#define KVASER_EXTENDED_FRAME BIT(31) + +struct kvaser_cmd_simple { + u8 tid; + u8 channel; +} __packed; + +struct kvaser_cmd_cardinfo { + u8 tid; + u8 nchannels; + __le32 serial_number; + __le32 padding0; + __le32 clock_resolution; + __le32 mfgdate; + u8 ean[8]; + u8 hw_revision; + union { + struct { + u8 usb_hs_mode; + } __packed leaf1; + struct { + u8 padding; + } __packed usbcan1; + } __packed; + __le16 padding1; +} __packed; + +struct leaf_cmd_softinfo { + u8 tid; + u8 padding0; + __le32 sw_options; + __le32 fw_version; + __le16 max_outstanding_tx; + __le16 padding1[9]; +} __packed; + +struct usbcan_cmd_softinfo { + u8 tid; + u8 fw_name[5]; + __le16 max_outstanding_tx; + u8 padding[6]; + __le32 fw_version; + __le16 checksum; + __le16 sw_options; +} __packed; + +struct kvaser_cmd_busparams { + u8 tid; + u8 channel; + __le32 bitrate; + u8 tseg1; + u8 tseg2; + u8 sjw; + u8 no_samp; +} __packed; + +struct kvaser_cmd_tx_can { + u8 channel; + u8 tid; + u8 data[14]; + union { + struct { + u8 padding; + u8 flags; + } __packed leaf; + struct { + u8 flags; + u8 padding; + } __packed usbcan; + } __packed; +} __packed; + +struct kvaser_cmd_rx_can_header { + u8 channel; + u8 flag; +} __packed; + +struct leaf_cmd_rx_can { + u8 channel; + u8 flag; + + __le16 time[3]; + u8 data[14]; +} __packed; + +struct usbcan_cmd_rx_can { + u8 channel; + u8 flag; + + u8 data[14]; + __le16 time; +} __packed; + +struct leaf_cmd_chip_state_event { + u8 tid; + u8 channel; + + __le16 time[3]; + u8 tx_errors_count; + u8 rx_errors_count; + + u8 status; + u8 padding[3]; +} __packed; + +struct usbcan_cmd_chip_state_event { + u8 tid; + u8 channel; + + u8 tx_errors_count; + u8 rx_errors_count; + __le16 time; + + u8 status; + u8 padding[3]; +} __packed; + +struct kvaser_cmd_tx_acknowledge_header { + u8 channel; + u8 tid; +} __packed; + +struct leaf_cmd_error_event { + u8 tid; + u8 flags; + __le16 time[3]; + u8 channel; + u8 padding; + u8 tx_errors_count; + u8 rx_errors_count; + u8 status; + u8 error_factor; +} __packed; + +struct usbcan_cmd_error_event { + u8 tid; + u8 padding; + u8 tx_errors_count_ch0; + u8 rx_errors_count_ch0; + u8 tx_errors_count_ch1; + u8 rx_errors_count_ch1; + u8 status_ch0; + u8 status_ch1; + __le16 time; +} __packed; + +struct kvaser_cmd_ctrl_mode { + u8 tid; + u8 channel; + u8 ctrl_mode; + u8 padding[3]; +} __packed; + +struct kvaser_cmd_flush_queue { + u8 tid; + u8 channel; + u8 flags; + u8 padding[3]; +} __packed; + +struct leaf_cmd_log_message { + u8 channel; + u8 flags; + __le16 time[3]; + u8 dlc; + u8 time_offset; + __le32 id; + u8 data[8]; +} __packed; + +struct kvaser_cmd { + u8 len; + u8 id; + union { + struct kvaser_cmd_simple simple; + struct kvaser_cmd_cardinfo cardinfo; + struct kvaser_cmd_busparams busparams; + + struct kvaser_cmd_rx_can_header rx_can_header; + struct kvaser_cmd_tx_acknowledge_header tx_acknowledge_header; + + union { + struct leaf_cmd_softinfo softinfo; + struct leaf_cmd_rx_can rx_can; + struct leaf_cmd_chip_state_event chip_state_event; + struct leaf_cmd_error_event error_event; + struct leaf_cmd_log_message log_message; + } __packed leaf; + + union { + struct usbcan_cmd_softinfo softinfo; + struct usbcan_cmd_rx_can rx_can; + struct usbcan_cmd_chip_state_event chip_state_event; + struct usbcan_cmd_error_event error_event; + } __packed usbcan; + + struct kvaser_cmd_tx_can tx_can; + struct kvaser_cmd_ctrl_mode ctrl_mode; + struct kvaser_cmd_flush_queue flush_queue; + } u; +} __packed; + +/* Summary of a kvaser error event, for a unified Leaf/Usbcan error + * handling. Some discrepancies between the two families exist: + * + * - USBCAN firmware does not report M16C "error factors" + * - USBCAN controllers has difficulties reporting if the raised error + * event is for ch0 or ch1. They leave such arbitration to the OS + * driver by letting it compare error counters with previous values + * and decide the error event's channel. Thus for USBCAN, the channel + * field is only advisory. + */ +struct kvaser_usb_err_summary { + u8 channel, status, txerr, rxerr; + union { + struct { + u8 error_factor; + } leaf; + struct { + u8 other_ch_status; + u8 error_state; + } usbcan; + }; +}; + +static void * +kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv, + const struct sk_buff *skb, int *frame_len, + int *cmd_len, u16 transid) +{ + struct kvaser_usb *dev = priv->dev; + struct kvaser_cmd *cmd; + u8 *cmd_tx_can_flags = NULL; /* GCC */ + struct can_frame *cf = (struct can_frame *)skb->data; + + *frame_len = cf->can_dlc; + + cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC); + if (cmd) { + cmd->u.tx_can.tid = transid & 0xff; + cmd->len = *cmd_len = CMD_HEADER_LEN + + sizeof(struct kvaser_cmd_tx_can); + cmd->u.tx_can.channel = priv->channel; + + switch (dev->card_data.leaf.family) { + case KVASER_LEAF: + cmd_tx_can_flags = &cmd->u.tx_can.leaf.flags; + break; + case KVASER_USBCAN: + cmd_tx_can_flags = &cmd->u.tx_can.usbcan.flags; + break; + } + + *cmd_tx_can_flags = 0; + + if (cf->can_id & CAN_EFF_FLAG) { + cmd->id = CMD_TX_EXT_MESSAGE; + cmd->u.tx_can.data[0] = (cf->can_id >> 24) & 0x1f; + cmd->u.tx_can.data[1] = (cf->can_id >> 18) & 0x3f; + cmd->u.tx_can.data[2] = (cf->can_id >> 14) & 0x0f; + cmd->u.tx_can.data[3] = (cf->can_id >> 6) & 0xff; + cmd->u.tx_can.data[4] = cf->can_id & 0x3f; + } else { + cmd->id = CMD_TX_STD_MESSAGE; + cmd->u.tx_can.data[0] = (cf->can_id >> 6) & 0x1f; + cmd->u.tx_can.data[1] = cf->can_id & 0x3f; + } + + cmd->u.tx_can.data[5] = cf->can_dlc; + memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc); + + if (cf->can_id & CAN_RTR_FLAG) + *cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME; + } + return cmd; +} + +static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id, + struct kvaser_cmd *cmd) +{ + struct kvaser_cmd *tmp; + void *buf; + int actual_len; + int err; + int pos; + unsigned long to = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT); + + buf = kzalloc(KVASER_USB_RX_BUFFER_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + do { + err = kvaser_usb_recv_cmd(dev, buf, KVASER_USB_RX_BUFFER_SIZE, + &actual_len); + if (err < 0) + goto end; + + pos = 0; + while (pos <= actual_len - CMD_HEADER_LEN) { + tmp = buf + pos; + + /* Handle commands crossing the USB endpoint max packet + * size boundary. Check kvaser_usb_read_bulk_callback() + * for further details. + */ + if (tmp->len == 0) { + pos = round_up(pos, + le16_to_cpu + (dev->bulk_in->wMaxPacketSize)); + continue; + } + + if (pos + tmp->len > actual_len) { + dev_err_ratelimited(&dev->intf->dev, + "Format error\n"); + break; + } + + if (tmp->id == id) { + memcpy(cmd, tmp, tmp->len); + goto end; + } + + pos += tmp->len; + } + } while (time_before(jiffies, to)); + + err = -EINVAL; + +end: + kfree(buf); + + return err; +} + +static int kvaser_usb_leaf_send_simple_cmd(const struct kvaser_usb *dev, + u8 cmd_id, int channel) +{ + struct kvaser_cmd *cmd; + int rc; + + cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->id = cmd_id; + cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple); + cmd->u.simple.channel = channel; + cmd->u.simple.tid = 0xff; + + rc = kvaser_usb_send_cmd(dev, cmd, cmd->len); + + kfree(cmd); + return rc; +} + +static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev) +{ + struct kvaser_cmd cmd; + int err; + + err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO, 0); + if (err) + return err; + + err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_REPLY, &cmd); + if (err) + return err; + + switch (dev->card_data.leaf.family) { + case KVASER_LEAF: + dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version); + dev->max_tx_urbs = + le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx); + break; + case KVASER_USBCAN: + dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version); + dev->max_tx_urbs = + le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx); + break; + } + + return 0; +} + +static int kvaser_usb_leaf_get_software_info(struct kvaser_usb *dev) +{ + int err; + int retry = 3; + + /* On some x86 laptops, plugging a Kvaser device again after + * an unplug makes the firmware always ignore the very first + * command. For such a case, provide some room for retries + * instead of completely exiting the driver. + */ + do { + err = kvaser_usb_leaf_get_software_info_inner(dev); + } while (--retry && err == -ETIMEDOUT); + + return err; +} + +static int kvaser_usb_leaf_get_card_info(struct kvaser_usb *dev) +{ + struct kvaser_cmd cmd; + int err; + + err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_CARD_INFO, 0); + if (err) + return err; + + err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_CARD_INFO_REPLY, &cmd); + if (err) + return err; + + dev->nchannels = cmd.u.cardinfo.nchannels; + if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES || + (dev->card_data.leaf.family == KVASER_USBCAN && + dev->nchannels > MAX_USBCAN_NET_DEVICES)) + return -EINVAL; + + return 0; +} + +static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct net_device_stats *stats; + struct kvaser_usb_tx_urb_context *context; + struct kvaser_usb_net_priv *priv; + unsigned long flags; + u8 channel, tid; + + channel = cmd->u.tx_acknowledge_header.channel; + tid = cmd->u.tx_acknowledge_header.tid; + + if (channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + return; + } + + priv = dev->nets[channel]; + + if (!netif_device_present(priv->netdev)) + return; + + stats = &priv->netdev->stats; + + context = &priv->tx_contexts[tid % dev->max_tx_urbs]; + + /* Sometimes the state change doesn't come after a bus-off event */ + if (priv->can.restart_ms && priv->can.state >= CAN_STATE_BUS_OFF) { + struct sk_buff *skb; + struct can_frame *cf; + + skb = alloc_can_err_skb(priv->netdev, &cf); + if (skb) { + cf->can_id |= CAN_ERR_RESTARTED; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } else { + netdev_err(priv->netdev, + "No memory left for err_skb\n"); + } + + priv->can.can_stats.restarts++; + netif_carrier_on(priv->netdev); + + priv->can.state = CAN_STATE_ERROR_ACTIVE; + } + + stats->tx_packets++; + stats->tx_bytes += context->dlc; + + spin_lock_irqsave(&priv->tx_contexts_lock, flags); + + can_get_echo_skb(priv->netdev, context->echo_index); + context->echo_index = dev->max_tx_urbs; + --priv->active_tx_contexts; + netif_wake_queue(priv->netdev); + + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); +} + +static int kvaser_usb_leaf_simple_cmd_async(struct kvaser_usb_net_priv *priv, + u8 cmd_id) +{ + struct kvaser_cmd *cmd; + int err; + + cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC); + if (!cmd) + return -ENOMEM; + + cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple); + cmd->id = cmd_id; + cmd->u.simple.channel = priv->channel; + + err = kvaser_usb_send_cmd_async(priv, cmd, cmd->len); + if (err) + kfree(cmd); + + return err; +} + +static void +kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, + const struct kvaser_usb_err_summary *es, + struct can_frame *cf) +{ + struct kvaser_usb *dev = priv->dev; + struct net_device_stats *stats = &priv->netdev->stats; + enum can_state cur_state, new_state, tx_state, rx_state; + + netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status); + + new_state = priv->can.state; + cur_state = priv->can.state; + + if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { + new_state = CAN_STATE_BUS_OFF; + } else if (es->status & M16C_STATE_BUS_PASSIVE) { + new_state = CAN_STATE_ERROR_PASSIVE; + } else if (es->status & M16C_STATE_BUS_ERROR) { + /* Guard against spurious error events after a busoff */ + if (cur_state < CAN_STATE_BUS_OFF) { + if (es->txerr >= 128 || es->rxerr >= 128) + new_state = CAN_STATE_ERROR_PASSIVE; + else if (es->txerr >= 96 || es->rxerr >= 96) + new_state = CAN_STATE_ERROR_WARNING; + else if (cur_state > CAN_STATE_ERROR_ACTIVE) + new_state = CAN_STATE_ERROR_ACTIVE; + } + } + + if (!es->status) + new_state = CAN_STATE_ERROR_ACTIVE; + + if (new_state != cur_state) { + tx_state = (es->txerr >= es->rxerr) ? new_state : 0; + rx_state = (es->txerr <= es->rxerr) ? new_state : 0; + + can_change_state(priv->netdev, cf, tx_state, rx_state); + } + + if (priv->can.restart_ms && + cur_state >= CAN_STATE_BUS_OFF && + new_state < CAN_STATE_BUS_OFF) + priv->can.can_stats.restarts++; + + switch (dev->card_data.leaf.family) { + case KVASER_LEAF: + if (es->leaf.error_factor) { + priv->can.can_stats.bus_error++; + stats->rx_errors++; + } + break; + case KVASER_USBCAN: + if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR) + stats->tx_errors++; + if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR) + stats->rx_errors++; + if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) + priv->can.can_stats.bus_error++; + break; + } + + priv->bec.txerr = es->txerr; + priv->bec.rxerr = es->rxerr; +} + +static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, + const struct kvaser_usb_err_summary *es) +{ + struct can_frame *cf; + struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG, + .can_dlc = CAN_ERR_DLC }; + struct sk_buff *skb; + struct net_device_stats *stats; + struct kvaser_usb_net_priv *priv; + enum can_state old_state, new_state; + + if (es->channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", es->channel); + return; + } + + priv = dev->nets[es->channel]; + stats = &priv->netdev->stats; + + /* Update all of the CAN interface's state and error counters before + * trying any memory allocation that can actually fail with -ENOMEM. + * + * We send a temporary stack-allocated error CAN frame to + * can_change_state() for the very same reason. + * + * TODO: Split can_change_state() responsibility between updating the + * CAN interface's state and counters, and the setting up of CAN error + * frame ID and data to userspace. Remove stack allocation afterwards. + */ + old_state = priv->can.state; + kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf); + new_state = priv->can.state; + + skb = alloc_can_err_skb(priv->netdev, &cf); + if (!skb) { + stats->rx_dropped++; + return; + } + memcpy(cf, &tmp_cf, sizeof(*cf)); + + if (new_state != old_state) { + if (es->status & + (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { + if (!priv->can.restart_ms) + kvaser_usb_leaf_simple_cmd_async(priv, + CMD_STOP_CHIP); + netif_carrier_off(priv->netdev); + } + + if (priv->can.restart_ms && + old_state >= CAN_STATE_BUS_OFF && + new_state < CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_RESTARTED; + netif_carrier_on(priv->netdev); + } + } + + switch (dev->card_data.leaf.family) { + case KVASER_LEAF: + if (es->leaf.error_factor) { + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT; + + if (es->leaf.error_factor & M16C_EF_ACKE) + cf->data[3] = CAN_ERR_PROT_LOC_ACK; + if (es->leaf.error_factor & M16C_EF_CRCE) + cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ; + if (es->leaf.error_factor & M16C_EF_FORME) + cf->data[2] |= CAN_ERR_PROT_FORM; + if (es->leaf.error_factor & M16C_EF_STFE) + cf->data[2] |= CAN_ERR_PROT_STUFF; + if (es->leaf.error_factor & M16C_EF_BITE0) + cf->data[2] |= CAN_ERR_PROT_BIT0; + if (es->leaf.error_factor & M16C_EF_BITE1) + cf->data[2] |= CAN_ERR_PROT_BIT1; + if (es->leaf.error_factor & M16C_EF_TRE) + cf->data[2] |= CAN_ERR_PROT_TX; + } + break; + case KVASER_USBCAN: + if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) + cf->can_id |= CAN_ERR_BUSERROR; + break; + } + + cf->data[6] = es->txerr; + cf->data[7] = es->rxerr; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); +} + +/* For USBCAN, report error to userspace if the channels's errors counter + * has changed, or we're the only channel seeing a bus error state. + */ +static void +kvaser_usb_leaf_usbcan_conditionally_rx_error(const struct kvaser_usb *dev, + struct kvaser_usb_err_summary *es) +{ + struct kvaser_usb_net_priv *priv; + unsigned int channel; + bool report_error; + + channel = es->channel; + if (channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + return; + } + + priv = dev->nets[channel]; + report_error = false; + + if (es->txerr != priv->bec.txerr) { + es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR; + report_error = true; + } + if (es->rxerr != priv->bec.rxerr) { + es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR; + report_error = true; + } + if ((es->status & M16C_STATE_BUS_ERROR) && + !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) { + es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR; + report_error = true; + } + + if (report_error) + kvaser_usb_leaf_rx_error(dev, es); +} + +static void kvaser_usb_leaf_usbcan_rx_error(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_err_summary es = { }; + + switch (cmd->id) { + /* Sometimes errors are sent as unsolicited chip state events */ + case CMD_CHIP_STATE_EVENT: + es.channel = cmd->u.usbcan.chip_state_event.channel; + es.status = cmd->u.usbcan.chip_state_event.status; + es.txerr = cmd->u.usbcan.chip_state_event.tx_errors_count; + es.rxerr = cmd->u.usbcan.chip_state_event.rx_errors_count; + kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es); + break; + + case CMD_CAN_ERROR_EVENT: + es.channel = 0; + es.status = cmd->u.usbcan.error_event.status_ch0; + es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch0; + es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch0; + es.usbcan.other_ch_status = + cmd->u.usbcan.error_event.status_ch1; + kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es); + + /* The USBCAN firmware supports up to 2 channels. + * Now that ch0 was checked, check if ch1 has any errors. + */ + if (dev->nchannels == MAX_USBCAN_NET_DEVICES) { + es.channel = 1; + es.status = cmd->u.usbcan.error_event.status_ch1; + es.txerr = + cmd->u.usbcan.error_event.tx_errors_count_ch1; + es.rxerr = + cmd->u.usbcan.error_event.rx_errors_count_ch1; + es.usbcan.other_ch_status = + cmd->u.usbcan.error_event.status_ch0; + kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es); + } + break; + + default: + dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id); + } +} + +static void kvaser_usb_leaf_leaf_rx_error(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_err_summary es = { }; + + switch (cmd->id) { + case CMD_CAN_ERROR_EVENT: + es.channel = cmd->u.leaf.error_event.channel; + es.status = cmd->u.leaf.error_event.status; + es.txerr = cmd->u.leaf.error_event.tx_errors_count; + es.rxerr = cmd->u.leaf.error_event.rx_errors_count; + es.leaf.error_factor = cmd->u.leaf.error_event.error_factor; + break; + case CMD_LEAF_LOG_MESSAGE: + es.channel = cmd->u.leaf.log_message.channel; + es.status = cmd->u.leaf.log_message.data[0]; + es.txerr = cmd->u.leaf.log_message.data[2]; + es.rxerr = cmd->u.leaf.log_message.data[3]; + es.leaf.error_factor = cmd->u.leaf.log_message.data[1]; + break; + case CMD_CHIP_STATE_EVENT: + es.channel = cmd->u.leaf.chip_state_event.channel; + es.status = cmd->u.leaf.chip_state_event.status; + es.txerr = cmd->u.leaf.chip_state_event.tx_errors_count; + es.rxerr = cmd->u.leaf.chip_state_event.rx_errors_count; + es.leaf.error_factor = 0; + break; + default: + dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id); + return; + } + + kvaser_usb_leaf_rx_error(dev, &es); +} + +static void kvaser_usb_leaf_rx_can_err(const struct kvaser_usb_net_priv *priv, + const struct kvaser_cmd *cmd) +{ + if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | + MSG_FLAG_NERR)) { + struct net_device_stats *stats = &priv->netdev->stats; + + netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n", + cmd->u.rx_can_header.flag); + + stats->rx_errors++; + return; + } + + if (cmd->u.rx_can_header.flag & MSG_FLAG_OVERRUN) + kvaser_usb_can_rx_over_error(priv->netdev); +} + +static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + struct can_frame *cf; + struct sk_buff *skb; + struct net_device_stats *stats; + u8 channel = cmd->u.rx_can_header.channel; + const u8 *rx_data = NULL; /* GCC */ + + if (channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + return; + } + + priv = dev->nets[channel]; + stats = &priv->netdev->stats; + + if ((cmd->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) && + (dev->card_data.leaf.family == KVASER_LEAF && + cmd->id == CMD_LEAF_LOG_MESSAGE)) { + kvaser_usb_leaf_leaf_rx_error(dev, cmd); + return; + } else if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | + MSG_FLAG_NERR | + MSG_FLAG_OVERRUN)) { + kvaser_usb_leaf_rx_can_err(priv, cmd); + return; + } else if (cmd->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) { + netdev_warn(priv->netdev, + "Unhandled frame (flags: 0x%02x)\n", + cmd->u.rx_can_header.flag); + return; + } + + switch (dev->card_data.leaf.family) { + case KVASER_LEAF: + rx_data = cmd->u.leaf.rx_can.data; + break; + case KVASER_USBCAN: + rx_data = cmd->u.usbcan.rx_can.data; + break; + } + + skb = alloc_can_skb(priv->netdev, &cf); + if (!skb) { + stats->rx_dropped++; + return; + } + + if (dev->card_data.leaf.family == KVASER_LEAF && cmd->id == + CMD_LEAF_LOG_MESSAGE) { + cf->can_id = le32_to_cpu(cmd->u.leaf.log_message.id); + if (cf->can_id & KVASER_EXTENDED_FRAME) + cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG; + else + cf->can_id &= CAN_SFF_MASK; + + cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc); + + if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME) + cf->can_id |= CAN_RTR_FLAG; + else + memcpy(cf->data, &cmd->u.leaf.log_message.data, + cf->can_dlc); + } else { + cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f); + + if (cmd->id == CMD_RX_EXT_MESSAGE) { + cf->can_id <<= 18; + cf->can_id |= ((rx_data[2] & 0x0f) << 14) | + ((rx_data[3] & 0xff) << 6) | + (rx_data[4] & 0x3f); + cf->can_id |= CAN_EFF_FLAG; + } + + cf->can_dlc = get_can_dlc(rx_data[5]); + + if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME) + cf->can_id |= CAN_RTR_FLAG; + else + memcpy(cf->data, &rx_data[6], cf->can_dlc); + } + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); +} + +static void kvaser_usb_leaf_start_chip_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + u8 channel = cmd->u.simple.channel; + + if (channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + return; + } + + priv = dev->nets[channel]; + + if (completion_done(&priv->start_comp) && + netif_queue_stopped(priv->netdev)) { + netif_wake_queue(priv->netdev); + } else { + netif_start_queue(priv->netdev); + complete(&priv->start_comp); + } +} + +static void kvaser_usb_leaf_stop_chip_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + u8 channel = cmd->u.simple.channel; + + if (channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + return; + } + + priv = dev->nets[channel]; + + complete(&priv->stop_comp); +} + +static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + switch (cmd->id) { + case CMD_START_CHIP_REPLY: + kvaser_usb_leaf_start_chip_reply(dev, cmd); + break; + + case CMD_STOP_CHIP_REPLY: + kvaser_usb_leaf_stop_chip_reply(dev, cmd); + break; + + case CMD_RX_STD_MESSAGE: + case CMD_RX_EXT_MESSAGE: + kvaser_usb_leaf_rx_can_msg(dev, cmd); + break; + + case CMD_LEAF_LOG_MESSAGE: + if (dev->card_data.leaf.family != KVASER_LEAF) + goto warn; + kvaser_usb_leaf_rx_can_msg(dev, cmd); + break; + + case CMD_CHIP_STATE_EVENT: + case CMD_CAN_ERROR_EVENT: + if (dev->card_data.leaf.family == KVASER_LEAF) + kvaser_usb_leaf_leaf_rx_error(dev, cmd); + else + kvaser_usb_leaf_usbcan_rx_error(dev, cmd); + break; + + case CMD_TX_ACKNOWLEDGE: + kvaser_usb_leaf_tx_acknowledge(dev, cmd); + break; + + /* Ignored commands */ + case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: + if (dev->card_data.leaf.family != KVASER_USBCAN) + goto warn; + break; + + case CMD_FLUSH_QUEUE_REPLY: + if (dev->card_data.leaf.family != KVASER_LEAF) + goto warn; + break; + + default: +warn: dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", cmd->id); + break; + } +} + +static void kvaser_usb_leaf_read_bulk_callback(struct kvaser_usb *dev, + void *buf, int len) +{ + struct kvaser_cmd *cmd; + int pos = 0; + + while (pos <= len - CMD_HEADER_LEN) { + cmd = buf + pos; + + /* The Kvaser firmware can only read and write commands that + * does not cross the USB's endpoint wMaxPacketSize boundary. + * If a follow-up command crosses such boundary, firmware puts + * a placeholder zero-length command in its place then aligns + * the real command to the next max packet size. + * + * Handle such cases or we're going to miss a significant + * number of events in case of a heavy rx load on the bus. + */ + if (cmd->len == 0) { + pos = round_up(pos, le16_to_cpu + (dev->bulk_in->wMaxPacketSize)); + continue; + } + + if (pos + cmd->len > len) { + dev_err_ratelimited(&dev->intf->dev, "Format error\n"); + break; + } + + kvaser_usb_leaf_handle_command(dev, cmd); + pos += cmd->len; + } +} + +static int kvaser_usb_leaf_set_opt_mode(const struct kvaser_usb_net_priv *priv) +{ + struct kvaser_cmd *cmd; + int rc; + + cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->id = CMD_SET_CTRL_MODE; + cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_ctrl_mode); + cmd->u.ctrl_mode.tid = 0xff; + cmd->u.ctrl_mode.channel = priv->channel; + + if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT; + else + cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL; + + rc = kvaser_usb_send_cmd(priv->dev, cmd, cmd->len); + + kfree(cmd); + return rc; +} + +static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv) +{ + int err; + + init_completion(&priv->start_comp); + + err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP, + priv->channel); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->start_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return 0; +} + +static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv) +{ + int err; + + init_completion(&priv->stop_comp); + + err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP, + priv->channel); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->stop_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return 0; +} + +static int kvaser_usb_leaf_reset_chip(struct kvaser_usb *dev, int channel) +{ + return kvaser_usb_leaf_send_simple_cmd(dev, CMD_RESET_CHIP, channel); +} + +static int kvaser_usb_leaf_flush_queue(struct kvaser_usb_net_priv *priv) +{ + struct kvaser_cmd *cmd; + int rc; + + cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->id = CMD_FLUSH_QUEUE; + cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_flush_queue); + cmd->u.flush_queue.channel = priv->channel; + cmd->u.flush_queue.flags = 0x00; + + rc = kvaser_usb_send_cmd(priv->dev, cmd, cmd->len); + + kfree(cmd); + return rc; +} + +static int kvaser_usb_leaf_init_card(struct kvaser_usb *dev) +{ + struct kvaser_usb_dev_card_data *card_data = &dev->card_data; + + dev->cfg = &kvaser_usb_leaf_dev_cfg; + card_data->ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES; + + return 0; +} + +static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = { + .name = "kvaser_usb", + .tseg1_min = KVASER_USB_TSEG1_MIN, + .tseg1_max = KVASER_USB_TSEG1_MAX, + .tseg2_min = KVASER_USB_TSEG2_MIN, + .tseg2_max = KVASER_USB_TSEG2_MAX, + .sjw_max = KVASER_USB_SJW_MAX, + .brp_min = KVASER_USB_BRP_MIN, + .brp_max = KVASER_USB_BRP_MAX, + .brp_inc = KVASER_USB_BRP_INC, +}; + +static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct can_bittiming *bt = &priv->can.bittiming; + struct kvaser_usb *dev = priv->dev; + struct kvaser_cmd *cmd; + int rc; + + cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->id = CMD_SET_BUS_PARAMS; + cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams); + cmd->u.busparams.channel = priv->channel; + cmd->u.busparams.tid = 0xff; + cmd->u.busparams.bitrate = cpu_to_le32(bt->bitrate); + cmd->u.busparams.sjw = bt->sjw; + cmd->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1; + cmd->u.busparams.tseg2 = bt->phase_seg2; + + if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) + cmd->u.busparams.no_samp = 3; + else + cmd->u.busparams.no_samp = 1; + + rc = kvaser_usb_send_cmd(dev, cmd, cmd->len); + + kfree(cmd); + return rc; +} + +static int kvaser_usb_leaf_set_mode(struct net_device *netdev, + enum can_mode mode) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + int err; + + switch (mode) { + case CAN_MODE_START: + err = kvaser_usb_leaf_simple_cmd_async(priv, CMD_START_CHIP); + if (err) + return err; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int kvaser_usb_leaf_get_berr_counter(const struct net_device *netdev, + struct can_berr_counter *bec) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + + *bec = priv->bec; + + return 0; +} + +static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev) +{ + const struct usb_host_interface *iface_desc; + struct usb_endpoint_descriptor *endpoint; + int i; + + iface_desc = &dev->intf->altsetting[0]; + + for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { + endpoint = &iface_desc->endpoint[i].desc; + + if (!dev->bulk_in && usb_endpoint_is_bulk_in(endpoint)) + dev->bulk_in = endpoint; + + if (!dev->bulk_out && usb_endpoint_is_bulk_out(endpoint)) + dev->bulk_out = endpoint; + + /* use first bulk endpoint for in and out */ + if (dev->bulk_in && dev->bulk_out) + return 0; + } + + return -ENODEV; +} + +const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = { + .dev_set_mode = kvaser_usb_leaf_set_mode, + .dev_set_bittiming = kvaser_usb_leaf_set_bittiming, + .dev_set_data_bittiming = NULL, + .dev_get_berr_counter = kvaser_usb_leaf_get_berr_counter, + .dev_setup_endpoints = kvaser_usb_leaf_setup_endpoints, + .dev_init_card = kvaser_usb_leaf_init_card, + .dev_get_software_info = kvaser_usb_leaf_get_software_info, + .dev_get_software_details = NULL, + .dev_get_card_info = kvaser_usb_leaf_get_card_info, + .dev_get_capabilities = NULL, + .dev_set_opt_mode = kvaser_usb_leaf_set_opt_mode, + .dev_start_chip = kvaser_usb_leaf_start_chip, + .dev_stop_chip = kvaser_usb_leaf_stop_chip, + .dev_reset_chip = kvaser_usb_leaf_reset_chip, + .dev_flush_queue = kvaser_usb_leaf_flush_queue, + .dev_read_bulk_callback = kvaser_usb_leaf_read_bulk_callback, + .dev_frame_to_cmd = kvaser_usb_leaf_frame_to_cmd, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg = { + .clock = { + .freq = CAN_USB_CLOCK, + }, + .timestamp_freq = 1, + .bittiming_const = &kvaser_usb_leaf_bittiming_const, +}; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index f530a80f5051..13238a72a338 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -423,6 +423,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, new_state = CAN_STATE_ERROR_WARNING; break; } + /* else: fall through */ case CAN_STATE_ERROR_WARNING: if (n & PCAN_USB_ERROR_BUS_HEAVY) { diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 50e911428638..611f9d31be5d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -353,6 +353,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, default: netdev_warn(netdev, "tx urb submitting failed err=%d\n", err); + /* fall through */ case -ENOENT: /* cable unplugged */ stats->tx_dropped++; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 0105fbfea273..d516def846ab 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -141,8 +141,10 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, u8 id, ...) switch (id) { case PCAN_USBPRO_TXMSG8: i += 4; + /* fall through */ case PCAN_USBPRO_TXMSG4: i += 4; + /* fall through */ case PCAN_USBPRO_TXMSG0: *pc++ = va_arg(ap, int); *pc++ = va_arg(ap, int); diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c new file mode 100644 index 000000000000..0678a38b1af4 --- /dev/null +++ b/drivers/net/can/usb/ucan.c @@ -0,0 +1,1613 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Driver for Theobroma Systems UCAN devices, Protocol Version 3 + * + * Copyright (C) 2018 Theobroma Systems Design und Consulting GmbH + * + * + * General Description: + * + * The USB Device uses three Endpoints: + * + * CONTROL Endpoint: Is used the setup the device (start, stop, + * info, configure). + * + * IN Endpoint: The device sends CAN Frame Messages and Device + * Information using the IN endpoint. + * + * OUT Endpoint: The driver sends configuration requests, and CAN + * Frames on the out endpoint. + * + * Error Handling: + * + * If error reporting is turned on the device encodes error into CAN + * error frames (see uapi/linux/can/error.h) and sends it using the + * IN Endpoint. The driver updates statistics and forward it. + */ + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/signal.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/usb.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> + +#define UCAN_DRIVER_NAME "ucan" +#define UCAN_MAX_RX_URBS 8 +/* the CAN controller needs a while to enable/disable the bus */ +#define UCAN_USB_CTL_PIPE_TIMEOUT 1000 +/* this driver currently supports protocol version 3 only */ +#define UCAN_PROTOCOL_VERSION_MIN 3 +#define UCAN_PROTOCOL_VERSION_MAX 3 + +/* UCAN Message Definitions + * ------------------------ + * + * ucan_message_out_t and ucan_message_in_t define the messages + * transmitted on the OUT and IN endpoint. + * + * Multibyte fields are transmitted with little endianness + * + * INTR Endpoint: a single uint32_t storing the current space in the fifo + * + * OUT Endpoint: single message of type ucan_message_out_t is + * transmitted on the out endpoint + * + * IN Endpoint: multiple messages ucan_message_in_t concateted in + * the following way: + * + * m[n].len <=> the length if message n(including the header in bytes) + * m[n] is is aligned to a 4 byte boundary, hence + * offset(m[0]) := 0; + * offset(m[n+1]) := offset(m[n]) + (m[n].len + 3) & 3 + * + * this implies that + * offset(m[n]) % 4 <=> 0 + */ + +/* Device Global Commands */ +enum { + UCAN_DEVICE_GET_FW_STRING = 0, +}; + +/* UCAN Commands */ +enum { + /* start the can transceiver - val defines the operation mode */ + UCAN_COMMAND_START = 0, + /* cancel pending transmissions and stop the can transceiver */ + UCAN_COMMAND_STOP = 1, + /* send can transceiver into low-power sleep mode */ + UCAN_COMMAND_SLEEP = 2, + /* wake up can transceiver from low-power sleep mode */ + UCAN_COMMAND_WAKEUP = 3, + /* reset the can transceiver */ + UCAN_COMMAND_RESET = 4, + /* get piece of info from the can transceiver - subcmd defines what + * piece + */ + UCAN_COMMAND_GET = 5, + /* clear or disable hardware filter - subcmd defines which of the two */ + UCAN_COMMAND_FILTER = 6, + /* Setup bittiming */ + UCAN_COMMAND_SET_BITTIMING = 7, + /* recover from bus-off state */ + UCAN_COMMAND_RESTART = 8, +}; + +/* UCAN_COMMAND_START and UCAN_COMMAND_GET_INFO operation modes (bitmap). + * Undefined bits must be set to 0. + */ +enum { + UCAN_MODE_LOOPBACK = BIT(0), + UCAN_MODE_SILENT = BIT(1), + UCAN_MODE_3_SAMPLES = BIT(2), + UCAN_MODE_ONE_SHOT = BIT(3), + UCAN_MODE_BERR_REPORT = BIT(4), +}; + +/* UCAN_COMMAND_GET subcommands */ +enum { + UCAN_COMMAND_GET_INFO = 0, + UCAN_COMMAND_GET_PROTOCOL_VERSION = 1, +}; + +/* UCAN_COMMAND_FILTER subcommands */ +enum { + UCAN_FILTER_CLEAR = 0, + UCAN_FILTER_DISABLE = 1, + UCAN_FILTER_ENABLE = 2, +}; + +/* OUT endpoint message types */ +enum { + UCAN_OUT_TX = 2, /* transmit a CAN frame */ +}; + +/* IN endpoint message types */ +enum { + UCAN_IN_TX_COMPLETE = 1, /* CAN frame transmission completed */ + UCAN_IN_RX = 2, /* CAN frame received */ +}; + +struct ucan_ctl_cmd_start { + __le16 mode; /* OR-ing any of UCAN_MODE_* */ +} __packed; + +struct ucan_ctl_cmd_set_bittiming { + __le32 tq; /* Time quanta (TQ) in nanoseconds */ + __le16 brp; /* TQ Prescaler */ + __le16 sample_point; /* Samplepoint on tenth percent */ + u8 prop_seg; /* Propagation segment in TQs */ + u8 phase_seg1; /* Phase buffer segment 1 in TQs */ + u8 phase_seg2; /* Phase buffer segment 2 in TQs */ + u8 sjw; /* Synchronisation jump width in TQs */ +} __packed; + +struct ucan_ctl_cmd_device_info { + __le32 freq; /* Clock Frequency for tq generation */ + u8 tx_fifo; /* Size of the transmission fifo */ + u8 sjw_max; /* can_bittiming fields... */ + u8 tseg1_min; + u8 tseg1_max; + u8 tseg2_min; + u8 tseg2_max; + __le16 brp_inc; + __le32 brp_min; + __le32 brp_max; /* ...can_bittiming fields */ + __le16 ctrlmodes; /* supported control modes */ + __le16 hwfilter; /* Number of HW filter banks */ + __le16 rxmboxes; /* Number of receive Mailboxes */ +} __packed; + +struct ucan_ctl_cmd_get_protocol_version { + __le32 version; +} __packed; + +union ucan_ctl_payload { + /* Setup Bittiming + * bmRequest == UCAN_COMMAND_START + */ + struct ucan_ctl_cmd_start cmd_start; + /* Setup Bittiming + * bmRequest == UCAN_COMMAND_SET_BITTIMING + */ + struct ucan_ctl_cmd_set_bittiming cmd_set_bittiming; + /* Get Device Information + * bmRequest == UCAN_COMMAND_GET; wValue = UCAN_COMMAND_GET_INFO + */ + struct ucan_ctl_cmd_device_info cmd_get_device_info; + /* Get Protocol Version + * bmRequest == UCAN_COMMAND_GET; + * wValue = UCAN_COMMAND_GET_PROTOCOL_VERSION + */ + struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version; + + u8 raw[128]; +} __packed; + +enum { + UCAN_TX_COMPLETE_SUCCESS = BIT(0), +}; + +/* Transmission Complete within ucan_message_in */ +struct ucan_tx_complete_entry_t { + u8 echo_index; + u8 flags; +} __packed __aligned(0x2); + +/* CAN Data message format within ucan_message_in/out */ +struct ucan_can_msg { + /* note DLC is computed by + * msg.len - sizeof (msg.len) + * - sizeof (msg.type) + * - sizeof (msg.can_msg.id) + */ + __le32 id; + + union { + u8 data[CAN_MAX_DLEN]; /* Data of CAN frames */ + u8 dlc; /* RTR dlc */ + }; +} __packed; + +/* OUT Endpoint, outbound messages */ +struct ucan_message_out { + __le16 len; /* Length of the content include header */ + u8 type; /* UCAN_OUT_TX and friends */ + u8 subtype; /* command sub type */ + + union { + /* Transmit CAN frame + * (type == UCAN_TX) && ((msg.can_msg.id & CAN_RTR_FLAG) == 0) + * subtype stores the echo id + */ + struct ucan_can_msg can_msg; + } msg; +} __packed __aligned(0x4); + +/* IN Endpoint, inbound messages */ +struct ucan_message_in { + __le16 len; /* Length of the content include header */ + u8 type; /* UCAN_IN_RX and friends */ + u8 subtype; /* command sub type */ + + union { + /* CAN Frame received + * (type == UCAN_IN_RX) + * && ((msg.can_msg.id & CAN_RTR_FLAG) == 0) + */ + struct ucan_can_msg can_msg; + + /* CAN transmission complete + * (type == UCAN_IN_TX_COMPLETE) + */ + struct ucan_tx_complete_entry_t can_tx_complete_msg[0]; + } __aligned(0x4) msg; +} __packed; + +/* Macros to calculate message lengths */ +#define UCAN_OUT_HDR_SIZE offsetof(struct ucan_message_out, msg) + +#define UCAN_IN_HDR_SIZE offsetof(struct ucan_message_in, msg) +#define UCAN_IN_LEN(member) (UCAN_OUT_HDR_SIZE + sizeof(member)) + +struct ucan_priv; + +/* Context Information for transmission URBs */ +struct ucan_urb_context { + struct ucan_priv *up; + u8 dlc; + bool allocated; +}; + +/* Information reported by the USB device */ +struct ucan_device_info { + struct can_bittiming_const bittiming_const; + u8 tx_fifo; +}; + +/* Driver private data */ +struct ucan_priv { + /* must be the first member */ + struct can_priv can; + + /* linux USB device structures */ + struct usb_device *udev; + struct usb_interface *intf; + struct net_device *netdev; + + /* lock for can->echo_skb (used around + * can_put/get/free_echo_skb + */ + spinlock_t echo_skb_lock; + + /* usb device information information */ + u8 intf_index; + u8 in_ep_addr; + u8 out_ep_addr; + u16 in_ep_size; + + /* transmission and reception buffers */ + struct usb_anchor rx_urbs; + struct usb_anchor tx_urbs; + + union ucan_ctl_payload *ctl_msg_buffer; + struct ucan_device_info device_info; + + /* transmission control information and locks */ + spinlock_t context_lock; + unsigned int available_tx_urbs; + struct ucan_urb_context *context_array; +}; + +static u8 ucan_get_can_dlc(struct ucan_can_msg *msg, u16 len) +{ + if (le32_to_cpu(msg->id) & CAN_RTR_FLAG) + return get_can_dlc(msg->dlc); + else + return get_can_dlc(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id))); +} + +static void ucan_release_context_array(struct ucan_priv *up) +{ + if (!up->context_array) + return; + + /* lock is not needed because, driver is currently opening or closing */ + up->available_tx_urbs = 0; + + kfree(up->context_array); + up->context_array = NULL; +} + +static int ucan_alloc_context_array(struct ucan_priv *up) +{ + int i; + + /* release contexts if any */ + ucan_release_context_array(up); + + up->context_array = kcalloc(up->device_info.tx_fifo, + sizeof(*up->context_array), + GFP_KERNEL); + if (!up->context_array) { + netdev_err(up->netdev, + "Not enough memory to allocate tx contexts\n"); + return -ENOMEM; + } + + for (i = 0; i < up->device_info.tx_fifo; i++) { + up->context_array[i].allocated = false; + up->context_array[i].up = up; + } + + /* lock is not needed because, driver is currently opening */ + up->available_tx_urbs = up->device_info.tx_fifo; + + return 0; +} + +static struct ucan_urb_context *ucan_alloc_context(struct ucan_priv *up) +{ + int i; + unsigned long flags; + struct ucan_urb_context *ret = NULL; + + if (WARN_ON_ONCE(!up->context_array)) + return NULL; + + /* execute context operation atomically */ + spin_lock_irqsave(&up->context_lock, flags); + + for (i = 0; i < up->device_info.tx_fifo; i++) { + if (!up->context_array[i].allocated) { + /* update context */ + ret = &up->context_array[i]; + up->context_array[i].allocated = true; + + /* stop queue if necessary */ + up->available_tx_urbs--; + if (!up->available_tx_urbs) + netif_stop_queue(up->netdev); + + break; + } + } + + spin_unlock_irqrestore(&up->context_lock, flags); + return ret; +} + +static bool ucan_release_context(struct ucan_priv *up, + struct ucan_urb_context *ctx) +{ + unsigned long flags; + bool ret = false; + + if (WARN_ON_ONCE(!up->context_array)) + return false; + + /* execute context operation atomically */ + spin_lock_irqsave(&up->context_lock, flags); + + /* context was not allocated, maybe the device sent garbage */ + if (ctx->allocated) { + ctx->allocated = false; + + /* check if the queue needs to be woken */ + if (!up->available_tx_urbs) + netif_wake_queue(up->netdev); + up->available_tx_urbs++; + + ret = true; + } + + spin_unlock_irqrestore(&up->context_lock, flags); + return ret; +} + +static int ucan_ctrl_command_out(struct ucan_priv *up, + u8 cmd, u16 subcmd, u16 datalen) +{ + return usb_control_msg(up->udev, + usb_sndctrlpipe(up->udev, 0), + cmd, + USB_DIR_OUT | USB_TYPE_VENDOR | + USB_RECIP_INTERFACE, + subcmd, + up->intf_index, + up->ctl_msg_buffer, + datalen, + UCAN_USB_CTL_PIPE_TIMEOUT); +} + +static int ucan_device_request_in(struct ucan_priv *up, + u8 cmd, u16 subcmd, u16 datalen) +{ + return usb_control_msg(up->udev, + usb_rcvctrlpipe(up->udev, 0), + cmd, + USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, + subcmd, + 0, + up->ctl_msg_buffer, + datalen, + UCAN_USB_CTL_PIPE_TIMEOUT); +} + +/* Parse the device information structure reported by the device and + * setup private variables accordingly + */ +static void ucan_parse_device_info(struct ucan_priv *up, + struct ucan_ctl_cmd_device_info *device_info) +{ + struct can_bittiming_const *bittiming = + &up->device_info.bittiming_const; + u16 ctrlmodes; + + /* store the data */ + up->can.clock.freq = le32_to_cpu(device_info->freq); + up->device_info.tx_fifo = device_info->tx_fifo; + strcpy(bittiming->name, "ucan"); + bittiming->tseg1_min = device_info->tseg1_min; + bittiming->tseg1_max = device_info->tseg1_max; + bittiming->tseg2_min = device_info->tseg2_min; + bittiming->tseg2_max = device_info->tseg2_max; + bittiming->sjw_max = device_info->sjw_max; + bittiming->brp_min = le32_to_cpu(device_info->brp_min); + bittiming->brp_max = le32_to_cpu(device_info->brp_max); + bittiming->brp_inc = le16_to_cpu(device_info->brp_inc); + + ctrlmodes = le16_to_cpu(device_info->ctrlmodes); + + up->can.ctrlmode_supported = 0; + + if (ctrlmodes & UCAN_MODE_LOOPBACK) + up->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK; + if (ctrlmodes & UCAN_MODE_SILENT) + up->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY; + if (ctrlmodes & UCAN_MODE_3_SAMPLES) + up->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES; + if (ctrlmodes & UCAN_MODE_ONE_SHOT) + up->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; + if (ctrlmodes & UCAN_MODE_BERR_REPORT) + up->can.ctrlmode_supported |= CAN_CTRLMODE_BERR_REPORTING; +} + +/* Handle a CAN error frame that we have received from the device. + * Returns true if the can state has changed. + */ +static bool ucan_handle_error_frame(struct ucan_priv *up, + struct ucan_message_in *m, + canid_t canid) +{ + enum can_state new_state = up->can.state; + struct net_device_stats *net_stats = &up->netdev->stats; + struct can_device_stats *can_stats = &up->can.can_stats; + + if (canid & CAN_ERR_LOSTARB) + can_stats->arbitration_lost++; + + if (canid & CAN_ERR_BUSERROR) + can_stats->bus_error++; + + if (canid & CAN_ERR_ACK) + net_stats->tx_errors++; + + if (canid & CAN_ERR_BUSOFF) + new_state = CAN_STATE_BUS_OFF; + + /* controller problems, details in data[1] */ + if (canid & CAN_ERR_CRTL) { + u8 d1 = m->msg.can_msg.data[1]; + + if (d1 & CAN_ERR_CRTL_RX_OVERFLOW) + net_stats->rx_over_errors++; + + /* controller state bits: if multiple are set the worst wins */ + if (d1 & CAN_ERR_CRTL_ACTIVE) + new_state = CAN_STATE_ERROR_ACTIVE; + + if (d1 & (CAN_ERR_CRTL_RX_WARNING | CAN_ERR_CRTL_TX_WARNING)) + new_state = CAN_STATE_ERROR_WARNING; + + if (d1 & (CAN_ERR_CRTL_RX_PASSIVE | CAN_ERR_CRTL_TX_PASSIVE)) + new_state = CAN_STATE_ERROR_PASSIVE; + } + + /* protocol error, details in data[2] */ + if (canid & CAN_ERR_PROT) { + u8 d2 = m->msg.can_msg.data[2]; + + if (d2 & CAN_ERR_PROT_TX) + net_stats->tx_errors++; + else + net_stats->rx_errors++; + } + + /* no state change - we are done */ + if (up->can.state == new_state) + return false; + + /* we switched into a better state */ + if (up->can.state > new_state) { + up->can.state = new_state; + return true; + } + + /* we switched into a worse state */ + up->can.state = new_state; + switch (new_state) { + case CAN_STATE_BUS_OFF: + can_stats->bus_off++; + can_bus_off(up->netdev); + break; + case CAN_STATE_ERROR_PASSIVE: + can_stats->error_passive++; + break; + case CAN_STATE_ERROR_WARNING: + can_stats->error_warning++; + break; + default: + break; + } + return true; +} + +/* Callback on reception of a can frame via the IN endpoint + * + * This function allocates an skb and transferres it to the Linux + * network stack + */ +static void ucan_rx_can_msg(struct ucan_priv *up, struct ucan_message_in *m) +{ + int len; + canid_t canid; + struct can_frame *cf; + struct sk_buff *skb; + struct net_device_stats *stats = &up->netdev->stats; + + /* get the contents of the length field */ + len = le16_to_cpu(m->len); + + /* check sanity */ + if (len < UCAN_IN_HDR_SIZE + sizeof(m->msg.can_msg.id)) { + netdev_warn(up->netdev, "invalid input message len: %d\n", len); + return; + } + + /* handle error frames */ + canid = le32_to_cpu(m->msg.can_msg.id); + if (canid & CAN_ERR_FLAG) { + bool busstate_changed = ucan_handle_error_frame(up, m, canid); + + /* if berr-reporting is off only state changes get through */ + if (!(up->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) && + !busstate_changed) + return; + } else { + canid_t canid_mask; + /* compute the mask for canid */ + canid_mask = CAN_RTR_FLAG; + if (canid & CAN_EFF_FLAG) + canid_mask |= CAN_EFF_MASK | CAN_EFF_FLAG; + else + canid_mask |= CAN_SFF_MASK; + + if (canid & ~canid_mask) + netdev_warn(up->netdev, + "unexpected bits set (canid %x, mask %x)", + canid, canid_mask); + + canid &= canid_mask; + } + + /* allocate skb */ + skb = alloc_can_skb(up->netdev, &cf); + if (!skb) + return; + + /* fill the can frame */ + cf->can_id = canid; + + /* compute DLC taking RTR_FLAG into account */ + cf->can_dlc = ucan_get_can_dlc(&m->msg.can_msg, len); + + /* copy the payload of non RTR frames */ + if (!(cf->can_id & CAN_RTR_FLAG) || (cf->can_id & CAN_ERR_FLAG)) + memcpy(cf->data, m->msg.can_msg.data, cf->can_dlc); + + /* don't count error frames as real packets */ + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + + /* pass it to Linux */ + netif_rx(skb); +} + +/* callback indicating completed transmission */ +static void ucan_tx_complete_msg(struct ucan_priv *up, + struct ucan_message_in *m) +{ + unsigned long flags; + u16 count, i; + u8 echo_index, dlc; + u16 len = le16_to_cpu(m->len); + + struct ucan_urb_context *context; + + if (len < UCAN_IN_HDR_SIZE || (len % 2 != 0)) { + netdev_err(up->netdev, "invalid tx complete length\n"); + return; + } + + count = (len - UCAN_IN_HDR_SIZE) / 2; + for (i = 0; i < count; i++) { + /* we did not submit such echo ids */ + echo_index = m->msg.can_tx_complete_msg[i].echo_index; + if (echo_index >= up->device_info.tx_fifo) { + up->netdev->stats.tx_errors++; + netdev_err(up->netdev, + "invalid echo_index %d received\n", + echo_index); + continue; + } + + /* gather information from the context */ + context = &up->context_array[echo_index]; + dlc = READ_ONCE(context->dlc); + + /* Release context and restart queue if necessary. + * Also check if the context was allocated + */ + if (!ucan_release_context(up, context)) + continue; + + spin_lock_irqsave(&up->echo_skb_lock, flags); + if (m->msg.can_tx_complete_msg[i].flags & + UCAN_TX_COMPLETE_SUCCESS) { + /* update statistics */ + up->netdev->stats.tx_packets++; + up->netdev->stats.tx_bytes += dlc; + can_get_echo_skb(up->netdev, echo_index); + } else { + up->netdev->stats.tx_dropped++; + can_free_echo_skb(up->netdev, echo_index); + } + spin_unlock_irqrestore(&up->echo_skb_lock, flags); + } +} + +/* callback on reception of a USB message */ +static void ucan_read_bulk_callback(struct urb *urb) +{ + int ret; + int pos; + struct ucan_priv *up = urb->context; + struct net_device *netdev = up->netdev; + struct ucan_message_in *m; + + /* the device is not up and the driver should not receive any + * data on the bulk in pipe + */ + if (WARN_ON(!up->context_array)) { + usb_free_coherent(up->udev, + up->in_ep_size, + urb->transfer_buffer, + urb->transfer_dma); + return; + } + + /* check URB status */ + switch (urb->status) { + case 0: + break; + case -ENOENT: + case -EPIPE: + case -EPROTO: + case -ESHUTDOWN: + case -ETIME: + /* urb is not resubmitted -> free dma data */ + usb_free_coherent(up->udev, + up->in_ep_size, + urb->transfer_buffer, + urb->transfer_dma); + netdev_dbg(up->netdev, "not resumbmitting urb; status: %d\n", + urb->status); + return; + default: + goto resubmit; + } + + /* sanity check */ + if (!netif_device_present(netdev)) + return; + + /* iterate over input */ + pos = 0; + while (pos < urb->actual_length) { + int len; + + /* check sanity (length of header) */ + if ((urb->actual_length - pos) < UCAN_IN_HDR_SIZE) { + netdev_warn(up->netdev, + "invalid message (short; no hdr; l:%d)\n", + urb->actual_length); + goto resubmit; + } + + /* setup the message address */ + m = (struct ucan_message_in *) + ((u8 *)urb->transfer_buffer + pos); + len = le16_to_cpu(m->len); + + /* check sanity (length of content) */ + if (urb->actual_length - pos < len) { + netdev_warn(up->netdev, + "invalid message (short; no data; l:%d)\n", + urb->actual_length); + print_hex_dump(KERN_WARNING, + "raw data: ", + DUMP_PREFIX_ADDRESS, + 16, + 1, + urb->transfer_buffer, + urb->actual_length, + true); + + goto resubmit; + } + + switch (m->type) { + case UCAN_IN_RX: + ucan_rx_can_msg(up, m); + break; + case UCAN_IN_TX_COMPLETE: + ucan_tx_complete_msg(up, m); + break; + default: + netdev_warn(up->netdev, + "invalid message (type; t:%d)\n", + m->type); + break; + } + + /* proceed to next message */ + pos += len; + /* align to 4 byte boundary */ + pos = round_up(pos, 4); + } + +resubmit: + /* resubmit urb when done */ + usb_fill_bulk_urb(urb, up->udev, + usb_rcvbulkpipe(up->udev, + up->in_ep_addr), + urb->transfer_buffer, + up->in_ep_size, + ucan_read_bulk_callback, + up); + + usb_anchor_urb(urb, &up->rx_urbs); + ret = usb_submit_urb(urb, GFP_KERNEL); + + if (ret < 0) { + netdev_err(up->netdev, + "failed resubmitting read bulk urb: %d\n", + ret); + + usb_unanchor_urb(urb); + usb_free_coherent(up->udev, + up->in_ep_size, + urb->transfer_buffer, + urb->transfer_dma); + + if (ret == -ENODEV) + netif_device_detach(netdev); + } +} + +/* callback after transmission of a USB message */ +static void ucan_write_bulk_callback(struct urb *urb) +{ + unsigned long flags; + struct ucan_priv *up; + struct ucan_urb_context *context = urb->context; + + /* get the urb context */ + if (WARN_ON_ONCE(!context)) + return; + + /* free up our allocated buffer */ + usb_free_coherent(urb->dev, + sizeof(struct ucan_message_out), + urb->transfer_buffer, + urb->transfer_dma); + + up = context->up; + if (WARN_ON_ONCE(!up)) + return; + + /* sanity check */ + if (!netif_device_present(up->netdev)) + return; + + /* transmission failed (USB - the device will not send a TX complete) */ + if (urb->status) { + netdev_warn(up->netdev, + "failed to transmit USB message to device: %d\n", + urb->status); + + /* update counters an cleanup */ + spin_lock_irqsave(&up->echo_skb_lock, flags); + can_free_echo_skb(up->netdev, context - up->context_array); + spin_unlock_irqrestore(&up->echo_skb_lock, flags); + + up->netdev->stats.tx_dropped++; + + /* release context and restart the queue if necessary */ + if (!ucan_release_context(up, context)) + netdev_err(up->netdev, + "urb failed, failed to release context\n"); + } +} + +static void ucan_cleanup_rx_urbs(struct ucan_priv *up, struct urb **urbs) +{ + int i; + + for (i = 0; i < UCAN_MAX_RX_URBS; i++) { + if (urbs[i]) { + usb_unanchor_urb(urbs[i]); + usb_free_coherent(up->udev, + up->in_ep_size, + urbs[i]->transfer_buffer, + urbs[i]->transfer_dma); + usb_free_urb(urbs[i]); + } + } + + memset(urbs, 0, sizeof(*urbs) * UCAN_MAX_RX_URBS); +} + +static int ucan_prepare_and_anchor_rx_urbs(struct ucan_priv *up, + struct urb **urbs) +{ + int i; + + memset(urbs, 0, sizeof(*urbs) * UCAN_MAX_RX_URBS); + + for (i = 0; i < UCAN_MAX_RX_URBS; i++) { + void *buf; + + urbs[i] = usb_alloc_urb(0, GFP_KERNEL); + if (!urbs[i]) + goto err; + + buf = usb_alloc_coherent(up->udev, + up->in_ep_size, + GFP_KERNEL, &urbs[i]->transfer_dma); + if (!buf) { + /* cleanup this urb */ + usb_free_urb(urbs[i]); + urbs[i] = NULL; + goto err; + } + + usb_fill_bulk_urb(urbs[i], up->udev, + usb_rcvbulkpipe(up->udev, + up->in_ep_addr), + buf, + up->in_ep_size, + ucan_read_bulk_callback, + up); + + urbs[i]->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + + usb_anchor_urb(urbs[i], &up->rx_urbs); + } + return 0; + +err: + /* cleanup other unsubmitted urbs */ + ucan_cleanup_rx_urbs(up, urbs); + return -ENOMEM; +} + +/* Submits rx urbs with the semantic: Either submit all, or cleanup + * everything. I case of errors submitted urbs are killed and all urbs in + * the array are freed. I case of no errors every entry in the urb + * array is set to NULL. + */ +static int ucan_submit_rx_urbs(struct ucan_priv *up, struct urb **urbs) +{ + int i, ret; + + /* Iterate over all urbs to submit. On success remove the urb + * from the list. + */ + for (i = 0; i < UCAN_MAX_RX_URBS; i++) { + ret = usb_submit_urb(urbs[i], GFP_KERNEL); + if (ret) { + netdev_err(up->netdev, + "could not submit urb; code: %d\n", + ret); + goto err; + } + + /* Anchor URB and drop reference, USB core will take + * care of freeing it + */ + usb_free_urb(urbs[i]); + urbs[i] = NULL; + } + return 0; + +err: + /* Cleanup unsubmitted urbs */ + ucan_cleanup_rx_urbs(up, urbs); + + /* Kill urbs that are already submitted */ + usb_kill_anchored_urbs(&up->rx_urbs); + + return ret; +} + +/* Open the network device */ +static int ucan_open(struct net_device *netdev) +{ + int ret, ret_cleanup; + u16 ctrlmode; + struct urb *urbs[UCAN_MAX_RX_URBS]; + struct ucan_priv *up = netdev_priv(netdev); + + ret = ucan_alloc_context_array(up); + if (ret) + return ret; + + /* Allocate and prepare IN URBS - allocated and anchored + * urbs are stored in urbs[] for clean + */ + ret = ucan_prepare_and_anchor_rx_urbs(up, urbs); + if (ret) + goto err_contexts; + + /* Check the control mode */ + ctrlmode = 0; + if (up->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) + ctrlmode |= UCAN_MODE_LOOPBACK; + if (up->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + ctrlmode |= UCAN_MODE_SILENT; + if (up->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) + ctrlmode |= UCAN_MODE_3_SAMPLES; + if (up->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + ctrlmode |= UCAN_MODE_ONE_SHOT; + + /* Enable this in any case - filtering is down within the + * receive path + */ + ctrlmode |= UCAN_MODE_BERR_REPORT; + up->ctl_msg_buffer->cmd_start.mode = cpu_to_le16(ctrlmode); + + /* Driver is ready to receive data - start the USB device */ + ret = ucan_ctrl_command_out(up, UCAN_COMMAND_START, 0, 2); + if (ret < 0) { + netdev_err(up->netdev, + "could not start device, code: %d\n", + ret); + goto err_reset; + } + + /* Call CAN layer open */ + ret = open_candev(netdev); + if (ret) + goto err_stop; + + /* Driver is ready to receive data. Submit RX URBS */ + ret = ucan_submit_rx_urbs(up, urbs); + if (ret) + goto err_stop; + + up->can.state = CAN_STATE_ERROR_ACTIVE; + + /* Start the network queue */ + netif_start_queue(netdev); + + return 0; + +err_stop: + /* The device have started already stop it */ + ret_cleanup = ucan_ctrl_command_out(up, UCAN_COMMAND_STOP, 0, 0); + if (ret_cleanup < 0) + netdev_err(up->netdev, + "could not stop device, code: %d\n", + ret_cleanup); + +err_reset: + /* The device might have received data, reset it for + * consistent state + */ + ret_cleanup = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0); + if (ret_cleanup < 0) + netdev_err(up->netdev, + "could not reset device, code: %d\n", + ret_cleanup); + + /* clean up unsubmitted urbs */ + ucan_cleanup_rx_urbs(up, urbs); + +err_contexts: + ucan_release_context_array(up); + return ret; +} + +static struct urb *ucan_prepare_tx_urb(struct ucan_priv *up, + struct ucan_urb_context *context, + struct can_frame *cf, + u8 echo_index) +{ + int mlen; + struct urb *urb; + struct ucan_message_out *m; + + /* create a URB, and a buffer for it, and copy the data to the URB */ + urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!urb) { + netdev_err(up->netdev, "no memory left for URBs\n"); + return NULL; + } + + m = usb_alloc_coherent(up->udev, + sizeof(struct ucan_message_out), + GFP_ATOMIC, + &urb->transfer_dma); + if (!m) { + netdev_err(up->netdev, "no memory left for USB buffer\n"); + usb_free_urb(urb); + return NULL; + } + + /* build the USB message */ + m->type = UCAN_OUT_TX; + m->msg.can_msg.id = cpu_to_le32(cf->can_id); + + if (cf->can_id & CAN_RTR_FLAG) { + mlen = UCAN_OUT_HDR_SIZE + + offsetof(struct ucan_can_msg, dlc) + + sizeof(m->msg.can_msg.dlc); + m->msg.can_msg.dlc = cf->can_dlc; + } else { + mlen = UCAN_OUT_HDR_SIZE + + sizeof(m->msg.can_msg.id) + cf->can_dlc; + memcpy(m->msg.can_msg.data, cf->data, cf->can_dlc); + } + m->len = cpu_to_le16(mlen); + + context->dlc = cf->can_dlc; + + m->subtype = echo_index; + + /* build the urb */ + usb_fill_bulk_urb(urb, up->udev, + usb_sndbulkpipe(up->udev, + up->out_ep_addr), + m, mlen, ucan_write_bulk_callback, context); + urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + + return urb; +} + +static void ucan_clean_up_tx_urb(struct ucan_priv *up, struct urb *urb) +{ + usb_free_coherent(up->udev, sizeof(struct ucan_message_out), + urb->transfer_buffer, urb->transfer_dma); + usb_free_urb(urb); +} + +/* callback when Linux needs to send a can frame */ +static netdev_tx_t ucan_start_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + unsigned long flags; + int ret; + u8 echo_index; + struct urb *urb; + struct ucan_urb_context *context; + struct ucan_priv *up = netdev_priv(netdev); + struct can_frame *cf = (struct can_frame *)skb->data; + + /* check skb */ + if (can_dropped_invalid_skb(netdev, skb)) + return NETDEV_TX_OK; + + /* allocate a context and slow down tx path, if fifo state is low */ + context = ucan_alloc_context(up); + echo_index = context - up->context_array; + + if (WARN_ON_ONCE(!context)) + return NETDEV_TX_BUSY; + + /* prepare urb for transmission */ + urb = ucan_prepare_tx_urb(up, context, cf, echo_index); + if (!urb) + goto drop; + + /* put the skb on can loopback stack */ + spin_lock_irqsave(&up->echo_skb_lock, flags); + can_put_echo_skb(skb, up->netdev, echo_index); + spin_unlock_irqrestore(&up->echo_skb_lock, flags); + + /* transmit it */ + usb_anchor_urb(urb, &up->tx_urbs); + ret = usb_submit_urb(urb, GFP_ATOMIC); + + /* cleanup urb */ + if (ret) { + /* on error, clean up */ + usb_unanchor_urb(urb); + ucan_clean_up_tx_urb(up, urb); + if (!ucan_release_context(up, context)) + netdev_err(up->netdev, + "xmit err: failed to release context\n"); + + /* remove the skb from the echo stack - this also + * frees the skb + */ + spin_lock_irqsave(&up->echo_skb_lock, flags); + can_free_echo_skb(up->netdev, echo_index); + spin_unlock_irqrestore(&up->echo_skb_lock, flags); + + if (ret == -ENODEV) { + netif_device_detach(up->netdev); + } else { + netdev_warn(up->netdev, + "xmit err: failed to submit urb %d\n", + ret); + up->netdev->stats.tx_dropped++; + } + return NETDEV_TX_OK; + } + + netif_trans_update(netdev); + + /* release ref, as we do not need the urb anymore */ + usb_free_urb(urb); + + return NETDEV_TX_OK; + +drop: + if (!ucan_release_context(up, context)) + netdev_err(up->netdev, + "xmit drop: failed to release context\n"); + dev_kfree_skb(skb); + up->netdev->stats.tx_dropped++; + + return NETDEV_TX_OK; +} + +/* Device goes down + * + * Clean up used resources + */ +static int ucan_close(struct net_device *netdev) +{ + int ret; + struct ucan_priv *up = netdev_priv(netdev); + + up->can.state = CAN_STATE_STOPPED; + + /* stop sending data */ + usb_kill_anchored_urbs(&up->tx_urbs); + + /* stop receiving data */ + usb_kill_anchored_urbs(&up->rx_urbs); + + /* stop and reset can device */ + ret = ucan_ctrl_command_out(up, UCAN_COMMAND_STOP, 0, 0); + if (ret < 0) + netdev_err(up->netdev, + "could not stop device, code: %d\n", + ret); + + ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0); + if (ret < 0) + netdev_err(up->netdev, + "could not reset device, code: %d\n", + ret); + + netif_stop_queue(netdev); + + ucan_release_context_array(up); + + close_candev(up->netdev); + return 0; +} + +/* CAN driver callbacks */ +static const struct net_device_ops ucan_netdev_ops = { + .ndo_open = ucan_open, + .ndo_stop = ucan_close, + .ndo_start_xmit = ucan_start_xmit, + .ndo_change_mtu = can_change_mtu, +}; + +/* Request to set bittiming + * + * This function generates an USB set bittiming message and transmits + * it to the device + */ +static int ucan_set_bittiming(struct net_device *netdev) +{ + int ret; + struct ucan_priv *up = netdev_priv(netdev); + struct ucan_ctl_cmd_set_bittiming *cmd_set_bittiming; + + cmd_set_bittiming = &up->ctl_msg_buffer->cmd_set_bittiming; + cmd_set_bittiming->tq = cpu_to_le32(up->can.bittiming.tq); + cmd_set_bittiming->brp = cpu_to_le16(up->can.bittiming.brp); + cmd_set_bittiming->sample_point = + cpu_to_le16(up->can.bittiming.sample_point); + cmd_set_bittiming->prop_seg = up->can.bittiming.prop_seg; + cmd_set_bittiming->phase_seg1 = up->can.bittiming.phase_seg1; + cmd_set_bittiming->phase_seg2 = up->can.bittiming.phase_seg2; + cmd_set_bittiming->sjw = up->can.bittiming.sjw; + + ret = ucan_ctrl_command_out(up, UCAN_COMMAND_SET_BITTIMING, 0, + sizeof(*cmd_set_bittiming)); + return (ret < 0) ? ret : 0; +} + +/* Restart the device to get it out of BUS-OFF state. + * Called when the user runs "ip link set can1 type can restart". + */ +static int ucan_set_mode(struct net_device *netdev, enum can_mode mode) +{ + int ret; + unsigned long flags; + struct ucan_priv *up = netdev_priv(netdev); + + switch (mode) { + case CAN_MODE_START: + netdev_dbg(up->netdev, "restarting device\n"); + + ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESTART, 0, 0); + up->can.state = CAN_STATE_ERROR_ACTIVE; + + /* check if queue can be restarted, + * up->available_tx_urbs must be protected by the + * lock + */ + spin_lock_irqsave(&up->context_lock, flags); + + if (up->available_tx_urbs > 0) + netif_wake_queue(up->netdev); + + spin_unlock_irqrestore(&up->context_lock, flags); + + return ret; + default: + return -EOPNOTSUPP; + } +} + +/* Probe the device, reset it and gather general device information */ +static int ucan_probe(struct usb_interface *intf, + const struct usb_device_id *id) +{ + int ret; + int i; + u32 protocol_version; + struct usb_device *udev; + struct net_device *netdev; + struct usb_host_interface *iface_desc; + struct ucan_priv *up; + struct usb_endpoint_descriptor *ep; + u16 in_ep_size; + u16 out_ep_size; + u8 in_ep_addr; + u8 out_ep_addr; + union ucan_ctl_payload *ctl_msg_buffer; + char firmware_str[sizeof(union ucan_ctl_payload) + 1]; + + udev = interface_to_usbdev(intf); + + /* Stage 1 - Interface Parsing + * --------------------------- + * + * Identifie the device USB interface descriptor and its + * endpoints. Probing is aborted on errors. + */ + + /* check if the interface is sane */ + iface_desc = intf->cur_altsetting; + if (!iface_desc) + return -ENODEV; + + dev_info(&udev->dev, + "%s: probing device on interface #%d\n", + UCAN_DRIVER_NAME, + iface_desc->desc.bInterfaceNumber); + + /* interface sanity check */ + if (iface_desc->desc.bNumEndpoints != 2) { + dev_err(&udev->dev, + "%s: invalid EP count (%d)", + UCAN_DRIVER_NAME, iface_desc->desc.bNumEndpoints); + goto err_firmware_needs_update; + } + + /* check interface endpoints */ + in_ep_addr = 0; + out_ep_addr = 0; + in_ep_size = 0; + out_ep_size = 0; + for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { + ep = &iface_desc->endpoint[i].desc; + + if (((ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK) != 0) && + ((ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_BULK)) { + /* In Endpoint */ + in_ep_addr = ep->bEndpointAddress; + in_ep_addr &= USB_ENDPOINT_NUMBER_MASK; + in_ep_size = le16_to_cpu(ep->wMaxPacketSize); + } else if (((ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == + 0) && + ((ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_BULK)) { + /* Out Endpoint */ + out_ep_addr = ep->bEndpointAddress; + out_ep_addr &= USB_ENDPOINT_NUMBER_MASK; + out_ep_size = le16_to_cpu(ep->wMaxPacketSize); + } + } + + /* check if interface is sane */ + if (!in_ep_addr || !out_ep_addr) { + dev_err(&udev->dev, "%s: invalid endpoint configuration\n", + UCAN_DRIVER_NAME); + goto err_firmware_needs_update; + } + if (in_ep_size < sizeof(struct ucan_message_in)) { + dev_err(&udev->dev, "%s: invalid in_ep MaxPacketSize\n", + UCAN_DRIVER_NAME); + goto err_firmware_needs_update; + } + if (out_ep_size < sizeof(struct ucan_message_out)) { + dev_err(&udev->dev, "%s: invalid out_ep MaxPacketSize\n", + UCAN_DRIVER_NAME); + goto err_firmware_needs_update; + } + + /* Stage 2 - Device Identification + * ------------------------------- + * + * The device interface seems to be a ucan device. Do further + * compatibility checks. On error probing is aborted, on + * success this stage leaves the ctl_msg_buffer with the + * reported contents of a GET_INFO command (supported + * bittimings, tx_fifo depth). This information is used in + * Stage 3 for the final driver initialisation. + */ + + /* Prepare Memory for control transferes */ + ctl_msg_buffer = devm_kzalloc(&udev->dev, + sizeof(union ucan_ctl_payload), + GFP_KERNEL); + if (!ctl_msg_buffer) { + dev_err(&udev->dev, + "%s: failed to allocate control pipe memory\n", + UCAN_DRIVER_NAME); + return -ENOMEM; + } + + /* get protocol version + * + * note: ucan_ctrl_command_* wrappers cannot be used yet + * because `up` is initialised in Stage 3 + */ + ret = usb_control_msg(udev, + usb_rcvctrlpipe(udev, 0), + UCAN_COMMAND_GET, + USB_DIR_IN | USB_TYPE_VENDOR | + USB_RECIP_INTERFACE, + UCAN_COMMAND_GET_PROTOCOL_VERSION, + iface_desc->desc.bInterfaceNumber, + ctl_msg_buffer, + sizeof(union ucan_ctl_payload), + UCAN_USB_CTL_PIPE_TIMEOUT); + + /* older firmware version do not support this command - those + * are not supported by this drive + */ + if (ret != 4) { + dev_err(&udev->dev, + "%s: could not read protocol version, ret=%d\n", + UCAN_DRIVER_NAME, ret); + if (ret >= 0) + ret = -EINVAL; + goto err_firmware_needs_update; + } + + /* this driver currently supports protocol version 3 only */ + protocol_version = + le32_to_cpu(ctl_msg_buffer->cmd_get_protocol_version.version); + if (protocol_version < UCAN_PROTOCOL_VERSION_MIN || + protocol_version > UCAN_PROTOCOL_VERSION_MAX) { + dev_err(&udev->dev, + "%s: device protocol version %d is not supported\n", + UCAN_DRIVER_NAME, protocol_version); + goto err_firmware_needs_update; + } + + /* request the device information and store it in ctl_msg_buffer + * + * note: ucan_ctrl_command_* wrappers connot be used yet + * because `up` is initialised in Stage 3 + */ + ret = usb_control_msg(udev, + usb_rcvctrlpipe(udev, 0), + UCAN_COMMAND_GET, + USB_DIR_IN | USB_TYPE_VENDOR | + USB_RECIP_INTERFACE, + UCAN_COMMAND_GET_INFO, + iface_desc->desc.bInterfaceNumber, + ctl_msg_buffer, + sizeof(ctl_msg_buffer->cmd_get_device_info), + UCAN_USB_CTL_PIPE_TIMEOUT); + + if (ret < 0) { + dev_err(&udev->dev, "%s: failed to retrieve device info\n", + UCAN_DRIVER_NAME); + goto err_firmware_needs_update; + } + if (ret < sizeof(ctl_msg_buffer->cmd_get_device_info)) { + dev_err(&udev->dev, "%s: device reported invalid device info\n", + UCAN_DRIVER_NAME); + goto err_firmware_needs_update; + } + if (ctl_msg_buffer->cmd_get_device_info.tx_fifo == 0) { + dev_err(&udev->dev, + "%s: device reported invalid tx-fifo size\n", + UCAN_DRIVER_NAME); + goto err_firmware_needs_update; + } + + /* Stage 3 - Driver Initialisation + * ------------------------------- + * + * Register device to Linux, prepare private structures and + * reset the device. + */ + + /* allocate driver resources */ + netdev = alloc_candev(sizeof(struct ucan_priv), + ctl_msg_buffer->cmd_get_device_info.tx_fifo); + if (!netdev) { + dev_err(&udev->dev, + "%s: cannot allocate candev\n", UCAN_DRIVER_NAME); + return -ENOMEM; + } + + up = netdev_priv(netdev); + + /* initialze data */ + up->udev = udev; + up->intf = intf; + up->netdev = netdev; + up->intf_index = iface_desc->desc.bInterfaceNumber; + up->in_ep_addr = in_ep_addr; + up->out_ep_addr = out_ep_addr; + up->in_ep_size = in_ep_size; + up->ctl_msg_buffer = ctl_msg_buffer; + up->context_array = NULL; + up->available_tx_urbs = 0; + + up->can.state = CAN_STATE_STOPPED; + up->can.bittiming_const = &up->device_info.bittiming_const; + up->can.do_set_bittiming = ucan_set_bittiming; + up->can.do_set_mode = &ucan_set_mode; + spin_lock_init(&up->context_lock); + spin_lock_init(&up->echo_skb_lock); + netdev->netdev_ops = &ucan_netdev_ops; + + usb_set_intfdata(intf, up); + SET_NETDEV_DEV(netdev, &intf->dev); + + /* parse device information + * the data retrieved in Stage 2 is still available in + * up->ctl_msg_buffer + */ + ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info); + + /* just print some device information - if available */ + ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0, + sizeof(union ucan_ctl_payload)); + if (ret > 0) { + /* copy string while ensuring zero terminiation */ + strncpy(firmware_str, up->ctl_msg_buffer->raw, + sizeof(union ucan_ctl_payload)); + firmware_str[sizeof(union ucan_ctl_payload)] = '\0'; + } else { + strcpy(firmware_str, "unknown"); + } + + /* device is compatible, reset it */ + ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0); + if (ret < 0) + goto err_free_candev; + + init_usb_anchor(&up->rx_urbs); + init_usb_anchor(&up->tx_urbs); + + up->can.state = CAN_STATE_STOPPED; + + /* register the device */ + ret = register_candev(netdev); + if (ret) + goto err_free_candev; + + /* initialisation complete, log device info */ + netdev_info(up->netdev, "registered device\n"); + netdev_info(up->netdev, "firmware string: %s\n", firmware_str); + + /* success */ + return 0; + +err_free_candev: + free_candev(netdev); + return ret; + +err_firmware_needs_update: + dev_err(&udev->dev, + "%s: probe failed; try to update the device firmware\n", + UCAN_DRIVER_NAME); + return -ENODEV; +} + +/* disconnect the device */ +static void ucan_disconnect(struct usb_interface *intf) +{ + struct usb_device *udev; + struct ucan_priv *up = usb_get_intfdata(intf); + + udev = interface_to_usbdev(intf); + + usb_set_intfdata(intf, NULL); + + if (up) { + unregister_netdev(up->netdev); + free_candev(up->netdev); + } +} + +static struct usb_device_id ucan_table[] = { + /* Mule (soldered onto compute modules) */ + {USB_DEVICE_INTERFACE_NUMBER(0x2294, 0x425a, 0)}, + /* Seal (standalone USB stick) */ + {USB_DEVICE_INTERFACE_NUMBER(0x2294, 0x425b, 0)}, + {} /* Terminating entry */ +}; + +MODULE_DEVICE_TABLE(usb, ucan_table); +/* driver callbacks */ +static struct usb_driver ucan_driver = { + .name = UCAN_DRIVER_NAME, + .probe = ucan_probe, + .disconnect = ucan_disconnect, + .id_table = ucan_table, +}; + +module_usb_driver(ucan_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Martin Elshuber <martin.elshuber@theobroma-systems.com>"); +MODULE_AUTHOR("Jakob Unterwurzacher <jakob.unterwurzacher@theobroma-systems.com>"); +MODULE_DESCRIPTION("Driver for Theobroma Systems UCAN devices"); diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 89aec07c225f..045f0845e665 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -2,6 +2,7 @@ * * Copyright (C) 2012 - 2014 Xilinx, Inc. * Copyright (C) 2009 PetaLogix. All rights reserved. + * Copyright (C) 2017 - 2018 Sandvik Mining and Construction Oy * * Description: * This driver is developed for Axi CAN IP and for Zynq CANPS Controller. @@ -25,8 +26,10 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/skbuff.h> +#include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> #include <linux/can/dev.h> @@ -48,16 +51,34 @@ enum xcan_reg { XCAN_ISR_OFFSET = 0x1C, /* Interrupt status */ XCAN_IER_OFFSET = 0x20, /* Interrupt enable */ XCAN_ICR_OFFSET = 0x24, /* Interrupt clear */ - XCAN_TXFIFO_ID_OFFSET = 0x30,/* TX FIFO ID */ - XCAN_TXFIFO_DLC_OFFSET = 0x34, /* TX FIFO DLC */ - XCAN_TXFIFO_DW1_OFFSET = 0x38, /* TX FIFO Data Word 1 */ - XCAN_TXFIFO_DW2_OFFSET = 0x3C, /* TX FIFO Data Word 2 */ - XCAN_RXFIFO_ID_OFFSET = 0x50, /* RX FIFO ID */ - XCAN_RXFIFO_DLC_OFFSET = 0x54, /* RX FIFO DLC */ - XCAN_RXFIFO_DW1_OFFSET = 0x58, /* RX FIFO Data Word 1 */ - XCAN_RXFIFO_DW2_OFFSET = 0x5C, /* RX FIFO Data Word 2 */ + + /* not on CAN FD cores */ + XCAN_TXFIFO_OFFSET = 0x30, /* TX FIFO base */ + XCAN_RXFIFO_OFFSET = 0x50, /* RX FIFO base */ + XCAN_AFR_OFFSET = 0x60, /* Acceptance Filter */ + + /* only on CAN FD cores */ + XCAN_TRR_OFFSET = 0x0090, /* TX Buffer Ready Request */ + XCAN_AFR_EXT_OFFSET = 0x00E0, /* Acceptance Filter */ + XCAN_FSR_OFFSET = 0x00E8, /* RX FIFO Status */ + XCAN_TXMSG_BASE_OFFSET = 0x0100, /* TX Message Space */ + XCAN_RXMSG_BASE_OFFSET = 0x1100, /* RX Message Space */ }; +#define XCAN_FRAME_ID_OFFSET(frame_base) ((frame_base) + 0x00) +#define XCAN_FRAME_DLC_OFFSET(frame_base) ((frame_base) + 0x04) +#define XCAN_FRAME_DW1_OFFSET(frame_base) ((frame_base) + 0x08) +#define XCAN_FRAME_DW2_OFFSET(frame_base) ((frame_base) + 0x0C) + +#define XCAN_CANFD_FRAME_SIZE 0x48 +#define XCAN_TXMSG_FRAME_OFFSET(n) (XCAN_TXMSG_BASE_OFFSET + \ + XCAN_CANFD_FRAME_SIZE * (n)) +#define XCAN_RXMSG_FRAME_OFFSET(n) (XCAN_RXMSG_BASE_OFFSET + \ + XCAN_CANFD_FRAME_SIZE * (n)) + +/* the single TX mailbox used by this driver on CAN FD HW */ +#define XCAN_TX_MAILBOX_IDX 0 + /* CAN register bit masks - XCAN_<REG>_<BIT>_MASK */ #define XCAN_SRR_CEN_MASK 0x00000002 /* CAN enable */ #define XCAN_SRR_RESET_MASK 0x00000001 /* Soft Reset the CAN core */ @@ -67,6 +88,9 @@ enum xcan_reg { #define XCAN_BTR_SJW_MASK 0x00000180 /* Synchronous jump width */ #define XCAN_BTR_TS2_MASK 0x00000070 /* Time segment 2 */ #define XCAN_BTR_TS1_MASK 0x0000000F /* Time segment 1 */ +#define XCAN_BTR_SJW_MASK_CANFD 0x000F0000 /* Synchronous jump width */ +#define XCAN_BTR_TS2_MASK_CANFD 0x00000F00 /* Time segment 2 */ +#define XCAN_BTR_TS1_MASK_CANFD 0x0000003F /* Time segment 1 */ #define XCAN_ECR_REC_MASK 0x0000FF00 /* Receive error counter */ #define XCAN_ECR_TEC_MASK 0x000000FF /* Transmit error counter */ #define XCAN_ESR_ACKER_MASK 0x00000010 /* ACK error */ @@ -80,6 +104,7 @@ enum xcan_reg { #define XCAN_SR_NORMAL_MASK 0x00000008 /* Normal mode */ #define XCAN_SR_LBACK_MASK 0x00000002 /* Loop back mode */ #define XCAN_SR_CONFIG_MASK 0x00000001 /* Configuration mode */ +#define XCAN_IXR_RXMNF_MASK 0x00020000 /* RX match not finished */ #define XCAN_IXR_TXFEMP_MASK 0x00004000 /* TX FIFO Empty */ #define XCAN_IXR_WKUP_MASK 0x00000800 /* Wake up interrupt */ #define XCAN_IXR_SLP_MASK 0x00000400 /* Sleep interrupt */ @@ -97,15 +122,15 @@ enum xcan_reg { #define XCAN_IDR_ID2_MASK 0x0007FFFE /* Extended message ident */ #define XCAN_IDR_RTR_MASK 0x00000001 /* Remote TX request */ #define XCAN_DLCR_DLC_MASK 0xF0000000 /* Data length code */ - -#define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\ - XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \ - XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \ - XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK) +#define XCAN_FSR_FL_MASK 0x00003F00 /* RX Fill Level */ +#define XCAN_FSR_IRI_MASK 0x00000080 /* RX Increment Read Index */ +#define XCAN_FSR_RI_MASK 0x0000001F /* RX Read Index */ /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ #define XCAN_BTR_TS2_SHIFT 4 /* Time segment 2 */ +#define XCAN_BTR_SJW_SHIFT_CANFD 16 /* Synchronous jump width */ +#define XCAN_BTR_TS2_SHIFT_CANFD 8 /* Time segment 2 */ #define XCAN_IDR_ID1_SHIFT 21 /* Standard Messg Identifier */ #define XCAN_IDR_ID2_SHIFT 1 /* Extended Message Identifier */ #define XCAN_DLCR_DLC_SHIFT 28 /* Data length code */ @@ -115,9 +140,31 @@ enum xcan_reg { #define XCAN_FRAME_MAX_DATA_LEN 8 #define XCAN_TIMEOUT (1 * HZ) +/* TX-FIFO-empty interrupt available */ +#define XCAN_FLAG_TXFEMP 0x0001 +/* RX Match Not Finished interrupt available */ +#define XCAN_FLAG_RXMNF 0x0002 +/* Extended acceptance filters with control at 0xE0 */ +#define XCAN_FLAG_EXT_FILTERS 0x0004 +/* TX mailboxes instead of TX FIFO */ +#define XCAN_FLAG_TX_MAILBOXES 0x0008 +/* RX FIFO with each buffer in separate registers at 0x1100 + * instead of the regular FIFO at 0x50 + */ +#define XCAN_FLAG_RX_FIFO_MULTI 0x0010 + +struct xcan_devtype_data { + unsigned int flags; + const struct can_bittiming_const *bittiming_const; + const char *bus_clk_name; + unsigned int btr_ts2_shift; + unsigned int btr_sjw_shift; +}; + /** * struct xcan_priv - This definition define CAN driver instance * @can: CAN private data structure. + * @tx_lock: Lock for synchronizing TX interrupt handling * @tx_head: Tx CAN packets ready to send on the queue * @tx_tail: Tx CAN packets successfully sended on the queue * @tx_max: Maximum number packets the driver can send @@ -129,9 +176,11 @@ enum xcan_reg { * @irq_flags: For request_irq() * @bus_clk: Pointer to struct clk * @can_clk: Pointer to struct clk + * @devtype: Device type specific constants */ struct xcan_priv { struct can_priv can; + spinlock_t tx_lock; unsigned int tx_head; unsigned int tx_tail; unsigned int tx_max; @@ -144,6 +193,7 @@ struct xcan_priv { unsigned long irq_flags; struct clk *bus_clk; struct clk *can_clk; + struct xcan_devtype_data devtype; }; /* CAN Bittiming constants as per Xilinx CAN specs */ @@ -159,6 +209,18 @@ static const struct can_bittiming_const xcan_bittiming_const = { .brp_inc = 1, }; +static const struct can_bittiming_const xcan_bittiming_const_canfd = { + .name = DRIVER_NAME, + .tseg1_min = 1, + .tseg1_max = 64, + .tseg2_min = 1, + .tseg2_max = 16, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 256, + .brp_inc = 1, +}; + /** * xcan_write_reg_le - Write a value to the device register little endian * @priv: Driver private data structure @@ -214,6 +276,23 @@ static u32 xcan_read_reg_be(const struct xcan_priv *priv, enum xcan_reg reg) } /** + * xcan_rx_int_mask - Get the mask for the receive interrupt + * @priv: Driver private data structure + * + * Return: The receive interrupt mask used by the driver on this HW + */ +static u32 xcan_rx_int_mask(const struct xcan_priv *priv) +{ + /* RXNEMP is better suited for our use case as it cannot be cleared + * while the FIFO is non-empty, but CAN FD HW does not have it + */ + if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) + return XCAN_IXR_RXOK_MASK; + else + return XCAN_IXR_RXNEMP_MASK; +} + +/** * set_reset_mode - Resets the CAN device mode * @ndev: Pointer to net_device structure * @@ -238,6 +317,10 @@ static int set_reset_mode(struct net_device *ndev) usleep_range(500, 10000); } + /* reset clears FIFOs */ + priv->tx_head = 0; + priv->tx_tail = 0; + return 0; } @@ -273,10 +356,10 @@ static int xcan_set_bittiming(struct net_device *ndev) btr1 = (bt->prop_seg + bt->phase_seg1 - 1); /* Setting Time Segment 2 in BTR Register */ - btr1 |= (bt->phase_seg2 - 1) << XCAN_BTR_TS2_SHIFT; + btr1 |= (bt->phase_seg2 - 1) << priv->devtype.btr_ts2_shift; /* Setting Synchronous jump width in BTR Register */ - btr1 |= (bt->sjw - 1) << XCAN_BTR_SJW_SHIFT; + btr1 |= (bt->sjw - 1) << priv->devtype.btr_sjw_shift; priv->write_reg(priv, XCAN_BRPR_OFFSET, btr0); priv->write_reg(priv, XCAN_BTR_OFFSET, btr1); @@ -304,6 +387,7 @@ static int xcan_chip_start(struct net_device *ndev) u32 reg_msr, reg_sr_mask; int err; unsigned long timeout; + u32 ier; /* Check if it is in reset mode */ err = set_reset_mode(ndev); @@ -315,7 +399,15 @@ static int xcan_chip_start(struct net_device *ndev) return err; /* Enable interrupts */ - priv->write_reg(priv, XCAN_IER_OFFSET, XCAN_INTR_ALL); + ier = XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK | + XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | + XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | + XCAN_IXR_ARBLST_MASK | xcan_rx_int_mask(priv); + + if (priv->devtype.flags & XCAN_FLAG_RXMNF) + ier |= XCAN_IXR_RXMNF_MASK; + + priv->write_reg(priv, XCAN_IER_OFFSET, ier); /* Check whether it is loopback mode or normal mode */ if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) { @@ -326,6 +418,12 @@ static int xcan_chip_start(struct net_device *ndev) reg_sr_mask = XCAN_SR_NORMAL_MASK; } + /* enable the first extended filter, if any, as cores with extended + * filtering default to non-receipt if all filters are disabled + */ + if (priv->devtype.flags & XCAN_FLAG_EXT_FILTERS) + priv->write_reg(priv, XCAN_AFR_EXT_OFFSET, 0x00000001); + priv->write_reg(priv, XCAN_MSR_OFFSET, reg_msr); priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_CEN_MASK); @@ -376,33 +474,15 @@ static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode) } /** - * xcan_start_xmit - Starts the transmission - * @skb: sk_buff pointer that contains data to be Txed - * @ndev: Pointer to net_device structure - * - * This function is invoked from upper layers to initiate transmission. This - * function uses the next available free txbuff and populates their fields to - * start the transmission. - * - * Return: 0 on success and failure value on error + * xcan_write_frame - Write a frame to HW + * @skb: sk_buff pointer that contains data to be Txed + * @frame_offset: Register offset to write the frame to */ -static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb, + int frame_offset) { - struct xcan_priv *priv = netdev_priv(ndev); - struct net_device_stats *stats = &ndev->stats; - struct can_frame *cf = (struct can_frame *)skb->data; u32 id, dlc, data[2] = {0, 0}; - - if (can_dropped_invalid_skb(ndev, skb)) - return NETDEV_TX_OK; - - /* Check if the TX buffer is full */ - if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) & - XCAN_SR_TXFLL_MASK)) { - netif_stop_queue(ndev); - netdev_err(ndev, "BUG!, TX FIFO full when queue awake!\n"); - return NETDEV_TX_BUSY; - } + struct can_frame *cf = (struct can_frame *)skb->data; /* Watch carefully on the bit sequence */ if (cf->can_id & CAN_EFF_FLAG) { @@ -438,26 +518,119 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (cf->can_dlc > 4) data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); - can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max); - priv->tx_head++; - - /* Write the Frame to Xilinx CAN TX FIFO */ - priv->write_reg(priv, XCAN_TXFIFO_ID_OFFSET, id); - /* If the CAN frame is RTR frame this write triggers tranmission */ - priv->write_reg(priv, XCAN_TXFIFO_DLC_OFFSET, dlc); + priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id); + /* If the CAN frame is RTR frame this write triggers transmission + * (not on CAN FD) + */ + priv->write_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_offset), dlc); if (!(cf->can_id & CAN_RTR_FLAG)) { - priv->write_reg(priv, XCAN_TXFIFO_DW1_OFFSET, data[0]); + priv->write_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_offset), + data[0]); /* If the CAN frame is Standard/Extended frame this - * write triggers tranmission + * write triggers transmission (not on CAN FD) */ - priv->write_reg(priv, XCAN_TXFIFO_DW2_OFFSET, data[1]); - stats->tx_bytes += cf->can_dlc; + priv->write_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_offset), + data[1]); } +} + +/** + * xcan_start_xmit_fifo - Starts the transmission (FIFO mode) + * + * Return: 0 on success, -ENOSPC if FIFO is full. + */ +static int xcan_start_xmit_fifo(struct sk_buff *skb, struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + unsigned long flags; + + /* Check if the TX buffer is full */ + if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) & + XCAN_SR_TXFLL_MASK)) + return -ENOSPC; + + can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max); + + spin_lock_irqsave(&priv->tx_lock, flags); + + priv->tx_head++; + + xcan_write_frame(priv, skb, XCAN_TXFIFO_OFFSET); + + /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */ + if (priv->tx_max > 1) + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK); /* Check if the TX buffer is full */ if ((priv->tx_head - priv->tx_tail) == priv->tx_max) netif_stop_queue(ndev); + spin_unlock_irqrestore(&priv->tx_lock, flags); + + return 0; +} + +/** + * xcan_start_xmit_mailbox - Starts the transmission (mailbox mode) + * + * Return: 0 on success, -ENOSPC if there is no space + */ +static int xcan_start_xmit_mailbox(struct sk_buff *skb, struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + unsigned long flags; + + if (unlikely(priv->read_reg(priv, XCAN_TRR_OFFSET) & + BIT(XCAN_TX_MAILBOX_IDX))) + return -ENOSPC; + + can_put_echo_skb(skb, ndev, 0); + + spin_lock_irqsave(&priv->tx_lock, flags); + + priv->tx_head++; + + xcan_write_frame(priv, skb, + XCAN_TXMSG_FRAME_OFFSET(XCAN_TX_MAILBOX_IDX)); + + /* Mark buffer as ready for transmit */ + priv->write_reg(priv, XCAN_TRR_OFFSET, BIT(XCAN_TX_MAILBOX_IDX)); + + netif_stop_queue(ndev); + + spin_unlock_irqrestore(&priv->tx_lock, flags); + + return 0; +} + +/** + * xcan_start_xmit - Starts the transmission + * @skb: sk_buff pointer that contains data to be Txed + * @ndev: Pointer to net_device structure + * + * This function is invoked from upper layers to initiate transmission. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full + */ +static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + int ret; + + if (can_dropped_invalid_skb(ndev, skb)) + return NETDEV_TX_OK; + + if (priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) + ret = xcan_start_xmit_mailbox(skb, ndev); + else + ret = xcan_start_xmit_fifo(skb, ndev); + + if (ret < 0) { + netdev_err(ndev, "BUG!, TX full when queue awake!\n"); + netif_stop_queue(ndev); + return NETDEV_TX_BUSY; + } + return NETDEV_TX_OK; } @@ -465,13 +638,14 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) * xcan_rx - Is called from CAN isr to complete the received * frame processing * @ndev: Pointer to net_device structure + * @frame_base: Register offset to the frame to be read * * This function is invoked from the CAN isr(poll) to process the Rx frames. It * does minimal processing and invokes "netif_receive_skb" to complete further * processing. * Return: 1 on success and 0 on failure. */ -static int xcan_rx(struct net_device *ndev) +static int xcan_rx(struct net_device *ndev, int frame_base) { struct xcan_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; @@ -486,9 +660,9 @@ static int xcan_rx(struct net_device *ndev) } /* Read a frame from Xilinx zynq CANPS */ - id_xcan = priv->read_reg(priv, XCAN_RXFIFO_ID_OFFSET); - dlc = priv->read_reg(priv, XCAN_RXFIFO_DLC_OFFSET) >> - XCAN_DLCR_DLC_SHIFT; + id_xcan = priv->read_reg(priv, XCAN_FRAME_ID_OFFSET(frame_base)); + dlc = priv->read_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_base)) >> + XCAN_DLCR_DLC_SHIFT; /* Change Xilinx CAN data length format to socketCAN data format */ cf->can_dlc = get_can_dlc(dlc); @@ -511,8 +685,8 @@ static int xcan_rx(struct net_device *ndev) } /* DW1/DW2 must always be read to remove message from RXFIFO */ - data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET); - data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET); + data[0] = priv->read_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_base)); + data[1] = priv->read_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_base)); if (!(cf->can_id & CAN_RTR_FLAG)) { /* Change Xilinx CAN data format to socketCAN data format */ @@ -530,6 +704,103 @@ static int xcan_rx(struct net_device *ndev) } /** + * xcan_current_error_state - Get current error state from HW + * @ndev: Pointer to net_device structure + * + * Checks the current CAN error state from the HW. Note that this + * only checks for ERROR_PASSIVE and ERROR_WARNING. + * + * Return: + * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE + * otherwise. + */ +static enum can_state xcan_current_error_state(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 status = priv->read_reg(priv, XCAN_SR_OFFSET); + + if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) + return CAN_STATE_ERROR_PASSIVE; + else if (status & XCAN_SR_ERRWRN_MASK) + return CAN_STATE_ERROR_WARNING; + else + return CAN_STATE_ERROR_ACTIVE; +} + +/** + * xcan_set_error_state - Set new CAN error state + * @ndev: Pointer to net_device structure + * @new_state: The new CAN state to be set + * @cf: Error frame to be populated or NULL + * + * Set new CAN error state for the device, updating statistics and + * populating the error frame if given. + */ +static void xcan_set_error_state(struct net_device *ndev, + enum can_state new_state, + struct can_frame *cf) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET); + u32 txerr = ecr & XCAN_ECR_TEC_MASK; + u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT; + enum can_state tx_state = txerr >= rxerr ? new_state : 0; + enum can_state rx_state = txerr <= rxerr ? new_state : 0; + + /* non-ERROR states are handled elsewhere */ + if (WARN_ON(new_state > CAN_STATE_ERROR_PASSIVE)) + return; + + can_change_state(ndev, cf, tx_state, rx_state); + + if (cf) { + cf->data[6] = txerr; + cf->data[7] = rxerr; + } +} + +/** + * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX + * @ndev: Pointer to net_device structure + * + * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if + * the performed RX/TX has caused it to drop to a lesser state and set + * the interface state accordingly. + */ +static void xcan_update_error_state_after_rxtx(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + enum can_state old_state = priv->can.state; + enum can_state new_state; + + /* changing error state due to successful frame RX/TX can only + * occur from these states + */ + if (old_state != CAN_STATE_ERROR_WARNING && + old_state != CAN_STATE_ERROR_PASSIVE) + return; + + new_state = xcan_current_error_state(ndev); + + if (new_state != old_state) { + struct sk_buff *skb; + struct can_frame *cf; + + skb = alloc_can_err_skb(ndev, &cf); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); + + if (skb) { + struct net_device_stats *stats = &ndev->stats; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } + } +} + +/** * xcan_err_interrupt - error frame Isr * @ndev: net_device pointer * @isr: interrupt status register value @@ -544,16 +815,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; - u32 err_status, status, txerr = 0, rxerr = 0; + u32 err_status; skb = alloc_can_err_skb(ndev, &cf); err_status = priv->read_reg(priv, XCAN_ESR_OFFSET); priv->write_reg(priv, XCAN_ESR_OFFSET, err_status); - txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK; - rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) & - XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT); - status = priv->read_reg(priv, XCAN_SR_OFFSET); if (isr & XCAN_IXR_BSOFF_MASK) { priv->can.state = CAN_STATE_BUS_OFF; @@ -563,28 +830,11 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) can_bus_off(ndev); if (skb) cf->can_id |= CAN_ERR_BUSOFF; - } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - priv->can.can_stats.error_passive++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = (rxerr > 127) ? - CAN_ERR_CRTL_RX_PASSIVE : - CAN_ERR_CRTL_TX_PASSIVE; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - priv->can.can_stats.error_warning++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] |= (txerr > rxerr) ? - CAN_ERR_CRTL_TX_WARNING : - CAN_ERR_CRTL_RX_WARNING; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } + } else { + enum can_state new_state = xcan_current_error_state(ndev); + + if (new_state != priv->can.state) + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); } /* Check for Arbitration lost interrupt */ @@ -600,13 +850,23 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) if (isr & XCAN_IXR_RXOFLW_MASK) { stats->rx_over_errors++; stats->rx_errors++; - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); if (skb) { cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW; } } + /* Check for RX Match Not Finished interrupt */ + if (isr & XCAN_IXR_RXMNF_MASK) { + stats->rx_dropped++; + stats->rx_errors++; + netdev_err(ndev, "RX match not finished, frame discarded\n"); + if (skb) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] |= CAN_ERR_CRTL_UNSPEC; + } + } + /* Check for error interrupt */ if (isr & XCAN_IXR_ERROR_MASK) { if (skb) @@ -691,6 +951,44 @@ static void xcan_state_interrupt(struct net_device *ndev, u32 isr) } /** + * xcan_rx_fifo_get_next_frame - Get register offset of next RX frame + * + * Return: Register offset of the next frame in RX FIFO. + */ +static int xcan_rx_fifo_get_next_frame(struct xcan_priv *priv) +{ + int offset; + + if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) { + u32 fsr; + + /* clear RXOK before the is-empty check so that any newly + * received frame will reassert it without a race + */ + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXOK_MASK); + + fsr = priv->read_reg(priv, XCAN_FSR_OFFSET); + + /* check if RX FIFO is empty */ + if (!(fsr & XCAN_FSR_FL_MASK)) + return -ENOENT; + + offset = XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK); + + } else { + /* check if RX FIFO is empty */ + if (!(priv->read_reg(priv, XCAN_ISR_OFFSET) & + XCAN_IXR_RXNEMP_MASK)) + return -ENOENT; + + /* frames are read from a static offset */ + offset = XCAN_RXFIFO_OFFSET; + } + + return offset; +} + +/** * xcan_rx_poll - Poll routine for rx packets (NAPI) * @napi: napi structure pointer * @quota: Max number of rx packets to be processed. @@ -704,31 +1002,35 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) { struct net_device *ndev = napi->dev; struct xcan_priv *priv = netdev_priv(ndev); - u32 isr, ier; + u32 ier; int work_done = 0; - - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); - while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) { - if (isr & XCAN_IXR_RXOK_MASK) { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXOK_MASK); - work_done += xcan_rx(ndev); - } else { + int frame_offset; + + while ((frame_offset = xcan_rx_fifo_get_next_frame(priv)) >= 0 && + (work_done < quota)) { + work_done += xcan_rx(ndev, frame_offset); + + if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) + /* increment read index */ + priv->write_reg(priv, XCAN_FSR_OFFSET, + XCAN_FSR_IRI_MASK); + else + /* clear rx-not-empty (will actually clear only if + * empty) + */ priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXNEMP_MASK); - break; - } - priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK); - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); + XCAN_IXR_RXNEMP_MASK); } - if (work_done) + if (work_done) { can_led_event(ndev, CAN_LED_EVENT_RX); + xcan_update_error_state_after_rxtx(ndev); + } if (work_done < quota) { napi_complete_done(napi, work_done); ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK); + ier |= xcan_rx_int_mask(priv); priv->write_reg(priv, XCAN_IER_OFFSET, ier); } return work_done; @@ -743,18 +1045,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) { struct xcan_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; + unsigned int frames_in_fifo; + int frames_sent = 1; /* TXOK => at least 1 frame was sent */ + unsigned long flags; + int retries = 0; + + /* Synchronize with xmit as we need to know the exact number + * of frames in the FIFO to stay in sync due to the TXFEMP + * handling. + * This also prevents a race between netif_wake_queue() and + * netif_stop_queue(). + */ + spin_lock_irqsave(&priv->tx_lock, flags); + + frames_in_fifo = priv->tx_head - priv->tx_tail; - while ((priv->tx_head - priv->tx_tail > 0) && - (isr & XCAN_IXR_TXOK_MASK)) { + if (WARN_ON_ONCE(frames_in_fifo == 0)) { + /* clear TXOK anyway to avoid getting back here */ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); - can_get_echo_skb(ndev, priv->tx_tail % - priv->tx_max); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return; + } + + /* Check if 2 frames were sent (TXOK only means that at least 1 + * frame was sent). + */ + if (frames_in_fifo > 1) { + WARN_ON(frames_in_fifo > priv->tx_max); + + /* Synchronize TXOK and isr so that after the loop: + * (1) isr variable is up-to-date at least up to TXOK clear + * time. This avoids us clearing a TXOK of a second frame + * but not noticing that the FIFO is now empty and thus + * marking only a single frame as sent. + * (2) No TXOK is left. Having one could mean leaving a + * stray TXOK as we might process the associated frame + * via TXFEMP handling as we read TXFEMP *after* TXOK + * clear to satisfy (1). + */ + while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) { + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + isr = priv->read_reg(priv, XCAN_ISR_OFFSET); + } + + if (isr & XCAN_IXR_TXFEMP_MASK) { + /* nothing in FIFO anymore */ + frames_sent = frames_in_fifo; + } + } else { + /* single frame in fifo, just clear TXOK */ + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + } + + while (frames_sent--) { + stats->tx_bytes += can_get_echo_skb(ndev, priv->tx_tail % + priv->tx_max); priv->tx_tail++; stats->tx_packets++; - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - can_led_event(ndev, CAN_LED_EVENT_TX); + netif_wake_queue(ndev); + + spin_unlock_irqrestore(&priv->tx_lock, flags); + + can_led_event(ndev, CAN_LED_EVENT_TX); + xcan_update_error_state_after_rxtx(ndev); } /** @@ -773,6 +1128,8 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) struct net_device *ndev = (struct net_device *)dev_id; struct xcan_priv *priv = netdev_priv(ndev); u32 isr, ier; + u32 isr_errors; + u32 rx_int_mask = xcan_rx_int_mask(priv); /* Get the interrupt status from Xilinx CAN */ isr = priv->read_reg(priv, XCAN_ISR_OFFSET); @@ -791,18 +1148,18 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) xcan_tx_interrupt(ndev, isr); /* Check for the type of error interrupt and Processing it */ - if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | - XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) { - priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK | - XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK | - XCAN_IXR_ARBLST_MASK)); + isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | + XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK | + XCAN_IXR_RXMNF_MASK); + if (isr_errors) { + priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors); xcan_err_interrupt(ndev, isr); } /* Check for the type of receive interrupt and Processing it */ - if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) { + if (isr & rx_int_mask) { ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK); + ier &= ~rx_int_mask; priv->write_reg(priv, XCAN_IER_OFFSET, ier); napi_schedule(&priv->napi); } @@ -819,13 +1176,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) static void xcan_chip_stop(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); - u32 ier; /* Disable interrupts and leave the can in configuration mode */ - ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~XCAN_INTR_ALL; - priv->write_reg(priv, XCAN_IER_OFFSET, ier); - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); + set_reset_mode(ndev); priv->can.state = CAN_STATE_STOPPED; } @@ -958,10 +1311,15 @@ static const struct net_device_ops xcan_netdev_ops = { */ static int __maybe_unused xcan_suspend(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_suspend(dev); + struct net_device *ndev = dev_get_drvdata(dev); - return 0; + if (netif_running(ndev)) { + netif_stop_queue(ndev); + netif_device_detach(ndev); + xcan_chip_stop(ndev); + } + + return pm_runtime_force_suspend(dev); } /** @@ -973,11 +1331,27 @@ static int __maybe_unused xcan_suspend(struct device *dev) */ static int __maybe_unused xcan_resume(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_resume(dev); + struct net_device *ndev = dev_get_drvdata(dev); + int ret; - return 0; + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + } + + if (netif_running(ndev)) { + ret = xcan_chip_start(ndev); + if (ret) { + dev_err(dev, "xcan_chip_start failed on resume\n"); + return ret; + } + + netif_device_attach(ndev); + netif_start_queue(ndev); + } + return 0; } /** @@ -992,14 +1366,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); - if (netif_running(ndev)) { - netif_stop_queue(ndev); - netif_device_detach(ndev); - } - - priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK); - priv->can.state = CAN_STATE_SLEEPING; - clk_disable_unprepare(priv->bus_clk); clk_disable_unprepare(priv->can_clk); @@ -1018,7 +1384,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); int ret; - u32 isr, status; ret = clk_prepare_enable(priv->bus_clk); if (ret) { @@ -1032,27 +1397,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) return ret; } - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); - status = priv->read_reg(priv, XCAN_SR_OFFSET); - - if (netif_running(ndev)) { - if (isr & XCAN_IXR_BSOFF_MASK) { - priv->can.state = CAN_STATE_BUS_OFF; - priv->write_reg(priv, XCAN_SRR_OFFSET, - XCAN_SRR_RESET_MASK); - } else if ((status & XCAN_SR_ESTAT_MASK) == - XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - } else { - priv->can.state = CAN_STATE_ERROR_ACTIVE; - } - netif_device_attach(ndev); - netif_start_queue(ndev); - } - return 0; } @@ -1061,6 +1405,40 @@ static const struct dev_pm_ops xcan_dev_pm_ops = { SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL) }; +static const struct xcan_devtype_data xcan_zynq_data = { + .bittiming_const = &xcan_bittiming_const, + .btr_ts2_shift = XCAN_BTR_TS2_SHIFT, + .btr_sjw_shift = XCAN_BTR_SJW_SHIFT, + .bus_clk_name = "pclk", +}; + +static const struct xcan_devtype_data xcan_axi_data = { + .bittiming_const = &xcan_bittiming_const, + .btr_ts2_shift = XCAN_BTR_TS2_SHIFT, + .btr_sjw_shift = XCAN_BTR_SJW_SHIFT, + .bus_clk_name = "s_axi_aclk", +}; + +static const struct xcan_devtype_data xcan_canfd_data = { + .flags = XCAN_FLAG_EXT_FILTERS | + XCAN_FLAG_RXMNF | + XCAN_FLAG_TX_MAILBOXES | + XCAN_FLAG_RX_FIFO_MULTI, + .bittiming_const = &xcan_bittiming_const, + .btr_ts2_shift = XCAN_BTR_TS2_SHIFT_CANFD, + .btr_sjw_shift = XCAN_BTR_SJW_SHIFT_CANFD, + .bus_clk_name = "s_axi_aclk", +}; + +/* Match table for OF platform binding */ +static const struct of_device_id xcan_of_match[] = { + { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data }, + { .compatible = "xlnx,axi-can-1.00.a", .data = &xcan_axi_data }, + { .compatible = "xlnx,canfd-1.0", .data = &xcan_canfd_data }, + { /* end of list */ }, +}; +MODULE_DEVICE_TABLE(of, xcan_of_match); + /** * xcan_probe - Platform registration call * @pdev: Handle to the platform device structure @@ -1075,8 +1453,13 @@ static int xcan_probe(struct platform_device *pdev) struct resource *res; /* IO mem resources */ struct net_device *ndev; struct xcan_priv *priv; + const struct of_device_id *of_id; + const struct xcan_devtype_data *devtype = &xcan_axi_data; void __iomem *addr; - int ret, rx_max, tx_max; + int ret; + int rx_max, tx_max; + int hw_tx_max, hw_rx_max; + const char *hw_tx_max_property; /* Get the virtual base address for the device */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1086,13 +1469,54 @@ static int xcan_probe(struct platform_device *pdev) goto err; } - ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max); - if (ret < 0) + of_id = of_match_device(xcan_of_match, &pdev->dev); + if (of_id && of_id->data) + devtype = of_id->data; + + hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ? + "tx-mailbox-count" : "tx-fifo-depth"; + + ret = of_property_read_u32(pdev->dev.of_node, hw_tx_max_property, + &hw_tx_max); + if (ret < 0) { + dev_err(&pdev->dev, "missing %s property\n", + hw_tx_max_property); goto err; + } - ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth", &rx_max); - if (ret < 0) + ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth", + &hw_rx_max); + if (ret < 0) { + dev_err(&pdev->dev, + "missing rx-fifo-depth property (mailbox mode is not supported)\n"); goto err; + } + + /* With TX FIFO: + * + * There is no way to directly figure out how many frames have been + * sent when the TXOK interrupt is processed. If TXFEMP + * is supported, we can have 2 frames in the FIFO and use TXFEMP + * to determine if 1 or 2 frames have been sent. + * Theoretically we should be able to use TXFWMEMP to determine up + * to 3 frames, but it seems that after putting a second frame in the + * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less + * than 2 frames in FIFO) is set anyway with no TXOK (a frame was + * sent), which is not a sensible state - possibly TXFWMEMP is not + * completely synchronized with the rest of the bits? + * + * With TX mailboxes: + * + * HW sends frames in CAN ID priority order. To preserve FIFO ordering + * we submit frames one at a time. + */ + if (!(devtype->flags & XCAN_FLAG_TX_MAILBOXES) && + (devtype->flags & XCAN_FLAG_TXFEMP)) + tx_max = min(hw_tx_max, 2); + else + tx_max = 1; + + rx_max = hw_rx_max; /* Create a CAN device instance */ ndev = alloc_candev(sizeof(struct xcan_priv), tx_max); @@ -1101,13 +1525,15 @@ static int xcan_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->dev = &pdev->dev; - priv->can.bittiming_const = &xcan_bittiming_const; + priv->can.bittiming_const = devtype->bittiming_const; priv->can.do_set_mode = xcan_do_set_mode; priv->can.do_get_berr_counter = xcan_get_berr_counter; priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_BERR_REPORTING; priv->reg_base = addr; priv->tx_max = tx_max; + priv->devtype = *devtype; + spin_lock_init(&priv->tx_lock); /* Get IRQ for the device */ ndev->irq = platform_get_irq(pdev, 0); @@ -1124,22 +1550,12 @@ static int xcan_probe(struct platform_device *pdev) ret = PTR_ERR(priv->can_clk); goto err_free; } - /* Check for type of CAN device */ - if (of_device_is_compatible(pdev->dev.of_node, - "xlnx,zynq-can-1.0")) { - priv->bus_clk = devm_clk_get(&pdev->dev, "pclk"); - if (IS_ERR(priv->bus_clk)) { - dev_err(&pdev->dev, "bus clock not found\n"); - ret = PTR_ERR(priv->bus_clk); - goto err_free; - } - } else { - priv->bus_clk = devm_clk_get(&pdev->dev, "s_axi_aclk"); - if (IS_ERR(priv->bus_clk)) { - dev_err(&pdev->dev, "bus clock not found\n"); - ret = PTR_ERR(priv->bus_clk); - goto err_free; - } + + priv->bus_clk = devm_clk_get(&pdev->dev, devtype->bus_clk_name); + if (IS_ERR(priv->bus_clk)) { + dev_err(&pdev->dev, "bus clock not found\n"); + ret = PTR_ERR(priv->bus_clk); + goto err_free; } priv->write_reg = xcan_write_reg_le; @@ -1172,9 +1588,9 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); - netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n", - priv->reg_base, ndev->irq, priv->can.clock.freq, - priv->tx_max); + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx buffers: actual %d, using %d\n", + priv->reg_base, ndev->irq, priv->can.clock.freq, + hw_tx_max, priv->tx_max); return 0; @@ -1208,14 +1624,6 @@ static int xcan_remove(struct platform_device *pdev) return 0; } -/* Match table for OF platform binding */ -static const struct of_device_id xcan_of_match[] = { - { .compatible = "xlnx,zynq-can-1.0", }, - { .compatible = "xlnx,axi-can-1.00.a", }, - { /* end of list */ }, -}; -MODULE_DEVICE_TABLE(of, xcan_of_match); - static struct platform_driver xcan_driver = { .probe = xcan_probe, .remove = xcan_remove, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index ac96ff40d37e..e0066adcd2f3 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -166,6 +166,11 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, reg &= ~P_TXQ_PSM_VDD(port); core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL); + /* Enable learning */ + reg = core_readl(priv, CORE_DIS_LEARN); + reg &= ~BIT(port); + core_writel(priv, reg, CORE_DIS_LEARN); + /* Enable Broadcom tags for that port if requested */ if (priv->brcm_tag_mask & BIT(port)) b53_brcm_hdr_setup(ds, port); @@ -222,8 +227,13 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port, struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); u32 reg; - if (priv->wol_ports_mask & (1 << port)) + /* Disable learning while in WoL mode */ + if (priv->wol_ports_mask & (1 << port)) { + reg = core_readl(priv, CORE_DIS_LEARN); + reg |= BIT(port); + core_writel(priv, reg, CORE_DIS_LEARN); return; + } if (port == priv->moca_port) bcm_sf2_port_intr_disable(priv, port); diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index b89acaee12d4..1e37b65aab93 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -755,7 +755,8 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port, port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES; if (fs->ring_cookie == RX_CLS_FLOW_DISC || - !dsa_is_user_port(ds, port_num) || + !(dsa_is_user_port(ds, port_num) || + dsa_is_cpu_port(ds, port_num)) || port_num >= priv->hw_params.num_ports) return -EINVAL; /* diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h index 3ccd5a865dcb..0a1e530d52b7 100644 --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -168,6 +168,8 @@ enum bcm_sf2_reg_offs { #define CORE_SWITCH_CTRL 0x00088 #define MII_DUMB_FWDG_EN (1 << 6) +#define CORE_DIS_LEARN 0x000f0 + #define CORE_SFT_LRN_CTRL 0x000f8 #define SW_LEARN_CNTL(x) (1 << (x)) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 9dd270978064..0b5a2c31f395 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = { .xlate = irq_domain_xlate_twocell, }; +/* To be called with reg_lock held */ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) { int irq, virq; @@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - + /* + * free_irq must be called without reg_lock taken because the irq + * handler takes this lock, too. + */ free_irq(chip->irq, chip); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) @@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - kthread_cancel_delayed_work_sync(&chip->irq_poll_work); kthread_destroy_worker(chip->kworker); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) @@ -2608,7 +2617,6 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6095_ops = { @@ -2774,6 +2782,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, .gpio_ops = &mv88e6352_gpio_ops, }; @@ -2955,7 +2964,6 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -3337,6 +3345,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, @@ -4523,12 +4532,10 @@ out_g2_irq: if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); out_g1_irq: - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); out: if (pdata) dev_put(pdata->netdev); @@ -4556,12 +4563,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); } static const struct of_device_id mv88e6xxx_of_match[] = { diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig index 5b7658bcf020..5c3ef9fc8207 100644 --- a/drivers/net/ethernet/3com/Kconfig +++ b/drivers/net/ethernet/3com/Kconfig @@ -32,7 +32,7 @@ config EL3 config 3C515 tristate "3c515 ISA \"Fast EtherLink\"" - depends on ISA && ISA_DMA_API + depends on ISA && ISA_DMA_API && !PPC32 ---help--- If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet network card, say Y here. diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index af766fd61151..6fde68aa13a4 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -81,7 +81,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/neterion/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" config JME @@ -128,6 +127,7 @@ config FEALNX cards. <http://www.myson.com.tw/> source "drivers/net/ethernet/natsemi/Kconfig" +source "drivers/net/ethernet/neterion/Kconfig" source "drivers/net/ethernet/netronome/Kconfig" source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/8390/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 22555e7fa752..b45d5f626b59 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -36,7 +36,6 @@ obj-$(CONFIG_NET_VENDOR_DEC) += dec/ obj-$(CONFIG_NET_VENDOR_DLINK) += dlink/ obj-$(CONFIG_NET_VENDOR_EMULEX) += emulex/ obj-$(CONFIG_NET_VENDOR_EZCHIP) += ezchip/ -obj-$(CONFIG_NET_VENDOR_EXAR) += neterion/ obj-$(CONFIG_NET_VENDOR_FARADAY) += faraday/ obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/ obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/ @@ -60,6 +59,7 @@ obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/ obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/ obj-$(CONFIG_FEALNX) += fealnx.o obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/ +obj-$(CONFIG_NET_VENDOR_NETERION) += neterion/ obj-$(CONFIG_NET_VENDOR_NETRONOME) += netronome/ obj-$(CONFIG_NET_VENDOR_NI) += ni/ obj-$(CONFIG_NET_NETX) += netx-eth.o diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 3872ab96b80a..097467f44b0d 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -802,7 +802,7 @@ static int starfire_init_one(struct pci_dev *pdev, int mii_status; for (phy = 0; phy < 32 && phy_idx < PHY_CNT; phy++) { mdio_write(dev, phy, MII_BMCR, BMCR_RESET); - mdelay(100); + msleep(100); boguscnt = 1000; while (--boguscnt > 0) if ((mdio_read(dev, phy, MII_BMCR) & BMCR_RESET) == 0) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 1b9d3130af4d..17f12c18d225 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -333,6 +333,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr)); + io_sq->dma_addr_bits = ena_dev->dma_addr_bits; io_sq->desc_entry_size = (io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ? sizeof(struct ena_eth_io_tx_desc) : diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index f273af136fc7..9e5cf5583c87 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -44,7 +44,7 @@ config AMD8111_ETH config LANCE tristate "AMD LANCE and PCnet (AT1500 and NE2100) support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. Some LinkSys cards are of this type. @@ -138,7 +138,7 @@ config PCMCIA_NMCLAN config NI65 tristate "NI6510 support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index be198cc0b10c..f5ad12c10934 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -2036,22 +2036,22 @@ static int pcnet32_alloc_ring(struct net_device *dev, const char *name) } lp->tx_dma_addr = kcalloc(lp->tx_ring_size, sizeof(dma_addr_t), - GFP_ATOMIC); + GFP_KERNEL); if (!lp->tx_dma_addr) return -ENOMEM; lp->rx_dma_addr = kcalloc(lp->rx_ring_size, sizeof(dma_addr_t), - GFP_ATOMIC); + GFP_KERNEL); if (!lp->rx_dma_addr) return -ENOMEM; lp->tx_skbuff = kcalloc(lp->tx_ring_size, sizeof(struct sk_buff *), - GFP_ATOMIC); + GFP_KERNEL); if (!lp->tx_skbuff) return -ENOMEM; lp->rx_skbuff = kcalloc(lp->rx_ring_size, sizeof(struct sk_buff *), - GFP_ATOMIC); + GFP_KERNEL); if (!lp->rx_skbuff) return -ENOMEM; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c index cc1e4f820e64..533094233659 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c @@ -289,7 +289,7 @@ static int xgbe_alloc_pages(struct xgbe_prv_data *pdata, struct page *pages = NULL; dma_addr_t pages_dma; gfp_t gfp; - int order, ret; + int order; again: order = alloc_order; @@ -316,10 +316,9 @@ again: /* Map the pages */ pages_dma = dma_map_page(pdata->dev, pages, 0, PAGE_SIZE << order, DMA_FROM_DEVICE); - ret = dma_mapping_error(pdata->dev, pages_dma); - if (ret) { + if (dma_mapping_error(pdata->dev, pages_dma)) { put_page(pages); - return ret; + return -ENOMEM; } pa->pages = pages; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 4b5d625de8f0..8a3a60bb2688 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1111,14 +1111,14 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata) if (pdata->tx_pause != pdata->phy.tx_pause) { new_state = 1; - pdata->hw_if.config_tx_flow_control(pdata); pdata->tx_pause = pdata->phy.tx_pause; + pdata->hw_if.config_tx_flow_control(pdata); } if (pdata->rx_pause != pdata->phy.rx_pause) { new_state = 1; - pdata->hw_if.config_rx_flow_control(pdata); pdata->rx_pause = pdata->phy.rx_pause; + pdata->hw_if.config_rx_flow_control(pdata); } /* Speed support */ diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 94270f654b3b..7087b88550db 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter) skb = build_skb(page_address(page) + adapter->rx_page_offset, adapter->rx_frag_size); if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); adapter->rx_page_offset += adapter->rx_frag_size; if (adapter->rx_page_offset >= PAGE_SIZE) adapter->rx_page = NULL; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index b7aa8ad96dfb..c1d3ee9baf7e 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -230,4 +230,12 @@ config BNXT_DCB If unsure, say N. +config BNXT_HWMON + bool "Broadcom NetXtreme-C/E HWMON support" + default y + depends on BNXT && HWMON && !(BNXT=y && HWMON=m) + ---help--- + Say Y if you want to expose the thermal sensor data on NetXtreme-C/E + devices, via the hwmon sysfs interface. + endif # NET_VENDOR_BROADCOM diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 631617d95769..284581c9680e 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1041,17 +1041,25 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget) return work_done; } -static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv) +static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable) { u32 reg; + reg = umac_readl(priv, UMAC_MPD_CTRL); + if (enable) + reg |= MPD_EN; + else + reg &= ~MPD_EN; + umac_writel(priv, reg, UMAC_MPD_CTRL); +} + +static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv) +{ /* Stop monitoring MPD interrupt */ intrl2_0_mask_set(priv, INTRL2_0_MPD); /* Clear the MagicPacket detection logic */ - reg = umac_readl(priv, UMAC_MPD_CTRL); - reg &= ~MPD_EN; - umac_writel(priv, reg, UMAC_MPD_CTRL); + mpd_enable_set(priv, false); netif_dbg(priv, wol, priv->netdev, "resumed from WOL\n"); } @@ -1102,10 +1110,8 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id) if (priv->irq0_stat & INTRL2_0_TX_RING_FULL) bcm_sysport_tx_reclaim_all(priv); - if (priv->irq0_stat & INTRL2_0_MPD) { + if (priv->irq0_stat & INTRL2_0_MPD) netdev_info(priv->netdev, "Wake-on-LAN interrupt!\n"); - bcm_sysport_resume_from_wol(priv); - } if (!priv->is_lite) goto out; @@ -2449,9 +2455,7 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) /* Do not leave the UniMAC RBUF matching only MPD packets */ if (!timeout) { - reg = umac_readl(priv, UMAC_MPD_CTRL); - reg &= ~MPD_EN; - umac_writel(priv, reg, UMAC_MPD_CTRL); + mpd_enable_set(priv, false); netif_err(priv, wol, ndev, "failed to enter WOL mode\n"); return -ETIMEDOUT; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index da18aa239acb..a4a90b6cdb46 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } else if ((info->flow_type == UDP_V6_FLOW) && (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) { bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested; DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } return 0; @@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir, bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id; } - return bnx2x_config_rss_eth(bp, false); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_config_rss_eth(bp, false); + + return 0; } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c612d74451a7..d7f51ab85b45 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -51,6 +51,8 @@ #include <linux/cpu_rmap.h> #include <linux/cpumask.h> #include <net/pkt_cls.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> #include "bnxt_hsi.h" #include "bnxt.h" @@ -1115,7 +1117,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, tpa_info->hash_type = PKT_HASH_TYPE_L4; tpa_info->gso_type = SKB_GSO_TCPV4; /* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */ - if (hash_type == 3) + if (hash_type == 3 || TPA_START_IS_IPV6(tpa_start1)) tpa_info->gso_type = SKB_GSO_TCPV6; tpa_info->rss_hash = le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash); @@ -3445,7 +3447,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, cp_ring_id = le16_to_cpu(req->cmpl_ring); intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1; - if (bp->flags & BNXT_FLAG_SHORT_CMD) { + if (bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) { void *short_cmd_req = bp->hwrm_short_cmd_req_addr; memcpy(short_cmd_req, req, msg_len); @@ -3638,7 +3640,9 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap, static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) { + struct hwrm_func_drv_rgtr_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_func_drv_rgtr_input req = {0}; + int rc; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1); @@ -3676,7 +3680,15 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD); } - return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + rc = -EIO; + else if (resp->flags & + cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED)) + bp->fw_cap |= BNXT_FW_CAP_IF_CHANGE; + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; } static int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp) @@ -3981,6 +3993,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1); if (set_rss) { req.hash_type = cpu_to_le32(bp->rss_hash_cfg); + req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; if (vnic->flags & BNXT_VNIC_RSS_FLAG) { if (BNXT_CHIP_TYPE_NITRO_A0(bp)) max_rings = bp->rx_nr_rings - 1; @@ -4578,7 +4591,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp) } hw_resc->resv_tx_rings = le16_to_cpu(resp->alloc_tx_rings); - if (bp->flags & BNXT_FLAG_NEW_RM) { + if (BNXT_NEW_RM(bp)) { u16 cp, stats; hw_resc->resv_rx_rings = le16_to_cpu(resp->alloc_rx_rings); @@ -4624,7 +4637,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req, req->fid = cpu_to_le16(0xffff); enables |= tx_rings ? FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS : 0; req->num_tx_rings = cpu_to_le16(tx_rings); - if (bp->flags & BNXT_FLAG_NEW_RM) { + if (BNXT_NEW_RM(bp)) { enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0; enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS | FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; @@ -4697,7 +4710,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, struct hwrm_func_vf_cfg_input req = {0}; int rc; - if (!(bp->flags & BNXT_FLAG_NEW_RM)) { + if (!BNXT_NEW_RM(bp)) { bp->hw_resc.resv_tx_rings = tx_rings; return 0; } @@ -4757,7 +4770,7 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) vnic = rx + 1; if (bp->flags & BNXT_FLAG_AGG_RINGS) rx <<= 1; - if ((bp->flags & BNXT_FLAG_NEW_RM) && + if (BNXT_NEW_RM(bp) && (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || hw_resc->resv_hw_ring_grps != grp || hw_resc->resv_vnics != vnic)) return true; @@ -4793,7 +4806,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp) return rc; tx = hw_resc->resv_tx_rings; - if (bp->flags & BNXT_FLAG_NEW_RM) { + if (BNXT_NEW_RM(bp)) { rx = hw_resc->resv_rx_rings; cp = hw_resc->resv_cp_rings; grp = hw_resc->resv_hw_ring_grps; @@ -4837,7 +4850,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, u32 flags; int rc; - if (!(bp->flags & BNXT_FLAG_NEW_RM)) + if (!BNXT_NEW_RM(bp)) return 0; __bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps, @@ -4866,7 +4879,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, __bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps, cp_rings, vnics); flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST; - if (bp->flags & BNXT_FLAG_NEW_RM) + if (BNXT_NEW_RM(bp)) flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST | FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST | FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST | @@ -5088,9 +5101,9 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) flags = le16_to_cpu(resp->flags); if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED | FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) { - bp->flags |= BNXT_FLAG_FW_LLDP_AGENT; + bp->fw_cap |= BNXT_FW_CAP_LLDP_AGENT; if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED) - bp->flags |= BNXT_FLAG_FW_DCBX_AGENT; + bp->fw_cap |= BNXT_FW_CAP_DCBX_AGENT; } if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)) bp->flags |= BNXT_FLAG_MULTI_HOST; @@ -5162,7 +5175,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all) pf->vf_resv_strategy = le16_to_cpu(resp->vf_reservation_strategy); - if (pf->vf_resv_strategy > BNXT_VF_RESV_STRATEGY_MINIMAL) + if (pf->vf_resv_strategy > BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) pf->vf_resv_strategy = BNXT_VF_RESV_STRATEGY_MAXIMAL; } hwrm_func_resc_qcaps_exit: @@ -5248,7 +5261,7 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) if (bp->hwrm_spec_code >= 0x10803) { rc = bnxt_hwrm_func_resc_qcaps(bp, true); if (!rc) - bp->flags |= BNXT_FLAG_NEW_RM; + bp->fw_cap |= BNXT_FW_CAP_NEW_RM; } return 0; } @@ -5268,7 +5281,8 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp) int rc = 0; struct hwrm_queue_qportcfg_input req = {0}; struct hwrm_queue_qportcfg_output *resp = bp->hwrm_cmd_resp_addr; - u8 i, *qptr; + u8 i, j, *qptr; + bool no_rdma; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_QPORTCFG, -1, -1); @@ -5286,19 +5300,24 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp) if (bp->max_tc > BNXT_MAX_QUEUE) bp->max_tc = BNXT_MAX_QUEUE; + no_rdma = !(bp->flags & BNXT_FLAG_ROCE_CAP); + qptr = &resp->queue_id0; + for (i = 0, j = 0; i < bp->max_tc; i++) { + bp->q_info[j].queue_id = *qptr++; + bp->q_info[j].queue_profile = *qptr++; + bp->tc_to_qidx[j] = j; + if (!BNXT_CNPQ(bp->q_info[j].queue_profile) || + (no_rdma && BNXT_PF(bp))) + j++; + } + bp->max_tc = max_t(u8, j, 1); + if (resp->queue_cfg_info & QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG) bp->max_tc = 1; if (bp->max_lltc > bp->max_tc) bp->max_lltc = bp->max_tc; - qptr = &resp->queue_id0; - for (i = 0; i < bp->max_tc; i++) { - bp->q_info[i].queue_id = *qptr++; - bp->q_info[i].queue_profile = *qptr++; - bp->tc_to_qidx[i] = i; - } - qportcfg_exit: mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -5351,7 +5370,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) dev_caps_cfg = le32_to_cpu(resp->dev_caps_cfg); if ((dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED) && (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED)) - bp->flags |= BNXT_FLAG_SHORT_CMD; + bp->fw_cap |= BNXT_FW_CAP_SHORT_CMD; hwrm_ver_get_exit: mutex_unlock(&bp->hwrm_cmd_lock); @@ -5920,7 +5939,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num) max_idx = min_t(int, bp->total_irqs, max_cp); avail_msix = max_idx - bp->cp_nr_rings; - if (!(bp->flags & BNXT_FLAG_NEW_RM) || avail_msix >= num) + if (!BNXT_NEW_RM(bp) || avail_msix >= num) return avail_msix; if (max_irq < total_req) { @@ -5933,7 +5952,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num) static int bnxt_get_num_msix(struct bnxt *bp) { - if (!(bp->flags & BNXT_FLAG_NEW_RM)) + if (!BNXT_NEW_RM(bp)) return bnxt_get_max_func_irqs(bp); return bnxt_cp_rings_in_use(bp); @@ -6056,8 +6075,7 @@ int bnxt_reserve_rings(struct bnxt *bp) netdev_err(bp->dev, "ring reservation failure rc: %d\n", rc); return rc; } - if ((bp->flags & BNXT_FLAG_NEW_RM) && - (bnxt_get_num_msix(bp) != bp->total_irqs)) { + if (BNXT_NEW_RM(bp) && (bnxt_get_num_msix(bp) != bp->total_irqs)) { bnxt_ulp_irq_stop(bp); bnxt_clear_int_mode(bp); rc = bnxt_init_int_mode(bp); @@ -6337,6 +6355,10 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) & PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK; } + if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED) { + if (bp->test_info) + bp->test_info->flags |= BNXT_TEST_FL_EXT_LPBK; + } if (resp->supported_speeds_auto_mode) link_info->support_auto_speeds = le16_to_cpu(resp->supported_speeds_auto_mode); @@ -6633,6 +6655,39 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } +static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) +{ + struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_func_drv_if_change_input req = {0}; + bool resc_reinit = false; + int rc; + + if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE)) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_IF_CHANGE, -1, -1); + if (up) + req.flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc && (resp->flags & + cpu_to_le32(FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE))) + resc_reinit = true; + mutex_unlock(&bp->hwrm_cmd_lock); + + if (up && resc_reinit && BNXT_NEW_RM(bp)) { + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + + rc = bnxt_hwrm_func_resc_qcaps(bp, true); + hw_resc->resv_cp_rings = 0; + hw_resc->resv_tx_rings = 0; + hw_resc->resv_rx_rings = 0; + hw_resc->resv_hw_ring_grps = 0; + hw_resc->resv_vnics = 0; + } + return rc; +} + static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp) { struct hwrm_port_led_qcaps_output *resp = bp->hwrm_cmd_resp_addr; @@ -6742,6 +6797,62 @@ static void bnxt_get_wol_settings(struct bnxt *bp) } while (handle && handle != 0xffff); } +#ifdef CONFIG_BNXT_HWMON +static ssize_t bnxt_show_temp(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + struct hwrm_temp_monitor_query_input req = {0}; + struct hwrm_temp_monitor_query_output *resp; + struct bnxt *bp = dev_get_drvdata(dev); + u32 temp = 0; + + resp = bp->hwrm_cmd_resp_addr; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); + mutex_lock(&bp->hwrm_cmd_lock); + if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + temp = resp->temp * 1000; /* display millidegree */ + mutex_unlock(&bp->hwrm_cmd_lock); + + return sprintf(buf, "%u\n", temp); +} +static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0); + +static struct attribute *bnxt_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(bnxt); + +static void bnxt_hwmon_close(struct bnxt *bp) +{ + if (bp->hwmon_dev) { + hwmon_device_unregister(bp->hwmon_dev); + bp->hwmon_dev = NULL; + } +} + +static void bnxt_hwmon_open(struct bnxt *bp) +{ + struct pci_dev *pdev = bp->pdev; + + bp->hwmon_dev = hwmon_device_register_with_groups(&pdev->dev, + DRV_MODULE_NAME, bp, + bnxt_groups); + if (IS_ERR(bp->hwmon_dev)) { + bp->hwmon_dev = NULL; + dev_warn(&pdev->dev, "Cannot register hwmon device\n"); + } +} +#else +static void bnxt_hwmon_close(struct bnxt *bp) +{ +} + +static void bnxt_hwmon_open(struct bnxt *bp) +{ +} +#endif + static bool bnxt_eee_config_ok(struct bnxt *bp) { struct ethtool_eee *eee = &bp->eee; @@ -6894,8 +7005,14 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) mutex_lock(&bp->link_lock); rc = bnxt_update_phy_setting(bp); mutex_unlock(&bp->link_lock); - if (rc) + if (rc) { netdev_warn(bp->dev, "failed to update phy settings\n"); + if (BNXT_SINGLE_PF(bp)) { + bp->link_info.phy_retry = true; + bp->link_info.phy_retry_expires = + jiffies + 5 * HZ; + } + } } if (irq_re_init) @@ -6981,8 +7098,16 @@ void bnxt_half_close_nic(struct bnxt *bp) static int bnxt_open(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); + int rc; + + bnxt_hwrm_if_change(bp, true); + rc = __bnxt_open_nic(bp, true, true); + if (rc) + bnxt_hwrm_if_change(bp, false); + + bnxt_hwmon_open(bp); - return __bnxt_open_nic(bp, true, true); + return rc; } static bool bnxt_drv_busy(struct bnxt *bp) @@ -7044,8 +7169,10 @@ static int bnxt_close(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); + bnxt_hwmon_close(bp); bnxt_close_nic(bp, true, true); bnxt_hwrm_shutdown_link(bp); + bnxt_hwrm_if_change(bp, false); return 0; } @@ -7295,7 +7422,7 @@ skip_uc: static bool bnxt_can_reserve_rings(struct bnxt *bp) { #ifdef CONFIG_BNXT_SRIOV - if ((bp->flags & BNXT_FLAG_NEW_RM) && BNXT_VF(bp)) { + if (BNXT_NEW_RM(bp) && BNXT_VF(bp)) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; /* No minimum rings were provisioned by the PF. Don't @@ -7345,7 +7472,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp) return false; } - if (!(bp->flags & BNXT_FLAG_NEW_RM)) + if (!BNXT_NEW_RM(bp)) return true; if (vnics == bp->hw_resc.resv_vnics) @@ -7579,6 +7706,16 @@ static void bnxt_timer(struct timer_list *t) set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event); bnxt_queue_sp_work(bp); } + + if (bp->link_info.phy_retry) { + if (time_after(jiffies, bp->link_info.phy_retry_expires)) { + bp->link_info.phy_retry = 0; + netdev_warn(bp->dev, "failed to update phy settings after maximum retries.\n"); + } else { + set_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event); + bnxt_queue_sp_work(bp); + } + } bnxt_restart_timer: mod_timer(&bp->timer, jiffies + bp->current_interval); } @@ -7666,6 +7803,19 @@ static void bnxt_sp_task(struct work_struct *work) netdev_err(bp->dev, "SP task can't update link (rc: %x)\n", rc); } + if (test_and_clear_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event)) { + int rc; + + mutex_lock(&bp->link_lock); + rc = bnxt_update_phy_setting(bp); + mutex_unlock(&bp->link_lock); + if (rc) { + netdev_warn(bp->dev, "update phy settings retry failed\n"); + } else { + bp->link_info.phy_retry = false; + netdev_info(bp->dev, "update phy settings retry succeeded\n"); + } + } if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) { mutex_lock(&bp->link_lock); bnxt_get_port_module_status(bp); @@ -7718,7 +7868,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, if (bp->flags & BNXT_FLAG_AGG_RINGS) rx_rings <<= 1; cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx; - if (bp->flags & BNXT_FLAG_NEW_RM) + if (BNXT_NEW_RM(bp)) cp += bnxt_get_ulp_msix_num(bp); return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp, vnics); @@ -8727,7 +8877,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; - if (bp->flags & BNXT_FLAG_SHORT_CMD) { + if (bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) { rc = bnxt_alloc_hwrm_short_cmd_req(bp); if (rc) goto init_err_pci_clean; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 934aa11c82eb..fefa011320e0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -12,11 +12,11 @@ #define BNXT_H #define DRV_MODULE_NAME "bnxt_en" -#define DRV_MODULE_VERSION "1.9.1" +#define DRV_MODULE_VERSION "1.9.2" #define DRV_VER_MAJ 1 #define DRV_VER_MIN 9 -#define DRV_VER_UPD 1 +#define DRV_VER_UPD 2 #include <linux/interrupt.h> #include <linux/rhashtable.h> @@ -326,6 +326,10 @@ struct rx_tpa_start_cmp_ext { ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ RX_TPA_START_CMP_CFA_CODE) >> RX_TPA_START_CMPL_CFA_CODE_SHIFT) +#define TPA_START_IS_IPV6(rx_tpa_start) \ + (!!((rx_tpa_start)->rx_tpa_start_cmp_flags2 & \ + cpu_to_le32(RX_TPA_START_CMP_FLAGS2_IP_TYPE))) + struct rx_tpa_end_cmp { __le32 rx_tpa_end_cmp_len_flags_type; #define RX_TPA_END_CMP_TYPE (0x3f << 0) @@ -862,6 +866,7 @@ struct bnxt_pf_info { u8 vf_resv_strategy; #define BNXT_VF_RESV_STRATEGY_MAXIMAL 0 #define BNXT_VF_RESV_STRATEGY_MINIMAL 1 +#define BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC 2 void *hwrm_cmd_req_addr[4]; dma_addr_t hwrm_cmd_req_dma_addr[4]; struct bnxt_vf_info *vf; @@ -959,6 +964,9 @@ struct bnxt_link_info { u16 advertising; /* user adv setting */ bool force_link_chng; + bool phy_retry; + unsigned long phy_retry_expires; + /* a copy of phy_qcfg output used to report link * info to VF */ @@ -990,6 +998,8 @@ struct bnxt_led_info { struct bnxt_test_info { u8 offline_mask; + u8 flags; +#define BNXT_TEST_FL_EXT_LPBK 0x1 u16 timeout; char string[BNXT_MAX_TEST][ETH_GSTRING_LEN]; }; @@ -1134,7 +1144,6 @@ struct bnxt { atomic_t intr_sem; u32 flags; - #define BNXT_FLAG_DCB_ENABLED 0x1 #define BNXT_FLAG_VF 0x2 #define BNXT_FLAG_LRO 0x4 #ifdef CONFIG_INET @@ -1163,15 +1172,11 @@ struct bnxt { BNXT_FLAG_ROCEV2_CAP) #define BNXT_FLAG_NO_AGG_RINGS 0x20000 #define BNXT_FLAG_RX_PAGE_MODE 0x40000 - #define BNXT_FLAG_FW_LLDP_AGENT 0x80000 #define BNXT_FLAG_MULTI_HOST 0x100000 - #define BNXT_FLAG_SHORT_CMD 0x200000 #define BNXT_FLAG_DOUBLE_DB 0x400000 - #define BNXT_FLAG_FW_DCBX_AGENT 0x800000 #define BNXT_FLAG_CHIP_NITRO_A0 0x1000000 #define BNXT_FLAG_DIM 0x2000000 #define BNXT_FLAG_ROCE_MIRROR_CAP 0x4000000 - #define BNXT_FLAG_NEW_RM 0x8000000 #define BNXT_FLAG_PORT_STATS_EXT 0x10000000 #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ @@ -1276,10 +1281,19 @@ struct bnxt { struct ieee_ets *ieee_ets; u8 dcbx_cap; u8 default_pri; + u8 max_dscp_value; #endif /* CONFIG_BNXT_DCB */ u32 msg_enable; + u32 fw_cap; + #define BNXT_FW_CAP_SHORT_CMD 0x00000001 + #define BNXT_FW_CAP_LLDP_AGENT 0x00000002 + #define BNXT_FW_CAP_DCBX_AGENT 0x00000004 + #define BNXT_FW_CAP_NEW_RM 0x00000008 + #define BNXT_FW_CAP_IF_CHANGE 0x00000010 + +#define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; u16 hwrm_cmd_seq; u32 hwrm_intr_seq_id; @@ -1342,6 +1356,7 @@ struct bnxt { #define BNXT_GENEVE_DEL_PORT_SP_EVENT 13 #define BNXT_LINK_SPEED_CHNG_SP_EVENT 14 #define BNXT_FLOW_STATS_SP_EVENT 15 +#define BNXT_UPDATE_PHY_SP_EVENT 16 struct bnxt_hw_resc hw_resc; struct bnxt_pf_info pf; @@ -1397,6 +1412,7 @@ struct bnxt { struct bnxt_tc_info *tc_info; struct dentry *debugfs_pdev; struct dentry *debugfs_dim; + struct device *hwmon_dev; }; #define BNXT_RX_STATS_OFFSET(counter) \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h new file mode 100644 index 000000000000..09c22f8fe399 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h @@ -0,0 +1,66 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2018 Broadcom Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#ifndef BNXT_COREDUMP_H +#define BNXT_COREDUMP_H + +struct bnxt_coredump_segment_hdr { + __u8 signature[4]; + __le32 component_id; + __le32 segment_id; + __le32 flags; + __u8 low_version; + __u8 high_version; + __le16 function_id; + __le32 offset; + __le32 length; + __le32 status; + __le32 duration; + __le32 data_offset; + __le32 instance; + __le32 rsvd[5]; +}; + +struct bnxt_coredump_record { + __u8 signature[4]; + __le32 flags; + __u8 low_version; + __u8 high_version; + __u8 asic_state; + __u8 rsvd0[5]; + char system_name[32]; + __le16 year; + __le16 month; + __le16 day; + __le16 hour; + __le16 minute; + __le16 second; + __le16 utc_bias; + __le16 rsvd1; + char commandline[256]; + __le32 total_segments; + __le32 os_ver_major; + __le32 os_ver_minor; + __le32 rsvd2; + char os_name[32]; + __le16 end_year; + __le16 end_month; + __le16 end_day; + __le16 end_hour; + __le16 end_minute; + __le16 end_second; + __le16 end_utc_bias; + __le32 asic_id1; + __le32 asic_id2; + __le32 coredump_status; + __u8 ioctl_low_version; + __u8 ioctl_high_version; + __le16 rsvd3[313]; +}; +#endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index d5bc72cecde3..ddc98c359488 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -385,6 +385,61 @@ set_app_exit: return rc; } +static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp) +{ + struct hwrm_queue_dscp_qcaps_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_queue_dscp_qcaps_input req = {0}; + int rc; + + if (bp->hwrm_spec_code < 0x10800 || BNXT_VF(bp)) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP_QCAPS, -1, -1); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) { + bp->max_dscp_value = (1 << resp->num_dscp_bits) - 1; + if (bp->max_dscp_value < 0x3f) + bp->max_dscp_value = 0; + } + + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app, + bool add) +{ + struct hwrm_queue_dscp2pri_cfg_input req = {0}; + struct bnxt_dscp2pri_entry *dscp2pri; + dma_addr_t mapping; + int rc; + + if (bp->hwrm_spec_code < 0x10800) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP2PRI_CFG, -1, -1); + dscp2pri = dma_alloc_coherent(&bp->pdev->dev, sizeof(*dscp2pri), + &mapping, GFP_KERNEL); + if (!dscp2pri) + return -ENOMEM; + + req.src_data_addr = cpu_to_le64(mapping); + dscp2pri->dscp = app->protocol; + if (add) + dscp2pri->mask = 0x3f; + else + dscp2pri->mask = 0; + dscp2pri->pri = app->priority; + req.entry_cnt = cpu_to_le16(1); + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + rc = -EIO; + dma_free_coherent(&bp->pdev->dev, sizeof(*dscp2pri), dscp2pri, + mapping); + return rc; +} + static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc) { int total_ets_bw = 0; @@ -551,15 +606,30 @@ static int bnxt_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) return rc; } +static int bnxt_dcbnl_ieee_dscp_app_prep(struct bnxt *bp, struct dcb_app *app) +{ + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) { + if (!bp->max_dscp_value) + return -ENOTSUPP; + if (app->protocol > bp->max_dscp_value) + return -EINVAL; + } + return 0; +} + static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) { struct bnxt *bp = netdev_priv(dev); - int rc = -EINVAL; + int rc; if (!(bp->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || !(bp->dcbx_cap & DCB_CAP_DCBX_HOST)) return -EINVAL; + rc = bnxt_dcbnl_ieee_dscp_app_prep(bp, app); + if (rc) + return rc; + rc = dcb_ieee_setapp(dev, app); if (rc) return rc; @@ -570,6 +640,9 @@ static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) app->protocol == ROCE_V2_UDP_DPORT)) rc = bnxt_hwrm_set_dcbx_app(bp, app, true); + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + rc = bnxt_hwrm_queue_dscp2pri_cfg(bp, app, true); + return rc; } @@ -582,6 +655,10 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) !(bp->dcbx_cap & DCB_CAP_DCBX_HOST)) return -EINVAL; + rc = bnxt_dcbnl_ieee_dscp_app_prep(bp, app); + if (rc) + return rc; + rc = dcb_ieee_delapp(dev, app); if (rc) return rc; @@ -591,6 +668,9 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) app->protocol == ROCE_V2_UDP_DPORT)) rc = bnxt_hwrm_set_dcbx_app(bp, app, false); + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + rc = bnxt_hwrm_queue_dscp2pri_cfg(bp, app, false); + return rc; } @@ -610,7 +690,7 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode) return 1; if (mode & DCB_CAP_DCBX_HOST) { - if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) + if (BNXT_VF(bp) || (bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT)) return 1; /* only support IEEE */ @@ -642,10 +722,11 @@ void bnxt_dcb_init(struct bnxt *bp) if (bp->hwrm_spec_code < 0x10501) return; + bnxt_hwrm_queue_dscp_qcaps(bp); bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE; - if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) + if (BNXT_PF(bp) && !(bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT)) bp->dcbx_cap |= DCB_CAP_DCBX_HOST; - else if (bp->flags & BNXT_FLAG_FW_DCBX_AGENT) + else if (bp->fw_cap & BNXT_FW_CAP_DCBX_AGENT) bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED; bp->dev->dcbnl_ops = &dcbnl_ops; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h index 69efde785f23..6eed231de565 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h @@ -33,10 +33,20 @@ struct bnxt_cos2bw_cfg { u8 unused; }; +struct bnxt_dscp2pri_entry { + u8 dscp; + u8 mask; + u8 pri; +}; + #define BNXT_LLQ(q_profile) \ ((q_profile) == \ QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE) +#define BNXT_CNPQ(q_profile) \ + ((q_profile) == \ + QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP) + #define HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL 0x0300 void bnxt_dcb_init(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 7bd96ab4f7c5..f3b9fbcc705b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -29,7 +29,7 @@ static const struct bnxt_dl_nvm_param nvm_params[] = { static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, int msg_len, union devlink_param_value *val) { - struct hwrm_nvm_variable_input *req = msg; + struct hwrm_nvm_get_variable_input *req = msg; void *data_addr = NULL, *buf = NULL; struct bnxt_dl_nvm_param nvm_param; int bytesize, idx = 0, rc, i; @@ -60,18 +60,18 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, if (!data_addr) return -ENOMEM; - req->data_addr = cpu_to_le64(data_dma_addr); + req->dest_data_addr = cpu_to_le64(data_dma_addr); req->data_len = cpu_to_le16(nvm_param.num_bits); req->option_num = cpu_to_le16(nvm_param.offset); req->index_0 = cpu_to_le16(idx); if (idx) req->dimensions = cpu_to_le16(1); - if (req->req_type == HWRM_NVM_SET_VARIABLE) + if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) memcpy(data_addr, buf, bytesize); rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT); - if (!rc && req->req_type == HWRM_NVM_GET_VARIABLE) + if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE)) memcpy(buf, data_addr, bytesize); dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 7270c8b0cef3..b6dbc3f6d309 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -16,12 +16,15 @@ #include <linux/etherdevice.h> #include <linux/crc32.h> #include <linux/firmware.h> +#include <linux/utsname.h> +#include <linux/time.h> #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_xdp.h" #include "bnxt_ethtool.h" #include "bnxt_nvm_defs.h" /* NVRAM content constant and structure defs */ #include "bnxt_fw_hdr.h" /* Firmware hdr constant and structure defs */ +#include "bnxt_coredump.h" #define FLASH_NVRAM_TIMEOUT ((HWRM_CMD_TIMEOUT) * 100) #define FLASH_PACKAGE_TIMEOUT ((HWRM_CMD_TIMEOUT) * 200) #define INSTALL_PACKAGE_TIMEOUT ((HWRM_CMD_TIMEOUT) * 200) @@ -112,6 +115,11 @@ static int bnxt_set_coalesce(struct net_device *dev, BNXT_MAX_STATS_COAL_TICKS); stats_ticks = rounddown(stats_ticks, BNXT_MIN_STATS_COAL_TICKS); bp->stats_coal_ticks = stats_ticks; + if (bp->stats_coal_ticks) + bp->current_interval = + bp->stats_coal_ticks * HZ / 1000000; + else + bp->current_interval = BNXT_TIMER_INTERVAL; update_stats = true; } @@ -162,7 +170,7 @@ static const struct { BNXT_RX_STATS_ENTRY(rx_128b_255b_frames), BNXT_RX_STATS_ENTRY(rx_256b_511b_frames), BNXT_RX_STATS_ENTRY(rx_512b_1023b_frames), - BNXT_RX_STATS_ENTRY(rx_1024b_1518_frames), + BNXT_RX_STATS_ENTRY(rx_1024b_1518b_frames), BNXT_RX_STATS_ENTRY(rx_good_vlan_frames), BNXT_RX_STATS_ENTRY(rx_1519b_2047b_frames), BNXT_RX_STATS_ENTRY(rx_2048b_4095b_frames), @@ -205,9 +213,9 @@ static const struct { BNXT_TX_STATS_ENTRY(tx_128b_255b_frames), BNXT_TX_STATS_ENTRY(tx_256b_511b_frames), BNXT_TX_STATS_ENTRY(tx_512b_1023b_frames), - BNXT_TX_STATS_ENTRY(tx_1024b_1518_frames), + BNXT_TX_STATS_ENTRY(tx_1024b_1518b_frames), BNXT_TX_STATS_ENTRY(tx_good_vlan_frames), - BNXT_TX_STATS_ENTRY(tx_1519b_2047_frames), + BNXT_TX_STATS_ENTRY(tx_1519b_2047b_frames), BNXT_TX_STATS_ENTRY(tx_2048b_4095b_frames), BNXT_TX_STATS_ENTRY(tx_4096b_9216b_frames), BNXT_TX_STATS_ENTRY(tx_9217b_16383b_frames), @@ -463,7 +471,7 @@ static void bnxt_get_channels(struct net_device *dev, int max_tx_sch_inputs; /* Get the most up-to-date max_tx_sch_inputs. */ - if (bp->flags & BNXT_FLAG_NEW_RM) + if (BNXT_NEW_RM(bp)) bnxt_hwrm_func_resc_qcaps(bp, false); max_tx_sch_inputs = hw_resc->max_tx_sch_inputs; @@ -2392,7 +2400,7 @@ static int bnxt_disable_an_for_lpbk(struct bnxt *bp, return rc; } -static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable) +static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable, bool ext) { struct hwrm_port_phy_cfg_input req = {0}; @@ -2400,7 +2408,10 @@ static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable) if (enable) { bnxt_disable_an_for_lpbk(bp, &req); - req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL; + if (ext) + req.lpbk = PORT_PHY_CFG_REQ_LPBK_EXTERNAL; + else + req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL; } else { req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE; } @@ -2533,15 +2544,17 @@ static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results) return rc; } -#define BNXT_DRV_TESTS 3 +#define BNXT_DRV_TESTS 4 #define BNXT_MACLPBK_TEST_IDX (bp->num_tests - BNXT_DRV_TESTS) #define BNXT_PHYLPBK_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 1) -#define BNXT_IRQ_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 2) +#define BNXT_EXTLPBK_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 2) +#define BNXT_IRQ_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 3) static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, u64 *buf) { struct bnxt *bp = netdev_priv(dev); + bool do_ext_lpbk = false; bool offline = false; u8 test_results = 0; u8 test_mask = 0; @@ -2555,6 +2568,10 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, return; } + if ((etest->flags & ETH_TEST_FL_EXTERNAL_LB) && + (bp->test_info->flags & BNXT_TEST_FL_EXT_LPBK)) + do_ext_lpbk = true; + if (etest->flags & ETH_TEST_FL_OFFLINE) { if (bp->pf.active_vfs) { etest->flags |= ETH_TEST_FL_FAILED; @@ -2595,13 +2612,22 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, buf[BNXT_MACLPBK_TEST_IDX] = 0; bnxt_hwrm_mac_loopback(bp, false); - bnxt_hwrm_phy_loopback(bp, true); + bnxt_hwrm_phy_loopback(bp, true, false); msleep(1000); if (bnxt_run_loopback(bp)) { buf[BNXT_PHYLPBK_TEST_IDX] = 1; etest->flags |= ETH_TEST_FL_FAILED; } - bnxt_hwrm_phy_loopback(bp, false); + if (do_ext_lpbk) { + etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE; + bnxt_hwrm_phy_loopback(bp, true, true); + msleep(1000); + if (bnxt_run_loopback(bp)) { + buf[BNXT_EXTLPBK_TEST_IDX] = 1; + etest->flags |= ETH_TEST_FL_FAILED; + } + } + bnxt_hwrm_phy_loopback(bp, false, false); bnxt_half_close_nic(bp); bnxt_open_nic(bp, false, true); } @@ -2662,6 +2688,334 @@ static int bnxt_reset(struct net_device *dev, u32 *flags) return rc; } +static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len, + struct bnxt_hwrm_dbg_dma_info *info) +{ + struct hwrm_dbg_cmn_output *cmn_resp = bp->hwrm_cmd_resp_addr; + struct hwrm_dbg_cmn_input *cmn_req = msg; + __le16 *seq_ptr = msg + info->seq_off; + u16 seq = 0, len, segs_off; + void *resp = cmn_resp; + dma_addr_t dma_handle; + int rc, off = 0; + void *dma_buf; + + dma_buf = dma_alloc_coherent(&bp->pdev->dev, info->dma_len, &dma_handle, + GFP_KERNEL); + if (!dma_buf) + return -ENOMEM; + + segs_off = offsetof(struct hwrm_dbg_coredump_list_output, + total_segments); + cmn_req->host_dest_addr = cpu_to_le64(dma_handle); + cmn_req->host_buf_len = cpu_to_le32(info->dma_len); + mutex_lock(&bp->hwrm_cmd_lock); + while (1) { + *seq_ptr = cpu_to_le16(seq); + rc = _hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT); + if (rc) + break; + + len = le16_to_cpu(*((__le16 *)(resp + info->data_len_off))); + if (!seq && + cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) { + info->segs = le16_to_cpu(*((__le16 *)(resp + + segs_off))); + if (!info->segs) { + rc = -EIO; + break; + } + + info->dest_buf_size = info->segs * + sizeof(struct coredump_segment_record); + info->dest_buf = kmalloc(info->dest_buf_size, + GFP_KERNEL); + if (!info->dest_buf) { + rc = -ENOMEM; + break; + } + } + + if (info->dest_buf) + memcpy(info->dest_buf + off, dma_buf, len); + + if (cmn_req->req_type == + cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE)) + info->dest_buf_size += len; + + if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE)) + break; + + seq++; + off += len; + } + mutex_unlock(&bp->hwrm_cmd_lock); + dma_free_coherent(&bp->pdev->dev, info->dma_len, dma_buf, dma_handle); + return rc; +} + +static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp, + struct bnxt_coredump *coredump) +{ + struct hwrm_dbg_coredump_list_input req = {0}; + struct bnxt_hwrm_dbg_dma_info info = {NULL}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_LIST, -1, -1); + + info.dma_len = COREDUMP_LIST_BUF_LEN; + info.seq_off = offsetof(struct hwrm_dbg_coredump_list_input, seq_no); + info.data_len_off = offsetof(struct hwrm_dbg_coredump_list_output, + data_len); + + rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info); + if (!rc) { + coredump->data = info.dest_buf; + coredump->data_size = info.dest_buf_size; + coredump->total_segs = info.segs; + } + return rc; +} + +static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id, + u16 segment_id) +{ + struct hwrm_dbg_coredump_initiate_input req = {0}; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_INITIATE, -1, -1); + req.component_id = cpu_to_le16(component_id); + req.segment_id = cpu_to_le16(segment_id); + + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + +static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, + u16 segment_id, u32 *seg_len, + void *buf, u32 offset) +{ + struct hwrm_dbg_coredump_retrieve_input req = {0}; + struct bnxt_hwrm_dbg_dma_info info = {NULL}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_RETRIEVE, -1, -1); + req.component_id = cpu_to_le16(component_id); + req.segment_id = cpu_to_le16(segment_id); + + info.dma_len = COREDUMP_RETRIEVE_BUF_LEN; + info.seq_off = offsetof(struct hwrm_dbg_coredump_retrieve_input, + seq_no); + info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output, + data_len); + if (buf) + info.dest_buf = buf + offset; + + rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info); + if (!rc) + *seg_len = info.dest_buf_size; + + return rc; +} + +static void +bnxt_fill_coredump_seg_hdr(struct bnxt *bp, + struct bnxt_coredump_segment_hdr *seg_hdr, + struct coredump_segment_record *seg_rec, u32 seg_len, + int status, u32 duration, u32 instance) +{ + memset(seg_hdr, 0, sizeof(*seg_hdr)); + strcpy(seg_hdr->signature, "sEgM"); + if (seg_rec) { + seg_hdr->component_id = (__force __le32)seg_rec->component_id; + seg_hdr->segment_id = (__force __le32)seg_rec->segment_id; + seg_hdr->low_version = seg_rec->version_low; + seg_hdr->high_version = seg_rec->version_hi; + } else { + /* For hwrm_ver_get response Component id = 2 + * and Segment id = 0 + */ + seg_hdr->component_id = cpu_to_le32(2); + seg_hdr->segment_id = 0; + } + seg_hdr->function_id = cpu_to_le16(bp->pdev->devfn); + seg_hdr->length = cpu_to_le32(seg_len); + seg_hdr->status = cpu_to_le32(status); + seg_hdr->duration = cpu_to_le32(duration); + seg_hdr->data_offset = cpu_to_le32(sizeof(*seg_hdr)); + seg_hdr->instance = cpu_to_le32(instance); +} + +static void +bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record, + time64_t start, s16 start_utc, u16 total_segs, + int status) +{ + time64_t end = ktime_get_real_seconds(); + u32 os_ver_major = 0, os_ver_minor = 0; + struct tm tm; + + time64_to_tm(start, 0, &tm); + memset(record, 0, sizeof(*record)); + strcpy(record->signature, "cOrE"); + record->flags = 0; + record->low_version = 0; + record->high_version = 1; + record->asic_state = 0; + strncpy(record->system_name, utsname()->nodename, + strlen(utsname()->nodename)); + record->year = cpu_to_le16(tm.tm_year); + record->month = cpu_to_le16(tm.tm_mon); + record->day = cpu_to_le16(tm.tm_mday); + record->hour = cpu_to_le16(tm.tm_hour); + record->minute = cpu_to_le16(tm.tm_min); + record->second = cpu_to_le16(tm.tm_sec); + record->utc_bias = cpu_to_le16(start_utc); + strcpy(record->commandline, "ethtool -w"); + record->total_segments = cpu_to_le32(total_segs); + + sscanf(utsname()->release, "%u.%u", &os_ver_major, &os_ver_minor); + record->os_ver_major = cpu_to_le32(os_ver_major); + record->os_ver_minor = cpu_to_le32(os_ver_minor); + + strcpy(record->os_name, utsname()->sysname); + time64_to_tm(end, 0, &tm); + record->end_year = cpu_to_le16(tm.tm_year + 1900); + record->end_month = cpu_to_le16(tm.tm_mon + 1); + record->end_day = cpu_to_le16(tm.tm_mday); + record->end_hour = cpu_to_le16(tm.tm_hour); + record->end_minute = cpu_to_le16(tm.tm_min); + record->end_second = cpu_to_le16(tm.tm_sec); + record->end_utc_bias = cpu_to_le16(sys_tz.tz_minuteswest * 60); + record->asic_id1 = cpu_to_le32(bp->chip_num << 16 | + bp->ver_resp.chip_rev << 8 | + bp->ver_resp.chip_metal); + record->asic_id2 = 0; + record->coredump_status = cpu_to_le32(status); + record->ioctl_low_version = 0; + record->ioctl_high_version = 0; +} + +static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) +{ + u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output); + struct coredump_segment_record *seg_record = NULL; + u32 offset = 0, seg_hdr_len, seg_record_len; + struct bnxt_coredump_segment_hdr seg_hdr; + struct bnxt_coredump_record coredump_rec; + struct bnxt_coredump coredump = {NULL}; + time64_t start_time; + u16 start_utc; + int rc = 0, i; + + start_time = ktime_get_real_seconds(); + start_utc = sys_tz.tz_minuteswest * 60; + seg_hdr_len = sizeof(seg_hdr); + + /* First segment should be hwrm_ver_get response */ + *dump_len = seg_hdr_len + ver_get_resp_len; + if (buf) { + bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, ver_get_resp_len, + 0, 0, 0); + memcpy(buf + offset, &seg_hdr, seg_hdr_len); + offset += seg_hdr_len; + memcpy(buf + offset, &bp->ver_resp, ver_get_resp_len); + offset += ver_get_resp_len; + } + + rc = bnxt_hwrm_dbg_coredump_list(bp, &coredump); + if (rc) { + netdev_err(bp->dev, "Failed to get coredump segment list\n"); + goto err; + } + + *dump_len += seg_hdr_len * coredump.total_segs; + + seg_record = (struct coredump_segment_record *)coredump.data; + seg_record_len = sizeof(*seg_record); + + for (i = 0; i < coredump.total_segs; i++) { + u16 comp_id = le16_to_cpu(seg_record->component_id); + u16 seg_id = le16_to_cpu(seg_record->segment_id); + u32 duration = 0, seg_len = 0; + unsigned long start, end; + + start = jiffies; + + rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id); + if (rc) { + netdev_err(bp->dev, + "Failed to initiate coredump for seg = %d\n", + seg_record->segment_id); + goto next_seg; + } + + /* Write segment data into the buffer */ + rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id, + &seg_len, buf, + offset + seg_hdr_len); + if (rc) + netdev_err(bp->dev, + "Failed to retrieve coredump for seg = %d\n", + seg_record->segment_id); + +next_seg: + end = jiffies; + duration = jiffies_to_msecs(end - start); + bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, seg_record, seg_len, + rc, duration, 0); + + if (buf) { + /* Write segment header into the buffer */ + memcpy(buf + offset, &seg_hdr, seg_hdr_len); + offset += seg_hdr_len + seg_len; + } + + *dump_len += seg_len; + seg_record = + (struct coredump_segment_record *)((u8 *)seg_record + + seg_record_len); + } + +err: + if (buf) { + bnxt_fill_coredump_record(bp, &coredump_rec, start_time, + start_utc, coredump.total_segs + 1, + rc); + memcpy(buf + offset, &coredump_rec, sizeof(coredump_rec)); + } + kfree(coredump.data); + *dump_len += sizeof(coredump_rec); + + return rc; +} + +static int bnxt_get_dump_flag(struct net_device *dev, struct ethtool_dump *dump) +{ + struct bnxt *bp = netdev_priv(dev); + + if (bp->hwrm_spec_code < 0x10801) + return -EOPNOTSUPP; + + dump->version = bp->ver_resp.hwrm_fw_maj_8b << 24 | + bp->ver_resp.hwrm_fw_min_8b << 16 | + bp->ver_resp.hwrm_fw_bld_8b << 8 | + bp->ver_resp.hwrm_fw_rsvd_8b; + + return bnxt_get_coredump(bp, NULL, &dump->len); +} + +static int bnxt_get_dump_data(struct net_device *dev, struct ethtool_dump *dump, + void *buf) +{ + struct bnxt *bp = netdev_priv(dev); + + if (bp->hwrm_spec_code < 0x10801) + return -EOPNOTSUPP; + + memset(buf, 0, dump->len); + + return bnxt_get_coredump(bp, buf, &dump->len); +} + void bnxt_ethtool_init(struct bnxt *bp) { struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr; @@ -2702,6 +3056,8 @@ void bnxt_ethtool_init(struct bnxt *bp) strcpy(str, "Mac loopback test (offline)"); } else if (i == BNXT_PHYLPBK_TEST_IDX) { strcpy(str, "Phy loopback test (offline)"); + } else if (i == BNXT_EXTLPBK_TEST_IDX) { + strcpy(str, "Ext loopback test (offline)"); } else if (i == BNXT_IRQ_TEST_IDX) { strcpy(str, "Interrupt_test (offline)"); } else { @@ -2763,4 +3119,6 @@ const struct ethtool_ops bnxt_ethtool_ops = { .set_phys_id = bnxt_set_phys_id, .self_test = bnxt_self_test, .reset = bnxt_reset, + .get_dump_flag = bnxt_get_dump_flag, + .get_dump_data = bnxt_get_dump_data, }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index 836ef682f24c..b5b65b3f8534 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -22,6 +22,43 @@ struct bnxt_led_cfg { u8 rsvd; }; +#define COREDUMP_LIST_BUF_LEN 2048 +#define COREDUMP_RETRIEVE_BUF_LEN 4096 + +struct bnxt_coredump { + void *data; + int data_size; + u16 total_segs; +}; + +struct bnxt_hwrm_dbg_dma_info { + void *dest_buf; + int dest_buf_size; + u16 dma_len; + u16 seq_off; + u16 data_len_off; + u16 segs; +}; + +struct hwrm_dbg_cmn_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 host_dest_addr; + __le32 host_buf_len; +}; + +struct hwrm_dbg_cmn_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 flags; + #define HWRM_DBG_CMN_FLAGS_MORE 1 +}; + #define BNXT_LED_DFLT_ENA \ (PORT_LED_CFG_REQ_ENABLES_LED0_ID | \ PORT_LED_CFG_REQ_ENABLES_LED0_STATE | \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index c75d7fa6dab6..971ace5d0d4a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -96,6 +96,7 @@ struct hwrm_short_input { struct cmd_nums { __le16 req_type; #define HWRM_VER_GET 0x0UL + #define HWRM_FUNC_DRV_IF_CHANGE 0xdUL #define HWRM_FUNC_BUF_UNRGTR 0xeUL #define HWRM_FUNC_VF_CFG 0xfUL #define HWRM_RESERVED1 0x10UL @@ -159,6 +160,7 @@ struct cmd_nums { #define HWRM_RING_FREE 0x51UL #define HWRM_RING_CMPL_RING_QAGGINT_PARAMS 0x52UL #define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS 0x53UL + #define HWRM_RING_AGGINT_QCAPS 0x54UL #define HWRM_RING_RESET 0x5eUL #define HWRM_RING_GRP_ALLOC 0x60UL #define HWRM_RING_GRP_FREE 0x61UL @@ -191,6 +193,8 @@ struct cmd_nums { #define HWRM_PORT_QSTATS_EXT 0xb4UL #define HWRM_FW_RESET 0xc0UL #define HWRM_FW_QSTATUS 0xc1UL + #define HWRM_FW_HEALTH_CHECK 0xc2UL + #define HWRM_FW_SYNC 0xc3UL #define HWRM_FW_SET_TIME 0xc8UL #define HWRM_FW_GET_TIME 0xc9UL #define HWRM_FW_SET_STRUCTURED_DATA 0xcaUL @@ -269,6 +273,11 @@ struct cmd_nums { #define HWRM_ENGINE_ON_DIE_RQE_CREDITS 0x164UL #define HWRM_FUNC_RESOURCE_QCAPS 0x190UL #define HWRM_FUNC_VF_RESOURCE_CFG 0x191UL + #define HWRM_FUNC_BACKING_STORE_QCAPS 0x192UL + #define HWRM_FUNC_BACKING_STORE_CFG 0x193UL + #define HWRM_FUNC_BACKING_STORE_QCFG 0x194UL + #define HWRM_FUNC_VF_BW_CFG 0x195UL + #define HWRM_FUNC_VF_BW_QCFG 0x196UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -284,6 +293,8 @@ struct cmd_nums { #define HWRM_DBG_COREDUMP_LIST 0xff17UL #define HWRM_DBG_COREDUMP_INITIATE 0xff18UL #define HWRM_DBG_COREDUMP_RETRIEVE 0xff19UL + #define HWRM_DBG_FW_CLI 0xff1aUL + #define HWRM_DBG_I2C_CMD 0xff1bUL #define HWRM_NVM_FACTORY_DEFAULTS 0xffeeUL #define HWRM_NVM_VALIDATE_OPTION 0xffefUL #define HWRM_NVM_FLUSH 0xfff0UL @@ -318,6 +329,7 @@ struct ret_codes { #define HWRM_ERR_CODE_INVALID_ENABLES 0x6UL #define HWRM_ERR_CODE_UNSUPPORTED_TLV 0x7UL #define HWRM_ERR_CODE_NO_BUFFER 0x8UL + #define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR 0x9UL #define HWRM_ERR_CODE_HWRM_ERROR 0xfUL #define HWRM_ERR_CODE_UNKNOWN_ERR 0xfffeUL #define HWRM_ERR_CODE_CMD_NOT_SUPPORTED 0xffffUL @@ -344,9 +356,9 @@ struct hwrm_err_output { #define HWRM_RESP_VALID_KEY 1 #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 9 -#define HWRM_VERSION_UPDATE 1 -#define HWRM_VERSION_RSVD 15 -#define HWRM_VERSION_STR "1.9.1.15" +#define HWRM_VERSION_UPDATE 2 +#define HWRM_VERSION_RSVD 25 +#define HWRM_VERSION_STR "1.9.2.25" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -526,6 +538,7 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE 0x32UL #define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE 0x33UL #define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE 0x34UL + #define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE 0x35UL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR __le32 event_data2; @@ -564,6 +577,8 @@ struct hwrm_async_event_cmpl_link_status_change { #define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT 1 #define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK 0xffff0UL #define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT 4 + #define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK 0xff00000UL + #define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT 20 }; /* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */ @@ -817,23 +832,26 @@ struct hwrm_func_qcaps_output { __le16 fid; __le16 port_id; __le32 flags; - #define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED 0x1UL - #define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING 0x2UL - #define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED 0x4UL - #define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED 0x8UL - #define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED 0x10UL - #define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED 0x20UL - #define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED 0x40UL - #define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED 0x80UL - #define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED 0x100UL - #define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED 0x200UL - #define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED 0x400UL - #define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED 0x800UL - #define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED 0x1000UL - #define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED 0x2000UL - #define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED 0x4000UL - #define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED 0x8000UL - #define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED 0x10000UL + #define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED 0x1UL + #define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING 0x2UL + #define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED 0x4UL + #define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED 0x8UL + #define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED 0x10UL + #define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED 0x20UL + #define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED 0x40UL + #define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED 0x80UL + #define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED 0x100UL + #define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED 0x200UL + #define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED 0x400UL + #define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED 0x800UL + #define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED 0x1000UL + #define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED 0x2000UL + #define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED 0x4000UL + #define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED 0x8000UL + #define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED 0x10000UL + #define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED 0x20000UL + #define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED 0x40000UL + #define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED 0x80000UL u8 mac_address[6]; __le16 max_rsscos_ctx; __le16 max_cmpl_rings; @@ -947,58 +965,26 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_EVB_MODE_VEPA 0x2UL #define FUNC_QCFG_RESP_EVB_MODE_LAST FUNC_QCFG_RESP_EVB_MODE_VEPA u8 options; - #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK 0x3UL - #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT 0 - #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64 0x0UL - #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128 0x1UL - #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128 - #define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK 0xfcUL - #define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT 2 + #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK 0x3UL + #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT 0 + #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64 0x0UL + #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128 0x1UL + #define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128 + #define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK 0xcUL + #define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT 2 + #define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN (0x0UL << 2) + #define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP (0x1UL << 2) + #define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO (0x2UL << 2) + #define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO + #define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK 0xf0UL + #define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT 4 __le16 alloc_vfs; __le32 alloc_mcast_filters; __le32 alloc_hw_ring_grps; __le16 alloc_sp_tx_rings; __le16 alloc_stat_ctx; - u8 unused_2[7]; - u8 valid; -}; - -/* hwrm_func_vlan_cfg_input (size:384b/48B) */ -struct hwrm_func_vlan_cfg_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le16 fid; - u8 unused_0[2]; - __le32 enables; - #define FUNC_VLAN_CFG_REQ_ENABLES_STAG_VID 0x1UL - #define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_VID 0x2UL - #define FUNC_VLAN_CFG_REQ_ENABLES_STAG_PCP 0x4UL - #define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_PCP 0x8UL - #define FUNC_VLAN_CFG_REQ_ENABLES_STAG_TPID 0x10UL - #define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_TPID 0x20UL - __le16 stag_vid; - u8 stag_pcp; - u8 unused_1; - __be16 stag_tpid; - __le16 ctag_vid; - u8 ctag_pcp; - u8 unused_2; - __be16 ctag_tpid; - __le32 rsvd1; - __le32 rsvd2; - u8 unused_3[4]; -}; - -/* hwrm_func_vlan_cfg_output (size:128b/16B) */ -struct hwrm_func_vlan_cfg_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - u8 unused_0[7]; + __le16 alloc_msix; + u8 unused_2[5]; u8 valid; }; @@ -1010,7 +996,7 @@ struct hwrm_func_cfg_input { __le16 target_id; __le64 resp_addr; __le16 fid; - u8 unused_0[2]; + __le16 num_msix; __le32 flags; #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE 0x1UL #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE 0x2UL @@ -1050,6 +1036,8 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS 0x40000UL #define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS 0x80000UL #define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE 0x100000UL + #define FUNC_CFG_REQ_ENABLES_NUM_MSIX 0x200000UL + #define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE 0x400000UL __le16 mtu; __le16 mru; __le16 num_rsscos_ctxs; @@ -1109,13 +1097,19 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_EVB_MODE_VEPA 0x2UL #define FUNC_CFG_REQ_EVB_MODE_LAST FUNC_CFG_REQ_EVB_MODE_VEPA u8 options; - #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK 0x3UL - #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT 0 - #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64 0x0UL - #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128 0x1UL - #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128 - #define FUNC_CFG_REQ_OPTIONS_RSVD_MASK 0xfcUL - #define FUNC_CFG_REQ_OPTIONS_RSVD_SFT 2 + #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK 0x3UL + #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT 0 + #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64 0x0UL + #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128 0x1UL + #define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128 + #define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK 0xcUL + #define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT 2 + #define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN (0x0UL << 2) + #define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP (0x1UL << 2) + #define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO (0x2UL << 2) + #define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO + #define FUNC_CFG_REQ_OPTIONS_RSVD_MASK 0xf0UL + #define FUNC_CFG_REQ_OPTIONS_RSVD_SFT 4 __le16 num_mcast_filters; }; @@ -1212,30 +1206,6 @@ struct hwrm_func_vf_resc_free_output { u8 valid; }; -/* hwrm_func_vf_vnic_ids_query_input (size:256b/32B) */ -struct hwrm_func_vf_vnic_ids_query_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le16 vf_id; - u8 unused_0[2]; - __le32 max_vnic_id_cnt; - __le64 vnic_id_tbl_addr; -}; - -/* hwrm_func_vf_vnic_ids_query_output (size:128b/16B) */ -struct hwrm_func_vf_vnic_ids_query_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - __le32 vnic_id_cnt; - u8 unused_0[3]; - u8 valid; -}; - /* hwrm_func_drv_rgtr_input (size:896b/112B) */ struct hwrm_func_drv_rgtr_input { __le16 req_type; @@ -1286,7 +1256,9 @@ struct hwrm_func_drv_rgtr_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - u8 unused_0[7]; + __le32 flags; + #define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED 0x1UL + u8 unused_0[3]; u8 valid; }; @@ -1372,7 +1344,7 @@ struct hwrm_func_drv_qver_input { u8 unused_0[2]; }; -/* hwrm_func_drv_qver_output (size:192b/24B) */ +/* hwrm_func_drv_qver_output (size:256b/32B) */ struct hwrm_func_drv_qver_output { __le16 error_code; __le16 req_type; @@ -1394,12 +1366,13 @@ struct hwrm_func_drv_qver_output { u8 ver_maj_8b; u8 ver_min_8b; u8 ver_upd_8b; - u8 unused_0[2]; - u8 valid; + u8 unused_0[3]; __le16 ver_maj; __le16 ver_min; __le16 ver_upd; __le16 ver_patch; + u8 unused_1[7]; + u8 valid; }; /* hwrm_func_resource_qcaps_input (size:192b/24B) */ @@ -1493,6 +1466,410 @@ struct hwrm_func_vf_resource_cfg_output { u8 valid; }; +/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */ +struct hwrm_func_backing_store_qcaps_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* hwrm_func_backing_store_qcaps_output (size:576b/72B) */ +struct hwrm_func_backing_store_qcaps_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 qp_max_entries; + __le16 qp_min_qp1_entries; + __le16 qp_max_l2_entries; + __le16 qp_entry_size; + __le16 srq_max_l2_entries; + __le32 srq_max_entries; + __le16 srq_entry_size; + __le16 cq_max_l2_entries; + __le32 cq_max_entries; + __le16 cq_entry_size; + __le16 vnic_max_vnic_entries; + __le16 vnic_max_ring_table_entries; + __le16 vnic_entry_size; + __le32 stat_max_entries; + __le16 stat_entry_size; + __le16 tqm_entry_size; + __le32 tqm_min_entries_per_ring; + __le32 tqm_max_entries_per_ring; + __le32 mrav_max_entries; + __le16 mrav_entry_size; + __le16 tim_entry_size; + __le32 tim_max_entries; + u8 unused_0[3]; + u8 valid; +}; + +/* hwrm_func_backing_store_cfg_input (size:2048b/256B) */ +struct hwrm_func_backing_store_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 flags; + #define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE 0x1UL + __le32 enables; + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ 0x4UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC 0x8UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT 0x10UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP 0x20UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0 0x40UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1 0x80UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2 0x100UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3 0x200UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4 0x400UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5 0x800UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6 0x1000UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7 0x2000UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV 0x4000UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM 0x8000UL + u8 qpc_pg_size_qpc_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G + u8 srq_pg_size_srq_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G + u8 cq_pg_size_cq_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G + u8 vnic_pg_size_vnic_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G + u8 stat_pg_size_stat_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G + u8 tqm_sp_pg_size_tqm_sp_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G + u8 tqm_ring0_pg_size_tqm_ring0_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G + u8 tqm_ring1_pg_size_tqm_ring1_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G + u8 tqm_ring2_pg_size_tqm_ring2_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G + u8 tqm_ring3_pg_size_tqm_ring3_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G + u8 tqm_ring4_pg_size_tqm_ring4_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G + u8 tqm_ring5_pg_size_tqm_ring5_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G + u8 tqm_ring6_pg_size_tqm_ring6_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G + u8 tqm_ring7_pg_size_tqm_ring7_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G + u8 mrav_pg_size_mrav_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G + u8 tim_pg_size_tim_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G + __le64 qpc_page_dir; + __le64 srq_page_dir; + __le64 cq_page_dir; + __le64 vnic_page_dir; + __le64 stat_page_dir; + __le64 tqm_sp_page_dir; + __le64 tqm_ring0_page_dir; + __le64 tqm_ring1_page_dir; + __le64 tqm_ring2_page_dir; + __le64 tqm_ring3_page_dir; + __le64 tqm_ring4_page_dir; + __le64 tqm_ring5_page_dir; + __le64 tqm_ring6_page_dir; + __le64 tqm_ring7_page_dir; + __le64 mrav_page_dir; + __le64 tim_page_dir; + __le32 qp_num_entries; + __le32 srq_num_entries; + __le32 cq_num_entries; + __le32 stat_num_entries; + __le32 tqm_sp_num_entries; + __le32 tqm_ring0_num_entries; + __le32 tqm_ring1_num_entries; + __le32 tqm_ring2_num_entries; + __le32 tqm_ring3_num_entries; + __le32 tqm_ring4_num_entries; + __le32 tqm_ring5_num_entries; + __le32 tqm_ring6_num_entries; + __le32 tqm_ring7_num_entries; + __le32 mrav_num_entries; + __le32 tim_num_entries; + __le16 qp_num_qp1_entries; + __le16 qp_num_l2_entries; + __le16 qp_entry_size; + __le16 srq_num_l2_entries; + __le16 srq_entry_size; + __le16 cq_num_l2_entries; + __le16 cq_entry_size; + __le16 vnic_num_vnic_entries; + __le16 vnic_num_ring_table_entries; + __le16 vnic_entry_size; + __le16 stat_entry_size; + __le16 tqm_entry_size; + __le16 mrav_entry_size; + __le16 tim_entry_size; +}; + +/* hwrm_func_backing_store_cfg_output (size:128b/16B) */ +struct hwrm_func_backing_store_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_drv_if_change_input (size:192b/24B) */ +struct hwrm_func_drv_if_change_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 flags; + #define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP 0x1UL + __le32 unused; +}; + +/* hwrm_func_drv_if_change_output (size:128b/16B) */ +struct hwrm_func_drv_if_change_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 flags; + #define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE 0x1UL + u8 unused_0[3]; + u8 valid; +}; + /* hwrm_port_phy_cfg_input (size:448b/56B) */ struct hwrm_port_phy_cfg_input { __le16 req_type; @@ -1592,10 +1969,11 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_WIRESPEED_ON 0x1UL #define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON u8 lpbk; - #define PORT_PHY_CFG_REQ_LPBK_NONE 0x0UL - #define PORT_PHY_CFG_REQ_LPBK_LOCAL 0x1UL - #define PORT_PHY_CFG_REQ_LPBK_REMOTE 0x2UL - #define PORT_PHY_CFG_REQ_LPBK_LAST PORT_PHY_CFG_REQ_LPBK_REMOTE + #define PORT_PHY_CFG_REQ_LPBK_NONE 0x0UL + #define PORT_PHY_CFG_REQ_LPBK_LOCAL 0x1UL + #define PORT_PHY_CFG_REQ_LPBK_REMOTE 0x2UL + #define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL + #define PORT_PHY_CFG_REQ_LPBK_LAST PORT_PHY_CFG_REQ_LPBK_EXTERNAL u8 force_pause; #define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX 0x1UL #define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX 0x2UL @@ -1751,10 +2129,11 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_WIRESPEED_ON 0x1UL #define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON u8 lpbk; - #define PORT_PHY_QCFG_RESP_LPBK_NONE 0x0UL - #define PORT_PHY_QCFG_RESP_LPBK_LOCAL 0x1UL - #define PORT_PHY_QCFG_RESP_LPBK_REMOTE 0x2UL - #define PORT_PHY_QCFG_RESP_LPBK_LAST PORT_PHY_QCFG_RESP_LPBK_REMOTE + #define PORT_PHY_QCFG_RESP_LPBK_NONE 0x0UL + #define PORT_PHY_QCFG_RESP_LPBK_LOCAL 0x1UL + #define PORT_PHY_QCFG_RESP_LPBK_REMOTE 0x2UL + #define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL + #define PORT_PHY_QCFG_RESP_LPBK_LAST PORT_PHY_QCFG_RESP_LPBK_EXTERNAL u8 force_pause; #define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX 0x1UL #define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX 0x2UL @@ -2014,6 +2393,131 @@ struct hwrm_port_mac_ptp_qcfg_output { u8 valid; }; +/* tx_port_stats (size:3264b/408B) */ +struct tx_port_stats { + __le64 tx_64b_frames; + __le64 tx_65b_127b_frames; + __le64 tx_128b_255b_frames; + __le64 tx_256b_511b_frames; + __le64 tx_512b_1023b_frames; + __le64 tx_1024b_1518b_frames; + __le64 tx_good_vlan_frames; + __le64 tx_1519b_2047b_frames; + __le64 tx_2048b_4095b_frames; + __le64 tx_4096b_9216b_frames; + __le64 tx_9217b_16383b_frames; + __le64 tx_good_frames; + __le64 tx_total_frames; + __le64 tx_ucast_frames; + __le64 tx_mcast_frames; + __le64 tx_bcast_frames; + __le64 tx_pause_frames; + __le64 tx_pfc_frames; + __le64 tx_jabber_frames; + __le64 tx_fcs_err_frames; + __le64 tx_control_frames; + __le64 tx_oversz_frames; + __le64 tx_single_dfrl_frames; + __le64 tx_multi_dfrl_frames; + __le64 tx_single_coll_frames; + __le64 tx_multi_coll_frames; + __le64 tx_late_coll_frames; + __le64 tx_excessive_coll_frames; + __le64 tx_frag_frames; + __le64 tx_err; + __le64 tx_tagged_frames; + __le64 tx_dbl_tagged_frames; + __le64 tx_runt_frames; + __le64 tx_fifo_underruns; + __le64 tx_pfc_ena_frames_pri0; + __le64 tx_pfc_ena_frames_pri1; + __le64 tx_pfc_ena_frames_pri2; + __le64 tx_pfc_ena_frames_pri3; + __le64 tx_pfc_ena_frames_pri4; + __le64 tx_pfc_ena_frames_pri5; + __le64 tx_pfc_ena_frames_pri6; + __le64 tx_pfc_ena_frames_pri7; + __le64 tx_eee_lpi_events; + __le64 tx_eee_lpi_duration; + __le64 tx_llfc_logical_msgs; + __le64 tx_hcfc_msgs; + __le64 tx_total_collisions; + __le64 tx_bytes; + __le64 tx_xthol_frames; + __le64 tx_stat_discard; + __le64 tx_stat_error; +}; + +/* rx_port_stats (size:4224b/528B) */ +struct rx_port_stats { + __le64 rx_64b_frames; + __le64 rx_65b_127b_frames; + __le64 rx_128b_255b_frames; + __le64 rx_256b_511b_frames; + __le64 rx_512b_1023b_frames; + __le64 rx_1024b_1518b_frames; + __le64 rx_good_vlan_frames; + __le64 rx_1519b_2047b_frames; + __le64 rx_2048b_4095b_frames; + __le64 rx_4096b_9216b_frames; + __le64 rx_9217b_16383b_frames; + __le64 rx_total_frames; + __le64 rx_ucast_frames; + __le64 rx_mcast_frames; + __le64 rx_bcast_frames; + __le64 rx_fcs_err_frames; + __le64 rx_ctrl_frames; + __le64 rx_pause_frames; + __le64 rx_pfc_frames; + __le64 rx_unsupported_opcode_frames; + __le64 rx_unsupported_da_pausepfc_frames; + __le64 rx_wrong_sa_frames; + __le64 rx_align_err_frames; + __le64 rx_oor_len_frames; + __le64 rx_code_err_frames; + __le64 rx_false_carrier_frames; + __le64 rx_ovrsz_frames; + __le64 rx_jbr_frames; + __le64 rx_mtu_err_frames; + __le64 rx_match_crc_frames; + __le64 rx_promiscuous_frames; + __le64 rx_tagged_frames; + __le64 rx_double_tagged_frames; + __le64 rx_trunc_frames; + __le64 rx_good_frames; + __le64 rx_pfc_xon2xoff_frames_pri0; + __le64 rx_pfc_xon2xoff_frames_pri1; + __le64 rx_pfc_xon2xoff_frames_pri2; + __le64 rx_pfc_xon2xoff_frames_pri3; + __le64 rx_pfc_xon2xoff_frames_pri4; + __le64 rx_pfc_xon2xoff_frames_pri5; + __le64 rx_pfc_xon2xoff_frames_pri6; + __le64 rx_pfc_xon2xoff_frames_pri7; + __le64 rx_pfc_ena_frames_pri0; + __le64 rx_pfc_ena_frames_pri1; + __le64 rx_pfc_ena_frames_pri2; + __le64 rx_pfc_ena_frames_pri3; + __le64 rx_pfc_ena_frames_pri4; + __le64 rx_pfc_ena_frames_pri5; + __le64 rx_pfc_ena_frames_pri6; + __le64 rx_pfc_ena_frames_pri7; + __le64 rx_sch_crc_err_frames; + __le64 rx_undrsz_frames; + __le64 rx_frag_frames; + __le64 rx_eee_lpi_events; + __le64 rx_eee_lpi_duration; + __le64 rx_llfc_physical_msgs; + __le64 rx_llfc_logical_msgs; + __le64 rx_llfc_msgs_with_crc_err; + __le64 rx_hcfc_msgs; + __le64 rx_hcfc_msgs_with_crc_err; + __le64 rx_bytes; + __le64 rx_runt_bytes; + __le64 rx_runt_frames; + __le64 rx_stat_discard; + __le64 rx_stat_err; +}; + /* hwrm_port_qstats_input (size:320b/40B) */ struct hwrm_port_qstats_input { __le16 req_type; @@ -2039,6 +2543,83 @@ struct hwrm_port_qstats_output { u8 valid; }; +/* tx_port_stats_ext (size:2048b/256B) */ +struct tx_port_stats_ext { + __le64 tx_bytes_cos0; + __le64 tx_bytes_cos1; + __le64 tx_bytes_cos2; + __le64 tx_bytes_cos3; + __le64 tx_bytes_cos4; + __le64 tx_bytes_cos5; + __le64 tx_bytes_cos6; + __le64 tx_bytes_cos7; + __le64 tx_packets_cos0; + __le64 tx_packets_cos1; + __le64 tx_packets_cos2; + __le64 tx_packets_cos3; + __le64 tx_packets_cos4; + __le64 tx_packets_cos5; + __le64 tx_packets_cos6; + __le64 tx_packets_cos7; + __le64 pfc_pri0_tx_duration_us; + __le64 pfc_pri0_tx_transitions; + __le64 pfc_pri1_tx_duration_us; + __le64 pfc_pri1_tx_transitions; + __le64 pfc_pri2_tx_duration_us; + __le64 pfc_pri2_tx_transitions; + __le64 pfc_pri3_tx_duration_us; + __le64 pfc_pri3_tx_transitions; + __le64 pfc_pri4_tx_duration_us; + __le64 pfc_pri4_tx_transitions; + __le64 pfc_pri5_tx_duration_us; + __le64 pfc_pri5_tx_transitions; + __le64 pfc_pri6_tx_duration_us; + __le64 pfc_pri6_tx_transitions; + __le64 pfc_pri7_tx_duration_us; + __le64 pfc_pri7_tx_transitions; +}; + +/* rx_port_stats_ext (size:2368b/296B) */ +struct rx_port_stats_ext { + __le64 link_down_events; + __le64 continuous_pause_events; + __le64 resume_pause_events; + __le64 continuous_roce_pause_events; + __le64 resume_roce_pause_events; + __le64 rx_bytes_cos0; + __le64 rx_bytes_cos1; + __le64 rx_bytes_cos2; + __le64 rx_bytes_cos3; + __le64 rx_bytes_cos4; + __le64 rx_bytes_cos5; + __le64 rx_bytes_cos6; + __le64 rx_bytes_cos7; + __le64 rx_packets_cos0; + __le64 rx_packets_cos1; + __le64 rx_packets_cos2; + __le64 rx_packets_cos3; + __le64 rx_packets_cos4; + __le64 rx_packets_cos5; + __le64 rx_packets_cos6; + __le64 rx_packets_cos7; + __le64 pfc_pri0_rx_duration_us; + __le64 pfc_pri0_rx_transitions; + __le64 pfc_pri1_rx_duration_us; + __le64 pfc_pri1_rx_transitions; + __le64 pfc_pri2_rx_duration_us; + __le64 pfc_pri2_rx_transitions; + __le64 pfc_pri3_rx_duration_us; + __le64 pfc_pri3_rx_transitions; + __le64 pfc_pri4_rx_duration_us; + __le64 pfc_pri4_rx_transitions; + __le64 pfc_pri5_rx_duration_us; + __le64 pfc_pri5_rx_transitions; + __le64 pfc_pri6_rx_duration_us; + __le64 pfc_pri6_rx_transitions; + __le64 pfc_pri7_rx_duration_us; + __le64 pfc_pri7_rx_transitions; +}; + /* hwrm_port_qstats_ext_input (size:320b/40B) */ struct hwrm_port_qstats_ext_input { __le16 req_type; @@ -2062,7 +2643,8 @@ struct hwrm_port_qstats_ext_output { __le16 resp_len; __le16 tx_stat_size; __le16 rx_stat_size; - u8 unused_0[3]; + __le16 total_active_cos_queues; + u8 unused_0; u8 valid; }; @@ -2153,9 +2735,10 @@ struct hwrm_port_phy_qcaps_output { __le16 seq_id; __le16 resp_len; u8 flags; - #define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED 0x1UL - #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK 0xfeUL - #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT 1 + #define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED 0x1UL + #define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED 0x2UL + #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK 0xfcUL + #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT 2 u8 port_cnt; #define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL #define PORT_PHY_QCAPS_RESP_PORT_CNT_1 0x1UL @@ -2612,6 +3195,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id0; u8 queue_id0_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2620,6 +3204,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id1; u8 queue_id1_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2628,6 +3213,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id2; u8 queue_id2_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2636,6 +3222,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id3; u8 queue_id3_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2644,6 +3231,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id4; u8 queue_id4_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2652,6 +3240,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id5; u8 queue_id5_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2660,6 +3249,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id6; u8 queue_id6_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -2668,6 +3258,7 @@ struct hwrm_queue_qportcfg_output { u8 queue_id7; u8 queue_id7_service_profile; #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE 0x1UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL @@ -3689,18 +4280,21 @@ struct hwrm_vnic_cfg_input { #define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE 0x20UL #define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE 0x40UL __le32 enables; - #define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP 0x1UL - #define VNIC_CFG_REQ_ENABLES_RSS_RULE 0x2UL - #define VNIC_CFG_REQ_ENABLES_COS_RULE 0x4UL - #define VNIC_CFG_REQ_ENABLES_LB_RULE 0x8UL - #define VNIC_CFG_REQ_ENABLES_MRU 0x10UL + #define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP 0x1UL + #define VNIC_CFG_REQ_ENABLES_RSS_RULE 0x2UL + #define VNIC_CFG_REQ_ENABLES_COS_RULE 0x4UL + #define VNIC_CFG_REQ_ENABLES_LB_RULE 0x8UL + #define VNIC_CFG_REQ_ENABLES_MRU 0x10UL + #define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID 0x20UL + #define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID 0x40UL __le16 vnic_id; __le16 dflt_ring_grp; __le16 rss_rule; __le16 cos_rule; __le16 lb_rule; __le16 mru; - u8 unused_0[4]; + __le16 default_rx_ring_id; + __le16 default_cmpl_ring_id; }; /* hwrm_vnic_cfg_output (size:128b/16B) */ @@ -3740,6 +4334,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP 0x10UL #define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP 0x20UL #define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP 0x40UL + #define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP 0x80UL u8 unused_1[7]; u8 valid; }; @@ -3857,7 +4452,14 @@ struct hwrm_vnic_rss_cfg_input { #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL - u8 unused_0[4]; + __le16 vnic_id; + u8 ring_table_pair_index; + u8 hash_mode_flags; + #define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT 0x1UL + #define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4 0x2UL + #define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2 0x4UL + #define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4 0x8UL + #define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2 0x10UL __le64 ring_grp_tbl_addr; __le64 hash_key_tbl_addr; __le16 rss_ctx_idx; @@ -3950,7 +4552,7 @@ struct hwrm_vnic_rss_cos_lb_ctx_free_output { u8 valid; }; -/* hwrm_ring_alloc_input (size:640b/80B) */ +/* hwrm_ring_alloc_input (size:704b/88B) */ struct hwrm_ring_alloc_input { __le16 req_type; __le16 cmpl_ring; @@ -3961,12 +4563,17 @@ struct hwrm_ring_alloc_input { #define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG 0x2UL #define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID 0x8UL #define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID 0x20UL + #define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID 0x40UL + #define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID 0x80UL + #define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID 0x100UL u8 ring_type; #define RING_ALLOC_REQ_RING_TYPE_L2_CMPL 0x0UL #define RING_ALLOC_REQ_RING_TYPE_TX 0x1UL #define RING_ALLOC_REQ_RING_TYPE_RX 0x2UL #define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL - #define RING_ALLOC_REQ_RING_TYPE_LAST RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL + #define RING_ALLOC_REQ_RING_TYPE_RX_AGG 0x4UL + #define RING_ALLOC_REQ_RING_TYPE_NQ 0x5UL + #define RING_ALLOC_REQ_RING_TYPE_LAST RING_ALLOC_REQ_RING_TYPE_NQ u8 unused_0[3]; __le64 page_tbl_addr; __le32 fbo; @@ -3977,8 +4584,9 @@ struct hwrm_ring_alloc_input { __le16 logical_id; __le16 cmpl_ring_id; __le16 queue_id; - u8 unused_2[2]; - __le32 reserved1; + __le16 rx_buf_size; + __le16 rx_ring_id; + __le16 nq_ring_id; __le16 ring_arb_cfg; #define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK 0xfUL #define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT 0 @@ -4016,6 +4624,7 @@ struct hwrm_ring_alloc_input { #define RING_ALLOC_REQ_INT_MODE_POLL 0x3UL #define RING_ALLOC_REQ_INT_MODE_LAST RING_ALLOC_REQ_INT_MODE_POLL u8 unused_4[3]; + __le64 cq_handle; }; /* hwrm_ring_alloc_output (size:128b/16B) */ @@ -4042,7 +4651,9 @@ struct hwrm_ring_free_input { #define RING_FREE_REQ_RING_TYPE_TX 0x1UL #define RING_FREE_REQ_RING_TYPE_RX 0x2UL #define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL - #define RING_FREE_REQ_RING_TYPE_LAST RING_FREE_REQ_RING_TYPE_ROCE_CMPL + #define RING_FREE_REQ_RING_TYPE_RX_AGG 0x4UL + #define RING_FREE_REQ_RING_TYPE_NQ 0x5UL + #define RING_FREE_REQ_RING_TYPE_LAST RING_FREE_REQ_RING_TYPE_NQ u8 unused_0; __le16 ring_id; u8 unused_1[4]; @@ -4058,6 +4669,52 @@ struct hwrm_ring_free_output { u8 valid; }; +/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */ +struct hwrm_ring_aggint_qcaps_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; +}; + +/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */ +struct hwrm_ring_aggint_qcaps_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 cmpl_params; + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN 0x1UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX 0x2UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET 0x4UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE 0x8UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR 0x10UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT 0x20UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR 0x40UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT 0x80UL + #define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT 0x100UL + __le32 nq_params; + #define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN 0x1UL + __le16 num_cmpl_dma_aggr_min; + __le16 num_cmpl_dma_aggr_max; + __le16 num_cmpl_dma_aggr_during_int_min; + __le16 num_cmpl_dma_aggr_during_int_max; + __le16 cmpl_aggr_dma_tmr_min; + __le16 cmpl_aggr_dma_tmr_max; + __le16 cmpl_aggr_dma_tmr_during_int_min; + __le16 cmpl_aggr_dma_tmr_during_int_max; + __le16 int_lat_tmr_min_min; + __le16 int_lat_tmr_min_max; + __le16 int_lat_tmr_max_min; + __le16 int_lat_tmr_max_max; + __le16 num_cmpl_aggr_int_min; + __le16 num_cmpl_aggr_int_max; + __le16 timer_units; + u8 unused_0[1]; + u8 valid; +}; + /* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */ struct hwrm_ring_cmpl_ring_qaggint_params_input { __le16 req_type; @@ -4100,6 +4757,7 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_input { __le16 flags; #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET 0x1UL #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE 0x2UL + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ 0x4UL __le16 num_cmpl_dma_aggr; __le16 num_cmpl_dma_aggr_during_int; __le16 cmpl_aggr_dma_tmr; @@ -4107,7 +4765,14 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_input { __le16 int_lat_tmr_min; __le16 int_lat_tmr_max; __le16 num_cmpl_aggr_int; - u8 unused_0[6]; + __le16 enables; + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR 0x1UL + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT 0x2UL + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR 0x4UL + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN 0x8UL + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX 0x10UL + #define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT 0x20UL + u8 unused_0[4]; }; /* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */ @@ -4120,34 +4785,6 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_output { u8 valid; }; -/* hwrm_ring_reset_input (size:192b/24B) */ -struct hwrm_ring_reset_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - u8 ring_type; - #define RING_RESET_REQ_RING_TYPE_L2_CMPL 0x0UL - #define RING_RESET_REQ_RING_TYPE_TX 0x1UL - #define RING_RESET_REQ_RING_TYPE_RX 0x2UL - #define RING_RESET_REQ_RING_TYPE_ROCE_CMPL 0x3UL - #define RING_RESET_REQ_RING_TYPE_LAST RING_RESET_REQ_RING_TYPE_ROCE_CMPL - u8 unused_0; - __le16 ring_id; - u8 unused_1[4]; -}; - -/* hwrm_ring_reset_output (size:128b/16B) */ -struct hwrm_ring_reset_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - u8 unused_0[7]; - u8 valid; -}; - /* hwrm_ring_grp_alloc_input (size:192b/24B) */ struct hwrm_ring_grp_alloc_input { __le16 req_type; @@ -5032,7 +5669,8 @@ struct hwrm_tunnel_dst_port_query_input { #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN 0x1UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE 0x5UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 u8 unused_0[7]; }; @@ -5059,7 +5697,8 @@ struct hwrm_tunnel_dst_port_alloc_input { #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN 0x1UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE 0x5UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 u8 unused_0; __be16 tunnel_dst_port_val; u8 unused_1[4]; @@ -5087,7 +5726,8 @@ struct hwrm_tunnel_dst_port_free_input { #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN 0x1UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE 0x5UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 u8 unused_0; __le16 tunnel_dst_port_id; u8 unused_1[4]; @@ -5259,140 +5899,6 @@ struct hwrm_pcie_qstats_output { u8 valid; }; -/* tx_port_stats (size:3264b/408B) */ -struct tx_port_stats { - __le64 tx_64b_frames; - __le64 tx_65b_127b_frames; - __le64 tx_128b_255b_frames; - __le64 tx_256b_511b_frames; - __le64 tx_512b_1023b_frames; - __le64 tx_1024b_1518_frames; - __le64 tx_good_vlan_frames; - __le64 tx_1519b_2047_frames; - __le64 tx_2048b_4095b_frames; - __le64 tx_4096b_9216b_frames; - __le64 tx_9217b_16383b_frames; - __le64 tx_good_frames; - __le64 tx_total_frames; - __le64 tx_ucast_frames; - __le64 tx_mcast_frames; - __le64 tx_bcast_frames; - __le64 tx_pause_frames; - __le64 tx_pfc_frames; - __le64 tx_jabber_frames; - __le64 tx_fcs_err_frames; - __le64 tx_control_frames; - __le64 tx_oversz_frames; - __le64 tx_single_dfrl_frames; - __le64 tx_multi_dfrl_frames; - __le64 tx_single_coll_frames; - __le64 tx_multi_coll_frames; - __le64 tx_late_coll_frames; - __le64 tx_excessive_coll_frames; - __le64 tx_frag_frames; - __le64 tx_err; - __le64 tx_tagged_frames; - __le64 tx_dbl_tagged_frames; - __le64 tx_runt_frames; - __le64 tx_fifo_underruns; - __le64 tx_pfc_ena_frames_pri0; - __le64 tx_pfc_ena_frames_pri1; - __le64 tx_pfc_ena_frames_pri2; - __le64 tx_pfc_ena_frames_pri3; - __le64 tx_pfc_ena_frames_pri4; - __le64 tx_pfc_ena_frames_pri5; - __le64 tx_pfc_ena_frames_pri6; - __le64 tx_pfc_ena_frames_pri7; - __le64 tx_eee_lpi_events; - __le64 tx_eee_lpi_duration; - __le64 tx_llfc_logical_msgs; - __le64 tx_hcfc_msgs; - __le64 tx_total_collisions; - __le64 tx_bytes; - __le64 tx_xthol_frames; - __le64 tx_stat_discard; - __le64 tx_stat_error; -}; - -/* rx_port_stats (size:4224b/528B) */ -struct rx_port_stats { - __le64 rx_64b_frames; - __le64 rx_65b_127b_frames; - __le64 rx_128b_255b_frames; - __le64 rx_256b_511b_frames; - __le64 rx_512b_1023b_frames; - __le64 rx_1024b_1518_frames; - __le64 rx_good_vlan_frames; - __le64 rx_1519b_2047b_frames; - __le64 rx_2048b_4095b_frames; - __le64 rx_4096b_9216b_frames; - __le64 rx_9217b_16383b_frames; - __le64 rx_total_frames; - __le64 rx_ucast_frames; - __le64 rx_mcast_frames; - __le64 rx_bcast_frames; - __le64 rx_fcs_err_frames; - __le64 rx_ctrl_frames; - __le64 rx_pause_frames; - __le64 rx_pfc_frames; - __le64 rx_unsupported_opcode_frames; - __le64 rx_unsupported_da_pausepfc_frames; - __le64 rx_wrong_sa_frames; - __le64 rx_align_err_frames; - __le64 rx_oor_len_frames; - __le64 rx_code_err_frames; - __le64 rx_false_carrier_frames; - __le64 rx_ovrsz_frames; - __le64 rx_jbr_frames; - __le64 rx_mtu_err_frames; - __le64 rx_match_crc_frames; - __le64 rx_promiscuous_frames; - __le64 rx_tagged_frames; - __le64 rx_double_tagged_frames; - __le64 rx_trunc_frames; - __le64 rx_good_frames; - __le64 rx_pfc_xon2xoff_frames_pri0; - __le64 rx_pfc_xon2xoff_frames_pri1; - __le64 rx_pfc_xon2xoff_frames_pri2; - __le64 rx_pfc_xon2xoff_frames_pri3; - __le64 rx_pfc_xon2xoff_frames_pri4; - __le64 rx_pfc_xon2xoff_frames_pri5; - __le64 rx_pfc_xon2xoff_frames_pri6; - __le64 rx_pfc_xon2xoff_frames_pri7; - __le64 rx_pfc_ena_frames_pri0; - __le64 rx_pfc_ena_frames_pri1; - __le64 rx_pfc_ena_frames_pri2; - __le64 rx_pfc_ena_frames_pri3; - __le64 rx_pfc_ena_frames_pri4; - __le64 rx_pfc_ena_frames_pri5; - __le64 rx_pfc_ena_frames_pri6; - __le64 rx_pfc_ena_frames_pri7; - __le64 rx_sch_crc_err_frames; - __le64 rx_undrsz_frames; - __le64 rx_frag_frames; - __le64 rx_eee_lpi_events; - __le64 rx_eee_lpi_duration; - __le64 rx_llfc_physical_msgs; - __le64 rx_llfc_logical_msgs; - __le64 rx_llfc_msgs_with_crc_err; - __le64 rx_hcfc_msgs; - __le64 rx_hcfc_msgs_with_crc_err; - __le64 rx_bytes; - __le64 rx_runt_bytes; - __le64 rx_runt_frames; - __le64 rx_stat_discard; - __le64 rx_stat_err; -}; - -/* rx_port_stats_ext (size:320b/40B) */ -struct rx_port_stats_ext { - __le64 link_down_events; - __le64 continuous_pause_events; - __le64 resume_pause_events; - __le64 continuous_roce_pause_events; - __le64 resume_roce_pause_events; -}; - /* pcie_ctx_hw_stats (size:768b/96B) */ struct pcie_ctx_hw_stats { __le64 pcie_pl_signal_integrity; @@ -5884,6 +6390,114 @@ struct hwrm_wol_reason_qcfg_output { u8 valid; }; +/* coredump_segment_record (size:128b/16B) */ +struct coredump_segment_record { + __le16 component_id; + __le16 segment_id; + __le16 max_instances; + u8 version_hi; + u8 version_low; + u8 seg_flags; + u8 unused_0[7]; +}; + +/* hwrm_dbg_coredump_list_input (size:256b/32B) */ +struct hwrm_dbg_coredump_list_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 host_dest_addr; + __le32 host_buf_len; + __le16 seq_no; + u8 unused_0[2]; +}; + +/* hwrm_dbg_coredump_list_output (size:128b/16B) */ +struct hwrm_dbg_coredump_list_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 flags; + #define DBG_COREDUMP_LIST_RESP_FLAGS_MORE 0x1UL + u8 unused_0; + __le16 total_segments; + __le16 data_len; + u8 unused_1; + u8 valid; +}; + +/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */ +struct hwrm_dbg_coredump_initiate_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 component_id; + __le16 segment_id; + __le16 instance; + __le16 unused_0; + u8 seg_flags; + u8 unused_1[7]; +}; + +/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */ +struct hwrm_dbg_coredump_initiate_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* coredump_data_hdr (size:128b/16B) */ +struct coredump_data_hdr { + __le32 address; + __le32 flags_length; + __le32 instance; + __le32 next_offset; +}; + +/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */ +struct hwrm_dbg_coredump_retrieve_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 host_dest_addr; + __le32 host_buf_len; + __le32 unused_0; + __le16 component_id; + __le16 segment_id; + __le16 instance; + __le16 unused_1; + u8 seg_flags; + u8 unused_2; + __le16 unused_3; + __le32 unused_4; + __le32 seq_no; + __le32 unused_5; +}; + +/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */ +struct hwrm_dbg_coredump_retrieve_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 flags; + #define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE 0x1UL + u8 unused_0; + __le16 data_len; + u8 unused_1[3]; + u8 valid; +}; + /* hwrm_nvm_read_input (size:320b/40B) */ struct hwrm_nvm_read_input { __le16 req_type; @@ -6201,19 +6815,6 @@ struct hwrm_nvm_install_update_cmd_err { u8 unused_0[7]; }; -struct hwrm_nvm_variable_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le64 data_addr; - __le16 data_len; - __le16 option_num; - __le16 dimensions; - __le16 index_0; -}; - /* hwrm_nvm_get_variable_input (size:320b/40B) */ struct hwrm_nvm_get_variable_input { __le16 req_type; @@ -6282,12 +6883,14 @@ struct hwrm_nvm_set_variable_input { __le16 index_2; __le16 index_3; u8 flags; - #define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH 0x1UL - #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK 0xeUL - #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT 1 - #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE (0x0UL << 1) - #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1 (0x1UL << 1) - #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1 + #define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH 0x1UL + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK 0xeUL + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT 1 + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE (0x0UL << 1) + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1 (0x1UL << 1) + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256 (0x2UL << 1) + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH (0x3UL << 1) + #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH u8 unused_0; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index a64910892c25..6d583bcd2a81 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -447,7 +447,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) u16 vf_tx_rings, vf_rx_rings, vf_cp_rings; u16 vf_stat_ctx, vf_vnics, vf_ring_grps; struct bnxt_pf_info *pf = &bp->pf; - int i, rc = 0; + int i, rc = 0, min = 1; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1); @@ -464,14 +464,19 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) req.min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX); req.max_rsscos_ctx = cpu_to_le16(BNXT_VF_MAX_RSS_CTX); - if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL) { - req.min_cmpl_rings = cpu_to_le16(1); - req.min_tx_rings = cpu_to_le16(1); - req.min_rx_rings = cpu_to_le16(1); - req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MIN_L2_CTX); - req.min_vnics = cpu_to_le16(1); - req.min_stat_ctx = cpu_to_le16(1); - req.min_hw_ring_grps = cpu_to_le16(1); + if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) { + min = 0; + req.min_rsscos_ctx = cpu_to_le16(min); + } + if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL || + pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) { + req.min_cmpl_rings = cpu_to_le16(min); + req.min_tx_rings = cpu_to_le16(min); + req.min_rx_rings = cpu_to_le16(min); + req.min_l2_ctxs = cpu_to_le16(min); + req.min_vnics = cpu_to_le16(min); + req.min_stat_ctx = cpu_to_le16(min); + req.min_hw_ring_grps = cpu_to_le16(min); } else { vf_cp_rings /= num_vfs; vf_tx_rings /= num_vfs; @@ -618,7 +623,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) static int bnxt_func_cfg(struct bnxt *bp, int num_vfs) { - if (bp->flags & BNXT_FLAG_NEW_RM) + if (BNXT_NEW_RM(bp)) return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs); else return bnxt_hwrm_func_cfg(bp, num_vfs); @@ -956,9 +961,13 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf) } else if (is_valid_ether_addr(vf->vf_mac_addr)) { if (ether_addr_equal((const u8 *)req->l2_addr, vf->vf_mac_addr)) mac_ok = true; - } else if (bp->hwrm_spec_code < 0x10202) { - mac_ok = true; } else { + /* There are two cases: + * 1.If firmware spec < 0x10202,VF MAC address is not forwarded + * to the PF and so it doesn't have to match + * 2.Allow VF to modify it's own MAC when PF has not assigned a + * valid MAC address and firmware spec >= 0x10202 + */ mac_ok = true; } if (mac_ok) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 840f6e505f73..c37b2842f972 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -141,7 +141,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, if (avail_msix > num_msix) avail_msix = num_msix; - if (bp->flags & BNXT_FLAG_NEW_RM) { + if (BNXT_NEW_RM(bp)) { idx = bp->cp_nr_rings; } else { max_idx = min_t(int, bp->total_irqs, max_cp_rings); @@ -162,7 +162,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, return -EAGAIN; } - if (bp->flags & BNXT_FLAG_NEW_RM) { + if (BNXT_NEW_RM(bp)) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; avail_msix = hw_resc->resv_cp_rings - bp->cp_nr_rings; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index e088dedc1747..9f4f3c1d5043 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1417,50 +1417,6 @@ int validate_cn23xx_pf_config_info(struct octeon_device *oct, return 0; } -void cn23xx_dump_iq_regs(struct octeon_device *oct) -{ - u32 regval, q_no; - - dev_dbg(&oct->pci_dev->dev, "SLI_IQ_DOORBELL_0 [0x%x]: 0x%016llx\n", - CN23XX_SLI_IQ_DOORBELL(0), - CVM_CAST64(octeon_read_csr64 - (oct, CN23XX_SLI_IQ_DOORBELL(0)))); - - dev_dbg(&oct->pci_dev->dev, "SLI_IQ_BASEADDR_0 [0x%x]: 0x%016llx\n", - CN23XX_SLI_IQ_BASE_ADDR64(0), - CVM_CAST64(octeon_read_csr64 - (oct, CN23XX_SLI_IQ_BASE_ADDR64(0)))); - - dev_dbg(&oct->pci_dev->dev, "SLI_IQ_FIFO_RSIZE_0 [0x%x]: 0x%016llx\n", - CN23XX_SLI_IQ_SIZE(0), - CVM_CAST64(octeon_read_csr64(oct, CN23XX_SLI_IQ_SIZE(0)))); - - dev_dbg(&oct->pci_dev->dev, "SLI_CTL_STATUS [0x%x]: 0x%016llx\n", - CN23XX_SLI_CTL_STATUS, - CVM_CAST64(octeon_read_csr64(oct, CN23XX_SLI_CTL_STATUS))); - - for (q_no = 0; q_no < CN23XX_MAX_INPUT_QUEUES; q_no++) { - dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n", - q_no, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), - CVM_CAST64(octeon_read_csr64 - (oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no)))); - } - - pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, ®val); - dev_dbg(&oct->pci_dev->dev, "Config DevCtl [0x%x]: 0x%08x\n", - CN23XX_CONFIG_PCIE_DEVCTL, regval); - - dev_dbg(&oct->pci_dev->dev, "SLI_PRT[%d]_CFG [0x%llx]: 0x%016llx\n", - oct->pcie_port, CN23XX_DPI_SLI_PRTX_CFG(oct->pcie_port), - CVM_CAST64(lio_pci_readq( - oct, CN23XX_DPI_SLI_PRTX_CFG(oct->pcie_port)))); - - dev_dbg(&oct->pci_dev->dev, "SLI_S2M_PORT[%d]_CTL [0x%x]: 0x%016llx\n", - oct->pcie_port, CN23XX_SLI_S2M_PORTX_CTL(oct->pcie_port), - CVM_CAST64(octeon_read_csr64( - oct, CN23XX_SLI_S2M_PORTX_CTL(oct->pcie_port)))); -} - int cn23xx_fw_loaded(struct octeon_device *oct) { u64 val; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c index 91dce8b8ef7e..962bb62933db 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c @@ -682,33 +682,3 @@ int cn23xx_setup_octeon_vf_device(struct octeon_device *oct) return 0; } - -void cn23xx_dump_vf_iq_regs(struct octeon_device *oct) -{ - u32 regval, q_no; - - dev_dbg(&oct->pci_dev->dev, "SLI_IQ_DOORBELL_0 [0x%x]: 0x%016llx\n", - CN23XX_VF_SLI_IQ_DOORBELL(0), - CVM_CAST64(octeon_read_csr64( - oct, CN23XX_VF_SLI_IQ_DOORBELL(0)))); - - dev_dbg(&oct->pci_dev->dev, "SLI_IQ_BASEADDR_0 [0x%x]: 0x%016llx\n", - CN23XX_VF_SLI_IQ_BASE_ADDR64(0), - CVM_CAST64(octeon_read_csr64( - oct, CN23XX_VF_SLI_IQ_BASE_ADDR64(0)))); - - dev_dbg(&oct->pci_dev->dev, "SLI_IQ_FIFO_RSIZE_0 [0x%x]: 0x%016llx\n", - CN23XX_VF_SLI_IQ_SIZE(0), - CVM_CAST64(octeon_read_csr64(oct, CN23XX_VF_SLI_IQ_SIZE(0)))); - - for (q_no = 0; q_no < oct->sriov_info.rings_per_vf; q_no++) { - dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n", - q_no, CN23XX_VF_SLI_IQ_PKT_CONTROL64(q_no), - CVM_CAST64(octeon_read_csr64( - oct, CN23XX_VF_SLI_IQ_PKT_CONTROL64(q_no)))); - } - - pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, ®val); - dev_dbg(&oct->pci_dev->dev, "Config DevCtl [0x%x]: 0x%08x\n", - CN23XX_CONFIG_PCIE_DEVCTL, regval); -} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 2320f7829a6b..6f312e03432f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2474,16 +2474,64 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset) return NULL; } +static int sge_qinfo_uld_txq_entries(const struct adapter *adap, int uld) +{ + const struct sge_uld_txq_info *utxq_info = adap->sge.uld_txq_info[uld]; + + if (!utxq_info) + return 0; + + return DIV_ROUND_UP(utxq_info->ntxq, 4); +} + +static int sge_qinfo_uld_rspq_entries(const struct adapter *adap, int uld, + bool ciq) +{ + const struct sge_uld_rxq_info *urxq_info = adap->sge.uld_rxq_info[uld]; + + if (!urxq_info) + return 0; + + return ciq ? DIV_ROUND_UP(urxq_info->nciq, 4) : + DIV_ROUND_UP(urxq_info->nrxq, 4); +} + +static int sge_qinfo_uld_rxq_entries(const struct adapter *adap, int uld) +{ + return sge_qinfo_uld_rspq_entries(adap, uld, false); +} + +static int sge_qinfo_uld_ciq_entries(const struct adapter *adap, int uld) +{ + return sge_qinfo_uld_rspq_entries(adap, uld, true); +} + static int sge_qinfo_show(struct seq_file *seq, void *v) { + int uld_rxq_entries[CXGB4_ULD_MAX] = { 0 }; + int uld_ciq_entries[CXGB4_ULD_MAX] = { 0 }; + int uld_txq_entries[CXGB4_TX_MAX] = { 0 }; + const struct sge_uld_txq_info *utxq_info; + const struct sge_uld_rxq_info *urxq_info; struct adapter *adap = seq->private; - int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4); - int ofld_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4); - int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4); - int i, r = (uintptr_t)v - 1; - int ofld_idx = r - eth_entries; - int ctrl_idx = ofld_idx - ofld_entries; - int fq_idx = ctrl_idx - ctrl_entries; + int i, n, r = (uintptr_t)v - 1; + int eth_entries, ctrl_entries; + struct sge *s = &adap->sge; + + eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4); + ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4); + + mutex_lock(&uld_mutex); + if (s->uld_txq_info) + for (i = 0; i < ARRAY_SIZE(uld_txq_entries); i++) + uld_txq_entries[i] = sge_qinfo_uld_txq_entries(adap, i); + + if (s->uld_rxq_info) { + for (i = 0; i < ARRAY_SIZE(uld_rxq_entries); i++) { + uld_rxq_entries[i] = sge_qinfo_uld_rxq_entries(adap, i); + uld_ciq_entries[i] = sge_qinfo_uld_ciq_entries(adap, i); + } + } if (r) seq_putc(seq, '\n'); @@ -2505,9 +2553,10 @@ do { \ if (r < eth_entries) { int base_qset = r * 4; - const struct sge_eth_rxq *rx = &adap->sge.ethrxq[base_qset]; - const struct sge_eth_txq *tx = &adap->sge.ethtxq[base_qset]; - int n = min(4, adap->sge.ethqsets - 4 * r); + const struct sge_eth_rxq *rx = &s->ethrxq[base_qset]; + const struct sge_eth_txq *tx = &s->ethtxq[base_qset]; + + n = min(4, s->ethqsets - 4 * r); S("QType:", "Ethernet"); S("Interface:", @@ -2532,8 +2581,7 @@ do { \ R("RspQ CIDX:", rspq.cidx); R("RspQ Gen:", rspq.gen); S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); - S3("u", "Intr pktcnt:", - adap->sge.counter_val[rx[i].rspq.pktcnt_idx]); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); R("FL ID:", fl.cntxt_id); R("FL size:", fl.size - 8); R("FL pend:", fl.pend_cred); @@ -2558,9 +2606,196 @@ do { \ RL("FLLow:", fl.low); RL("FLStarving:", fl.starving); - } else if (ctrl_idx < ctrl_entries) { - const struct sge_ctrl_txq *tx = &adap->sge.ctrlq[ctrl_idx * 4]; - int n = min(4, adap->params.nports - 4 * ctrl_idx); + goto unlock; + } + + r -= eth_entries; + if (r < uld_txq_entries[CXGB4_TX_OFLD]) { + const struct sge_uld_txq *tx; + + utxq_info = s->uld_txq_info[CXGB4_TX_OFLD]; + tx = &utxq_info->uldtxq[r * 4]; + n = min(4, utxq_info->ntxq - 4 * r); + + S("QType:", "OFLD-TXQ"); + T("TxQ ID:", q.cntxt_id); + T("TxQ size:", q.size); + T("TxQ inuse:", q.in_use); + T("TxQ CIDX:", q.cidx); + T("TxQ PIDX:", q.pidx); + + goto unlock; + } + + r -= uld_txq_entries[CXGB4_TX_OFLD]; + if (r < uld_rxq_entries[CXGB4_ULD_RDMA]) { + const struct sge_ofld_rxq *rx; + + urxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA]; + rx = &urxq_info->uldrxq[r * 4]; + n = min(4, urxq_info->nrxq - 4 * r); + + S("QType:", "RDMA-CPL"); + S("Interface:", + rx[i].rspq.netdev ? rx[i].rspq.netdev->name : "N/A"); + R("RspQ ID:", rspq.abs_id); + R("RspQ size:", rspq.size); + R("RspQE size:", rspq.iqe_len); + R("RspQ CIDX:", rspq.cidx); + R("RspQ Gen:", rspq.gen); + S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); + R("FL ID:", fl.cntxt_id); + R("FL size:", fl.size - 8); + R("FL pend:", fl.pend_cred); + R("FL avail:", fl.avail); + R("FL PIDX:", fl.pidx); + R("FL CIDX:", fl.cidx); + + goto unlock; + } + + r -= uld_rxq_entries[CXGB4_ULD_RDMA]; + if (r < uld_ciq_entries[CXGB4_ULD_RDMA]) { + const struct sge_ofld_rxq *rx; + int ciq_idx = 0; + + urxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA]; + ciq_idx = urxq_info->nrxq + (r * 4); + rx = &urxq_info->uldrxq[ciq_idx]; + n = min(4, urxq_info->nciq - 4 * r); + + S("QType:", "RDMA-CIQ"); + S("Interface:", + rx[i].rspq.netdev ? rx[i].rspq.netdev->name : "N/A"); + R("RspQ ID:", rspq.abs_id); + R("RspQ size:", rspq.size); + R("RspQE size:", rspq.iqe_len); + R("RspQ CIDX:", rspq.cidx); + R("RspQ Gen:", rspq.gen); + S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); + + goto unlock; + } + + r -= uld_ciq_entries[CXGB4_ULD_RDMA]; + if (r < uld_rxq_entries[CXGB4_ULD_ISCSI]) { + const struct sge_ofld_rxq *rx; + + urxq_info = s->uld_rxq_info[CXGB4_ULD_ISCSI]; + rx = &urxq_info->uldrxq[r * 4]; + n = min(4, urxq_info->nrxq - 4 * r); + + S("QType:", "iSCSI"); + R("RspQ ID:", rspq.abs_id); + R("RspQ size:", rspq.size); + R("RspQE size:", rspq.iqe_len); + R("RspQ CIDX:", rspq.cidx); + R("RspQ Gen:", rspq.gen); + S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); + R("FL ID:", fl.cntxt_id); + R("FL size:", fl.size - 8); + R("FL pend:", fl.pend_cred); + R("FL avail:", fl.avail); + R("FL PIDX:", fl.pidx); + R("FL CIDX:", fl.cidx); + + goto unlock; + } + + r -= uld_rxq_entries[CXGB4_ULD_ISCSI]; + if (r < uld_rxq_entries[CXGB4_ULD_ISCSIT]) { + const struct sge_ofld_rxq *rx; + + urxq_info = s->uld_rxq_info[CXGB4_ULD_ISCSIT]; + rx = &urxq_info->uldrxq[r * 4]; + n = min(4, urxq_info->nrxq - 4 * r); + + S("QType:", "iSCSIT"); + R("RspQ ID:", rspq.abs_id); + R("RspQ size:", rspq.size); + R("RspQE size:", rspq.iqe_len); + R("RspQ CIDX:", rspq.cidx); + R("RspQ Gen:", rspq.gen); + S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); + R("FL ID:", fl.cntxt_id); + R("FL size:", fl.size - 8); + R("FL pend:", fl.pend_cred); + R("FL avail:", fl.avail); + R("FL PIDX:", fl.pidx); + R("FL CIDX:", fl.cidx); + + goto unlock; + } + + r -= uld_rxq_entries[CXGB4_ULD_ISCSIT]; + if (r < uld_rxq_entries[CXGB4_ULD_TLS]) { + const struct sge_ofld_rxq *rx; + + urxq_info = s->uld_rxq_info[CXGB4_ULD_TLS]; + rx = &urxq_info->uldrxq[r * 4]; + n = min(4, urxq_info->nrxq - 4 * r); + + S("QType:", "TLS"); + R("RspQ ID:", rspq.abs_id); + R("RspQ size:", rspq.size); + R("RspQE size:", rspq.iqe_len); + R("RspQ CIDX:", rspq.cidx); + R("RspQ Gen:", rspq.gen); + S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); + R("FL ID:", fl.cntxt_id); + R("FL size:", fl.size - 8); + R("FL pend:", fl.pend_cred); + R("FL avail:", fl.avail); + R("FL PIDX:", fl.pidx); + R("FL CIDX:", fl.cidx); + + goto unlock; + } + + r -= uld_rxq_entries[CXGB4_ULD_TLS]; + if (r < uld_txq_entries[CXGB4_TX_CRYPTO]) { + const struct sge_ofld_rxq *rx; + const struct sge_uld_txq *tx; + + utxq_info = s->uld_txq_info[CXGB4_TX_CRYPTO]; + urxq_info = s->uld_rxq_info[CXGB4_ULD_CRYPTO]; + tx = &utxq_info->uldtxq[r * 4]; + rx = &urxq_info->uldrxq[r * 4]; + n = min(4, utxq_info->ntxq - 4 * r); + + S("QType:", "Crypto"); + T("TxQ ID:", q.cntxt_id); + T("TxQ size:", q.size); + T("TxQ inuse:", q.in_use); + T("TxQ CIDX:", q.cidx); + T("TxQ PIDX:", q.pidx); + R("RspQ ID:", rspq.abs_id); + R("RspQ size:", rspq.size); + R("RspQE size:", rspq.iqe_len); + R("RspQ CIDX:", rspq.cidx); + R("RspQ Gen:", rspq.gen); + S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq)); + S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]); + R("FL ID:", fl.cntxt_id); + R("FL size:", fl.size - 8); + R("FL pend:", fl.pend_cred); + R("FL avail:", fl.avail); + R("FL PIDX:", fl.pidx); + R("FL CIDX:", fl.cidx); + + goto unlock; + } + + r -= uld_txq_entries[CXGB4_TX_CRYPTO]; + if (r < ctrl_entries) { + const struct sge_ctrl_txq *tx = &s->ctrlq[r * 4]; + + n = min(4, adap->params.nports - 4 * r); S("QType:", "Control"); T("TxQ ID:", q.cntxt_id); @@ -2570,8 +2805,13 @@ do { \ T("TxQ PIDX:", q.pidx); TL("TxQFull:", q.stops); TL("TxQRestarts:", q.restarts); - } else if (fq_idx == 0) { - const struct sge_rspq *evtq = &adap->sge.fw_evtq; + + goto unlock; + } + + r -= ctrl_entries; + if (r < 1) { + const struct sge_rspq *evtq = &s->fw_evtq; seq_printf(seq, "%-12s %16s\n", "QType:", "FW event queue"); seq_printf(seq, "%-12s %16u\n", "RspQ ID:", evtq->abs_id); @@ -2582,8 +2822,13 @@ do { \ seq_printf(seq, "%-12s %16u\n", "Intr delay:", qtimer_val(adap, evtq)); seq_printf(seq, "%-12s %16u\n", "Intr pktcnt:", - adap->sge.counter_val[evtq->pktcnt_idx]); + s->counter_val[evtq->pktcnt_idx]); + + goto unlock; } + +unlock: + mutex_unlock(&uld_mutex); #undef R #undef RL #undef T @@ -2597,8 +2842,21 @@ do { \ static int sge_queue_entries(const struct adapter *adap) { + int tot_uld_entries = 0; + int i; + + mutex_lock(&uld_mutex); + for (i = 0; i < CXGB4_TX_MAX; i++) + tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i); + + for (i = 0; i < CXGB4_ULD_MAX; i++) { + tot_uld_entries += sge_qinfo_uld_rxq_entries(adap, i); + tot_uld_entries += sge_qinfo_uld_ciq_entries(adap, i); + } + mutex_unlock(&uld_mutex); + return DIV_ROUND_UP(adap->sge.ethqsets, 4) + - DIV_ROUND_UP(adap->sge.ofldqsets, 4) + + tot_uld_entries + DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 40cf8dc9f163..0f7ce71205e6 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -554,10 +554,9 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp, dev = q->adap->port[q->adap->chan_map[port]]; dcbxdis = (action == FW_PORT_ACTION_GET_PORT_INFO - ? !!(pcmd->u.info.dcbxdis_pkd & - FW_PORT_CMD_DCBXDIS_F) - : !!(pcmd->u.info32.lstatus32_to_cbllen32 & - FW_PORT_CMD_DCBXDIS32_F)); + ? !!(pcmd->u.info.dcbxdis_pkd & FW_PORT_CMD_DCBXDIS_F) + : !!(be32_to_cpu(pcmd->u.info32.lstatus32_to_cbllen32) + & FW_PORT_CMD_DCBXDIS32_F)); state_input = (dcbxdis ? CXGB4_DCB_INPUT_FW_DISABLED : CXGB4_DCB_INPUT_FW_ENABLED); @@ -3074,6 +3073,7 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev, adapter->geneve_port = 0; t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0); + break; default: return; } @@ -3159,6 +3159,7 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F); + break; default: return; } diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig index 5ab912937aff..ec0b545197e2 100644 --- a/drivers/net/ethernet/cirrus/Kconfig +++ b/drivers/net/ethernet/cirrus/Kconfig @@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS config CS89x0 tristate "CS89x0 support" depends on ISA || EISA || ARM + depends on !PPC32 ---help--- Support for CS89x0 chipset based Ethernet cards. If you have a network (Ethernet) card of this type, say Y and read the file diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 90c645b8538e..60641e202534 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2047,28 +2047,42 @@ static int enic_stop(struct net_device *netdev) return 0; } +static int _enic_change_mtu(struct net_device *netdev, int new_mtu) +{ + bool running = netif_running(netdev); + int err = 0; + + ASSERT_RTNL(); + if (running) { + err = enic_stop(netdev); + if (err) + return err; + } + + netdev->mtu = new_mtu; + + if (running) { + err = enic_open(netdev); + if (err) + return err; + } + + return 0; +} + static int enic_change_mtu(struct net_device *netdev, int new_mtu) { struct enic *enic = netdev_priv(netdev); - int running = netif_running(netdev); if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic)) return -EOPNOTSUPP; - if (running) - enic_stop(netdev); - - netdev->mtu = new_mtu; - if (netdev->mtu > enic->port_mtu) netdev_warn(netdev, - "interface MTU (%d) set higher than port MTU (%d)\n", - netdev->mtu, enic->port_mtu); + "interface MTU (%d) set higher than port MTU (%d)\n", + netdev->mtu, enic->port_mtu); - if (running) - enic_open(netdev); - - return 0; + return _enic_change_mtu(netdev, new_mtu); } static void enic_change_mtu_work(struct work_struct *work) @@ -2076,47 +2090,9 @@ static void enic_change_mtu_work(struct work_struct *work) struct enic *enic = container_of(work, struct enic, change_mtu_work); struct net_device *netdev = enic->netdev; int new_mtu = vnic_dev_mtu(enic->vdev); - int err; - unsigned int i; - - new_mtu = max_t(int, ENIC_MIN_MTU, min_t(int, ENIC_MAX_MTU, new_mtu)); rtnl_lock(); - - /* Stop RQ */ - del_timer_sync(&enic->notify_timer); - - for (i = 0; i < enic->rq_count; i++) - napi_disable(&enic->napi[i]); - - vnic_intr_mask(&enic->intr[0]); - enic_synchronize_irqs(enic); - err = vnic_rq_disable(&enic->rq[0]); - if (err) { - rtnl_unlock(); - netdev_err(netdev, "Unable to disable RQ.\n"); - return; - } - vnic_rq_clean(&enic->rq[0], enic_free_rq_buf); - vnic_cq_clean(&enic->cq[0]); - vnic_intr_clean(&enic->intr[0]); - - /* Fill RQ with new_mtu-sized buffers */ - netdev->mtu = new_mtu; - vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf); - /* Need at least one buffer on ring to get going */ - if (vnic_rq_desc_used(&enic->rq[0]) == 0) { - rtnl_unlock(); - netdev_err(netdev, "Unable to alloc receive buffers.\n"); - return; - } - - /* Start RQ */ - vnic_rq_enable(&enic->rq[0]); - napi_enable(&enic->napi[0]); - vnic_intr_unmask(&enic->intr[0]); - enic_notify_timer_start(enic); - + (void)_enic_change_mtu(netdev, new_mtu); rtnl_unlock(); netdev_info(netdev, "interface MTU set as %d\n", netdev->mtu); @@ -2916,7 +2892,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ enic->port_mtu = enic->config.mtu; - (void)enic_change_mtu(netdev, enic->port_mtu); err = enic_set_mac_addr(netdev, enic->mac_addr); if (err) { @@ -3006,6 +2981,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* MTU range: 68 - 9000 */ netdev->min_mtu = ENIC_MIN_MTU; netdev->max_mtu = ENIC_MAX_MTU; + netdev->mtu = enic->port_mtu; err = register_netdev(netdev); if (err) { diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c index e9db811df59c..901e44b0b795 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.c +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c @@ -1071,7 +1071,7 @@ struct vnic_dev *vnic_dev_register(struct vnic_dev *vdev, unsigned int num_bars) { if (!vdev) { - vdev = kzalloc(sizeof(struct vnic_dev), GFP_ATOMIC); + vdev = kzalloc(sizeof(struct vnic_dev), GFP_KERNEL); if (!vdev) return NULL; } diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c index f8aa326d1d58..a3e7b003ada1 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_rq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c @@ -35,7 +35,7 @@ static int vnic_rq_alloc_bufs(struct vnic_rq *rq) unsigned int blks = VNIC_RQ_BUF_BLKS_NEEDED(count); for (i = 0; i < blks; i++) { - rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_ATOMIC); + rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_KERNEL); if (!rq->bufs[i]) return -ENOMEM; } diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.c b/drivers/net/ethernet/cisco/enic/vnic_wq.c index 090cc65658a3..eb75891974df 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_wq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_wq.c @@ -35,7 +35,7 @@ static int vnic_wq_alloc_bufs(struct vnic_wq *wq) unsigned int blks = VNIC_WQ_BUF_BLKS_NEEDED(count); for (i = 0; i < blks; i++) { - wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_ATOMIC); + wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_KERNEL); if (!wq->bufs[i]) return -ENOMEM; } diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 7005949dc17b..d80fe03d3107 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -37,7 +37,7 @@ #include "be_hw.h" #include "be_roce.h" -#define DRV_VER "11.4.0.0" +#define DRV_VER "12.0.0.0" #define DRV_NAME "be2net" #define BE_NAME "Emulex BladeEngine2" #define BE3_NAME "Emulex BladeEngine3" diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 05e4c0bb25f4..d0b9415d9ae7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1412,6 +1412,83 @@ drop: return NETDEV_TX_OK; } +static void be_tx_timeout(struct net_device *netdev) +{ + struct be_adapter *adapter = netdev_priv(netdev); + struct device *dev = &adapter->pdev->dev; + struct be_tx_obj *txo; + struct sk_buff *skb; + struct tcphdr *tcphdr; + struct udphdr *udphdr; + u32 *entry; + int status; + int i, j; + + for_all_tx_queues(adapter, txo, i) { + dev_info(dev, "TXQ Dump: %d H: %d T: %d used: %d, qid: 0x%x\n", + i, txo->q.head, txo->q.tail, + atomic_read(&txo->q.used), txo->q.id); + + entry = txo->q.dma_mem.va; + for (j = 0; j < TX_Q_LEN * 4; j += 4) { + if (entry[j] != 0 || entry[j + 1] != 0 || + entry[j + 2] != 0 || entry[j + 3] != 0) { + dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n", + j, entry[j], entry[j + 1], + entry[j + 2], entry[j + 3]); + } + } + + entry = txo->cq.dma_mem.va; + dev_info(dev, "TXCQ Dump: %d H: %d T: %d used: %d\n", + i, txo->cq.head, txo->cq.tail, + atomic_read(&txo->cq.used)); + for (j = 0; j < TX_CQ_LEN * 4; j += 4) { + if (entry[j] != 0 || entry[j + 1] != 0 || + entry[j + 2] != 0 || entry[j + 3] != 0) { + dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n", + j, entry[j], entry[j + 1], + entry[j + 2], entry[j + 3]); + } + } + + for (j = 0; j < TX_Q_LEN; j++) { + if (txo->sent_skb_list[j]) { + skb = txo->sent_skb_list[j]; + if (ip_hdr(skb)->protocol == IPPROTO_TCP) { + tcphdr = tcp_hdr(skb); + dev_info(dev, "TCP source port %d\n", + ntohs(tcphdr->source)); + dev_info(dev, "TCP dest port %d\n", + ntohs(tcphdr->dest)); + dev_info(dev, "TCP sequence num %d\n", + ntohs(tcphdr->seq)); + dev_info(dev, "TCP ack_seq %d\n", + ntohs(tcphdr->ack_seq)); + } else if (ip_hdr(skb)->protocol == + IPPROTO_UDP) { + udphdr = udp_hdr(skb); + dev_info(dev, "UDP source port %d\n", + ntohs(udphdr->source)); + dev_info(dev, "UDP dest port %d\n", + ntohs(udphdr->dest)); + } + dev_info(dev, "skb[%d] %p len %d proto 0x%x\n", + j, skb, skb->len, skb->protocol); + } + } + } + + if (lancer_chip(adapter)) { + dev_info(dev, "Initiating reset due to tx timeout\n"); + dev_info(dev, "Resetting adapter\n"); + status = lancer_physdev_ctrl(adapter, + PHYSDEV_CONTROL_FW_RESET_MASK); + if (status) + dev_err(dev, "Reset failed .. Reboot server\n"); + } +} + static inline bool be_in_all_promisc(struct be_adapter *adapter) { return (adapter->if_flags & BE_IF_FLAGS_ALL_PROMISCUOUS) == @@ -3274,7 +3351,7 @@ void be_detect_error(struct be_adapter *adapter) /* Do not log error messages if its a FW reset */ if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 && sliport_err2 == SLIPORT_ERROR_FW_RESET2) { - dev_info(dev, "Firmware update in progress\n"); + dev_info(dev, "Reset is in progress\n"); } else { dev_err(dev, "Error detected in the card\n"); dev_err(dev, "ERR: sliport status 0x%x\n", @@ -5218,6 +5295,7 @@ static const struct net_device_ops be_netdev_ops = { .ndo_get_vf_config = be_get_vf_config, .ndo_set_vf_link_state = be_set_vf_link_state, .ndo_set_vf_spoofchk = be_set_vf_spoofchk, + .ndo_tx_timeout = be_tx_timeout, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = be_netpoll, #endif diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index c729665107f5..76366c735831 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -48,6 +48,7 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/clk.h> +#include <linux/crc32.h> #include <linux/platform_device.h> #include <linux/mdio.h> #include <linux/phy.h> @@ -2955,7 +2956,7 @@ static void set_multicast_list(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); struct netdev_hw_addr *ha; - unsigned int i, bit, data, crc, tmp; + unsigned int crc, tmp; unsigned char hash; unsigned int hash_high = 0, hash_low = 0; @@ -2983,15 +2984,7 @@ static void set_multicast_list(struct net_device *ndev) /* Add the addresses in hash register */ netdev_for_each_mc_addr(ha, ndev) { /* calculate crc32 value of mac address */ - crc = 0xffffffff; - - for (i = 0; i < ndev->addr_len; i++) { - data = ha->addr[i]; - for (bit = 0; bit < 8; bit++, data >>= 1) { - crc = (crc >> 1) ^ - (((crc ^ data) & 1) ? CRC32_POLY : 0); - } - } + crc = ether_crc_le(ndev->addr_len, ha->addr); /* only upper 6 bits (FEC_HASH_BITS) are used * which point to specific bit in the hash registers @@ -3136,6 +3129,7 @@ static int fec_enet_init(struct net_device *ndev) unsigned dsize = fep->bufdesc_ex ? sizeof(struct bufdesc_ex) : sizeof(struct bufdesc); unsigned dsize_log2 = __fls(dsize); + int ret; WARN_ON(dsize != (1 << dsize_log2)); #if defined(CONFIG_ARM) || defined(CONFIG_ARM64) @@ -3146,6 +3140,13 @@ static int fec_enet_init(struct net_device *ndev) fep->tx_align = 0x3; #endif + /* Check mask of the streaming and coherent API */ + ret = dma_set_mask_and_coherent(&fep->pdev->dev, DMA_BIT_MASK(32)); + if (ret < 0) { + dev_warn(&fep->pdev->dev, "No suitable DMA available\n"); + return ret; + } + fec_enet_alloc_queue(ndev); bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize; diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index 1fc27c97e3b2..99fe2c210d0f 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -18,6 +18,7 @@ #include <linux/string.h> #include <linux/ptrace.h> #include <linux/errno.h> +#include <linux/crc32.h> #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/delay.h> @@ -176,21 +177,10 @@ static void set_multicast_start(struct net_device *dev) static void set_multicast_one(struct net_device *dev, const u8 *mac) { struct fs_enet_private *fep = netdev_priv(dev); - int temp, hash_index, i, j; + int temp, hash_index; u32 crc, csrVal; - u8 byte, msb; - - crc = 0xffffffff; - for (i = 0; i < 6; i++) { - byte = mac[i]; - for (j = 0; j < 8; j++) { - msb = crc >> 31; - crc <<= 1; - if (msb ^ (byte & 0x1)) - crc ^= FEC_CRC_POLY; - byte >>= 1; - } - } + + crc = ether_crc(6, mac); temp = (crc & 0x3f) >> 1; hash_index = ((temp & 0x01) << 4) | diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index bd68379d2bea..e6aad30e7e69 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -70,8 +70,8 @@ static struct ring_pair_cb *hns_ae_get_ring_pair(struct hnae_queue *q) return container_of(q, struct ring_pair_cb, q); } -struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, - u32 port_id) +static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, + u32 port_id) { int vfnum_per_port; int qnum_per_vf; @@ -329,7 +329,7 @@ static int hns_ae_start(struct hnae_handle *handle) return 0; } -void hns_ae_stop(struct hnae_handle *handle) +static void hns_ae_stop(struct hnae_handle *handle) { struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); @@ -357,7 +357,7 @@ static void hns_ae_reset(struct hnae_handle *handle) } } -void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask) +static void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask) { u32 flag; @@ -577,8 +577,8 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle, *rx_usecs_high = HNS_RCB_RX_USECS_HIGH; } -void hns_ae_update_stats(struct hnae_handle *handle, - struct net_device_stats *net_stats) +static void hns_ae_update_stats(struct hnae_handle *handle, + struct net_device_stats *net_stats) { int port; int idx; @@ -660,7 +660,7 @@ void hns_ae_update_stats(struct hnae_handle *handle, net_stats->multicast = mac_cb->hw_stats.rx_mc_pkts; } -void hns_ae_get_stats(struct hnae_handle *handle, u64 *data) +static void hns_ae_get_stats(struct hnae_handle *handle, u64 *data) { int idx; struct hns_mac_cb *mac_cb; @@ -692,8 +692,8 @@ void hns_ae_get_stats(struct hnae_handle *handle, u64 *data) hns_dsaf_get_stats(vf_cb->dsaf_dev, p, vf_cb->port_index); } -void hns_ae_get_strings(struct hnae_handle *handle, - u32 stringset, u8 *data) +static void hns_ae_get_strings(struct hnae_handle *handle, + u32 stringset, u8 *data) { int port; int idx; @@ -725,7 +725,7 @@ void hns_ae_get_strings(struct hnae_handle *handle, hns_dsaf_get_strings(stringset, p, port, dsaf_dev); } -int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset) +static int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset) { u32 sset_count = 0; struct hns_mac_cb *mac_cb; @@ -771,7 +771,7 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, return ret; } -void hns_ae_update_led_status(struct hnae_handle *handle) +static void hns_ae_update_led_status(struct hnae_handle *handle) { struct hns_mac_cb *mac_cb; @@ -783,8 +783,8 @@ void hns_ae_update_led_status(struct hnae_handle *handle) hns_set_led_opt(mac_cb); } -int hns_ae_cpld_set_led_id(struct hnae_handle *handle, - enum hnae_led_state status) +static int hns_ae_cpld_set_led_id(struct hnae_handle *handle, + enum hnae_led_state status) { struct hns_mac_cb *mac_cb; @@ -795,7 +795,7 @@ int hns_ae_cpld_set_led_id(struct hnae_handle *handle, return hns_cpld_led_set_id(mac_cb, status); } -void hns_ae_get_regs(struct hnae_handle *handle, void *data) +static void hns_ae_get_regs(struct hnae_handle *handle, void *data) { u32 *p = data; int i; @@ -820,7 +820,7 @@ void hns_ae_get_regs(struct hnae_handle *handle, void *data) hns_dsaf_get_regs(vf_cb->dsaf_dev, vf_cb->port_index, p); } -int hns_ae_get_regs_len(struct hnae_handle *handle) +static int hns_ae_get_regs_len(struct hnae_handle *handle) { u32 total_num; struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 74bd260ca02a..5488c6e89f21 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -339,7 +339,7 @@ static void hns_gmac_init(void *mac_drv) GMAC_TX_WATER_LINE_SHIFT, 8); } -void hns_gmac_update_stats(void *mac_drv) +static void hns_gmac_update_stats(void *mac_drv) { struct mac_hw_stats *hw_stats = NULL; struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 9dcc5765f11f..3545a5d0bc95 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -458,11 +458,6 @@ int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size) { struct mac_driver *drv = hns_mac_get_drv(mac_cb); u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ? - MAC_MAX_MTU : MAC_MAX_MTU_V2; - - if (mac_cb->mac_type == HNAE_PORT_DEBUG) - max_frm = MAC_MAX_MTU_DBG; if (new_frm > HNS_RCB_RING_MAX_BD_PER_PKT * buf_size) return -EINVAL; @@ -931,8 +926,9 @@ static int hns_mac_get_mode(phy_interface_t phy_if) } } -u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev, - struct hns_mac_cb *mac_cb, u32 mac_mode_idx) +static u8 __iomem * +hns_mac_get_vaddr(struct dsaf_device *dsaf_dev, + struct hns_mac_cb *mac_cb, u32 mac_mode_idx) { u8 __iomem *base = dsaf_dev->io_base; int mac_id = mac_cb->mac_id; @@ -950,7 +946,8 @@ u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev, * @mac_cb: mac control block * return 0 - success , negative --fail */ -int hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb) +static int +hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb) { int ret; u32 mac_mode_idx; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 0ce07f6eb1e6..ca50c2553a9c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -28,7 +28,7 @@ #include "hns_dsaf_rcb.h" #include "hns_dsaf_misc.h" -const char *g_dsaf_mode_match[DSAF_MODE_MAX] = { +const static char *g_dsaf_mode_match[DSAF_MODE_MAX] = { [DSAF_MODE_DISABLE_2PORT_64VM] = "2port-64vf", [DSAF_MODE_DISABLE_6PORT_0VM] = "6port-16rss", [DSAF_MODE_DISABLE_6PORT_16VM] = "6port-16vf", @@ -42,7 +42,7 @@ static const struct acpi_device_id hns_dsaf_acpi_match[] = { }; MODULE_DEVICE_TABLE(acpi, hns_dsaf_acpi_match); -int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) +static int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) { int ret, i; u32 desc_num; @@ -959,7 +959,8 @@ static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address) spin_unlock_bh(&dsaf_dev->tcam_lock); } -void hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr) +static void +hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr) { addr[0] = mac_key->high.bits.mac_0; addr[1] = mac_key->high.bits.mac_1; @@ -1682,7 +1683,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, struct dsaf_tbl_tcam_mcast_cfg mac_data; struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev); struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; - struct dsaf_drv_tbl_tcam_key tmp_mac_key; struct dsaf_tbl_tcam_data tcam_data; u8 mc_addr[ETH_ALEN]; int mskid; @@ -1739,10 +1739,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, /* if exist, add in */ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data); - - tmp_mac_key.high.val = - le32_to_cpu(tcam_data.tbl_tcam_data_high); - tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); } /* config hardware entry */ @@ -1852,7 +1848,7 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, struct dsaf_tbl_tcam_data tcam_data; int mskid; const u8 empty_msk[sizeof(mac_data.tbl_mcast_port_msk)] = {0}; - struct dsaf_drv_tbl_tcam_key mask_key, tmp_mac_key; + struct dsaf_drv_tbl_tcam_key mask_key; struct dsaf_tbl_tcam_data *pmask_key = NULL; u8 mc_addr[ETH_ALEN]; @@ -1915,9 +1911,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, /* read entry */ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data); - tmp_mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high); - tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low); - /*del the port*/ if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) { mskid = mac_entry->port_num; @@ -2084,8 +2077,9 @@ static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int mac_id, * @dsaf_id: dsa fabric id * @xge_ge_work_mode */ -void hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id, - enum dsaf_port_rate_mode rate_mode) +static void +hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id, + enum dsaf_port_rate_mode rate_mode) { u32 port_work_mode; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index acf29633ec79..16294cd3c954 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -340,7 +340,8 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev, * bit18-19 for com/dfx * @enable: false - request reset , true - drop reset */ -void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) +static void +hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) { u32 reg_addr; @@ -362,7 +363,7 @@ void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) * bit18-19 for com/dfx * @enable: false - request reset , true - drop reset */ -void +static void hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) { hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC, @@ -370,7 +371,7 @@ hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) msk, dereset); } -void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset) +static void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset) { if (!dereset) { dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_RESET_REQ_REG, 1); @@ -384,7 +385,7 @@ void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset) } } -void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset) +static void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset) { hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC, HNS_ROCE_RESET_FUNC, 0, dereset); @@ -568,7 +569,7 @@ static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb) return phy_if; } -int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) +static int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) { u32 val = 0; int ret; @@ -586,7 +587,7 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) return 0; } -int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt) +static int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt) { union acpi_object *obj; union acpi_object obj_args, argv4; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index 93e71e27401b..d160d8c9e45b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -73,7 +73,7 @@ hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common) * comm_index: common index * retuen 0 - success , negative --fail */ -int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index) +static int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index) { struct ppe_common_cb *ppe_common; int ppe_num; @@ -104,7 +104,8 @@ int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index) return 0; } -void hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index) +static void +hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index) { dsaf_dev->ppe_common[comm_index] = NULL; } @@ -203,9 +204,9 @@ static int hns_ppe_common_init_hw(struct ppe_common_cb *ppe_common) enum dsaf_mode dsaf_mode = dsaf_dev->dsaf_mode; dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 0); - mdelay(100); + msleep(100); dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 1); - mdelay(100); + msleep(100); if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) { switch (dsaf_mode) { @@ -337,7 +338,7 @@ static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb) } } -void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common) +static void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common) { u32 i; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index e2e28532e4dc..9d76e2e54f9d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -705,7 +705,7 @@ void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, u16 *max_vfn, } } -int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev) +static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev) { switch (dsaf_dev->dsaf_mode) { case DSAF_MODE_ENABLE_FIX: @@ -741,7 +741,7 @@ int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev) } } -void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common) +static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common) { struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index 51e7e9f5af49..ba4316910dea 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -215,10 +215,10 @@ static void hns_xgmac_init(void *mac_drv) u32 port = drv->mac_id; dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 0); - mdelay(100); + msleep(100); dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 1); - mdelay(100); + msleep(100); hns_xgmac_lf_rf_control_init(drv); hns_xgmac_exc_irq_en(drv, 0); @@ -311,7 +311,7 @@ static void hns_xgmac_config_max_frame_length(void *mac_drv, u16 newval) dsaf_write_dev(drv, XGMAC_MAC_MAX_PKT_SIZE_REG, newval); } -void hns_xgmac_update_stats(void *mac_drv) +static void hns_xgmac_update_stats(void *mac_drv) { struct mac_driver *drv = (struct mac_driver *)mac_drv; struct mac_hw_stats *hw_stats = &drv->mac_cb->hw_stats; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 948b3e0d18f4..c2ac187ec8fc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1300,7 +1300,7 @@ static int hns_nic_net_set_mac_address(struct net_device *ndev, void *p) return 0; } -void hns_nic_update_stats(struct net_device *netdev) +static void hns_nic_update_stats(struct net_device *netdev) { struct hns_nic_priv *priv = netdev_priv(netdev); struct hnae_handle *h = priv->ae_handle; @@ -1582,7 +1582,7 @@ static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, /* use only for netconsole to poll with the device without interrupt */ #ifdef CONFIG_NET_POLL_CONTROLLER -void hns_nic_poll_controller(struct net_device *ndev) +static void hns_nic_poll_controller(struct net_device *ndev) { struct hns_nic_priv *priv = netdev_priv(ndev); unsigned long flags; @@ -1935,7 +1935,7 @@ static int hns_nic_uc_unsync(struct net_device *netdev, * * return void */ -void hns_set_multicast_list(struct net_device *ndev) +static void hns_set_multicast_list(struct net_device *ndev) { struct hns_nic_priv *priv = netdev_priv(ndev); struct hnae_handle *h = priv->ae_handle; @@ -1957,7 +1957,7 @@ void hns_set_multicast_list(struct net_device *ndev) } } -void hns_nic_set_rx_mode(struct net_device *ndev) +static void hns_nic_set_rx_mode(struct net_device *ndev) { struct hns_nic_priv *priv = netdev_priv(ndev); struct hnae_handle *h = priv->ae_handle; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 2e14a3ae1d8b..3957205abb81 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -658,8 +658,8 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, * @dev: net device * @param: ethtool parameter */ -void hns_get_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *param) +static void hns_get_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *param) { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; @@ -808,7 +808,8 @@ static int hns_set_coalesce(struct net_device *net_dev, * @dev: net device * @ch: channel info. */ -void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) +static void +hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) { struct hns_nic_priv *priv = netdev_priv(net_dev); @@ -825,8 +826,8 @@ void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) * @stats: statistics info. * @data: statistics data. */ -void hns_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) +static void hns_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) { u64 *p = data; struct hns_nic_priv *priv = netdev_priv(netdev); @@ -883,7 +884,7 @@ void hns_get_ethtool_stats(struct net_device *netdev, * @stats: string set ID. * @data: objects data. */ -void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct hns_nic_priv *priv = netdev_priv(netdev); struct hnae_handle *h = priv->ae_handle; @@ -973,7 +974,7 @@ void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) * * Return string set count. */ -int hns_get_sset_count(struct net_device *netdev, int stringset) +static int hns_get_sset_count(struct net_device *netdev, int stringset) { struct hns_nic_priv *priv = netdev_priv(netdev); struct hnae_handle *h = priv->ae_handle; @@ -1007,7 +1008,7 @@ int hns_get_sset_count(struct net_device *netdev, int stringset) * * Return 0 on success, negative on failure. */ -int hns_phy_led_set(struct net_device *netdev, int value) +static int hns_phy_led_set(struct net_device *netdev, int value) { int retval; struct phy_device *phy_dev = netdev->phydev; @@ -1029,7 +1030,8 @@ int hns_phy_led_set(struct net_device *netdev, int value) * * Return 0 on success, negative on failure. */ -int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) +static int +hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) { struct hns_nic_priv *priv = netdev_priv(netdev); struct hnae_handle *h = priv->ae_handle; @@ -1103,8 +1105,8 @@ int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) * @cmd: ethtool cmd * @date: register data */ -void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, - void *data) +static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, + void *data) { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 6c9e5d62455b..bd031af38a96 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -50,7 +50,8 @@ static const struct pci_device_id hns3_pci_tbl[] = { {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_VF), 0}, - {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF), + HNAE3_DEV_SUPPORT_ROCE_DCB_BITS}, /* required last entry */ {0, } }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 165c3d5e1c4c..ac13cb2b168e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -147,7 +147,12 @@ static int hclge_cmd_csq_clean(struct hclge_hw *hw) if (!is_valid_csq_clean_head(csq, head)) { dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head, csq->next_to_use, csq->next_to_clean); - return 0; + dev_warn(&hdev->pdev->dev, + "Disabling any further commands to IMP firmware\n"); + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); + dev_warn(&hdev->pdev->dev, + "IMP firmware watchdog reset soon expected!\n"); + return -EIO; } clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num; @@ -267,10 +272,11 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) /* Clean the command send queue */ handle = hclge_cmd_csq_clean(hw); - if (handle != num) { + if (handle < 0) + retval = handle; + else if (handle != num) dev_warn(&hdev->pdev->dev, "cleaned %d, need to clean %d\n", handle, num); - } spin_unlock_bh(&hw->cmq.csq.lock); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 5cd22f9bbdec..cd0a4f228470 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -358,6 +358,8 @@ struct hclge_pf_res_cmd { __le16 buf_size; __le16 msixcap_localid_ba_nic; __le16 msixcap_localid_ba_rocee; +#define HCLGE_MSIX_OFT_ROCEE_S 0 +#define HCLGE_MSIX_OFT_ROCEE_M GENMASK(15, 0) #define HCLGE_PF_VEC_NUM_S 0 #define HCLGE_PF_VEC_NUM_M GENMASK(7, 0) __le16 pf_intr_vector_number; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index a9b888f1544a..fc813b7f20e8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -932,6 +932,9 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S; if (hnae3_dev_roce_supported(hdev)) { + hdev->roce_base_msix_offset = + hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee), + HCLGE_MSIX_OFT_ROCEE_M, HCLGE_MSIX_OFT_ROCEE_S); hdev->num_roce_msi = hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); @@ -939,7 +942,8 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) /* PF should have NIC vectors and Roce vectors, * NIC vectors are queued before Roce vectors. */ - hdev->num_msi = hdev->num_roce_msi + HCLGE_ROCE_VECTOR_OFFSET; + hdev->num_msi = hdev->num_roce_msi + + hdev->roce_base_msix_offset; } else { hdev->num_msi = hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), @@ -2037,7 +2041,7 @@ static int hclge_init_msi(struct hclge_dev *hdev) hdev->num_msi_left = vectors; hdev->base_msi_vector = pdev->irq; hdev->roce_base_vector = hdev->base_msi_vector + - HCLGE_ROCE_VECTOR_OFFSET; + hdev->roce_base_msix_offset; hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi, sizeof(u16), GFP_KERNEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index dfa5c9456d22..1528fb3fa6be 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -16,8 +16,6 @@ #define HCLGE_INVALID_VPORT 0xffff -#define HCLGE_ROCE_VECTOR_OFFSET 96 - #define HCLGE_PF_CFG_BLOCK_SIZE 32 #define HCLGE_PF_CFG_DESC_NUM \ (HCLGE_PF_CFG_BLOCK_SIZE / HCLGE_CFG_RD_LEN_BYTES) @@ -509,6 +507,7 @@ struct hclge_dev { u16 num_msi; u16 num_msi_left; u16 num_msi_used; + u16 roce_base_msix_offset; u32 base_msi_vector; u16 *vector_status; int *vector_irq; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h index 621c6cbacf76..19b32860309c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h @@ -82,6 +82,7 @@ struct hclgevf_cmq { enum hclgevf_opcode_type { /* Generic command */ HCLGEVF_OPC_QUERY_FW_VER = 0x0001, + HCLGEVF_OPC_QUERY_VF_RSRC = 0x0024, /* TQP command */ HCLGEVF_OPC_QUERY_TX_STATUS = 0x0B03, HCLGEVF_OPC_QUERY_RX_STATUS = 0x0B13, @@ -134,6 +135,19 @@ struct hclgevf_query_version_cmd { __le32 firmware_rsv[5]; }; +#define HCLGEVF_MSIX_OFT_ROCEE_S 0 +#define HCLGEVF_MSIX_OFT_ROCEE_M (0xffff << HCLGEVF_MSIX_OFT_ROCEE_S) +#define HCLGEVF_VEC_NUM_S 0 +#define HCLGEVF_VEC_NUM_M (0xff << HCLGEVF_VEC_NUM_S) +struct hclgevf_query_res_cmd { + __le16 tqp_num; + __le16 reserved; + __le16 msixcap_localid_ba_nic; + __le16 msixcap_localid_ba_rocee; + __le16 vf_intr_vector_number; + __le16 rsv[7]; +}; + #define HCLGEVF_RSS_HASH_KEY_OFFSET 4 #define HCLGEVF_RSS_HASH_KEY_NUM 16 struct hclgevf_rss_config_cmd { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index d1f16f0c1646..9c0091f2addf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1370,14 +1370,13 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev) struct hnae3_handle *roce = &hdev->roce; struct hnae3_handle *nic = &hdev->nic; - roce->rinfo.num_vectors = HCLGEVF_ROCEE_VECTOR_NUM; + roce->rinfo.num_vectors = hdev->num_roce_msix; if (hdev->num_msi_left < roce->rinfo.num_vectors || hdev->num_msi_left == 0) return -EINVAL; - roce->rinfo.base_vector = - hdev->vector_status[hdev->num_msi_used]; + roce->rinfo.base_vector = hdev->roce_base_vector; roce->rinfo.netdev = nic->kinfo.netdev; roce->rinfo.roce_io_base = hdev->hw.io_base; @@ -1520,10 +1519,15 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev) if (hclgevf_dev_ongoing_reset(hdev)) return 0; - hdev->num_msi = HCLGEVF_MAX_VF_VECTOR_NUM; + if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) + vectors = pci_alloc_irq_vectors(pdev, + hdev->roce_base_msix_offset + 1, + hdev->num_msi, + PCI_IRQ_MSIX); + else + vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi, + PCI_IRQ_MSI | PCI_IRQ_MSIX); - vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi, - PCI_IRQ_MSI | PCI_IRQ_MSIX); if (vectors < 0) { dev_err(&pdev->dev, "failed(%d) to allocate MSI/MSI-X vectors\n", @@ -1538,6 +1542,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev) hdev->num_msi = vectors; hdev->num_msi_left = vectors; hdev->base_msi_vector = pdev->irq; + hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset; hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi, sizeof(u16), GFP_KERNEL); @@ -1733,6 +1738,45 @@ static void hclgevf_pci_uninit(struct hclgevf_dev *hdev) pci_disable_device(pdev); } +static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev) +{ + struct hclgevf_query_res_cmd *req; + struct hclgevf_desc desc; + int ret; + + hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_QUERY_VF_RSRC, true); + ret = hclgevf_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "query vf resource failed, ret = %d.\n", ret); + return ret; + } + + req = (struct hclgevf_query_res_cmd *)desc.data; + + if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) { + hdev->roce_base_msix_offset = + hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee), + HCLGEVF_MSIX_OFT_ROCEE_M, + HCLGEVF_MSIX_OFT_ROCEE_S); + hdev->num_roce_msix = + hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number), + HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S); + + /* VF should have NIC vectors and Roce vectors, NIC vectors + * are queued before Roce vectors. The offset is fixed to 64. + */ + hdev->num_msi = hdev->num_roce_msix + + hdev->roce_base_msix_offset; + } else { + hdev->num_msi = + hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number), + HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S); + } + + return 0; +} + static int hclgevf_init_hdev(struct hclgevf_dev *hdev) { struct pci_dev *pdev = hdev->pdev; @@ -1750,18 +1794,26 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) return ret; } + ret = hclgevf_cmd_init(hdev); + if (ret) + goto err_cmd_init; + + /* Get vf resource */ + ret = hclgevf_query_vf_resource(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query vf status error, ret = %d.\n", ret); + goto err_query_vf; + } + ret = hclgevf_init_msi(hdev); if (ret) { dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret); - goto err_irq_init; + goto err_query_vf; } hclgevf_state_init(hdev); - ret = hclgevf_cmd_init(hdev); - if (ret) - goto err_cmd_init; - ret = hclgevf_misc_irq_init(hdev); if (ret) { dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n", @@ -1817,11 +1869,11 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) err_config: hclgevf_misc_irq_uninit(hdev); err_misc_irq_init: - hclgevf_cmd_uninit(hdev); -err_cmd_init: hclgevf_state_uninit(hdev); hclgevf_uninit_msi(hdev); -err_irq_init: +err_query_vf: + hclgevf_cmd_uninit(hdev); +err_cmd_init: hclgevf_pci_uninit(hdev); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 0656e8e5c5f0..b23ba171473c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -12,7 +12,6 @@ #define HCLGEVF_MOD_VERSION "1.0" #define HCLGEVF_DRIVER_NAME "hclgevf" -#define HCLGEVF_ROCEE_VECTOR_NUM 0 #define HCLGEVF_MISC_VECTOR_NUM 0 #define HCLGEVF_INVALID_VPORT 0xffff @@ -150,6 +149,9 @@ struct hclgevf_dev { u16 num_msi; u16 num_msi_left; u16 num_msi_used; + u16 num_roce_msix; /* Num of roce vectors for this VF */ + u16 roce_base_msix_offset; + int roce_base_vector; u32 base_msi_vector; u16 *vector_status; int *vector_irq; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 5b122728dcb4..09e9da10b786 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -983,6 +983,7 @@ static int nic_dev_init(struct pci_dev *pdev) hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS, nic_dev, link_status_event_handler); + SET_NETDEV_DEV(netdev, &pdev->dev); err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 9128858479c4..2353ec829c04 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) txq->txq_stats.tx_busy++; u64_stats_update_end(&txq->txq_stats.syncp); err = NETDEV_TX_BUSY; + wqe_size = 0; goto flush_skbs; } diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index b13b42e5a1d9..a795c07d0df7 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -225,19 +225,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >> E1000_STATUS_FUNC_SHIFT; - /* Make sure the PHY is in a good state. Several people have reported - * firmware leaving the PHY's page select register set to something - * other than the default of zero, which causes the PHY ID read to - * access something other than the intended register. - */ - ret_val = hw->phy.ops.reset(hw); - if (ret_val) { - hw_dbg("Error resetting the PHY.\n"); - goto out; - } - /* Set phy->phy_addr and phy->id. */ - igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, 0); ret_val = igb_get_phy_id_82575(hw); if (ret_val) return ret_val; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index e3a0c02721c9..25720d95d4ea 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6031,7 +6031,7 @@ static int igb_tx_map(struct igb_ring *tx_ring, * We also need this memory barrier to make certain all of the * status bits have been updated before next_to_watch is written. */ - wmb(); + dma_wmb(); /* set next_to_watch value indicating a packet is present */ first->next_to_watch = tx_desc; @@ -8531,7 +8531,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) * applicable for weak-ordered memory model archs, * such as IA-64). */ - wmb(); + dma_wmb(); writel(i, rx_ring->tail); } } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 144d5fe6b944..4fc906c6166b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -855,7 +855,8 @@ void ixgbe_free_rx_resources(struct ixgbe_ring *); void ixgbe_free_tx_resources(struct ixgbe_ring *); void ixgbe_configure_rx_ring(struct ixgbe_adapter *, struct ixgbe_ring *); void ixgbe_configure_tx_ring(struct ixgbe_adapter *, struct ixgbe_ring *); -void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, struct ixgbe_ring *); +void ixgbe_disable_rx(struct ixgbe_adapter *adapter); +void ixgbe_disable_tx(struct ixgbe_adapter *adapter); void ixgbe_update_stats(struct ixgbe_adapter *adapter); int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter); bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index bd1ba88ec1d5..e5a8461fe6a9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -511,7 +511,7 @@ static void ixgbe_set_msglevel(struct net_device *netdev, u32 data) static int ixgbe_get_regs_len(struct net_device *netdev) { -#define IXGBE_REGS_LEN 1139 +#define IXGBE_REGS_LEN 1145 return IXGBE_REGS_LEN * sizeof(u32); } @@ -874,6 +874,14 @@ static void ixgbe_get_regs(struct net_device *netdev, /* X540 specific DCB registers */ regs_buff[1137] = IXGBE_READ_REG(hw, IXGBE_RTTQCNCR); regs_buff[1138] = IXGBE_READ_REG(hw, IXGBE_RTTQCNTG); + + /* Security config registers */ + regs_buff[1139] = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL); + regs_buff[1140] = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT); + regs_buff[1141] = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF); + regs_buff[1142] = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + regs_buff[1143] = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + regs_buff[1144] = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT); } static int ixgbe_get_eeprom_len(struct net_device *netdev) @@ -1690,35 +1698,17 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data) static void ixgbe_free_desc_rings(struct ixgbe_adapter *adapter) { - struct ixgbe_ring *tx_ring = &adapter->test_tx_ring; - struct ixgbe_ring *rx_ring = &adapter->test_rx_ring; - struct ixgbe_hw *hw = &adapter->hw; - u32 reg_ctl; - - /* shut down the DMA engines now so they can be reinitialized later */ + /* Shut down the DMA engines now so they can be reinitialized later, + * since the test rings and normally used rings should overlap on + * queue 0 we can just use the standard disable Rx/Tx calls and they + * will take care of disabling the test rings for us. + */ /* first Rx */ - hw->mac.ops.disable_rx(hw); - ixgbe_disable_rx_queue(adapter, rx_ring); + ixgbe_disable_rx(adapter); /* now Tx */ - reg_ctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx)); - reg_ctl &= ~IXGBE_TXDCTL_ENABLE; - IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx), reg_ctl); - - switch (hw->mac.type) { - case ixgbe_mac_82599EB: - case ixgbe_mac_X540: - case ixgbe_mac_X550: - case ixgbe_mac_X550EM_x: - case ixgbe_mac_x550em_a: - reg_ctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL); - reg_ctl &= ~IXGBE_DMATXCTL_TE; - IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, reg_ctl); - break; - default: - break; - } + ixgbe_disable_tx(adapter); ixgbe_reset(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 5a6600f7b382..447098005490 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4022,38 +4022,6 @@ static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter, } } -void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, - struct ixgbe_ring *ring) -{ - struct ixgbe_hw *hw = &adapter->hw; - int wait_loop = IXGBE_MAX_RX_DESC_POLL; - u32 rxdctl; - u8 reg_idx = ring->reg_idx; - - if (ixgbe_removed(hw->hw_addr)) - return; - rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); - rxdctl &= ~IXGBE_RXDCTL_ENABLE; - - /* write value back with RXDCTL.ENABLE bit cleared */ - IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); - - if (hw->mac.type == ixgbe_mac_82598EB && - !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) - return; - - /* the hardware may take up to 100us to really disable the rx queue */ - do { - udelay(10); - rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); - } while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE)); - - if (!wait_loop) { - e_err(drv, "RXDCTL.ENABLE on Rx queue %d not cleared within " - "the polling period\n", reg_idx); - } -} - void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, struct ixgbe_ring *ring) { @@ -4063,9 +4031,13 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; - /* disable queue to avoid issues while updating state */ + /* disable queue to avoid use of these values while updating state */ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); - ixgbe_disable_rx_queue(adapter, ring); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + IXGBE_WRITE_FLUSH(hw); IXGBE_WRITE_REG(hw, IXGBE_RDBAL(reg_idx), (rdba & DMA_BIT_MASK(32))); IXGBE_WRITE_REG(hw, IXGBE_RDBAH(reg_idx), (rdba >> 32)); @@ -5633,6 +5605,212 @@ void ixgbe_up(struct ixgbe_adapter *adapter) ixgbe_up_complete(adapter); } +static unsigned long ixgbe_get_completion_timeout(struct ixgbe_adapter *adapter) +{ + u16 devctl2; + + pcie_capability_read_word(adapter->pdev, PCI_EXP_DEVCTL2, &devctl2); + + switch (devctl2 & IXGBE_PCIDEVCTRL2_TIMEO_MASK) { + case IXGBE_PCIDEVCTRL2_17_34s: + case IXGBE_PCIDEVCTRL2_4_8s: + /* For now we cap the upper limit on delay to 2 seconds + * as we end up going up to 34 seconds of delay in worst + * case timeout value. + */ + case IXGBE_PCIDEVCTRL2_1_2s: + return 2000000ul; /* 2.0 s */ + case IXGBE_PCIDEVCTRL2_260_520ms: + return 520000ul; /* 520 ms */ + case IXGBE_PCIDEVCTRL2_65_130ms: + return 130000ul; /* 130 ms */ + case IXGBE_PCIDEVCTRL2_16_32ms: + return 32000ul; /* 32 ms */ + case IXGBE_PCIDEVCTRL2_1_2ms: + return 2000ul; /* 2 ms */ + case IXGBE_PCIDEVCTRL2_50_100us: + return 100ul; /* 100 us */ + case IXGBE_PCIDEVCTRL2_16_32ms_def: + return 32000ul; /* 32 ms */ + default: + break; + } + + /* We shouldn't need to hit this path, but just in case default as + * though completion timeout is not supported and support 32ms. + */ + return 32000ul; +} + +void ixgbe_disable_rx(struct ixgbe_adapter *adapter) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + int i, wait_loop; + u32 rxdctl; + + /* disable receives */ + hw->mac.ops.disable_rx(hw); + + if (ixgbe_removed(hw->hw_addr)) + return; + + /* disable all enabled Rx queues */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + u8 reg_idx = ring->reg_idx; + + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + rxdctl |= IXGBE_RXDCTL_SWFLSH; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + } + + /* RXDCTL.EN may not change on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* Determine our minimum delay interval. We will increase this value + * with each subsequent test. This way if the device returns quickly + * we should spend as little time as possible waiting, however as + * the time increases we will wait for larger periods of time. + * + * The trick here is that we increase the interval using the + * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result + * of that wait is that it totals up to 100x whatever interval we + * choose. Since our minimum wait is 100us we can just divide the + * total timeout by 100 to get our minimum delay interval. + */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + rxdctl = 0; + + /* OR together the reading of all the active RXDCTL registers, + * and then test the result. We need the disable to complete + * before we start freeing the memory and invalidating the + * DMA mappings. + */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + u8 reg_idx = ring->reg_idx; + + rxdctl |= IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + } + + if (!(rxdctl & IXGBE_RXDCTL_ENABLE)) + return; + } + + e_err(drv, + "RXDCTL.ENABLE for one or more queues not cleared within the polling period\n"); +} + +void ixgbe_disable_tx(struct ixgbe_adapter *adapter) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + int i, wait_loop; + u32 txdctl; + + if (ixgbe_removed(hw->hw_addr)) + return; + + /* disable all enabled Tx queues */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *ring = adapter->tx_ring[i]; + u8 reg_idx = ring->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } + + /* disable all enabled XDP Tx queues */ + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + u8 reg_idx = ring->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } + + /* If the link is not up there shouldn't be much in the way of + * pending transactions. Those that are left will be flushed out + * when the reset logic goes through the flush sequence to clean out + * the pending Tx transactions. + */ + if (!(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + goto dma_engine_disable; + + /* Determine our minimum delay interval. We will increase this value + * with each subsequent test. This way if the device returns quickly + * we should spend as little time as possible waiting, however as + * the time increases we will wait for larger periods of time. + * + * The trick here is that we increase the interval using the + * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result + * of that wait is that it totals up to 100x whatever interval we + * choose. Since our minimum wait is 100us we can just divide the + * total timeout by 100 to get our minimum delay interval. + */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + txdctl = 0; + + /* OR together the reading of all the active TXDCTL registers, + * and then test the result. We need the disable to complete + * before we start freeing the memory and invalidating the + * DMA mappings. + */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *ring = adapter->tx_ring[i]; + u8 reg_idx = ring->reg_idx; + + txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + u8 reg_idx = ring->reg_idx; + + txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + } + + if (!(txdctl & IXGBE_TXDCTL_ENABLE)) + goto dma_engine_disable; + } + + e_err(drv, + "TXDCTL.ENABLE for one or more queues not cleared within the polling period\n"); + +dma_engine_disable: + /* Disable the Tx DMA engine on 82599 and later MAC */ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, + (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & + ~IXGBE_DMATXCTL_TE)); + /* fall through */ + default: + break; + } +} + void ixgbe_reset(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -5814,24 +5992,19 @@ void ixgbe_down(struct ixgbe_adapter *adapter) if (test_and_set_bit(__IXGBE_DOWN, &adapter->state)) return; /* do nothing if already down */ - /* disable receives */ - hw->mac.ops.disable_rx(hw); + /* Shut off incoming Tx traffic */ + netif_tx_stop_all_queues(netdev); - /* disable all enabled rx queues */ - for (i = 0; i < adapter->num_rx_queues; i++) - /* this call also flushes the previous write */ - ixgbe_disable_rx_queue(adapter, adapter->rx_ring[i]); + /* call carrier off first to avoid false dev_watchdog timeouts */ + netif_carrier_off(netdev); + netif_tx_disable(netdev); - usleep_range(10000, 20000); + /* Disable Rx */ + ixgbe_disable_rx(adapter); /* synchronize_sched() needed for pending XDP buffers to drain */ if (adapter->xdp_ring[0]) synchronize_sched(); - netif_tx_stop_all_queues(netdev); - - /* call carrier off first to avoid false dev_watchdog timeouts */ - netif_carrier_off(netdev); - netif_tx_disable(netdev); ixgbe_irq_disable(adapter); @@ -5859,30 +6032,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter) } /* disable transmits in the hardware now that interrupts are off */ - for (i = 0; i < adapter->num_tx_queues; i++) { - u8 reg_idx = adapter->tx_ring[i]->reg_idx; - IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); - } - for (i = 0; i < adapter->num_xdp_queues; i++) { - u8 reg_idx = adapter->xdp_ring[i]->reg_idx; - - IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); - } - - /* Disable the Tx DMA engine on 82599 and later MAC */ - switch (hw->mac.type) { - case ixgbe_mac_82599EB: - case ixgbe_mac_X540: - case ixgbe_mac_X550: - case ixgbe_mac_X550EM_x: - case ixgbe_mac_x550em_a: - IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, - (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & - ~IXGBE_DMATXCTL_TE)); - break; - default: - break; - } + ixgbe_disable_tx(adapter); if (!pci_channel_offline(adapter->pdev)) ixgbe_reset(adapter); @@ -6469,6 +6619,11 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbe_adapter *adapter = netdev_priv(netdev); + if (adapter->xdp_prog) { + e_warn(probe, "MTU cannot be changed while XDP program is loaded\n"); + return -EPERM; + } + /* * For 82599EB we cannot allow legacy VFs to enable their receive * paths when MTU greater than 1500 is configured. So display a @@ -9407,6 +9562,11 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev, if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) features &= ~NETIF_F_LRO; + if (adapter->xdp_prog && (features & NETIF_F_LRO)) { + e_dev_err("LRO is not supported with XDP\n"); + features &= ~NETIF_F_LRO; + } + return features; } diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 06ff185eb188..a5ab6f3403ae 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -1911,10 +1911,10 @@ jme_wait_link(struct jme_adapter *jme) { u32 phylink, to = JME_WAIT_LINK_TIME; - mdelay(1000); + msleep(1000); phylink = jme_linkstat_from_phy(jme); while (!(phylink & PHY_LINK_UP) && (to -= 10) > 0) { - mdelay(10); + usleep_range(10000, 11000); phylink = jme_linkstat_from_phy(jme); } } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 0ad2f3f7da85..55c2a56c5dae 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -295,10 +295,10 @@ #define MVNETA_RSS_LU_TABLE_SIZE 1 /* Max number of Rx descriptors */ -#define MVNETA_MAX_RXD 128 +#define MVNETA_MAX_RXD 512 /* Max number of Tx descriptors */ -#define MVNETA_MAX_TXD 532 +#define MVNETA_MAX_TXD 1024 /* Max number of allowed TCP segments for software TSO */ #define MVNETA_MAX_TSO_SEGS 100 @@ -328,6 +328,8 @@ enum { ETHTOOL_STAT_EEE_WAKEUP, + ETHTOOL_STAT_SKB_ALLOC_ERR, + ETHTOOL_STAT_REFILL_ERR, ETHTOOL_MAX_STATS, }; @@ -375,6 +377,8 @@ static const struct mvneta_statistic mvneta_statistics[] = { { 0x3054, T_REG_32, "fc_sent", }, { 0x300c, T_REG_32, "internal_mac_transmit_err", }, { ETHTOOL_STAT_EEE_WAKEUP, T_SW, "eee_wakeup_errors", }, + { ETHTOOL_STAT_SKB_ALLOC_ERR, T_SW, "skb_alloc_errors", }, + { ETHTOOL_STAT_REFILL_ERR, T_SW, "refill_errors", }, }; struct mvneta_pcpu_stats { @@ -479,7 +483,10 @@ struct mvneta_port { #define MVNETA_RXD_ERR_RESOURCE (BIT(17) | BIT(18)) #define MVNETA_RXD_ERR_CODE_MASK (BIT(17) | BIT(18)) #define MVNETA_RXD_L3_IP4 BIT(25) -#define MVNETA_RXD_FIRST_LAST_DESC (BIT(26) | BIT(27)) +#define MVNETA_RXD_LAST_DESC BIT(26) +#define MVNETA_RXD_FIRST_DESC BIT(27) +#define MVNETA_RXD_FIRST_LAST_DESC (MVNETA_RXD_FIRST_DESC | \ + MVNETA_RXD_LAST_DESC) #define MVNETA_RXD_L4_CSUM_OK BIT(30) #if defined(__LITTLE_ENDIAN) @@ -589,9 +596,6 @@ struct mvneta_rx_queue { /* num of rx descriptors in the rx descriptor ring */ int size; - /* counter of times when mvneta_refill() failed */ - int missed; - u32 pkts_coal; u32 time_coal; @@ -609,6 +613,18 @@ struct mvneta_rx_queue { /* Index of the next RX DMA descriptor to process */ int next_desc_to_proc; + + /* Index of first RX DMA descriptor to refill */ + int first_to_refill; + u32 refill_num; + + /* pointer to uncomplete skb buffer */ + struct sk_buff *skb; + int left_size; + + /* error counters */ + u32 skb_alloc_err; + u32 refill_err; }; static enum cpuhp_state online_hpstate; @@ -621,6 +637,7 @@ static int txq_number = 8; static int rxq_def; static int rx_copybreak __read_mostly = 256; +static int rx_header_size __read_mostly = 128; /* HW BM need that each port be identify by a unique ID */ static int global_port_id; @@ -1684,13 +1701,6 @@ static void mvneta_rx_error(struct mvneta_port *pp, { u32 status = rx_desc->status; - if (!mvneta_rxq_desc_is_first_last(status)) { - netdev_err(pp->dev, - "bad rx status %08x (buffer oversize), size=%d\n", - status, rx_desc->data_size); - return; - } - switch (status & MVNETA_RXD_ERR_CODE_MASK) { case MVNETA_RXD_ERR_CRC: netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n", @@ -1715,7 +1725,8 @@ static void mvneta_rx_error(struct mvneta_port *pp, static void mvneta_rx_csum(struct mvneta_port *pp, u32 status, struct sk_buff *skb) { - if ((status & MVNETA_RXD_L3_IP4) && + if ((pp->dev->features & NETIF_F_RXCSUM) && + (status & MVNETA_RXD_L3_IP4) && (status & MVNETA_RXD_L4_CSUM_OK)) { skb->csum = 0; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1790,47 +1801,30 @@ static void mvneta_txq_done(struct mvneta_port *pp, } } -void *mvneta_frag_alloc(unsigned int frag_size) -{ - if (likely(frag_size <= PAGE_SIZE)) - return netdev_alloc_frag(frag_size); - else - return kmalloc(frag_size, GFP_ATOMIC); -} -EXPORT_SYMBOL_GPL(mvneta_frag_alloc); - -void mvneta_frag_free(unsigned int frag_size, void *data) -{ - if (likely(frag_size <= PAGE_SIZE)) - skb_free_frag(data); - else - kfree(data); -} -EXPORT_SYMBOL_GPL(mvneta_frag_free); - /* Refill processing for SW buffer management */ +/* Allocate page per descriptor */ static int mvneta_rx_refill(struct mvneta_port *pp, struct mvneta_rx_desc *rx_desc, - struct mvneta_rx_queue *rxq) - + struct mvneta_rx_queue *rxq, + gfp_t gfp_mask) { dma_addr_t phys_addr; - void *data; + struct page *page; - data = mvneta_frag_alloc(pp->frag_size); - if (!data) + page = __dev_alloc_page(gfp_mask); + if (!page) return -ENOMEM; - phys_addr = dma_map_single(pp->dev->dev.parent, data, - MVNETA_RX_BUF_SIZE(pp->pkt_size), - DMA_FROM_DEVICE); + /* map page for use */ + phys_addr = dma_map_page(pp->dev->dev.parent, page, 0, PAGE_SIZE, + DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pp->dev->dev.parent, phys_addr))) { - mvneta_frag_free(pp->frag_size, data); + __free_page(page); return -ENOMEM; } phys_addr += pp->rx_offset_correction; - mvneta_rx_desc_fill(rx_desc, phys_addr, data, rxq); + mvneta_rx_desc_fill(rx_desc, phys_addr, page, rxq); return 0; } @@ -1893,115 +1887,192 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, for (i = 0; i < rxq->size; i++) { struct mvneta_rx_desc *rx_desc = rxq->descs + i; void *data = rxq->buf_virt_addr[i]; + if (!data || !(rx_desc->buf_phys_addr)) + continue; dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr, MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE); - mvneta_frag_free(pp->frag_size, data); + __free_page(data); } } +static inline +int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq) +{ + struct mvneta_rx_desc *rx_desc; + int curr_desc = rxq->first_to_refill; + int i; + + for (i = 0; (i < rxq->refill_num) && (i < 64); i++) { + rx_desc = rxq->descs + curr_desc; + if (!(rx_desc->buf_phys_addr)) { + if (mvneta_rx_refill(pp, rx_desc, rxq, GFP_ATOMIC)) { + pr_err("Can't refill queue %d. Done %d from %d\n", + rxq->id, i, rxq->refill_num); + rxq->refill_err++; + break; + } + } + curr_desc = MVNETA_QUEUE_NEXT_DESC(rxq, curr_desc); + } + rxq->refill_num -= i; + rxq->first_to_refill = curr_desc; + + return i; +} + /* Main rx processing when using software buffer management */ -static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo, +static int mvneta_rx_swbm(struct napi_struct *napi, + struct mvneta_port *pp, int budget, struct mvneta_rx_queue *rxq) { - struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports); struct net_device *dev = pp->dev; - int rx_done; + int rx_todo, rx_proc; + int refill = 0; u32 rcvd_pkts = 0; u32 rcvd_bytes = 0; /* Get number of received packets */ - rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq); - - if (rx_todo > rx_done) - rx_todo = rx_done; - - rx_done = 0; + rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq); + rx_proc = 0; /* Fairness NAPI loop */ - while (rx_done < rx_todo) { + while ((rcvd_pkts < budget) && (rx_proc < rx_todo)) { struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq); - struct sk_buff *skb; unsigned char *data; + struct page *page; dma_addr_t phys_addr; - u32 rx_status, frag_size; - int rx_bytes, err, index; + u32 rx_status, index; + int rx_bytes, skb_size, copy_size; + int frag_num, frag_size, frag_offset; - rx_done++; - rx_status = rx_desc->status; - rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); index = rx_desc - rxq->descs; - data = rxq->buf_virt_addr[index]; - phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction; - - if (!mvneta_rxq_desc_is_first_last(rx_status) || - (rx_status & MVNETA_RXD_ERR_SUMMARY)) { - mvneta_rx_error(pp, rx_desc); -err_drop_frame: - dev->stats.rx_errors++; - /* leave the descriptor untouched */ - continue; - } - - if (rx_bytes <= rx_copybreak) { - /* better copy a small frame and not unmap the DMA region */ - skb = netdev_alloc_skb_ip_align(dev, rx_bytes); - if (unlikely(!skb)) - goto err_drop_frame; - - dma_sync_single_range_for_cpu(dev->dev.parent, - phys_addr, - MVNETA_MH_SIZE + NET_SKB_PAD, - rx_bytes, - DMA_FROM_DEVICE); - skb_put_data(skb, data + MVNETA_MH_SIZE + NET_SKB_PAD, - rx_bytes); + page = (struct page *)rxq->buf_virt_addr[index]; + data = page_address(page); + /* Prefetch header */ + prefetch(data); - skb->protocol = eth_type_trans(skb, dev); - mvneta_rx_csum(pp, rx_status, skb); - napi_gro_receive(&port->napi, skb); - - rcvd_pkts++; - rcvd_bytes += rx_bytes; + phys_addr = rx_desc->buf_phys_addr; + rx_status = rx_desc->status; + rx_proc++; + rxq->refill_num++; + + if (rx_status & MVNETA_RXD_FIRST_DESC) { + /* Check errors only for FIRST descriptor */ + if (rx_status & MVNETA_RXD_ERR_SUMMARY) { + mvneta_rx_error(pp, rx_desc); + dev->stats.rx_errors++; + /* leave the descriptor untouched */ + continue; + } + rx_bytes = rx_desc->data_size - + (ETH_FCS_LEN + MVNETA_MH_SIZE); + + /* Allocate small skb for each new packet */ + skb_size = max(rx_copybreak, rx_header_size); + rxq->skb = netdev_alloc_skb_ip_align(dev, skb_size); + if (unlikely(!rxq->skb)) { + netdev_err(dev, + "Can't allocate skb on queue %d\n", + rxq->id); + dev->stats.rx_dropped++; + rxq->skb_alloc_err++; + continue; + } + copy_size = min(skb_size, rx_bytes); + + /* Copy data from buffer to SKB, skip Marvell header */ + memcpy(rxq->skb->data, data + MVNETA_MH_SIZE, + copy_size); + skb_put(rxq->skb, copy_size); + rxq->left_size = rx_bytes - copy_size; + + mvneta_rx_csum(pp, rx_status, rxq->skb); + if (rxq->left_size == 0) { + int size = copy_size + MVNETA_MH_SIZE; + + dma_sync_single_range_for_cpu(dev->dev.parent, + phys_addr, 0, + size, + DMA_FROM_DEVICE); + + /* leave the descriptor and buffer untouched */ + } else { + /* refill descriptor with new buffer later */ + rx_desc->buf_phys_addr = 0; + + frag_num = 0; + frag_offset = copy_size + MVNETA_MH_SIZE; + frag_size = min(rxq->left_size, + (int)(PAGE_SIZE - frag_offset)); + skb_add_rx_frag(rxq->skb, frag_num, page, + frag_offset, frag_size, + PAGE_SIZE); + dma_unmap_single(dev->dev.parent, phys_addr, + PAGE_SIZE, DMA_FROM_DEVICE); + rxq->left_size -= frag_size; + } + } else { + /* Middle or Last descriptor */ + if (unlikely(!rxq->skb)) { + pr_debug("no skb for rx_status 0x%x\n", + rx_status); + continue; + } + if (!rxq->left_size) { + /* last descriptor has only FCS */ + /* and can be discarded */ + dma_sync_single_range_for_cpu(dev->dev.parent, + phys_addr, 0, + ETH_FCS_LEN, + DMA_FROM_DEVICE); + /* leave the descriptor and buffer untouched */ + } else { + /* refill descriptor with new buffer later */ + rx_desc->buf_phys_addr = 0; + + frag_num = skb_shinfo(rxq->skb)->nr_frags; + frag_offset = 0; + frag_size = min(rxq->left_size, + (int)(PAGE_SIZE - frag_offset)); + skb_add_rx_frag(rxq->skb, frag_num, page, + frag_offset, frag_size, + PAGE_SIZE); + + dma_unmap_single(dev->dev.parent, phys_addr, + PAGE_SIZE, + DMA_FROM_DEVICE); + + rxq->left_size -= frag_size; + } + } /* Middle or Last descriptor */ - /* leave the descriptor and buffer untouched */ + if (!(rx_status & MVNETA_RXD_LAST_DESC)) + /* no last descriptor this time */ continue; - } - /* Refill processing */ - err = mvneta_rx_refill(pp, rx_desc, rxq); - if (err) { - netdev_err(dev, "Linux processing - Can't refill\n"); - rxq->missed++; - goto err_drop_frame; + if (rxq->left_size) { + pr_err("get last desc, but left_size (%d) != 0\n", + rxq->left_size); + dev_kfree_skb_any(rxq->skb); + rxq->left_size = 0; + rxq->skb = NULL; + continue; } - - frag_size = pp->frag_size; - - skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size); - - /* After refill old buffer has to be unmapped regardless - * the skb is successfully built or not. - */ - dma_unmap_single(dev->dev.parent, phys_addr, - MVNETA_RX_BUF_SIZE(pp->pkt_size), - DMA_FROM_DEVICE); - - if (!skb) - goto err_drop_frame; - rcvd_pkts++; - rcvd_bytes += rx_bytes; + rcvd_bytes += rxq->skb->len; /* Linux processing */ - skb_reserve(skb, MVNETA_MH_SIZE + NET_SKB_PAD); - skb_put(skb, rx_bytes); - - skb->protocol = eth_type_trans(skb, dev); + rxq->skb->protocol = eth_type_trans(rxq->skb, dev); - mvneta_rx_csum(pp, rx_status, skb); + if (dev->features & NETIF_F_GRO) + napi_gro_receive(napi, rxq->skb); + else + netif_receive_skb(rxq->skb); - napi_gro_receive(&port->napi, skb); + /* clean uncomplete skb pointer in queue */ + rxq->skb = NULL; + rxq->left_size = 0; } if (rcvd_pkts) { @@ -2013,17 +2084,20 @@ err_drop_frame: u64_stats_update_end(&stats->syncp); } + /* return some buffers to hardware queue, one at a time is too slow */ + refill = mvneta_rx_refill_queue(pp, rxq); + /* Update rxq management counters */ - mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done); + mvneta_rxq_desc_num_update(pp, rxq, rx_proc, refill); - return rx_done; + return rcvd_pkts; } /* Main rx processing when using hardware buffer management */ -static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo, +static int mvneta_rx_hwbm(struct napi_struct *napi, + struct mvneta_port *pp, int rx_todo, struct mvneta_rx_queue *rxq) { - struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports); struct net_device *dev = pp->dev; int rx_done; u32 rcvd_pkts = 0; @@ -2085,7 +2159,7 @@ err_drop_frame: skb->protocol = eth_type_trans(skb, dev); mvneta_rx_csum(pp, rx_status, skb); - napi_gro_receive(&port->napi, skb); + napi_gro_receive(napi, skb); rcvd_pkts++; rcvd_bytes += rx_bytes; @@ -2102,7 +2176,7 @@ err_drop_frame: err = hwbm_pool_refill(&bm_pool->hwbm_pool, GFP_ATOMIC); if (err) { netdev_err(dev, "Linux processing - Can't refill\n"); - rxq->missed++; + rxq->refill_err++; goto err_drop_frame_ret_pool; } @@ -2129,7 +2203,7 @@ err_drop_frame: mvneta_rx_csum(pp, rx_status, skb); - napi_gro_receive(&port->napi, skb); + napi_gro_receive(napi, skb); } if (rcvd_pkts) { @@ -2722,9 +2796,11 @@ static int mvneta_poll(struct napi_struct *napi, int budget) if (rx_queue) { rx_queue = rx_queue - 1; if (pp->bm_priv) - rx_done = mvneta_rx_hwbm(pp, budget, &pp->rxqs[rx_queue]); + rx_done = mvneta_rx_hwbm(napi, pp, budget, + &pp->rxqs[rx_queue]); else - rx_done = mvneta_rx_swbm(pp, budget, &pp->rxqs[rx_queue]); + rx_done = mvneta_rx_swbm(napi, pp, budget, + &pp->rxqs[rx_queue]); } if (rx_done < budget) { @@ -2761,9 +2837,11 @@ static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, for (i = 0; i < num; i++) { memset(rxq->descs + i, 0, sizeof(struct mvneta_rx_desc)); - if (mvneta_rx_refill(pp, rxq->descs + i, rxq) != 0) { - netdev_err(pp->dev, "%s:rxq %d, %d of %d buffs filled\n", - __func__, rxq->id, i, num); + if (mvneta_rx_refill(pp, rxq->descs + i, rxq, + GFP_KERNEL) != 0) { + netdev_err(pp->dev, + "%s:rxq %d, %d of %d buffs filled\n", + __func__, rxq->id, i, num); break; } } @@ -2821,21 +2899,23 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp, mvreg_write(pp, MVNETA_RXQ_BASE_ADDR_REG(rxq->id), rxq->descs_phys); mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size); - /* Set Offset */ - mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD - pp->rx_offset_correction); - /* Set coalescing pkts and time */ mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal); mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal); if (!pp->bm_priv) { - /* Fill RXQ with buffers from RX pool */ - mvneta_rxq_buf_size_set(pp, rxq, - MVNETA_RX_BUF_SIZE(pp->pkt_size)); + /* Set Offset */ + mvneta_rxq_offset_set(pp, rxq, 0); + mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size); mvneta_rxq_bm_disable(pp, rxq); mvneta_rxq_fill(pp, rxq, rxq->size); } else { + /* Set Offset */ + mvneta_rxq_offset_set(pp, rxq, + NET_SKB_PAD - pp->rx_offset_correction); + mvneta_rxq_bm_enable(pp, rxq); + /* Fill RXQ with buffers from RX pool */ mvneta_rxq_long_pool_set(pp, rxq); mvneta_rxq_short_pool_set(pp, rxq); mvneta_rxq_non_occup_desc_add(pp, rxq, rxq->size); @@ -2864,6 +2944,9 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp, { mvneta_rxq_drop_pkts(pp, rxq); + if (rxq->skb) + dev_kfree_skb_any(rxq->skb); + if (rxq->descs) dma_free_coherent(pp->dev->dev.parent, rxq->size * MVNETA_DESC_ALIGNED_SIZE, @@ -2874,6 +2957,10 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp, rxq->last_desc = 0; rxq->next_desc_to_proc = 0; rxq->descs_phys = 0; + rxq->first_to_refill = 0; + rxq->refill_num = 0; + rxq->skb = NULL; + rxq->left_size = 0; } static int mvneta_txq_sw_init(struct mvneta_port *pp, @@ -3177,8 +3264,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) mvneta_bm_update_mtu(pp, mtu); pp->pkt_size = MVNETA_RX_PKT_SIZE(dev->mtu); - pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); ret = mvneta_setup_rxqs(pp); if (ret) { @@ -3194,7 +3279,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) on_each_cpu(mvneta_percpu_enable, pp, true); mvneta_start_dev(pp); - mvneta_port_up(pp); netdev_update_features(dev); @@ -3666,8 +3750,7 @@ static int mvneta_open(struct net_device *dev) int ret; pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); - pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + pp->frag_size = PAGE_SIZE; ret = mvneta_setup_rxqs(pp); if (ret) @@ -3962,6 +4045,12 @@ static void mvneta_ethtool_update_stats(struct mvneta_port *pp) case ETHTOOL_STAT_EEE_WAKEUP: val = phylink_get_eee_err(pp->phylink); break; + case ETHTOOL_STAT_SKB_ALLOC_ERR: + val = pp->rxqs[0].skb_alloc_err; + break; + case ETHTOOL_STAT_REFILL_ERR: + val = pp->rxqs[0].refill_err; + break; } break; } @@ -4362,14 +4451,6 @@ static int mvneta_probe(struct platform_device *pdev) pp->dn = dn; pp->rxq_def = rxq_def; - - /* Set RX packet offset correction for platforms, whose - * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit - * platforms and 0B for 32-bit ones. - */ - pp->rx_offset_correction = - max(0, NET_SKB_PAD - MVNETA_RX_PKT_OFFSET_CORRECTION); - pp->indir[0] = rxq_def; /* Get special SoC configurations */ @@ -4457,16 +4538,28 @@ static int mvneta_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); pp->id = global_port_id++; + pp->rx_offset_correction = 0; /* not relevant for SW BM */ /* Obtain access to BM resources if enabled and already initialized */ bm_node = of_parse_phandle(dn, "buffer-manager", 0); - if (bm_node && bm_node->data) { - pp->bm_priv = bm_node->data; - err = mvneta_bm_port_init(pdev, pp); - if (err < 0) { - dev_info(&pdev->dev, "use SW buffer management\n"); - pp->bm_priv = NULL; + if (bm_node) { + pp->bm_priv = mvneta_bm_get(bm_node); + if (pp->bm_priv) { + err = mvneta_bm_port_init(pdev, pp); + if (err < 0) { + dev_info(&pdev->dev, + "use SW buffer management\n"); + mvneta_bm_put(pp->bm_priv); + pp->bm_priv = NULL; + } } + /* Set RX packet offset correction for platforms, whose + * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit + * platforms and 0B for 32-bit ones. + */ + pp->rx_offset_correction = max(0, + NET_SKB_PAD - + MVNETA_RX_PKT_OFFSET_CORRECTION); } of_node_put(bm_node); @@ -4526,6 +4619,7 @@ err_netdev: mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id); mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id); + mvneta_bm_put(pp->bm_priv); } err_free_stats: free_percpu(pp->stats); @@ -4563,6 +4657,7 @@ static int mvneta_remove(struct platform_device *pdev) mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id); mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id); + mvneta_bm_put(pp->bm_priv); } return 0; diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c index 466939f8f0cf..de468e1bdba9 100644 --- a/drivers/net/ethernet/marvell/mvneta_bm.c +++ b/drivers/net/ethernet/marvell/mvneta_bm.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/skbuff.h> #include <net/hwbm.h> @@ -392,6 +393,20 @@ static void mvneta_bm_put_sram(struct mvneta_bm *priv) MVNETA_BM_BPPI_SIZE); } +struct mvneta_bm *mvneta_bm_get(struct device_node *node) +{ + struct platform_device *pdev = of_find_device_by_node(node); + + return pdev ? platform_get_drvdata(pdev) : NULL; +} +EXPORT_SYMBOL_GPL(mvneta_bm_get); + +void mvneta_bm_put(struct mvneta_bm *priv) +{ + platform_device_put(priv->pdev); +} +EXPORT_SYMBOL_GPL(mvneta_bm_put); + static int mvneta_bm_probe(struct platform_device *pdev) { struct device_node *dn = pdev->dev.of_node; diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h index a32de432800c..c8425d35c049 100644 --- a/drivers/net/ethernet/marvell/mvneta_bm.h +++ b/drivers/net/ethernet/marvell/mvneta_bm.h @@ -130,10 +130,10 @@ struct mvneta_bm_pool { }; /* Declarations and definitions */ -void *mvneta_frag_alloc(unsigned int frag_size); -void mvneta_frag_free(unsigned int frag_size, void *data); - #if IS_ENABLED(CONFIG_MVNETA_BM) +struct mvneta_bm *mvneta_bm_get(struct device_node *node); +void mvneta_bm_put(struct mvneta_bm *priv); + void mvneta_bm_pool_destroy(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool, u8 port_map); void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool, @@ -178,5 +178,7 @@ static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv, static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool) { return 0; } +struct mvneta_bm *mvneta_bm_get(struct device_node *node) { return NULL; } +void mvneta_bm_put(struct mvneta_bm *priv) {} #endif /* CONFIG_MVNETA_BM */ #endif diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index c30aea2ab767..6e6abdc399de 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -605,10 +605,10 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) dma_addr_t dma_addr; int i; - eth->scratch_ring = dma_alloc_coherent(eth->dev, - cnt * sizeof(struct mtk_tx_dma), - ð->phy_scratch_ring, - GFP_ATOMIC | __GFP_ZERO); + eth->scratch_ring = dma_zalloc_coherent(eth->dev, + cnt * sizeof(struct mtk_tx_dma), + ð->phy_scratch_ring, + GFP_ATOMIC); if (unlikely(!eth->scratch_ring)) return -ENOMEM; @@ -623,7 +623,6 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) if (unlikely(dma_mapping_error(eth->dev, dma_addr))) return -ENOMEM; - memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt); phy_ring_tail = eth->phy_scratch_ring + (sizeof(struct mtk_tx_dma) * (cnt - 1)); @@ -1318,10 +1317,9 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) return -ENOMEM; } - ring->dma = dma_alloc_coherent(eth->dev, - rx_dma_size * sizeof(*ring->dma), - &ring->phys, - GFP_ATOMIC | __GFP_ZERO); + ring->dma = dma_zalloc_coherent(eth->dev, + rx_dma_size * sizeof(*ring->dma), + &ring->phys, GFP_ATOMIC); if (!ring->dma) return -ENOMEM; @@ -2460,42 +2458,6 @@ free_netdev: return err; } -static int mtk_get_chip_id(struct mtk_eth *eth, u32 *chip_id) -{ - u32 val[2], id[4]; - - regmap_read(eth->ethsys, ETHSYS_CHIPID0_3, &val[0]); - regmap_read(eth->ethsys, ETHSYS_CHIPID4_7, &val[1]); - - id[3] = ((val[0] >> 16) & 0xff) - '0'; - id[2] = ((val[0] >> 24) & 0xff) - '0'; - id[1] = (val[1] & 0xff) - '0'; - id[0] = ((val[1] >> 8) & 0xff) - '0'; - - *chip_id = (id[3] * 1000) + (id[2] * 100) + - (id[1] * 10) + id[0]; - - if (!(*chip_id)) { - dev_err(eth->dev, "failed to get chip id\n"); - return -ENODEV; - } - - dev_info(eth->dev, "chip id = %d\n", *chip_id); - - return 0; -} - -static bool mtk_is_hwlro_supported(struct mtk_eth *eth) -{ - switch (eth->chip_id) { - case MT7622_ETH: - case MT7623_ETH: - return true; - } - - return false; -} - static int mtk_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -2574,11 +2536,7 @@ static int mtk_probe(struct platform_device *pdev) if (err) return err; - err = mtk_get_chip_id(eth, ð->chip_id); - if (err) - return err; - - eth->hwlro = mtk_is_hwlro_supported(eth); + eth->hwlro = MTK_HAS_CAPS(eth->soc->caps, MTK_HWLRO); for_each_child_of_node(pdev->dev.of_node, mac_np) { if (!of_device_is_compatible(mac_np, @@ -2667,19 +2625,19 @@ static int mtk_remove(struct platform_device *pdev) } static const struct mtk_soc_data mt2701_data = { - .caps = MTK_GMAC1_TRGMII, + .caps = MTK_GMAC1_TRGMII | MTK_HWLRO, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, }; static const struct mtk_soc_data mt7622_data = { - .caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW, + .caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW | MTK_HWLRO, .required_clks = MT7622_CLKS_BITMAP, .required_pctl = false, }; static const struct mtk_soc_data mt7623_data = { - .caps = MTK_GMAC1_TRGMII, + .caps = MTK_GMAC1_TRGMII | MTK_HWLRO, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, }; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 672b8c353c47..46819297fc3e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -566,6 +566,7 @@ struct mtk_rx_ring { #define MTK_GMAC2_SGMII (BIT(10) | MTK_SGMII) #define MTK_DUAL_GMAC_SHARED_SGMII (BIT(11) | MTK_GMAC1_SGMII | \ MTK_GMAC2_SGMII) +#define MTK_HWLRO BIT(12) #define MTK_HAS_CAPS(caps, _x) (((caps) & (_x)) == (_x)) /* struct mtk_eth_data - This is the structure holding all differences @@ -635,7 +636,6 @@ struct mtk_eth { struct regmap *ethsys; struct regmap *sgmiisys; struct regmap *pctl; - u32 chip_id; bool hwlro; refcount_t dma_refcnt; struct mtk_tx_ring tx_ring; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2d979a652b7b..d2d59444f562 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -159,9 +159,10 @@ static bool use_prio; module_param_named(use_prio, use_prio, bool, 0444); MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)"); -int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG); +int log_mtts_per_seg = ilog2(1); module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444); -MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)"); +MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment " + "(0-7) (default: 0)"); static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE}; static int arr_argc = 2; @@ -4410,7 +4411,7 @@ static int __init mlx4_verify_params(void) if (use_prio != 0) pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n"); - if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) { + if ((log_mtts_per_seg < 0) || (log_mtts_per_seg > 7)) { pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n", log_mtts_per_seg); return -1; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 6e016092a6f1..ebcd2778eeb3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -84,7 +84,6 @@ enum { MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7, MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12, MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2), - MLX4_MTT_ENTRY_PER_SEG = 8, }; enum { diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c index bae8b22edbb7..ba361c5fbda3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/profile.c +++ b/drivers/net/ethernet/mellanox/mlx4/profile.c @@ -105,7 +105,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev, request->num_mtt = roundup_pow_of_two(max_t(unsigned, request->num_mtt, min(1UL << (31 - log_mtts_per_seg), - si.totalram >> (log_mtts_per_seg - 1)))); + (si.totalram << 1) >> log_mtts_per_seg))); + profile[MLX4_RES_QP].size = dev_cap->qpc_entry_sz; profile[MLX4_RES_RDMARC].size = dev_cap->rdmarc_entry_sz; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 7b1b5ac986d0..31bd56727022 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, u32 srqn = qp_get_srqn(qpc) & 0xffffff; int use_srq = (qp_get_srqn(qpc) >> 24) & 1; struct res_srq *srq; - int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; + int local_qpn = vhcr->in_modifier & 0xffffff; err = adjust_qp_sched_queue(dev, slave, qpc, inbox); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index fa7fcca5dc78..f20fda1ced4f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o fpga/tls.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ - en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \ - en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o + en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ + en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o lib/vxlan.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 323ffe8bf7e4..456f30007ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, int i; buf->size = size; - buf->npages = 1 << get_order(size); + buf->npages = DIV_ROUND_UP(size, PAGE_SIZE); buf->page_shift = PAGE_SHIFT; buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index e1b237ccdf56..c7ed3d20fd54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -147,10 +147,6 @@ struct page_pool; (DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB)) #define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS -#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) -#define MLX5E_XDP_TX_DS_COUNT \ - ((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */) - #define MLX5E_NUM_MAIN_GROUPS 9 #define MLX5E_MSG_LEVEL NETIF_MSG_LINK @@ -348,6 +344,7 @@ enum { MLX5E_SQ_STATE_IPSEC, MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, + MLX5E_SQ_STATE_REDIRECT, }; struct mlx5e_sq_wqe_info { @@ -368,16 +365,14 @@ struct mlx5e_txqsq { struct mlx5e_cq cq; - /* write@xmit, read@completion */ - struct { - struct mlx5e_sq_dma *dma_fifo; - struct mlx5e_tx_wqe_info *wqe_info; - } db; - /* read only */ struct mlx5_wq_cyc wq; u32 dma_fifo_mask; struct mlx5e_sq_stats *stats; + struct { + struct mlx5e_sq_dma *dma_fifo; + struct mlx5e_tx_wqe_info *wqe_info; + } db; void __iomem *uar_map; struct netdev_queue *txq; u32 sqn; @@ -399,30 +394,43 @@ struct mlx5e_txqsq { } recover; } ____cacheline_aligned_in_smp; +struct mlx5e_dma_info { + struct page *page; + dma_addr_t addr; +}; + +struct mlx5e_xdp_info { + struct xdp_frame *xdpf; + dma_addr_t dma_addr; + struct mlx5e_dma_info di; +}; + struct mlx5e_xdpsq { /* data path */ - /* dirtied @rx completion */ + /* dirtied @completion */ u16 cc; - u16 pc; + bool redirect_flush; - struct mlx5e_cq cq; + /* dirtied @xmit */ + u16 pc ____cacheline_aligned_in_smp; + bool doorbell; - /* write@xmit, read@completion */ - struct { - struct mlx5e_dma_info *di; - bool doorbell; - bool redirect_flush; - } db; + struct mlx5e_cq cq; /* read only */ struct mlx5_wq_cyc wq; + struct mlx5e_xdpsq_stats *stats; + struct { + struct mlx5e_xdp_info *xdpi; + } db; void __iomem *uar_map; u32 sqn; struct device *pdev; __be32 mkey_be; u8 min_inline_mode; unsigned long state; + unsigned int hw_mtu; /* control path */ struct mlx5_wq_ctrl wq_ctrl; @@ -459,11 +467,6 @@ mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n) return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc); } -struct mlx5e_dma_info { - struct page *page; - dma_addr_t addr; -}; - struct mlx5e_wqe_frag_info { struct mlx5e_dma_info *di; u32 offset; @@ -566,7 +569,6 @@ struct mlx5e_rq { /* XDP */ struct bpf_prog *xdp_prog; - unsigned int hw_mtu; struct mlx5e_xdpsq xdpsq; DECLARE_BITMAP(flags, 8); struct page_pool *page_pool; @@ -595,6 +597,9 @@ struct mlx5e_channel { __be32 mkey_be; u8 num_tc; + /* XDP_REDIRECT */ + struct mlx5e_xdpsq xdpsq; + /* data path - accessed per napi poll */ struct irq_desc *irq_desc; struct mlx5e_ch_stats *stats; @@ -617,6 +622,8 @@ struct mlx5e_channel_stats { struct mlx5e_ch_stats ch; struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC]; struct mlx5e_rq_stats rq; + struct mlx5e_xdpsq_stats rq_xdpsq; + struct mlx5e_xdpsq_stats xdpsq; } ____cacheline_aligned_in_smp; enum mlx5e_traffic_types { @@ -647,11 +654,6 @@ enum { MLX5E_STATE_DESTROYING, }; -struct mlx5e_vxlan_db { - spinlock_t lock; /* protect vxlan table */ - struct radix_tree_root tree; -}; - struct mlx5e_l2_rule { u8 addr[ETH_ALEN + 2]; struct mlx5_flow_handle *rule; @@ -809,7 +811,6 @@ struct mlx5e_priv { u32 tx_rates[MLX5E_MAX_NUM_SQS]; struct mlx5e_flow_steering fs; - struct mlx5e_vxlan_db vxlan; struct workqueue_struct *wq; struct work_struct update_carrier_work; @@ -876,14 +877,13 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); int mlx5e_napi_poll(struct napi_struct *napi, int budget); bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); -bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq); void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); -void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq); bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev); bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info); void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, bool recycle); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); @@ -892,7 +892,6 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq); void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix); void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix); -void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi); struct sk_buff * mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c new file mode 100644 index 000000000000..1881468dbcfa --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -0,0 +1,305 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/bpf_trace.h> +#include "en/xdp.h" + +static inline bool +mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di, + struct xdp_buff *xdp) +{ + struct mlx5e_xdp_info xdpi; + + xdpi.xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpi.xdpf)) + return false; + xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf); + dma_sync_single_for_device(sq->pdev, xdpi.dma_addr, + xdpi.xdpf->len, PCI_DMA_TODEVICE); + xdpi.di = *di; + + return mlx5e_xmit_xdp_frame(sq, &xdpi); +} + +/* returns true if packet was consumed by xdp */ +bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, + void *va, u16 *rx_headroom, u32 *len) +{ + struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct xdp_buff xdp; + u32 act; + int err; + + if (!prog) + return false; + + xdp.data = va + *rx_headroom; + xdp_set_data_meta_invalid(&xdp); + xdp.data_end = xdp.data + *len; + xdp.data_hard_start = va; + xdp.rxq = &rq->xdp_rxq; + + act = bpf_prog_run_xdp(prog, &xdp); + switch (act) { + case XDP_PASS: + *rx_headroom = xdp.data - xdp.data_hard_start; + *len = xdp.data_end - xdp.data; + return false; + case XDP_TX: + if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp))) + goto xdp_abort; + __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */ + return true; + case XDP_REDIRECT: + /* When XDP enabled then page-refcnt==1 here */ + err = xdp_do_redirect(rq->netdev, &xdp, prog); + if (unlikely(err)) + goto xdp_abort; + __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); + rq->xdpsq.redirect_flush = true; + mlx5e_page_dma_unmap(rq, di); + rq->stats->xdp_redirect++; + return true; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_ABORTED: +xdp_abort: + trace_xdp_exception(rq->netdev, prog, act); + case XDP_DROP: + rq->stats->xdp_drop++; + return true; + } +} + +bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + + struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; + struct mlx5_wqe_eth_seg *eseg = &wqe->eth; + struct mlx5_wqe_data_seg *dseg = wqe->data; + + struct xdp_frame *xdpf = xdpi->xdpf; + dma_addr_t dma_addr = xdpi->dma_addr; + unsigned int dma_len = xdpf->len; + + struct mlx5e_xdpsq_stats *stats = sq->stats; + + prefetchw(wqe); + + if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) { + stats->err++; + return false; + } + + if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) { + if (sq->doorbell) { + /* SQ is full, ring doorbell */ + mlx5e_xmit_xdp_doorbell(sq); + sq->doorbell = false; + } + stats->full++; + return false; + } + + cseg->fm_ce_se = 0; + + /* copy the inline part if required */ + if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { + memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE); + eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + dma_len -= MLX5E_XDP_MIN_INLINE; + dma_addr += MLX5E_XDP_MIN_INLINE; + dseg++; + } + + /* write the dma part */ + dseg->addr = cpu_to_be64(dma_addr); + dseg->byte_count = cpu_to_be32(dma_len); + + cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND); + + /* move page to reference to sq responsibility, + * and mark so it's not put back in page-cache. + */ + sq->db.xdpi[pi] = *xdpi; + sq->pc++; + + sq->doorbell = true; + + stats->xmit++; + return true; +} + +bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) +{ + struct mlx5e_xdpsq *sq; + struct mlx5_cqe64 *cqe; + struct mlx5e_rq *rq; + bool is_redirect; + u16 sqcc; + int i; + + sq = container_of(cq, struct mlx5e_xdpsq, cq); + + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) + return false; + + cqe = mlx5_cqwq_get_cqe(&cq->wq); + if (!cqe) + return false; + + is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state); + rq = container_of(sq, struct mlx5e_rq, xdpsq); + + /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), + * otherwise a cq overrun may occur + */ + sqcc = sq->cc; + + i = 0; + do { + u16 wqe_counter; + bool last_wqe; + + mlx5_cqwq_pop(&cq->wq); + + wqe_counter = be16_to_cpu(cqe->wqe_counter); + + do { + u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); + struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci]; + + last_wqe = (sqcc == wqe_counter); + sqcc++; + + if (is_redirect) { + xdp_return_frame(xdpi->xdpf); + dma_unmap_single(sq->pdev, xdpi->dma_addr, + xdpi->xdpf->len, DMA_TO_DEVICE); + } else { + /* Recycle RX page */ + mlx5e_page_release(rq, &xdpi->di, true); + } + } while (!last_wqe); + } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + + sq->stats->cqes += i; + + mlx5_cqwq_update_db_record(&cq->wq); + + /* ensure cq space is freed before enabling more cqes */ + wmb(); + + sq->cc = sqcc; + return (i == MLX5E_TX_CQ_POLL_BUDGET); +} + +void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) +{ + struct mlx5e_rq *rq; + bool is_redirect; + + is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state); + rq = is_redirect ? NULL : container_of(sq, struct mlx5e_rq, xdpsq); + + while (sq->cc != sq->pc) { + u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc); + struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci]; + + sq->cc++; + + if (is_redirect) { + xdp_return_frame(xdpi->xdpf); + dma_unmap_single(sq->pdev, xdpi->dma_addr, + xdpi->xdpf->len, DMA_TO_DEVICE); + } else { + /* Recycle RX page */ + mlx5e_page_release(rq, &xdpi->di, false); + } + } +} + +int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_xdpsq *sq; + int drops = 0; + int sq_num; + int i; + + if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state))) + return -ENETDOWN; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + sq_num = smp_processor_id(); + + if (unlikely(sq_num >= priv->channels.num)) + return -ENXIO; + + sq = &priv->channels.c[sq_num]->xdpsq; + + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) + return -ENETDOWN; + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + struct mlx5e_xdp_info xdpi; + + xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) { + xdp_return_frame_rx_napi(xdpf); + drops++; + continue; + } + + xdpi.xdpf = xdpf; + + if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) { + dma_unmap_single(sq->pdev, xdpi.dma_addr, + xdpf->len, DMA_TO_DEVICE); + xdp_return_frame_rx_napi(xdpf); + drops++; + } + } + + if (flags & XDP_XMIT_FLUSH) + mlx5e_xmit_xdp_doorbell(sq); + + return n - drops; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h new file mode 100644 index 000000000000..6dfab045925f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -0,0 +1,63 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __MLX5_EN_XDP_H__ +#define __MLX5_EN_XDP_H__ + +#include "en.h" + +#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \ + MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM))) +#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) +#define MLX5E_XDP_TX_DS_COUNT \ + ((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */) + +bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, + void *va, u16 *rx_headroom, u32 *len); +bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq); +void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq); + +bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi); +int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags); + +static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + struct mlx5e_tx_wqe *wqe; + u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */ + + wqe = mlx5_wq_cyc_get_wqe(wq, pi); + + mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl); +} + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 75e4308ba786..d258bb679271 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv) HLIST_HEAD(del_list); spin_lock_bh(&priv->fs.arfs.arfs_lock); mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) { - if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) - break; if (!work_pending(&arfs_rule->arfs_work) && rps_may_expire_flow(priv->netdev, arfs_rule->rxq, arfs_rule->flow_id, arfs_rule->filter_id)) { hlist_del_init(&arfs_rule->hlist); hlist_add_head(&arfs_rule->hlist, &del_list); + if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) + break; } } spin_unlock_bh(&priv->fs.arfs.arfs_lock); @@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, skb->protocol != htons(ETH_P_IPV6)) return -EPROTONOSUPPORT; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol); if (!arfs_t) return -EPROTONOSUPPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 0a52f31fef37..e33afa8d2417 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) } static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, - struct ieee_ets *ets) + struct ieee_ets *ets, + bool zero_sum_allowed) { bool have_ets_tc = false; int bw_sum = 0; @@ -300,8 +301,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } if (have_ets_tc && bw_sum != 100) { - netdev_err(netdev, - "Failed to validate ETS: BW sum is illegal\n"); + if (bw_sum || (!bw_sum && !zero_sum_allowed)) + netdev_err(netdev, + "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; } return 0; @@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, if (!MLX5_CAP_GEN(priv->mdev, ets)) return -EOPNOTSUPP; - err = mlx5e_dbcnl_validate_ets(netdev, ets); + err = mlx5e_dbcnl_validate_ets(netdev, ets, false); if (err) return err; @@ -642,12 +644,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev) ets.prio_tc[i]); } - err = mlx5e_dbcnl_validate_ets(netdev, &ets); - if (err) { - netdev_err(netdev, - "%s, Failed to validate ETS: %d\n", __func__, err); + err = mlx5e_dbcnl_validate_ets(netdev, &ets, true); + if (err) goto out; - } err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); if (err) { @@ -1173,6 +1172,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; int err; + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP; + if (!MLX5_DSCP_SUPPORTED(mdev)) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dccde18f6170..a2fb21ca5767 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -45,8 +45,9 @@ #include "en_accel/tls.h" #include "accel/ipsec.h" #include "accel/tls.h" -#include "vxlan.h" +#include "lib/vxlan.h" #include "en/port.h" +#include "en/xdp.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -96,14 +97,19 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params) { - if (!params->xdp_prog) { - u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); - u16 rq_headroom = MLX5_RX_HEADROOM + NET_IP_ALIGN; + u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + u16 linear_rq_headroom = params->xdp_prog ? + XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM; + u32 frag_sz; - return MLX5_SKB_FRAG_SZ(rq_headroom + hw_mtu); - } + linear_rq_headroom += NET_IP_ALIGN; + + frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu); - return PAGE_SIZE; + if (params->xdp_prog && frag_sz < PAGE_SIZE) + frag_sz = PAGE_SIZE; + + return frag_sz; } static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params) @@ -485,7 +491,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->channel = c; rq->ix = c->ix; rq->mdev = mdev; - rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); rq->stats = &c->priv->channel_stats[c->ix].rq; rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL; @@ -877,7 +882,7 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) /* UMR WQE (if in progress) is always at wq->head */ if (rq->mpwqe.umr_in_progress) - mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); + rq->dealloc_wqe(rq, wq->head); while (!mlx5_wq_ll_is_empty(wq)) { struct mlx5e_rx_wqe_ll *wqe; @@ -963,16 +968,16 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq) static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq) { - kvfree(sq->db.di); + kvfree(sq->db.xdpi); } static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) { int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); - sq->db.di = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.di)), - GFP_KERNEL, numa); - if (!sq->db.di) { + sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)), + GFP_KERNEL, numa); + if (!sq->db.xdpi) { mlx5e_free_xdpsq_db(sq); return -ENOMEM; } @@ -983,7 +988,8 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_sq_param *param, - struct mlx5e_xdpsq *sq) + struct mlx5e_xdpsq *sq, + bool is_redirect) { void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq); struct mlx5_core_dev *mdev = c->mdev; @@ -995,6 +1001,10 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; + sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + sq->stats = is_redirect ? + &c->priv->channel_stats[c->ix].xdpsq : + &c->priv->channel_stats[c->ix].rq_xdpsq; param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -1524,7 +1534,8 @@ static void mlx5e_close_icosq(struct mlx5e_icosq *sq) static int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_sq_param *param, - struct mlx5e_xdpsq *sq) + struct mlx5e_xdpsq *sq, + bool is_redirect) { unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT; struct mlx5e_create_sq_param csp = {}; @@ -1532,7 +1543,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c, int err; int i; - err = mlx5e_alloc_xdpsq(c, params, param, sq); + err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect); if (err) return err; @@ -1541,6 +1552,8 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c, csp.cqn = sq->cq.mcq.cqn; csp.wq_ctrl = &sq->wq_ctrl; csp.min_inline_mode = sq->min_inline_mode; + if (is_redirect) + set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state); set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn); if (err) @@ -1923,10 +1936,14 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (err) goto err_close_icosq_cq; - err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq); + err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xdpsq.cq); if (err) goto err_close_tx_cqs; + err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq); + if (err) + goto err_close_xdp_tx_cqs; + /* XDP SQ CQ params are same as normal TXQ sq CQ params */ err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->rq.xdpsq.cq) : 0; @@ -1943,7 +1960,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (err) goto err_close_icosq; - err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0; + err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0; if (err) goto err_close_sqs; @@ -1951,9 +1968,17 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (err) goto err_close_xdp_sq; + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true); + if (err) + goto err_close_rq; + *cp = c; return 0; + +err_close_rq: + mlx5e_close_rq(&c->rq); + err_close_xdp_sq: if (c->xdp) mlx5e_close_xdpsq(&c->rq.xdpsq); @@ -1972,6 +1997,9 @@ err_disable_napi: err_close_rx_cq: mlx5e_close_cq(&c->rq.cq); +err_close_xdp_tx_cqs: + mlx5e_close_cq(&c->xdpsq.cq); + err_close_tx_cqs: mlx5e_close_tx_cqs(c); @@ -2006,6 +2034,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c) static void mlx5e_close_channel(struct mlx5e_channel *c) { + mlx5e_close_xdpsq(&c->xdpsq); mlx5e_close_rq(&c->rq); if (c->xdp) mlx5e_close_xdpsq(&c->rq.xdpsq); @@ -2015,6 +2044,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) if (c->xdp) mlx5e_close_cq(&c->rq.xdpsq.cq); mlx5e_close_cq(&c->rq.cq); + mlx5e_close_cq(&c->xdpsq.cq); mlx5e_close_tx_cqs(c); mlx5e_close_cq(&c->icosq.cq); netif_napi_del(&c->napi); @@ -2944,7 +2974,7 @@ int mlx5e_open(struct net_device *netdev) mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); - if (mlx5e_vxlan_allowed(priv->mdev)) + if (mlx5_vxlan_allowed(priv->mdev->vxlan)) udp_tunnel_get_rx_info(netdev); return err; @@ -3707,6 +3737,14 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; + if (params->xdp_prog && + !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { + netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n", + new_mtu, MLX5E_XDP_MAX_MTU); + err = -EINVAL; + goto out; + } + if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params); u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params); @@ -3716,7 +3754,8 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (!reset) { params->sw_mtu = new_mtu; - set_mtu_cb(priv); + if (set_mtu_cb) + set_mtu_cb(priv); netdev->mtu = params->sw_mtu; goto out; } @@ -3931,6 +3970,57 @@ static int mlx5e_get_vf_stats(struct net_device *dev, } #endif +struct mlx5e_vxlan_work { + struct work_struct work; + struct mlx5e_priv *priv; + u16 port; +}; + +static void mlx5e_vxlan_add_work(struct work_struct *work) +{ + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; + u16 port = vxlan_work->port; + + mutex_lock(&priv->state_lock); + mlx5_vxlan_add_port(priv->mdev->vxlan, port); + mutex_unlock(&priv->state_lock); + + kfree(vxlan_work); +} + +static void mlx5e_vxlan_del_work(struct work_struct *work) +{ + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; + u16 port = vxlan_work->port; + + mutex_lock(&priv->state_lock); + mlx5_vxlan_del_port(priv->mdev->vxlan, port); + mutex_unlock(&priv->state_lock); + kfree(vxlan_work); +} + +static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add) +{ + struct mlx5e_vxlan_work *vxlan_work; + + vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC); + if (!vxlan_work) + return; + + if (add) + INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work); + else + INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work); + + vxlan_work->priv = priv; + vxlan_work->port = port; + queue_work(priv->wq, &vxlan_work->work); +} + static void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti) { @@ -3939,10 +4029,10 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev, if (ti->type != UDP_TUNNEL_TYPE_VXLAN) return; - if (!mlx5e_vxlan_allowed(priv->mdev)) + if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) return; - mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1); + mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1); } static void mlx5e_del_vxlan_port(struct net_device *netdev, @@ -3953,10 +4043,10 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev, if (ti->type != UDP_TUNNEL_TYPE_VXLAN) return; - if (!mlx5e_vxlan_allowed(priv->mdev)) + if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) return; - mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0); + mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0); } static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, @@ -3987,7 +4077,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, port = be16_to_cpu(udph->dest); /* Verify if UDP port is being offloaded by HW */ - if (mlx5e_vxlan_lookup_port(priv, port)) + if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port)) return features; } @@ -4094,26 +4184,47 @@ static void mlx5e_tx_timeout(struct net_device *dev) queue_work(priv->wq, &priv->tx_timeout_work); } +static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) +{ + struct net_device *netdev = priv->netdev; + struct mlx5e_channels new_channels = {}; + + if (priv->channels.params.lro_en) { + netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n"); + return -EINVAL; + } + + if (MLX5_IPSEC_DEV(priv->mdev)) { + netdev_warn(netdev, "can't set XDP with IPSec offload\n"); + return -EINVAL; + } + + new_channels.params = priv->channels.params; + new_channels.params.xdp_prog = prog; + + if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { + netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n", + new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU); + return -EINVAL; + } + + return 0; +} + static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); struct bpf_prog *old_prog; - int err = 0; bool reset, was_opened; + int err = 0; int i; mutex_lock(&priv->state_lock); - if ((netdev->features & NETIF_F_LRO) && prog) { - netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n"); - err = -EINVAL; - goto unlock; - } - - if ((netdev->features & NETIF_F_HW_ESP) && prog) { - netdev_warn(netdev, "can't set XDP with IPSec offload\n"); - err = -EINVAL; - goto unlock; + if (prog) { + err = mlx5e_xdp_allowed(priv, prog); + if (err) + goto unlock; } was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state); @@ -4242,6 +4353,7 @@ static const struct net_device_ops mlx5e_netdev_ops = { #endif .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, + .ndo_xdp_xmit = mlx5e_xdp_xmit, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = mlx5e_netpoll, #endif @@ -4537,7 +4649,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { netdev->hw_enc_features |= NETIF_F_IP_CSUM; netdev->hw_enc_features |= NETIF_F_IPV6_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; @@ -4545,7 +4657,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL; } - if (mlx5e_vxlan_allowed(mdev)) { + if (mlx5_vxlan_allowed(mdev->vxlan)) { netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | @@ -4656,14 +4768,12 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_build_nic_netdev(netdev); mlx5e_build_tc2txq_maps(priv); - mlx5e_vxlan_init(priv); } static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); - mlx5e_vxlan_cleanup(priv); } static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1d5295ee863c..15d8ae28c040 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -34,7 +34,6 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> -#include <linux/bpf_trace.h> #include <net/busy_poll.h> #include <net/ip6_checksum.h> #include <net/page_pool.h> @@ -46,6 +45,7 @@ #include "en_accel/ipsec_rxtx.h" #include "en_accel/tls_rxtx.h" #include "lib/clock.h" +#include "en/xdp.h" static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { @@ -239,8 +239,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, return 0; } -static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, - struct mlx5e_dma_info *dma_info) +void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir); } @@ -277,10 +276,11 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, } static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq, - struct mlx5e_wqe_frag_info *frag) + struct mlx5e_wqe_frag_info *frag, + bool recycle) { if (frag->last_in_page) - mlx5e_page_release(rq, frag->di, true); + mlx5e_page_release(rq, frag->di, recycle); } static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix) @@ -308,25 +308,26 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe, free_frags: while (--i >= 0) - mlx5e_put_rx_frag(rq, --frag); + mlx5e_put_rx_frag(rq, --frag, true); return err; } static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, - struct mlx5e_wqe_frag_info *wi) + struct mlx5e_wqe_frag_info *wi, + bool recycle) { int i; for (i = 0; i < rq->wqe.info.num_frags; i++, wi++) - mlx5e_put_rx_frag(rq, wi); + mlx5e_put_rx_frag(rq, wi, recycle); } void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix); - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, false); } static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) @@ -396,7 +397,8 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev, } } -void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi) +static void +mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle) { const bool no_xdp_xmit = bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE); @@ -405,7 +407,7 @@ void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi) for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap)) - mlx5e_page_release(rq, &dma_info[i], true); + mlx5e_page_release(rq, &dma_info[i], recycle); } static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) @@ -505,8 +507,8 @@ err_unmap: void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; - - mlx5e_free_rx_mpwqe(rq, wi); + /* Don't recycle, this function is called on rq/netdev close */ + mlx5e_free_rx_mpwqe(rq, wi, false); } bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) @@ -847,135 +849,6 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb); } -static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) -{ - struct mlx5_wq_cyc *wq = &sq->wq; - struct mlx5e_tx_wqe *wqe; - u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */ - - wqe = mlx5_wq_cyc_get_wqe(wq, pi); - - mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl); -} - -static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, - struct mlx5e_dma_info *di, - const struct xdp_buff *xdp) -{ - struct mlx5e_xdpsq *sq = &rq->xdpsq; - struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); - struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - - struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; - struct mlx5_wqe_eth_seg *eseg = &wqe->eth; - struct mlx5_wqe_data_seg *dseg; - - ptrdiff_t data_offset = xdp->data - xdp->data_hard_start; - dma_addr_t dma_addr = di->addr + data_offset; - unsigned int dma_len = xdp->data_end - xdp->data; - - struct mlx5e_rq_stats *stats = rq->stats; - - prefetchw(wqe); - - if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) { - stats->xdp_drop++; - return false; - } - - if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) { - if (sq->db.doorbell) { - /* SQ is full, ring doorbell */ - mlx5e_xmit_xdp_doorbell(sq); - sq->db.doorbell = false; - } - stats->xdp_tx_full++; - return false; - } - - dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE); - - cseg->fm_ce_se = 0; - - dseg = (struct mlx5_wqe_data_seg *)eseg + 1; - - /* copy the inline part if required */ - if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE); - eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); - dma_len -= MLX5E_XDP_MIN_INLINE; - dma_addr += MLX5E_XDP_MIN_INLINE; - dseg++; - } - - /* write the dma part */ - dseg->addr = cpu_to_be64(dma_addr); - dseg->byte_count = cpu_to_be32(dma_len); - - cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND); - - /* move page to reference to sq responsibility, - * and mark so it's not put back in page-cache. - */ - __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */ - sq->db.di[pi] = *di; - sq->pc++; - - sq->db.doorbell = true; - - stats->xdp_tx++; - return true; -} - -/* returns true if packet was consumed by xdp */ -static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq, - struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len) -{ - struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); - struct xdp_buff xdp; - u32 act; - int err; - - if (!prog) - return false; - - xdp.data = va + *rx_headroom; - xdp_set_data_meta_invalid(&xdp); - xdp.data_end = xdp.data + *len; - xdp.data_hard_start = va; - xdp.rxq = &rq->xdp_rxq; - - act = bpf_prog_run_xdp(prog, &xdp); - switch (act) { - case XDP_PASS: - *rx_headroom = xdp.data - xdp.data_hard_start; - *len = xdp.data_end - xdp.data; - return false; - case XDP_TX: - if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp))) - trace_xdp_exception(rq->netdev, prog, act); - return true; - case XDP_REDIRECT: - /* When XDP enabled then page-refcnt==1 here */ - err = xdp_do_redirect(rq->netdev, &xdp, prog); - if (!err) { - __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); - rq->xdpsq.db.redirect_flush = true; - mlx5e_page_dma_unmap(rq, di); - } - return true; - default: - bpf_warn_invalid_xdp_action(act); - case XDP_ABORTED: - trace_xdp_exception(rq->netdev, prog, act); - case XDP_DROP: - rq->stats->xdp_drop++; - return true; - } -} - static inline struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va, u32 frag_size, u16 headroom, @@ -1113,7 +986,7 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) napi_gro_receive(rq->cq.napi, skb); free_wqe: - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, true); wq_cyc_pop: mlx5_wq_cyc_pop(wq); } @@ -1155,7 +1028,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) napi_gro_receive(rq->cq.napi, skb); free_wqe: - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, true); wq_cyc_pop: mlx5_wq_cyc_pop(wq); } @@ -1226,6 +1099,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset, frag_size, DMA_FROM_DEVICE); + prefetchw(va); /* xdp_frame data area */ prefetch(data); rcu_read_lock(); @@ -1292,7 +1166,7 @@ mpwrq_cqe_out: wq = &rq->mpwqe.wq; wqe = mlx5_wq_ll_get_wqe(wq, wqe_id); - mlx5e_free_rx_mpwqe(rq, wi); + mlx5e_free_rx_mpwqe(rq, wi, true); mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); } @@ -1328,14 +1202,14 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) rq->handle_rx_cqe(rq, cqe); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); - if (xdpsq->db.doorbell) { + if (xdpsq->doorbell) { mlx5e_xmit_xdp_doorbell(xdpsq); - xdpsq->db.doorbell = false; + xdpsq->doorbell = false; } - if (xdpsq->db.redirect_flush) { + if (xdpsq->redirect_flush) { xdp_do_flush_map(); - xdpsq->db.redirect_flush = false; + xdpsq->redirect_flush = false; } mlx5_cqwq_update_db_record(&cq->wq); @@ -1346,80 +1220,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) return work_done; } -bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) -{ - struct mlx5e_xdpsq *sq; - struct mlx5_cqe64 *cqe; - struct mlx5e_rq *rq; - u16 sqcc; - int i; - - sq = container_of(cq, struct mlx5e_xdpsq, cq); - - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return false; - - cqe = mlx5_cqwq_get_cqe(&cq->wq); - if (!cqe) - return false; - - rq = container_of(sq, struct mlx5e_rq, xdpsq); - - /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), - * otherwise a cq overrun may occur - */ - sqcc = sq->cc; - - i = 0; - do { - u16 wqe_counter; - bool last_wqe; - - mlx5_cqwq_pop(&cq->wq); - - wqe_counter = be16_to_cpu(cqe->wqe_counter); - - do { - struct mlx5e_dma_info *di; - u16 ci; - - last_wqe = (sqcc == wqe_counter); - - ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); - di = &sq->db.di[ci]; - - sqcc++; - /* Recycle RX page */ - mlx5e_page_release(rq, di, true); - } while (!last_wqe); - } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); - - rq->stats->xdp_tx_cqe += i; - - mlx5_cqwq_update_db_record(&cq->wq); - - /* ensure cq space is freed before enabling more cqes */ - wmb(); - - sq->cc = sqcc; - return (i == MLX5E_TX_CQ_POLL_BUDGET); -} - -void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) -{ - struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq); - struct mlx5e_dma_info *di; - u16 ci; - - while (sq->cc != sq->pc) { - ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc); - di = &sq->db.di[ci]; - sq->cc++; - - mlx5e_page_release(rq, di, false); - } -} - #ifdef CONFIG_MLX5_CORE_IPOIB #define MLX5_IB_GRH_DGID_OFFSET 24 @@ -1521,7 +1321,7 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) napi_gro_receive(rq->cq.napi, skb); wq_free_wqe: - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, true); mlx5_wq_cyc_pop(wq); } @@ -1544,19 +1344,19 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt); if (unlikely(!skb)) { /* a DROP, save the page-reuse checks */ - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, true); goto wq_cyc_pop; } skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt); if (unlikely(!skb)) { - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, true); goto wq_cyc_pop; } mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); napi_gro_receive(rq->cq.napi, skb); - mlx5e_free_rx_wqe(rq, wi); + mlx5e_free_rx_wqe(rq, wi, true); wq_cyc_pop: mlx5_wq_cyc_pop(wq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index c0507fada0be..12fdf5c92b67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -59,9 +59,11 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) }, @@ -73,6 +75,10 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) }, @@ -128,6 +134,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; + struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq; + struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; struct mlx5e_ch_stats *ch_stats = &channel_stats->ch; int j; @@ -141,10 +149,12 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_csum_complete += rq_stats->csum_complete; s->rx_csum_unnecessary += rq_stats->csum_unnecessary; s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; - s->rx_xdp_drop += rq_stats->xdp_drop; - s->rx_xdp_tx += rq_stats->xdp_tx; - s->rx_xdp_tx_cqe += rq_stats->xdp_tx_cqe; - s->rx_xdp_tx_full += rq_stats->xdp_tx_full; + s->rx_xdp_drop += rq_stats->xdp_drop; + s->rx_xdp_redirect += rq_stats->xdp_redirect; + s->rx_xdp_tx_xmit += xdpsq_stats->xmit; + s->rx_xdp_tx_full += xdpsq_stats->full; + s->rx_xdp_tx_err += xdpsq_stats->err; + s->rx_xdp_tx_cqe += xdpsq_stats->cqes; s->rx_wqe_err += rq_stats->wqe_err; s->rx_mpwqe_filler_cqes += rq_stats->mpwqe_filler_cqes; s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides; @@ -162,7 +172,12 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->ch_poll += ch_stats->poll; s->ch_arm += ch_stats->arm; s->ch_aff_change += ch_stats->aff_change; - s->ch_eq_rearm += ch_stats->eq_rearm; + s->ch_eq_rearm += ch_stats->eq_rearm; + /* xdp redirect */ + s->tx_xdp_xmit += xdpsq_red_stats->xmit; + s->tx_xdp_full += xdpsq_red_stats->full; + s->tx_xdp_err += xdpsq_red_stats->err; + s->tx_xdp_cqes += xdpsq_red_stats->cqes; for (j = 0; j < priv->max_opened_tc; j++) { struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; @@ -1126,9 +1141,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) }, @@ -1168,6 +1181,20 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) }, }; +static const struct counter_desc rq_xdpsq_stats_desc[] = { + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, +}; + +static const struct counter_desc xdpsq_stats_desc[] = { + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, +}; + static const struct counter_desc ch_stats_desc[] = { { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) }, { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) }, @@ -1178,6 +1205,8 @@ static const struct counter_desc ch_stats_desc[] = { #define NUM_RQ_STATS ARRAY_SIZE(rq_stats_desc) #define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc) +#define NUM_XDPSQ_STATS ARRAY_SIZE(xdpsq_stats_desc) +#define NUM_RQ_XDPSQ_STATS ARRAY_SIZE(rq_xdpsq_stats_desc) #define NUM_CH_STATS ARRAY_SIZE(ch_stats_desc) static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) @@ -1186,7 +1215,9 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) return (NUM_RQ_STATS * max_nch) + (NUM_CH_STATS * max_nch) + - (NUM_SQ_STATS * max_nch * priv->max_opened_tc); + (NUM_SQ_STATS * max_nch * priv->max_opened_tc) + + (NUM_RQ_XDPSQ_STATS * max_nch) + + (NUM_XDPSQ_STATS * max_nch); } static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, @@ -1200,9 +1231,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, sprintf(data + (idx++) * ETH_GSTRING_LEN, ch_stats_desc[j].format, i); - for (i = 0; i < max_nch; i++) + for (i = 0; i < max_nch; i++) { for (j = 0; j < NUM_RQ_STATS; j++) - sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i); + sprintf(data + (idx++) * ETH_GSTRING_LEN, + rq_stats_desc[j].format, i); + for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + rq_xdpsq_stats_desc[j].format, i); + } for (tc = 0; tc < priv->max_opened_tc; tc++) for (i = 0; i < max_nch; i++) @@ -1211,6 +1247,11 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, sq_stats_desc[j].format, priv->channel_tc2txq[i][tc]); + for (i = 0; i < max_nch; i++) + for (j = 0; j < NUM_XDPSQ_STATS; j++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + xdpsq_stats_desc[j].format, i); + return idx; } @@ -1226,11 +1267,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].ch, ch_stats_desc, j); - for (i = 0; i < max_nch; i++) + for (i = 0; i < max_nch; i++) { for (j = 0; j < NUM_RQ_STATS; j++) data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq, rq_stats_desc, j); + for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq, + rq_xdpsq_stats_desc, j); + } for (tc = 0; tc < priv->max_opened_tc; tc++) for (i = 0; i < max_nch; i++) @@ -1239,6 +1285,12 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc], sq_stats_desc, j); + for (i = 0; i < max_nch; i++) + for (j = 0; j < NUM_XDPSQ_STATS; j++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq, + xdpsq_stats_desc, j); + return idx; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index fc3f66003edd..a4c035aedd46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -44,6 +44,8 @@ #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld) #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld) #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld) #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld) struct counter_desc { @@ -70,9 +72,11 @@ struct mlx5e_sw_stats { u64 rx_csum_complete; u64 rx_csum_unnecessary_inner; u64 rx_xdp_drop; - u64 rx_xdp_tx; - u64 rx_xdp_tx_cqe; + u64 rx_xdp_redirect; + u64 rx_xdp_tx_xmit; u64 rx_xdp_tx_full; + u64 rx_xdp_tx_err; + u64 rx_xdp_tx_cqe; u64 tx_csum_none; u64 tx_csum_partial; u64 tx_csum_partial_inner; @@ -84,6 +88,10 @@ struct mlx5e_sw_stats { u64 tx_queue_wake; u64 tx_udp_seg_rem; u64 tx_cqe_err; + u64 tx_xdp_xmit; + u64 tx_xdp_full; + u64 tx_xdp_err; + u64 tx_xdp_cqes; u64 rx_wqe_err; u64 rx_mpwqe_filler_cqes; u64 rx_mpwqe_filler_strides; @@ -178,9 +186,7 @@ struct mlx5e_rq_stats { u64 lro_bytes; u64 removed_vlan_packets; u64 xdp_drop; - u64 xdp_tx; - u64 xdp_tx_cqe; - u64 xdp_tx_full; + u64 xdp_redirect; u64 wqe_err; u64 mpwqe_filler_cqes; u64 mpwqe_filler_strides; @@ -225,6 +231,14 @@ struct mlx5e_sq_stats { u64 cqe_err; }; +struct mlx5e_xdpsq_stats { + u64 xmit; + u64 full; + u64 err; + /* dirtied @completion */ + u64 cqes ____cacheline_aligned_in_smp; +}; + struct mlx5e_ch_stats { u64 events; u64 poll; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e9888d6c1f7c..c28fe469b04a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -50,7 +50,7 @@ #include "en_rep.h" #include "en_tc.h" #include "eswitch.h" -#include "vxlan.h" +#include "lib/vxlan.h" #include "fs_core.h" #include "en/port.h" @@ -1124,16 +1124,12 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, f->mask); - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); - struct net_device *up_dev = uplink_rpriv->netdev; - struct mlx5e_priv *up_priv = netdev_priv(up_dev); /* Full udp dst port must be given */ if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) goto vxlan_match_offload_err; - if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) && + if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) parse_vxlan_attr(spec, f); else { @@ -1211,6 +1207,26 @@ vxlan_match_offload_err: MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6); } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_dissector_key_ip *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_IP, + f->key); + struct flow_dissector_key_ip *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_IP, + f->mask); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos >> 2); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + } + /* Enforce DMAC when offloading incoming tunneled flows. * Flow counters require a match on the DMAC. */ @@ -1259,7 +1275,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | BIT(FLOW_DISSECTOR_KEY_TCP) | - BIT(FLOW_DISSECTOR_KEY_IP))) { + BIT(FLOW_DISSECTOR_KEY_IP) | + BIT(FLOW_DISSECTOR_KEY_ENC_IP))) { netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", f->dissector->used_keys); return -EOPNOTSUPP; @@ -2004,6 +2021,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv, else actions = flow->nic_attr->action; + if (flow->flags & MLX5E_TC_FLOW_EGRESS && + !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)) + return false; + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, exts); @@ -2125,7 +2146,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, struct net_device **out_dev, struct flowi4 *fl4, struct neighbour **out_n, - int *out_ttl) + u8 *out_ttl) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *uplink_rpriv; @@ -2149,7 +2170,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, else *out_dev = rt->dst.dev; - *out_ttl = ip4_dst_hoplimit(&rt->dst); + if (!(*out_ttl)) + *out_ttl = ip4_dst_hoplimit(&rt->dst); n = dst_neigh_lookup(&rt->dst, &fl4->daddr); ip_rt_put(rt); if (!n) @@ -2178,7 +2200,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, struct net_device **out_dev, struct flowi6 *fl6, struct neighbour **out_n, - int *out_ttl) + u8 *out_ttl) { struct neighbour *n = NULL; struct dst_entry *dst; @@ -2193,7 +2215,8 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, if (ret < 0) return ret; - *out_ttl = ip6_dst_hoplimit(dst); + if (!(*out_ttl)) + *out_ttl = ip6_dst_hoplimit(dst); uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); /* if the egress device isn't on the same HW e-switch, we use the uplink */ @@ -2217,7 +2240,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, static void gen_vxlan_header_ipv4(struct net_device *out_dev, char buf[], int encap_size, unsigned char h_dest[ETH_ALEN], - int ttl, + u8 tos, u8 ttl, __be32 daddr, __be32 saddr, __be16 udp_dst_port, @@ -2237,6 +2260,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev, ip->daddr = daddr; ip->saddr = saddr; + ip->tos = tos; ip->ttl = ttl; ip->protocol = IPPROTO_UDP; ip->version = 0x4; @@ -2250,7 +2274,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev, static void gen_vxlan_header_ipv6(struct net_device *out_dev, char buf[], int encap_size, unsigned char h_dest[ETH_ALEN], - int ttl, + u8 tos, u8 ttl, struct in6_addr *daddr, struct in6_addr *saddr, __be16 udp_dst_port, @@ -2267,7 +2291,7 @@ static void gen_vxlan_header_ipv6(struct net_device *out_dev, ether_addr_copy(eth->h_source, out_dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); - ip6_flow_hdr(ip6h, 0, 0); + ip6_flow_hdr(ip6h, tos, 0); /* the HW fills up ipv6 payload len */ ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; @@ -2289,9 +2313,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, struct net_device *out_dev; struct neighbour *n = NULL; struct flowi4 fl4 = {}; + u8 nud_state, tos, ttl; char *encap_header; - int ttl, err; - u8 nud_state; + int err; if (max_encap_size < ipv4_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", @@ -2312,6 +2336,10 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, err = -EOPNOTSUPP; goto free_encap; } + + tos = tun_key->tos; + ttl = tun_key->ttl; + fl4.flowi4_tos = tun_key->tos; fl4.daddr = tun_key->u.ipv4.dst; fl4.saddr = tun_key->u.ipv4.src; @@ -2346,7 +2374,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, switch (e->tunnel_type) { case MLX5_HEADER_TYPE_VXLAN: gen_vxlan_header_ipv4(out_dev, encap_header, - ipv4_encap_size, e->h_dest, ttl, + ipv4_encap_size, e->h_dest, tos, ttl, fl4.daddr, fl4.saddr, tun_key->tp_dst, tunnel_id_to_key32(tun_key->tun_id)); @@ -2394,9 +2422,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, struct net_device *out_dev; struct neighbour *n = NULL; struct flowi6 fl6 = {}; + u8 nud_state, tos, ttl; char *encap_header; - int err, ttl = 0; - u8 nud_state; + int err; if (max_encap_size < ipv6_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", @@ -2418,6 +2446,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, goto free_encap; } + tos = tun_key->tos; + ttl = tun_key->ttl; + fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label); fl6.daddr = tun_key->u.ipv6.dst; fl6.saddr = tun_key->u.ipv6.src; @@ -2452,7 +2483,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, switch (e->tunnel_type) { case MLX5_HEADER_TYPE_VXLAN: gen_vxlan_header_ipv6(out_dev, encap_header, - ipv6_encap_size, e->h_dest, ttl, + ipv6_encap_size, e->h_dest, tos, ttl, &fl6.daddr, &fl6.saddr, tun_key->tp_dst, tunnel_id_to_key32(tun_key->tun_id)); @@ -2498,11 +2529,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, - REP_ETH); - struct net_device *up_dev = uplink_rpriv->netdev; unsigned short family = ip_tunnel_info_af(tun_info); - struct mlx5e_priv *up_priv = netdev_priv(up_dev); struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct ip_tunnel_key *key = &tun_info->key; struct mlx5e_encap_entry *e; @@ -2522,7 +2549,7 @@ vxlan_encap_offload_err: return -EOPNOTSUPP; } - if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) && + if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { tunnel_type = MLX5_HEADER_TYPE_VXLAN; } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 9106ea45e3cb..ae73ea992845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -66,22 +66,21 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev, } } +static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i) +{ + return &sq->db.dma_fifo[i & sq->dma_fifo_mask]; +} + static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size, enum mlx5e_dma_map_type map_type) { - u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask; + struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++); - sq->db.dma_fifo[i].addr = addr; - sq->db.dma_fifo[i].size = size; - sq->db.dma_fifo[i].type = map_type; - sq->dma_fifo_pc++; -} - -static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i) -{ - return &sq->db.dma_fifo[i & sq->dma_fifo_mask]; + dma->addr = addr; + dma->size = size; + dma->type = map_type; } static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 4e1f99a98d5d..85d517360157 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -32,6 +32,7 @@ #include <linux/irq.h> #include "en.h" +#include "en/xdp.h" static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) { @@ -84,6 +85,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) for (i = 0; i < c->num_tc; i++) busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget); + busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq); + if (c->xdp) busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq); @@ -116,6 +119,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_cq_arm(&c->rq.cq); mlx5e_cq_arm(&c->icosq.cq); + mlx5e_cq_arm(&c->xdpsq.cq); return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b79d74860a30..40dba9e8af92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1696,7 +1696,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) int vport_num; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; esw_info(dev, @@ -1765,7 +1765,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) + if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); @@ -2216,6 +2216,6 @@ free_out: u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) { - return esw->mode; + return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE; } EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f880ffc9acd6..a21df24b695e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1889,7 +1889,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!fwd_next_prio_supported(ft)) return ERR_PTR(-EOPNOTSUPP); - if (dest) + if (dest_num) return ERR_PTR(-EINVAL); mutex_lock(&root->chain_lock); next_ft = find_next_chained_ft(prio); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index af3bb2f7a504..b7c21eb21a21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -76,6 +76,7 @@ void mlx5i_init(struct mlx5_core_dev *mdev, void *ppriv) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); + u16 max_mtu; /* priv init */ priv->mdev = mdev; @@ -84,6 +85,9 @@ void mlx5i_init(struct mlx5_core_dev *mdev, priv->ppriv = ppriv; mutex_init(&priv->state_lock); + mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + netdev->mtu = max_mtu; + mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev), netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 1e062e6b2587..3f767cde4c1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, void mlx5_init_clock(struct mlx5_core_dev *mdev) { struct mlx5_clock *clock = &mdev->clock; + u64 overflow_cycles; u64 ns; u64 frac = 0; u32 dev_freq; @@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) /* Calculate period in seconds to call the overflow watchdog - to make * sure counter is checked at least once every wrap around. + * The period is calculated as the minimum between max HW cycles count + * (The clock source mask) and max amount of cycles that can be + * multiplied by clock multiplier where the result doesn't exceed + * 64bits. */ - ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, + overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult); + overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1); + + ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles, frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); + do_div(ns, NSEC_PER_SEC / HZ); clock->overflow_period = ns; mdev->clock_info_page = alloc_page(GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c new file mode 100644 index 000000000000..9a8fd762167b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -0,0 +1,230 @@ +/* + * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" +#include "vxlan.h" + +struct mlx5_vxlan { + struct mlx5_core_dev *mdev; + spinlock_t lock; /* protect vxlan table */ + /* max_num_ports is usuallly 4, 16 buckets is more than enough */ + DECLARE_HASHTABLE(htable, 4); + int num_ports; + struct mutex sync_lock; /* sync add/del port HW operations */ +}; + +struct mlx5_vxlan_port { + struct hlist_node hlist; + atomic_t refcount; + u16 udp_port; +}; + +static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev) +{ + return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4; +} + +static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port) +{ + u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0}; + + MLX5_SET(add_vxlan_udp_dport_in, in, opcode, + MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT); + MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port); + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) +{ + u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0}; + + MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, + MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); + MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port); + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +static struct mlx5_vxlan_port* +mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + + hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) { + if (vxlanp->udp_port == port) + return vxlanp; + } + + return NULL; +} + +struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + + if (!mlx5_vxlan_allowed(vxlan)) + return NULL; + + spin_lock_bh(&vxlan->lock); + vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port); + spin_unlock_bh(&vxlan->lock); + + return vxlanp; +} + +int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + int ret = -ENOSPC; + + vxlanp = mlx5_vxlan_lookup_port(vxlan, port); + if (vxlanp) { + atomic_inc(&vxlanp->refcount); + return 0; + } + + mutex_lock(&vxlan->sync_lock); + if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) { + mlx5_core_info(vxlan->mdev, + "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n", + port, mlx5_vxlan_max_udp_ports(vxlan->mdev)); + ret = -ENOSPC; + goto unlock; + } + + ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port); + if (ret) + goto unlock; + + vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL); + if (!vxlanp) { + ret = -ENOMEM; + goto err_delete_port; + } + + vxlanp->udp_port = port; + atomic_set(&vxlanp->refcount, 1); + + spin_lock_bh(&vxlan->lock); + hash_add(vxlan->htable, &vxlanp->hlist, port); + spin_unlock_bh(&vxlan->lock); + + vxlan->num_ports++; + mutex_unlock(&vxlan->sync_lock); + return 0; + +err_delete_port: + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); + +unlock: + mutex_unlock(&vxlan->sync_lock); + return ret; +} + +int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + bool remove = false; + int ret = 0; + + mutex_lock(&vxlan->sync_lock); + + spin_lock_bh(&vxlan->lock); + vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port); + if (!vxlanp) { + ret = -ENOENT; + goto out_unlock; + } + + if (atomic_dec_and_test(&vxlanp->refcount)) { + hash_del(&vxlanp->hlist); + remove = true; + } + +out_unlock: + spin_unlock_bh(&vxlan->lock); + + if (remove) { + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); + kfree(vxlanp); + vxlan->num_ports--; + } + + mutex_unlock(&vxlan->sync_lock); + + return ret; +} + +struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) +{ + struct mlx5_vxlan *vxlan; + + if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev)) + return ERR_PTR(-ENOTSUPP); + + vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); + if (!vxlan) + return ERR_PTR(-ENOMEM); + + vxlan->mdev = mdev; + mutex_init(&vxlan->sync_lock); + spin_lock_init(&vxlan->lock); + hash_init(vxlan->htable); + + /* Hardware adds 4789 by default */ + mlx5_vxlan_add_port(vxlan, 4789); + + return vxlan; +} + +void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) +{ + struct mlx5_vxlan_port *vxlanp; + struct hlist_node *tmp; + int bkt; + + if (!mlx5_vxlan_allowed(vxlan)) + return; + + /* Lockless since we are the only hash table consumers*/ + hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) { + hash_del(&vxlanp->hlist); + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port); + kfree(vxlanp); + } + + kfree(vxlan); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h index 5ef6ae7d568a..fd874a30c4d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h @@ -33,31 +33,32 @@ #define __MLX5_VXLAN_H__ #include <linux/mlx5/driver.h> -#include "en.h" -struct mlx5e_vxlan { - atomic_t refcount; - u16 udp_port; -}; +struct mlx5_vxlan; +struct mlx5_vxlan_port; -struct mlx5e_vxlan_work { - struct work_struct work; - struct mlx5e_priv *priv; - sa_family_t sa_family; - u16 port; -}; +#ifdef CONFIG_MLX5_CORE_EN -static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev) +static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan) { - return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) && - mlx5_core_is_pf(mdev)); + /* not allowed reason is encoded in vxlan pointer as error, + * on mlx5_vxlan_create + */ + return !IS_ERR_OR_NULL(vxlan); } -void mlx5e_vxlan_init(struct mlx5e_priv *priv); -void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv); +struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev); +void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan); +int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port); +int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port); +struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port); -void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family, - u16 port, int add); -struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port); +#else + +static inline struct mlx5_vxlan* +mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); } +static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; } + +#endif #endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 6ddbb70e95de..03b9c6733eed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -62,6 +62,7 @@ #include "accel/ipsec.h" #include "accel/tls.h" #include "lib/clock.h" +#include "lib/vxlan.h" #include "diag/fw_tracer.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); @@ -961,6 +962,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_clock(dev); + dev->vxlan = mlx5_vxlan_create(dev); + err = mlx5_init_rl_table(dev); if (err) { dev_err(&pdev->dev, "Failed to init rate limiting\n"); @@ -1004,6 +1007,7 @@ err_mpfs_cleanup: err_rl_cleanup: mlx5_cleanup_rl_table(dev); err_tables_cleanup: + mlx5_vxlan_destroy(dev->vxlan); mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); @@ -1024,6 +1028,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_mpfs_cleanup(dev); mlx5_cleanup_rl_table(dev); + mlx5_vxlan_destroy(dev->vxlan); mlx5_cleanup_clock(dev); mlx5_cleanup_reserved_gids(dev); mlx5_cleanup_mkey_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c deleted file mode 100644 index 2f74953e4561..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ /dev/null @@ -1,190 +0,0 @@ -/* - * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/mlx5/driver.h> -#include "mlx5_core.h" -#include "vxlan.h" - -void mlx5e_vxlan_init(struct mlx5e_priv *priv) -{ - struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; - - spin_lock_init(&vxlan_db->lock); - INIT_RADIX_TREE(&vxlan_db->tree, GFP_ATOMIC); -} - -static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port) -{ - u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0}; - - MLX5_SET(add_vxlan_udp_dport_in, in, opcode, - MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT); - MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port); - return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); -} - -static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) -{ - u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0}; - - MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, - MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); - MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port); - return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); -} - -struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) -{ - struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; - struct mlx5e_vxlan *vxlan; - - spin_lock_bh(&vxlan_db->lock); - vxlan = radix_tree_lookup(&vxlan_db->tree, port); - spin_unlock_bh(&vxlan_db->lock); - - return vxlan; -} - -static void mlx5e_vxlan_add_port(struct work_struct *work) -{ - struct mlx5e_vxlan_work *vxlan_work = - container_of(work, struct mlx5e_vxlan_work, work); - struct mlx5e_priv *priv = vxlan_work->priv; - struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; - u16 port = vxlan_work->port; - struct mlx5e_vxlan *vxlan; - int err; - - mutex_lock(&priv->state_lock); - vxlan = mlx5e_vxlan_lookup_port(priv, port); - if (vxlan) { - atomic_inc(&vxlan->refcount); - goto free_work; - } - - if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) - goto free_work; - - vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); - if (!vxlan) - goto err_delete_port; - - vxlan->udp_port = port; - atomic_set(&vxlan->refcount, 1); - - spin_lock_bh(&vxlan_db->lock); - err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan); - spin_unlock_bh(&vxlan_db->lock); - if (err) - goto err_free; - - goto free_work; - -err_free: - kfree(vxlan); -err_delete_port: - mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); -free_work: - mutex_unlock(&priv->state_lock); - kfree(vxlan_work); -} - -static void mlx5e_vxlan_del_port(struct work_struct *work) -{ - struct mlx5e_vxlan_work *vxlan_work = - container_of(work, struct mlx5e_vxlan_work, work); - struct mlx5e_priv *priv = vxlan_work->priv; - struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; - u16 port = vxlan_work->port; - struct mlx5e_vxlan *vxlan; - bool remove = false; - - mutex_lock(&priv->state_lock); - spin_lock_bh(&vxlan_db->lock); - vxlan = radix_tree_lookup(&vxlan_db->tree, port); - if (!vxlan) - goto out_unlock; - - if (atomic_dec_and_test(&vxlan->refcount)) { - radix_tree_delete(&vxlan_db->tree, port); - remove = true; - } - -out_unlock: - spin_unlock_bh(&vxlan_db->lock); - - if (remove) { - mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); - kfree(vxlan); - } - mutex_unlock(&priv->state_lock); - kfree(vxlan_work); -} - -void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family, - u16 port, int add) -{ - struct mlx5e_vxlan_work *vxlan_work; - - vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC); - if (!vxlan_work) - return; - - if (add) - INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_port); - else - INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_port); - - vxlan_work->priv = priv; - vxlan_work->port = port; - vxlan_work->sa_family = sa_family; - queue_work(priv->wq, &vxlan_work->work); -} - -void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) -{ - struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; - struct mlx5e_vxlan *vxlan; - unsigned int port = 0; - - /* Lockless since we are the only radix-tree consumers, wq is disabled */ - while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) { - port = vxlan->udp_port; - radix_tree_delete(&vxlan_db->tree, port); - mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); - kfree(vxlan); - } -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index b97bb72b4db4..86478a6b99c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -113,35 +113,45 @@ err_db_free: return err; } -static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf, - struct mlx5_wq_qp *qp) +static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf, + struct mlx5_wq_qp *qp) { + struct mlx5_frag_buf_ctrl *sq_fbc; struct mlx5_frag_buf *rqb, *sqb; - rqb = &qp->rq.fbc.frag_buf; + rqb = &qp->rq.fbc.frag_buf; *rqb = *buf; rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - rqb->npages = 1 << get_order(rqb->size); + rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE); - sqb = &qp->sq.fbc.frag_buf; - *sqb = *buf; - sqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - sqb->npages = 1 << get_order(sqb->size); + sq_fbc = &qp->sq.fbc; + sqb = &sq_fbc->frag_buf; + *sqb = *buf; + sqb->size = mlx5_wq_cyc_get_byte_size(&qp->sq); + sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE); sqb->frags += rqb->npages; /* first part is for the rq */ + if (sq_fbc->strides_offset) + sqb->frags--; } int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u32 sq_strides_offset; int err; mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, MLX5_GET(qpc, qpc, log_rq_size), &wq->rq.fbc); - mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB), - MLX5_GET(qpc, qpc, log_sq_size), - &wq->sq.fbc); + + sq_strides_offset = + ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB; + + mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), + MLX5_GET(qpc, qpc, log_sq_size), + sq_strides_offset, + &wq->sq.fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq); + mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq); wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 82827a8d3d67..8a291eb36c64 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -78,6 +78,7 @@ config MLXSW_SPECTRUM depends on IPV6 || IPV6=n depends on NET_IPGRE || NET_IPGRE=n depends on IPV6_GRE || IPV6_GRE=n + select GENERIC_ALLOCATOR select PARMAN select MLXFW default m diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 4a1069166119..68fa44a41485 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -18,7 +18,7 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum1_kvdl.o spectrum2_kvdl.o \ spectrum_kvdl.o \ spectrum_acl_tcam.o spectrum_acl_ctcam.o \ - spectrum_acl_atcam.o \ + spectrum_acl_atcam.o spectrum_acl_erp.o \ spectrum1_acl_tcam.o spectrum2_acl_tcam.o \ spectrum_acl.o \ spectrum_flower.o spectrum_cnt.o \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index a4669e79fdf9..66ea256fe560 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -327,12 +327,16 @@ static void mlxsw_afa_resource_add(struct mlxsw_afa_block *block, list_add(&resource->list, &block->resource_list); } +static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource) +{ + list_del(&resource->list); +} + static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block) { struct mlxsw_afa_resource *resource, *tmp; list_for_each_entry_safe(resource, tmp, &block->resource_list, list) { - list_del(&resource->list); resource->destructor(block, resource); } } @@ -565,6 +569,7 @@ static void mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref) { + mlxsw_afa_resource_del(&fwd_entry_ref->resource); mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry); kfree(fwd_entry_ref); } @@ -614,6 +619,7 @@ static void mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_counter *counter) { + mlxsw_afa_resource_del(&counter->resource); block->afa->ops->counter_index_put(block->afa->ops_priv, counter->counter_index); kfree(counter); @@ -661,8 +667,8 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, char *oneact; char *actions; - if (WARN_ON(block->finished)) - return NULL; + if (block->finished) + return ERR_PTR(-EINVAL); if (block->cur_act_index + action_size > block->afa->max_acts_per_set) { struct mlxsw_afa_set *set; @@ -672,7 +678,7 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, */ set = mlxsw_afa_set_create(false); if (!set) - return NULL; + return ERR_PTR(-ENOBUFS); set->prev = block->cur_set; block->cur_act_index = 0; block->cur_set->next = set; @@ -760,9 +766,9 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, MLXSW_AFA_VLAN_CODE, MLXSW_AFA_VLAN_SIZE); - if (!act) { + if (IS_ERR(act)) { NL_SET_ERR_MSG_MOD(extack, "Cannot append vlan_modify action"); - return -ENOBUFS; + return PTR_ERR(act); } mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, MLXSW_AFA_VLAN_CMD_SET_OUTER, vid, @@ -844,8 +850,8 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block) MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0); return 0; @@ -858,8 +864,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id) MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, trap_id); @@ -874,8 +880,8 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, trap_id); @@ -894,6 +900,7 @@ static void mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_mirror *mirror) { + mlxsw_afa_resource_del(&mirror->resource); block->afa->ops->mirror_del(block->afa->ops_priv, mirror->local_in_port, mirror->span_id, @@ -946,8 +953,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0); mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent); @@ -1043,9 +1050,9 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE, MLXSW_AFA_FORWARD_SIZE); - if (!act) { - err = -ENOBUFS; + if (IS_ERR(act)) { NL_SET_ERR_MSG_MOD(extack, "Cannot append forward action"); + err = PTR_ERR(act); goto err_append_action; } mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS, @@ -1100,8 +1107,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block, { char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE, MLXSW_AFA_POLCNT_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES, counter_index); return 0; @@ -1176,9 +1183,9 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_VIRFWD_CODE, MLXSW_AFA_VIRFWD_SIZE); - if (!act) { + if (IS_ERR(act)) { NL_SET_ERR_MSG_MOD(extack, "Cannot append fid_set action"); - return -ENOBUFS; + return PTR_ERR(act); } mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid); return 0; @@ -1248,8 +1255,8 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_MCROUTER_CODE, MLXSW_AFA_MCROUTER_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP, expected_irif, min_mtu, rmid_valid, kvdl_index); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index 5f8485c7640e..9649b4d9349a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -457,7 +457,7 @@ mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst, void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk, struct mlxsw_afk_key_info *key_info, struct mlxsw_afk_element_values *values, - char *key, char *mask) + char *key, char *mask, int block_start, int block_end) { char block_mask[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE]; char block_key[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE]; @@ -465,7 +465,7 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk, enum mlxsw_afk_element element; int block_index, i; - for (i = 0; i < key_info->blocks_count; i++) { + for (i = block_start; i <= block_end; i++) { memset(block_key, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE); memset(block_mask, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE); @@ -482,8 +482,10 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk, values->storage.mask); } - mlxsw_afk->ops->encode_block(block_key, i, key); - mlxsw_afk->ops->encode_block(block_mask, i, mask); + if (key) + mlxsw_afk->ops->encode_block(block_key, i, key); + if (mask) + mlxsw_afk->ops->encode_block(block_mask, i, mask); } } EXPORT_SYMBOL(mlxsw_afk_encode); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index 2ffde915349b..18d9bfed6001 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -259,6 +259,6 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values, void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk, struct mlxsw_afk_key_info *key_info, struct mlxsw_afk_element_values *values, - char *key, char *mask); + char *key, char *mask, int block_start, int block_end); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 596fddfb3850..9f344914c4a5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2466,14 +2466,14 @@ MLXSW_ITEM32(reg, ptce2, priority, 0x04, 0, 24); MLXSW_ITEM_BUF(reg, ptce2, tcam_region_info, 0x10, MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN); -#define MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN 96 +#define MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN 96 /* reg_ptce2_flex_key_blocks * ACL Key. * Access: RW */ MLXSW_ITEM_BUF(reg, ptce2, flex_key_blocks, 0x20, - MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN); + MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN); /* reg_ptce2_mask * mask- in the same size as key. A bit that is set directs the TCAM @@ -2482,7 +2482,7 @@ MLXSW_ITEM_BUF(reg, ptce2, flex_key_blocks, 0x20, * Access: RW */ MLXSW_ITEM_BUF(reg, ptce2, mask, 0x80, - MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN); + MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN); /* reg_ptce2_flex_action_set * ACL action set. @@ -2504,6 +2504,118 @@ static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid, mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info); } +/* PERPT - Policy-Engine ERP Table Register + * ---------------------------------------- + * This register adds and removes eRPs from the eRP table. + */ +#define MLXSW_REG_PERPT_ID 0x3021 +#define MLXSW_REG_PERPT_LEN 0x80 + +MLXSW_REG_DEFINE(perpt, MLXSW_REG_PERPT_ID, MLXSW_REG_PERPT_LEN); + +/* reg_perpt_erpt_bank + * eRP table bank. + * Range 0 .. cap_max_erp_table_banks - 1 + * Access: Index + */ +MLXSW_ITEM32(reg, perpt, erpt_bank, 0x00, 16, 4); + +/* reg_perpt_erpt_index + * Index to eRP table within the eRP bank. + * Range is 0 .. cap_max_erp_table_bank_size - 1 + * Access: Index + */ +MLXSW_ITEM32(reg, perpt, erpt_index, 0x00, 0, 8); + +enum mlxsw_reg_perpt_key_size { + MLXSW_REG_PERPT_KEY_SIZE_2KB, + MLXSW_REG_PERPT_KEY_SIZE_4KB, + MLXSW_REG_PERPT_KEY_SIZE_8KB, + MLXSW_REG_PERPT_KEY_SIZE_12KB, +}; + +/* reg_perpt_key_size + * Access: OP + */ +MLXSW_ITEM32(reg, perpt, key_size, 0x04, 0, 4); + +/* reg_perpt_bf_bypass + * 0 - The eRP is used only if bloom filter state is set for the given + * rule. + * 1 - The eRP is used regardless of bloom filter state. + * The bypass is an OR condition of region_id or eRP. See PERCR.bf_bypass + * Access: RW + */ +MLXSW_ITEM32(reg, perpt, bf_bypass, 0x08, 8, 1); + +/* reg_perpt_erp_id + * eRP ID for use by the rules. + * Access: RW + */ +MLXSW_ITEM32(reg, perpt, erp_id, 0x08, 0, 4); + +/* reg_perpt_erpt_base_bank + * Base eRP table bank, points to head of erp_vector + * Range is 0 .. cap_max_erp_table_banks - 1 + * Access: OP + */ +MLXSW_ITEM32(reg, perpt, erpt_base_bank, 0x0C, 16, 4); + +/* reg_perpt_erpt_base_index + * Base index to eRP table within the eRP bank + * Range is 0 .. cap_max_erp_table_bank_size - 1 + * Access: OP + */ +MLXSW_ITEM32(reg, perpt, erpt_base_index, 0x0C, 0, 8); + +/* reg_perpt_erp_index_in_vector + * eRP index in the vector. + * Access: OP + */ +MLXSW_ITEM32(reg, perpt, erp_index_in_vector, 0x10, 0, 4); + +/* reg_perpt_erp_vector + * eRP vector. + * Access: OP + */ +MLXSW_ITEM_BIT_ARRAY(reg, perpt, erp_vector, 0x14, 4, 1); + +/* reg_perpt_mask + * Mask + * 0 - A-TCAM will ignore the bit in key + * 1 - A-TCAM will compare the bit in key + * Access: RW + */ +MLXSW_ITEM_BUF(reg, perpt, mask, 0x20, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN); + +static inline void mlxsw_reg_perpt_erp_vector_pack(char *payload, + unsigned long *erp_vector, + unsigned long size) +{ + unsigned long bit; + + for_each_set_bit(bit, erp_vector, size) + mlxsw_reg_perpt_erp_vector_set(payload, bit, true); +} + +static inline void +mlxsw_reg_perpt_pack(char *payload, u8 erpt_bank, u8 erpt_index, + enum mlxsw_reg_perpt_key_size key_size, u8 erp_id, + u8 erpt_base_bank, u8 erpt_base_index, u8 erp_index, + char *mask) +{ + MLXSW_REG_ZERO(perpt, payload); + mlxsw_reg_perpt_erpt_bank_set(payload, erpt_bank); + mlxsw_reg_perpt_erpt_index_set(payload, erpt_index); + mlxsw_reg_perpt_key_size_set(payload, key_size); + mlxsw_reg_perpt_bf_bypass_set(payload, true); + mlxsw_reg_perpt_erp_id_set(payload, erp_id); + mlxsw_reg_perpt_erpt_base_bank_set(payload, erpt_base_bank); + mlxsw_reg_perpt_erpt_base_index_set(payload, erpt_base_index); + mlxsw_reg_perpt_erp_index_in_vector_set(payload, erp_index); + mlxsw_reg_perpt_mask_memcpy_to(payload, mask); +} + /* PERAR - Policy-Engine Region Association Register * ------------------------------------------------- * This register associates a hw region for region_id's. Changing on the fly @@ -2545,6 +2657,164 @@ static inline void mlxsw_reg_perar_pack(char *payload, u16 region_id, mlxsw_reg_perar_hw_region_set(payload, hw_region); } +/* PTCE-V3 - Policy-Engine TCAM Entry Register Version 3 + * ----------------------------------------------------- + * This register is a new version of PTCE-V2 in order to support the + * A-TCAM. This register is not supported by SwitchX/-2 and Spectrum. + */ +#define MLXSW_REG_PTCE3_ID 0x3027 +#define MLXSW_REG_PTCE3_LEN 0xF0 + +MLXSW_REG_DEFINE(ptce3, MLXSW_REG_PTCE3_ID, MLXSW_REG_PTCE3_LEN); + +/* reg_ptce3_v + * Valid. + * Access: RW + */ +MLXSW_ITEM32(reg, ptce3, v, 0x00, 31, 1); + +enum mlxsw_reg_ptce3_op { + /* Write operation. Used to write a new entry to the table. + * All R/W fields are relevant for new entry. Activity bit is set + * for new entries. Write with v = 0 will delete the entry. Must + * not be used if an entry exists. + */ + MLXSW_REG_PTCE3_OP_WRITE_WRITE = 0, + /* Update operation */ + MLXSW_REG_PTCE3_OP_WRITE_UPDATE = 1, + /* Read operation */ + MLXSW_REG_PTCE3_OP_QUERY_READ = 0, +}; + +/* reg_ptce3_op + * Access: OP + */ +MLXSW_ITEM32(reg, ptce3, op, 0x00, 20, 3); + +/* reg_ptce3_priority + * Priority of the rule. Higher values win. + * For Spectrum-2 range is 1..cap_kvd_size - 1 + * Note: Priority does not have to be unique per rule. + * Access: RW + */ +MLXSW_ITEM32(reg, ptce3, priority, 0x04, 0, 24); + +/* reg_ptce3_tcam_region_info + * Opaque object that represents the TCAM region. + * Access: Index + */ +MLXSW_ITEM_BUF(reg, ptce3, tcam_region_info, 0x10, + MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN); + +/* reg_ptce3_flex2_key_blocks + * ACL key. The key must be masked according to eRP (if exists) or + * according to master mask. + * Access: Index + */ +MLXSW_ITEM_BUF(reg, ptce3, flex2_key_blocks, 0x20, + MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN); + +/* reg_ptce3_erp_id + * eRP ID. + * Access: Index + */ +MLXSW_ITEM32(reg, ptce3, erp_id, 0x80, 0, 4); + +/* reg_ptce3_delta_start + * Start point of delta_value and delta_mask, in bits. Must not exceed + * num_key_blocks * 36 - 8. Reserved when delta_mask = 0. + * Access: Index + */ +MLXSW_ITEM32(reg, ptce3, delta_start, 0x84, 0, 10); + +/* reg_ptce3_delta_mask + * Delta mask. + * 0 - Ignore relevant bit in delta_value + * 1 - Compare relevant bit in delta_value + * Delta mask must not be set for reserved fields in the key blocks. + * Note: No delta when no eRPs. Thus, for regions with + * PERERP.erpt_pointer_valid = 0 the delta mask must be 0. + * Access: Index + */ +MLXSW_ITEM32(reg, ptce3, delta_mask, 0x88, 16, 8); + +/* reg_ptce3_delta_value + * Delta value. + * Bits which are masked by delta_mask must be 0. + * Access: Index + */ +MLXSW_ITEM32(reg, ptce3, delta_value, 0x88, 0, 8); + +/* reg_ptce3_prune_vector + * Pruning vector relative to the PERPT.erp_id. + * Used for reducing lookups. + * 0 - NEED: Do a lookup using the eRP. + * 1 - PRUNE: Do not perform a lookup using the eRP. + * Maybe be modified by PEAPBL and PEAPBM. + * Note: In Spectrum-2, a region of 8 key blocks must be set to either + * all 1's or all 0's. + * Access: RW + */ +MLXSW_ITEM_BIT_ARRAY(reg, ptce3, prune_vector, 0x90, 4, 1); + +/* reg_ptce3_prune_ctcam + * Pruning on C-TCAM. Used for reducing lookups. + * 0 - NEED: Do a lookup in the C-TCAM. + * 1 - PRUNE: Do not perform a lookup in the C-TCAM. + * Access: RW + */ +MLXSW_ITEM32(reg, ptce3, prune_ctcam, 0x94, 31, 1); + +/* reg_ptce3_large_exists + * Large entry key ID exists. + * Within the region: + * 0 - SINGLE: The large_entry_key_id is not currently in use. + * For rule insert: The MSB of the key (blocks 6..11) will be added. + * For rule delete: The MSB of the key will be removed. + * 1 - NON_SINGLE: The large_entry_key_id is currently in use. + * For rule insert: The MSB of the key (blocks 6..11) will not be added. + * For rule delete: The MSB of the key will not be removed. + * Access: WO + */ +MLXSW_ITEM32(reg, ptce3, large_exists, 0x98, 31, 1); + +/* reg_ptce3_large_entry_key_id + * Large entry key ID. + * A key for 12 key blocks rules. Reserved when region has less than 12 key + * blocks. Must be different for different keys which have the same common + * 6 key blocks (MSB, blocks 6..11) key within a region. + * Range is 0..cap_max_pe_large_key_id - 1 + * Access: RW + */ +MLXSW_ITEM32(reg, ptce3, large_entry_key_id, 0x98, 0, 24); + +/* reg_ptce3_action_pointer + * Pointer to action. + * Range is 0..cap_max_kvd_action_sets - 1 + * Access: RW + */ +MLXSW_ITEM32(reg, ptce3, action_pointer, 0xA0, 0, 24); + +static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid, + enum mlxsw_reg_ptce3_op op, + u32 priority, + const char *tcam_region_info, + const char *key, u8 erp_id, + bool large_exists, u32 lkey_id, + u32 action_pointer) +{ + MLXSW_REG_ZERO(ptce3, payload); + mlxsw_reg_ptce3_v_set(payload, valid); + mlxsw_reg_ptce3_op_set(payload, op); + mlxsw_reg_ptce3_priority_set(payload, priority); + mlxsw_reg_ptce3_tcam_region_info_memcpy_to(payload, tcam_region_info); + mlxsw_reg_ptce3_flex2_key_blocks_memcpy_to(payload, key); + mlxsw_reg_ptce3_erp_id_set(payload, erp_id); + mlxsw_reg_ptce3_large_exists_set(payload, large_exists); + mlxsw_reg_ptce3_large_entry_key_id_set(payload, lkey_id); + mlxsw_reg_ptce3_action_pointer_set(payload, action_pointer); +} + /* PERCR - Policy-Engine Region Configuration Register * --------------------------------------------------- * This register configures the region parameters. The region_id must be @@ -2598,7 +2868,6 @@ static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id) mlxsw_reg_percr_atcam_ignore_prune_set(payload, false); mlxsw_reg_percr_ctcam_ignore_prune_set(payload, false); mlxsw_reg_percr_bf_bypass_set(payload, true); - memset(payload + 0x20, 0xff, 96); } /* PERERP - Policy-Engine Region eRP Register @@ -2663,12 +2932,28 @@ MLXSW_ITEM_BIT_ARRAY(reg, pererp, erpt_vector, 0x14, 4, 1); */ MLXSW_ITEM32(reg, pererp, master_rp_id, 0x18, 0, 4); -static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id) +static inline void mlxsw_reg_pererp_erp_vector_pack(char *payload, + unsigned long *erp_vector, + unsigned long size) +{ + unsigned long bit; + + for_each_set_bit(bit, erp_vector, size) + mlxsw_reg_pererp_erpt_vector_set(payload, bit, true); +} + +static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id, + bool ctcam_le, bool erpt_pointer_valid, + u8 erpt_bank_pointer, u8 erpt_pointer, + u8 master_rp_id) { MLXSW_REG_ZERO(pererp, payload); mlxsw_reg_pererp_region_id_set(payload, region_id); - mlxsw_reg_pererp_ctcam_le_set(payload, true); - mlxsw_reg_pererp_erpt_pointer_valid_set(payload, true); + mlxsw_reg_pererp_ctcam_le_set(payload, ctcam_le); + mlxsw_reg_pererp_erpt_pointer_valid_set(payload, erpt_pointer_valid); + mlxsw_reg_pererp_erpt_bank_pointer_set(payload, erpt_bank_pointer); + mlxsw_reg_pererp_erpt_pointer_set(payload, erpt_pointer); + mlxsw_reg_pererp_master_rp_id_set(payload, master_rp_id); } /* IEDR - Infrastructure Entry Delete Register @@ -2732,6 +3017,44 @@ static inline void mlxsw_reg_iedr_rec_pack(char *payload, int rec_index, mlxsw_reg_iedr_rec_index_start_set(payload, rec_index, rec_index_start); } +/* QPTS - QoS Priority Trust State Register + * ---------------------------------------- + * This register controls the port policy to calculate the switch priority and + * packet color based on incoming packet fields. + */ +#define MLXSW_REG_QPTS_ID 0x4002 +#define MLXSW_REG_QPTS_LEN 0x8 + +MLXSW_REG_DEFINE(qpts, MLXSW_REG_QPTS_ID, MLXSW_REG_QPTS_LEN); + +/* reg_qpts_local_port + * Local port number. + * Access: Index + * + * Note: CPU port is supported. + */ +MLXSW_ITEM32(reg, qpts, local_port, 0x00, 16, 8); + +enum mlxsw_reg_qpts_trust_state { + MLXSW_REG_QPTS_TRUST_STATE_PCP = 1, + MLXSW_REG_QPTS_TRUST_STATE_DSCP = 2, /* For MPLS, trust EXP. */ +}; + +/* reg_qpts_trust_state + * Trust state for a given port. + * Access: RW + */ +MLXSW_ITEM32(reg, qpts, trust_state, 0x04, 0, 3); + +static inline void mlxsw_reg_qpts_pack(char *payload, u8 local_port, + enum mlxsw_reg_qpts_trust_state ts) +{ + MLXSW_REG_ZERO(qpts, payload); + + mlxsw_reg_qpts_local_port_set(payload, local_port); + mlxsw_reg_qpts_trust_state_set(payload, ts); +} + /* QPCR - QoS Policer Configuration Register * ----------------------------------------- * The QPCR register is used to create policers - that limit @@ -3044,6 +3367,219 @@ static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port, mlxsw_reg_qeec_next_element_index_set(payload, next_index); } +/* QRWE - QoS ReWrite Enable + * ------------------------- + * This register configures the rewrite enable per receive port. + */ +#define MLXSW_REG_QRWE_ID 0x400F +#define MLXSW_REG_QRWE_LEN 0x08 + +MLXSW_REG_DEFINE(qrwe, MLXSW_REG_QRWE_ID, MLXSW_REG_QRWE_LEN); + +/* reg_qrwe_local_port + * Local port number. + * Access: Index + * + * Note: CPU port is supported. No support for router port. + */ +MLXSW_ITEM32(reg, qrwe, local_port, 0x00, 16, 8); + +/* reg_qrwe_dscp + * Whether to enable DSCP rewrite (default is 0, don't rewrite). + * Access: RW + */ +MLXSW_ITEM32(reg, qrwe, dscp, 0x04, 1, 1); + +/* reg_qrwe_pcp + * Whether to enable PCP and DEI rewrite (default is 0, don't rewrite). + * Access: RW + */ +MLXSW_ITEM32(reg, qrwe, pcp, 0x04, 0, 1); + +static inline void mlxsw_reg_qrwe_pack(char *payload, u8 local_port, + bool rewrite_pcp, bool rewrite_dscp) +{ + MLXSW_REG_ZERO(qrwe, payload); + mlxsw_reg_qrwe_local_port_set(payload, local_port); + mlxsw_reg_qrwe_pcp_set(payload, rewrite_pcp); + mlxsw_reg_qrwe_dscp_set(payload, rewrite_dscp); +} + +/* QPDSM - QoS Priority to DSCP Mapping + * ------------------------------------ + * QoS Priority to DSCP Mapping Register + */ +#define MLXSW_REG_QPDSM_ID 0x4011 +#define MLXSW_REG_QPDSM_BASE_LEN 0x04 /* base length, without records */ +#define MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN 0x4 /* record length */ +#define MLXSW_REG_QPDSM_PRIO_ENTRY_REC_MAX_COUNT 16 +#define MLXSW_REG_QPDSM_LEN (MLXSW_REG_QPDSM_BASE_LEN + \ + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN * \ + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_MAX_COUNT) + +MLXSW_REG_DEFINE(qpdsm, MLXSW_REG_QPDSM_ID, MLXSW_REG_QPDSM_LEN); + +/* reg_qpdsm_local_port + * Local Port. Supported for data packets from CPU port. + * Access: Index + */ +MLXSW_ITEM32(reg, qpdsm, local_port, 0x00, 16, 8); + +/* reg_qpdsm_prio_entry_color0_e + * Enable update of the entry for color 0 and a given port. + * Access: WO + */ +MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color0_e, + MLXSW_REG_QPDSM_BASE_LEN, 31, 1, + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false); + +/* reg_qpdsm_prio_entry_color0_dscp + * DSCP field in the outer label of the packet for color 0 and a given port. + * Reserved when e=0. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color0_dscp, + MLXSW_REG_QPDSM_BASE_LEN, 24, 6, + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false); + +/* reg_qpdsm_prio_entry_color1_e + * Enable update of the entry for color 1 and a given port. + * Access: WO + */ +MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color1_e, + MLXSW_REG_QPDSM_BASE_LEN, 23, 1, + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false); + +/* reg_qpdsm_prio_entry_color1_dscp + * DSCP field in the outer label of the packet for color 1 and a given port. + * Reserved when e=0. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color1_dscp, + MLXSW_REG_QPDSM_BASE_LEN, 16, 6, + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false); + +/* reg_qpdsm_prio_entry_color2_e + * Enable update of the entry for color 2 and a given port. + * Access: WO + */ +MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color2_e, + MLXSW_REG_QPDSM_BASE_LEN, 15, 1, + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false); + +/* reg_qpdsm_prio_entry_color2_dscp + * DSCP field in the outer label of the packet for color 2 and a given port. + * Reserved when e=0. + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color2_dscp, + MLXSW_REG_QPDSM_BASE_LEN, 8, 6, + MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false); + +static inline void mlxsw_reg_qpdsm_pack(char *payload, u8 local_port) +{ + MLXSW_REG_ZERO(qpdsm, payload); + mlxsw_reg_qpdsm_local_port_set(payload, local_port); +} + +static inline void +mlxsw_reg_qpdsm_prio_pack(char *payload, unsigned short prio, u8 dscp) +{ + mlxsw_reg_qpdsm_prio_entry_color0_e_set(payload, prio, 1); + mlxsw_reg_qpdsm_prio_entry_color0_dscp_set(payload, prio, dscp); + mlxsw_reg_qpdsm_prio_entry_color1_e_set(payload, prio, 1); + mlxsw_reg_qpdsm_prio_entry_color1_dscp_set(payload, prio, dscp); + mlxsw_reg_qpdsm_prio_entry_color2_e_set(payload, prio, 1); + mlxsw_reg_qpdsm_prio_entry_color2_dscp_set(payload, prio, dscp); +} + +/* QPDPM - QoS Port DSCP to Priority Mapping Register + * -------------------------------------------------- + * This register controls the mapping from DSCP field to + * Switch Priority for IP packets. + */ +#define MLXSW_REG_QPDPM_ID 0x4013 +#define MLXSW_REG_QPDPM_BASE_LEN 0x4 /* base length, without records */ +#define MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN 0x2 /* record length */ +#define MLXSW_REG_QPDPM_DSCP_ENTRY_REC_MAX_COUNT 64 +#define MLXSW_REG_QPDPM_LEN (MLXSW_REG_QPDPM_BASE_LEN + \ + MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN * \ + MLXSW_REG_QPDPM_DSCP_ENTRY_REC_MAX_COUNT) + +MLXSW_REG_DEFINE(qpdpm, MLXSW_REG_QPDPM_ID, MLXSW_REG_QPDPM_LEN); + +/* reg_qpdpm_local_port + * Local Port. Supported for data packets from CPU port. + * Access: Index + */ +MLXSW_ITEM32(reg, qpdpm, local_port, 0x00, 16, 8); + +/* reg_qpdpm_dscp_e + * Enable update of the specific entry. When cleared, the switch_prio and color + * fields are ignored and the previous switch_prio and color values are + * preserved. + * Access: WO + */ +MLXSW_ITEM16_INDEXED(reg, qpdpm, dscp_entry_e, MLXSW_REG_QPDPM_BASE_LEN, 15, 1, + MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN, 0x00, false); + +/* reg_qpdpm_dscp_prio + * The new Switch Priority value for the relevant DSCP value. + * Access: RW + */ +MLXSW_ITEM16_INDEXED(reg, qpdpm, dscp_entry_prio, + MLXSW_REG_QPDPM_BASE_LEN, 0, 4, + MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN, 0x00, false); + +static inline void mlxsw_reg_qpdpm_pack(char *payload, u8 local_port) +{ + MLXSW_REG_ZERO(qpdpm, payload); + mlxsw_reg_qpdpm_local_port_set(payload, local_port); +} + +static inline void +mlxsw_reg_qpdpm_dscp_pack(char *payload, unsigned short dscp, u8 prio) +{ + mlxsw_reg_qpdpm_dscp_entry_e_set(payload, dscp, 1); + mlxsw_reg_qpdpm_dscp_entry_prio_set(payload, dscp, prio); +} + +/* QTCTM - QoS Switch Traffic Class Table is Multicast-Aware Register + * ------------------------------------------------------------------ + * This register configures if the Switch Priority to Traffic Class mapping is + * based on Multicast packet indication. If so, then multicast packets will get + * a Traffic Class that is plus (cap_max_tclass_data/2) the value configured by + * QTCT. + * By default, Switch Priority to Traffic Class mapping is not based on + * Multicast packet indication. + */ +#define MLXSW_REG_QTCTM_ID 0x401A +#define MLXSW_REG_QTCTM_LEN 0x08 + +MLXSW_REG_DEFINE(qtctm, MLXSW_REG_QTCTM_ID, MLXSW_REG_QTCTM_LEN); + +/* reg_qtctm_local_port + * Local port number. + * No support for CPU port. + * Access: Index + */ +MLXSW_ITEM32(reg, qtctm, local_port, 0x00, 16, 8); + +/* reg_qtctm_mc + * Multicast Mode + * Whether Switch Priority to Traffic Class mapping is based on Multicast packet + * indication (default is 0, not based on Multicast packet indication). + */ +MLXSW_ITEM32(reg, qtctm, mc, 0x04, 0, 1); + +static inline void +mlxsw_reg_qtctm_pack(char *payload, u8 local_port, bool mc) +{ + MLXSW_REG_ZERO(qtctm, payload); + mlxsw_reg_qtctm_local_port_set(payload, local_port); + mlxsw_reg_qtctm_mc_set(payload, mc); +} + /* PMLP - Ports Module to Local Port Register * ------------------------------------------ * Configures the assignment of modules to local ports. @@ -8248,13 +8784,20 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(prcr), MLXSW_REG(pefa), MLXSW_REG(ptce2), + MLXSW_REG(perpt), MLXSW_REG(perar), + MLXSW_REG(ptce3), MLXSW_REG(percr), MLXSW_REG(pererp), MLXSW_REG(iedr), + MLXSW_REG(qpts), MLXSW_REG(qpcr), MLXSW_REG(qtct), MLXSW_REG(qeec), + MLXSW_REG(qrwe), + MLXSW_REG(qpdsm), + MLXSW_REG(qpdpm), + MLXSW_REG(qtctm), MLXSW_REG(pmlp), MLXSW_REG(pmtu), MLXSW_REG(ptys), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index f672a7b71de7..bf650f2cd5af 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -65,6 +65,13 @@ enum mlxsw_res_id { MLXSW_RES_ID_ACL_FLEX_KEYS, MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE, MLXSW_RES_ID_ACL_ACTIONS_PER_SET, + MLXSW_RES_ID_ACL_MAX_ERPT_BANKS, + MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE, + MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID, + MLXSW_RES_ID_ACL_ERPT_ENTRIES_2KB, + MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB, + MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB, + MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB, MLXSW_RES_ID_MAX_CPU_POLICERS, MLXSW_RES_ID_MAX_VRS, MLXSW_RES_ID_MAX_RIFS, @@ -108,6 +115,13 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910, [MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911, [MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912, + [MLXSW_RES_ID_ACL_MAX_ERPT_BANKS] = 0x2940, + [MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE] = 0x2941, + [MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID] = 0x2942, + [MLXSW_RES_ID_ACL_ERPT_ENTRIES_2KB] = 0x2950, + [MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB] = 0x2951, + [MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB] = 0x2952, + [MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB] = 0x2953, [MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13, [MLXSW_RES_ID_MAX_VRS] = 0x2C01, [MLXSW_RES_ID_MAX_RIFS] = 0x2C02, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 039228525fb1..028ecc9aa5f1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2793,9 +2793,16 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) false, 0); if (err) return err; + + err = mlxsw_sp_port_ets_set(mlxsw_sp_port, + MLXSW_REG_QEEC_HIERARCY_TC, + i + 8, i, + false, 0); + if (err) + return err; } - /* Make sure the max shaper is disabled in all hierarcies that + /* Make sure the max shaper is disabled in all hierarchies that * support it. */ err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, @@ -2830,6 +2837,16 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } +static int mlxsw_sp_port_tc_mc_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool enable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char qtctm_pl[MLXSW_REG_QTCTM_LEN]; + + mlxsw_reg_qtctm_pack(qtctm_pl, mlxsw_sp_port->local_port, enable); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qtctm), qtctm_pl); +} + static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, bool split, u8 module, u8 width, u8 lane) { @@ -2958,6 +2975,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_ets_init; } + err = mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, true); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to initialize TC MC mode\n", + mlxsw_sp_port->local_port); + goto err_port_tc_mc_mode; + } + /* ETS and buffers must be initialized before DCB. */ err = mlxsw_sp_port_dcb_init(mlxsw_sp_port); if (err) { @@ -3014,6 +3038,8 @@ err_port_qdiscs_init: err_port_fids_init: mlxsw_sp_port_dcb_fini(mlxsw_sp_port); err_port_dcb_init: + mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false); +err_port_tc_mc_mode: err_port_ets_init: err_port_buffers_init: err_port_admin_status_set: @@ -3048,6 +3074,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port); mlxsw_sp_port_fids_fini(mlxsw_sp_port); mlxsw_sp_port_dcb_fini(mlxsw_sp_port); + mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false); mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); mlxsw_sp_port_module_unmap(mlxsw_sp_port); kfree(mlxsw_sp_port->sample); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 589c63daf085..13eca1a79d52 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum.h - * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> @@ -54,6 +54,7 @@ #include "core.h" #include "core_acl_flex_keys.h" #include "core_acl_flex_actions.h" +#include "reg.h" #define MLXSW_SP_FID_8021D_MAX 1024 @@ -243,6 +244,7 @@ struct mlxsw_sp_port { struct ieee_ets *ets; struct ieee_maxrate *maxrate; struct ieee_pfc *pfc; + enum mlxsw_reg_qpts_trust_state trust_state; } dcb; struct { u8 module; @@ -628,6 +630,7 @@ struct mlxsw_sp_acl_tcam_ops { void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv); size_t region_priv_size; int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv, + void *tcam_priv, struct mlxsw_sp_acl_tcam_region *region); void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv); int (*region_associate)(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c index d339ec43d79c..5c8956573632 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c @@ -58,6 +58,26 @@ struct mlxsw_sp1_acl_tcam_entry { struct mlxsw_sp_acl_ctcam_entry centry; }; +static int +mlxsw_sp1_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry, + const char *mask) +{ + return 0; +} + +static void +mlxsw_sp1_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry) +{ +} + +static const struct mlxsw_sp_acl_ctcam_region_ops +mlxsw_sp1_acl_ctcam_region_ops = { + .entry_insert = mlxsw_sp1_acl_ctcam_region_entry_insert, + .entry_remove = mlxsw_sp1_acl_ctcam_region_entry_remove, +}; + static int mlxsw_sp1_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, struct mlxsw_sp_acl_tcam *tcam) { @@ -122,13 +142,15 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, + void *tcam_priv, struct mlxsw_sp_acl_tcam_region *_region) { struct mlxsw_sp1_acl_tcam_region *region = region_priv; int err; err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, ®ion->cregion, - _region); + _region, + &mlxsw_sp1_acl_ctcam_region_ops); if (err) return err; err = mlxsw_sp1_acl_ctcam_region_catchall_add(mlxsw_sp, region); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c index d7f1fb35ea2a..22c876496379 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c @@ -39,23 +39,64 @@ #include "core_acl_flex_actions.h" struct mlxsw_sp2_acl_tcam { + struct mlxsw_sp_acl_atcam atcam; u32 kvdl_index; unsigned int kvdl_count; }; struct mlxsw_sp2_acl_tcam_region { - struct mlxsw_sp_acl_ctcam_region cregion; + struct mlxsw_sp_acl_atcam_region aregion; + struct mlxsw_sp_acl_tcam_region *region; }; struct mlxsw_sp2_acl_tcam_chunk { - struct mlxsw_sp_acl_ctcam_chunk cchunk; + struct mlxsw_sp_acl_atcam_chunk achunk; }; struct mlxsw_sp2_acl_tcam_entry { - struct mlxsw_sp_acl_ctcam_entry centry; + struct mlxsw_sp_acl_atcam_entry aentry; struct mlxsw_afa_block *act_block; }; +static int +mlxsw_sp2_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry, + const char *mask) +{ + struct mlxsw_sp_acl_atcam_region *aregion; + struct mlxsw_sp_acl_atcam_entry *aentry; + struct mlxsw_sp_acl_erp *erp; + + aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion); + aentry = mlxsw_sp_acl_tcam_centry_aentry(centry); + + erp = mlxsw_sp_acl_erp_get(aregion, mask, true); + if (IS_ERR(erp)) + return PTR_ERR(erp); + aentry->erp = erp; + + return 0; +} + +static void +mlxsw_sp2_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry) +{ + struct mlxsw_sp_acl_atcam_region *aregion; + struct mlxsw_sp_acl_atcam_entry *aentry; + + aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion); + aentry = mlxsw_sp_acl_tcam_centry_aentry(centry); + + mlxsw_sp_acl_erp_put(aregion, aentry->erp); +} + +static const struct mlxsw_sp_acl_ctcam_region_ops +mlxsw_sp2_acl_ctcam_region_ops = { + .entry_insert = mlxsw_sp2_acl_ctcam_region_entry_insert, + .entry_remove = mlxsw_sp2_acl_ctcam_region_entry_remove, +}; + static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, struct mlxsw_sp_acl_tcam *_tcam) { @@ -99,9 +140,14 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, if (err) goto err_pgcr_write; + err = mlxsw_sp_acl_atcam_init(mlxsw_sp, &tcam->atcam); + if (err) + goto err_atcam_init; + mlxsw_afa_block_destroy(afa_block); return 0; +err_atcam_init: err_pgcr_write: err_pefa_write: err_afa_block_continue: @@ -116,22 +162,24 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv) { struct mlxsw_sp2_acl_tcam *tcam = priv; + mlxsw_sp_acl_atcam_fini(mlxsw_sp, &tcam->atcam); mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET, tcam->kvdl_count, tcam->kvdl_index); } static int mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, + void *tcam_priv, struct mlxsw_sp_acl_tcam_region *_region) { struct mlxsw_sp2_acl_tcam_region *region = region_priv; - int err; + struct mlxsw_sp2_acl_tcam *tcam = tcam_priv; - err = mlxsw_sp_acl_atcam_region_init(mlxsw_sp, _region); - if (err) - return err; - return mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, ®ion->cregion, - _region); + region->region = _region; + + return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam, + ®ion->aregion, _region, + &mlxsw_sp2_acl_ctcam_region_ops); } static void @@ -139,7 +187,7 @@ mlxsw_sp2_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv) { struct mlxsw_sp2_acl_tcam_region *region = region_priv; - mlxsw_sp_acl_ctcam_region_fini(®ion->cregion); + mlxsw_sp_acl_atcam_region_fini(®ion->aregion); } static int @@ -155,7 +203,7 @@ static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv, struct mlxsw_sp2_acl_tcam_region *region = region_priv; struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv; - mlxsw_sp_acl_ctcam_chunk_init(®ion->cregion, &chunk->cchunk, + mlxsw_sp_acl_atcam_chunk_init(®ion->aregion, &chunk->achunk, priority); } @@ -163,7 +211,7 @@ static void mlxsw_sp2_acl_tcam_chunk_fini(void *chunk_priv) { struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv; - mlxsw_sp_acl_ctcam_chunk_fini(&chunk->cchunk); + mlxsw_sp_acl_atcam_chunk_fini(&chunk->achunk); } static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp, @@ -176,9 +224,9 @@ static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv; entry->act_block = rulei->act_block; - return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, ®ion->cregion, - &chunk->cchunk, &entry->centry, - rulei, true); + return mlxsw_sp_acl_atcam_entry_add(mlxsw_sp, ®ion->aregion, + &chunk->achunk, &entry->aentry, + rulei); } static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp, @@ -189,8 +237,8 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv; struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv; - mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, ®ion->cregion, - &chunk->cchunk, &entry->centry); + mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, ®ion->aregion, &chunk->achunk, + &entry->aentry); } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c index b1b3b0e0c00e..3a05e0b3f730 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c @@ -34,12 +34,275 @@ */ #include <linux/kernel.h> +#include <linux/err.h> #include <linux/errno.h> +#include <linux/gfp.h> +#include <linux/refcount.h> +#include <linux/rhashtable.h> #include "reg.h" #include "core.h" #include "spectrum.h" #include "spectrum_acl_tcam.h" +#include "core_acl_flex_keys.h" + +#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START 6 +#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END 11 + +struct mlxsw_sp_acl_atcam_lkey_id_ht_key { + char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* MSB blocks */ + u8 erp_id; +}; + +struct mlxsw_sp_acl_atcam_lkey_id { + struct rhash_head ht_node; + struct mlxsw_sp_acl_atcam_lkey_id_ht_key ht_key; + refcount_t refcnt; + u32 id; +}; + +struct mlxsw_sp_acl_atcam_region_ops { + int (*init)(struct mlxsw_sp_acl_atcam_region *aregion); + void (*fini)(struct mlxsw_sp_acl_atcam_region *aregion); + struct mlxsw_sp_acl_atcam_lkey_id * + (*lkey_id_get)(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_rule_info *rulei, u8 erp_id); + void (*lkey_id_put)(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id); +}; + +struct mlxsw_sp_acl_atcam_region_generic { + struct mlxsw_sp_acl_atcam_lkey_id dummy_lkey_id; +}; + +struct mlxsw_sp_acl_atcam_region_12kb { + struct rhashtable lkey_ht; + unsigned int max_lkey_id; + unsigned long *used_lkey_id; +}; + +static const struct rhashtable_params mlxsw_sp_acl_atcam_lkey_id_ht_params = { + .key_len = sizeof(struct mlxsw_sp_acl_atcam_lkey_id_ht_key), + .key_offset = offsetof(struct mlxsw_sp_acl_atcam_lkey_id, ht_key), + .head_offset = offsetof(struct mlxsw_sp_acl_atcam_lkey_id, ht_node), +}; + +static const struct rhashtable_params mlxsw_sp_acl_atcam_entries_ht_params = { + .key_len = sizeof(struct mlxsw_sp_acl_atcam_entry_ht_key), + .key_offset = offsetof(struct mlxsw_sp_acl_atcam_entry, ht_key), + .head_offset = offsetof(struct mlxsw_sp_acl_atcam_entry, ht_node), +}; + +static bool +mlxsw_sp_acl_atcam_is_centry(const struct mlxsw_sp_acl_atcam_entry *aentry) +{ + return mlxsw_sp_acl_erp_is_ctcam_erp(aentry->erp); +} + +static int +mlxsw_sp_acl_atcam_region_generic_init(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp_acl_atcam_region_generic *region_generic; + + region_generic = kzalloc(sizeof(*region_generic), GFP_KERNEL); + if (!region_generic) + return -ENOMEM; + + refcount_set(®ion_generic->dummy_lkey_id.refcnt, 1); + aregion->priv = region_generic; + + return 0; +} + +static void +mlxsw_sp_acl_atcam_region_generic_fini(struct mlxsw_sp_acl_atcam_region *aregion) +{ + kfree(aregion->priv); +} + +static struct mlxsw_sp_acl_atcam_lkey_id * +mlxsw_sp_acl_atcam_generic_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_rule_info *rulei, + u8 erp_id) +{ + struct mlxsw_sp_acl_atcam_region_generic *region_generic; + + region_generic = aregion->priv; + return ®ion_generic->dummy_lkey_id; +} + +static void +mlxsw_sp_acl_atcam_generic_lkey_id_put(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id) +{ +} + +static const struct mlxsw_sp_acl_atcam_region_ops +mlxsw_sp_acl_atcam_region_generic_ops = { + .init = mlxsw_sp_acl_atcam_region_generic_init, + .fini = mlxsw_sp_acl_atcam_region_generic_fini, + .lkey_id_get = mlxsw_sp_acl_atcam_generic_lkey_id_get, + .lkey_id_put = mlxsw_sp_acl_atcam_generic_lkey_id_put, +}; + +static int +mlxsw_sp_acl_atcam_region_12kb_init(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp; + struct mlxsw_sp_acl_atcam_region_12kb *region_12kb; + size_t alloc_size; + u64 max_lkey_id; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_LARGE_KEY_ID)) + return -EIO; + + max_lkey_id = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_LARGE_KEY_ID); + region_12kb = kzalloc(sizeof(*region_12kb), GFP_KERNEL); + if (!region_12kb) + return -ENOMEM; + + alloc_size = BITS_TO_LONGS(max_lkey_id) * sizeof(unsigned long); + region_12kb->used_lkey_id = kzalloc(alloc_size, GFP_KERNEL); + if (!region_12kb->used_lkey_id) { + err = -ENOMEM; + goto err_used_lkey_id_alloc; + } + + err = rhashtable_init(®ion_12kb->lkey_ht, + &mlxsw_sp_acl_atcam_lkey_id_ht_params); + if (err) + goto err_rhashtable_init; + + region_12kb->max_lkey_id = max_lkey_id; + aregion->priv = region_12kb; + + return 0; + +err_rhashtable_init: + kfree(region_12kb->used_lkey_id); +err_used_lkey_id_alloc: + kfree(region_12kb); + return err; +} + +static void +mlxsw_sp_acl_atcam_region_12kb_fini(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv; + + rhashtable_destroy(®ion_12kb->lkey_ht); + kfree(region_12kb->used_lkey_id); + kfree(region_12kb); +} + +static struct mlxsw_sp_acl_atcam_lkey_id * +mlxsw_sp_acl_atcam_lkey_id_create(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_lkey_id_ht_key *ht_key) +{ + struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv; + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id; + u32 id; + int err; + + id = find_first_zero_bit(region_12kb->used_lkey_id, + region_12kb->max_lkey_id); + if (id < region_12kb->max_lkey_id) + __set_bit(id, region_12kb->used_lkey_id); + else + return ERR_PTR(-ENOBUFS); + + lkey_id = kzalloc(sizeof(*lkey_id), GFP_KERNEL); + if (!lkey_id) { + err = -ENOMEM; + goto err_lkey_id_alloc; + } + + lkey_id->id = id; + memcpy(&lkey_id->ht_key, ht_key, sizeof(*ht_key)); + refcount_set(&lkey_id->refcnt, 1); + + err = rhashtable_insert_fast(®ion_12kb->lkey_ht, + &lkey_id->ht_node, + mlxsw_sp_acl_atcam_lkey_id_ht_params); + if (err) + goto err_rhashtable_insert; + + return lkey_id; + +err_rhashtable_insert: + kfree(lkey_id); +err_lkey_id_alloc: + __clear_bit(id, region_12kb->used_lkey_id); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_atcam_lkey_id_destroy(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id) +{ + struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv; + u32 id = lkey_id->id; + + rhashtable_remove_fast(®ion_12kb->lkey_ht, &lkey_id->ht_node, + mlxsw_sp_acl_atcam_lkey_id_ht_params); + kfree(lkey_id); + __clear_bit(id, region_12kb->used_lkey_id); +} + +static struct mlxsw_sp_acl_atcam_lkey_id * +mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_rule_info *rulei, + u8 erp_id) +{ + struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv; + struct mlxsw_sp_acl_tcam_region *region = aregion->region; + struct mlxsw_sp_acl_atcam_lkey_id_ht_key ht_key = {{ 0 } }; + struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp; + struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id; + + mlxsw_afk_encode(afk, region->key_info, &rulei->values, ht_key.enc_key, + NULL, MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START, + MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END); + ht_key.erp_id = erp_id; + lkey_id = rhashtable_lookup_fast(®ion_12kb->lkey_ht, &ht_key, + mlxsw_sp_acl_atcam_lkey_id_ht_params); + if (lkey_id) { + refcount_inc(&lkey_id->refcnt); + return lkey_id; + } + + return mlxsw_sp_acl_atcam_lkey_id_create(aregion, &ht_key); +} + +static void +mlxsw_sp_acl_atcam_12kb_lkey_id_put(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id) +{ + if (refcount_dec_and_test(&lkey_id->refcnt)) + mlxsw_sp_acl_atcam_lkey_id_destroy(aregion, lkey_id); +} + +static const struct mlxsw_sp_acl_atcam_region_ops +mlxsw_sp_acl_atcam_region_12kb_ops = { + .init = mlxsw_sp_acl_atcam_region_12kb_init, + .fini = mlxsw_sp_acl_atcam_region_12kb_fini, + .lkey_id_get = mlxsw_sp_acl_atcam_12kb_lkey_id_get, + .lkey_id_put = mlxsw_sp_acl_atcam_12kb_lkey_id_put, +}; + +static const struct mlxsw_sp_acl_atcam_region_ops * +mlxsw_sp_acl_atcam_region_ops_arr[] = { + [MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB] = + &mlxsw_sp_acl_atcam_region_generic_ops, + [MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB] = + &mlxsw_sp_acl_atcam_region_generic_ops, + [MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB] = + &mlxsw_sp_acl_atcam_region_generic_ops, + [MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB] = + &mlxsw_sp_acl_atcam_region_12kb_ops, +}; int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp, u16 region_id) @@ -57,39 +320,249 @@ int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perar), perar_pl); } -static int mlxsw_sp_acl_atcam_region_param_init(struct mlxsw_sp *mlxsw_sp, - u16 region_id) +static void +mlxsw_sp_acl_atcam_region_type_init(struct mlxsw_sp_acl_atcam_region *aregion) { - char percr_pl[MLXSW_REG_PERCR_LEN]; + struct mlxsw_sp_acl_tcam_region *region = aregion->region; + enum mlxsw_sp_acl_atcam_region_type region_type; + unsigned int blocks_count; - mlxsw_reg_percr_pack(percr_pl, region_id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl); + /* We already know the blocks count can not exceed the maximum + * blocks count. + */ + blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info); + if (blocks_count <= 2) + region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB; + else if (blocks_count <= 4) + region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB; + else if (blocks_count <= 8) + region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB; + else + region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB; + + aregion->type = region_type; + aregion->ops = mlxsw_sp_acl_atcam_region_ops_arr[region_type]; } -static int -mlxsw_sp_acl_atcam_region_erp_init(struct mlxsw_sp *mlxsw_sp, - u16 region_id) +int +mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_tcam_region *region, + const struct mlxsw_sp_acl_ctcam_region_ops *ops) +{ + int err; + + aregion->region = region; + aregion->atcam = atcam; + mlxsw_sp_acl_atcam_region_type_init(aregion); + + err = rhashtable_init(&aregion->entries_ht, + &mlxsw_sp_acl_atcam_entries_ht_params); + if (err) + return err; + err = aregion->ops->init(aregion); + if (err) + goto err_ops_init; + err = mlxsw_sp_acl_erp_region_init(aregion); + if (err) + goto err_erp_region_init; + err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion, + region, ops); + if (err) + goto err_ctcam_region_init; + + return 0; + +err_ctcam_region_init: + mlxsw_sp_acl_erp_region_fini(aregion); +err_erp_region_init: + aregion->ops->fini(aregion); +err_ops_init: + rhashtable_destroy(&aregion->entries_ht); + return err; +} + +void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion) { - char pererp_pl[MLXSW_REG_PERERP_LEN]; + mlxsw_sp_acl_ctcam_region_fini(&aregion->cregion); + mlxsw_sp_acl_erp_region_fini(aregion); + aregion->ops->fini(aregion); + rhashtable_destroy(&aregion->entries_ht); +} - mlxsw_reg_pererp_pack(pererp_pl, region_id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); +void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_chunk *achunk, + unsigned int priority) +{ + mlxsw_sp_acl_ctcam_chunk_init(&aregion->cregion, &achunk->cchunk, + priority); } -int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_region *region) +void mlxsw_sp_acl_atcam_chunk_fini(struct mlxsw_sp_acl_atcam_chunk *achunk) { + mlxsw_sp_acl_ctcam_chunk_fini(&achunk->cchunk); +} + +static int +mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_entry *aentry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + struct mlxsw_sp_acl_tcam_region *region = aregion->region; + u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp); + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id; + char ptce3_pl[MLXSW_REG_PTCE3_LEN]; + u32 kvdl_index, priority; int err; - err = mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id); + err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority, true); if (err) return err; - err = mlxsw_sp_acl_atcam_region_param_init(mlxsw_sp, region->id); + + lkey_id = aregion->ops->lkey_id_get(aregion, rulei, erp_id); + if (IS_ERR(lkey_id)) + return PTR_ERR(lkey_id); + aentry->lkey_id = lkey_id; + + kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block); + mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE, + priority, region->tcam_region_info, + aentry->ht_key.enc_key, erp_id, + refcount_read(&lkey_id->refcnt) != 1, lkey_id->id, + kvdl_index); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl); if (err) - return err; - err = mlxsw_sp_acl_atcam_region_erp_init(mlxsw_sp, region->id); + goto err_ptce3_write; + + return 0; + +err_ptce3_write: + aregion->ops->lkey_id_put(aregion, lkey_id); + return err; +} + +static void +mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_entry *aentry) +{ + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id; + struct mlxsw_sp_acl_tcam_region *region = aregion->region; + u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp); + char ptce3_pl[MLXSW_REG_PTCE3_LEN]; + + mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0, + region->tcam_region_info, aentry->ht_key.enc_key, + erp_id, refcount_read(&lkey_id->refcnt) != 1, + lkey_id->id, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl); + aregion->ops->lkey_id_put(aregion, lkey_id); +} + +static int +__mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_entry *aentry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + struct mlxsw_sp_acl_tcam_region *region = aregion->region; + char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 }; + struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); + struct mlxsw_sp_acl_erp *erp; + unsigned int blocks_count; + int err; + + blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info); + mlxsw_afk_encode(afk, region->key_info, &rulei->values, + aentry->ht_key.enc_key, mask, 0, blocks_count - 1); + + erp = mlxsw_sp_acl_erp_get(aregion, mask, false); + if (IS_ERR(erp)) + return PTR_ERR(erp); + aentry->erp = erp; + aentry->ht_key.erp_id = mlxsw_sp_acl_erp_id(erp); + + /* We can't insert identical rules into the A-TCAM, so fail and + * let the rule spill into C-TCAM + */ + err = rhashtable_lookup_insert_fast(&aregion->entries_ht, + &aentry->ht_node, + mlxsw_sp_acl_atcam_entries_ht_params); if (err) - return err; + goto err_rhashtable_insert; + + err = mlxsw_sp_acl_atcam_region_entry_insert(mlxsw_sp, aregion, aentry, + rulei); + if (err) + goto err_rule_insert; return 0; + +err_rule_insert: + rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node, + mlxsw_sp_acl_atcam_entries_ht_params); +err_rhashtable_insert: + mlxsw_sp_acl_erp_put(aregion, erp); + return err; +} + +static void +__mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_entry *aentry) +{ + mlxsw_sp_acl_atcam_region_entry_remove(mlxsw_sp, aregion, aentry); + rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node, + mlxsw_sp_acl_atcam_entries_ht_params); + mlxsw_sp_acl_erp_put(aregion, aentry->erp); +} + +int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_chunk *achunk, + struct mlxsw_sp_acl_atcam_entry *aentry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + int err; + + err = __mlxsw_sp_acl_atcam_entry_add(mlxsw_sp, aregion, aentry, rulei); + if (!err) + return 0; + + /* It is possible we failed to add the rule to the A-TCAM due to + * exceeded number of masks. Try to spill into C-TCAM. + */ + err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion, + &achunk->cchunk, &aentry->centry, + rulei, true); + if (!err) + return 0; + + return err; +} + +void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_chunk *achunk, + struct mlxsw_sp_acl_atcam_entry *aentry) +{ + if (mlxsw_sp_acl_atcam_is_centry(aentry)) + mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &aregion->cregion, + &achunk->cchunk, &aentry->centry); + else + __mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, aregion, aentry); +} + +int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam) +{ + return mlxsw_sp_acl_erps_init(mlxsw_sp, atcam); +} + +void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam) +{ + mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c index ef0d4c0a5a1f..7440a1189250 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c @@ -69,13 +69,15 @@ mlxsw_sp_acl_ctcam_region_move(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_region *region, - unsigned int offset, + struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry, struct mlxsw_sp_acl_rule_info *rulei, bool fillup_priority) { + struct mlxsw_sp_acl_tcam_region *region = cregion->region; struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); char ptce2_pl[MLXSW_REG_PTCE2_LEN]; + unsigned int blocks_count; char *act_set; u32 priority; char *mask; @@ -88,10 +90,17 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, return err; mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE, - region->tcam_region_info, offset, priority); + region->tcam_region_info, + centry->parman_item.index, priority); key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl); mask = mlxsw_reg_ptce2_mask_data(ptce2_pl); - mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask); + blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info); + mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask, 0, + blocks_count - 1); + + err = cregion->ops->entry_insert(cregion, centry, mask); + if (err) + return err; /* Only the first action set belongs here, the rest is in KVD */ act_set = mlxsw_afa_block_first_set(rulei->act_block); @@ -102,14 +111,16 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_region *region, - unsigned int offset) + struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry) { char ptce2_pl[MLXSW_REG_PTCE2_LEN]; mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE, - region->tcam_region_info, offset, 0); + cregion->region->tcam_region_info, + centry->parman_item.index, 0); mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl); + cregion->ops->entry_remove(cregion, centry); } static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv, @@ -147,11 +158,14 @@ static const struct parman_ops mlxsw_sp_acl_ctcam_region_parman_ops = { .algo = PARMAN_ALGO_TYPE_LSORT, }; -int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_ctcam_region *cregion, - struct mlxsw_sp_acl_tcam_region *region) +int +mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_tcam_region *region, + const struct mlxsw_sp_acl_ctcam_region_ops *ops) { cregion->region = region; + cregion->ops = ops; cregion->parman = parman_create(&mlxsw_sp_acl_ctcam_region_parman_ops, cregion); if (!cregion->parman) @@ -190,8 +204,7 @@ int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp, if (err) return err; - err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion->region, - centry->parman_item.index, + err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion, centry, rulei, fillup_priority); if (err) goto err_rule_insert; @@ -208,8 +221,7 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ctcam_chunk *cchunk, struct mlxsw_sp_acl_ctcam_entry *centry) { - mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion->region, - centry->parman_item.index); + mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion, centry); parman_item_remove(cregion->parman, &cchunk->parman_prio, ¢ry->parman_item); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c new file mode 100644 index 000000000000..463590bbb348 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -0,0 +1,1199 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2018 Ido Schimmel <idosch@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/bitmap.h> +#include <linux/errno.h> +#include <linux/genalloc.h> +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/rhashtable.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> + +#include "core.h" +#include "reg.h" +#include "spectrum.h" +#include "spectrum_acl_tcam.h" + +/* gen_pool_alloc() returns 0 when allocation fails, so use an offset */ +#define MLXSW_SP_ACL_ERP_GENALLOC_OFFSET 0x100 +#define MLXSW_SP_ACL_ERP_MAX_PER_REGION 16 + +struct mlxsw_sp_acl_erp_core { + unsigned int erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX + 1]; + struct gen_pool *erp_tables; + struct mlxsw_sp *mlxsw_sp; + unsigned int num_erp_banks; +}; + +struct mlxsw_sp_acl_erp_key { + char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; + bool ctcam; +}; + +struct mlxsw_sp_acl_erp { + struct mlxsw_sp_acl_erp_key key; + u8 id; + u8 index; + refcount_t refcnt; + DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN); + struct list_head list; + struct rhash_head ht_node; + struct mlxsw_sp_acl_erp_table *erp_table; +}; + +struct mlxsw_sp_acl_erp_master_mask { + DECLARE_BITMAP(bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN); + unsigned int count[MLXSW_SP_ACL_TCAM_MASK_LEN]; +}; + +struct mlxsw_sp_acl_erp_table { + struct mlxsw_sp_acl_erp_master_mask master_mask; + DECLARE_BITMAP(erp_id_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION); + DECLARE_BITMAP(erp_index_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION); + struct list_head atcam_erps_list; + struct rhashtable erp_ht; + struct mlxsw_sp_acl_erp_core *erp_core; + struct mlxsw_sp_acl_atcam_region *aregion; + const struct mlxsw_sp_acl_erp_table_ops *ops; + unsigned long base_index; + unsigned int num_atcam_erps; + unsigned int num_max_atcam_erps; + unsigned int num_ctcam_erps; +}; + +static const struct rhashtable_params mlxsw_sp_acl_erp_ht_params = { + .key_len = sizeof(struct mlxsw_sp_acl_erp_key), + .key_offset = offsetof(struct mlxsw_sp_acl_erp, key), + .head_offset = offsetof(struct mlxsw_sp_acl_erp, ht_node), +}; + +struct mlxsw_sp_acl_erp_table_ops { + struct mlxsw_sp_acl_erp * + (*erp_create)(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key); + void (*erp_destroy)(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp); +}; + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key); +static void +mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp); +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key); +static void +mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp); +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key); +static void +mlxsw_sp_acl_erp_first_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp); +static void +mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp); + +static const struct mlxsw_sp_acl_erp_table_ops erp_multiple_masks_ops = { + .erp_create = mlxsw_sp_acl_erp_mask_create, + .erp_destroy = mlxsw_sp_acl_erp_mask_destroy, +}; + +static const struct mlxsw_sp_acl_erp_table_ops erp_two_masks_ops = { + .erp_create = mlxsw_sp_acl_erp_mask_create, + .erp_destroy = mlxsw_sp_acl_erp_second_mask_destroy, +}; + +static const struct mlxsw_sp_acl_erp_table_ops erp_single_mask_ops = { + .erp_create = mlxsw_sp_acl_erp_second_mask_create, + .erp_destroy = mlxsw_sp_acl_erp_first_mask_destroy, +}; + +static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = { + .erp_create = mlxsw_sp_acl_erp_first_mask_create, + .erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy, +}; + +bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp) +{ + return erp->key.ctcam; +} + +u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp) +{ + return erp->id; +} + +static unsigned int +mlxsw_sp_acl_erp_table_entry_size(const struct mlxsw_sp_acl_erp_table *erp_table) +{ + struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion; + struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core; + + return erp_core->erpt_entries_size[aregion->type]; +} + +static int mlxsw_sp_acl_erp_id_get(struct mlxsw_sp_acl_erp_table *erp_table, + u8 *p_id) +{ + u8 id; + + id = find_first_zero_bit(erp_table->erp_id_bitmap, + MLXSW_SP_ACL_ERP_MAX_PER_REGION); + if (id < MLXSW_SP_ACL_ERP_MAX_PER_REGION) { + __set_bit(id, erp_table->erp_id_bitmap); + *p_id = id; + return 0; + } + + return -ENOBUFS; +} + +static void mlxsw_sp_acl_erp_id_put(struct mlxsw_sp_acl_erp_table *erp_table, + u8 id) +{ + __clear_bit(id, erp_table->erp_id_bitmap); +} + +static void +mlxsw_sp_acl_erp_master_mask_bit_set(unsigned long bit, + struct mlxsw_sp_acl_erp_master_mask *mask) +{ + if (mask->count[bit]++ == 0) + __set_bit(bit, mask->bitmap); +} + +static void +mlxsw_sp_acl_erp_master_mask_bit_clear(unsigned long bit, + struct mlxsw_sp_acl_erp_master_mask *mask) +{ + if (--mask->count[bit] == 0) + __clear_bit(bit, mask->bitmap); +} + +static int +mlxsw_sp_acl_erp_master_mask_update(struct mlxsw_sp_acl_erp_table *erp_table) +{ + struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region; + struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp; + char percr_pl[MLXSW_REG_PERCR_LEN]; + char *master_mask; + + mlxsw_reg_percr_pack(percr_pl, region->id); + master_mask = mlxsw_reg_percr_master_mask_data(percr_pl); + bitmap_to_arr32((u32 *) master_mask, erp_table->master_mask.bitmap, + MLXSW_SP_ACL_TCAM_MASK_LEN); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl); +} + +static int +mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table, + const struct mlxsw_sp_acl_erp *erp) +{ + unsigned long bit; + int err; + + for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN) + mlxsw_sp_acl_erp_master_mask_bit_set(bit, + &erp_table->master_mask); + + err = mlxsw_sp_acl_erp_master_mask_update(erp_table); + if (err) + goto err_master_mask_update; + + return 0; + +err_master_mask_update: + for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN) + mlxsw_sp_acl_erp_master_mask_bit_clear(bit, + &erp_table->master_mask); + return err; +} + +static int +mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table, + const struct mlxsw_sp_acl_erp *erp) +{ + unsigned long bit; + int err; + + for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN) + mlxsw_sp_acl_erp_master_mask_bit_clear(bit, + &erp_table->master_mask); + + err = mlxsw_sp_acl_erp_master_mask_update(erp_table); + if (err) + goto err_master_mask_update; + + return 0; + +err_master_mask_update: + for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN) + mlxsw_sp_acl_erp_master_mask_bit_set(bit, + &erp_table->master_mask); + return err; +} + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key) +{ + struct mlxsw_sp_acl_erp *erp; + int err; + + erp = kzalloc(sizeof(*erp), GFP_KERNEL); + if (!erp) + return ERR_PTR(-ENOMEM); + + err = mlxsw_sp_acl_erp_id_get(erp_table, &erp->id); + if (err) + goto err_erp_id_get; + + memcpy(&erp->key, key, sizeof(*key)); + bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask, + MLXSW_SP_ACL_TCAM_MASK_LEN); + list_add(&erp->list, &erp_table->atcam_erps_list); + refcount_set(&erp->refcnt, 1); + erp_table->num_atcam_erps++; + erp->erp_table = erp_table; + + err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp); + if (err) + goto err_master_mask_set; + + err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node, + mlxsw_sp_acl_erp_ht_params); + if (err) + goto err_rhashtable_insert; + + return erp; + +err_rhashtable_insert: + mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp); +err_master_mask_set: + erp_table->num_atcam_erps--; + list_del(&erp->list); + mlxsw_sp_acl_erp_id_put(erp_table, erp->id); +err_erp_id_get: + kfree(erp); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_erp_generic_destroy(struct mlxsw_sp_acl_erp *erp) +{ + struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table; + + rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node, + mlxsw_sp_acl_erp_ht_params); + mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp); + erp_table->num_atcam_erps--; + list_del(&erp->list); + mlxsw_sp_acl_erp_id_put(erp_table, erp->id); + kfree(erp); +} + +static int +mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, + unsigned int num_erps, + enum mlxsw_sp_acl_atcam_region_type region_type, + unsigned long *p_index) +{ + unsigned int num_rows, entry_size; + + /* We only allow allocations of entire rows */ + if (num_erps % erp_core->num_erp_banks != 0) + return -EINVAL; + + entry_size = erp_core->erpt_entries_size[region_type]; + num_rows = num_erps / erp_core->num_erp_banks; + + *p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); + if (*p_index == 0) + return -ENOBUFS; + *p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; + + return 0; +} + +static void +mlxsw_sp_acl_erp_table_free(struct mlxsw_sp_acl_erp_core *erp_core, + unsigned int num_erps, + enum mlxsw_sp_acl_atcam_region_type region_type, + unsigned long index) +{ + unsigned long base_index; + unsigned int entry_size; + size_t size; + + entry_size = erp_core->erpt_entries_size[region_type]; + base_index = index + MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; + size = num_erps / erp_core->num_erp_banks * entry_size; + gen_pool_free(erp_core->erp_tables, base_index, size); +} + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_table_master_rp(struct mlxsw_sp_acl_erp_table *erp_table) +{ + if (!list_is_singular(&erp_table->atcam_erps_list)) + return NULL; + + return list_first_entry(&erp_table->atcam_erps_list, + struct mlxsw_sp_acl_erp, list); +} + +static int mlxsw_sp_acl_erp_index_get(struct mlxsw_sp_acl_erp_table *erp_table, + u8 *p_index) +{ + u8 index; + + index = find_first_zero_bit(erp_table->erp_index_bitmap, + erp_table->num_max_atcam_erps); + if (index < erp_table->num_max_atcam_erps) { + __set_bit(index, erp_table->erp_index_bitmap); + *p_index = index; + return 0; + } + + return -ENOBUFS; +} + +static void mlxsw_sp_acl_erp_index_put(struct mlxsw_sp_acl_erp_table *erp_table, + u8 index) +{ + __clear_bit(index, erp_table->erp_index_bitmap); +} + +static void +mlxsw_sp_acl_erp_table_locate(const struct mlxsw_sp_acl_erp_table *erp_table, + const struct mlxsw_sp_acl_erp *erp, + u8 *p_erpt_bank, u8 *p_erpt_index) +{ + unsigned int entry_size = mlxsw_sp_acl_erp_table_entry_size(erp_table); + struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core; + unsigned int row; + + *p_erpt_bank = erp->index % erp_core->num_erp_banks; + row = erp->index / erp_core->num_erp_banks; + *p_erpt_index = erp_table->base_index + row * entry_size; +} + +static int +mlxsw_sp_acl_erp_table_erp_add(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp) +{ + struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp; + enum mlxsw_reg_perpt_key_size key_size; + char perpt_pl[MLXSW_REG_PERPT_LEN]; + u8 erpt_bank, erpt_index; + + mlxsw_sp_acl_erp_table_locate(erp_table, erp, &erpt_bank, &erpt_index); + key_size = (enum mlxsw_reg_perpt_key_size) erp_table->aregion->type; + mlxsw_reg_perpt_pack(perpt_pl, erpt_bank, erpt_index, key_size, erp->id, + 0, erp_table->base_index, erp->index, + erp->key.mask); + mlxsw_reg_perpt_erp_vector_pack(perpt_pl, erp_table->erp_index_bitmap, + MLXSW_SP_ACL_ERP_MAX_PER_REGION); + mlxsw_reg_perpt_erp_vector_set(perpt_pl, erp->index, true); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perpt), perpt_pl); +} + +static void mlxsw_sp_acl_erp_table_erp_del(struct mlxsw_sp_acl_erp *erp) +{ + char empty_mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 }; + struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table; + struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp; + enum mlxsw_reg_perpt_key_size key_size; + char perpt_pl[MLXSW_REG_PERPT_LEN]; + u8 erpt_bank, erpt_index; + + mlxsw_sp_acl_erp_table_locate(erp_table, erp, &erpt_bank, &erpt_index); + key_size = (enum mlxsw_reg_perpt_key_size) erp_table->aregion->type; + mlxsw_reg_perpt_pack(perpt_pl, erpt_bank, erpt_index, key_size, erp->id, + 0, erp_table->base_index, erp->index, empty_mask); + mlxsw_reg_perpt_erp_vector_pack(perpt_pl, erp_table->erp_index_bitmap, + MLXSW_SP_ACL_ERP_MAX_PER_REGION); + mlxsw_reg_perpt_erp_vector_set(perpt_pl, erp->index, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perpt), perpt_pl); +} + +static int +mlxsw_sp_acl_erp_table_enable(struct mlxsw_sp_acl_erp_table *erp_table, + bool ctcam_le) +{ + struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region; + struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp; + char pererp_pl[MLXSW_REG_PERERP_LEN]; + + mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0, + erp_table->base_index, 0); + mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap, + MLXSW_SP_ACL_ERP_MAX_PER_REGION); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); +} + +static void +mlxsw_sp_acl_erp_table_disable(struct mlxsw_sp_acl_erp_table *erp_table) +{ + struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region; + struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp; + char pererp_pl[MLXSW_REG_PERERP_LEN]; + struct mlxsw_sp_acl_erp *master_rp; + + master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table); + /* It is possible we do not have a master RP when we disable the + * table when there are no rules in the A-TCAM and the last C-TCAM + * rule is deleted + */ + mlxsw_reg_pererp_pack(pererp_pl, region->id, false, false, 0, 0, + master_rp ? master_rp->id : 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); +} + +static int +mlxsw_sp_acl_erp_table_relocate(struct mlxsw_sp_acl_erp_table *erp_table) +{ + struct mlxsw_sp_acl_erp *erp; + int err; + + list_for_each_entry(erp, &erp_table->atcam_erps_list, list) { + err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp); + if (err) + goto err_table_erp_add; + } + + return 0; + +err_table_erp_add: + list_for_each_entry_continue_reverse(erp, &erp_table->atcam_erps_list, + list) + mlxsw_sp_acl_erp_table_erp_del(erp); + return err; +} + +static int +mlxsw_sp_acl_erp_table_expand(struct mlxsw_sp_acl_erp_table *erp_table) +{ + unsigned int num_erps, old_num_erps = erp_table->num_max_atcam_erps; + struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core; + unsigned long old_base_index = erp_table->base_index; + bool ctcam_le = erp_table->num_ctcam_erps > 0; + int err; + + if (erp_table->num_atcam_erps < erp_table->num_max_atcam_erps) + return 0; + + if (erp_table->num_max_atcam_erps == MLXSW_SP_ACL_ERP_MAX_PER_REGION) + return -ENOBUFS; + + num_erps = old_num_erps + erp_core->num_erp_banks; + err = mlxsw_sp_acl_erp_table_alloc(erp_core, num_erps, + erp_table->aregion->type, + &erp_table->base_index); + if (err) + return err; + erp_table->num_max_atcam_erps = num_erps; + + err = mlxsw_sp_acl_erp_table_relocate(erp_table); + if (err) + goto err_table_relocate; + + err = mlxsw_sp_acl_erp_table_enable(erp_table, ctcam_le); + if (err) + goto err_table_enable; + + mlxsw_sp_acl_erp_table_free(erp_core, old_num_erps, + erp_table->aregion->type, old_base_index); + + return 0; + +err_table_enable: +err_table_relocate: + erp_table->num_max_atcam_erps = old_num_erps; + mlxsw_sp_acl_erp_table_free(erp_core, num_erps, + erp_table->aregion->type, + erp_table->base_index); + erp_table->base_index = old_base_index; + return err; +} + +static int +mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table) +{ + struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core; + struct mlxsw_sp_acl_erp *master_rp; + int err; + + /* Initially, allocate a single eRP row. Expand later as needed */ + err = mlxsw_sp_acl_erp_table_alloc(erp_core, erp_core->num_erp_banks, + erp_table->aregion->type, + &erp_table->base_index); + if (err) + return err; + erp_table->num_max_atcam_erps = erp_core->num_erp_banks; + + /* Transition the sole RP currently configured (the master RP) + * to the eRP table + */ + master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table); + if (!master_rp) { + err = -EINVAL; + goto err_table_master_rp; + } + + /* Maintain the same eRP bank for the master RP, so that we + * wouldn't need to update the bloom filter + */ + master_rp->index = master_rp->index % erp_core->num_erp_banks; + __set_bit(master_rp->index, erp_table->erp_index_bitmap); + + err = mlxsw_sp_acl_erp_table_erp_add(erp_table, master_rp); + if (err) + goto err_table_master_rp_add; + + err = mlxsw_sp_acl_erp_table_enable(erp_table, false); + if (err) + goto err_table_enable; + + return 0; + +err_table_enable: + mlxsw_sp_acl_erp_table_erp_del(master_rp); +err_table_master_rp_add: + __clear_bit(master_rp->index, erp_table->erp_index_bitmap); +err_table_master_rp: + mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps, + erp_table->aregion->type, + erp_table->base_index); + return err; +} + +static void +mlxsw_sp_acl_erp_region_master_mask_trans(struct mlxsw_sp_acl_erp_table *erp_table) +{ + struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core; + struct mlxsw_sp_acl_erp *master_rp; + + mlxsw_sp_acl_erp_table_disable(erp_table); + master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table); + if (!master_rp) + return; + mlxsw_sp_acl_erp_table_erp_del(master_rp); + __clear_bit(master_rp->index, erp_table->erp_index_bitmap); + mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps, + erp_table->aregion->type, + erp_table->base_index); +} + +static int +mlxsw_sp_acl_erp_region_erp_add(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp) +{ + struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region; + struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp; + bool ctcam_le = erp_table->num_ctcam_erps > 0; + char pererp_pl[MLXSW_REG_PERERP_LEN]; + + mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0, + erp_table->base_index, 0); + mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap, + MLXSW_SP_ACL_ERP_MAX_PER_REGION); + mlxsw_reg_pererp_erpt_vector_set(pererp_pl, erp->index, true); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); +} + +static void mlxsw_sp_acl_erp_region_erp_del(struct mlxsw_sp_acl_erp *erp) +{ + struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table; + struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region; + struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp; + bool ctcam_le = erp_table->num_ctcam_erps > 0; + char pererp_pl[MLXSW_REG_PERERP_LEN]; + + mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0, + erp_table->base_index, 0); + mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap, + MLXSW_SP_ACL_ERP_MAX_PER_REGION); + mlxsw_reg_pererp_erpt_vector_set(pererp_pl, erp->index, false); + + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); +} + +static int +mlxsw_sp_acl_erp_region_ctcam_enable(struct mlxsw_sp_acl_erp_table *erp_table) +{ + /* No need to re-enable lookup in the C-TCAM */ + if (erp_table->num_ctcam_erps > 1) + return 0; + + return mlxsw_sp_acl_erp_table_enable(erp_table, true); +} + +static void +mlxsw_sp_acl_erp_region_ctcam_disable(struct mlxsw_sp_acl_erp_table *erp_table) +{ + /* Only disable C-TCAM lookup when last C-TCAM eRP is deleted */ + if (erp_table->num_ctcam_erps > 1) + return; + + mlxsw_sp_acl_erp_table_enable(erp_table, false); +} + +static void +mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table) +{ + switch (erp_table->num_atcam_erps) { + case 2: + /* Keep using the eRP table, but correctly set the + * operations pointer so that when an A-TCAM eRP is + * deleted we will transition to use the master mask + */ + erp_table->ops = &erp_two_masks_ops; + break; + case 1: + /* We only kept the eRP table because we had C-TCAM + * eRPs in use. Now that the last C-TCAM eRP is gone we + * can stop using the table and transition to use the + * master mask + */ + mlxsw_sp_acl_erp_region_master_mask_trans(erp_table); + erp_table->ops = &erp_single_mask_ops; + break; + case 0: + /* There are no more eRPs of any kind used by the region + * so free its eRP table and transition to initial state + */ + mlxsw_sp_acl_erp_table_disable(erp_table); + mlxsw_sp_acl_erp_table_free(erp_table->erp_core, + erp_table->num_max_atcam_erps, + erp_table->aregion->type, + erp_table->base_index); + erp_table->ops = &erp_no_mask_ops; + break; + default: + break; + } +} + +static struct mlxsw_sp_acl_erp * +__mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key) +{ + struct mlxsw_sp_acl_erp *erp; + int err; + + erp = kzalloc(sizeof(*erp), GFP_KERNEL); + if (!erp) + return ERR_PTR(-ENOMEM); + + memcpy(&erp->key, key, sizeof(*key)); + bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask, + MLXSW_SP_ACL_TCAM_MASK_LEN); + refcount_set(&erp->refcnt, 1); + erp_table->num_ctcam_erps++; + erp->erp_table = erp_table; + + err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp); + if (err) + goto err_master_mask_set; + + err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node, + mlxsw_sp_acl_erp_ht_params); + if (err) + goto err_rhashtable_insert; + + err = mlxsw_sp_acl_erp_region_ctcam_enable(erp_table); + if (err) + goto err_erp_region_ctcam_enable; + + /* When C-TCAM is used, the eRP table must be used */ + erp_table->ops = &erp_multiple_masks_ops; + + return erp; + +err_erp_region_ctcam_enable: + rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node, + mlxsw_sp_acl_erp_ht_params); +err_rhashtable_insert: + mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp); +err_master_mask_set: + erp_table->num_ctcam_erps--; + kfree(erp); + return ERR_PTR(err); +} + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key) +{ + struct mlxsw_sp_acl_erp *erp; + int err; + + /* There is a special situation where we need to spill rules + * into the C-TCAM, yet the region is still using a master + * mask and thus not performing a lookup in the C-TCAM. This + * can happen when two rules that only differ in priority - and + * thus sharing the same key - are programmed. In this case + * we transition the region to use an eRP table + */ + err = mlxsw_sp_acl_erp_region_table_trans(erp_table); + if (err) + return ERR_PTR(err); + + erp = __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key); + if (IS_ERR(erp)) { + err = PTR_ERR(erp); + goto err_erp_create; + } + + return erp; + +err_erp_create: + mlxsw_sp_acl_erp_region_master_mask_trans(erp_table); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp) +{ + struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table; + + mlxsw_sp_acl_erp_region_ctcam_disable(erp_table); + rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node, + mlxsw_sp_acl_erp_ht_params); + mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp); + erp_table->num_ctcam_erps--; + kfree(erp); + + /* Once the last C-TCAM eRP was destroyed, the state we + * transition to depends on the number of A-TCAM eRPs currently + * in use + */ + if (erp_table->num_ctcam_erps > 0) + return; + mlxsw_sp_acl_erp_ctcam_table_ops_set(erp_table); +} + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key) +{ + struct mlxsw_sp_acl_erp *erp; + int err; + + if (key->ctcam) + return __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key); + + /* Expand the eRP table for the new eRP, if needed */ + err = mlxsw_sp_acl_erp_table_expand(erp_table); + if (err) + return ERR_PTR(err); + + erp = mlxsw_sp_acl_erp_generic_create(erp_table, key); + if (IS_ERR(erp)) + return erp; + + err = mlxsw_sp_acl_erp_index_get(erp_table, &erp->index); + if (err) + goto err_erp_index_get; + + err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp); + if (err) + goto err_table_erp_add; + + err = mlxsw_sp_acl_erp_region_erp_add(erp_table, erp); + if (err) + goto err_region_erp_add; + + erp_table->ops = &erp_multiple_masks_ops; + + return erp; + +err_region_erp_add: + mlxsw_sp_acl_erp_table_erp_del(erp); +err_table_erp_add: + mlxsw_sp_acl_erp_index_put(erp_table, erp->index); +err_erp_index_get: + mlxsw_sp_acl_erp_generic_destroy(erp); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp) +{ + if (erp->key.ctcam) + return mlxsw_sp_acl_erp_ctcam_mask_destroy(erp); + + mlxsw_sp_acl_erp_region_erp_del(erp); + mlxsw_sp_acl_erp_table_erp_del(erp); + mlxsw_sp_acl_erp_index_put(erp_table, erp->index); + mlxsw_sp_acl_erp_generic_destroy(erp); + + if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0) + erp_table->ops = &erp_two_masks_ops; +} + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key) +{ + struct mlxsw_sp_acl_erp *erp; + int err; + + if (key->ctcam) + return mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key); + + /* Transition to use eRP table instead of master mask */ + err = mlxsw_sp_acl_erp_region_table_trans(erp_table); + if (err) + return ERR_PTR(err); + + erp = mlxsw_sp_acl_erp_generic_create(erp_table, key); + if (IS_ERR(erp)) { + err = PTR_ERR(erp); + goto err_erp_create; + } + + err = mlxsw_sp_acl_erp_index_get(erp_table, &erp->index); + if (err) + goto err_erp_index_get; + + err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp); + if (err) + goto err_table_erp_add; + + err = mlxsw_sp_acl_erp_region_erp_add(erp_table, erp); + if (err) + goto err_region_erp_add; + + erp_table->ops = &erp_two_masks_ops; + + return erp; + +err_region_erp_add: + mlxsw_sp_acl_erp_table_erp_del(erp); +err_table_erp_add: + mlxsw_sp_acl_erp_index_put(erp_table, erp->index); +err_erp_index_get: + mlxsw_sp_acl_erp_generic_destroy(erp); +err_erp_create: + mlxsw_sp_acl_erp_region_master_mask_trans(erp_table); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp) +{ + if (erp->key.ctcam) + return mlxsw_sp_acl_erp_ctcam_mask_destroy(erp); + + mlxsw_sp_acl_erp_region_erp_del(erp); + mlxsw_sp_acl_erp_table_erp_del(erp); + mlxsw_sp_acl_erp_index_put(erp_table, erp->index); + mlxsw_sp_acl_erp_generic_destroy(erp); + /* Transition to use master mask instead of eRP table */ + mlxsw_sp_acl_erp_region_master_mask_trans(erp_table); + + erp_table->ops = &erp_single_mask_ops; +} + +static struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp_key *key) +{ + struct mlxsw_sp_acl_erp *erp; + + if (key->ctcam) + return ERR_PTR(-EINVAL); + + erp = mlxsw_sp_acl_erp_generic_create(erp_table, key); + if (IS_ERR(erp)) + return erp; + + erp_table->ops = &erp_single_mask_ops; + + return erp; +} + +static void +mlxsw_sp_acl_erp_first_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp) +{ + mlxsw_sp_acl_erp_generic_destroy(erp); + erp_table->ops = &erp_no_mask_ops; +} + +static void +mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table, + struct mlxsw_sp_acl_erp *erp) +{ + WARN_ON(1); +} + +struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion, + const char *mask, bool ctcam) +{ + struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table; + struct mlxsw_sp_acl_erp_key key; + struct mlxsw_sp_acl_erp *erp; + + /* eRPs are allocated from a shared resource, but currently all + * allocations are done under RTNL. + */ + ASSERT_RTNL(); + + memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN); + key.ctcam = ctcam; + erp = rhashtable_lookup_fast(&erp_table->erp_ht, &key, + mlxsw_sp_acl_erp_ht_params); + if (erp) { + refcount_inc(&erp->refcnt); + return erp; + } + + return erp_table->ops->erp_create(erp_table, &key); +} + +void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_erp *erp) +{ + struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table; + + ASSERT_RTNL(); + + if (!refcount_dec_and_test(&erp->refcnt)) + return; + + erp_table->ops->erp_destroy(erp_table, erp); +} + +static struct mlxsw_sp_acl_erp_table * +mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp_acl_erp_table *erp_table; + int err; + + erp_table = kzalloc(sizeof(*erp_table), GFP_KERNEL); + if (!erp_table) + return ERR_PTR(-ENOMEM); + + err = rhashtable_init(&erp_table->erp_ht, &mlxsw_sp_acl_erp_ht_params); + if (err) + goto err_rhashtable_init; + + erp_table->erp_core = aregion->atcam->erp_core; + erp_table->ops = &erp_no_mask_ops; + INIT_LIST_HEAD(&erp_table->atcam_erps_list); + erp_table->aregion = aregion; + + return erp_table; + +err_rhashtable_init: + kfree(erp_table); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_erp_table_destroy(struct mlxsw_sp_acl_erp_table *erp_table) +{ + WARN_ON(!list_empty(&erp_table->atcam_erps_list)); + rhashtable_destroy(&erp_table->erp_ht); + kfree(erp_table); +} + +static int +mlxsw_sp_acl_erp_master_mask_init(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp; + char percr_pl[MLXSW_REG_PERCR_LEN]; + + mlxsw_reg_percr_pack(percr_pl, aregion->region->id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl); +} + +static int +mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp; + char pererp_pl[MLXSW_REG_PERERP_LEN]; + + mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, false, false, 0, + 0, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); +} + +int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp_acl_erp_table *erp_table; + int err; + + erp_table = mlxsw_sp_acl_erp_table_create(aregion); + if (IS_ERR(erp_table)) + return PTR_ERR(erp_table); + aregion->erp_table = erp_table; + + /* Initialize the region's master mask to all zeroes */ + err = mlxsw_sp_acl_erp_master_mask_init(aregion); + if (err) + goto err_erp_master_mask_init; + + /* Initialize the region to not use the eRP table */ + err = mlxsw_sp_acl_erp_region_param_init(aregion); + if (err) + goto err_erp_region_param_init; + + return 0; + +err_erp_region_param_init: +err_erp_master_mask_init: + mlxsw_sp_acl_erp_table_destroy(erp_table); + return err; +} + +void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion) +{ + mlxsw_sp_acl_erp_table_destroy(aregion->erp_table); +} + +static int +mlxsw_sp_acl_erp_tables_sizes_query(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_erp_core *erp_core) +{ + unsigned int size; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_2KB) || + !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_4KB) || + !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_8KB) || + !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_12KB)) + return -EIO; + + size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_2KB); + erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB] = size; + + size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_4KB); + erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB] = size; + + size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_8KB); + erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB] = size; + + size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_12KB); + erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB] = size; + + return 0; +} + +static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_erp_core *erp_core) +{ + unsigned int erpt_bank_size; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_ERPT_BANK_SIZE) || + !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_ERPT_BANKS)) + return -EIO; + erpt_bank_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_ERPT_BANK_SIZE); + erp_core->num_erp_banks = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_ERPT_BANKS); + + erp_core->erp_tables = gen_pool_create(0, -1); + if (!erp_core->erp_tables) + return -ENOMEM; + gen_pool_set_algo(erp_core->erp_tables, gen_pool_best_fit, NULL); + + err = gen_pool_add(erp_core->erp_tables, + MLXSW_SP_ACL_ERP_GENALLOC_OFFSET, erpt_bank_size, + -1); + if (err) + goto err_gen_pool_add; + + /* Different regions require masks of different sizes */ + err = mlxsw_sp_acl_erp_tables_sizes_query(mlxsw_sp, erp_core); + if (err) + goto err_erp_tables_sizes_query; + + return 0; + +err_erp_tables_sizes_query: +err_gen_pool_add: + gen_pool_destroy(erp_core->erp_tables); + return err; +} + +static void mlxsw_sp_acl_erp_tables_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_erp_core *erp_core) +{ + gen_pool_destroy(erp_core->erp_tables); +} + +int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam) +{ + struct mlxsw_sp_acl_erp_core *erp_core; + int err; + + erp_core = kzalloc(sizeof(*erp_core), GFP_KERNEL); + if (!erp_core) + return -ENOMEM; + erp_core->mlxsw_sp = mlxsw_sp; + atcam->erp_core = erp_core; + + err = mlxsw_sp_acl_erp_tables_init(mlxsw_sp, erp_core); + if (err) + goto err_erp_tables_init; + + return 0; + +err_erp_tables_init: + kfree(erp_core); + return err; +} + +void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam) +{ + mlxsw_sp_acl_erp_tables_fini(mlxsw_sp, atcam->erp_core); + kfree(atcam->erp_core); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 310fd87895b8..245e2f473c6f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -577,7 +577,7 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_tcam_region_enable; - err = ops->region_init(mlxsw_sp, region->priv, region); + err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region); if (err) goto err_tcam_region_init; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index 6403ec4f5267..881ade760ace 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -92,6 +92,9 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp, #define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U) +#define MLXSW_SP_ACL_TCAM_MASK_LEN \ + (MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE) + struct mlxsw_sp_acl_tcam_group; struct mlxsw_sp_acl_tcam_region { @@ -109,6 +112,7 @@ struct mlxsw_sp_acl_tcam_region { struct mlxsw_sp_acl_ctcam_region { struct parman *parman; + const struct mlxsw_sp_acl_ctcam_region_ops *ops; struct mlxsw_sp_acl_tcam_region *region; }; @@ -120,9 +124,19 @@ struct mlxsw_sp_acl_ctcam_entry { struct parman_item parman_item; }; -int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_ctcam_region *cregion, - struct mlxsw_sp_acl_tcam_region *region); +struct mlxsw_sp_acl_ctcam_region_ops { + int (*entry_insert)(struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry, + const char *mask); + void (*entry_remove)(struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_ctcam_entry *centry); +}; + +int +mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_ctcam_region *cregion, + struct mlxsw_sp_acl_tcam_region *region, + const struct mlxsw_sp_acl_ctcam_region_ops *ops); void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion); void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion, struct mlxsw_sp_acl_ctcam_chunk *cchunk, @@ -144,9 +158,102 @@ mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry) return centry->parman_item.index; } +enum mlxsw_sp_acl_atcam_region_type { + MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB, + MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB, + MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB, + MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB, + __MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX, +}; + +#define MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX \ + (__MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX - 1) + +struct mlxsw_sp_acl_atcam { + struct mlxsw_sp_acl_erp_core *erp_core; +}; + +struct mlxsw_sp_acl_atcam_region { + struct rhashtable entries_ht; /* A-TCAM only */ + struct mlxsw_sp_acl_ctcam_region cregion; + const struct mlxsw_sp_acl_atcam_region_ops *ops; + struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_atcam *atcam; + enum mlxsw_sp_acl_atcam_region_type type; + struct mlxsw_sp_acl_erp_table *erp_table; + void *priv; +}; + +struct mlxsw_sp_acl_atcam_entry_ht_key { + char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */ + u8 erp_id; +}; + +struct mlxsw_sp_acl_atcam_chunk { + struct mlxsw_sp_acl_ctcam_chunk cchunk; +}; + +struct mlxsw_sp_acl_atcam_entry { + struct rhash_head ht_node; + struct mlxsw_sp_acl_atcam_entry_ht_key ht_key; + struct mlxsw_sp_acl_ctcam_entry centry; + struct mlxsw_sp_acl_atcam_lkey_id *lkey_id; + struct mlxsw_sp_acl_erp *erp; +}; + +static inline struct mlxsw_sp_acl_atcam_region * +mlxsw_sp_acl_tcam_cregion_aregion(struct mlxsw_sp_acl_ctcam_region *cregion) +{ + return container_of(cregion, struct mlxsw_sp_acl_atcam_region, cregion); +} + +static inline struct mlxsw_sp_acl_atcam_entry * +mlxsw_sp_acl_tcam_centry_aentry(struct mlxsw_sp_acl_ctcam_entry *centry) +{ + return container_of(centry, struct mlxsw_sp_acl_atcam_entry, centry); +} + int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp, u16 region_id); -int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_region *region); +int +mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_tcam_region *region, + const struct mlxsw_sp_acl_ctcam_region_ops *ops); +void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion); +void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_chunk *achunk, + unsigned int priority); +void mlxsw_sp_acl_atcam_chunk_fini(struct mlxsw_sp_acl_atcam_chunk *achunk); +int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_chunk *achunk, + struct mlxsw_sp_acl_atcam_entry *aentry, + struct mlxsw_sp_acl_rule_info *rulei); +void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_chunk *achunk, + struct mlxsw_sp_acl_atcam_entry *aentry); +int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam); +void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam); + +struct mlxsw_sp_acl_erp; + +bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp); +u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp); +struct mlxsw_sp_acl_erp * +mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion, + const char *mask, bool ctcam); +void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_erp *erp); +int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion); +void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion); +int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam); +void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam *atcam); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c index b6ed7f7c531e..c31aeb25ab5a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com> * * Redistribution and use in source and binary forms, with or without @@ -255,6 +255,270 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev, return 0; } +static int mlxsw_sp_dcbnl_app_validate(struct net_device *dev, + struct dcb_app *app) +{ + int prio; + + if (app->priority >= IEEE_8021QAZ_MAX_TCS) { + netdev_err(dev, "APP entry with priority value %u is invalid\n", + app->priority); + return -EINVAL; + } + + switch (app->selector) { + case IEEE_8021QAZ_APP_SEL_DSCP: + if (app->protocol >= 64) { + netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n", + app->protocol); + return -EINVAL; + } + + /* Warn about any DSCP APP entries with the same PID. */ + prio = fls(dcb_ieee_getapp_mask(dev, app)); + if (prio--) { + if (prio < app->priority) + netdev_warn(dev, "Choosing priority %d for DSCP %d in favor of previously-active value of %d\n", + app->priority, app->protocol, prio); + else if (prio > app->priority) + netdev_warn(dev, "Ignoring new priority %d for DSCP %d in favor of current value of %d\n", + app->priority, app->protocol, prio); + } + break; + + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + if (app->protocol) { + netdev_err(dev, "EtherType APP entries with protocol value != 0 not supported\n"); + return -EINVAL; + } + break; + + default: + netdev_err(dev, "APP entries with selector %u not supported\n", + app->selector); + return -EINVAL; + } + + return 0; +} + +static u8 +mlxsw_sp_port_dcb_app_default_prio(struct mlxsw_sp_port *mlxsw_sp_port) +{ + u8 prio_mask; + + prio_mask = dcb_ieee_getapp_default_prio_mask(mlxsw_sp_port->dev); + if (prio_mask) + /* Take the highest configured priority. */ + return fls(prio_mask) - 1; + + return 0; +} + +static void +mlxsw_sp_port_dcb_app_dscp_prio_map(struct mlxsw_sp_port *mlxsw_sp_port, + u8 default_prio, + struct dcb_ieee_app_dscp_map *map) +{ + int i; + + dcb_ieee_getapp_dscp_prio_mask_map(mlxsw_sp_port->dev, map); + for (i = 0; i < ARRAY_SIZE(map->map); ++i) { + if (map->map[i]) + map->map[i] = fls(map->map[i]) - 1; + else + map->map[i] = default_prio; + } +} + +static bool +mlxsw_sp_port_dcb_app_prio_dscp_map(struct mlxsw_sp_port *mlxsw_sp_port, + struct dcb_ieee_app_prio_map *map) +{ + bool have_dscp = false; + int i; + + dcb_ieee_getapp_prio_dscp_mask_map(mlxsw_sp_port->dev, map); + for (i = 0; i < ARRAY_SIZE(map->map); ++i) { + if (map->map[i]) { + map->map[i] = fls64(map->map[i]) - 1; + have_dscp = true; + } + } + + return have_dscp; +} + +static int +mlxsw_sp_port_dcb_app_update_qpts(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_reg_qpts_trust_state ts) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char qpts_pl[MLXSW_REG_QPTS_LEN]; + + mlxsw_reg_qpts_pack(qpts_pl, mlxsw_sp_port->local_port, ts); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpts), qpts_pl); +} + +static int +mlxsw_sp_port_dcb_app_update_qrwe(struct mlxsw_sp_port *mlxsw_sp_port, + bool rewrite_dscp) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char qrwe_pl[MLXSW_REG_QRWE_LEN]; + + mlxsw_reg_qrwe_pack(qrwe_pl, mlxsw_sp_port->local_port, + false, rewrite_dscp); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qrwe), qrwe_pl); +} + +static int +mlxsw_sp_port_dcb_toggle_trust(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_reg_qpts_trust_state ts) +{ + bool rewrite_dscp = ts == MLXSW_REG_QPTS_TRUST_STATE_DSCP; + int err; + + if (mlxsw_sp_port->dcb.trust_state == ts) + return 0; + + err = mlxsw_sp_port_dcb_app_update_qpts(mlxsw_sp_port, ts); + if (err) + return err; + + err = mlxsw_sp_port_dcb_app_update_qrwe(mlxsw_sp_port, rewrite_dscp); + if (err) + goto err_update_qrwe; + + mlxsw_sp_port->dcb.trust_state = ts; + return 0; + +err_update_qrwe: + mlxsw_sp_port_dcb_app_update_qpts(mlxsw_sp_port, + mlxsw_sp_port->dcb.trust_state); + return err; +} + +static int +mlxsw_sp_port_dcb_app_update_qpdpm(struct mlxsw_sp_port *mlxsw_sp_port, + struct dcb_ieee_app_dscp_map *map) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char qpdpm_pl[MLXSW_REG_QPDPM_LEN]; + short int i; + + mlxsw_reg_qpdpm_pack(qpdpm_pl, mlxsw_sp_port->local_port); + for (i = 0; i < ARRAY_SIZE(map->map); ++i) + mlxsw_reg_qpdpm_dscp_pack(qpdpm_pl, i, map->map[i]); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpdpm), qpdpm_pl); +} + +static int +mlxsw_sp_port_dcb_app_update_qpdsm(struct mlxsw_sp_port *mlxsw_sp_port, + struct dcb_ieee_app_prio_map *map) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char qpdsm_pl[MLXSW_REG_QPDSM_LEN]; + short int i; + + mlxsw_reg_qpdsm_pack(qpdsm_pl, mlxsw_sp_port->local_port); + for (i = 0; i < ARRAY_SIZE(map->map); ++i) + mlxsw_reg_qpdsm_prio_pack(qpdsm_pl, i, map->map[i]); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpdsm), qpdsm_pl); +} + +static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct dcb_ieee_app_prio_map prio_map; + struct dcb_ieee_app_dscp_map dscp_map; + u8 default_prio; + bool have_dscp; + int err; + + default_prio = mlxsw_sp_port_dcb_app_default_prio(mlxsw_sp_port); + have_dscp = mlxsw_sp_port_dcb_app_prio_dscp_map(mlxsw_sp_port, + &prio_map); + + if (!have_dscp) { + err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port, + MLXSW_REG_QPTS_TRUST_STATE_PCP); + if (err) + netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n"); + return err; + } + + mlxsw_sp_port_dcb_app_dscp_prio_map(mlxsw_sp_port, default_prio, + &dscp_map); + err = mlxsw_sp_port_dcb_app_update_qpdpm(mlxsw_sp_port, + &dscp_map); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Couldn't configure priority map\n"); + return err; + } + + err = mlxsw_sp_port_dcb_app_update_qpdsm(mlxsw_sp_port, + &prio_map); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Couldn't configure DSCP rewrite map\n"); + return err; + } + + err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port, + MLXSW_REG_QPTS_TRUST_STATE_DSCP); + if (err) { + /* A failure to set trust DSCP means that the QPDPM and QPDSM + * maps installed above are not in effect. And since we are here + * attempting to set trust DSCP, we couldn't have attempted to + * switch trust to PCP. Thus no cleanup is necessary. + */ + netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L3\n"); + return err; + } + + return 0; +} + +static int mlxsw_sp_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err; + + err = mlxsw_sp_dcbnl_app_validate(dev, app); + if (err) + return err; + + err = dcb_ieee_setapp(dev, app); + if (err) + return err; + + err = mlxsw_sp_port_dcb_app_update(mlxsw_sp_port); + if (err) + goto err_update; + + return 0; + +err_update: + dcb_ieee_delapp(dev, app); + return err; +} + +static int mlxsw_sp_dcbnl_ieee_delapp(struct net_device *dev, + struct dcb_app *app) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + int err; + + err = dcb_ieee_delapp(dev, app); + if (err) + return err; + + err = mlxsw_sp_port_dcb_app_update(mlxsw_sp_port); + if (err) + netdev_err(dev, "Failed to update DCB APP configuration\n"); + return 0; +} + static int mlxsw_sp_dcbnl_ieee_getmaxrate(struct net_device *dev, struct ieee_maxrate *maxrate) { @@ -394,6 +658,8 @@ static const struct dcbnl_rtnl_ops mlxsw_sp_dcbnl_ops = { .ieee_setmaxrate = mlxsw_sp_dcbnl_ieee_setmaxrate, .ieee_getpfc = mlxsw_sp_dcbnl_ieee_getpfc, .ieee_setpfc = mlxsw_sp_dcbnl_ieee_setpfc, + .ieee_setapp = mlxsw_sp_dcbnl_ieee_setapp, + .ieee_delapp = mlxsw_sp_dcbnl_ieee_delapp, .getdcbx = mlxsw_sp_dcbnl_getdcbx, .setdcbx = mlxsw_sp_dcbnl_setdcbx, @@ -467,6 +733,7 @@ int mlxsw_sp_port_dcb_init(struct mlxsw_sp_port *mlxsw_sp_port) if (err) goto err_port_pfc_init; + mlxsw_sp_port->dcb.trust_state = MLXSW_REG_QPTS_TRUST_STATE_PCP; mlxsw_sp_port->dev->dcbnl_ops = &mlxsw_sp_dcbnl_ops; return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 8d67f0123699..eec7166fad62 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2436,17 +2436,48 @@ static void mlxsw_sp_router_mp_hash_event_work(struct work_struct *work) kfree(net_work); } +static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp); + +static void mlxsw_sp_router_update_priority_work(struct work_struct *work) +{ + struct mlxsw_sp_netevent_work *net_work = + container_of(work, struct mlxsw_sp_netevent_work, work); + struct mlxsw_sp *mlxsw_sp = net_work->mlxsw_sp; + + __mlxsw_sp_router_init(mlxsw_sp); + kfree(net_work); +} + +static int mlxsw_sp_router_schedule_work(struct net *net, + struct notifier_block *nb, + void (*cb)(struct work_struct *)) +{ + struct mlxsw_sp_netevent_work *net_work; + struct mlxsw_sp_router *router; + + if (!net_eq(net, &init_net)) + return NOTIFY_DONE; + + net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC); + if (!net_work) + return NOTIFY_BAD; + + router = container_of(nb, struct mlxsw_sp_router, netevent_nb); + INIT_WORK(&net_work->work, cb); + net_work->mlxsw_sp = router->mlxsw_sp; + mlxsw_core_schedule_work(&net_work->work); + return NOTIFY_DONE; +} + static int mlxsw_sp_router_netevent_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct mlxsw_sp_netevent_work *net_work; struct mlxsw_sp_port *mlxsw_sp_port; - struct mlxsw_sp_router *router; struct mlxsw_sp *mlxsw_sp; unsigned long interval; struct neigh_parms *p; struct neighbour *n; - struct net *net; switch (event) { case NETEVENT_DELAY_PROBE_TIME_UPDATE: @@ -2500,20 +2531,12 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb, break; case NETEVENT_IPV4_MPATH_HASH_UPDATE: case NETEVENT_IPV6_MPATH_HASH_UPDATE: - net = ptr; + return mlxsw_sp_router_schedule_work(ptr, nb, + mlxsw_sp_router_mp_hash_event_work); - if (!net_eq(net, &init_net)) - return NOTIFY_DONE; - - net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC); - if (!net_work) - return NOTIFY_BAD; - - router = container_of(nb, struct mlxsw_sp_router, netevent_nb); - INIT_WORK(&net_work->work, mlxsw_sp_router_mp_hash_event_work); - net_work->mlxsw_sp = router->mlxsw_sp; - mlxsw_core_schedule_work(&net_work->work); - break; + case NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE: + return mlxsw_sp_router_schedule_work(ptr, nb, + mlxsw_sp_router_update_priority_work); } return NOTIFY_DONE; @@ -7382,6 +7405,7 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp) static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { + bool usp = init_net.ipv4.sysctl_ip_fwd_update_priority; char rgcr_pl[MLXSW_REG_RGCR_LEN]; u64 max_rifs; int err; @@ -7392,7 +7416,7 @@ static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_rgcr_pack(rgcr_pl, true, true); mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); - mlxsw_reg_rgcr_usp_set(rgcr_pl, true); + mlxsw_reg_rgcr_usp_set(rgcr_pl, usp); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); if (err) return err; diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index cd41911013e9..bb323f269839 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2941,7 +2941,7 @@ static int lan743x_pm_resume(struct device *dev) return 0; } -const struct dev_pm_ops lan743x_pm_ops = { +static const struct dev_pm_ops lan743x_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume) }; #endif /*CONFIG_PM */ diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig index 71899009c468..c26e0f70c494 100644 --- a/drivers/net/ethernet/neterion/Kconfig +++ b/drivers/net/ethernet/neterion/Kconfig @@ -2,8 +2,8 @@ # Exar device configuration # -config NET_VENDOR_EXAR - bool "Exar devices" +config NET_VENDOR_NETERION + bool "Neterion (Exar) devices" default y depends on PCI ---help--- @@ -11,16 +11,19 @@ config NET_VENDOR_EXAR Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about Exar cards. If you say Y, you will be asked for - your specific card in the following questions. + the questions about Neterion/Exar cards. If you say Y, you will be + asked for your specific card in the following questions. -if NET_VENDOR_EXAR +if NET_VENDOR_NETERION config S2IO - tristate "Exar Xframe 10Gb Ethernet Adapter" + tristate "Neterion (Exar) Xframe 10Gb Ethernet Adapter" depends on PCI ---help--- This driver supports Exar Corp's Xframe Series 10Gb Ethernet Adapters. + These were originally released from S2IO, which renamed itself + Neterion. So, the adapters might be labeled as either one, depending + on its age. More specific information on configuring the driver is in <file:Documentation/networking/s2io.txt>. @@ -29,11 +32,13 @@ config S2IO will be called s2io. config VXGE - tristate "Exar X3100 Series 10GbE PCIe Server Adapter" + tristate "Neterion (Exar) X3100 Series 10GbE PCIe Server Adapter" depends on PCI ---help--- This driver supports Exar Corp's X3100 Series 10 GbE PCIe - I/O Virtualized Server Adapter. + I/O Virtualized Server Adapter. These were originally released from + Neterion, which was later acquired by Exar. So, the adapters might be + labeled as either one, depending on its age. More specific information on configuring the driver is in <file:Documentation/networking/vxge.txt>. @@ -50,4 +55,4 @@ config VXGE_DEBUG_TRACE_ALL the vxge driver. By default only few debug trace statements are enabled. -endif # NET_VENDOR_EXAR +endif # NET_VENDOR_NETERION diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 358ed6118881..a2c0a93ca8b6 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -14,7 +14,6 @@ #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/pci.h> -#include <linux/pci_hotplug.h> #include <linux/slab.h> #include "vxge-traffic.h" diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 1decf3a1cad3..e57d23746585 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -80,7 +80,7 @@ nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port) return NFP_REPR_TYPE_VF; } - return NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC; + return __NFP_REPR_TYPE_MAX; } static struct net_device * @@ -91,6 +91,8 @@ nfp_flower_repr_get(struct nfp_app *app, u32 port_id) u8 port = 0; repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port); + if (repr_type > NFP_REPR_TYPE_MAX) + return NULL; reprs = rcu_dereference(app->reprs[repr_type]); if (!reprs) diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 78afe75129ab..382bb93cb090 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, payload.dst_ipv4 = flow->daddr; /* If entry has expired send dst IP with all other fields 0. */ - if (!(neigh->nud_state & NUD_VALID)) { + if (!(neigh->nud_state & NUD_VALID) || neigh->dead) { nfp_tun_del_route_from_cache(app, payload.dst_ipv4); /* Trigger ARP to verify invalid neighbour state. */ neigh_event_send(neigh, NULL); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 152283d7e59c..4a540c5e27fe 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -236,16 +236,20 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf) int err; pf->limit_vfs = nfp_rtsym_read_le(pf->rtbl, "nfd_vf_cfg_max_vfs", &err); - if (!err) - return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs); + if (err) { + /* For backwards compatibility if symbol not found allow all */ + pf->limit_vfs = ~0; + if (err == -ENOENT) + return 0; - pf->limit_vfs = ~0; - /* Allow any setting for backwards compatibility if symbol not found */ - if (err == -ENOENT) - return 0; + nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err); + return err; + } - nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err); - return err; + err = pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs); + if (err) + nfp_warn(pf->cpp, "Failed to set VF count in sysfs: %d\n", err); + return 0; } static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 8970ec981e11..439e6ffe2f05 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -250,7 +250,7 @@ struct nfp_net_tx_ring { struct nfp_net_tx_desc *txds; dma_addr_t dma; - unsigned int size; + size_t size; bool is_xdp; } ____cacheline_aligned; @@ -350,9 +350,9 @@ struct nfp_net_rx_buf { * @qcp_fl: Pointer to base of the QCP freelist queue * @rxbufs: Array of transmitted FL/RX buffers * @rxds: Virtual address of FL/RX ring in host memory + * @xdp_rxq: RX-ring info avail for XDP * @dma: DMA address of the FL/RX ring * @size: Size, in bytes, of the FL/RX ring (needed to free) - * @xdp_rxq: RX-ring info avail for XDP */ struct nfp_net_rx_ring { struct nfp_net_r_vector *r_vec; @@ -364,14 +364,15 @@ struct nfp_net_rx_ring { u32 idx; int fl_qcidx; - unsigned int size; u8 __iomem *qcp_fl; struct nfp_net_rx_buf *rxbufs; struct nfp_net_rx_desc *rxds; - dma_addr_t dma; struct xdp_rxq_info xdp_rxq; + + dma_addr_t dma; + size_t size; } ____cacheline_aligned; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index cf1704e972b7..7c1a921d178d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -53,6 +53,8 @@ #include <linux/interrupt.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/mm.h> +#include <linux/overflow.h> #include <linux/page_ref.h> #include <linux/pci.h> #include <linux/pci_regs.h> @@ -1120,7 +1122,7 @@ nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) tx_ring->rd_p++; } - memset(tx_ring->txds, 0, sizeof(*tx_ring->txds) * tx_ring->cnt); + memset(tx_ring->txds, 0, tx_ring->size); tx_ring->wr_p = 0; tx_ring->rd_p = 0; tx_ring->qcp_rd_p = 0; @@ -1300,7 +1302,7 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring) rx_ring->rxbufs[last_idx].dma_addr = 0; rx_ring->rxbufs[last_idx].frag = NULL; - memset(rx_ring->rxds, 0, sizeof(*rx_ring->rxds) * rx_ring->cnt); + memset(rx_ring->rxds, 0, rx_ring->size); rx_ring->wr_p = 0; rx_ring->rd_p = 0; } @@ -2126,7 +2128,7 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring) struct nfp_net_r_vector *r_vec = tx_ring->r_vec; struct nfp_net_dp *dp = &r_vec->nfp_net->dp; - kfree(tx_ring->txbufs); + kvfree(tx_ring->txbufs); if (tx_ring->txds) dma_free_coherent(dp->dev, tx_ring->size, @@ -2150,18 +2152,17 @@ static int nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; - int sz; tx_ring->cnt = dp->txd_cnt; - tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt; + tx_ring->size = array_size(tx_ring->cnt, sizeof(*tx_ring->txds)); tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->txds) goto err_alloc; - sz = sizeof(*tx_ring->txbufs) * tx_ring->cnt; - tx_ring->txbufs = kzalloc(sz, GFP_KERNEL); + tx_ring->txbufs = kvcalloc(tx_ring->cnt, sizeof(*tx_ring->txbufs), + GFP_KERNEL); if (!tx_ring->txbufs) goto err_alloc; @@ -2275,7 +2276,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) if (dp->netdev) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - kfree(rx_ring->rxbufs); + kvfree(rx_ring->rxbufs); if (rx_ring->rxds) dma_free_coherent(dp->dev, rx_ring->size, @@ -2298,7 +2299,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring) static int nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) { - int sz, err; + int err; if (dp->netdev) { err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, dp->netdev, @@ -2308,14 +2309,14 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) } rx_ring->cnt = dp->rxd_cnt; - rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt; + rx_ring->size = array_size(rx_ring->cnt, sizeof(*rx_ring->rxds)); rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->rxds) goto err_alloc; - sz = sizeof(*rx_ring->rxbufs) * rx_ring->cnt; - rx_ring->rxbufs = kzalloc(sz, GFP_KERNEL); + rx_ring->rxbufs = kvcalloc(rx_ring->cnt, sizeof(*rx_ring->rxbufs), + GFP_KERNEL); if (!rx_ring->rxbufs) goto err_alloc; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 7cbd0174459c..1d9b0d44ddb6 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -5777,7 +5777,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) (np->rx_ring_size + np->tx_ring_size), &np->ring_addr, - GFP_ATOMIC); + GFP_KERNEL); if (!np->rx_ring.orig) goto out_unmap; np->tx_ring.orig = &np->rx_ring.orig[np->rx_ring_size]; @@ -5786,7 +5786,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) sizeof(struct ring_desc_ex) * (np->rx_ring_size + np->tx_ring_size), - &np->ring_addr, GFP_ATOMIC); + &np->ring_addr, GFP_KERNEL); if (!np->rx_ring.ex) goto out_unmap; np->tx_ring.ex = &np->rx_ring.ex[np->rx_ring_size]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index b5b5ff725426..f1977aa440e5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -1531,7 +1531,7 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn, } /* CM PF */ -void qed_cm_init_pf(struct qed_hwfn *p_hwfn) +static void qed_cm_init_pf(struct qed_hwfn *p_hwfn) { /* XCM pure-LB queue */ STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 12b4c2ab5796..d02e774c8d66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -867,7 +867,7 @@ static int qed_dcbx_read_mib(struct qed_hwfn *p_hwfn, return rc; } -void qed_dcbx_aen(struct qed_hwfn *hwfn, u32 mib_type) +static void qed_dcbx_aen(struct qed_hwfn *hwfn, u32 mib_type) { struct qed_common_cb_ops *op = hwfn->cdev->protocol_ops.common; void *cookie = hwfn->cdev->ops_cookie; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 4340c4c90bcb..1aa9fc1c5890 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -7838,8 +7838,8 @@ int qed_dbg_igu_fifo_size(struct qed_dev *cdev) return qed_dbg_feature_size(cdev, DBG_FEATURE_IGU_FIFO); } -int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn, - enum qed_nvm_images image_id, u32 *length) +static int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn, + enum qed_nvm_images image_id, u32 *length) { struct qed_nvm_image_att image_att; int rc; @@ -7854,8 +7854,9 @@ int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn, return rc; } -int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer, - u32 *num_dumped_bytes, enum qed_nvm_images image_id) +static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes, + enum qed_nvm_images image_id) { struct qed_hwfn *p_hwfn = &cdev->hwfns[cdev->dbg_params.engine_for_debug]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index e5249b4741d0..6a0b46f214f4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -230,12 +230,12 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn) } /* Getters for resource amounts necessary for qm initialization */ -u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn) +static u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn) { return p_hwfn->hw_info.num_hw_tc; } -u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn) +static u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn) { return IS_QED_SRIOV(p_hwfn->cdev) ? p_hwfn->cdev->p_iov_info->total_vfs : 0; @@ -243,7 +243,7 @@ u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn) #define NUM_DEFAULT_RLS 1 -u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn) +static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn) { u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn); @@ -261,7 +261,7 @@ u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn) return num_pf_rls; } -u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn) +static u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn) { u32 pq_flags = qed_get_pq_flags(p_hwfn); @@ -273,7 +273,7 @@ u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn) } /* calc amount of PQs according to the requested flags */ -u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn) +static u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn) { u32 pq_flags = qed_get_pq_flags(p_hwfn); @@ -507,16 +507,6 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf) return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf; } -u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl) -{ - u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn); - - if (rl > max_rl) - DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl); - - return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl; -} - /* Functions for creating specific types of pqs */ static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index d845badf9b90..d6430dfebd83 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -1225,19 +1225,6 @@ void qed_gft_disable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 pf_id) 0); } -void qed_set_gft_event_id_cm_hdr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) -{ - u32 rfs_cm_hdr_event_id; - - /* Set RFS event ID to be awakened i Tstorm By Prs */ - rfs_cm_hdr_event_id = qed_rd(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT); - rfs_cm_hdr_event_id |= T_ETH_PACKET_ACTION_GFT_EVENTID << - PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT; - rfs_cm_hdr_event_id |= PARSER_ETH_CONN_GFT_ACTION_CM_HDR << - PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT; - qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, rfs_cm_hdr_event_id); -} - void qed_gft_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 pf_id, diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index c0d4a54a5edb..1135387bd99d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -873,8 +873,8 @@ static void qed_iscsi_release_connection(struct qed_hwfn *p_hwfn, spin_unlock_bh(&p_hwfn->p_iscsi_info->lock); } -void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn, - struct qed_iscsi_conn *p_conn) +static void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn, + struct qed_iscsi_conn *p_conn) { qed_chain_free(p_hwfn->cdev, &p_conn->xhq); qed_chain_free(p_hwfn->cdev, &p_conn->uhq); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 90a2b53096e2..17f3dfa2cc94 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -377,7 +377,7 @@ qed_iwarp2roce_state(enum qed_iwarp_qp_state state) } } -const char *iwarp_state_names[] = { +const static char *iwarp_state_names[] = { "IDLE", "RTS", "TERMINATE", @@ -942,7 +942,7 @@ qed_iwarp_return_ep(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep) spin_unlock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock); } -void +static void qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep) { struct mpa_v2_hdr *mpa_v2_params; @@ -967,7 +967,7 @@ qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep) mpa_data_size; } -void +static void qed_iwarp_mpa_reply_arrived(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep) { struct qed_iwarp_cm_event_params params; @@ -2500,7 +2500,7 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, /* The only slowpath for iwarp ll2 is unalign flush. When this completion * is received, need to reset the FPDU. */ -void +static void qed_iwarp_ll2_slowpath(void *cxt, u8 connection_handle, u32 opaque_data_0, u32 opaque_data_1) @@ -2803,8 +2803,9 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return qed_iwarp_ll2_stop(p_hwfn, p_ptt); } -void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn, - struct qed_iwarp_ep *ep, u8 fw_return_code) +static void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn, + struct qed_iwarp_ep *ep, + u8 fw_return_code) { struct qed_iwarp_cm_event_params params; @@ -2824,8 +2825,9 @@ void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn, ep->event_cb(ep->cb_context, ¶ms); } -void qed_iwarp_exception_received(struct qed_hwfn *p_hwfn, - struct qed_iwarp_ep *ep, int fw_ret_code) +static void qed_iwarp_exception_received(struct qed_hwfn *p_hwfn, + struct qed_iwarp_ep *ep, + int fw_ret_code) { struct qed_iwarp_cm_event_params params; bool event_cb = false; @@ -2954,7 +2956,7 @@ qed_iwarp_tcp_connect_unsuccessful(struct qed_hwfn *p_hwfn, } } -void +static void qed_iwarp_connect_complete(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep, u8 fw_return_code) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 99973e10b179..5ede6408649d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn, p_ramrod->common.update_approx_mcast_flg = 1; for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { - u32 *p_bins = (u32 *)p_params->bins; + u32 *p_bins = p_params->bins; p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]); } @@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data) { - unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct vport_update_ramrod_data *p_ramrod = NULL; + u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; u8 abs_vport_id = 0; @@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, /* explicitly clear out the entire vector */ memset(&p_ramrod->approx_mcast.bins, 0, sizeof(p_ramrod->approx_mcast.bins)); - memset(bins, 0, sizeof(unsigned long) * - ETH_MULTICAST_MAC_BINS_IN_REGS); + memset(bins, 0, sizeof(bins)); /* filter ADD op is explicit set op and it removes * any existing filters for the vport */ if (p_filter_cmd->opcode == QED_FILTER_ADD) { for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) { - u32 bit; + u32 bit, nbits; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, bins); + nbits = sizeof(u32) * BITS_PER_BYTE; + bins[bit / nbits] |= 1 << (bit % nbits); } /* Convert to correct endianity */ for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { struct vport_update_ramrod_mcast *p_ramrod_bins; - u32 *p_bins = (u32 *)bins; p_ramrod_bins = &p_ramrod->approx_mcast; - p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]); + p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 806a8da257e9..8d80f1095d17 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -215,7 +215,7 @@ struct qed_sp_vport_update_params { u8 anti_spoofing_en; u8 update_accept_any_vlan_flg; u8 accept_any_vlan; - unsigned long bins[8]; + u32 bins[8]; struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 012973d75ad0..14ac9cab2653 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -158,7 +158,8 @@ static void qed_ll2_kill_buffers(struct qed_dev *cdev) qed_ll2_dealloc_buffer(cdev, buffer); } -void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data) +static void qed_ll2b_complete_rx_packet(void *cxt, + struct qed_ll2_comp_rx_data *data) { struct qed_hwfn *p_hwfn = cxt; struct qed_ll2_buffer *buffer = data->cookie; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 15f1b3294289..8e4f60e4520a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -570,12 +570,13 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, return 0; } -int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 cmd, - u32 param, - u32 *o_mcp_resp, - u32 *o_mcp_param, u32 i_txn_size, u32 *i_buf) +static int +qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param, u32 i_txn_size, u32 *i_buf) { struct qed_mcp_mb_params mb_params; int rc; @@ -1211,6 +1212,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, break; default: p_link->speed = 0; + p_link->link_up = 0; } if (p_link->link_up && p_link->speed) @@ -1308,9 +1310,15 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up) phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0; phy_cfg.adv_speed = params->speed.advertised_speeds; phy_cfg.loopback_mode = params->loopback_mode; - if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) { - if (params->eee.enable) - phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; + + /* There are MFWs that share this capability regardless of whether + * this is feasible or not. And given that at the very least adv_caps + * would be set internally by qed, we want to make sure LFA would + * still work. + */ + if ((p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) { + phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; if (params->eee.tx_lpi_enable) phy_cfg.eee_cfg |= EEE_CFG_TX_LPI; if (params->eee.adv_caps & QED_EEE_1G_ADV) @@ -3001,7 +3009,7 @@ static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn, return rc; } -int +static int __qed_mcp_resc_lock(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params) diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 101d677114f2..be941cfaa2d4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -134,7 +134,7 @@ static bool qed_bmap_is_empty(struct qed_bmap *bmap) return bmap->max_count == find_first_bit(bmap->bitmap, bmap->max_count); } -u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id) +static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id) { /* First sb id for RoCE is after all the l2 sb */ return FEAT_NUM((struct qed_hwfn *)p_hwfn, QED_PF_L2_QUE) + rel_sb_id; @@ -706,7 +706,7 @@ static int qed_rdma_setup(struct qed_hwfn *p_hwfn, return qed_rdma_start_fw(p_hwfn, params, p_ptt); } -int qed_rdma_stop(void *rdma_cxt) +static int qed_rdma_stop(void *rdma_cxt) { struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt; struct rdma_close_func_ramrod_data *p_ramrod; diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index b5ce1581645f..ada4c1810864 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -157,7 +157,7 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode) return flavor; } -void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid) +static void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid) { spin_lock_bh(&p_hwfn->p_rdma_info->lock); qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index fd59cf45f4be..9b08a9d9e151 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -672,8 +672,8 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn) return 0; } -bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, - int vfid, bool b_fail_malicious) +static bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, + int vfid, bool b_fail_malicious) { /* Check PF supports sriov */ if (IS_VF(p_hwfn->cdev) || !IS_QED_SRIOV(p_hwfn->cdev) || @@ -687,7 +687,7 @@ bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, return true; } -bool qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, int vfid) +static bool qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, int vfid) { return _qed_iov_pf_sanity_check(p_hwfn, vfid, true); } @@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn, p_data->update_approx_mcast_flg = 1; memcpy(p_data->bins, p_mcast_tlv->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); *tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST; } @@ -3979,7 +3979,7 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn, } } -void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events) +static void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events) { int i; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 2d7fcd6a0777..3d4269659820 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -169,7 +169,7 @@ static void qed_vf_pf_add_qid(struct qed_hwfn *p_hwfn, p_qid_tlv->qid = p_cid->qid_usage_idx; } -int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final) +static int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final) { struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; struct pfvf_def_resp_tlv *resp; @@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, resp_size += sizeof(struct pfvf_def_resp_tlv); memcpy(p_mcast_tlv->bins, p_params->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); } update_rx = p_params->accept_flags.update_rx_mode_config; @@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn, u32 bit; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, sp_params.bins); + sp_params.bins[bit / 32] |= 1 << (bit % 32); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 4f05d5eb3cf5..033409db86ae 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv { struct channel_tlv tl; u8 padding[4]; - u64 bins[8]; + /* There are only 256 approx bins, and in HSI they're divided into + * 32-bit values. As old VFs used to set-bit to the values on its side, + * the upper half of the array is never expected to contain any data. + */ + u64 bins[4]; + u64 obsolete_bins[4]; }; struct vfpf_vport_update_accept_param_tlv { diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 49a6e25ddc2b..8ea1fa36ca43 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7396,8 +7396,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } - /* override BIOS settings, use userspace tools to enable WOL */ - __rtl8169_set_wol(tp, 0); + tp->saved_wolopts = __rtl8169_get_wol(tp); mutex_init(&tp->wk.mutex); u64_stats_init(&tp->rx_stats.syncp); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d9e60cfd8a85..9d104a05044d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -53,7 +53,7 @@ #include "dwmac1000.h" #include "hwif.h" -#define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) +#define STMMAC_ALIGN(x) __ALIGN_KERNEL(x, SMP_CACHE_BYTES) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) /* Module parameters */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 8d375e51a526..6a393b16a1fc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -257,7 +257,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, return -ENOMEM; /* Enable pci device */ - ret = pcim_enable_device(pdev); + ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); @@ -300,9 +300,45 @@ static int stmmac_pci_probe(struct pci_dev *pdev, static void stmmac_pci_remove(struct pci_dev *pdev) { stmmac_dvr_remove(&pdev->dev); + pci_disable_device(pdev); } -static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume); +static int stmmac_pci_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = stmmac_suspend(dev); + if (ret) + return ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + return 0; +} + +static int stmmac_pci_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return stmmac_resume(dev); +} + +static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume); /* synthetic ID, no official vendor */ #define PCI_VENDOR_ID_STMMAC 0x700 diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 171abcfb6184..f051ce35a440 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -565,40 +565,28 @@ static const struct cpsw_stats cpsw_gstrings_ch_stats[] = { (func)(slave++, ##arg); \ } while (0) -#define cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb) \ - do { \ - if (!cpsw->data.dual_emac) \ - break; \ - if (CPDMA_RX_SOURCE_PORT(status) == 1) { \ - ndev = cpsw->slaves[0].ndev; \ - skb->dev = ndev; \ - } else if (CPDMA_RX_SOURCE_PORT(status) == 2) { \ - ndev = cpsw->slaves[1].ndev; \ - skb->dev = ndev; \ - } \ - } while (0) -#define cpsw_add_mcast(cpsw, priv, addr) \ - do { \ - if (cpsw->data.dual_emac) { \ - struct cpsw_slave *slave = cpsw->slaves + \ - priv->emac_port; \ - int slave_port = cpsw_get_slave_port( \ - slave->slave_num); \ - cpsw_ale_add_mcast(cpsw->ale, addr, \ - 1 << slave_port | ALE_PORT_HOST, \ - ALE_VLAN, slave->port_vlan, 0); \ - } else { \ - cpsw_ale_add_mcast(cpsw->ale, addr, \ - ALE_ALL_PORTS, \ - 0, 0, 0); \ - } \ - } while (0) - static inline int cpsw_get_slave_port(u32 slave_num) { return slave_num + 1; } +static void cpsw_add_mcast(struct cpsw_priv *priv, u8 *addr) +{ + struct cpsw_common *cpsw = priv->cpsw; + + if (cpsw->data.dual_emac) { + struct cpsw_slave *slave = cpsw->slaves + priv->emac_port; + int slave_port = cpsw_get_slave_port(slave->slave_num); + + cpsw_ale_add_mcast(cpsw->ale, addr, + 1 << slave_port | ALE_PORT_HOST, + ALE_VLAN, slave->port_vlan, 0); + return; + } + + cpsw_ale_add_mcast(cpsw->ale, addr, ALE_ALL_PORTS, 0, 0, 0); +} + static void cpsw_set_promiscious(struct net_device *ndev, bool enable) { struct cpsw_common *cpsw = ndev_to_cpsw(ndev); @@ -706,7 +694,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* program multicast address list into ALE register */ netdev_for_each_mc_addr(ha, ndev) { - cpsw_add_mcast(cpsw, priv, (u8 *)ha->addr); + cpsw_add_mcast(priv, ha->addr); } } } @@ -798,10 +786,16 @@ static void cpsw_rx_handler(void *token, int len, int status) struct sk_buff *skb = token; struct sk_buff *new_skb; struct net_device *ndev = skb->dev; - int ret = 0; + int ret = 0, port; struct cpsw_common *cpsw = ndev_to_cpsw(ndev); - cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb); + if (cpsw->data.dual_emac) { + port = CPDMA_RX_SOURCE_PORT(status); + if (port) { + ndev = cpsw->slaves[--port].ndev; + skb->dev = ndev; + } + } if (unlikely(status < 0) || unlikely(!netif_running(ndev))) { /* In dual emac mode check for all interfaces */ @@ -3287,7 +3281,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) priv_sl2->emac_port = 1; cpsw->slaves[1].ndev = ndev; - ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX; ndev->netdev_ops = &cpsw_netdev_ops; ndev->ethtool_ops = &cpsw_ethtool_ops; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 16c3bfbe1992..757a3b37ae8a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -218,6 +218,7 @@ issue: ret = of_mdiobus_register(bus, np1); if (ret) { mdiobus_free(bus); + lp->mii_bus = NULL; return ret; } return 0; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 4b6e308199d2..a32ded5b4f41 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -873,6 +873,17 @@ struct netvsc_ethtool_stats { unsigned long wake_queue; }; +struct netvsc_ethtool_pcpu_stats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + u64 vf_rx_packets; + u64 vf_rx_bytes; + u64 vf_tx_packets; + u64 vf_tx_bytes; +}; + struct netvsc_vf_pcpu_stats { u64 rx_packets; u64 rx_bytes; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index cf4f40a04194..20275d1e6f9a 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1118,6 +1118,64 @@ static void netvsc_get_vf_stats(struct net_device *net, } } +static void netvsc_get_pcpu_stats(struct net_device *net, + struct netvsc_ethtool_pcpu_stats *pcpu_tot) +{ + struct net_device_context *ndev_ctx = netdev_priv(net); + struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev); + int i; + + /* fetch percpu stats of vf */ + for_each_possible_cpu(i) { + const struct netvsc_vf_pcpu_stats *stats = + per_cpu_ptr(ndev_ctx->vf_stats, i); + struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i]; + unsigned int start; + + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + this_tot->vf_rx_packets = stats->rx_packets; + this_tot->vf_tx_packets = stats->tx_packets; + this_tot->vf_rx_bytes = stats->rx_bytes; + this_tot->vf_tx_bytes = stats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + this_tot->rx_packets = this_tot->vf_rx_packets; + this_tot->tx_packets = this_tot->vf_tx_packets; + this_tot->rx_bytes = this_tot->vf_rx_bytes; + this_tot->tx_bytes = this_tot->vf_tx_bytes; + } + + /* fetch percpu stats of netvsc */ + for (i = 0; i < nvdev->num_chn; i++) { + const struct netvsc_channel *nvchan = &nvdev->chan_table[i]; + const struct netvsc_stats *stats; + struct netvsc_ethtool_pcpu_stats *this_tot = + &pcpu_tot[nvchan->channel->target_cpu]; + u64 packets, bytes; + unsigned int start; + + stats = &nvchan->tx_stats; + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + packets = stats->packets; + bytes = stats->bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + this_tot->tx_bytes += bytes; + this_tot->tx_packets += packets; + + stats = &nvchan->rx_stats; + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + packets = stats->packets; + bytes = stats->bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + this_tot->rx_bytes += bytes; + this_tot->rx_packets += packets; + } +} + static void netvsc_get_stats64(struct net_device *net, struct rtnl_link_stats64 *t) { @@ -1215,6 +1273,23 @@ static const struct { { "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) }, { "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) }, { "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) }, +}, pcpu_stats[] = { + { "cpu%u_rx_packets", + offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) }, + { "cpu%u_rx_bytes", + offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) }, + { "cpu%u_tx_packets", + offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) }, + { "cpu%u_tx_bytes", + offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) }, + { "cpu%u_vf_rx_packets", + offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) }, + { "cpu%u_vf_rx_bytes", + offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) }, + { "cpu%u_vf_tx_packets", + offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) }, + { "cpu%u_vf_tx_bytes", + offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) }, }, vf_stats[] = { { "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) }, { "vf_rx_bytes", offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) }, @@ -1226,6 +1301,9 @@ static const struct { #define NETVSC_GLOBAL_STATS_LEN ARRAY_SIZE(netvsc_stats) #define NETVSC_VF_STATS_LEN ARRAY_SIZE(vf_stats) +/* statistics per queue (rx/tx packets/bytes) */ +#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats)) + /* 4 statistics per queue (rx/tx packets/bytes) */ #define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4) @@ -1241,7 +1319,8 @@ static int netvsc_get_sset_count(struct net_device *dev, int string_set) case ETH_SS_STATS: return NETVSC_GLOBAL_STATS_LEN + NETVSC_VF_STATS_LEN - + NETVSC_QUEUE_STATS_LEN(nvdev); + + NETVSC_QUEUE_STATS_LEN(nvdev) + + NETVSC_PCPU_STATS_LEN; default: return -EINVAL; } @@ -1255,9 +1334,10 @@ static void netvsc_get_ethtool_stats(struct net_device *dev, const void *nds = &ndc->eth_stats; const struct netvsc_stats *qstats; struct netvsc_vf_pcpu_stats sum; + struct netvsc_ethtool_pcpu_stats *pcpu_sum; unsigned int start; u64 packets, bytes; - int i, j; + int i, j, cpu; if (!nvdev) return; @@ -1289,6 +1369,19 @@ static void netvsc_get_ethtool_stats(struct net_device *dev, data[i++] = packets; data[i++] = bytes; } + + pcpu_sum = kvmalloc_array(num_possible_cpus(), + sizeof(struct netvsc_ethtool_pcpu_stats), + GFP_KERNEL); + netvsc_get_pcpu_stats(dev, pcpu_sum); + for_each_present_cpu(cpu) { + struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu]; + + for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++) + data[i++] = *(u64 *)((void *)this_sum + + pcpu_stats[j].offset); + } + kvfree(pcpu_sum); } static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -1296,7 +1389,7 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data) struct net_device_context *ndc = netdev_priv(dev); struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev); u8 *p = data; - int i; + int i, cpu; if (!nvdev) return; @@ -1324,6 +1417,13 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; } + for_each_present_cpu(cpu) { + for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++) { + sprintf(p, pcpu_stats[i].name, cpu); + p += ETH_GSTRING_LEN; + } + } + break; } } diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index d00d42c845b7..7ae1856d1f18 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -220,14 +220,14 @@ static int net_failover_change_mtu(struct net_device *dev, int new_mtu) struct net_device *primary_dev, *standby_dev; int ret = 0; - primary_dev = rcu_dereference(nfo_info->primary_dev); + primary_dev = rtnl_dereference(nfo_info->primary_dev); if (primary_dev) { ret = dev_set_mtu(primary_dev, new_mtu); if (ret) return ret; } - standby_dev = rcu_dereference(nfo_info->standby_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); if (standby_dev) { ret = dev_set_mtu(standby_dev, new_mtu); if (ret) { diff --git a/drivers/net/netdevsim/devlink.c b/drivers/net/netdevsim/devlink.c index ba663e5af168..5135fc371f01 100644 --- a/drivers/net/netdevsim/devlink.c +++ b/drivers/net/netdevsim/devlink.c @@ -207,6 +207,7 @@ void nsim_devlink_teardown(struct netdevsim *ns) struct net *net = nsim_to_net(ns); bool *reg_devlink = net_generic(net, nsim_devlink_id); + devlink_resources_unregister(ns->devlink, NULL); devlink_unregister(ns->devlink); devlink_free(ns->devlink); ns->devlink = NULL; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 2d244551298b..8d8e2b3f263e 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -41,6 +41,9 @@ struct nsim_vf_config { static u32 nsim_dev_id; +static struct dentry *nsim_ddir; +static struct dentry *nsim_sdev_ddir; + static int nsim_num_vf(struct device *dev) { struct netdevsim *ns = to_nsim(dev); @@ -566,9 +569,6 @@ static struct rtnl_link_ops nsim_link_ops __read_mostly = { .dellink = nsim_dellink, }; -struct dentry *nsim_ddir; -struct dentry *nsim_sdev_ddir; - static int __init nsim_module_init(void) { int err; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 02be199eb005..384c254fafc5 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -103,9 +103,6 @@ struct netdevsim { struct nsim_ipsec ipsec; }; -extern struct dentry *nsim_ddir; -extern struct dentry *nsim_sdev_ddir; - #ifdef CONFIG_BPF_SYSCALL int nsim_bpf_init(struct netdevsim *ns); void nsim_bpf_uninit(struct netdevsim *ns); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 1cd439bdf608..f7c69ca34056 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -679,7 +679,7 @@ static int m88e1116r_config_init(struct phy_device *phydev) if (err < 0) return err; - mdelay(500); + msleep(500); err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c index 0831b7142df7..c017486e9b86 100644 --- a/drivers/net/phy/mdio-mux-bcm-iproc.c +++ b/drivers/net/phy/mdio-mux-bcm-iproc.c @@ -13,7 +13,7 @@ * You should have received a copy of the GNU General Public License * version 2 (GPLv2) along with this source code. */ - +#include <linux/clk.h> #include <linux/platform_device.h> #include <linux/device.h> #include <linux/of_mdio.h> @@ -22,7 +22,14 @@ #include <linux/mdio-mux.h> #include <linux/delay.h> -#define MDIO_PARAM_OFFSET 0x00 +#define MDIO_RATE_ADJ_EXT_OFFSET 0x000 +#define MDIO_RATE_ADJ_INT_OFFSET 0x004 +#define MDIO_RATE_ADJ_DIVIDENT_SHIFT 16 + +#define MDIO_SCAN_CTRL_OFFSET 0x008 +#define MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR 28 + +#define MDIO_PARAM_OFFSET 0x23c #define MDIO_PARAM_MIIM_CYCLE 29 #define MDIO_PARAM_INTERNAL_SEL 25 #define MDIO_PARAM_BUS_ID 22 @@ -30,27 +37,56 @@ #define MDIO_PARAM_PHY_ID 16 #define MDIO_PARAM_PHY_DATA 0 -#define MDIO_READ_OFFSET 0x04 +#define MDIO_READ_OFFSET 0x240 #define MDIO_READ_DATA_MASK 0xffff -#define MDIO_ADDR_OFFSET 0x08 +#define MDIO_ADDR_OFFSET 0x244 -#define MDIO_CTRL_OFFSET 0x0C +#define MDIO_CTRL_OFFSET 0x248 #define MDIO_CTRL_WRITE_OP 0x1 #define MDIO_CTRL_READ_OP 0x2 -#define MDIO_STAT_OFFSET 0x10 +#define MDIO_STAT_OFFSET 0x24c #define MDIO_STAT_DONE 1 #define BUS_MAX_ADDR 32 #define EXT_BUS_START_ADDR 16 +#define MDIO_REG_ADDR_SPACE_SIZE 0x250 + +#define MDIO_OPERATING_FREQUENCY 11000000 +#define MDIO_RATE_ADJ_DIVIDENT 1 + struct iproc_mdiomux_desc { void *mux_handle; void __iomem *base; struct device *dev; struct mii_bus *mii_bus; + struct clk *core_clk; }; +static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md) +{ + u32 divisor; + u32 val; + + /* Disable external mdio master access */ + val = readl(md->base + MDIO_SCAN_CTRL_OFFSET); + val |= BIT(MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR); + writel(val, md->base + MDIO_SCAN_CTRL_OFFSET); + + if (md->core_clk) { + /* use rate adjust regs to derrive the mdio's operating + * frequency from the specified core clock + */ + divisor = clk_get_rate(md->core_clk) / MDIO_OPERATING_FREQUENCY; + divisor = divisor / (MDIO_RATE_ADJ_DIVIDENT + 1); + val = divisor; + val |= MDIO_RATE_ADJ_DIVIDENT << MDIO_RATE_ADJ_DIVIDENT_SHIFT; + writel(val, md->base + MDIO_RATE_ADJ_EXT_OFFSET); + writel(val, md->base + MDIO_RATE_ADJ_INT_OFFSET); + } +} + static int iproc_mdio_wait_for_idle(void __iomem *base, bool result) { unsigned int timeout = 1000; /* loop for 1s */ @@ -169,18 +205,39 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev) md->dev = &pdev->dev; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res->start & 0xfff) { + /* For backward compatibility in case the + * base address is specified with an offset. + */ + dev_info(&pdev->dev, "fix base address in dt-blob\n"); + res->start &= ~0xfff; + res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1; + } md->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(md->base)) { dev_err(&pdev->dev, "failed to ioremap register\n"); return PTR_ERR(md->base); } - md->mii_bus = mdiobus_alloc(); + md->mii_bus = devm_mdiobus_alloc(&pdev->dev); if (!md->mii_bus) { dev_err(&pdev->dev, "mdiomux bus alloc failed\n"); return -ENOMEM; } + md->core_clk = devm_clk_get(&pdev->dev, NULL); + if (md->core_clk == ERR_PTR(-ENOENT) || + md->core_clk == ERR_PTR(-EINVAL)) + md->core_clk = NULL; + else if (IS_ERR(md->core_clk)) + return PTR_ERR(md->core_clk); + + rc = clk_prepare_enable(md->core_clk); + if (rc) { + dev_err(&pdev->dev, "failed to enable core clk\n"); + return rc; + } + bus = md->mii_bus; bus->priv = md; bus->name = "iProc MDIO mux bus"; @@ -194,7 +251,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev) rc = mdiobus_register(bus); if (rc) { dev_err(&pdev->dev, "mdiomux registration failed\n"); - goto out; + goto out_clk; } platform_set_drvdata(pdev, md); @@ -206,27 +263,55 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev) goto out_register; } + mdio_mux_iproc_config(md); + dev_info(md->dev, "iProc mdiomux registered\n"); return 0; out_register: mdiobus_unregister(bus); -out: - mdiobus_free(bus); +out_clk: + clk_disable_unprepare(md->core_clk); return rc; } static int mdio_mux_iproc_remove(struct platform_device *pdev) { - struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev); + struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev); mdio_mux_uninit(md->mux_handle); mdiobus_unregister(md->mii_bus); - mdiobus_free(md->mii_bus); + clk_disable_unprepare(md->core_clk); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP +static int mdio_mux_iproc_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev); + + clk_disable_unprepare(md->core_clk); return 0; } +static int mdio_mux_iproc_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev); + + clk_prepare_enable(md->core_clk); + mdio_mux_iproc_config(md); + + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(mdio_mux_iproc_pm_ops, + mdio_mux_iproc_suspend, mdio_mux_iproc_resume); + static const struct of_device_id mdio_mux_iproc_match[] = { { .compatible = "brcm,mdio-mux-iproc", @@ -239,6 +324,7 @@ static struct platform_driver mdiomux_iproc_driver = { .driver = { .name = "mdio-mux-iproc", .of_match_table = mdio_mux_iproc_match, + .pm = &mdio_mux_iproc_pm_ops, }, .probe = mdio_mux_iproc_probe, .remove = mdio_mux_iproc_remove, diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 650c2667d523..84ca9ff40ae0 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -123,7 +123,7 @@ static const struct vsc8531_edge_rate_table edge_table[] = { }; #endif /* CONFIG_OF_MDIO */ -static int vsc85xx_phy_page_set(struct phy_device *phydev, u8 page) +static int vsc85xx_phy_page_set(struct phy_device *phydev, u16 page) { int rc; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index d2baedc4ea91..1ee25877c4d1 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -471,8 +471,14 @@ static int phy_config_aneg(struct phy_device *phydev) { if (phydev->drv->config_aneg) return phydev->drv->config_aneg(phydev); - else - return genphy_config_aneg(phydev); + + /* Clause 45 PHYs that don't implement Clause 22 registers are not + * allowed to call genphy_config_aneg() + */ + if (phydev->is_c45 && !(phydev->c45_ids.devices_in_package & BIT(0))) + return -EOPNOTSUPP; + + return genphy_config_aneg(phydev); } /** @@ -519,7 +525,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) * negotiation may already be done and aneg interrupt may not be * generated. */ - if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { + if (!phy_polling_mode(phydev) && phydev->state == PHY_AN) { err = phy_aneg_done(phydev); if (err > 0) { trigger = true; @@ -977,7 +983,7 @@ void phy_state_machine(struct work_struct *work) needs_aneg = true; break; case PHY_NOLINK: - if (phydev->irq != PHY_POLL) + if (!phy_polling_mode(phydev)) break; err = phy_read_status(phydev); @@ -1018,7 +1024,7 @@ void phy_state_machine(struct work_struct *work) /* Only register a CHANGE if we are polling and link changed * since latest checking. */ - if (phydev->irq == PHY_POLL) { + if (phy_polling_mode(phydev)) { old_link = phydev->link; err = phy_read_status(phydev); if (err) @@ -1117,7 +1123,7 @@ void phy_state_machine(struct work_struct *work) * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving * between states from phy_mac_interrupt() */ - if (phydev->irq == PHY_POLL) + if (phy_polling_mode(phydev)) queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, PHY_STATE_TIME * HZ); } diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c index 6c7fd98cb00a..a205750b431b 100644 --- a/drivers/net/ppp/ppp_mppe.c +++ b/drivers/net/ppp/ppp_mppe.c @@ -96,7 +96,7 @@ static inline void sha_pad_init(struct sha_pad *shapad) */ struct ppp_mppe_state { struct crypto_skcipher *arc4; - struct crypto_ahash *sha1; + struct shash_desc *sha1; unsigned char *sha1_digest; unsigned char master_key[MPPE_MAX_KEY_LEN]; unsigned char session_key[MPPE_MAX_KEY_LEN]; @@ -136,25 +136,16 @@ struct ppp_mppe_state { */ static void get_new_key_from_sha(struct ppp_mppe_state * state) { - AHASH_REQUEST_ON_STACK(req, state->sha1); - struct scatterlist sg[4]; - unsigned int nbytes; - - sg_init_table(sg, 4); - - nbytes = setup_sg(&sg[0], state->master_key, state->keylen); - nbytes += setup_sg(&sg[1], sha_pad->sha_pad1, - sizeof(sha_pad->sha_pad1)); - nbytes += setup_sg(&sg[2], state->session_key, state->keylen); - nbytes += setup_sg(&sg[3], sha_pad->sha_pad2, - sizeof(sha_pad->sha_pad2)); - - ahash_request_set_tfm(req, state->sha1); - ahash_request_set_callback(req, 0, NULL, NULL); - ahash_request_set_crypt(req, sg, state->sha1_digest, nbytes); - - crypto_ahash_digest(req); - ahash_request_zero(req); + crypto_shash_init(state->sha1); + crypto_shash_update(state->sha1, state->master_key, + state->keylen); + crypto_shash_update(state->sha1, sha_pad->sha_pad1, + sizeof(sha_pad->sha_pad1)); + crypto_shash_update(state->sha1, state->session_key, + state->keylen); + crypto_shash_update(state->sha1, sha_pad->sha_pad2, + sizeof(sha_pad->sha_pad2)); + crypto_shash_final(state->sha1, state->sha1_digest); } /* @@ -200,6 +191,7 @@ static void mppe_rekey(struct ppp_mppe_state * state, int initial_key) static void *mppe_alloc(unsigned char *options, int optlen) { struct ppp_mppe_state *state; + struct crypto_shash *shash; unsigned int digestsize; if (optlen != CILEN_MPPE + sizeof(state->master_key) || @@ -217,13 +209,21 @@ static void *mppe_alloc(unsigned char *options, int optlen) goto out_free; } - state->sha1 = crypto_alloc_ahash("sha1", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(state->sha1)) { - state->sha1 = NULL; + shash = crypto_alloc_shash("sha1", 0, 0); + if (IS_ERR(shash)) + goto out_free; + + state->sha1 = kmalloc(sizeof(*state->sha1) + + crypto_shash_descsize(shash), + GFP_KERNEL); + if (!state->sha1) { + crypto_free_shash(shash); goto out_free; } + state->sha1->tfm = shash; + state->sha1->flags = 0; - digestsize = crypto_ahash_digestsize(state->sha1); + digestsize = crypto_shash_digestsize(shash); if (digestsize < MPPE_MAX_KEY_LEN) goto out_free; @@ -246,7 +246,10 @@ static void *mppe_alloc(unsigned char *options, int optlen) out_free: kfree(state->sha1_digest); - crypto_free_ahash(state->sha1); + if (state->sha1) { + crypto_free_shash(state->sha1->tfm); + kzfree(state->sha1); + } crypto_free_skcipher(state->arc4); kfree(state); out: @@ -261,7 +264,8 @@ static void mppe_free(void *arg) struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; if (state) { kfree(state->sha1_digest); - crypto_free_ahash(state->sha1); + crypto_free_shash(state->sha1->tfm); + kzfree(state->sha1); crypto_free_skcipher(state->arc4); kfree(state); } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0a3134712652..2bbefe828670 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -200,6 +200,7 @@ struct tun_flow_entry { }; #define TUN_NUM_FLOW_ENTRIES 1024 +#define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) struct tun_prog { struct rcu_head rcu; @@ -406,7 +407,7 @@ static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val) static inline u32 tun_hashfn(u32 rxhash) { - return rxhash & 0x3ff; + return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index ac25981ee4d5..a9991c5f4736 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1242,6 +1242,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) mod_timer(&dev->stat_monitor, jiffies + STAT_UPDATE_TIMER); } + + tasklet_schedule(&dev->bh); } return ret; @@ -1647,7 +1649,7 @@ lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs, struct lan78xx_net *dev = netdev_priv(netdev); /* Read Device/MAC registers */ - for (i = 0; i < (sizeof(lan78xx_regs) / sizeof(u32)); i++) + for (i = 0; i < ARRAY_SIZE(lan78xx_regs); i++) lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]); if (!netdev->phydev) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 6514c86f043e..f4247b275e09 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -1067,7 +1067,7 @@ static inline void setup_pegasus_II(pegasus_t *pegasus) set_register(pegasus, Reg1d, 0); set_register(pegasus, Reg7b, 1); - mdelay(100); + msleep(100); if ((pegasus->features & HAS_HOME_PNA) && mii_mode) set_register(pegasus, Reg7b, 0); else diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 38502809420b..cb0cc30c3d6a 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1246,7 +1246,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ - {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 2d316c1b851b..6ac232e52bf7 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -358,7 +358,7 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf) /* power up and reset phy */ sr_write_reg(dev, SR_PRR, PRR_PHY_RST); /* at least 10ms, here 20ms for safe */ - mdelay(20); + msleep(20); sr_write_reg(dev, SR_PRR, 0); /* at least 1ms, here 2ms for reading right register */ udelay(2 * 1000); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2ff08bc103a9..62311dde6e71 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -82,25 +82,43 @@ struct virtnet_sq_stats { struct u64_stats_sync syncp; u64 packets; u64 bytes; + u64 xdp_tx; + u64 xdp_tx_drops; + u64 kicks; }; struct virtnet_rq_stats { struct u64_stats_sync syncp; u64 packets; u64 bytes; + u64 drops; + u64 xdp_packets; + u64 xdp_tx; + u64 xdp_redirects; + u64 xdp_drops; + u64 kicks; }; #define VIRTNET_SQ_STAT(m) offsetof(struct virtnet_sq_stats, m) #define VIRTNET_RQ_STAT(m) offsetof(struct virtnet_rq_stats, m) static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = { - { "packets", VIRTNET_SQ_STAT(packets) }, - { "bytes", VIRTNET_SQ_STAT(bytes) }, + { "packets", VIRTNET_SQ_STAT(packets) }, + { "bytes", VIRTNET_SQ_STAT(bytes) }, + { "xdp_tx", VIRTNET_SQ_STAT(xdp_tx) }, + { "xdp_tx_drops", VIRTNET_SQ_STAT(xdp_tx_drops) }, + { "kicks", VIRTNET_SQ_STAT(kicks) }, }; static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = { - { "packets", VIRTNET_RQ_STAT(packets) }, - { "bytes", VIRTNET_RQ_STAT(bytes) }, + { "packets", VIRTNET_RQ_STAT(packets) }, + { "bytes", VIRTNET_RQ_STAT(bytes) }, + { "drops", VIRTNET_RQ_STAT(drops) }, + { "xdp_packets", VIRTNET_RQ_STAT(xdp_packets) }, + { "xdp_tx", VIRTNET_RQ_STAT(xdp_tx) }, + { "xdp_redirects", VIRTNET_RQ_STAT(xdp_redirects) }, + { "xdp_drops", VIRTNET_RQ_STAT(xdp_drops) }, + { "kicks", VIRTNET_RQ_STAT(kicks) }, }; #define VIRTNET_SQ_STATS_LEN ARRAY_SIZE(virtnet_sq_stats_desc) @@ -447,22 +465,12 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, return 0; } -static int __virtnet_xdp_tx_xmit(struct virtnet_info *vi, - struct xdp_frame *xdpf) +static struct send_queue *virtnet_xdp_sq(struct virtnet_info *vi) { - struct xdp_frame *xdpf_sent; - struct send_queue *sq; - unsigned int len; unsigned int qp; qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); - sq = &vi->sq[qp]; - - /* Free up any pending old buffers before queueing new ones. */ - while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) - xdp_return_frame(xdpf_sent); - - return __virtnet_xdp_xmit_one(vi, sq, xdpf); + return &vi->sq[qp]; } static int virtnet_xdp_xmit(struct net_device *dev, @@ -474,23 +482,28 @@ static int virtnet_xdp_xmit(struct net_device *dev, struct bpf_prog *xdp_prog; struct send_queue *sq; unsigned int len; - unsigned int qp; int drops = 0; - int err; + int kicks = 0; + int ret, err; int i; - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) - return -EINVAL; + sq = virtnet_xdp_sq(vi); - qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); - sq = &vi->sq[qp]; + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { + ret = -EINVAL; + drops = n; + goto out; + } /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_dereference(rq->xdp_prog); - if (!xdp_prog) - return -ENXIO; + if (!xdp_prog) { + ret = -ENXIO; + drops = n; + goto out; + } /* Free up any pending old buffers before queueing new ones. */ while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) @@ -505,11 +518,20 @@ static int virtnet_xdp_xmit(struct net_device *dev, drops++; } } + ret = n - drops; - if (flags & XDP_XMIT_FLUSH) - virtqueue_kick(sq->vq); + if (flags & XDP_XMIT_FLUSH) { + if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) + kicks = 1; + } +out: + u64_stats_update_begin(&sq->stats.syncp); + sq->stats.xdp_tx += n; + sq->stats.xdp_tx_drops += drops; + sq->stats.kicks += kicks; + u64_stats_update_end(&sq->stats.syncp); - return n - drops; + return ret; } static unsigned int virtnet_get_headroom(struct virtnet_info *vi) @@ -586,7 +608,8 @@ static struct sk_buff *receive_small(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + struct virtnet_rq_stats *stats) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -601,6 +624,7 @@ static struct sk_buff *receive_small(struct net_device *dev, int err; len -= vi->hdr_len; + stats->bytes += len; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -642,6 +666,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp.rxq = &rq->xdp_rxq; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); + stats->xdp_packets++; switch (act) { case XDP_PASS: @@ -650,11 +675,12 @@ static struct sk_buff *receive_small(struct net_device *dev, len = xdp.data_end - xdp.data; break; case XDP_TX: + stats->xdp_tx++; xdpf = convert_to_xdp_frame(&xdp); if (unlikely(!xdpf)) goto err_xdp; - err = __virtnet_xdp_tx_xmit(vi, xdpf); - if (unlikely(err)) { + err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); + if (unlikely(err < 0)) { trace_xdp_exception(vi->dev, xdp_prog, act); goto err_xdp; } @@ -662,6 +688,7 @@ static struct sk_buff *receive_small(struct net_device *dev, rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: + stats->xdp_redirects++; err = xdp_do_redirect(dev, &xdp, xdp_prog); if (err) goto err_xdp; @@ -670,6 +697,7 @@ static struct sk_buff *receive_small(struct net_device *dev, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); case XDP_DROP: @@ -695,7 +723,8 @@ err: err_xdp: rcu_read_unlock(); - dev->stats.rx_dropped++; + stats->xdp_drops++; + stats->drops++; put_page(page); xdp_xmit: return NULL; @@ -705,18 +734,20 @@ static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, - unsigned int len) + unsigned int len, + struct virtnet_rq_stats *stats) { struct page *page = buf; struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); + stats->bytes += len - vi->hdr_len; if (unlikely(!skb)) goto err; return skb; err: - dev->stats.rx_dropped++; + stats->drops++; give_pages(rq, page); return NULL; } @@ -727,7 +758,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *buf, void *ctx, unsigned int len, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -740,6 +772,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, int err; head_skb = NULL; + stats->bytes += len - vi->hdr_len; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -788,6 +821,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, xdp.rxq = &rq->xdp_rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); + stats->xdp_packets++; switch (act) { case XDP_PASS: @@ -812,11 +846,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } break; case XDP_TX: + stats->xdp_tx++; xdpf = convert_to_xdp_frame(&xdp); if (unlikely(!xdpf)) goto err_xdp; - err = __virtnet_xdp_tx_xmit(vi, xdpf); - if (unlikely(err)) { + err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); + if (unlikely(err < 0)) { trace_xdp_exception(vi->dev, xdp_prog, act); if (unlikely(xdp_page != page)) put_page(xdp_page); @@ -828,6 +863,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: + stats->xdp_redirects++; err = xdp_do_redirect(dev, &xdp, xdp_prog); if (err) { if (unlikely(xdp_page != page)) @@ -841,8 +877,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); + /* fall through */ case XDP_DROP: if (unlikely(xdp_page != page)) __free_pages(xdp_page, 0); @@ -877,6 +915,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto err_buf; } + stats->bytes += len; page = virt_to_head_page(buf); truesize = mergeable_ctx_to_truesize(ctx); @@ -922,6 +961,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, err_xdp: rcu_read_unlock(); + stats->xdp_drops++; err_skb: put_page(page); while (num_buf-- > 1) { @@ -932,24 +972,25 @@ err_skb: dev->stats.rx_length_errors++; break; } + stats->bytes += len; page = virt_to_head_page(buf); put_page(page); } err_buf: - dev->stats.rx_dropped++; + stats->drops++; dev_kfree_skb(head_skb); xdp_xmit: return NULL; } -static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx, - unsigned int *xdp_xmit) +static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, + void *buf, unsigned int len, void **ctx, + unsigned int *xdp_xmit, + struct virtnet_rq_stats *stats) { struct net_device *dev = vi->dev; struct sk_buff *skb; struct virtio_net_hdr_mrg_rxbuf *hdr; - int ret; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); @@ -961,23 +1002,22 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, } else { put_page(virt_to_head_page(buf)); } - return 0; + return; } if (vi->mergeable_rx_bufs) - skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit); + skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, + stats); else if (vi->big_packets) - skb = receive_big(dev, vi, rq, buf, len); + skb = receive_big(dev, vi, rq, buf, len, stats); else - skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit); + skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); if (unlikely(!skb)) - return 0; + return; hdr = skb_vnet_hdr(skb); - ret = skb->len; - if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -994,12 +1034,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, ntohs(skb->protocol), skb->len, skb->pkt_type); napi_gro_receive(&rq->napi, skb); - return ret; + return; frame_err: dev->stats.rx_frame_errors++; dev_kfree_skb(skb); - return 0; } /* Unlike mergeable buffers, all buffers are allocated to the @@ -1166,7 +1205,12 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, if (err) break; } while (rq->vq->num_free); - virtqueue_kick(rq->vq); + if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { + u64_stats_update_begin(&rq->stats.syncp); + rq->stats.kicks++; + u64_stats_update_end(&rq->stats.syncp); + } + return !oom; } @@ -1241,22 +1285,24 @@ static int virtnet_receive(struct receive_queue *rq, int budget, unsigned int *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; - unsigned int len, received = 0, bytes = 0; + struct virtnet_rq_stats stats = {}; + unsigned int len; void *buf; + int i; if (!vi->big_packets || vi->mergeable_rx_bufs) { void *ctx; - while (received < budget && + while (stats.packets < budget && (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) { - bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit); - received++; + receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats); + stats.packets++; } } else { - while (received < budget && + while (stats.packets < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { - bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit); - received++; + receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats); + stats.packets++; } } @@ -1266,11 +1312,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget, } u64_stats_update_begin(&rq->stats.syncp); - rq->stats.bytes += bytes; - rq->stats.packets += received; + for (i = 0; i < VIRTNET_RQ_STATS_LEN; i++) { + size_t offset = virtnet_rq_stats_desc[i].offset; + u64 *item; + + item = (u64 *)((u8 *)&rq->stats + offset); + *item += *(u64 *)((u8 *)&stats + offset); + } u64_stats_update_end(&rq->stats.syncp); - return received; + return stats.packets; } static void free_old_xmit_skbs(struct send_queue *sq) @@ -1326,7 +1377,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget) container_of(napi, struct receive_queue, napi); struct virtnet_info *vi = rq->vq->vdev->priv; struct send_queue *sq; - unsigned int received, qp; + unsigned int received; unsigned int xdp_xmit = 0; virtnet_poll_cleantx(rq); @@ -1341,10 +1392,12 @@ static int virtnet_poll(struct napi_struct *napi, int budget) xdp_do_flush_map(); if (xdp_xmit & VIRTIO_XDP_TX) { - qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + - smp_processor_id(); - sq = &vi->sq[qp]; - virtqueue_kick(sq->vq); + sq = virtnet_xdp_sq(vi); + if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { + u64_stats_update_begin(&sq->stats.syncp); + sq->stats.kicks++; + u64_stats_update_end(&sq->stats.syncp); + } } return received; @@ -1506,8 +1559,13 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) } } - if (kick || netif_xmit_stopped(txq)) - virtqueue_kick(sq->vq); + if (kick || netif_xmit_stopped(txq)) { + if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { + u64_stats_update_begin(&sq->stats.syncp); + sq->stats.kicks++; + u64_stats_update_end(&sq->stats.syncp); + } + } return NETDEV_TX_OK; } @@ -1611,7 +1669,7 @@ static void virtnet_stats(struct net_device *dev, int i; for (i = 0; i < vi->max_queue_pairs; i++) { - u64 tpackets, tbytes, rpackets, rbytes; + u64 tpackets, tbytes, rpackets, rbytes, rdrops; struct receive_queue *rq = &vi->rq[i]; struct send_queue *sq = &vi->sq[i]; @@ -1625,17 +1683,18 @@ static void virtnet_stats(struct net_device *dev, start = u64_stats_fetch_begin_irq(&rq->stats.syncp); rpackets = rq->stats.packets; rbytes = rq->stats.bytes; + rdrops = rq->stats.drops; } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; tot->rx_bytes += rbytes; tot->tx_bytes += tbytes; + tot->rx_dropped += rdrops; } tot->tx_dropped = dev->stats.tx_dropped; tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->rx_dropped = dev->stats.rx_dropped; tot->rx_length_errors = dev->stats.rx_length_errors; tot->rx_frame_errors = dev->stats.rx_frame_errors; } diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c index 093bd21f574d..4907453f17f5 100644 --- a/drivers/net/wan/lmc/lmc_main.c +++ b/drivers/net/wan/lmc/lmc_main.c @@ -1362,7 +1362,7 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/ case 0x001: printk(KERN_WARNING "%s: Master Abort (naughty)\n", dev->name); break; - case 0x010: + case 0x002: printk(KERN_WARNING "%s: Target Abort (not so naughty)\n", dev->name); break; default: diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 45928b5b8d97..4fffa6988087 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1785,7 +1785,8 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo) fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY; fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM; fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL; - fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus); + /* NVRAM reserves PCI domain 0 for Broadcom's SDK faked bus */ + fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus) + 1; fwreq->bus_nr = devinfo->pdev->bus->number; return fwreq; diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index db176954cf34..24b2f7cbb308 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -179,6 +179,17 @@ const struct iwl_cfg iwl9260_2ac_cfg = { .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; +const struct iwl_cfg iwl9260_killer_2ac_cfg = { + .name = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW)", + .fw_name_pre = IWL9260A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, +}; + const struct iwl_cfg iwl9270_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9270", .fw_name_pre = IWL9260A_FW_PRE, @@ -268,6 +279,34 @@ const struct iwl_cfg iwl9560_2ac_cfg_soc = { .soc_latency = 5000, }; +const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = { + .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, +}; + +const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = { + .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, +}; + const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9460", .fw_name_pre = IWL9000A_FW_PRE, @@ -328,6 +367,36 @@ const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = { .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK }; +const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = { + .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + +const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = { + .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + MODULE_FIRMWARE(IWL9000A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL9000B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL9000RFB_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 72fbf97229b9..12fddcf15bab 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -554,6 +554,7 @@ extern const struct iwl_cfg iwl8275_2ac_cfg; extern const struct iwl_cfg iwl4165_2ac_cfg; extern const struct iwl_cfg iwl9160_2ac_cfg; extern const struct iwl_cfg iwl9260_2ac_cfg; +extern const struct iwl_cfg iwl9260_killer_2ac_cfg; extern const struct iwl_cfg iwl9270_2ac_cfg; extern const struct iwl_cfg iwl9460_2ac_cfg; extern const struct iwl_cfg iwl9560_2ac_cfg; @@ -561,10 +562,14 @@ extern const struct iwl_cfg iwl9460_2ac_cfg_soc; extern const struct iwl_cfg iwl9461_2ac_cfg_soc; extern const struct iwl_cfg iwl9462_2ac_cfg_soc; extern const struct iwl_cfg iwl9560_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_killer_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc; extern const struct iwl_cfg iwl9460_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9461_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9462_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9560_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl22000_2ac_cfg_hr; extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb; extern const struct iwl_cfg iwl22000_2ac_cfg_jf; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 51a2e2deea9c..562cc79288a6 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -545,6 +545,9 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1410, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1420, iwl9460_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x1550, iwl9260_killer_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_cfg_soc)}, @@ -554,6 +557,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, @@ -578,6 +582,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_cfg)}, @@ -604,6 +610,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -630,6 +638,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x31DC, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x31DC, 0x1030, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x31DC, 0x1551, iwl9560_killer_s_2ac_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x1552, iwl9560_killer_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_cfg_shared_clk)}, @@ -656,6 +666,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x34F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x34F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x34F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x34F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -682,6 +694,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -708,6 +722,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -743,6 +759,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x9DF0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x9DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2010, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_cfg_soc)}, @@ -771,6 +789,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -797,6 +817,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA370, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA370, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0xA370, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_cfg_soc)}, diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index a27daa23c9dc..3621e05a7494 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1603,9 +1603,9 @@ static void xenvif_ctrl_action(struct xenvif *vif) static bool xenvif_ctrl_work_todo(struct xenvif *vif) { if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->ctrl))) - return 1; + return true; - return 0; + return false; } irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4d88aa394273..799cba4624a5 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -87,6 +87,7 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) +static DECLARE_WAIT_QUEUE_HEAD(module_load_q); static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); struct netfront_stats { @@ -1331,6 +1332,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); xenbus_switch_state(dev, XenbusStateInitialising); + wait_event(module_load_q, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown); return netdev; exit: diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 46df030b2c3f..bf65501e6ed6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -100,6 +100,22 @@ static struct class *nvme_subsys_class; static void nvme_ns_remove(struct nvme_ns *ns); static int nvme_revalidate_disk(struct gendisk *disk); static void nvme_put_subsystem(struct nvme_subsystem *subsys); +static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, + unsigned nsid); + +static void nvme_set_queue_dying(struct nvme_ns *ns) +{ + /* + * Revalidating a dead namespace sets capacity to 0. This will end + * buffered writers dirtying pages that can't be synced. + */ + if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + return; + revalidate_disk(ns->disk); + blk_set_queue_dying(ns->queue); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + blk_mq_unquiesce_queue(ns->queue); +} static void nvme_queue_scan(struct nvme_ctrl *ctrl) { @@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count); static void nvme_enable_aen(struct nvme_ctrl *ctrl) { - u32 result; + u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED; int status; - status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, - ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result); + if (!supported_aens) + return; + + status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens, + NULL, 0, &result); if (status) dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n", - ctrl->oaes & NVME_AEN_SUPPORTED); + supported_aens); } static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) @@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static void nvme_update_formats(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns, *next; - LIST_HEAD(rm_list); + struct nvme_ns *ns; - down_write(&ctrl->namespaces_rwsem); - list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->disk && nvme_revalidate_disk(ns->disk)) { - list_move_tail(&ns->list, &rm_list); - } - } - up_write(&ctrl->namespaces_rwsem); + down_read(&ctrl->namespaces_rwsem); + list_for_each_entry(ns, &ctrl->namespaces, list) + if (ns->disk && nvme_revalidate_disk(ns->disk)) + nvme_set_queue_dying(ns); + up_read(&ctrl->namespaces_rwsem); - list_for_each_entry_safe(ns, next, &rm_list, list) - nvme_ns_remove(ns); + nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL); } static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) @@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, effects = nvme_passthru_start(ctrl, ns, cmd.opcode); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - (void __user *)(uintptr_t)cmd.metadata, cmd.metadata, + (void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len, 0, &cmd.result, timeout); nvme_passthru_end(ctrl, effects); @@ -3138,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, down_write(&ctrl->namespaces_rwsem); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) + if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags)) list_move_tail(&ns->list, &rm_list); } up_write(&ctrl->namespaces_rwsem); @@ -3542,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) if (ctrl->admin_q) blk_mq_unquiesce_queue(ctrl->admin_q); - list_for_each_entry(ns, &ctrl->namespaces, list) { - /* - * Revalidating a dead namespace sets capacity to 0. This will - * end buffered writers dirtying pages that can't be synced. - */ - if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) - continue; - revalidate_disk(ns->disk); - blk_set_queue_dying(ns->queue); + list_for_each_entry(ns, &ctrl->namespaces, list) + nvme_set_queue_dying(ns); - /* Forcibly unquiesce queues to avoid blocking dispatch */ - blk_mq_unquiesce_queue(ns->queue); - } up_read(&ctrl->namespaces_rwsem); } EXPORT_SYMBOL_GPL(nvme_kill_queues); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 903eb4545e26..f7efe5a58cc7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport( /* * For something we're not in a state to send to the device the default action * is to busy it and retry it after the controller state is recovered. However, - * anything marked for failfast or nvme multipath is immediately failed. + * if the controller is deleting or if anything is marked for failfast or + * nvme multipath it is immediately failed. * * Note: commands used to initialize the controller will be marked for failfast. * Note: nvme cli/ioctl commands are marked for failfast. */ -blk_status_t nvmf_fail_nonready_command(struct request *rq) +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq) { - if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) + if (ctrl->state != NVME_CTRL_DELETING && + ctrl->state != NVME_CTRL_DEAD && + !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index e1818a27aa2d..aa2fdb2a2e8f 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); -blk_status_t nvmf_fail_nonready_command(struct request *rq); +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq); bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 41d45a1b5c62..9bac912173ba 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE || !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); ret = nvme_setup_cmd(ns, rq, sqe); if (ret) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ba943f211687..ddd441b1516a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2556,11 +2556,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) quirks |= check_vendor_combination_bug(pdev); - result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, - quirks); - if (result) - goto release_pools; - /* * Double check that our mempool alloc size will cover the biggest * command we support. @@ -2578,6 +2573,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto release_pools; } + result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, + quirks); + if (result) + goto release_mempool; + dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); nvme_get_ctrl(&dev->ctrl); @@ -2585,6 +2585,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; + release_mempool: + mempool_destroy(dev->iod_mempool); release_pools: nvme_release_prp_pools(dev); unmap: diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 518c5b09038c..66ec5985c9f3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1639,7 +1639,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, WARN_ON_ONCE(rq->tag < 0); if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); dev = queue->device->dev; ib_dma_sync_single_for_cpu(dev, sqe->dma, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index d3f3b3ec4d1a..ebea1373d1b7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, { struct nvmet_ns *ns = to_nvmet_ns(item); struct nvmet_subsys *subsys = ns->subsys; + size_t len; int ret; mutex_lock(&subsys->lock); @@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, if (ns->enabled) goto out_unlock; - kfree(ns->device_path); + ret = -EINVAL; + len = strcspn(page, "\n"); + if (!len) + goto out_unlock; + kfree(ns->device_path); ret = -ENOMEM; - ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL); + ns->device_path = kstrndup(page, len, GFP_KERNEL); if (!ns->device_path) goto out_unlock; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 74d4b785d2da..9838103f2d62 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = nvmet_bdev_ns_enable(ns); - if (ret) + if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); if (ret) goto out_unlock; diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 408279cb6f2c..29b4b236afd8 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod { struct work_struct work; } __aligned(sizeof(unsigned long long)); +/* desired maximum for a single sequence - if sg list allows it */ #define NVMET_FC_MAX_SEQ_LENGTH (256 * 1024) -#define NVMET_FC_MAX_XFR_SGENTS (NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE) enum nvmet_fcp_datadir { NVMET_FCP_NODATA, @@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod { struct nvme_fc_cmd_iu cmdiubuf; struct nvme_fc_ersp_iu rspiubuf; dma_addr_t rspdma; + struct scatterlist *next_sg; struct scatterlist *data_sg; int data_sg_cnt; u32 offset; @@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->assoc_list); kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); - newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS, - template->max_sgl_segments); + newrec->max_sg_cnt = template->max_sgl_segments; ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod) ((fod->io_dir == NVMET_FCP_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE)); /* note: write from initiator perspective */ + fod->next_sg = fod->data_sg; return 0; @@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod, u8 op) { struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq; + struct scatterlist *sg = fod->next_sg; unsigned long flags; - u32 tlen; + u32 remaininglen = fod->req.transfer_len - fod->offset; + u32 tlen = 0; int ret; fcpreq->op = op; fcpreq->offset = fod->offset; fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC; - tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE, - (fod->req.transfer_len - fod->offset)); + /* + * for next sequence: + * break at a sg element boundary + * attempt to keep sequence length capped at + * NVMET_FC_MAX_SEQ_LENGTH but allow sequence to + * be longer if a single sg element is larger + * than that amount. This is done to avoid creating + * a new sg list to use for the tgtport api. + */ + fcpreq->sg = sg; + fcpreq->sg_cnt = 0; + while (tlen < remaininglen && + fcpreq->sg_cnt < tgtport->max_sg_cnt && + tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) { + fcpreq->sg_cnt++; + tlen += sg_dma_len(sg); + sg = sg_next(sg); + } + if (tlen < remaininglen && fcpreq->sg_cnt == 0) { + fcpreq->sg_cnt++; + tlen += min_t(u32, sg_dma_len(sg), remaininglen); + sg = sg_next(sg); + } + if (tlen < remaininglen) + fod->next_sg = sg; + else + fod->next_sg = NULL; + fcpreq->transfer_length = tlen; fcpreq->transferred_length = 0; fcpreq->fcp_error = 0; fcpreq->rsplen = 0; - fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE]; - fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE); - /* * If the last READDATA request: check if LLDD supports * combined xfr with response. diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index d8d91f04bd7e..ae7586b8be07 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t ret; if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready)) - return nvmf_fail_nonready_command(req); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req); ret = nvme_setup_cmd(ns, req, &iod->cmd); if (ret) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 35b7fc87eac5..5cb40b2518f9 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev) return; } - dev->is_added = 1; + pci_dev_assign_added(dev, true); } EXPORT_SYMBOL_GPL(pci_bus_add_device); @@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip if device attach failed */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) continue; child = dev->subordinate; if (child) diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index 4d6c20e47bed..cf0aa7cee5b0 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -107,7 +107,7 @@ #define CFG_WINDOW_TYPE 0 #define IO_WINDOW_TYPE 1 #define MEM_WINDOW_TYPE 2 -#define IB_WIN_SIZE (256 * 1024 * 1024 * 1024) +#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) #define MAX_PIO_WINDOWS 8 /* Parameters for the waiting for link up routine */ diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 3a17b290df5d..ef0b1b6ba86f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot) list_for_each_entry(dev, &bus->devices, bus_list) { /* Assume that newly added devices are powered on already. */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) dev->current_state = PCI_D0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 882f1f9596df..08817253c8a2 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -288,6 +288,7 @@ struct pci_sriov { /* pci_dev priv_flags */ #define PCI_DEV_DISCONNECTED 0 +#define PCI_DEV_ADDED 1 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { @@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags); } +static inline void pci_dev_assign_added(struct pci_dev *dev, bool added) +{ + assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added); +} + +static inline bool pci_dev_is_added(const struct pci_dev *dev) +{ + return test_bit(PCI_DEV_ADDED, &dev->priv_flags); +} + #ifdef CONFIG_PCI_ATS void pci_restore_ats_state(struct pci_dev *dev); #else diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index f7ce0cb0b0b7..f02e334beb45 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -295,6 +295,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) parent = udev->subordinate; pci_lock_rescan_remove(); + pci_dev_get(dev); list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, bus_list) { pci_dev_get(pdev); @@ -328,6 +329,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) pci_info(dev, "Device recovery from fatal error failed\n"); } + pci_dev_put(dev); pci_unlock_rescan_remove(); } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ac876e32de4b..611adcd9c169 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) dev = pci_scan_single_device(bus, devfn); if (!dev) return 0; - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; dev->multifunction = 1; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 6f072eae4f7a..5e3d0dced2b8 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev) { pci_pme_active(dev, false); - if (dev->is_added) { + if (pci_dev_is_added(dev)) { device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); - dev->is_added = 0; + + pci_dev_assign_added(dev, false); } if (dev->bus->self) diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c index 1b7febc43da9..29d2c3b1913a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init.c @@ -962,6 +962,10 @@ void brcm_usb_init_xhci(struct brcm_usb_init_params *params) { void __iomem *ctrl = params->ctrl_regs; + USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE); + /* 1 millisecond - for USB clocks to settle down */ + usleep_range(1000, 2000); + if (BRCM_ID(params->family_id) == 0x7366) { /* * The PHY3_SOFT_RESETB bits default to the wrong state. diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 23705e1a0023..0075fb0bef8c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -182,13 +182,13 @@ static void phy_mdm6600_status(struct work_struct *work) ddata = container_of(work, struct phy_mdm6600, status_work.work); dev = ddata->dev; - error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES, + error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES, ddata->status_gpios->desc, values); if (error) return; - for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) { + for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) { val |= values[i] << i; dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n", __func__, i, values[i], val); diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index a14c317b5a38..095c18532dc7 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -29,6 +29,7 @@ #include <linux/of_platform.h> #include <linux/timex.h> #include <linux/slab.h> +#include <linux/clk.h> #include <linux/fsl/ptp_qoriq.h> @@ -317,6 +318,105 @@ static const struct ptp_clock_info ptp_qoriq_caps = { .enable = ptp_qoriq_enable, }; +/** + * qoriq_ptp_nominal_freq - calculate nominal frequency according to + * reference clock frequency + * + * @clk_src: reference clock frequency + * + * The nominal frequency is the desired clock frequency. + * It should be less than the reference clock frequency. + * It should be a factor of 1000MHz. + * + * Return the nominal frequency + */ +static u32 qoriq_ptp_nominal_freq(u32 clk_src) +{ + u32 remainder = 0; + + clk_src /= 1000000; + remainder = clk_src % 100; + if (remainder) { + clk_src -= remainder; + clk_src += 100; + } + + do { + clk_src -= 100; + + } while (1000 % clk_src); + + return clk_src * 1000000; +} + +/** + * qoriq_ptp_auto_config - calculate a set of default configurations + * + * @qoriq_ptp: pointer to qoriq_ptp + * @node: pointer to device_node + * + * If below dts properties are not provided, this function will be + * called to calculate a set of default configurations for them. + * "fsl,tclk-period" + * "fsl,tmr-prsc" + * "fsl,tmr-add" + * "fsl,tmr-fiper1" + * "fsl,tmr-fiper2" + * "fsl,max-adj" + * + * Return 0 if success + */ +static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp, + struct device_node *node) +{ + struct clk *clk; + u64 freq_comp; + u64 max_adj; + u32 nominal_freq; + u32 clk_src = 0; + + qoriq_ptp->cksel = DEFAULT_CKSEL; + + clk = of_clk_get(node, 0); + if (!IS_ERR(clk)) { + clk_src = clk_get_rate(clk); + clk_put(clk); + } + + if (clk_src <= 100000000UL) { + pr_err("error reference clock value, or lower than 100MHz\n"); + return -EINVAL; + } + + nominal_freq = qoriq_ptp_nominal_freq(clk_src); + if (!nominal_freq) + return -EINVAL; + + qoriq_ptp->tclk_period = 1000000000UL / nominal_freq; + qoriq_ptp->tmr_prsc = DEFAULT_TMR_PRSC; + + /* Calculate initial frequency compensation value for TMR_ADD register. + * freq_comp = ceil(2^32 / freq_ratio) + * freq_ratio = reference_clock_freq / nominal_freq + */ + freq_comp = ((u64)1 << 32) * nominal_freq; + if (do_div(freq_comp, clk_src)) + freq_comp++; + + qoriq_ptp->tmr_add = freq_comp; + qoriq_ptp->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - qoriq_ptp->tclk_period; + qoriq_ptp->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - qoriq_ptp->tclk_period; + + /* max_adj = 1000000000 * (freq_ratio - 1.0) - 1 + * freq_ratio = reference_clock_freq / nominal_freq + */ + max_adj = 1000000000ULL * (clk_src - nominal_freq); + max_adj = max_adj / nominal_freq - 1; + qoriq_ptp->caps.max_adj = max_adj; + + return 0; +} + static int qoriq_ptp_probe(struct platform_device *dev) { struct device_node *node = dev->dev.of_node; @@ -332,7 +432,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) if (!qoriq_ptp) goto no_memory; - err = -ENODEV; + err = -EINVAL; qoriq_ptp->caps = ptp_qoriq_caps; @@ -351,10 +451,14 @@ static int qoriq_ptp_probe(struct platform_device *dev) "fsl,tmr-fiper2", &qoriq_ptp->tmr_fiper2) || of_property_read_u32(node, "fsl,max-adj", &qoriq_ptp->caps.max_adj)) { - pr_err("device tree node missing required elements\n"); - goto no_node; + pr_warn("device tree node missing required elements, try automatic configuration\n"); + + if (qoriq_ptp_auto_config(qoriq_ptp, node)) + goto no_config; } + err = -ENODEV; + qoriq_ptp->irq = platform_get_irq(dev, 0); if (qoriq_ptp->irq < 0) { @@ -436,6 +540,7 @@ no_ioremap: release_resource(qoriq_ptp->rsrc); no_resource: free_irq(qoriq_ptp->irq, qoriq_ptp); +no_config: no_node: kfree(qoriq_ptp); no_memory: diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index 0a95b5f25380..497a68389461 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -134,15 +134,14 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name, rc = PTR_ERR(file); dev_err(dev, "%s: alloc_file failed rc=%d\n", __func__, rc); - goto err5; + path_put(&path); + goto err3; } file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; out: return file; -err5: - path_put(&path); err4: iput(inode); err3: diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d6093838f5f2..c972cc2b3d5b 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -284,11 +284,11 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (opcode != ISCSI_OP_SCSI_DATA_OUT) { iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " + "task [op %x itt " "0x%x/0x%x] " "rejected.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + opcode, task->itt, + task->hdr_itt); return -EACCES; } /* @@ -297,10 +297,10 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (conn->session->fast_abort) { iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " + "task [op %x itt " "0x%x/0x%x] fast abort.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + opcode, task->itt, + task->hdr_itt); return -EACCES; } break; diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 89a4999fa631..c8731568f9c4 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2141,6 +2141,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) msleep(1000); qla24xx_disable_vp(vha); + qla2x00_wait_for_sess_deletion(vha); vha->flags.delete_progress = 1; diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index f68eb6096559..2660a48d918a 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -214,6 +214,7 @@ void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *, int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *); int qla24xx_async_abort_cmd(srb_t *); int qla24xx_post_relogin_work(struct scsi_qla_host *vha); +void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *); /* * Global Functions in qla_mid.c source file. diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 2c35b0b2baa0..7a3744006419 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3708,6 +3708,10 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) return rval; done_free_sp: + spin_lock_irqsave(&vha->hw->vport_slock, flags); + list_del(&sp->elem); + spin_unlock_irqrestore(&vha->hw->vport_slock, flags); + if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index db0e3279e07a..1b19b954bbae 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1489,11 +1489,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun, wait_for_completion(&tm_iocb->u.tmf.comp); - rval = tm_iocb->u.tmf.comp_status == CS_COMPLETE ? - QLA_SUCCESS : QLA_FUNCTION_FAILED; + rval = tm_iocb->u.tmf.data; - if ((rval != QLA_SUCCESS) || tm_iocb->u.tmf.data) { - ql_dbg(ql_dbg_taskm, vha, 0x8030, + if (rval != QLA_SUCCESS) { + ql_log(ql_log_warn, vha, 0x8030, "TM IOCB failed (%x).\n", rval); } diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 37ae0f6d8ae5..59fd5a9dfeb8 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -222,6 +222,8 @@ qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag) sp->fcport = fcport; sp->iocbs = 1; sp->vha = qpair->vha; + INIT_LIST_HEAD(&sp->elem); + done: if (!sp) QLA_QPAIR_MARK_NOT_BUSY(qpair); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 9fa5a2557f2c..7756106d4555 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -631,6 +631,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) unsigned long flags; fc_port_t *fcport = NULL; + if (!vha->hw->flags.fw_started) + return; + /* Setup to process RIO completion. */ handle_cnt = 0; if (IS_CNA_CAPABLE(ha)) diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 7e875f575229..f0ec13d48bf3 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -4220,6 +4220,9 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d3, "Entered %s.\n", __func__); @@ -4289,6 +4292,9 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d6, "Entered %s.\n", __func__); diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index f6f0a759a7c2..aa727d07b702 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -152,11 +152,18 @@ int qla24xx_disable_vp(scsi_qla_host_t *vha) { unsigned long flags; - int ret; + int ret = QLA_SUCCESS; + fc_port_t *fcport; + + if (vha->hw->flags.fw_started) + ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); - ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); + list_for_each_entry(fcport, &vha->vp_fcports, list) + fcport->logout_on_delete = 0; + + qla2x00_mark_all_devices_lost(vha, 0); /* Remove port id from vp target map */ spin_lock_irqsave(&vha->hw->hardware_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 9f309e572be4..1fbd16c8c9a7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -303,6 +303,7 @@ static void qla2x00_free_device(scsi_qla_host_t *); static int qla2xxx_map_queues(struct Scsi_Host *shost); static void qla2x00_destroy_deferred_work(struct qla_hw_data *); + struct scsi_host_template qla2xxx_driver_template = { .module = THIS_MODULE, .name = QLA2XXX_DRIVER_NAME, @@ -1147,7 +1148,7 @@ static inline int test_fcport_count(scsi_qla_host_t *vha) * qla2x00_wait_for_sess_deletion can only be called from remove_one. * it has dependency on UNLOADING flag to stop device discovery */ -static void +void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) { qla2x00_mark_all_devices_lost(vha, 0); @@ -3603,6 +3604,8 @@ qla2x00_remove_one(struct pci_dev *pdev) base_vha = pci_get_drvdata(pdev); ha = base_vha->hw; + ql_log(ql_log_info, base_vha, 0xb079, + "Removing driver\n"); /* Indicate device removal to prevent future board_disable and wait * until any pending board_disable has completed. */ @@ -3625,6 +3628,21 @@ qla2x00_remove_one(struct pci_dev *pdev) } qla2x00_wait_for_hba_ready(base_vha); + if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) { + if (ha->flags.fw_started) + qla2x00_abort_isp_cleanup(base_vha); + } else if (!IS_QLAFX00(ha)) { + if (IS_QLA8031(ha)) { + ql_dbg(ql_dbg_p3p, base_vha, 0xb07e, + "Clearing fcoe driver presence.\n"); + if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS) + ql_dbg(ql_dbg_p3p, base_vha, 0xb079, + "Error while clearing DRV-Presence.\n"); + } + + qla2x00_try_to_stop_firmware(base_vha); + } + qla2x00_wait_for_sess_deletion(base_vha); /* @@ -3648,14 +3666,6 @@ qla2x00_remove_one(struct pci_dev *pdev) qla2x00_delete_all_vps(ha, base_vha); - if (IS_QLA8031(ha)) { - ql_dbg(ql_dbg_p3p, base_vha, 0xb07e, - "Clearing fcoe driver presence.\n"); - if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS) - ql_dbg(ql_dbg_p3p, base_vha, 0xb079, - "Error while clearing DRV-Presence.\n"); - } - qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16); qla2x00_dfs_remove(base_vha); @@ -3715,24 +3725,6 @@ qla2x00_free_device(scsi_qla_host_t *vha) qla2x00_stop_timer(vha); qla25xx_delete_queues(vha); - - if (ha->flags.fce_enabled) - qla2x00_disable_fce_trace(vha, NULL, NULL); - - if (ha->eft) - qla2x00_disable_eft_trace(vha); - - if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) { - if (ha->flags.fw_started) - qla2x00_abort_isp_cleanup(vha); - } else { - if (ha->flags.fw_started) { - /* Stop currently executing firmware. */ - qla2x00_try_to_stop_firmware(vha); - ha->flags.fw_started = 0; - } - } - vha->flags.online = 0; /* turn-off interrupts on the card */ @@ -6028,8 +6020,9 @@ qla2x00_do_dpc(void *data) set_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags); } - if (test_and_clear_bit(ISP_ABORT_NEEDED, - &base_vha->dpc_flags)) { + if (test_and_clear_bit + (ISP_ABORT_NEEDED, &base_vha->dpc_flags) && + !test_bit(UNLOADING, &base_vha->dpc_flags)) { ql_dbg(ql_dbg_dpc, base_vha, 0x4007, "ISP abort scheduled.\n"); diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index 04458eb19d38..4499c787165f 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -1880,6 +1880,9 @@ qla24xx_beacon_off(struct scsi_qla_host *vha) if (IS_P3P_TYPE(ha)) return QLA_SUCCESS; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ha->beacon_blink_led = 0; if (IS_QLA2031(ha) || IS_QLA27XX(ha)) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 8932ae81a15a..2715cdaa669c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req) rtn = host->hostt->eh_timed_out(scmd); if (rtn == BLK_EH_DONE) { + /* + * For blk-mq, we must set the request state to complete now + * before sending the request to the scsi error handler. This + * will prevent a use-after-free in the event the LLD manages + * to complete the request before the error handler finishes + * processing this timed out request. + * + * If the request was already completed, then the LLD beat the + * time out handler from transferring the request to the scsi + * error handler. In that case we can return immediately as no + * further action is required. + */ + if (req->q->mq_ops && !blk_mq_mark_complete(req)) + return rtn; if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index cd2fdac000c9..ba9ba0e04f42 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1741,15 +1741,11 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) * * With scsi-mq enabled, there are a fixed number of preallocated * requests equal in number to shost->can_queue. If all of the - * preallocated requests are already in use, then using GFP_ATOMIC with - * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL - * will cause blk_get_request() to sleep until an active command - * completes, freeing up a request. Neither option is ideal, but - * GFP_KERNEL is the better choice to prevent userspace from getting an - * unexpected EWOULDBLOCK. - * - * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually - * does not sleep except under memory pressure. + * preallocated requests are already in use, then blk_get_request() + * will sleep until an active command completes, freeing up a request. + * Although waiting in an asynchronous interface is less than ideal, we + * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might + * not expect an EWOULDBLOCK from this condition. */ rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); @@ -2185,6 +2181,7 @@ sg_add_sfp(Sg_device * sdp) write_lock_irqsave(&sdp->sfd_lock, iflags); if (atomic_read(&sdp->detaching)) { write_unlock_irqrestore(&sdp->sfd_lock, iflags); + kfree(sfp); return ERR_PTR(-ENODEV); } list_add_tail(&sfp->sfd_siblings, &sdp->sfds); diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index 32f0748fd067..0097a939487f 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -27,9 +27,16 @@ #define GPC_PGC_SW2ISO_SHIFT 0x8 #define GPC_PGC_SW_SHIFT 0x0 +#define GPC_PGC_PCI_PDN 0x200 +#define GPC_PGC_PCI_SR 0x20c + #define GPC_PGC_GPU_PDN 0x260 #define GPC_PGC_GPU_PUPSCR 0x264 #define GPC_PGC_GPU_PDNSCR 0x268 +#define GPC_PGC_GPU_SR 0x26c + +#define GPC_PGC_DISP_PDN 0x240 +#define GPC_PGC_DISP_SR 0x24c #define GPU_VPU_PUP_REQ BIT(1) #define GPU_VPU_PDN_REQ BIT(0) @@ -318,10 +325,24 @@ static const struct of_device_id imx_gpc_dt_ids[] = { { } }; +static const struct regmap_range yes_ranges[] = { + regmap_reg_range(GPC_CNTR, GPC_CNTR), + regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR), + regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR), + regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR), +}; + +static const struct regmap_access_table access_table = { + .yes_ranges = yes_ranges, + .n_yes_ranges = ARRAY_SIZE(yes_ranges), +}; + static const struct regmap_config imx_gpc_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, + .rd_table = &access_table, + .wr_table = &access_table, .max_register = 0x2ac, }; diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index a1a0025b59e0..d5d33e12e952 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -402,6 +402,8 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) fput(asma->file); goto out; } + } else { + vma_set_anonymous(vma); } if (vma->vm_file) diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c index 0ecffab52ec2..abdaf7cf8162 100644 --- a/drivers/staging/ks7010/ks_hostif.c +++ b/drivers/staging/ks7010/ks_hostif.c @@ -1842,15 +1842,15 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN); if (dev->flags & IFF_PROMISC) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_PROMISC); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_PROMISC); goto spin_unlock; } if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) || (dev->flags & IFF_ALLMULTI)) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCASTALL); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCASTALL); goto spin_unlock; } @@ -1866,8 +1866,8 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) ETH_ALEN * mc_count); } else { priv->sme_i.sme_flag |= SME_MULTICAST; - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCAST); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCAST); } spin_unlock: diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c index a3a83424a926..16478fe9e3f8 100644 --- a/drivers/staging/media/omap4iss/iss_video.c +++ b/drivers/staging/media/omap4iss/iss_video.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include <asm/cacheflush.h> #include <linux/clk.h> #include <linux/mm.h> #include <linux/pagemap.h> @@ -24,6 +23,8 @@ #include <media/v4l2-ioctl.h> #include <media/v4l2-mc.h> +#include <asm/cacheflush.h> + #include "iss_video.h" #include "iss.h" diff --git a/drivers/staging/rtl8188eu/Kconfig b/drivers/staging/rtl8188eu/Kconfig index 673fdce25530..ff7832798a77 100644 --- a/drivers/staging/rtl8188eu/Kconfig +++ b/drivers/staging/rtl8188eu/Kconfig @@ -7,7 +7,6 @@ config R8188EU select LIB80211 select LIB80211_CRYPT_WEP select LIB80211_CRYPT_CCMP - select LIB80211_CRYPT_TKIP ---help--- This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N. If built as a module, it will be called r8188eu. diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index 05936a45eb93..c6857a5be12a 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -23,7 +23,6 @@ #include <mon.h> #include <wifi.h> #include <linux/vmalloc.h> -#include <net/lib80211.h> #define ETHERNET_HEADER_SIZE 14 /* Ethernet Header Length */ #define LLC_HEADER_SIZE 6 /* LLC Header Length */ @@ -221,20 +220,31 @@ u32 rtw_free_uc_swdec_pending_queue(struct adapter *adapter) static int recvframe_chkmic(struct adapter *adapter, struct recv_frame *precvframe) { - int res = _SUCCESS; - struct rx_pkt_attrib *prxattrib = &precvframe->attrib; - struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta); + int i, res = _SUCCESS; + u32 datalen; + u8 miccode[8]; + u8 bmic_err = false, brpt_micerror = true; + u8 *pframe, *payload, *pframemic; + u8 *mickey; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &precvframe->attrib; + struct security_priv *psecuritypriv = &adapter->securitypriv; + + struct mlme_ext_priv *pmlmeext = &adapter->mlmeextpriv; + struct mlme_ext_info *pmlmeinfo = &(pmlmeext->mlmext_info); + + stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]); if (prxattrib->encrypt == _TKIP_) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5])); + + /* calculate mic code */ if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - struct sk_buff *skb = precvframe->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - void *crypto_private = NULL; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &adapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv) { res = _FAIL; @@ -243,58 +253,115 @@ static int recvframe_chkmic(struct adapter *adapter, DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0]; + + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: bcmc key\n", __func__)); } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + mickey = &stainfo->dot11tkiprxmickey.skey[0]; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n %s: unicast key\n", __func__)); } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + /* icv_len included the mic code */ + datalen = precvframe->pkt->len-prxattrib->hdrlen - + prxattrib->iv_len-prxattrib->icv_len-8; + pframe = precvframe->pkt->data; + payload = pframe+prxattrib->hdrlen+prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); - memmove(pframe + iv_len, pframe, prxattrib->hdrlen); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len)); + rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0], + (unsigned char)prxattrib->priority); /* care the length of the data */ - skb_pull(skb, iv_len); - skb_trim(skb, skb->len - icv_len); + pframemic = payload+datalen; - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; + bmic_err = false; + + for (i = 0; i < 8; i++) { + if (miccode[i] != *(pframemic+i)) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ", + __func__, i, miccode[i], i, *(pframemic + i))); + bmic_err = true; + } } - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + if (bmic_err) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-8), *(pframemic-7), *(pframemic-6), + *(pframemic-5), *(pframemic-4), *(pframemic-3), + *(pframemic-2), *(pframemic-1))); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-16), *(pframemic-15), *(pframemic-14), + *(pframemic-13), *(pframemic-12), *(pframemic-11), + *(pframemic-10), *(pframemic-9))); + { + uint i; - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n ======demp packet (len=%d)======\n", + precvframe->pkt->len)); + for (i = 0; i < precvframe->pkt->len; i += 8) { + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x", + *(precvframe->pkt->data+i), + *(precvframe->pkt->data+i+1), + *(precvframe->pkt->data+i+2), + *(precvframe->pkt->data+i+3), + *(precvframe->pkt->data+i+4), + *(precvframe->pkt->data+i+5), + *(precvframe->pkt->data+i+6), + *(precvframe->pkt->data+i+7))); + } + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n ====== demp packet end [len=%d]======\n", + precvframe->pkt->len)); + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n hrdlen=%d,\n", + prxattrib->hdrlen)); + } -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ", + prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey)); + + /* double check key_index for some timing issue , */ + /* cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */ + if ((IS_MCAST(prxattrib->ra) == true) && (prxattrib->key_index != pmlmeinfo->key_index)) + brpt_micerror = false; + + if ((prxattrib->bdecrypted) && (brpt_micerror)) { + rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } else { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } + res = _FAIL; + } else { + /* mic checked ok */ + if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) { + psecuritypriv->bcheck_grpkey = true; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true")); + } + } } else { RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("%s: rtw_get_stainfo==NULL!!!\n", __func__)); } + + skb_trim(precvframe->pkt, precvframe->pkt->len - 8); } exit: + return res; } diff --git a/drivers/staging/rtl8188eu/core/rtw_security.c b/drivers/staging/rtl8188eu/core/rtw_security.c index bfe0b217e679..67a2490f055e 100644 --- a/drivers/staging/rtl8188eu/core/rtw_security.c +++ b/drivers/staging/rtl8188eu/core/rtw_security.c @@ -650,71 +650,71 @@ u32 rtw_tkip_encrypt(struct adapter *padapter, u8 *pxmitframe) return res; } +/* The hlen isn't include the IV */ u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe) -{ - struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; - u32 res = _SUCCESS; +{ /* exclude ICV */ + u16 pnl; + u32 pnh; + u8 rc4key[16]; + u8 ttkey[16]; + u8 crc[4]; + struct arc4context mycontext; + int length; + + u8 *pframe, *payload, *iv, *prwskey; + union pn48 dot11txpn; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; + struct security_priv *psecuritypriv = &padapter->securitypriv; + u32 res = _SUCCESS; + + + pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data; /* 4 start to decrypt recvframe */ if (prxattrib->encrypt == _TKIP_) { - struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta); - + stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]); if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - void *crypto_private = NULL; - struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &padapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv->binstallGrpkey) { res = _FAIL; DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey; } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__)); + prwskey = &stainfo->dot118021x_UncstKey.skey[0]; } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + iv = pframe+prxattrib->hdrlen; + payload = pframe+prxattrib->iv_len+prxattrib->hdrlen; + length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); + GET_TKIP_PN(iv, dot11txpn); - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; - } + pnl = (u16)(dot11txpn.val); + pnh = (u32)(dot11txpn.val>>16); - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh); + phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl); - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + /* 4 decrypt payload include icv */ -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + arcfour_init(&mycontext, rc4key, 16); + arcfour_encrypt(&mycontext, payload, payload, length); + + *((__le32 *)crc) = getcrc32(payload, length-4); + + if (crc[3] != payload[length-1] || + crc[2] != payload[length-2] || + crc[1] != payload[length-3] || + crc[0] != payload[length-4]) { + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, + ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n", + &crc, &payload[length-4])); + res = _FAIL; + } } else { RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n")); res = _FAIL; diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c index a61bc41b82d7..947c79532e10 100644 --- a/drivers/staging/speakup/speakup_soft.c +++ b/drivers/staging/speakup/speakup_soft.c @@ -198,11 +198,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, int chars_sent = 0; char __user *cp; char *init; + size_t bytes_per_ch = unicode ? 3 : 1; u16 ch; int empty; unsigned long flags; DEFINE_WAIT(wait); + if (count < bytes_per_ch) + return -EINVAL; + spin_lock_irqsave(&speakup_info.spinlock, flags); while (1) { prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE); @@ -228,7 +232,7 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, init = get_initstring(); /* Keep 3 bytes available for a 16bit UTF-8-encoded character */ - while (chars_sent <= count - 3) { + while (chars_sent <= count - bytes_per_ch) { if (speakup_info.flushing) { speakup_info.flushing = 0; ch = '\x18'; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index 514986b57c2d..25eb3891e34b 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -652,6 +652,7 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) struct iscsi_param *param; u32 mrdsl, mbl; u32 max_npdu, max_iso_npdu; + u32 max_iso_payload; if (conn->login->leading_connection) { param = iscsi_find_param_from_key(MAXBURSTLENGTH, @@ -670,8 +671,10 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) mrdsl = conn_ops->MaxRecvDataSegmentLength; max_npdu = mbl / mrdsl; - max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD / - (ISCSI_HDR_LEN + mrdsl + + max_iso_payload = rounddown(CXGBIT_MAX_ISO_PAYLOAD, csk->emss); + + max_iso_npdu = max_iso_payload / + (ISCSI_HDR_LEN + mrdsl + cxgbit_digest_len[csk->submode]); csk->max_iso_npdu = min(max_npdu, max_iso_npdu); @@ -741,6 +744,9 @@ static int cxgbit_set_params(struct iscsi_conn *conn) if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl) conn_ops->MaxRecvDataSegmentLength = cdev->mdsl; + if (cxgbit_set_digest(csk)) + return -1; + if (conn->login->leading_connection) { param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL, conn->param_list); @@ -764,7 +770,7 @@ static int cxgbit_set_params(struct iscsi_conn *conn) if (is_t5(cdev->lldi.adapter_type)) goto enable_ddp; else - goto enable_digest; + return 0; } if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) { @@ -781,10 +787,6 @@ enable_ddp: } } -enable_digest: - if (cxgbit_set_digest(csk)) - return -1; - return 0; } diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig index 785f0ed037f7..ee34e9046f7e 100644 --- a/drivers/usb/chipidea/Kconfig +++ b/drivers/usb/chipidea/Kconfig @@ -3,6 +3,7 @@ config USB_CHIPIDEA depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA select EXTCON select RESET_CONTROLLER + select USB_ULPI_BUS help Say Y here if your system has a dual role high speed USB controller based on ChipIdea silicon IP. It supports: @@ -38,12 +39,4 @@ config USB_CHIPIDEA_HOST help Say Y here to enable host controller functionality of the ChipIdea driver. - -config USB_CHIPIDEA_ULPI - bool "ChipIdea ULPI PHY support" - depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA - help - Say Y here if you have a ULPI PHY attached to your ChipIdea - controller. - endif diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile index e3d5e728fa53..12df94f78f72 100644 --- a/drivers/usb/chipidea/Makefile +++ b/drivers/usb/chipidea/Makefile @@ -1,11 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_USB_CHIPIDEA) += ci_hdrc.o -ci_hdrc-y := core.o otg.o debug.o +ci_hdrc-y := core.o otg.o debug.o ulpi.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC) += udc.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST) += host.o ci_hdrc-$(CONFIG_USB_OTG_FSM) += otg_fsm.o -ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI) += ulpi.o # Glue/Bridge layers go here diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 0bf244d50544..6a2cc5cd0281 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -240,10 +240,8 @@ struct ci_hdrc { struct ci_hdrc_platform_data *platdata; int vbus_active; -#ifdef CONFIG_USB_CHIPIDEA_ULPI struct ulpi *ulpi; struct ulpi_ops ulpi_ops; -#endif struct phy *phy; /* old usb_phy interface */ struct usb_phy *usb_phy; @@ -426,15 +424,9 @@ static inline bool ci_otg_is_fsm_mode(struct ci_hdrc *ci) #endif } -#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI) int ci_ulpi_init(struct ci_hdrc *ci); void ci_ulpi_exit(struct ci_hdrc *ci); int ci_ulpi_resume(struct ci_hdrc *ci); -#else -static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; } -static inline void ci_ulpi_exit(struct ci_hdrc *ci) { } -static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; } -#endif u32 hw_read_intr_enable(struct ci_hdrc *ci); diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c index 6da42dcd2888..dfec07e8ae1d 100644 --- a/drivers/usb/chipidea/ulpi.c +++ b/drivers/usb/chipidea/ulpi.c @@ -95,6 +95,9 @@ int ci_ulpi_resume(struct ci_hdrc *ci) { int cnt = 100000; + if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI) + return 0; + while (cnt-- > 0) { if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE)) return 0; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 998b32d0167e..75c4623ad779 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1831,6 +1831,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */ .driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */ }, + { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index fcae521df29b..1fb266809966 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1142,10 +1142,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) if (!udev || udev->state == USB_STATE_NOTATTACHED) { /* Tell hub_wq to disconnect the device or - * check for a new connection + * check for a new connection or over current condition. + * Based on USB2.0 Spec Section 11.12.5, + * C_PORT_OVER_CURRENT could be set while + * PORT_OVER_CURRENT is not. So check for any of them. */ if (udev || (portstatus & USB_PORT_STAT_CONNECTION) || - (portstatus & USB_PORT_STAT_OVERCURRENT)) + (portstatus & USB_PORT_STAT_OVERCURRENT) || + (portchange & USB_PORT_STAT_C_OVERCURRENT)) set_bit(port1, hub->change_bits); } else if (portstatus & USB_PORT_STAT_ENABLE) { diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index a0f82cca2d9a..cefc99ae69b2 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3430,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_in[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx)); @@ -3476,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); @@ -3650,7 +3650,7 @@ irq_retry: for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index b1104be3429c..6e2cdd7b93d4 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2665,34 +2665,35 @@ static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg, #define DWC2_USB_DMA_ALIGN 4 -struct dma_aligned_buffer { - void *kmalloc_ptr; - void *old_xfer_buffer; - u8 data[0]; -}; - static void dwc2_free_dma_aligned_buffer(struct urb *urb) { - struct dma_aligned_buffer *temp; + void *stored_xfer_buffer; + size_t length; if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER)) return; - temp = container_of(urb->transfer_buffer, - struct dma_aligned_buffer, data); + /* Restore urb->transfer_buffer from the end of the allocated area */ + memcpy(&stored_xfer_buffer, urb->transfer_buffer + + urb->transfer_buffer_length, sizeof(urb->transfer_buffer)); - if (usb_urb_dir_in(urb)) - memcpy(temp->old_xfer_buffer, temp->data, - urb->transfer_buffer_length); - urb->transfer_buffer = temp->old_xfer_buffer; - kfree(temp->kmalloc_ptr); + if (usb_urb_dir_in(urb)) { + if (usb_pipeisoc(urb->pipe)) + length = urb->transfer_buffer_length; + else + length = urb->actual_length; + + memcpy(stored_xfer_buffer, urb->transfer_buffer, length); + } + kfree(urb->transfer_buffer); + urb->transfer_buffer = stored_xfer_buffer; urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER; } static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) { - struct dma_aligned_buffer *temp, *kmalloc_ptr; + void *kmalloc_ptr; size_t kmalloc_size; if (urb->num_sgs || urb->sg || @@ -2700,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1))) return 0; - /* Allocate a buffer with enough padding for alignment */ + /* + * Allocate a buffer with enough padding for original transfer_buffer + * pointer. This allocation is guaranteed to be aligned properly for + * DMA + */ kmalloc_size = urb->transfer_buffer_length + - sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1; + sizeof(urb->transfer_buffer); kmalloc_ptr = kmalloc(kmalloc_size, mem_flags); if (!kmalloc_ptr) return -ENOMEM; - /* Position our struct dma_aligned_buffer such that data is aligned */ - temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1; - temp->kmalloc_ptr = kmalloc_ptr; - temp->old_xfer_buffer = urb->transfer_buffer; + /* + * Position value of original urb->transfer_buffer pointer to the end + * of allocation for later referencing + */ + memcpy(kmalloc_ptr + urb->transfer_buffer_length, + &urb->transfer_buffer, sizeof(urb->transfer_buffer)); + if (usb_urb_dir_out(urb)) - memcpy(temp->data, urb->transfer_buffer, + memcpy(kmalloc_ptr, urb->transfer_buffer, urb->transfer_buffer_length); - urb->transfer_buffer = temp->data; + urb->transfer_buffer = kmalloc_ptr; urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER; diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index ed7f05cf4906..8ce10caf3e19 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -1231,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, * avoid interrupt storms we'll wait before retrying if we've got * several NAKs. If we didn't do this we'd retry directly from the * interrupt handler and could end up quickly getting another - * interrupt (another NAK), which we'd retry. + * interrupt (another NAK), which we'd retry. Note that we do not + * delay retries for IN parts of control requests, as those are expected + * to complete fairly quickly, and if we delay them we risk confusing + * the device and cause it issue STALL. * * Note that in DMA mode software only gets involved to re-send NAKed * transfers for split transactions, so we only need to apply this @@ -1244,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, qtd->error_count = 0; qtd->complete_split = 0; qtd->num_naks++; - qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY; + qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY && + !(chan->ep_type == USB_ENDPOINT_XFER_CONTROL && + chan->ep_is_in); dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK); goto handle_nak_done; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index c77ff50a88a2..8efde178eef4 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, ret = dwc3_ep0_start_trans(dep); } else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) && req->request.length && req->request.zero) { - u32 maxpacket; ret = usb_gadget_map_request_by_dev(dwc->sysdev, &req->request, dep->number); if (ret) return; - maxpacket = dep->endpoint.maxpacket; - /* prepare normal TRB */ dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d2fa071c21b1..b8a15840b4ff 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1819,7 +1819,6 @@ unknown: if (cdev->use_os_string && cdev->os_desc_config && (ctrl->bRequestType & USB_TYPE_VENDOR) && ctrl->bRequest == cdev->b_vendor_code) { - struct usb_request *req; struct usb_configuration *os_desc_cfg; u8 *buf; int interface; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 33e2030503fa..3ada83d81bda 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3263,7 +3263,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return USB_GADGET_DELAYED_STATUS; + return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index d2dc1f00180b..d582921f7257 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = { }; struct cntrl_cur_lay3 { - __u32 dCUR; + __le32 dCUR; }; struct cntrl_range_lay3 { - __u16 wNumSubRanges; - __u32 dMIN; - __u32 dMAX; - __u32 dRES; + __le16 wNumSubRanges; + __le32 dMIN; + __le32 dMAX; + __le32 dRES; } __packed; static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts, @@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc); if (!agdev->out_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc); if (!agdev->in_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep_maxpsize = max_t(u16, @@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr) memset(&c, 0, sizeof(struct cntrl_cur_lay3)); if (entity_id == USB_IN_CLK_ID) - c.dCUR = p_srate; + c.dCUR = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - c.dCUR = c_srate; + c.dCUR = cpu_to_le32(c_srate); value = min_t(unsigned, w_length, sizeof c); memcpy(req->buf, &c, value); @@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr) if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) { if (entity_id == USB_IN_CLK_ID) - r.dMIN = p_srate; + r.dMIN = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - r.dMIN = c_srate; + r.dMIN = cpu_to_le32(c_srate); else return -EOPNOTSUPP; r.dMAX = r.dMIN; r.dRES = 0; - r.wNumSubRanges = 1; + r.wNumSubRanges = cpu_to_le16(1); value = min_t(unsigned, w_length, sizeof r); memcpy(req->buf, &r, value); diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index a72295c953bb..fb5ed97572e5 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -32,9 +32,6 @@ struct uac_req { struct uac_rtd_params { struct snd_uac_chip *uac; /* parent chip */ bool ep_enabled; /* if the ep is enabled */ - /* Size of the ring buffer */ - size_t dma_bytes; - unsigned char *dma_area; struct snd_pcm_substream *ss; @@ -43,8 +40,6 @@ struct uac_rtd_params { void *rbuf; - size_t period_size; - unsigned max_psize; /* MaxPacketSize of endpoint */ struct uac_req *ureq; @@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = { static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) { unsigned pending; - unsigned long flags; + unsigned long flags, flags2; unsigned int hw_ptr; - bool update_alsa = false; int status = req->status; struct uac_req *ur = req->context; struct snd_pcm_substream *substream; + struct snd_pcm_runtime *runtime; struct uac_rtd_params *prm = ur->pp; struct snd_uac_chip *uac = prm->uac; @@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) if (!substream) goto exit; + snd_pcm_stream_lock_irqsave(substream, flags2); + + runtime = substream->runtime; + if (!runtime || !snd_pcm_running(substream)) { + snd_pcm_stream_unlock_irqrestore(substream, flags2); + goto exit; + } + spin_lock_irqsave(&prm->lock, flags); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { @@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) req->actual = req->length; } - pending = prm->hw_ptr % prm->period_size; - pending += req->actual; - if (pending >= prm->period_size) - update_alsa = true; - hw_ptr = prm->hw_ptr; - prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes; spin_unlock_irqrestore(&prm->lock, flags); /* Pack USB load in ALSA ring buffer */ - pending = prm->dma_bytes - hw_ptr; + pending = runtime->dma_bytes - hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (unlikely(pending < req->actual)) { - memcpy(req->buf, prm->dma_area + hw_ptr, pending); - memcpy(req->buf + pending, prm->dma_area, + memcpy(req->buf, runtime->dma_area + hw_ptr, pending); + memcpy(req->buf + pending, runtime->dma_area, req->actual - pending); } else { - memcpy(req->buf, prm->dma_area + hw_ptr, req->actual); + memcpy(req->buf, runtime->dma_area + hw_ptr, + req->actual); } } else { if (unlikely(pending < req->actual)) { - memcpy(prm->dma_area + hw_ptr, req->buf, pending); - memcpy(prm->dma_area, req->buf + pending, + memcpy(runtime->dma_area + hw_ptr, req->buf, pending); + memcpy(runtime->dma_area, req->buf + pending, req->actual - pending); } else { - memcpy(prm->dma_area + hw_ptr, req->buf, req->actual); + memcpy(runtime->dma_area + hw_ptr, req->buf, + req->actual); } } + spin_lock_irqsave(&prm->lock, flags); + /* update hw_ptr after data is copied to memory */ + prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes; + hw_ptr = prm->hw_ptr; + spin_unlock_irqrestore(&prm->lock, flags); + snd_pcm_stream_unlock_irqrestore(substream, flags2); + + if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual) + snd_pcm_period_elapsed(substream); + exit: if (usb_ep_queue(ep, req, GFP_ATOMIC)) dev_err(uac->card->dev, "%d Error!\n", __LINE__); - - if (update_alsa) - snd_pcm_period_elapsed(substream); } static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd) @@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream) static int uac_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *hw_params) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - int err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - err = snd_pcm_lib_malloc_pages(substream, + return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params)); - if (err >= 0) { - prm->dma_bytes = substream->runtime->dma_bytes; - prm->dma_area = substream->runtime->dma_area; - prm->period_size = params_period_bytes(hw_params); - } - - return err; } static int uac_pcm_hw_free(struct snd_pcm_substream *substream) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - prm->dma_area = NULL; - prm->dma_bytes = 0; - prm->period_size = 0; - return snd_pcm_lib_free_pages(substream); } @@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, if (err < 0) goto snd_fail; - strcpy(pcm->name, pcm_name); + strlcpy(pcm->name, pcm_name, sizeof(pcm->name)); pcm->private_data = uac; uac->pcm = pcm; snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops); snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops); - strcpy(card->driver, card_name); - strcpy(card->shortname, card_name); + strlcpy(card->driver, card_name, sizeof(card->driver)); + strlcpy(card->shortname, card_name, sizeof(card->shortname)); sprintf(card->longname, "%s %i", card_name, card->dev->id); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c index 20ffb03ff6ac..e2927fb083cf 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c @@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep) /* Check our state, cancel pending requests if needed */ if (ep->ep0.state != ep0_state_token) { EPDBG(ep, "wrong state\n"); + ast_vhub_nuke(ep, -EIO); + + /* + * Accept the packet regardless, this seems to happen + * when stalling a SETUP packet that has an OUT data + * phase. + */ ast_vhub_nuke(ep, 0); goto stall; } @@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep, if (chunk && req->req.buf) memcpy(ep->buf, req->req.buf + req->req.actual, chunk); + vhub_dma_workaround(ep->buf); + /* Remember chunk size and trigger send */ reg = VHUB_EP0_SET_TX_LEN(chunk); writel(reg, ep->ep0.ctlstat); @@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep) EPVDBG(ep, "rx prime\n"); /* Prime endpoint for receiving data */ - writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL); + writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat); } static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 80c9feac5147..5939eb1e97f2 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req) if (!req->req.dma) { /* For IN transfers, copy data over first */ - if (ep->epn.is_in) + if (ep->epn.is_in) { memcpy(ep->buf, req->req.buf + act, chunk); + vhub_dma_workaround(ep->buf); + } writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE); - } else + } else { + if (ep->epn.is_in) + vhub_dma_workaround(req->req.buf); writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE); + } /* Start DMA */ req->active = true; @@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep) static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, struct ast_vhub_req *req) { + struct ast_vhub_desc *desc = NULL; unsigned int act = req->act_count; unsigned int len = req->req.length; unsigned int chunk; @@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, /* While we can create descriptors */ while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) { - struct ast_vhub_desc *desc; unsigned int d_num; /* Grab next free descriptor */ @@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, req->act_count = act = act + chunk; } + if (likely(desc)) + vhub_dma_workaround(desc); + /* Tell HW about new descriptors */ writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next), ep->epn.regs + AST_VHUB_EP_DESC_STATUS); diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h index 2b040257bc1f..4ed03d33a5a9 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h +++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h @@ -462,6 +462,39 @@ enum std_req_rc { #define DDBG(d, fmt, ...) do { } while(0) #endif +static inline void vhub_dma_workaround(void *addr) +{ + /* + * This works around a confirmed HW issue with the Aspeed chip. + * + * The core uses a different bus to memory than the AHB going to + * the USB device controller. Due to the latter having a higher + * priority than the core for arbitration on that bus, it's + * possible for an MMIO to the device, followed by a DMA by the + * device from memory to all be performed and services before + * a previous store to memory gets completed. + * + * This the following scenario can happen: + * + * - Driver writes to a DMA descriptor (Mbus) + * - Driver writes to the MMIO register to start the DMA (AHB) + * - The gadget sees the second write and sends a read of the + * descriptor to the memory controller (Mbus) + * - The gadget hits memory before the descriptor write + * causing it to read an obsolete value. + * + * Thankfully the problem is limited to the USB gadget device, other + * masters in the SoC all have a lower priority than the core, thus + * ensuring that the store by the core arrives first. + * + * The workaround consists of using a dummy read of the memory before + * doing the MMIO writes. This will ensure that the previous writes + * have been "pushed out". + */ + mb(); + (void)__raw_readl((void __iomem *)addr); +} + /* core.c */ void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req, int status); diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c index a3ecce62662b..11e25a3f4f1f 100644 --- a/drivers/usb/gadget/udc/r8a66597-udc.c +++ b/drivers/usb/gadget/udc/r8a66597-udc.c @@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597) r8a66597_bset(r8a66597, XCKE, SYSCFG0); - msleep(3); + mdelay(3); r8a66597_bset(r8a66597, PLLC, SYSCFG0); - msleep(1); + mdelay(1); r8a66597_bset(r8a66597, SCKE, SYSCFG0); @@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock) r8a66597->ep0_req->length = 2; /* AV: what happens if we get called again before that gets through? */ spin_unlock(&r8a66597->lock); - r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL); + r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC); spin_lock(&r8a66597->lock); } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 2f4850f25e82..68e6132aa8b2 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3051,6 +3051,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd, if (!list_empty(&ep->ring->td_list)) { dev_err(&udev->dev, "EP not empty, refuse reset\n"); spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, cfg_cmd); goto cleanup; } xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0); diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 900875f326d7..f7c96d209eda 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev) if (pdata->init && pdata->init(pdev) != 0) return -EINVAL; +#ifdef CONFIG_PPC32 if (pdata->big_endian_mmio) { _fsl_readl = _fsl_readl_be; _fsl_writel = _fsl_writel_be; @@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev) _fsl_readl = _fsl_readl_le; _fsl_writel = _fsl_writel_le; } +#endif /* request irq */ p_otg->irq = platform_get_irq(pdev, 0); @@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev) /* * state file in sysfs */ -static int show_fsl_usb2_otg_state(struct device *dev, +static ssize_t show_fsl_usb2_otg_state(struct device *dev, struct device_attribute *attr, char *buf) { struct otg_fsm *fsm = &fsl_otg_dev->fsm; diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c index 150f43668bec..d1d20252bad8 100644 --- a/drivers/usb/typec/tcpm.c +++ b/drivers/usb/typec/tcpm.c @@ -2140,7 +2140,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) * PPS APDO. Again skip the first sink PDO as this will * always be 5V 3A. */ - for (j = i; j < port->nr_snk_pdo; j++) { + for (j = 1; j < port->nr_snk_pdo; j++) { pdo = port->snk_pdo[j]; switch (pdo_type(pdo)) { diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 759a5bdd40e1..7cd63b0c1a46 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -457,17 +457,17 @@ static void tce_iommu_unuse_page(struct tce_container *container, } static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container, - unsigned long tce, unsigned long size, + unsigned long tce, unsigned long shift, unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem) { long ret = 0; struct mm_iommu_table_group_mem_t *mem; - mem = mm_iommu_lookup(container->mm, tce, size); + mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift); if (!mem) return -EINVAL; - ret = mm_iommu_ua_to_hpa(mem, tce, phpa); + ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa); if (ret) return -EINVAL; @@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container, if (!pua) return; - ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl), + ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift, &hpa, &mem); if (ret) pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n", @@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container, entry + i); ret = tce_iommu_prereg_ua_to_hpa(container, - tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem); + tce, tbl->it_page_shift, &hpa, &mem); if (ret) break; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 6b237e3f4983..3988c0914322 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -513,7 +513,9 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, tell_host(vb, vb->inflate_vq); /* balloon's page migration 2nd step -- deflate "page" */ + spin_lock_irqsave(&vb_dev_info->pages_lock, flags); balloon_page_delete(page); + spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags); vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE; set_page_pfns(vb, vb->pfns, page); tell_host(vb, vb->deflate_vq); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a1b18082991b..19db5f672a9d 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -346,7 +346,6 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, struct rxrpc_call *rxcall; struct msghdr msg; struct kvec iov[1]; - size_t offset; s64 tx_total_len; int ret; @@ -433,10 +432,10 @@ error_do_abort: rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); } else { - offset = 0; - rxrpc_kernel_recv_data(call->net->socket, rxcall, NULL, - 0, &offset, false, &call->abort_code, - &call->service_id); + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0); + rxrpc_kernel_recv_data(call->net->socket, rxcall, + &msg.msg_iter, false, + &call->abort_code, &call->service_id); ac->abort_code = call->abort_code; ac->responded = true; } @@ -467,13 +466,14 @@ static void afs_deliver_to_call(struct afs_call *call) state == AFS_CALL_SV_AWAIT_ACK ) { if (state == AFS_CALL_SV_AWAIT_ACK) { - size_t offset = 0; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0); ret = rxrpc_kernel_recv_data(call->net->socket, - call->rxcall, - NULL, 0, &offset, false, + call->rxcall, &iter, false, &remote_abort, &call->service_id); - trace_afs_recv_data(call, 0, offset, false, ret); + trace_afs_recv_data(call, 0, 0, false, ret); if (ret == -EINPROGRESS || ret == -EAGAIN) return; @@ -894,6 +894,8 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, bool want_more) { struct afs_net *net = call->net; + struct iov_iter iter; + struct kvec iov; enum afs_call_state state; u32 remote_abort = 0; int ret; @@ -903,10 +905,14 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, ASSERTCMP(call->offset, <=, count); - ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, - buf, count, &call->offset, + iov.iov_base = buf + call->offset; + iov.iov_len = count - call->offset; + iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset); + + ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter, want_more, &remote_abort, &call->service_id); + call->offset += (count - call->offset) - iov_iter_count(&iter); trace_afs_recv_data(call, count, call->offset, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; @@ -1896,6 +1896,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, return ret; } +struct __aio_sigset { + const sigset_t __user *sigmask; + size_t sigsetsize; +}; + SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, diff --git a/fs/block_dev.c b/fs/block_dev.c index 0dd87aaeb39a..aba25414231a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -221,7 +221,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) - return ret; + goto out; ret = bio.bi_iter.bi_size; if (iov_iter_rw(iter) == READ) { @@ -250,12 +250,13 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, put_page(bvec->bv_page); } - if (vecs != inline_vecs) - kfree(vecs); - if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); +out: + if (vecs != inline_vecs) + kfree(vecs); + bio_uninit(&bio); return ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e55843f536bc..b3e45714d28f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4238,8 +4238,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) struct extent_map *em; u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; - struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; - struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree; + struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host); + struct extent_io_tree *tree = &btrfs_inode->io_tree; + struct extent_map_tree *map = &btrfs_inode->extent_tree; if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > SZ_16M) { @@ -4262,6 +4263,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) extent_map_end(em) - 1, EXTENT_LOCKED | EXTENT_WRITEBACK, 0, NULL)) { + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &btrfs_inode->runtime_flags); remove_extent_mapping(map, em); /* once for the rb tree */ free_extent_map(em); diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index d9f001078e08..4a717d400807 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -218,7 +218,8 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) "%s", fsdef->dentry->d_sb->s_id); - fscache_object_init(&fsdef->fscache, NULL, &cache->cache); + fscache_object_init(&fsdef->fscache, &fscache_fsdef_index, + &cache->cache); ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag); if (ret < 0) diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ab0bbe93b398..af2b17b21b94 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -186,12 +186,12 @@ try_again: * need to wait for it to be destroyed */ wait_for_old_object: trace_cachefiles_wait_active(object, dentry, xobject); + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); if (fscache_object_is_live(&xobject->fscache)) { pr_err("\n"); pr_err("Error: Unexpected object collision\n"); cachefiles_printk_object(object, xobject); - BUG(); } atomic_inc(&xobject->usage); write_unlock(&cache->active_lock); @@ -248,7 +248,6 @@ wait_for_old_object: goto try_again; requeue: - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo); _leave(" = -ETIMEDOUT"); return -ETIMEDOUT; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 5082c8a49686..40f7595aad10 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -27,6 +27,7 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, struct cachefiles_one_read *monitor = container_of(wait, struct cachefiles_one_read, monitor); struct cachefiles_object *object; + struct fscache_retrieval *op = monitor->op; struct wait_bit_key *key = _key; struct page *page = wait->private; @@ -51,16 +52,22 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, list_del(&wait->entry); /* move onto the action list and queue for FS-Cache thread pool */ - ASSERT(monitor->op); + ASSERT(op); - object = container_of(monitor->op->op.object, - struct cachefiles_object, fscache); + /* We need to temporarily bump the usage count as we don't own a ref + * here otherwise cachefiles_read_copier() may free the op between the + * monitor being enqueued on the op->to_do list and the op getting + * enqueued on the work queue. + */ + fscache_get_retrieval(op); + object = container_of(op->op.object, struct cachefiles_object, fscache); spin_lock(&object->work_lock); - list_add_tail(&monitor->op_link, &monitor->op->to_do); + list_add_tail(&monitor->op_link, &op->to_do); spin_unlock(&object->work_lock); - fscache_enqueue_retrieval(monitor->op); + fscache_enqueue_retrieval(op); + fscache_put_retrieval(op); return 0; } diff --git a/fs/exec.c b/fs/exec.c index 2d4e0075bd24..bdd0eacefdf5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -290,15 +290,15 @@ static int __bprm_mm_init(struct linux_binprm *bprm) struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; - bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; + vma_set_anonymous(vma); if (down_write_killable(&mm->mmap_sem)) { err = -EINTR; goto err_free; } - vma->vm_mm = mm; /* * Place the stack at the largest stack address the architecture @@ -311,7 +311,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) @@ -326,7 +325,7 @@ err: up_write(&mm->mmap_sem); err_free: bprm->vma = NULL; - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return err; } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e68cefe08261..aa52d87985aa 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -368,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, desc, bh))) { ext4_unlock_group(sb, block_group); @@ -386,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index fb83750c1a14..f336cbc6e932 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, EXT4_INODES_PER_GROUP(sb) / 8)) { @@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSBADCRC; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } @@ -1385,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, ext4_itable_unused_count(sb, gdp)), sbi->s_inodes_per_block); - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || + ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)) < + EXT4_FIRST_INO(sb)))) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e55a8bc870bd..3543fe80a3c4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -682,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto convert; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out; + flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); @@ -710,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, out_up_read: up_read(&EXT4_I(inode)->xattr_sem); out: - if (handle) + if (handle && (ret != 1)) ext4_journal_stop(handle); brelse(iloc.bh); return ret; @@ -752,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); + mark_inode_dirty(inode); out: return copied; } @@ -898,7 +903,6 @@ retry_journal: goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; @@ -916,6 +920,9 @@ retry_journal: if (ret < 0) goto out_release_page; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); *pagep = page; @@ -936,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int i_size_changed = 0; int ret; ret = ext4_write_inline_data_end(inode, pos, len, copied, page); @@ -954,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ - if (pos+copied > inode->i_size) { + if (pos+copied > inode->i_size) i_size_write(inode, pos+copied); - i_size_changed = 1; - } unlock_page(page); put_page(page); @@ -967,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) - mark_inode_dirty(inode); + mark_inode_dirty(inode); return copied; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7d6c10017bdf..4efe77286ecd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) + if (i_size_changed || inline_data) ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && ext4_can_truncate(inode)) @@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); @@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); - if (size_changed) { + if (size_changed || inline_data) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page, } if (inline_data) { - BUFFER_TRACE(inode_bh, "get write access"); - ret = ext4_journal_get_write_access(handle, inode_bh); - - err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - + ret = ext4_mark_inode_dirty(handle, inode); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 27b9a76a0dfa..638ad4743477 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -186,11 +186,8 @@ static int kmmpd(void *data) goto exit_thread; } - if (sb_rdonly(sb)) { - ext4_warning(sb, "kmmpd being stopped since filesystem " - "has been remounted as readonly."); - goto exit_thread; - } + if (sb_rdonly(sb)) + break; diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba2396a7bd04..b7f7922061be 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2342,7 +2342,7 @@ static int ext4_check_descriptors(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; - ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0) + 1; + ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; @@ -3141,14 +3141,8 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) if (!gdp) continue; - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) - continue; - if (group != 0) + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; - ext4_error(sb, "Inode table for bg 0 marked as " - "needing zeroing"); - if (sb_rdonly(sb)) - return ngroups; } return group; @@ -4085,14 +4079,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } + sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; } - sbi->s_gdb_count = db_count; - timer_setup(&sbi->s_err_report, print_daily_error_info, 0); /* Register extent status tree shrinker */ @@ -5213,6 +5206,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); + if (sbi->s_mmp_tsk) + kthread_stop(sbi->s_mmp_tsk); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 065dc919a0ce..bfd589ea74c0 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -707,13 +707,21 @@ static void fat_set_state(struct super_block *sb, brelse(bh); } +static void fat_reset_iocharset(struct fat_mount_options *opts) +{ + if (opts->iocharset != fat_default_iocharset) { + /* Note: opts->iocharset can be NULL here */ + kfree(opts->iocharset); + opts->iocharset = fat_default_iocharset; + } +} + static void delayed_free(struct rcu_head *p) { struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); unload_nls(sbi->nls_disk); unload_nls(sbi->nls_io); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); kfree(sbi); } @@ -1132,7 +1140,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, opts->fs_fmask = opts->fs_dmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; - opts->iocharset = fat_default_iocharset; + fat_reset_iocharset(opts); if (is_vfat) { opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; opts->rodir = 0; @@ -1289,8 +1297,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, /* vfat specific */ case Opt_charset: - if (opts->iocharset != fat_default_iocharset) - kfree(opts->iocharset); + fat_reset_iocharset(opts); iocharset = match_strdup(&args[0]); if (!iocharset) return -ENOMEM; @@ -1881,8 +1888,7 @@ out_fail: iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index c184c5a356ff..cdcb376ef8df 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -220,6 +220,7 @@ int fscache_add_cache(struct fscache_cache *cache, { struct fscache_cache_tag *tag; + ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index); BUG_ON(!cache->ops); BUG_ON(!ifsdef); @@ -248,7 +249,6 @@ int fscache_add_cache(struct fscache_cache *cache, if (!cache->kobj) goto error; - ifsdef->cookie = &fscache_fsdef_index; ifsdef->cache = cache; cache->fsdef = ifsdef; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 97137d7ec5ee..83bfe04456b6 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -516,6 +516,7 @@ static int fscache_alloc_object(struct fscache_cache *cache, goto error; } + ASSERTCMP(object->cookie, ==, cookie); fscache_stat(&fscache_n_object_alloc); object->debug_id = atomic_inc_return(&fscache_object_debug_id); @@ -571,6 +572,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie, _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); + ASSERTCMP(object->cookie, ==, cookie); + spin_lock(&cookie->lock); /* there may be multiple initial creations of this object, but we only @@ -610,9 +613,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, spin_unlock(&cache->object_list_lock); } - /* attach to the cookie */ - object->cookie = cookie; - fscache_cookie_get(cookie, fscache_cookie_get_attach_object); + /* Attach to the cookie. The object already has a ref on it. */ hlist_add_head(&object->cookie_link, &cookie->backing_objects); fscache_objlist_add(object); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 20e0d0a4dc8c..9edc920f651f 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -327,6 +327,7 @@ void fscache_object_init(struct fscache_object *object, object->store_limit_l = 0; object->cache = cache; object->cookie = cookie; + fscache_cookie_get(cookie, fscache_cookie_get_attach_object); object->parent = NULL; #ifdef CONFIG_FSCACHE_OBJECT_LIST RB_CLEAR_NODE(&object->objlist_link); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index e30c5975ea58..8d265790374c 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -70,7 +70,8 @@ void fscache_enqueue_operation(struct fscache_operation *op) ASSERT(op->processor != NULL); ASSERT(fscache_object_is_available(op->object)); ASSERTCMP(atomic_read(&op->usage), >, 0); - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS); + ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS, + op->state, ==, FSCACHE_OP_ST_CANCELLED); fscache_stat(&fscache_n_op_enqueue); switch (op->flags & FSCACHE_OP_TYPE) { @@ -499,7 +500,8 @@ void fscache_put_operation(struct fscache_operation *op) struct fscache_cache *cache; _enter("{OBJ%x OP%x,%d}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); + op->object ? op->object->debug_id : 0, + op->debug_id, atomic_read(&op->usage)); ASSERTCMP(atomic_read(&op->usage), >, 0); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d508c7844681..40d4c66c7751 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, current->mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pagevec_init(&pvec); next = start; @@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * as input to create an allocation policy. */ memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; diff --git a/fs/internal.h b/fs/internal.h index 980d005b21b4..5645b4ebf494 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -127,7 +127,6 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); -extern struct file *filp_clone_open(struct file *); /* * inode.c diff --git a/fs/iomap.c b/fs/iomap.c index 77397b5a96ef..0d0bd8845586 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1443,7 +1443,7 @@ iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops) { struct inode *inode = mapping->host; - loff_t pos = bno >> inode->i_blkbits; + loff_t pos = bno << inode->i_blkbits; unsigned blocksize = i_blocksize(inode); if (filemap_write_and_wait(mapping)) diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 395c4c0d0f06..1682a87c00b2 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -115,6 +115,13 @@ struct dinode { dxd_t _dxd; /* 16: */ union { __le32 _rdev; /* 4: */ + /* + * The fast symlink area + * is expected to overflow + * into _inlineea when + * needed (which will clear + * INLINEEA). + */ u8 _fastsymlink[128]; } _u; u8 _inlineea[128]; diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 1f26d1910409..9940a1e04cbf 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -87,6 +87,7 @@ struct jfs_inode_info { struct { unchar _unused[16]; /* 16: */ dxd_t _dxd; /* 16: */ + /* _inline may overflow into _inline_ea when needed */ unchar _inline[128]; /* 128: inline symlink */ /* _inline_ea may overlay the last part of * file._xtroot if maxentry = XTROOTINITSLOT diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 1b9264fd54b6..f08571433aba 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -967,8 +967,7 @@ static int __init init_jfs_fs(void) jfs_inode_cachep = kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, - offsetof(struct jfs_inode_info, i_inline), - sizeof_field(struct jfs_inode_info, i_inline), + offsetof(struct jfs_inode_info, i_inline), IDATASIZE, init_once); if (jfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6dd146885da9..f6c4ccd693f4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6466,34 +6466,34 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) - break; + goto out_restart; } - if (data->arg.new_lock_owner != 0) { nfs_confirm_seqid(&lsp->ls_seqid, 0); nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); - goto out_done; - } else if (nfs4_update_lock_stateid(lsp, &data->res.stateid)) - goto out_done; - + } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) + goto out_restart; break; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: if (data->arg.new_lock_owner != 0) { - if (nfs4_stateid_match(&data->arg.open_stateid, + if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) - goto out_done; - } else if (nfs4_stateid_match(&data->arg.lock_stateid, + goto out_restart; + } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) - goto out_done; + goto out_restart; } - if (!data->cancelled) - rpc_restart_call_prepare(task); out_done: dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); + return; +out_restart: + if (!data->cancelled) + rpc_restart_call_prepare(task); + goto out_done; } static void nfs4_lock_release(void *calldata) @@ -6502,7 +6502,7 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: begin!\n", __func__); nfs_free_seqid(data->arg.open_seqid); - if (data->cancelled) { + if (data->cancelled && data->rpc_status == 0) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, data->arg.lock_seqid); diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 2751476e6b6e..f098b9f1c396 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -167,6 +167,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, } if (compressed) { + if (!msblk->stream) + goto read_failure; length = squashfs_decompress(msblk, bh, b, offset, length, output); if (length < 0) diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 23813c078cc9..0839efa720b3 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer, TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset); + if (unlikely(length < 0)) + return -EIO; + while (length) { entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); if (entry->error) { diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 13d80947bf9e..f1c1430ae721 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n, } for (i = 0; i < blocks; i++) { - int size = le32_to_cpu(blist[i]); + int size = squashfs_block_size(blist[i]); + if (size < 0) { + err = size; + goto failure; + } block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size); } n -= blocks; @@ -367,7 +371,24 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) sizeof(size)); if (res < 0) return res; - return le32_to_cpu(size); + return squashfs_block_size(size); +} + +void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail) +{ + int copied; + void *pageaddr; + + pageaddr = kmap_atomic(page); + copied = squashfs_copy_data(pageaddr, buffer, offset, avail); + memset(pageaddr + copied, 0, PAGE_SIZE - copied); + kunmap_atomic(pageaddr); + + flush_dcache_page(page); + if (copied == avail) + SetPageUptodate(page); + else + SetPageError(page); } /* Copy data into page cache */ @@ -376,7 +397,6 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, { struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - void *pageaddr; int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; int start_index = page->index & ~mask, end_index = start_index | mask; @@ -402,12 +422,7 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, if (PageUptodate(push_page)) goto skip_page; - pageaddr = kmap_atomic(push_page); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(push_page); - SetPageUptodate(push_page); + squashfs_fill_page(push_page, buffer, offset, avail); skip_page: unlock_page(push_page); if (i != page->index) @@ -416,10 +431,9 @@ skip_page: } /* Read datablock stored packed inside a fragment (tail-end packed block) */ -static int squashfs_readpage_fragment(struct page *page) +static int squashfs_readpage_fragment(struct page *page, int expected) { struct inode *inode = page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); @@ -430,23 +444,16 @@ static int squashfs_readpage_fragment(struct page *page) squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); else - squashfs_copy_cache(page, buffer, i_size_read(inode) & - (msblk->block_size - 1), + squashfs_copy_cache(page, buffer, expected, squashfs_i(inode)->fragment_offset); squashfs_cache_put(buffer); return res; } -static int squashfs_readpage_sparse(struct page *page, int index, int file_end) +static int squashfs_readpage_sparse(struct page *page, int expected) { - struct inode *inode = page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int bytes = index == file_end ? - (i_size_read(inode) & (msblk->block_size - 1)) : - msblk->block_size; - - squashfs_copy_cache(page, NULL, bytes, 0); + squashfs_copy_cache(page, NULL, expected, 0); return 0; } @@ -456,6 +463,9 @@ static int squashfs_readpage(struct file *file, struct page *page) struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; int index = page->index >> (msblk->block_log - PAGE_SHIFT); int file_end = i_size_read(inode) >> msblk->block_log; + int expected = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; int res; void *pageaddr; @@ -474,11 +484,11 @@ static int squashfs_readpage(struct file *file, struct page *page) goto error_out; if (bsize == 0) - res = squashfs_readpage_sparse(page, index, file_end); + res = squashfs_readpage_sparse(page, expected); else - res = squashfs_readpage_block(page, block, bsize); + res = squashfs_readpage_block(page, block, bsize, expected); } else - res = squashfs_readpage_fragment(page); + res = squashfs_readpage_fragment(page, expected); if (!res) return 0; diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c index f2310d2a2019..a9ba8d96776a 100644 --- a/fs/squashfs/file_cache.c +++ b/fs/squashfs/file_cache.c @@ -20,7 +20,7 @@ #include "squashfs.h" /* Read separately compressed datablock and memcopy into page cache */ -int squashfs_readpage_block(struct page *page, u64 block, int bsize) +int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected) { struct inode *i = page->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, @@ -31,7 +31,7 @@ int squashfs_readpage_block(struct page *page, u64 block, int bsize) ERROR("Unable to read page, block %llx, size %x\n", block, bsize); else - squashfs_copy_cache(page, buffer, buffer->length, 0); + squashfs_copy_cache(page, buffer, expected, 0); squashfs_cache_put(buffer); return res; diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index cb485d8e0e91..80db1b86a27c 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -21,10 +21,11 @@ #include "page_actor.h" static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page); + int pages, struct page **page, int bytes); /* Read separately compressed datablock directly into page cache */ -int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) +int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, + int expected) { struct inode *inode = target_page->mapping->host; @@ -83,7 +84,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) * using an intermediate buffer. */ res = squashfs_read_cache(target_page, block, bsize, pages, - page); + page, expected); if (res < 0) goto mark_errored; @@ -95,6 +96,11 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) if (res < 0) goto mark_errored; + if (res != expected) { + res = -EIO; + goto mark_errored; + } + /* Last page may have trailing bytes not filled */ bytes = res % PAGE_SIZE; if (bytes) { @@ -138,13 +144,12 @@ out: static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page) + int pages, struct page **page, int bytes) { struct inode *i = target_page->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, block, bsize); - int bytes = buffer->length, res = buffer->error, n, offset = 0; - void *pageaddr; + int res = buffer->error, n, offset = 0; if (res) { ERROR("Unable to read page, block %llx, size %x\n", block, @@ -159,12 +164,7 @@ static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, if (page[n] == NULL) continue; - pageaddr = kmap_atomic(page[n]); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(page[n]); - SetPageUptodate(page[n]); + squashfs_fill_page(page[n], buffer, offset, avail); unlock_page(page[n]); if (page[n] != target_page) put_page(page[n]); diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c index 0ed6edbc5c71..0681feab4a84 100644 --- a/fs/squashfs/fragment.c +++ b/fs/squashfs/fragment.c @@ -49,11 +49,16 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, u64 *fragment_block) { struct squashfs_sb_info *msblk = sb->s_fs_info; - int block = SQUASHFS_FRAGMENT_INDEX(fragment); - int offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); - u64 start_block = le64_to_cpu(msblk->fragment_index[block]); + int block, offset, size; struct squashfs_fragment_entry fragment_entry; - int size; + u64 start_block; + + if (fragment >= msblk->fragments) + return -EIO; + block = SQUASHFS_FRAGMENT_INDEX(fragment); + offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); + + start_block = le64_to_cpu(msblk->fragment_index[block]); size = squashfs_read_metadata(sb, &fragment_entry, &start_block, &offset, sizeof(fragment_entry)); @@ -61,9 +66,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, return size; *fragment_block = le64_to_cpu(fragment_entry.start_block); - size = le32_to_cpu(fragment_entry.size); - - return size; + return squashfs_block_size(fragment_entry.size); } diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 887d6d270080..f89f8a74c6ce 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -67,11 +67,12 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *, u64, u64, unsigned int); /* file.c */ +void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int); void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, int); /* file_xxx.c */ -extern int squashfs_readpage_block(struct page *, u64, int); +extern int squashfs_readpage_block(struct page *, u64, int, int); /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 24d12fd14177..4e6853f084d0 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -129,6 +129,12 @@ #define SQUASHFS_COMPRESSED_BLOCK(B) (!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK)) +static inline int squashfs_block_size(__le32 raw) +{ + u32 size = le32_to_cpu(raw); + return (size >> 25) ? -EIO : size; +} + /* * Inode number ops. Inodes consist of a compressed block number, and an * uncompressed offset within that block diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 1da565cb50c3..ef69c31947bf 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -75,6 +75,7 @@ struct squashfs_sb_info { unsigned short block_log; long long bytes_used; unsigned int inodes; + unsigned int fragments; int xattr_ids; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 8a73b97217c8..40e657386fa5 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -175,6 +175,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->inode_table = le64_to_cpu(sblk->inode_table_start); msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); + msblk->fragments = le32_to_cpu(sblk->fragments); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -185,7 +186,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) TRACE("Filesystem size %lld bytes\n", msblk->bytes_used); TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); - TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments)); + TRACE("Number of fragments %d\n", msblk->fragments); TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); @@ -272,7 +273,7 @@ allocate_id_index_table: sb->s_export_op = &squashfs_export_ops; handle_fragments: - fragments = le32_to_cpu(sblk->fragments); + fragments = msblk->fragments; if (fragments == 0) goto check_directory_table; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index fa46216523cf..052e5ad9a4d2 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -373,7 +373,7 @@ int sysfs_add_file_to_group(struct kobject *kobj, return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); - error = sysfs_add_file_mode_ns(kobj->sd, attr, false, + error = sysfs_add_file_mode_ns(parent, attr, false, attr->mode, uid, gid, NULL); kernfs_put(parent); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 594d192b2331..bad9cea37f12 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -633,8 +633,10 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) - if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) + if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + } up_write(&mm->mmap_sem); userfaultfd_ctx_put(release_new_ctx); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index eef466260d43..75dbdc14c45f 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -223,12 +223,13 @@ xfs_alloc_get_rec( error = xfs_btree_get_rec(cur, &rec, stat); if (error || !(*stat)) return error; - if (rec->alloc.ar_blockcount == 0) - goto out_bad_rec; *bno = be32_to_cpu(rec->alloc.ar_startblock); *len = be32_to_cpu(rec->alloc.ar_blockcount); + if (*len == 0) + goto out_bad_rec; + /* check for valid extent range, including overflow */ if (!xfs_verify_agbno(mp, agno, *bno)) goto out_bad_rec; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 33dc34655ac3..30d1d60f1d46 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -731,7 +731,8 @@ xfs_inode_validate_extsize( if ((hint_flag || inherit_flag) && extsize == 0) return __this_address; - if (!(hint_flag || inherit_flag) && extsize != 0) + /* free inodes get flags set to zero but extsize remains */ + if (mode && !(hint_flag || inherit_flag) && extsize != 0) return __this_address; if (extsize_bytes % blocksize_bytes) @@ -777,7 +778,8 @@ xfs_inode_validate_cowextsize( if (hint_flag && cowextsize == 0) return __this_address; - if (!hint_flag && cowextsize != 0) + /* free inodes get flags set to zero but cowextsize remains */ + if (mode && !hint_flag && cowextsize != 0) return __this_address; if (hint_flag && rt_flag) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ca3f2c2edd85 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -287,6 +287,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +/** + * blk_mq_mark_complete() - Set request state to complete + * @rq: request to set to complete state + * + * Returns true if request state was successfully set to complete. If + * successful, the caller is responsibile for seeing this request is ended, as + * blk_mq_complete_request will not work again. + */ +static inline bool blk_mq_mark_complete(struct request *rq) +{ + return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) == + MQ_RQ_IN_FLIGHT; +} + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 687b1760bb9f..f02cee0225d4 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -5,10 +5,10 @@ #include <uapi/linux/bpfilter.h> struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval, - int *optlen); +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen); extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 055aaf5ed9af..a83e1f632eb7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -143,7 +143,12 @@ u8 can_dlc2len(u8 can_dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_len2dlc(u8 len); -struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max); +struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, + unsigned int txqs, unsigned int rxqs); +#define alloc_candev(sizeof_priv, echo_skb_max) \ + alloc_candev_mqs(sizeof_priv, echo_skb_max, 1, 1) +#define alloc_candev_mq(sizeof_priv, echo_skb_max, count) \ + alloc_candev_mqs(sizeof_priv, echo_skb_max, count, count) void free_candev(struct net_device *dev); /* a candev safe wrapper around netdev_priv */ diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index e6c0448ebcc7..31c865d1842e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { - if (current->delays) + if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 7094718b653b..ffcc7724ca21 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -11,6 +11,7 @@ #include <linux/fcntl.h> #include <linux/wait.h> +#include <linux/err.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining diff --git a/include/linux/fs.h b/include/linux/fs.h index d78d146a98da..805bf22898cf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2420,6 +2420,7 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *filp_clone_open(struct file *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index dc3dac40f069..c1f003aadcce 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -127,9 +127,13 @@ struct qoriq_ptp_registers { #define DRIVER "ptp_qoriq" -#define DEFAULT_CKSEL 1 #define N_EXT_TS 2 +#define DEFAULT_CKSEL 1 +#define DEFAULT_TMR_PRSC 2 +#define DEFAULT_FIPER1_PERIOD 1000000000 +#define DEFAULT_FIPER2_PERIOD 100000 + struct qoriq_ptp { void __iomem *base; struct qoriq_ptp_registers regs; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 27650f1bff3d..c759d1cbcedd 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -93,6 +93,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) +#define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 86cb0ebf92fa..54f385cc8811 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -363,6 +363,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u32 frag_sz_m1; + u32 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -817,6 +818,7 @@ struct mlx5_clock { }; struct mlx5_fw_tracer; +struct mlx5_vxlan; struct mlx5_core_dev { struct pci_dev *pdev; @@ -849,6 +851,7 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct mlx5_vxlan *vxlan; struct { struct mlx5_rsvd_gids reserved_gids; u32 roce_en; @@ -991,14 +994,22 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, - struct mlx5_frag_buf_ctrl *fbc) +static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, + u32 strides_offset, + struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; + fbc->strides_offset = strides_offset; +} + +static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, + struct mlx5_frag_buf_ctrl *fbc) +{ + mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); } static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, @@ -1012,7 +1023,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, u32 ix) { - unsigned int frag = (ix >> fbc->log_frag_strides); + unsigned int frag; + + ix += fbc->strides_offset; + frag = ix >> fbc->log_frag_strides; return fbc->frag_buf.frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 22f54bedfaae..60c2308fe062 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -668,7 +668,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp[0x1]; u8 swp_csum[0x1]; u8 swp_lso[0x1]; - u8 reserved_at_23[0x1b]; + u8 reserved_at_23[0xd]; + u8 max_vxlan_udp_ports[0x8]; + u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; u8 tunnel_stateless_geneve_rx[0x1]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 3982c83fdcbf..68a5121694ef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -extern struct kmem_cache *vm_area_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *); +struct vm_area_struct *vm_area_dup(struct vm_area_struct *); +void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -450,6 +452,23 @@ struct vm_operations_struct { unsigned long addr); }; +static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + + vma->vm_mm = mm; + vma->vm_ops = &dummy_vm_ops; + INIT_LIST_HEAD(&vma->anon_vma_chain); +} + +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + +/* flush_tlb_range() takes a vma, not a mm, and can care about flags */ +#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } + struct mmu_gather; struct inode; diff --git a/include/linux/net.h b/include/linux/net.h index 6554d3ba4396..e0930678c8bf 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -114,7 +114,7 @@ struct socket { unsigned long flags; - struct socket_wq __rcu *wq; + struct socket_wq *wq; struct file *file; struct sock *sk; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c1295c7a452e..282e2e95ad5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -872,10 +872,10 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */ struct { - struct xdp_umem *umem; - u16 queue_id; + struct xdp_umem *umem; /* out for query*/ + u16 queue_id; /* in for query */ } xsk; }; }; @@ -3431,8 +3431,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxq) + unsigned int rxqs) { + dev->real_num_rx_queues = rxqs; return 0; } #endif @@ -3546,6 +3547,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_set_mtu_ext(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); int dev_change_tx_queue_len(struct net_device *, unsigned long); void dev_set_group(struct net_device *, int); @@ -3565,6 +3568,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, enum bpf_netdev_command cmd); +int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nfnetlink_osf.h index 0e114c492fb8..a7311bc03d3a 100644 --- a/include/linux/netfilter/nf_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -1,4 +1,8 @@ -#include <uapi/linux/netfilter/nf_osf.h> +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFOSF_H +#define _NFOSF_H + +#include <uapi/linux/netfilter/nfnetlink_osf.h> /* Initial window size option state machine: multiple of mss, mtu or * plain numeric value. Can also be made as plain numeric value which @@ -21,6 +25,8 @@ enum osf_fmatch_states { FMATCH_OPT_WRONG, }; +extern struct list_head nf_osf_fingers[2]; + struct nf_osf_finger { struct rcu_head rcu_head; struct list_head finger_entry; @@ -31,3 +37,8 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, const struct list_head *nf_osf_fingers); + +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers); + +#endif /* _NFOSF_H */ diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index b671fdfd212b..fa0686500970 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -5,17 +5,6 @@ #include <uapi/linux/netfilter_bridge.h> #include <linux/skbuff.h> -enum nf_br_hook_priorities { - NF_BR_PRI_FIRST = INT_MIN, - NF_BR_PRI_NAT_DST_BRIDGED = -300, - NF_BR_PRI_FILTER_BRIDGED = -200, - NF_BR_PRI_BRNF = 0, - NF_BR_PRI_NAT_DST_OTHER = 100, - NF_BR_PRI_FILTER_OTHER = 200, - NF_BR_PRI_NAT_SRC = 300, - NF_BR_PRI_LAST = INT_MAX, -}; - #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/linux/pci.h b/include/linux/pci.h index abd5d5e17aee..c133ccfa002e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -368,7 +368,6 @@ struct pci_dev { unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int multifunction:1; /* Multi-function device */ - unsigned int is_added:1; unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..87f6db437e4a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); +extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); diff --git a/include/linux/phy.h b/include/linux/phy.h index 075c2f770d3e..cd6f637cbbfb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -825,6 +825,16 @@ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) } /** + * phy_polling_mode - Convenience function for testing whether polling is + * used to detect PHY status changes + * @phydev: the phy_device struct + */ +static inline bool phy_polling_mode(struct phy_device *phydev) +{ + return phydev->irq == PHY_POLL; +} + +/** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ diff --git a/include/linux/platform_data/bt-nokia-h4p.h b/include/linux/platform_data/bt-nokia-h4p.h deleted file mode 100644 index 30d169dfadf3..000000000000 --- a/include/linux/platform_data/bt-nokia-h4p.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * This file is part of Nokia H4P bluetooth driver - * - * Copyright (C) 2010 Nokia Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * - */ - - -/** - * struct hci_h4p_platform data - hci_h4p Platform data structure - */ -struct hci_h4p_platform_data { - int chip_type; - int bt_sysclk; - unsigned int bt_wakeup_gpio; - unsigned int host_wakeup_gpio; - unsigned int reset_gpio; - int reset_gpio_shared; - unsigned int uart_irq; - phys_addr_t uart_base; - const char *uart_iclk; - const char *uart_fclk; - void (*set_pm_limits)(struct device *dev, bool set); -}; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b72ebdff0b77..003d09ab308d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); int ring_buffer_record_is_on(struct ring_buffer *buffer); +int ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1b92a28dd672..6fd615a0eea9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -106,7 +106,14 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#else extern void rt_mutex_lock(struct rt_mutex *lock); +#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#endif + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout); diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 5be31eb7b266..108ede99e533 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -extern long kernel_wait4(pid_t, int *, int, struct rusage *); +extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); extern void free_task(struct task_struct *tsk); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fd3cb1b247df..7ebdf158a795 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -676,13 +676,16 @@ struct sk_buff { * UDP receive path is one user. */ unsigned long dev_scratch; - int ip_defrag_offset; }; }; - struct rb_node rbnode; /* used in netem & tcp stack */ + struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; }; - struct sock *sk; + + union { + struct sock *sk; + int ip_defrag_offset; + }; union { ktime_t tstamp; @@ -2585,7 +2588,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } -void skb_rbtree_purge(struct rb_root *root); +unsigned int skb_rbtree_purge(struct rb_root *root); void *netdev_alloc_frag(unsigned int fragsz); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a368a68cb667..5c1a0933768e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SYSCALLS_H #define _LINUX_SYSCALLS_H +struct __aio_sigset; struct epoll_event; struct iattr; struct inode; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 58a8d7d71354..263e37271afd 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -181,10 +181,16 @@ struct tcp_sock { u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut * total number of data segments sent. */ + u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut + * total number of data bytes sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. */ + u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ @@ -214,8 +220,7 @@ struct tcp_sock { #define TCP_RACK_RECOVERY_THRESH 16 u8 reo_wnd_persist:5, /* No. of recovery since last adj */ dsack_seen:1, /* Whether DSACK seen after last adj */ - advanced:1, /* mstamp advanced since last lost marking */ - reord:1; /* reordering detected */ + advanced:1; /* mstamp advanced since last lost marking */ } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; @@ -261,6 +266,7 @@ struct tcp_sock { u8 ecn_flags; /* ECN status bits. */ u8 keepalive_probes; /* num of allowed keep alive probes */ u32 reordering; /* Packet reordering metric. */ + u32 reord_seen; /* number of data packet reordering events */ u32 snd_up; /* Urgent pointer */ /* @@ -330,6 +336,9 @@ struct tcp_sock { * the first SYN. */ u32 undo_marker; /* snd_una upon a new recovery episode. */ int undo_retrans; /* number of undoable retransmissions. */ + u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans + * Total data bytes retransmitted + */ u32 total_retrans; /* Total retransmits for entire connection */ u32 urg_seq; /* Seq of received urgent pointer */ diff --git a/include/net/act_api.h b/include/net/act_api.h index 683ce41053d9..8c9bc02d05e1 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -85,7 +85,7 @@ struct tc_action_ops { size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, - struct tcf_result *); + struct tcf_result *); /* called under RCU BH lock*/ int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); int (*lookup)(struct net *net, struct tc_action **a, u32 index, diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 8ae8ee004258..f53edb3754bc 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -61,7 +61,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, struct msghdr *, size_t, rxrpc_notify_end_tx_t); int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *, - void *, size_t, size_t *, bool, u32 *, u16 *); + struct iov_iter *, bool, u32 *, u16 *); bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, u32, int, const char *); void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 1668211297a9..7f008097552e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -183,6 +183,15 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_NON_PERSISTENT_DIAG, + + /* When this quirk is set, setup() would be run after every + * open() and not just after the first open(). + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + * + */ + HCI_QUIRK_NON_PERSISTENT_SETUP, }; /* HCI device flags */ @@ -291,6 +300,14 @@ enum { #define HCI_DH3 0x0800 #define HCI_DH5 0x8000 +/* HCI packet types inverted masks */ +#define HCI_2DH1 0x0002 +#define HCI_3DH1 0x0004 +#define HCI_2DH3 0x0100 +#define HCI_3DH3 0x0200 +#define HCI_2DH5 0x1000 +#define HCI_3DH5 0x2000 + #define HCI_HV1 0x0020 #define HCI_HV2 0x0040 #define HCI_HV3 0x0080 @@ -354,6 +371,8 @@ enum { #define LMP_PCONTROL 0x04 #define LMP_TRANSPARENT 0x08 +#define LMP_EDR_2M 0x02 +#define LMP_EDR_3M 0x04 #define LMP_RSSI_INQ 0x40 #define LMP_ESCO 0x80 @@ -361,7 +380,9 @@ enum { #define LMP_EV5 0x02 #define LMP_NO_BREDR 0x20 #define LMP_LE 0x40 +#define LMP_EDR_3SLOT 0x80 +#define LMP_EDR_5SLOT 0x01 #define LMP_SNIFF_SUBR 0x02 #define LMP_PAUSE_ENC 0x04 #define LMP_EDR_ESCO_2M 0x20 @@ -398,7 +419,12 @@ enum { #define HCI_LE_SLAVE_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 +#define HCI_LE_PHY_2M 0x01 +#define HCI_LE_PHY_CODED 0x08 +#define HCI_LE_EXT_ADV 0x10 #define HCI_LE_EXT_SCAN_POLICY 0x80 +#define HCI_LE_PHY_2M 0x01 +#define HCI_LE_PHY_CODED 0x08 #define HCI_LE_CHAN_SEL_ALG2 0x40 /* Connection modes */ @@ -1490,6 +1516,14 @@ struct hci_cp_le_write_def_data_len { __le16 tx_time; } __packed; +#define HCI_OP_LE_CLEAR_RESOLV_LIST 0x2029 + +#define HCI_OP_LE_READ_RESOLV_LIST_SIZE 0x202a +struct hci_rp_le_read_resolv_list_size { + __u8 status; + __u8 size; +} __packed; + #define HCI_OP_LE_READ_MAX_DATA_LEN 0x202f struct hci_rp_le_read_max_data_len { __u8 status; @@ -1506,6 +1540,134 @@ struct hci_cp_le_set_default_phy { __u8 rx_phys; } __packed; +#define HCI_LE_SET_PHY_1M 0x01 +#define HCI_LE_SET_PHY_2M 0x02 +#define HCI_LE_SET_PHY_CODED 0x04 + +#define HCI_OP_LE_SET_EXT_SCAN_PARAMS 0x2041 +struct hci_cp_le_set_ext_scan_params { + __u8 own_addr_type; + __u8 filter_policy; + __u8 scanning_phys; + __u8 data[0]; +} __packed; + +#define LE_SCAN_PHY_1M 0x01 +#define LE_SCAN_PHY_2M 0x02 +#define LE_SCAN_PHY_CODED 0x04 + +struct hci_cp_le_scan_phy_params { + __u8 type; + __le16 interval; + __le16 window; +} __packed; + +#define HCI_OP_LE_SET_EXT_SCAN_ENABLE 0x2042 +struct hci_cp_le_set_ext_scan_enable { + __u8 enable; + __u8 filter_dup; + __le16 duration; + __le16 period; +} __packed; + +#define HCI_OP_LE_EXT_CREATE_CONN 0x2043 +struct hci_cp_le_ext_create_conn { + __u8 filter_policy; + __u8 own_addr_type; + __u8 peer_addr_type; + bdaddr_t peer_addr; + __u8 phys; + __u8 data[0]; +} __packed; + +struct hci_cp_le_ext_conn_param { + __le16 scan_interval; + __le16 scan_window; + __le16 conn_interval_min; + __le16 conn_interval_max; + __le16 conn_latency; + __le16 supervision_timeout; + __le16 min_ce_len; + __le16 max_ce_len; +} __packed; + +#define HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS 0x203b +struct hci_rp_le_read_num_supported_adv_sets { + __u8 status; + __u8 num_of_sets; +} __packed; + +#define HCI_OP_LE_SET_EXT_ADV_PARAMS 0x2036 +struct hci_cp_le_set_ext_adv_params { + __u8 handle; + __le16 evt_properties; + __u8 min_interval[3]; + __u8 max_interval[3]; + __u8 channel_map; + __u8 own_addr_type; + __u8 peer_addr_type; + bdaddr_t peer_addr; + __u8 filter_policy; + __u8 tx_power; + __u8 primary_phy; + __u8 secondary_max_skip; + __u8 secondary_phy; + __u8 sid; + __u8 notif_enable; +} __packed; + +#define HCI_ADV_PHY_1M 0X01 +#define HCI_ADV_PHY_2M 0x02 +#define HCI_ADV_PHY_CODED 0x03 + +struct hci_rp_le_set_ext_adv_params { + __u8 status; + __u8 tx_power; +} __packed; + +#define HCI_OP_LE_SET_EXT_ADV_ENABLE 0x2039 +struct hci_cp_le_set_ext_adv_enable { + __u8 enable; + __u8 num_of_sets; + __u8 data[0]; +} __packed; + +struct hci_cp_ext_adv_set { + __u8 handle; + __le16 duration; + __u8 max_events; +} __packed; + +#define HCI_OP_LE_SET_EXT_ADV_DATA 0x2037 +struct hci_cp_le_set_ext_adv_data { + __u8 handle; + __u8 operation; + __u8 frag_pref; + __u8 length; + __u8 data[HCI_MAX_AD_LENGTH]; +} __packed; + +#define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 +struct hci_cp_le_set_ext_scan_rsp_data { + __u8 handle; + __u8 operation; + __u8 frag_pref; + __u8 length; + __u8 data[HCI_MAX_AD_LENGTH]; +} __packed; + +#define LE_SET_ADV_DATA_OP_COMPLETE 0x03 + +#define LE_SET_ADV_DATA_NO_FRAG 0x01 + +#define HCI_OP_LE_CLEAR_ADV_SETS 0x203d + +#define HCI_OP_LE_SET_ADV_SET_RAND_ADDR 0x2035 +struct hci_cp_le_set_adv_set_rand_addr { + __u8 handle; + bdaddr_t bdaddr; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 @@ -1893,6 +2055,23 @@ struct hci_ev_le_conn_complete { #define LE_ADV_SCAN_IND 0x02 #define LE_ADV_NONCONN_IND 0x03 #define LE_ADV_SCAN_RSP 0x04 +#define LE_ADV_INVALID 0x05 + +/* Legacy event types in extended adv report */ +#define LE_LEGACY_ADV_IND 0x0013 +#define LE_LEGACY_ADV_DIRECT_IND 0x0015 +#define LE_LEGACY_ADV_SCAN_IND 0x0012 +#define LE_LEGACY_NONCONN_IND 0x0010 +#define LE_LEGACY_SCAN_RSP_ADV 0x001b +#define LE_LEGACY_SCAN_RSP_ADV_SCAN 0x001a + +/* Extended Advertising event types */ +#define LE_EXT_ADV_NON_CONN_IND 0x0000 +#define LE_EXT_ADV_CONN_IND 0x0001 +#define LE_EXT_ADV_SCAN_IND 0x0002 +#define LE_EXT_ADV_DIRECT_IND 0x0004 +#define LE_EXT_ADV_SCAN_RSP 0x0008 +#define LE_EXT_ADV_LEGACY_PDU 0x0010 #define ADDR_LE_DEV_PUBLIC 0x00 #define ADDR_LE_DEV_RANDOM 0x01 @@ -1957,6 +2136,46 @@ struct hci_ev_le_direct_adv_info { __s8 rssi; } __packed; +#define HCI_EV_LE_EXT_ADV_REPORT 0x0d +struct hci_ev_le_ext_adv_report { + __le16 evt_type; + __u8 bdaddr_type; + bdaddr_t bdaddr; + __u8 primary_phy; + __u8 secondary_phy; + __u8 sid; + __u8 tx_power; + __s8 rssi; + __le16 interval; + __u8 direct_addr_type; + bdaddr_t direct_addr; + __u8 length; + __u8 data[0]; +} __packed; + +#define HCI_EV_LE_ENHANCED_CONN_COMPLETE 0x0a +struct hci_ev_le_enh_conn_complete { + __u8 status; + __le16 handle; + __u8 role; + __u8 bdaddr_type; + bdaddr_t bdaddr; + bdaddr_t local_rpa; + bdaddr_t peer_rpa; + __le16 interval; + __le16 latency; + __le16 supervision_timeout; + __u8 clk_accurancy; +} __packed; + +#define HCI_EV_LE_EXT_ADV_SET_TERM 0x12 +struct hci_evt_le_ext_adv_set_term { + __u8 status; + __u8 handle; + __le16 conn_handle; + __u8 num_evts; +} __packed; + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xfd struct hci_ev_stack_internal { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 893bbbb5d2fa..0db1b9b428b7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -171,6 +171,10 @@ struct adv_info { __u8 adv_data[HCI_MAX_AD_LENGTH]; __u16 scan_rsp_len; __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; + __s8 tx_power; + bdaddr_t random_addr; + bool rpa_expired; + struct delayed_work rpa_expired_cb; }; #define HCI_MAX_ADV_INSTANCES 5 @@ -221,6 +225,8 @@ struct hci_dev { __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; __u8 le_white_list_size; + __u8 le_resolv_list_size; + __u8 le_num_of_adv_sets; __u8 le_states[8]; __u8 commands[64]; __u8 hci_ver; @@ -314,6 +320,9 @@ struct hci_dev { unsigned long sco_last_tx; unsigned long le_last_tx; + __u8 le_tx_def_phys; + __u8 le_rx_def_phys; + struct workqueue_struct *workqueue; struct workqueue_struct *req_workqueue; @@ -367,6 +376,7 @@ struct hci_dev { struct list_head identity_resolving_keys; struct list_head remote_oob_data; struct list_head le_white_list; + struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; struct list_head pend_le_reports; @@ -1106,6 +1116,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration); int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); +void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); @@ -1136,6 +1147,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR) #define lmp_ext_feat_capable(dev) ((dev)->features[0][7] & LMP_EXTFEATURES) #define lmp_transp_capable(dev) ((dev)->features[0][2] & LMP_TRANSPARENT) +#define lmp_edr_2m_capable(dev) ((dev)->features[0][3] & LMP_EDR_2M) +#define lmp_edr_3m_capable(dev) ((dev)->features[0][3] & LMP_EDR_3M) +#define lmp_edr_3slot_capable(dev) ((dev)->features[0][4] & LMP_EDR_3SLOT) +#define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ #define lmp_csb_master_capable(dev) ((dev)->features[2][0] & LMP_CSB_MASTER) @@ -1156,6 +1171,24 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) +#define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ + ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) + +#define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \ + ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) + +#define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ + ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) + +/* Use ext scanning if set ext scan param and ext scan enable is supported */ +#define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ + ((dev)->commands[37] & 0x40)) +/* Use ext create connection if command is supported */ +#define use_ext_conn(dev) ((dev)->commands[37] & 0x80) + +/* Extended advertising support */ +#define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 @@ -1529,6 +1562,7 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); +int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index e7303eee65cd..9cee7ddc6741 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -101,6 +101,7 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_PRIVACY 0x00002000 #define MGMT_SETTING_CONFIGURATION 0x00004000 #define MGMT_SETTING_STATIC_ADDRESS 0x00008000 +#define MGMT_SETTING_PHY_CONFIGURATION 0x00010000 #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 @@ -561,6 +562,12 @@ struct mgmt_rp_add_advertising { #define MGMT_ADV_FLAG_TX_POWER BIT(4) #define MGMT_ADV_FLAG_APPEARANCE BIT(5) #define MGMT_ADV_FLAG_LOCAL_NAME BIT(6) +#define MGMT_ADV_FLAG_SEC_1M BIT(7) +#define MGMT_ADV_FLAG_SEC_2M BIT(8) +#define MGMT_ADV_FLAG_SEC_CODED BIT(9) + +#define MGMT_ADV_FLAG_SEC_MASK (MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \ + MGMT_ADV_FLAG_SEC_CODED) #define MGMT_OP_REMOVE_ADVERTISING 0x003F struct mgmt_cp_remove_advertising { @@ -604,6 +611,49 @@ struct mgmt_cp_set_appearance { } __packed; #define MGMT_SET_APPEARANCE_SIZE 2 +#define MGMT_OP_GET_PHY_CONFIGURATION 0x0044 +struct mgmt_rp_get_phy_confguration { + __le32 supported_phys; + __le32 configurable_phys; + __le32 selected_phys; +} __packed; +#define MGMT_GET_PHY_CONFIGURATION_SIZE 0 + +#define MGMT_PHY_BR_1M_1SLOT 0x00000001 +#define MGMT_PHY_BR_1M_3SLOT 0x00000002 +#define MGMT_PHY_BR_1M_5SLOT 0x00000004 +#define MGMT_PHY_EDR_2M_1SLOT 0x00000008 +#define MGMT_PHY_EDR_2M_3SLOT 0x00000010 +#define MGMT_PHY_EDR_2M_5SLOT 0x00000020 +#define MGMT_PHY_EDR_3M_1SLOT 0x00000040 +#define MGMT_PHY_EDR_3M_3SLOT 0x00000080 +#define MGMT_PHY_EDR_3M_5SLOT 0x00000100 +#define MGMT_PHY_LE_1M_TX 0x00000200 +#define MGMT_PHY_LE_1M_RX 0x00000400 +#define MGMT_PHY_LE_2M_TX 0x00000800 +#define MGMT_PHY_LE_2M_RX 0x00001000 +#define MGMT_PHY_LE_CODED_TX 0x00002000 +#define MGMT_PHY_LE_CODED_RX 0x00004000 + +#define MGMT_PHY_BREDR_MASK (MGMT_PHY_BR_1M_1SLOT | MGMT_PHY_BR_1M_3SLOT | \ + MGMT_PHY_BR_1M_5SLOT | MGMT_PHY_EDR_2M_1SLOT | \ + MGMT_PHY_EDR_2M_3SLOT | MGMT_PHY_EDR_2M_5SLOT | \ + MGMT_PHY_EDR_3M_1SLOT | MGMT_PHY_EDR_3M_3SLOT | \ + MGMT_PHY_EDR_3M_5SLOT) +#define MGMT_PHY_LE_MASK (MGMT_PHY_LE_1M_TX | MGMT_PHY_LE_1M_RX | \ + MGMT_PHY_LE_2M_TX | MGMT_PHY_LE_2M_RX | \ + MGMT_PHY_LE_CODED_TX | MGMT_PHY_LE_CODED_RX) +#define MGMT_PHY_LE_TX_MASK (MGMT_PHY_LE_1M_TX | MGMT_PHY_LE_2M_TX | \ + MGMT_PHY_LE_CODED_TX) +#define MGMT_PHY_LE_RX_MASK (MGMT_PHY_LE_1M_RX | MGMT_PHY_LE_2M_RX | \ + MGMT_PHY_LE_CODED_RX) + +#define MGMT_OP_SET_PHY_CONFIGURATION 0x0045 +struct mgmt_cp_set_phy_confguration { + __le32 selected_phys; +} __packed; +#define MGMT_SET_PHY_CONFIGURATION_SIZE 4 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -824,3 +874,8 @@ struct mgmt_ev_ext_info_changed { __le16 eir_len; __u8 eir[0]; } __packed; + +#define MGMT_EV_PHY_CONFIGURATION_CHANGED 0x0026 +struct mgmt_ev_phy_configuration_changed { + __le32 selected_phys; +} __packed; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index f358ad5e4214..fc3111515f5c 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -283,7 +283,7 @@ static inline const char *bond_3ad_churn_desc(churn_state_t state) "none", "unknown" }; - int max_size = sizeof(churn_description) / sizeof(churn_description[0]); + int max_size = ARRAY_SIZE(churn_description); if (state >= max_size) state = max_size - 1; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9e36fda652b7..ba61cdd09eaa 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -121,21 +121,6 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) #endif } -static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events) -{ - if (sk_can_busy_loop(sock->sk) && - events && (events & POLL_BUSY_LOOP)) { - /* once, only if requested by syscall */ - sk_busy_loop(sock->sk, 1); - } -} - -/* if this socket can poll_ll, tell the system call */ -static inline __poll_t sock_poll_busy_flag(struct socket *sock) -{ - return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0; -} - /* used in the NIC receive handler to mark the skb */ static inline void skb_mark_napi_id(struct sk_buff *skb, struct napi_struct *napi) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9ba1f289c439..9a850973e09a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5937,10 +5937,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, /** * cfg80211_rx_control_port - notification about a received control port frame * @dev: The device the frame matched to - * @buf: control port frame - * @len: length of the frame data - * @addr: The peer from which the frame was received - * @proto: frame protocol, typically PAE or Pre-authentication + * @skb: The skbuf with the control port frame. It is assumed that the skbuf + * is 802.3 formatted (with 802.3 header). The skb can be non-linear. + * This function does not take ownership of the skb, so the caller is + * responsible for any cleanup. The caller must also ensure that + * skb->protocol is set appropriately. * @unencrypted: Whether the frame was received unencrypted * * This function is used to inform userspace about a received control port @@ -5953,8 +5954,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, * Return: %true if the frame was passed to userspace */ bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted); + struct sk_buff *skb, bool unencrypted); /** * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 0e5e91be2d30..e22a8a3c089b 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -34,6 +34,19 @@ 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_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); + +struct dcb_ieee_app_dscp_map { + u8 map[64]; +}; +void dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, + struct dcb_ieee_app_dscp_map *p_map); +u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev); + int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 pid); int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, diff --git a/include/net/dst.h b/include/net/dst.h index b3219cd8a5a1..7f735e76ca73 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -475,6 +475,14 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, return dst_orig; } +static inline struct dst_entry * +xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags, u32 if_id) +{ + return dst_orig; +} + static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, @@ -494,6 +502,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, int flags, + u32 if_id); + struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index f4272a29dc44..b86d14528188 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -75,7 +75,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; refcount_t refcnt; - struct sk_buff *fragments; + struct sk_buff *fragments; /* Used in IPv6. */ + struct rb_root rb_fragments; /* Used in IPv4. */ struct sk_buff *fragments_tail; ktime_t stamp; int len; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 314be484c696..e03b93360f33 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -359,4 +359,12 @@ static inline bool inet_get_convert_csum(struct sock *sk) return !!inet_sk(sk)->convert_csum; } + +static inline bool inet_can_nonlocal_bind(struct net *net, + struct inet_sock *inet) +{ + return net->ipv4.sysctl_ip_nonlocal_bind || + inet->freebind || inet->transparent; +} + #endif /* _INET_SOCK_H */ diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 71b9043aa0e7..3d4930528db0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i) atomic_inc(&f6i->fib6_ref); } +static inline bool fib6_info_hold_safe(struct fib6_info *f6i) +{ + return atomic_inc_not_zero(&f6i->fib6_ref); +} + static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index a44509f4e985..ff33f498c137 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -782,6 +782,13 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, #if IS_ENABLED(CONFIG_IPV6) +static inline bool ipv6_can_nonlocal_bind(struct net *net, + struct inet_sock *inet) +{ + return net->ipv6.sysctl.ip_nonlocal_bind || + inet->freebind || inet->transparent; +} + /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 diff --git a/include/net/netevent.h b/include/net/netevent.h index d9918261701c..4107016c3bb4 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -28,6 +28,7 @@ enum netevent_notif_type { NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */ NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */ NETEVENT_IPV6_MPATH_HASH_UPDATE, /* arg is struct net ptr */ + NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, /* arg is struct net ptr */ }; int register_netevent_notifier(struct notifier_block *nb); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a2b0ed025908..7e012312cd61 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -176,8 +176,6 @@ void nf_ct_netns_put(struct net *net, u8 nfproto); */ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -void nf_ct_free_hashtable(void *hash, unsigned int size); - int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 08c005ce56e9..dc417ef0a0c5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data) * @portid: netlink portID of the original message * @seq: netlink sequence number * @family: protocol family + * @level: depth of the chains * @report: notify via unicast netlink message */ struct nft_ctx { @@ -160,6 +161,7 @@ struct nft_ctx { u32 portid; u32 seq; u8 family; + u8 level; bool report; }; @@ -865,7 +867,6 @@ enum nft_chain_flags { * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain - * @level: length of longest path to this chain * @flags: bitmask of enum nft_chain_flags * @name: name of the chain */ @@ -878,7 +879,6 @@ struct nft_chain { struct nft_table *table; u64 handle; u32 use; - u16 level; u8 flags:6, genmask:2; char *name; @@ -1124,7 +1124,6 @@ struct nft_flowtable { u32 genmask:2, use:30; u64 handle; - char *dev_name[NFT_FLOWTABLE_DEVICE_MAX]; /* runtime data below here */ struct nf_hook_ops *ops ____cacheline_aligned; struct nf_flowtable data; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index a05134507e7b..8da837d2aaf9 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -71,4 +71,11 @@ extern struct nft_set_type nft_set_hash_fast_type; extern struct nft_set_type nft_set_rbtree_type; extern struct nft_set_type nft_set_bitmap_type; +struct nft_expr; +struct nft_regs; +struct nft_pktinfo; +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_lookup_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/net/netns/ipv4.h b/include/net/netns/ipv4.h index 661348f23ea5..e47503b4e4d1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -98,6 +98,7 @@ struct netns_ipv4 { int sysctl_ip_default_ttl; int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; + int sysctl_ip_fwd_update_priority; int sysctl_ip_nonlocal_bind; /* Shall we try to damage output packets if routing dev changes? */ int sysctl_ip_dynaddr; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3101582f642..ef727f71336e 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -7,6 +7,9 @@ #include <net/sch_generic.h> #include <net/act_api.h> +/* TC action not accessible from user space */ +#define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) + /* Basic packet classifier frontend definitions. */ struct tcf_walker { @@ -37,9 +40,9 @@ struct tcf_block_cb; bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); #ifdef CONFIG_NET_CLS -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, - bool create); -void tcf_chain_put(struct tcf_chain *chain); +struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, + u32 chain_index); +void tcf_chain_put_by_act(struct tcf_chain *chain); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 085c509c8674..a6d00093f35e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -235,6 +235,12 @@ struct tcf_result { u32 classid; }; const struct tcf_proto *goto_tp; + + /* used by the TC_ACT_REINSERT action */ + struct { + bool ingress; + struct gnet_stats_queue *qstats; + }; }; }; @@ -285,6 +291,8 @@ struct tcf_proto { /* Fast access part */ struct tcf_proto __rcu *next; void __rcu *root; + + /* called under RCU BH lock*/ int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); @@ -314,6 +322,7 @@ struct tcf_chain { struct tcf_block *block; u32 index; /* chain index */ unsigned int refcnt; + unsigned int action_refcnt; bool explicitly_created; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; @@ -566,6 +575,15 @@ static inline void skb_reset_tc(struct sk_buff *skb) #endif } +static inline bool skb_is_tc_redirected(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + return skb->tc_redirected; +#else + return false; +#endif +} + static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT @@ -1105,4 +1123,17 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq); +static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) +{ + struct gnet_stats_queue *stats = res->qstats; + int ret; + + if (res->ingress) + ret = netif_receive_skb(skb); + else + ret = dev_queue_xmit(skb); + if (ret && stats) + qstats_overlimit_inc(res->qstats); +} + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 83b747538bd0..433f45fc2d68 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1788,7 +1788,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); - sk->sk_wq = parent->wq; + rcu_assign_pointer(sk->sk_wq, parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; @@ -2057,16 +2057,16 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) /** * sock_poll_wait - place memory barrier behind the poll_wait call. * @filp: file - * @wait_address: socket wait queue * @p: poll_table * * See the comments in the wq_has_sleeper function. */ -static inline void sock_poll_wait(struct file *filp, - wait_queue_head_t *wait_address, poll_table *p) +static inline void sock_poll_wait(struct file *filp, poll_table *p) { - if (!poll_does_not_wait(p) && wait_address) { - poll_wait(filp, wait_address, p); + struct socket *sock = filp->private_data; + + if (!poll_does_not_wait(p)) { + poll_wait(filp, &sock->wq->wait, p); /* We need to be sure we are in sync with the * socket flags modification. * diff --git a/include/net/tcp.h b/include/net/tcp.h index f6e0a9b1dff3..d769dc20359b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { @@ -540,6 +541,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -840,6 +842,11 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) */ static inline int tcp_v6_iif(const struct sk_buff *skb) { + return TCP_SKB_CB(skb)->header.h6.iif; +} + +static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) +{ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 557122846e0e..ca820945f30c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -23,6 +23,7 @@ #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/flow.h> +#include <net/gro_cells.h> #include <linux/interrupt.h> @@ -147,6 +148,7 @@ struct xfrm_state { struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; + u32 if_id; u32 tfcpad; u32 genid; @@ -166,7 +168,7 @@ struct xfrm_state { int header_len; int trailer_len; u32 extra_flags; - u32 output_mark; + struct xfrm_mark smark; } props; struct xfrm_lifetime_cfg lft; @@ -225,7 +227,7 @@ struct xfrm_state { long saved_tmo; /* Last used time */ - unsigned long lastused; + time64_t lastused; struct page_frag xfrag; @@ -292,6 +294,13 @@ struct xfrm_replay { int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); }; +struct xfrm_if_cb { + struct xfrm_if *(*decode_session)(struct sk_buff *skb); +}; + +void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); +void xfrm_if_unregister_cb(void); + struct net_device; struct xfrm_type; struct xfrm_dst; @@ -323,7 +332,6 @@ int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int fam void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); -void xfrm_policy_cache_flush(void); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; @@ -574,6 +582,7 @@ struct xfrm_policy { atomic_t genid; u32 priority; u32 index; + u32 if_id; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; @@ -1037,6 +1046,22 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); +struct xfrm_if_parms { + char name[IFNAMSIZ]; /* name of XFRM device */ + int link; /* ifindex of underlying L2 interface */ + u32 if_id; /* interface identifyer */ +}; + +struct xfrm_if { + struct xfrm_if __rcu *next; /* next interface in list */ + struct net_device *dev; /* virtual device associated with interface */ + struct net_device *phydev; /* physical device */ + struct net *net; /* netns for packet i/o */ + struct xfrm_if_parms p; /* interface parms */ + + struct gro_cells gro_cells; +}; + struct xfrm_offload { /* Output sequence number for replay protection on offloading. */ struct { @@ -1532,8 +1557,8 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family); -struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, + unsigned short family, u32 if_id); +struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, @@ -1690,20 +1715,20 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, - u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8, + int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, - u8 mode, u32 reqid, u8 proto, + u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); @@ -2012,6 +2037,22 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) return ret; } +static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) +{ + struct xfrm_mark *m = &x->props.smark; + + return (m->v & m->m) | (mark & ~m->m); +} + +static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id) +{ + int ret = 0; + + if (if_id) + ret = nla_put_u32(skb, XFRMA_IF_ID, if_id); + return ret; +} + static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4fff00e9da8a..196587b8f204 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -211,18 +211,18 @@ enum rxrpc_congest_change { rxrpc_cong_saw_nack, }; -enum rxrpc_tx_fail_trace { - rxrpc_tx_fail_call_abort, - rxrpc_tx_fail_call_ack, - rxrpc_tx_fail_call_data_frag, - rxrpc_tx_fail_call_data_nofrag, - rxrpc_tx_fail_call_final_resend, - rxrpc_tx_fail_conn_abort, - rxrpc_tx_fail_conn_challenge, - rxrpc_tx_fail_conn_response, - rxrpc_tx_fail_reject, - rxrpc_tx_fail_version_keepalive, - rxrpc_tx_fail_version_reply, +enum rxrpc_tx_point { + rxrpc_tx_point_call_abort, + rxrpc_tx_point_call_ack, + rxrpc_tx_point_call_data_frag, + rxrpc_tx_point_call_data_nofrag, + rxrpc_tx_point_call_final_resend, + rxrpc_tx_point_conn_abort, + rxrpc_tx_point_rxkad_challenge, + rxrpc_tx_point_rxkad_response, + rxrpc_tx_point_reject, + rxrpc_tx_point_version_keepalive, + rxrpc_tx_point_version_reply, }; #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -396,7 +396,7 @@ enum rxrpc_tx_fail_trace { #define rxrpc_propose_ack_outcomes \ EM(rxrpc_propose_ack_subsume, " Subsume") \ EM(rxrpc_propose_ack_update, " Update") \ - E_(rxrpc_propose_ack_use, "") + E_(rxrpc_propose_ack_use, " New") #define rxrpc_congest_modes \ EM(RXRPC_CALL_CONGEST_AVOIDANCE, "CongAvoid") \ @@ -452,18 +452,18 @@ enum rxrpc_tx_fail_trace { EM(RXRPC_CALL_LOCAL_ERROR, "LocalError") \ E_(RXRPC_CALL_NETWORK_ERROR, "NetError") -#define rxrpc_tx_fail_traces \ - EM(rxrpc_tx_fail_call_abort, "CallAbort") \ - EM(rxrpc_tx_fail_call_ack, "CallAck") \ - EM(rxrpc_tx_fail_call_data_frag, "CallDataFrag") \ - EM(rxrpc_tx_fail_call_data_nofrag, "CallDataNofrag") \ - EM(rxrpc_tx_fail_call_final_resend, "CallFinalResend") \ - EM(rxrpc_tx_fail_conn_abort, "ConnAbort") \ - EM(rxrpc_tx_fail_conn_challenge, "ConnChall") \ - EM(rxrpc_tx_fail_conn_response, "ConnResp") \ - EM(rxrpc_tx_fail_reject, "Reject") \ - EM(rxrpc_tx_fail_version_keepalive, "VerKeepalive") \ - E_(rxrpc_tx_fail_version_reply, "VerReply") +#define rxrpc_tx_points \ + EM(rxrpc_tx_point_call_abort, "CallAbort") \ + EM(rxrpc_tx_point_call_ack, "CallAck") \ + EM(rxrpc_tx_point_call_data_frag, "CallDataFrag") \ + EM(rxrpc_tx_point_call_data_nofrag, "CallDataNofrag") \ + EM(rxrpc_tx_point_call_final_resend, "CallFinalResend") \ + EM(rxrpc_tx_point_conn_abort, "ConnAbort") \ + EM(rxrpc_tx_point_reject, "Reject") \ + EM(rxrpc_tx_point_rxkad_challenge, "RxkadChall") \ + EM(rxrpc_tx_point_rxkad_response, "RxkadResp") \ + EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ + E_(rxrpc_tx_point_version_reply, "VerReply") /* * Export enum symbols via userspace. @@ -488,7 +488,7 @@ rxrpc_propose_ack_traces; rxrpc_propose_ack_outcomes; rxrpc_congest_modes; rxrpc_congest_changes; -rxrpc_tx_fail_traces; +rxrpc_tx_points; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -801,7 +801,7 @@ TRACE_EVENT(rxrpc_transmit, ); TRACE_EVENT(rxrpc_rx_data, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, + TP_PROTO(unsigned int call, rxrpc_seq_t seq, rxrpc_serial_t serial, u8 flags, u8 anno), TP_ARGS(call, seq, serial, flags, anno), @@ -815,7 +815,7 @@ TRACE_EVENT(rxrpc_rx_data, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call; __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; @@ -918,6 +918,37 @@ TRACE_EVENT(rxrpc_rx_rwind_change, __entry->wake ? " wake" : "") ); +TRACE_EVENT(rxrpc_tx_packet, + TP_PROTO(unsigned int call_id, struct rxrpc_wire_header *whdr, + enum rxrpc_tx_point where), + + TP_ARGS(call_id, whdr, where), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_tx_point, where ) + __field_struct(struct rxrpc_wire_header, whdr ) + ), + + TP_fast_assign( + __entry->call = call_id; + memcpy(&__entry->whdr, whdr, sizeof(__entry->whdr)); + ), + + TP_printk("c=%08x %08x:%08x:%08x:%04x %08x %08x %02x %02x %s %s", + __entry->call, + ntohl(__entry->whdr.epoch), + ntohl(__entry->whdr.cid), + ntohl(__entry->whdr.callNumber), + ntohs(__entry->whdr.serviceId), + ntohl(__entry->whdr.serial), + ntohl(__entry->whdr.seq), + __entry->whdr.type, __entry->whdr.flags, + __entry->whdr.type <= 15 ? + __print_symbolic(__entry->whdr.type, rxrpc_pkts) : "?UNK", + __print_symbolic(__entry->where, rxrpc_tx_points)) + ); + TRACE_EVENT(rxrpc_tx_data, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, rxrpc_serial_t serial, u8 flags, bool retrans, bool lose), @@ -928,6 +959,8 @@ TRACE_EVENT(rxrpc_tx_data, __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) __field(rxrpc_serial_t, serial ) + __field(u32, cid ) + __field(u32, call_id ) __field(u8, flags ) __field(bool, retrans ) __field(bool, lose ) @@ -935,6 +968,8 @@ TRACE_EVENT(rxrpc_tx_data, TP_fast_assign( __entry->call = call->debug_id; + __entry->cid = call->cid; + __entry->call_id = call->call_id; __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; @@ -942,8 +977,10 @@ TRACE_EVENT(rxrpc_tx_data, __entry->lose = lose; ), - TP_printk("c=%08x DATA %08x q=%08x fl=%02x%s%s", + TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s%s", __entry->call, + __entry->cid, + __entry->call_id, __entry->serial, __entry->seq, __entry->flags, @@ -952,7 +989,7 @@ TRACE_EVENT(rxrpc_tx_data, ); TRACE_EVENT(rxrpc_tx_ack, - TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, + TP_PROTO(unsigned int call, rxrpc_serial_t serial, rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial, u8 reason, u8 n_acks), @@ -968,7 +1005,7 @@ TRACE_EVENT(rxrpc_tx_ack, ), TP_fast_assign( - __entry->call = call ? call->debug_id : 0; + __entry->call = call; __entry->serial = serial; __entry->ack_first = ack_first; __entry->ack_serial = ack_serial; @@ -1434,29 +1471,29 @@ TRACE_EVENT(rxrpc_rx_icmp, TRACE_EVENT(rxrpc_tx_fail, TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret, - enum rxrpc_tx_fail_trace what), + enum rxrpc_tx_point where), - TP_ARGS(debug_id, serial, ret, what), + TP_ARGS(debug_id, serial, ret, where), TP_STRUCT__entry( __field(unsigned int, debug_id ) __field(rxrpc_serial_t, serial ) __field(int, ret ) - __field(enum rxrpc_tx_fail_trace, what ) + __field(enum rxrpc_tx_point, where ) ), TP_fast_assign( __entry->debug_id = debug_id; __entry->serial = serial; __entry->ret = ret; - __entry->what = what; + __entry->where = where; ), TP_printk("c=%08x r=%x ret=%d %s", __entry->debug_id, __entry->serial, __entry->ret, - __print_symbolic(__entry->what, rxrpc_tx_fail_traces)) + __print_symbolic(__entry->where, rxrpc_tx_points)) ); TRACE_EVENT(rxrpc_call_reset, @@ -1491,6 +1528,26 @@ TRACE_EVENT(rxrpc_call_reset, __entry->tx_seq, __entry->rx_seq) ); +TRACE_EVENT(rxrpc_notify_socket, + TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial), + + TP_ARGS(debug_id, serial), + + TP_STRUCT__entry( + __field(unsigned int, debug_id ) + __field(rxrpc_serial_t, serial ) + ), + + TP_fast_assign( + __entry->debug_id = debug_id; + __entry->serial = serial; + ), + + TP_printk("c=%08x r=%08x", + __entry->debug_id, + __entry->serial) + ); + #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index 3c5038b587ba..d4593a6062ef 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -29,7 +29,6 @@ #include <linux/types.h> #include <linux/fs.h> -#include <linux/signal.h> #include <asm/byteorder.h> typedef __kernel_ulong_t aio_context_t; @@ -110,10 +109,5 @@ struct iocb { #undef IFBIG #undef IFLITTLE -struct __aio_sigset { - const sigset_t __user *sigmask; - size_t sigsetsize; -}; - #endif /* __LINUX__AIO_ABI_H */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index d7f97ac197a9..0afb7d8e867f 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -77,7 +77,7 @@ typedef __u32 canid_t; /* * Controller Area Network Error Message Frame Mask structure * - * bit 0-28 : error class mask (see include/linux/can/error.h) + * bit 0-28 : error class mask (see include/uapi/linux/can/error.h) * bit 29-31 : set to zero */ typedef __u32 can_err_mask_t; diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 60aa2e446698..69df19aa8e72 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -233,7 +233,8 @@ struct cee_pfc { * 2 Well known port number over TCP or SCTP * 3 Well known port number over UDP or DCCP * 4 Well known port number over TCP, SCTP, UDP, or DCCP - * 5-7 Reserved + * 5 Differentiated Services Code Point (DSCP) value + * 6-7 Reserved * * Selector field values for CEE * 0 Ethertype diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7363f18e65a5..813282cc8af6 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -902,13 +902,13 @@ struct ethtool_rx_flow_spec { static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie) { return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie; -}; +} static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie) { return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; -}; +} /** * struct ethtool_rxnfc - command to get or set RX flow classification rules diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 01b5069a73a5..43391e2d1153 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -164,6 +164,8 @@ enum { IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, __IFLA_MAX }; @@ -460,6 +462,16 @@ enum { #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + enum macsec_validation_type { MACSEC_VALIDATE_DISABLED = 0, MACSEC_VALIDATE_CHECK = 1, diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index b24a742beae5..e42d13b55cf3 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -168,6 +168,7 @@ enum IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, IPV4_DEVCONF_DROP_GRATUITOUS_ARP, + IPV4_DEVCONF_BC_FORWARDING, __IPV4_DEVCONF_MAX }; diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 7d570c7bd117..61158f5a1a5b 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -60,14 +60,14 @@ struct sockaddr_l2tpip6 { /* * Commands. * Valid TLVs of each command are:- - * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum, vlanid + * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum * TUNNEL_DELETE - CONN_ID * TUNNEL_MODIFY - CONN_ID, udpcsum * TUNNEL_GETSTATS - CONN_ID, (stats) * TUNNEL_GET - CONN_ID, (...) - * SESSION_CREATE - SESSION_ID, PW_TYPE, data_seq, cookie, peer_cookie, l2spec + * SESSION_CREATE - SESSION_ID, PW_TYPE, cookie, peer_cookie, l2spec * SESSION_DELETE - SESSION_ID - * SESSION_MODIFY - SESSION_ID, data_seq + * SESSION_MODIFY - SESSION_ID * SESSION_GET - SESSION_ID, (...) * SESSION_GETSTATS - SESSION_ID, (stats) * @@ -95,7 +95,7 @@ enum { L2TP_ATTR_PW_TYPE, /* u16, enum l2tp_pwtype */ L2TP_ATTR_ENCAP_TYPE, /* u16, enum l2tp_encap_type */ L2TP_ATTR_OFFSET, /* u16 (not used) */ - L2TP_ATTR_DATA_SEQ, /* u16 */ + L2TP_ATTR_DATA_SEQ, /* u16 (not used) */ L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */ L2TP_ATTR_L2SPEC_LEN, /* u8 (not used) */ L2TP_ATTR_PROTO_VERSION, /* u8 */ @@ -105,7 +105,7 @@ enum { L2TP_ATTR_SESSION_ID, /* u32 */ L2TP_ATTR_PEER_SESSION_ID, /* u32 */ L2TP_ATTR_UDP_CSUM, /* u8 */ - L2TP_ATTR_VLAN_ID, /* u16 */ + L2TP_ATTR_VLAN_ID, /* u16 (not used) */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ @@ -119,8 +119,8 @@ enum { L2TP_ATTR_IP_DADDR, /* u32 */ L2TP_ATTR_UDP_SPORT, /* u16 */ L2TP_ATTR_UDP_DPORT, /* u16 */ - L2TP_ATTR_MTU, /* u16 */ - L2TP_ATTR_MRU, /* u16 */ + L2TP_ATTR_MTU, /* u16 (not used) */ + L2TP_ATTR_MRU, /* u16 (not used) */ L2TP_ATTR_STATS, /* nested */ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */ L2TP_ATTR_IP6_DADDR, /* struct in6_addr */ @@ -169,6 +169,7 @@ enum l2tp_encap_type { L2TP_ENCAPTYPE_IP, }; +/* For L2TP_ATTR_DATA_SEQ. Unused. */ enum l2tp_seqmode { L2TP_SEQ_NONE = 0, L2TP_SEQ_IP = 1, diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index c84fcdfca862..fac4edd55379 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -18,6 +18,7 @@ enum { NETCONFA_PROXY_NEIGH, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_INPUT, + NETCONFA_BC_FORWARDING, __NETCONFA_MAX }; #define NETCONFA_MAX (__NETCONFA_MAX - 1) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index f466860bcf75..357862d948de 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1253,6 +1253,22 @@ enum nft_nat_attributes { #define NFTA_NAT_MAX (__NFTA_NAT_MAX - 1) /** + * enum nft_tproxy_attributes - nf_tables tproxy expression netlink attributes + * + * NFTA_TPROXY_FAMILY: Target address family (NLA_U32: nft_registers) + * NFTA_TPROXY_REG_ADDR: Target address register (NLA_U32: nft_registers) + * NFTA_TPROXY_REG_PORT: Target port register (NLA_U32: nft_registers) + */ +enum nft_tproxy_attributes { + NFTA_TPROXY_UNSPEC, + NFTA_TPROXY_FAMILY, + NFTA_TPROXY_REG_ADDR, + NFTA_TPROXY_REG_PORT, + __NFTA_TPROXY_MAX +}; +#define NFTA_TPROXY_MAX (__NFTA_TPROXY_MAX - 1) + +/** * enum nft_masq_attributes - nf_tables masquerade expression attributes * * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32) @@ -1400,7 +1416,8 @@ enum nft_ct_helper_attributes { #define NFT_OBJECT_CT_HELPER 3 #define NFT_OBJECT_LIMIT 4 #define NFT_OBJECT_CONNLIMIT 5 -#define __NFT_OBJECT_MAX 6 +#define NFT_OBJECT_TUNNEL 6 +#define __NFT_OBJECT_MAX 7 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** @@ -1463,6 +1480,13 @@ enum nft_flowtable_hook_attributes { }; #define NFTA_FLOWTABLE_HOOK_MAX (__NFTA_FLOWTABLE_HOOK_MAX - 1) +enum nft_osf_attributes { + NFTA_OSF_UNSPEC, + NFTA_OSF_DREG, + __NFTA_OSF_MAX, +}; +#define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1) + /** * enum nft_device_attributes - nf_tables device netlink attributes * @@ -1557,4 +1581,85 @@ enum nft_ng_types { }; #define NFT_NG_MAX (__NFT_NG_MAX - 1) +enum nft_tunnel_key_ip_attributes { + NFTA_TUNNEL_KEY_IP_UNSPEC, + NFTA_TUNNEL_KEY_IP_SRC, + NFTA_TUNNEL_KEY_IP_DST, + __NFTA_TUNNEL_KEY_IP_MAX +}; +#define NFTA_TUNNEL_KEY_IP_MAX (__NFTA_TUNNEL_KEY_IP_MAX - 1) + +enum nft_tunnel_ip6_attributes { + NFTA_TUNNEL_KEY_IP6_UNSPEC, + NFTA_TUNNEL_KEY_IP6_SRC, + NFTA_TUNNEL_KEY_IP6_DST, + NFTA_TUNNEL_KEY_IP6_FLOWLABEL, + __NFTA_TUNNEL_KEY_IP6_MAX +}; +#define NFTA_TUNNEL_KEY_IP6_MAX (__NFTA_TUNNEL_KEY_IP6_MAX - 1) + +enum nft_tunnel_opts_attributes { + NFTA_TUNNEL_KEY_OPTS_UNSPEC, + NFTA_TUNNEL_KEY_OPTS_VXLAN, + NFTA_TUNNEL_KEY_OPTS_ERSPAN, + __NFTA_TUNNEL_KEY_OPTS_MAX +}; +#define NFTA_TUNNEL_KEY_OPTS_MAX (__NFTA_TUNNEL_KEY_OPTS_MAX - 1) + +enum nft_tunnel_opts_vxlan_attributes { + NFTA_TUNNEL_KEY_VXLAN_UNSPEC, + NFTA_TUNNEL_KEY_VXLAN_GBP, + __NFTA_TUNNEL_KEY_VXLAN_MAX +}; +#define NFTA_TUNNEL_KEY_VXLAN_MAX (__NFTA_TUNNEL_KEY_VXLAN_MAX - 1) + +enum nft_tunnel_opts_erspan_attributes { + NFTA_TUNNEL_KEY_ERSPAN_UNSPEC, + NFTA_TUNNEL_KEY_ERSPAN_VERSION, + NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX, + NFTA_TUNNEL_KEY_ERSPAN_V2_HWID, + NFTA_TUNNEL_KEY_ERSPAN_V2_DIR, + __NFTA_TUNNEL_KEY_ERSPAN_MAX +}; +#define NFTA_TUNNEL_KEY_ERSPAN_MAX (__NFTA_TUNNEL_KEY_ERSPAN_MAX - 1) + +enum nft_tunnel_flags { + NFT_TUNNEL_F_ZERO_CSUM_TX = (1 << 0), + NFT_TUNNEL_F_DONT_FRAGMENT = (1 << 1), + NFT_TUNNEL_F_SEQ_NUMBER = (1 << 2), +}; +#define NFT_TUNNEL_F_MASK (NFT_TUNNEL_F_ZERO_CSUM_TX | \ + NFT_TUNNEL_F_DONT_FRAGMENT | \ + NFT_TUNNEL_F_SEQ_NUMBER) + +enum nft_tunnel_key_attributes { + NFTA_TUNNEL_KEY_UNSPEC, + NFTA_TUNNEL_KEY_ID, + NFTA_TUNNEL_KEY_IP, + NFTA_TUNNEL_KEY_IP6, + NFTA_TUNNEL_KEY_FLAGS, + NFTA_TUNNEL_KEY_TOS, + NFTA_TUNNEL_KEY_TTL, + NFTA_TUNNEL_KEY_SPORT, + NFTA_TUNNEL_KEY_DPORT, + NFTA_TUNNEL_KEY_OPTS, + __NFTA_TUNNEL_KEY_MAX +}; +#define NFTA_TUNNEL_KEY_MAX (__NFTA_TUNNEL_KEY_MAX - 1) + +enum nft_tunnel_keys { + NFT_TUNNEL_PATH, + NFT_TUNNEL_ID, + __NFT_TUNNEL_MAX +}; +#define NFT_TUNNEL_MAX (__NFT_TUNNEL_MAX - 1) + +enum nft_tunnel_attributes { + NFTA_TUNNEL_UNSPEC, + NFTA_TUNNEL_KEY, + NFTA_TUNNEL_DREG, + __NFTA_TUNNEL_MAX +}; +#define NFTA_TUNNEL_MAX (__NFTA_TUNNEL_MAX - 1) + #endif /* _LINUX_NF_TABLES_H */ diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nfnetlink_osf.h index 3738116b2bbe..3b93fbb9fc24 100644 --- a/include/uapi/linux/netfilter/nf_osf.h +++ b/include/uapi/linux/netfilter/nfnetlink_osf.h @@ -94,4 +94,13 @@ enum nf_osf_attr_type { OSF_ATTR_MAX, }; +/* + * Add/remove fingerprint from the kernel. + */ +enum nf_osf_msg_types { + OSF_MSG_ADD, + OSF_MSG_REMOVE, + OSF_MSG_MAX, +}; + #endif /* _NF_OSF_H */ diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index b189007f4f28..c56c59605c2b 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -23,7 +23,7 @@ #include <linux/types.h> #include <linux/ip.h> #include <linux/tcp.h> -#include <linux/netfilter/nf_osf.h> +#include <linux/netfilter/nfnetlink_osf.h> #define XT_OSF_GENRE NF_OSF_GENRE #define XT_OSF_INVERT NF_OSF_INVERT @@ -47,13 +47,6 @@ #define xt_osf_nlmsg nf_osf_nlmsg #define xt_osf_attr_type nf_osf_attr_type -/* - * Add/remove fingerprint from the kernel. - */ -enum xt_osf_msg_types { - OSF_MSG_ADD, - OSF_MSG_REMOVE, - OSF_MSG_MAX, -}; +#define xt_osf_msg_types nf_osf_msg_types #endif /* _XT_OSF_H */ diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 12fb77633f83..156ccd089df1 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -26,4 +26,15 @@ #define NF_BR_BROUTING 5 #define NF_BR_NUMHOOKS 6 +enum nf_br_hook_priorities { + NF_BR_PRI_FIRST = INT_MIN, + NF_BR_PRI_NAT_DST_BRIDGED = -300, + NF_BR_PRI_FILTER_BRIDGED = -200, + NF_BR_PRI_BRNF = 0, + NF_BR_PRI_NAT_DST_OTHER = 100, + NF_BR_PRI_FILTER_OTHER = 200, + NF_BR_PRI_NAT_SRC = 300, + NF_BR_PRI_LAST = INT_MAX, +}; + #endif /* _UAPI__LINUX_BRIDGE_NETFILTER_H */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index b4512254036b..48e5b5d49a34 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -45,6 +45,7 @@ enum { * the skb and act like everything * is alright. */ +#define TC_ACT_VALUE_MAX TC_ACT_TRAP /* There is a special kind of actions called "extended actions", * which need a value parameter. These have a local opcode located in @@ -55,11 +56,12 @@ enum { #define __TC_ACT_EXT_SHIFT 28 #define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT) #define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1) -#define TC_ACT_EXT_CMP(combined, opcode) \ - (((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode) +#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK)) +#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode) #define TC_ACT_JUMP __TC_ACT_EXT(1) #define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) +#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN /* Action type identifiers*/ enum { diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 48ae3ee22b2d..ac9e8c96d9bd 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -43,6 +43,7 @@ enum { SMC_DIAG_LGRINFO, SMC_DIAG_SHUTDOWN, SMC_DIAG_DMBINFO, + SMC_DIAG_FALLBACK, __SMC_DIAG_MAX, }; @@ -92,6 +93,11 @@ struct smc_diag_lgrinfo { __u8 role; }; +struct smc_diag_fallback { + __u32 reason; + __u32 peer_diagnosis; +}; + struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ __u32 linkid; /* Link identifier */ __u64 peer_gid; /* Peer GID */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index e5ebc83827ab..f80135e5feaa 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -56,6 +56,7 @@ enum IPSTATS_MIB_ECT1PKTS, /* InECT1Pkts */ IPSTATS_MIB_ECT0PKTS, /* InECT0Pkts */ IPSTATS_MIB_CEPKTS, /* InCEPkts */ + IPSTATS_MIB_REASM_OVERLAPS, /* ReasmOverlaps */ __IPSTATS_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index e3f6ed8a7064..e02d31986ff9 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -235,6 +235,11 @@ struct tcp_info { __u32 tcpi_delivered; __u32 tcpi_delivered_ce; + + __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */ + __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */ + __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */ + __u32 tcpi_reord_seen; /* reordering events seen */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -257,7 +262,10 @@ enum { TCP_NLA_SND_SSTHRESH, /* Slow start size threshold */ TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */ TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */ - + TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */ + TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */ + TCP_NLA_DSACK_DUPS, /* DSACK blocks received */ + TCP_NLA_REORD_SEEN, /* reordering events seen */ }; /* for TCP_MD5SIG socket option */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index e3af2859188b..5f3b9fec7b5f 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -305,9 +305,12 @@ enum xfrm_attr_type_t { XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ - XFRMA_OUTPUT_MARK, /* __u32 */ + XFRMA_SET_MARK, /* __u32 */ + XFRMA_SET_MARK_MASK, /* __u32 */ + XFRMA_IF_ID, /* __u32 */ __XFRMA_MAX +#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ #define XFRMA_MAX (__XFRMA_MAX - 1) }; diff --git a/ipc/sem.c b/ipc/sem.c index 29c0347ef11d..00ef2f743a62 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2119,7 +2119,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, } do { - queue.status = -EINTR; + WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; __set_current_state(TASK_INTERRUPTIBLE); diff --git a/ipc/shm.c b/ipc/shm.c index d4daf78df6da..fa1d322daa27 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -428,6 +428,17 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr) return 0; } +static unsigned long shm_pagesize(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + if (sfd->vm_ops->pagesize) + return sfd->vm_ops->pagesize(vma); + + return PAGE_SIZE; +} + #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { @@ -555,6 +566,7 @@ static const struct vm_operations_struct shm_vm_ops = { .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .split = shm_split, + .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ceb1c4596c51..80d672a11088 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic) break; case AUDIT_KERN_MODULE: audit_log_format(ab, "name="); - audit_log_untrustedstring(ab, context->module.name); - kfree(context->module.name); + if (context->module.name) { + audit_log_untrustedstring(ab, context->module.name); + kfree(context->module.name); + } else + audit_log_format(ab, "(null)"); + break; } audit_log_end(ab); @@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name) { struct audit_context *context = audit_context(); - context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL); - strcpy(context->module.name, name); + context->module.name = kstrdup(name, GFP_KERNEL); + if (!context->module.name) + audit_log_lost("out of memory in __audit_log_kern_module"); context->type = AUDIT_KERN_MODULE; } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 544e58f5f642..2aa55d030c77 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, return -EINVAL; value_type = btf_type_id_size(btf, &btf_value_id, &value_size); - if (!value_type || value_size > map->value_size) + if (!value_type || value_size != map->value_size) return -EINVAL; return 0; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e016ac3afa24..2590700237c1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) */ static bool btf_type_int_is_regular(const struct btf_type *t) { - u16 nr_bits, nr_bytes; + u8 nr_bits, nr_bytes; u32 int_data; int_data = btf_type_int(t); @@ -993,12 +993,16 @@ static void btf_int_bits_seq_show(const struct btf *btf, { u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); - u16 nr_bits = BTF_INT_BITS(int_data); - u16 total_bits_offset; - u16 nr_copy_bytes; - u16 nr_copy_bits; + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + u8 nr_copy_bytes; + u8 nr_copy_bits; u64 print_num; + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); @@ -1028,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; - u32 nr_bits = BTF_INT_BITS(int_data); + u8 nr_bits = BTF_INT_BITS(int_data); if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { @@ -1515,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, { bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; const struct btf_member *member; + u32 meta_needed, last_offset; struct btf *btf = env->btf; u32 struct_size = t->size; - u32 meta_needed; u16 i; meta_needed = btf_type_vlen(t) * sizeof(*member); @@ -1530,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, btf_verifier_log_type(env, t, NULL); + last_offset = 0; for_each_member(i, t, member) { if (!btf_name_offset_valid(btf, member->name_off)) { btf_verifier_log_member(env, t, member, @@ -1551,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* + * ">" instead of ">=" because the last member could be + * "char a[0];" + */ + if (last_offset > member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { btf_verifier_log_member(env, t, member, "Memmber bits_offset exceeds its struct size"); @@ -1558,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, } btf_verifier_log_member(env, t, member, NULL); + last_offset = member->offset; } return meta_needed; diff --git a/kernel/events/core.c b/kernel/events/core.c index 8f0434a9951a..eec2d5fb676b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt) static struct perf_callchain_entry __empty_callchain = { .nr = 0, }; -static struct perf_callchain_entry * +struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; @@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; - data->callchain = perf_callchain(event, regs); + if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY)) + data->callchain = perf_callchain(event, regs); + size += data->callchain->nr; header->size += size * sizeof(u64); @@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter, struct file *file, unsigned long offset, unsigned long size) { + /* d_inode(NULL) won't be equal to any mapped user-space file */ + if (!filter->path.dentry) + return false; + if (d_inode(filter->path.dentry) != file_inode(file)) return false; diff --git a/kernel/fork.c b/kernel/fork.c index 9440d61b925c..1b27babc4c78 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -303,11 +303,36 @@ struct kmem_cache *files_cachep; struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ -struct kmem_cache *vm_area_cachep; +static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) +{ + struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + + if (vma) + vma_init(vma, mm); + return vma; +} + +struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) +{ + struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + + if (new) { + *new = *orig; + INIT_LIST_HEAD(&new->anon_vma_chain); + } + return new; +} + +void vm_area_free(struct vm_area_struct *vma) +{ + kmem_cache_free(vm_area_cachep, vma); +} + static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); @@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto fail_nomem; charge = len; } - tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; - *tmp = *mpnt; - INIT_LIST_HEAD(&tmp->anon_vma_chain); retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; @@ -539,7 +562,7 @@ fail_uprobe_end: fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: - kmem_cache_free(vm_area_cachep, tmp); + vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index daeabd791d58..9a8b7ba9aa88 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1068,6 +1068,13 @@ static int irq_setup_forced_threading(struct irqaction *new) if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; + /* + * No further action required for interrupts which are requested as + * threaded interrupts already + */ + if (new->handler == irq_default_primary_handler) + return 0; + new->flags |= IRQF_ONESHOT; /* @@ -1075,7 +1082,7 @@ static int irq_setup_forced_threading(struct irqaction *new) * thread handler. We force thread them as well by creating a * secondary action. */ - if (new->handler != irq_default_primary_handler && new->thread_fn) { + if (new->handler && new->thread_fn) { /* Allocate the secondary action */ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!new->secondary) diff --git a/kernel/kthread.c b/kernel/kthread.c index 750cb8082694..486dedbd9af5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; + char name[TASK_COMM_LEN]; - vsnprintf(task->comm, sizeof(task->comm), namefmt, args); + /* + * task is already visible to other tasks, so updating + * COMM must be protected. + */ + vsnprintf(name, sizeof(name), namefmt, args); + set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f014be7a4b8..2823d4163a37 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock, rt_mutex_postunlock(&wake_q); } +static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +{ + might_sleep(); + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/** + * rt_mutex_lock_nested - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * @subclass: the lockdep subclass + */ +void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) +{ + __rt_mutex_lock(lock, subclass); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); +#endif + +#ifndef CONFIG_DEBUG_LOCK_ALLOC /** * rt_mutex_lock - lock a rt_mutex * @@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock, */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + __rt_mutex_lock(lock, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock); +#endif /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible diff --git a/kernel/memremap.c b/kernel/memremap.c index 5857267a4af5..38283363da06 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - align_start; + align_end = align_start + align_size - 1; + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + is_ram = region_intersects(align_start, align_size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); @@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) mutex_lock(&pgmap_lock); error = 0; - align_end = align_start + align_size - 1; foreach_order_pgoff(res, order, pgoff) { error = __radix_tree_insert(&pgmap_radix, @@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL_GPL(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); static atomic_t devmap_enable; /* @@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page) } else if (!count) __put_page(page); } -EXPORT_SYMBOL_GPL(__put_devmap_managed_page); +EXPORT_SYMBOL(__put_devmap_managed_page); #endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fbfc3f1d368a..b5fbdde6afa9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2090,8 +2090,14 @@ retry: sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); add_rq_bw(&next_task->dl, &later_rq->dl); + + /* + * Update the later_rq clock here, because the clock is used + * by the cpufreq_update_util() inside __add_running_bw(). + */ + update_rq_clock(later_rq); add_running_bw(&next_task->dl, &later_rq->dl); - activate_task(later_rq, next_task, 0); + activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; resched_curr(later_rq); @@ -2290,8 +2296,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + /* + * Inactive timer is armed. However, p is leaving DEADLINE and + * might migrate away from this rq while continuing to run on + * some other class. We need to remove its contribution from + * this rq running_bw now, or sub_rq_bw (below) will complain. + */ + if (p->dl.dl_non_contending) + sub_running_bw(&p->dl, &rq->dl); sub_rq_bw(&p->dl, &rq->dl); + } /* * We cannot use inactive_task_timer() to invoke sub_running_bw() diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 572567078b60..eaaec8364f96 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -836,6 +836,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) * can be time-consuming. Try to avoid it when possible. */ raw_spin_lock(&rt_rq->rt_runtime_lock); + if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF) + rt_rq->rt_runtime = rt_b->rt_runtime; skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; raw_spin_unlock(&rt_rq->rt_runtime_lock); if (skip) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 05a831427bc7..56a0fed30c0a 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu); } - if (!cpumask_test_cpu(cpu, sched_group_span(group))) { + if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 75ffc1d1a2e0..6f584861d329 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -390,7 +390,7 @@ static inline void tick_irq_exit(void) /* Make sure that timer wheel updates are propagated */ if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { - if (!in_interrupt()) + if (!in_irq()) tick_nohz_irq_exit(); } #endif diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index f89014a2c238..e190d1ef3a23 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -260,6 +260,15 @@ retry: err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); + /* + * The waking up of stopper threads has to happen + * in the same scheduling context as the queueing. + * Otherwise, there is a possibility of one of the + * above stoppers being woken up by another CPU, + * and preempting us. This will cause us to n ot + * wake up the other stopper forever. + */ + preempt_disable(); unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); @@ -270,7 +279,10 @@ unlock: goto retry; } - wake_up_q(&wakeq); + if (!err) { + wake_up_q(&wakeq); + preempt_enable(); + } return err; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index da9455a6b42b..5b33e2f5c0ed 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static inline bool local_timer_softirq_pending(void) { - return local_softirq_pending() & TIMER_SOFTIRQ; + return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6a46af21765c..0b0b688ea166 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer) } /** + * ring_buffer_record_is_set_on - return true if the ring buffer is set writable + * @buffer: The ring buffer to see if write is set enabled + * + * Returns true if the ring buffer is set writable by ring_buffer_record_on(). + * Note that this does NOT mean it is in a writable state. + * + * It may return true when the ring buffer has been disabled by + * ring_buffer_record_disable(), as that is a temporary disabling of + * the ring buffer. + */ +int ring_buffer_record_is_set_on(struct ring_buffer *buffer) +{ + return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87cf25171fb8..823687997b01 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); + /* Inherit the recordable setting from trace_buffer */ + if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + ring_buffer_record_on(tr->max_buffer.buffer); + else + ring_buffer_record_off(tr->max_buffer.buffer); + swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d18249683682..5dea177cef53 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops, goto out_free; out_reg: + /* Up the trigger_data count to make sure reg doesn't free it on failure */ + event_trigger_init(trigger_ops, trigger_data); ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); /* * The above returns on success the # of functions enabled, @@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops, * Consider no functions a failure too. */ if (!ret) { + cmd_ops->unreg(glob, trigger_ops, trigger_data, file); ret = -ENOENT; - goto out_free; - } else if (ret < 0) - goto out_free; - ret = 0; + } else if (ret > 0) + ret = 0; + + /* Down the counter of trigger_data or free it if not used anymore */ + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out; } + /* Up the trigger_data count to make sure nothing frees it on failure */ + event_trigger_init(trigger_ops, trigger_data); + if (trigger) { number = strsep(&trigger, ":"); @@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out_disable; /* Just return zero, not the number of enabled functions */ ret = 0; + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); - kfree(trigger_data); + event_trigger_free(trigger_ops, trigger_data); kfree(enable_data); goto out; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 21f718472942..6b71860f3998 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, static int enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { + struct event_file_link *link = NULL; int ret = 0; if (file) { - struct event_file_link *link; - link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; @@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) else ret = enable_kprobe(&tk->rp.kp); } + + if (ret) { + if (file) { + /* Notice the if is true on not WARN() */ + if (!WARN_ON_ONCE(!link)) + list_del_rcu(&link->list); + kfree(link); + tk->tp.flags &= ~TP_FLAG_TRACE; + } else { + tk->tp.flags &= ~TP_FLAG_PROFILE; + } + } out: return ret; } diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index c253c1b46c6b..befb127507c0 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -5,7 +5,7 @@ if HAVE_ARCH_KASAN config KASAN bool "KASan: runtime memory debugger" - depends on SLUB || (SLAB && !DEBUG_SLAB) + depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) select SLUB_DEBUG if SLUB select CONSTRUCTORS select STACKDEPOT diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 7e43cd54c84c..8be175df3075 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset, return ret; } +static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, + struct iov_iter *i) +{ + struct pipe_inode_info *pipe = i->pipe; + size_t n, off, xfer = 0; + int idx; + + if (!sanity(i)) + return 0; + + bytes = n = push_pipe(i, bytes, &idx, &off); + if (unlikely(!n)) + return 0; + for ( ; n; idx = next_idx(idx, pipe), off = 0) { + size_t chunk = min_t(size_t, n, PAGE_SIZE - off); + unsigned long rem; + + rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr, + chunk); + i->idx = idx; + i->iov_offset = off + chunk - rem; + xfer += chunk - rem; + if (rem) + break; + n -= chunk; + addr += chunk; + } + i->count -= xfer; + return xfer; +} + +/** + * _copy_to_iter_mcsafe - copy to user with source-read error exception handling + * @addr: source kernel address + * @bytes: total transfer length + * @iter: destination iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_to_iter() for protecting read/write to persistent memory. + * Unless / until an architecture can guarantee identical performance + * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a + * performance regression to switch more users to the mcsafe version. + * + * Otherwise, the main differences between this and typical _copy_to_iter(). + * + * * Typical tail/residue handling after a fault retries the copy + * byte-by-byte until the fault happens again. Re-triggering machine + * checks is potentially fatal so the implementation uses source + * alignment and poison alignment assumptions to avoid re-triggering + * hardware exceptions. + * + * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. + * Compare to copy_to_iter() where only ITER_IOVEC attempts might return + * a short copy. + * + * See MCSAFE_TEST for self-test. + */ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) { - WARN_ON(1); - return 0; - } + if (unlikely(i->type & ITER_PIPE)) + return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, @@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/** + * _copy_from_iter_flushcache - write destination through cpu cache + * @addr: destination kernel address + * @bytes: total transfer length + * @iter: source iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_from_iter() for ensuring that writes to persistent memory + * are flushed through the CPU cache. It is differentiated from + * _copy_from_iter_nocache() in that guarantees all data is flushed for + * all iterator types. The _copy_from_iter_nocache() only attempts to + * bypass the cache for the ITER_IOVEC case, and on some archs may use + * instructions that strand dirty-data in the cache. + */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1cd7c1a57a14..25346bd99364 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (vma_is_dax(vma)) return; page = pmd_page(_pmd); + if (!PageDirty(page) && pmd_dirty(_pmd)) + set_page_dirty(page); if (!PageReferenced(page) && pmd_young(_pmd)) SetPageReferenced(page); page_remove_rmap(page, true); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 039ddbc574e9..3103099f64fd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3167,6 +3167,13 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) return 0; } +/* + * When a new function is introduced to vm_operations_struct and added + * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. + * This is because under System V memory model, mappings created via + * shmget/shmat with "huge page" specified are backed by hugetlbfs files, + * their original vm_ops are overwritten with shm_vm_ops. + */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, diff --git a/mm/memblock.c b/mm/memblock.c index 11e46f83e1ad..4b5d245fafc1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,6 +20,7 @@ #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> +#include <linux/bootmem.h> #include <asm/sections.h> #include <linux/io.h> @@ -1225,6 +1226,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } +#if defined(CONFIG_NO_BOOTMEM) /** * memblock_virt_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes @@ -1432,6 +1434,7 @@ void * __init memblock_virt_alloc_try_nid( (u64)max_addr); return NULL; } +#endif /** * __memblock_free_early - free boot memory block diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e6f0d5ef320a..b2173f7e5164 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) int nid; int i; - while ((memcg = parent_mem_cgroup(memcg))) { + for (; memcg; memcg = parent_mem_cgroup(memcg)) { for_each_node(nid) { mz = mem_cgroup_nodeinfo(memcg, nid); for (i = 0; i <= DEF_PRIORITY; i++) { @@ -4037,6 +4037,14 @@ static struct cftype mem_cgroup_legacy_files[] = { static DEFINE_IDR(mem_cgroup_idr); +static void mem_cgroup_id_remove(struct mem_cgroup *memcg) +{ + if (memcg->id.id > 0) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + } +} + static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0); @@ -4047,8 +4055,7 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { VM_BUG_ON(atomic_read(&memcg->id.ref) < n); if (atomic_sub_and_test(n, &memcg->id.ref)) { - idr_remove(&mem_cgroup_idr, memcg->id.id); - memcg->id.id = 0; + mem_cgroup_id_remove(memcg); /* Memcg ID pins CSS */ css_put(&memcg->css); @@ -4185,8 +4192,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: - if (memcg->id.id > 0) - idr_remove(&mem_cgroup_idr, memcg->id.id); + mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); return NULL; } @@ -4245,6 +4251,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) return &memcg->css; fail: + mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); return ERR_PTR(-ENOMEM); } diff --git a/mm/memory.c b/mm/memory.c index 7206a634270b..dab1511294ad 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1417,11 +1417,9 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { - if (next - addr != HPAGE_PMD_SIZE) { - VM_BUG_ON_VMA(vma_is_anonymous(vma) && - !rwsem_is_locked(&tlb->mm->mmap_sem), vma); + if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); - } else if (zap_huge_pmd(tlb, vma, pmd, addr)) + else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9ac49ef17b4e..01f1a14facc4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) /* Create pseudo-vma that contains just the policy */ memset(&pvma, 0, sizeof(struct vm_area_struct)); + vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ diff --git a/mm/mmap.c b/mm/mmap.c index 5801b5f0a634..17bbf4d3e24f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -182,7 +182,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return next; } @@ -911,7 +911,7 @@ again: anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); - kmem_cache_free(vm_area_cachep, next); + vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter @@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { if (vm_flags & VM_DENYWRITE) { @@ -1780,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, error = shmem_zero_setup(vma); if (error) goto free_vma; + } else { + vma_set_anonymous(vma); } vma_link(mm, vma, prev, rb_link, rb_parent); @@ -1832,7 +1832,7 @@ allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); @@ -2620,15 +2620,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return err; } - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) return -ENOMEM; - /* most fields are the same, copy all, and then fixup */ - *new = *vma; - - INIT_LIST_HEAD(&new->anon_vma_chain); - if (new_below) new->vm_end = addr; else { @@ -2669,7 +2664,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: - kmem_cache_free(vm_area_cachep, new); + vm_area_free(new); return err; } @@ -2984,14 +2979,13 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* * create a vma struct for an anonymous mapping */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; + vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; @@ -3202,16 +3196,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { - new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new_vma = vm_area_dup(vma); if (!new_vma) goto out; - *new_vma = *vma; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; - INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) @@ -3226,7 +3218,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: - kmem_cache_free(vm_area_cachep, new_vma); + vm_area_free(new_vma); out: return NULL; } @@ -3350,12 +3342,10 @@ static struct vm_area_struct *__install_special_mapping( int ret; struct vm_area_struct *vma; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -3376,7 +3366,7 @@ static struct vm_area_struct *__install_special_mapping( return vma; out: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ERR_PTR(ret); } diff --git a/mm/nommu.c b/mm/nommu.c index 4452d8bd9ae4..9fc9e43335b6 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); } /* @@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma, if (ret < len) memset(base + ret, 0, len - ret); + } else { + vma_set_anonymous(vma); } return 0; @@ -1204,7 +1206,7 @@ unsigned long do_mmap(struct file *file, if (!region) goto error_getting_region; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (!vma) goto error_getting_vma; @@ -1212,7 +1214,6 @@ unsigned long do_mmap(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_flags = vm_flags; vma->vm_pgoff = pgoff; @@ -1368,7 +1369,7 @@ error: kmem_cache_free(vm_region_jar, region); if (vma->vm_file) fput(vma->vm_file); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ret; sharing_violation: @@ -1469,14 +1470,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (!region) return -ENOMEM; - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) { kmem_cache_free(vm_region_jar, region); return -ENOMEM; } /* most fields are the same, copy all, and then fixup */ - *new = *vma; *region = *vma->vm_region; new->vm_region = region; diff --git a/mm/shmem.c b/mm/shmem.c index 2cab84403055..41b9bbf24e16 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma, { /* Create a pseudo vma that just contains the policy */ memset(vma, 0, sizeof(*vma)); + vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); diff --git a/mm/zswap.c b/mm/zswap.c index 7d34e69507e3..cd91fd9d96b8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, ret = -ENOMEM; goto reject; } + + /* A second zswap_is_full() check after + * zswap_shrink() to make sure it's now + * under the max_pool_percent + */ + if (zswap_is_full()) { + ret = -ENOMEM; + goto reject; + } } /* allocate entry */ diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 6b1042e21656..52fad5dad9f7 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -770,6 +770,7 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev, hdr.hop_limit, &hdr.daddr); skb_push(skb, sizeof(hdr)); + skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_copy_to_linear_data(skb, &hdr, sizeof(hdr)); diff --git a/net/atm/common.c b/net/atm/common.c index a7a68e509628..9f8cb0d2e71e 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -653,7 +653,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) struct atm_vcc *vcc; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; vcc = ATM_SD(sock); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 3264e1873219..deacc52d7ff1 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -159,7 +159,7 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk) BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; release_sock(sk); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 45ff5dc124cc..bd4978ce8c45 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -748,11 +748,30 @@ static bool conn_use_rpa(struct hci_conn *conn) return hci_dev_test_flag(hdev, HCI_PRIVACY); } +static void set_ext_conn_params(struct hci_conn *conn, + struct hci_cp_le_ext_conn_param *p) +{ + struct hci_dev *hdev = conn->hdev; + + memset(p, 0, sizeof(*p)); + + /* Set window to be the same value as the interval to + * enable continuous scanning. + */ + p->scan_interval = cpu_to_le16(hdev->le_scan_interval); + p->scan_window = p->scan_interval; + p->conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); + p->conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); + p->conn_latency = cpu_to_le16(conn->le_conn_latency); + p->supervision_timeout = cpu_to_le16(conn->le_supv_timeout); + p->min_ce_len = cpu_to_le16(0x0000); + p->max_ce_len = cpu_to_le16(0x0000); +} + static void hci_req_add_le_create_conn(struct hci_request *req, struct hci_conn *conn, bdaddr_t *direct_rpa) { - struct hci_cp_le_create_conn cp; struct hci_dev *hdev = conn->hdev; u8 own_addr_type; @@ -775,25 +794,71 @@ static void hci_req_add_le_create_conn(struct hci_request *req, return; } - memset(&cp, 0, sizeof(cp)); + if (use_ext_conn(hdev)) { + struct hci_cp_le_ext_create_conn *cp; + struct hci_cp_le_ext_conn_param *p; + u8 data[sizeof(*cp) + sizeof(*p) * 3]; + u32 plen; - /* Set window to be the same value as the interval to enable - * continuous scanning. - */ - cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); - cp.scan_window = cp.scan_interval; + cp = (void *) data; + p = (void *) cp->data; + + memset(cp, 0, sizeof(*cp)); - bacpy(&cp.peer_addr, &conn->dst); - cp.peer_addr_type = conn->dst_type; - cp.own_address_type = own_addr_type; - cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); - cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); - cp.conn_latency = cpu_to_le16(conn->le_conn_latency); - cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout); - cp.min_ce_len = cpu_to_le16(0x0000); - cp.max_ce_len = cpu_to_le16(0x0000); + bacpy(&cp->peer_addr, &conn->dst); + cp->peer_addr_type = conn->dst_type; + cp->own_addr_type = own_addr_type; - hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); + plen = sizeof(*cp); + + if (scan_1m(hdev)) { + cp->phys |= LE_SCAN_PHY_1M; + set_ext_conn_params(conn, p); + + p++; + plen += sizeof(*p); + } + + if (scan_2m(hdev)) { + cp->phys |= LE_SCAN_PHY_2M; + set_ext_conn_params(conn, p); + + p++; + plen += sizeof(*p); + } + + if (scan_coded(hdev)) { + cp->phys |= LE_SCAN_PHY_CODED; + set_ext_conn_params(conn, p); + + plen += sizeof(*p); + } + + hci_req_add(req, HCI_OP_LE_EXT_CREATE_CONN, plen, data); + + } else { + struct hci_cp_le_create_conn cp; + + memset(&cp, 0, sizeof(cp)); + + /* Set window to be the same value as the interval to enable + * continuous scanning. + */ + cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); + cp.scan_window = cp.scan_interval; + + bacpy(&cp.peer_addr, &conn->dst); + cp.peer_addr_type = conn->dst_type; + cp.own_address_type = own_addr_type; + cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); + cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); + cp.conn_latency = cpu_to_le16(conn->le_conn_latency); + cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout); + cp.min_ce_len = cpu_to_le16(0x0000); + cp.max_ce_len = cpu_to_le16(0x0000); + + hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); + } conn->state = BT_CONNECT; clear_bit(HCI_CONN_SCANNING, &conn->flags); @@ -803,35 +868,81 @@ static void hci_req_directed_advertising(struct hci_request *req, struct hci_conn *conn) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_param cp; u8 own_addr_type; u8 enable; - /* Clear the HCI_LE_ADV bit temporarily so that the - * hci_update_random_address knows that it's safe to go ahead - * and write a new random address. The flag will be set back on - * as soon as the SET_ADV_ENABLE HCI command completes. - */ - hci_dev_clear_flag(hdev, HCI_LE_ADV); + if (ext_adv_capable(hdev)) { + struct hci_cp_le_set_ext_adv_params cp; + bdaddr_t random_addr; - /* Set require_privacy to false so that the remote device has a - * chance of identifying us. - */ - if (hci_update_random_address(req, false, conn_use_rpa(conn), - &own_addr_type) < 0) - return; + /* Set require_privacy to false so that the remote device has a + * chance of identifying us. + */ + if (hci_get_random_address(hdev, false, conn_use_rpa(conn), NULL, + &own_addr_type, &random_addr) < 0) + return; - memset(&cp, 0, sizeof(cp)); - cp.type = LE_ADV_DIRECT_IND; - cp.own_address_type = own_addr_type; - cp.direct_addr_type = conn->dst_type; - bacpy(&cp.direct_addr, &conn->dst); - cp.channel_map = hdev->le_adv_channel_map; + memset(&cp, 0, sizeof(cp)); - hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_DIRECT_IND); + cp.own_addr_type = own_addr_type; + cp.channel_map = hdev->le_adv_channel_map; + cp.tx_power = HCI_TX_POWER_INVALID; + cp.primary_phy = HCI_ADV_PHY_1M; + cp.secondary_phy = HCI_ADV_PHY_1M; + cp.handle = 0; /* Use instance 0 for directed adv */ + cp.own_addr_type = own_addr_type; + cp.peer_addr_type = conn->dst_type; + bacpy(&cp.peer_addr, &conn->dst); + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); + + if (own_addr_type == ADDR_LE_DEV_RANDOM && + bacmp(&random_addr, BDADDR_ANY) && + bacmp(&random_addr, &hdev->random_addr)) { + struct hci_cp_le_set_adv_set_rand_addr cp; + + memset(&cp, 0, sizeof(cp)); + + cp.handle = 0; + bacpy(&cp.bdaddr, &random_addr); + + hci_req_add(req, + HCI_OP_LE_SET_ADV_SET_RAND_ADDR, + sizeof(cp), &cp); + } - enable = 0x01; - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); + __hci_req_enable_ext_advertising(req); + } else { + struct hci_cp_le_set_adv_param cp; + + /* Clear the HCI_LE_ADV bit temporarily so that the + * hci_update_random_address knows that it's safe to go ahead + * and write a new random address. The flag will be set back on + * as soon as the SET_ADV_ENABLE HCI command completes. + */ + hci_dev_clear_flag(hdev, HCI_LE_ADV); + + /* Set require_privacy to false so that the remote device has a + * chance of identifying us. + */ + if (hci_update_random_address(req, false, conn_use_rpa(conn), + &own_addr_type) < 0) + return; + + memset(&cp, 0, sizeof(cp)); + cp.type = LE_ADV_DIRECT_IND; + cp.own_address_type = own_addr_type; + cp.direct_addr_type = conn->dst_type; + bacpy(&cp.direct_addr, &conn->dst); + cp.channel_map = hdev->le_adv_channel_map; + + hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); + + enable = 0x01; + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), + &enable); + } conn->state = BT_CONNECT; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ee8ef1228263..74b29c7d841c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -695,11 +695,42 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[35] & (0x20 | 0x40)) events[1] |= 0x08; /* LE PHY Update Complete */ + /* If the controller supports LE Set Extended Scan Parameters + * and LE Set Extended Scan Enable commands, enable the + * corresponding event. + */ + if (use_ext_scan(hdev)) + events[1] |= 0x10; /* LE Extended Advertising + * Report + */ + + /* If the controller supports the LE Extended Create Connection + * command, enable the corresponding event. + */ + if (use_ext_conn(hdev)) + events[1] |= 0x02; /* LE Enhanced Connection + * Complete + */ + + /* If the controller supports the LE Extended Advertising + * command, enable the corresponding event. + */ + if (ext_adv_capable(hdev)) + events[2] |= 0x02; /* LE Advertising Set + * Terminated + */ + hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), events); - if (hdev->commands[25] & 0x40) { - /* Read LE Advertising Channel TX Power */ + /* Read LE Advertising Channel TX Power */ + if ((hdev->commands[25] & 0x40) && !ext_adv_capable(hdev)) { + /* HCI TS spec forbids mixing of legacy and extended + * advertising commands wherein READ_ADV_TX_POWER is + * also included. So do not call it if extended adv + * is supported otherwise controller will return + * COMMAND_DISALLOWED for extended commands. + */ hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); } @@ -714,6 +745,17 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL); } + if (hdev->commands[34] & 0x40) { + /* Read LE Resolving List Size */ + hci_req_add(req, HCI_OP_LE_READ_RESOLV_LIST_SIZE, + 0, NULL); + } + + if (hdev->commands[34] & 0x20) { + /* Clear LE Resolving List */ + hci_req_add(req, HCI_OP_LE_CLEAR_RESOLV_LIST, 0, NULL); + } + if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) { /* Read LE Maximum Data Length */ hci_req_add(req, HCI_OP_LE_READ_MAX_DATA_LEN, 0, NULL); @@ -722,6 +764,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_READ_DEF_DATA_LEN, 0, NULL); } + if (ext_adv_capable(hdev)) { + /* Read LE Number of Supported Advertising Sets */ + hci_req_add(req, HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS, + 0, NULL); + } + hci_set_le_support(req); } @@ -802,10 +850,9 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) if (hdev->commands[35] & 0x20) { struct hci_cp_le_set_default_phy cp; - /* No transmitter PHY or receiver PHY preferences */ - cp.all_phys = 0x03; - cp.tx_phys = 0; - cp.rx_phys = 0; + cp.all_phys = 0x00; + cp.tx_phys = hdev->le_tx_def_phys; + cp.rx_phys = hdev->le_rx_def_phys; hci_req_add(req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp), &cp); } @@ -1368,7 +1415,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) atomic_set(&hdev->cmd_cnt, 1); set_bit(HCI_INIT, &hdev->flags); - if (hci_dev_test_flag(hdev, HCI_SETUP)) { + if (hci_dev_test_flag(hdev, HCI_SETUP) || + test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) { hci_sock_dev_event(hdev, HCI_DEV_SETUP); if (hdev->setup) @@ -1432,6 +1480,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) if (!ret) { hci_dev_hold(hdev); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, true); set_bit(HCI_UP, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_UP); hci_leds_update_powered(hdev, true); @@ -1587,9 +1636,15 @@ int hci_dev_do_close(struct hci_dev *hdev) if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE)) cancel_delayed_work(&hdev->service_cache); - if (hci_dev_test_flag(hdev, HCI_MGMT)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) { + struct adv_info *adv_instance; + cancel_delayed_work_sync(&hdev->rpa_expired); + list_for_each_entry(adv_instance, &hdev->adv_instances, list) + cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); + } + /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ @@ -1897,7 +1952,11 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) break; case HCISETPTYPE: + if (hdev->pkt_type == (__u16) dr.dev_opt) + break; + hdev->pkt_type = (__u16) dr.dev_opt; + mgmt_phy_configuration_changed(hdev, NULL); break; case HCISETACLMTU: @@ -2661,6 +2720,8 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) hdev->cur_adv_instance = 0x00; } + cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); + list_del(&adv_instance->list); kfree(adv_instance); @@ -2669,6 +2730,14 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) return 0; } +void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired) +{ + struct adv_info *adv_instance, *n; + + list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) + adv_instance->rpa_expired = rpa_expired; +} + /* This function requires the caller holds hdev->lock */ void hci_adv_instances_clear(struct hci_dev *hdev) { @@ -2680,6 +2749,7 @@ void hci_adv_instances_clear(struct hci_dev *hdev) } list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) { + cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); } @@ -2688,6 +2758,16 @@ void hci_adv_instances_clear(struct hci_dev *hdev) hdev->cur_adv_instance = 0x00; } +static void adv_instance_rpa_expired(struct work_struct *work) +{ + struct adv_info *adv_instance = container_of(work, struct adv_info, + rpa_expired_cb.work); + + BT_DBG(""); + + adv_instance->rpa_expired = true; +} + /* This function requires the caller holds hdev->lock */ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, @@ -2736,6 +2816,11 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, else adv_instance->duration = duration; + adv_instance->tx_power = HCI_TX_POWER_INVALID; + + INIT_DELAYED_WORK(&adv_instance->rpa_expired_cb, + adv_instance_rpa_expired); + BT_DBG("%s for %dMR", hdev->name, instance); return 0; @@ -2999,6 +3084,8 @@ struct hci_dev *hci_alloc_dev(void) hdev->le_max_tx_time = 0x0148; hdev->le_max_rx_len = 0x001b; hdev->le_max_rx_time = 0x0148; + hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; + hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; @@ -3017,6 +3104,7 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); INIT_LIST_HEAD(&hdev->le_white_list); + INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->pend_le_reports); @@ -3218,6 +3306,7 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 0d8ab5b3c177..51f5b1efc3a5 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -694,6 +694,21 @@ static int white_list_show(struct seq_file *f, void *ptr) DEFINE_SHOW_ATTRIBUTE(white_list); +static int resolv_list_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct bdaddr_list *b; + + hci_dev_lock(hdev); + list_for_each_entry(b, &hdev->le_resolv_list, list) + seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(resolv_list); + static int identity_resolving_keys_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -955,6 +970,10 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &hdev->le_white_list_size); debugfs_create_file("white_list", 0444, hdev->debugfs, hdev, &white_list_fops); + debugfs_create_u8("resolv_list_size", 0444, hdev->debugfs, + &hdev->le_resolv_list_size); + debugfs_create_file("resolv_list", 0444, hdev->debugfs, hdev, + &resolv_list_fops); debugfs_create_file("identity_resolving_keys", 0400, hdev->debugfs, hdev, &identity_resolving_keys_fops); debugfs_create_file("long_term_keys", 0400, hdev->debugfs, hdev, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 235b5aaab23d..754714c8d752 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -221,6 +221,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) hdev->ssp_debug_mode = 0; hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_resolv_list); } static void hci_cc_read_stored_link_key(struct hci_dev *hdev, @@ -1041,6 +1042,57 @@ static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_default_phy(struct hci_dev *hdev, struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + struct hci_cp_le_set_default_phy *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_DEFAULT_PHY); + if (!cp) + return; + + hci_dev_lock(hdev); + + hdev->le_tx_def_phys = cp->tx_phys; + hdev->le_rx_def_phys = cp->rx_phys; + + hci_dev_unlock(hdev); +} + +static void hci_cc_le_set_adv_set_random_addr(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + struct hci_cp_le_set_adv_set_rand_addr *cp; + struct adv_info *adv_instance; + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_SET_RAND_ADDR); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (!hdev->cur_adv_instance) { + /* Store in hdev for instance 0 (Set adv and Directed advs) */ + bacpy(&hdev->random_addr, &cp->bdaddr); + } else { + adv_instance = hci_find_adv_instance(hdev, + hdev->cur_adv_instance); + if (adv_instance) + bacpy(&adv_instance->random_addr, &cp->bdaddr); + } + + hci_dev_unlock(hdev); +} + static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) { __u8 *sent, status = *((__u8 *) skb->data); @@ -1076,6 +1128,43 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_ext_adv_enable *cp; + struct hci_cp_ext_adv_set *adv_set; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_ENABLE); + if (!cp) + return; + + adv_set = (void *) cp->data; + + hci_dev_lock(hdev); + + if (cp->enable) { + struct hci_conn *conn; + + hci_dev_set_flag(hdev, HCI_LE_ADV); + + conn = hci_lookup_le_connect(hdev); + if (conn) + queue_delayed_work(hdev->workqueue, + &conn->le_conn_timeout, + conn->conn_timeout); + } else { + hci_dev_clear_flag(hdev, HCI_LE_ADV); + } + + hci_dev_unlock(hdev); +} + static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_cp_le_set_scan_param *cp; @@ -1097,6 +1186,31 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_ext_scan_param(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_ext_scan_params *cp; + __u8 status = *((__u8 *) skb->data); + struct hci_cp_le_scan_phy_params *phy_param; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS); + if (!cp) + return; + + phy_param = (void *)cp->data; + + hci_dev_lock(hdev); + + hdev->le_scan_type = phy_param->type; + + hci_dev_unlock(hdev); +} + static bool has_pending_adv_report(struct hci_dev *hdev) { struct discovery_state *d = &hdev->discovery; @@ -1126,24 +1240,11 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, d->last_adv_data_len = len; } -static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, - struct sk_buff *skb) +static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable) { - struct hci_cp_le_set_scan_enable *cp; - __u8 status = *((__u8 *) skb->data); - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); - if (!cp) - return; - hci_dev_lock(hdev); - switch (cp->enable) { + switch (enable) { case LE_SCAN_ENABLE: hci_dev_set_flag(hdev, HCI_LE_SCAN); if (hdev->le_scan_type == LE_SCAN_ACTIVE) @@ -1189,13 +1290,63 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, default: bt_dev_err(hdev, "use of reserved LE_Scan_Enable param %d", - cp->enable); + enable); break; } hci_dev_unlock(hdev); } +static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_scan_enable *cp; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); + if (!cp) + return; + + le_set_scan_enable_complete(hdev, cp->enable); +} + +static void hci_cc_le_set_ext_scan_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_ext_scan_enable *cp; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_ENABLE); + if (!cp) + return; + + le_set_scan_enable_complete(hdev, cp->enable); +} + +static void hci_cc_le_read_num_adv_sets(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_le_read_num_supported_adv_sets *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x No of Adv sets %u", hdev->name, rp->status, + rp->num_of_sets); + + if (rp->status) + return; + + hdev->le_num_of_adv_sets = rp->num_of_sets; +} + static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, struct sk_buff *skb) { @@ -1306,6 +1457,32 @@ static void hci_cc_le_write_def_data_len(struct hci_dev *hdev, hdev->le_def_tx_time = le16_to_cpu(sent->tx_time); } +static void hci_cc_le_clear_resolv_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + hci_bdaddr_list_clear(&hdev->le_resolv_list); +} + +static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_le_read_resolv_list_size *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x size %u", hdev->name, rp->status, rp->size); + + if (rp->status) + return; + + hdev->le_resolv_list_size = rp->size; +} + static void hci_cc_le_read_max_data_len(struct hci_dev *hdev, struct sk_buff *skb) { @@ -1375,6 +1552,37 @@ static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_set_ext_adv_param(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_rp_le_set_ext_adv_params *rp = (void *) skb->data; + struct hci_cp_le_set_ext_adv_params *cp; + struct adv_info *adv_instance; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS); + if (!cp) + return; + + hci_dev_lock(hdev); + hdev->adv_addr_type = cp->own_addr_type; + if (!hdev->cur_adv_instance) { + /* Store in hdev for instance 0 */ + hdev->adv_tx_power = rp->tx_power; + } else { + adv_instance = hci_find_adv_instance(hdev, + hdev->cur_adv_instance); + if (adv_instance) + adv_instance->tx_power = rp->tx_power; + } + /* Update adv data as tx power is known now */ + hci_req_update_adv_data(hdev, hdev->cur_adv_instance); + hci_dev_unlock(hdev); +} + static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_rssi *rp = (void *) skb->data; @@ -1896,10 +2104,44 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_dev_unlock(hdev); } +static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, + u8 peer_addr_type, u8 own_address_type, + u8 filter_policy) +{ + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_le(hdev, peer_addr, + peer_addr_type); + if (!conn) + return; + + /* Store the initiator and responder address information which + * is needed for SMP. These values will not change during the + * lifetime of the connection. + */ + conn->init_addr_type = own_address_type; + if (own_address_type == ADDR_LE_DEV_RANDOM) + bacpy(&conn->init_addr, &hdev->random_addr); + else + bacpy(&conn->init_addr, &hdev->bdaddr); + + conn->resp_addr_type = peer_addr_type; + bacpy(&conn->resp_addr, peer_addr); + + /* We don't want the connection attempt to stick around + * indefinitely since LE doesn't have a page timeout concept + * like BR/EDR. Set a timer for any connection that doesn't use + * the white list for connecting. + */ + if (filter_policy == HCI_LE_USE_PEER_ADDR) + queue_delayed_work(conn->hdev->workqueue, + &conn->le_conn_timeout, + conn->conn_timeout); +} + static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_conn *cp; - struct hci_conn *conn; BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1916,35 +2158,34 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) hci_dev_lock(hdev); - conn = hci_conn_hash_lookup_le(hdev, &cp->peer_addr, - cp->peer_addr_type); - if (!conn) - goto unlock; + cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type, + cp->own_address_type, cp->filter_policy); - /* Store the initiator and responder address information which - * is needed for SMP. These values will not change during the - * lifetime of the connection. - */ - conn->init_addr_type = cp->own_address_type; - if (cp->own_address_type == ADDR_LE_DEV_RANDOM) - bacpy(&conn->init_addr, &hdev->random_addr); - else - bacpy(&conn->init_addr, &hdev->bdaddr); + hci_dev_unlock(hdev); +} - conn->resp_addr_type = cp->peer_addr_type; - bacpy(&conn->resp_addr, &cp->peer_addr); +static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_le_ext_create_conn *cp; - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the white list for connecting. + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + /* All connection failure handling is taken care of by the + * hci_le_conn_failed function which is triggered by the HCI + * request completion callbacks used for connecting. */ - if (cp->filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_EXT_CREATE_CONN); + if (!cp) + return; + + hci_dev_lock(hdev); + + cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type, + cp->own_addr_type, cp->filter_policy); -unlock: hci_dev_unlock(hdev); } @@ -2618,8 +2859,10 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) /* We should disregard the current RPA and generate a new one * whenever the encryption procedure fails. */ - if (ev->status && conn->type == LE_LINK) + if (ev->status && conn->type == LE_LINK) { hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, true); + } clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); @@ -3015,6 +3258,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_write_def_data_len(hdev, skb); break; + case HCI_OP_LE_CLEAR_RESOLV_LIST: + hci_cc_le_clear_resolv_list(hdev, skb); + break; + + case HCI_OP_LE_READ_RESOLV_LIST_SIZE: + hci_cc_le_read_resolv_list_size(hdev, skb); + break; + case HCI_OP_LE_READ_MAX_DATA_LEN: hci_cc_le_read_max_data_len(hdev, skb); break; @@ -3039,6 +3290,34 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_write_ssp_debug_mode(hdev, skb); break; + case HCI_OP_LE_SET_EXT_SCAN_PARAMS: + hci_cc_le_set_ext_scan_param(hdev, skb); + break; + + case HCI_OP_LE_SET_EXT_SCAN_ENABLE: + hci_cc_le_set_ext_scan_enable(hdev, skb); + break; + + case HCI_OP_LE_SET_DEFAULT_PHY: + hci_cc_le_set_default_phy(hdev, skb); + break; + + case HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS: + hci_cc_le_read_num_adv_sets(hdev, skb); + break; + + case HCI_OP_LE_SET_EXT_ADV_PARAMS: + hci_cc_set_ext_adv_param(hdev, skb); + break; + + case HCI_OP_LE_SET_EXT_ADV_ENABLE: + hci_cc_le_set_ext_adv_enable(hdev, skb); + break; + + case HCI_OP_LE_SET_ADV_SET_RAND_ADDR: + hci_cc_le_set_adv_set_random_addr(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; @@ -3134,6 +3413,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cs_le_start_enc(hdev, ev->status); break; + case HCI_OP_LE_EXT_CREATE_CONN: + hci_cs_le_ext_create_conn(hdev, ev->status); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; @@ -4460,16 +4743,15 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, } #endif -static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, + bdaddr_t *bdaddr, u8 bdaddr_type, u8 role, u16 handle, + u16 interval, u16 latency, u16 supervision_timeout) { - struct hci_ev_le_conn_complete *ev = (void *) skb->data; struct hci_conn_params *params; struct hci_conn *conn; struct smp_irk *irk; u8 addr_type; - BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); - hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -4479,13 +4761,13 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_lookup_le_connect(hdev); if (!conn) { - conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role); + conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); goto unlock; } - conn->dst_type = ev->bdaddr_type; + conn->dst_type = bdaddr_type; /* If we didn't have a hci_conn object previously * but we're in master role this must be something @@ -4496,8 +4778,8 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) * initiator address based on the HCI_PRIVACY flag. */ if (conn->out) { - conn->resp_addr_type = ev->bdaddr_type; - bacpy(&conn->resp_addr, &ev->bdaddr); + conn->resp_addr_type = bdaddr_type; + bacpy(&conn->resp_addr, bdaddr); if (hci_dev_test_flag(hdev, HCI_PRIVACY)) { conn->init_addr_type = ADDR_LE_DEV_RANDOM; bacpy(&conn->init_addr, &hdev->rpa); @@ -4516,13 +4798,18 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) * the advertising address type. */ conn->resp_addr_type = hdev->adv_addr_type; - if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) - bacpy(&conn->resp_addr, &hdev->random_addr); - else + if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { + /* In case of ext adv, resp_addr will be updated in + * Adv Terminated event. + */ + if (!ext_adv_capable(hdev)) + bacpy(&conn->resp_addr, &hdev->random_addr); + } else { bacpy(&conn->resp_addr, &hdev->bdaddr); + } - conn->init_addr_type = ev->bdaddr_type; - bacpy(&conn->init_addr, &ev->bdaddr); + conn->init_addr_type = bdaddr_type; + bacpy(&conn->init_addr, bdaddr); /* For incoming connections, set the default minimum * and maximum connection interval. They will be used @@ -4548,8 +4835,8 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->dst_type = irk->addr_type; } - if (ev->status) { - hci_le_conn_failed(conn, ev->status); + if (status) { + hci_le_conn_failed(conn, status); goto unlock; } @@ -4568,17 +4855,17 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) mgmt_device_connected(hdev, conn, 0, NULL, 0); conn->sec_level = BT_SECURITY_LOW; - conn->handle = __le16_to_cpu(ev->handle); + conn->handle = handle; conn->state = BT_CONFIG; - conn->le_conn_interval = le16_to_cpu(ev->interval); - conn->le_conn_latency = le16_to_cpu(ev->latency); - conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout); + conn->le_conn_interval = interval; + conn->le_conn_latency = latency; + conn->le_supv_timeout = supervision_timeout; hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); - if (!ev->status) { + if (!status) { /* The remote features procedure is defined for master * role only. So only in case of an initiated connection * request the remote features. @@ -4600,10 +4887,10 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_hold(conn); } else { conn->state = BT_CONNECTED; - hci_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, status); } } else { - hci_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, status); } params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, @@ -4622,6 +4909,61 @@ unlock: hci_dev_unlock(hdev); } +static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_ev_le_conn_complete *ev = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, + ev->role, le16_to_cpu(ev->handle), + le16_to_cpu(ev->interval), + le16_to_cpu(ev->latency), + le16_to_cpu(ev->supervision_timeout)); +} + +static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_enh_conn_complete *ev = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, + ev->role, le16_to_cpu(ev->handle), + le16_to_cpu(ev->interval), + le16_to_cpu(ev->latency), + le16_to_cpu(ev->supervision_timeout)); +} + +static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_evt_le_ext_adv_set_term *ev = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + if (ev->status) + return; + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); + if (conn) { + struct adv_info *adv_instance; + + if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM) + return; + + if (!hdev->cur_adv_instance) { + bacpy(&conn->resp_addr, &hdev->random_addr); + return; + } + + adv_instance = hci_find_adv_instance(hdev, hdev->cur_adv_instance); + if (adv_instance) + bacpy(&conn->resp_addr, &adv_instance->random_addr); + } +} + static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -4957,6 +5299,78 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static u8 ext_evt_type_to_legacy(u16 evt_type) +{ + if (evt_type & LE_EXT_ADV_LEGACY_PDU) { + switch (evt_type) { + case LE_LEGACY_ADV_IND: + return LE_ADV_IND; + case LE_LEGACY_ADV_DIRECT_IND: + return LE_ADV_DIRECT_IND; + case LE_LEGACY_ADV_SCAN_IND: + return LE_ADV_SCAN_IND; + case LE_LEGACY_NONCONN_IND: + return LE_ADV_NONCONN_IND; + case LE_LEGACY_SCAN_RSP_ADV: + case LE_LEGACY_SCAN_RSP_ADV_SCAN: + return LE_ADV_SCAN_RSP; + } + + BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", + evt_type); + + return LE_ADV_INVALID; + } + + if (evt_type & LE_EXT_ADV_CONN_IND) { + if (evt_type & LE_EXT_ADV_DIRECT_IND) + return LE_ADV_DIRECT_IND; + + return LE_ADV_IND; + } + + if (evt_type & LE_EXT_ADV_SCAN_RSP) + return LE_ADV_SCAN_RSP; + + if (evt_type & LE_EXT_ADV_SCAN_IND) + return LE_ADV_SCAN_IND; + + if (evt_type == LE_EXT_ADV_NON_CONN_IND || + evt_type & LE_EXT_ADV_DIRECT_IND) + return LE_ADV_NONCONN_IND; + + BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", + evt_type); + + return LE_ADV_INVALID; +} + +static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + u8 num_reports = skb->data[0]; + void *ptr = &skb->data[1]; + + hci_dev_lock(hdev); + + while (num_reports--) { + struct hci_ev_le_ext_adv_report *ev = ptr; + u8 legacy_evt_type; + u16 evt_type; + + evt_type = __le16_to_cpu(ev->evt_type); + legacy_evt_type = ext_evt_type_to_legacy(evt_type); + if (legacy_evt_type != LE_ADV_INVALID) { + process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, + ev->bdaddr_type, NULL, 0, ev->rssi, + ev->data, ev->length); + } + + ptr += sizeof(*ev) + ev->length + 1; + } + + hci_dev_unlock(hdev); +} + static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -5189,6 +5603,18 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_direct_adv_report_evt(hdev, skb); break; + case HCI_EV_LE_EXT_ADV_REPORT: + hci_le_ext_adv_report_evt(hdev, skb); + break; + + case HCI_EV_LE_ENHANCED_CONN_COMPLETE: + hci_le_enh_conn_complete_evt(hdev, skb); + break; + + case HCI_EV_LE_EXT_ADV_SET_TERM: + hci_le_ext_adv_term_evt(hdev, skb); + break; + default: break; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index e44d34734834..e8c9ef1e1922 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -647,11 +647,22 @@ void __hci_req_update_eir(struct hci_request *req) void hci_req_add_le_scan_disable(struct hci_request *req) { - struct hci_cp_le_set_scan_enable cp; + struct hci_dev *hdev = req->hdev; - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_DISABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + if (use_ext_scan(hdev)) { + struct hci_cp_le_set_ext_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, sizeof(cp), + &cp); + } else { + struct hci_cp_le_set_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + } } static void add_to_white_list(struct hci_request *req, @@ -767,10 +778,86 @@ static bool scan_use_rpa(struct hci_dev *hdev) return hci_dev_test_flag(hdev, HCI_PRIVACY); } +static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, + u16 window, u8 own_addr_type, u8 filter_policy) +{ + struct hci_dev *hdev = req->hdev; + + /* Use ext scanning if set ext scan param and ext scan enable is + * supported + */ + if (use_ext_scan(hdev)) { + struct hci_cp_le_set_ext_scan_params *ext_param_cp; + struct hci_cp_le_set_ext_scan_enable ext_enable_cp; + struct hci_cp_le_scan_phy_params *phy_params; + u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 2]; + u32 plen; + + ext_param_cp = (void *)data; + phy_params = (void *)ext_param_cp->data; + + memset(ext_param_cp, 0, sizeof(*ext_param_cp)); + ext_param_cp->own_addr_type = own_addr_type; + ext_param_cp->filter_policy = filter_policy; + + plen = sizeof(*ext_param_cp); + + if (scan_1m(hdev) || scan_2m(hdev)) { + ext_param_cp->scanning_phys |= LE_SCAN_PHY_1M; + + memset(phy_params, 0, sizeof(*phy_params)); + phy_params->type = type; + phy_params->interval = cpu_to_le16(interval); + phy_params->window = cpu_to_le16(window); + + plen += sizeof(*phy_params); + phy_params++; + } + + if (scan_coded(hdev)) { + ext_param_cp->scanning_phys |= LE_SCAN_PHY_CODED; + + memset(phy_params, 0, sizeof(*phy_params)); + phy_params->type = type; + phy_params->interval = cpu_to_le16(interval); + phy_params->window = cpu_to_le16(window); + + plen += sizeof(*phy_params); + phy_params++; + } + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_PARAMS, + plen, ext_param_cp); + + memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); + ext_enable_cp.enable = LE_SCAN_ENABLE; + ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, + sizeof(ext_enable_cp), &ext_enable_cp); + } else { + struct hci_cp_le_set_scan_param param_cp; + struct hci_cp_le_set_scan_enable enable_cp; + + memset(¶m_cp, 0, sizeof(param_cp)); + param_cp.type = type; + param_cp.interval = cpu_to_le16(interval); + param_cp.window = cpu_to_le16(window); + param_cp.own_address_type = own_addr_type; + param_cp.filter_policy = filter_policy; + hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), + ¶m_cp); + + memset(&enable_cp, 0, sizeof(enable_cp)); + enable_cp.enable = LE_SCAN_ENABLE; + enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), + &enable_cp); + } +} + void hci_req_add_le_passive_scan(struct hci_request *req) { - struct hci_cp_le_set_scan_param param_cp; - struct hci_cp_le_set_scan_enable enable_cp; struct hci_dev *hdev = req->hdev; u8 own_addr_type; u8 filter_policy; @@ -804,20 +891,26 @@ void hci_req_add_le_passive_scan(struct hci_request *req) (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)) filter_policy |= 0x02; - memset(¶m_cp, 0, sizeof(param_cp)); - param_cp.type = LE_SCAN_PASSIVE; - param_cp.interval = cpu_to_le16(hdev->le_scan_interval); - param_cp.window = cpu_to_le16(hdev->le_scan_window); - param_cp.own_address_type = own_addr_type; - param_cp.filter_policy = filter_policy; - hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), - ¶m_cp); + hci_req_start_scan(req, LE_SCAN_PASSIVE, hdev->le_scan_interval, + hdev->le_scan_window, own_addr_type, filter_policy); +} + +static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance) +{ + struct adv_info *adv_instance; + + /* Ignore instance 0 */ + if (instance == 0x00) + return 0; + + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return 0; - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), - &enable_cp); + /* TODO: Take into account the "appearance" and "local-name" flags here. + * These are currently being ignored as they are not supported. + */ + return adv_instance->scan_rsp_len; } static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) @@ -841,9 +934,19 @@ static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) void __hci_req_disable_advertising(struct hci_request *req) { - u8 enable = 0x00; + if (ext_adv_capable(req->hdev)) { + struct hci_cp_le_set_ext_adv_enable cp; - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); + cp.enable = 0x00; + /* Disable all sets since we only support one set at the moment */ + cp.num_of_sets = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, sizeof(cp), &cp); + } else { + u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); + } } static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance) @@ -1081,29 +1184,58 @@ static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_rsp_data cp; u8 len; if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; - memset(&cp, 0, sizeof(cp)); + if (ext_adv_capable(hdev)) { + struct hci_cp_le_set_ext_scan_rsp_data cp; - if (instance) - len = create_instance_scan_rsp_data(hdev, instance, cp.data); - else - len = create_default_scan_rsp_data(hdev, cp.data); + memset(&cp, 0, sizeof(cp)); - if (hdev->scan_rsp_data_len == len && - !memcmp(cp.data, hdev->scan_rsp_data, len)) - return; + if (instance) + len = create_instance_scan_rsp_data(hdev, instance, + cp.data); + else + len = create_default_scan_rsp_data(hdev, cp.data); + + if (hdev->scan_rsp_data_len == len && + !memcmp(cp.data, hdev->scan_rsp_data, len)) + return; - memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); - hdev->scan_rsp_data_len = len; + memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + hdev->scan_rsp_data_len = len; - cp.length = len; + cp.handle = 0; + cp.length = len; + cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, sizeof(cp), + &cp); + } else { + struct hci_cp_le_set_scan_rsp_data cp; + + memset(&cp, 0, sizeof(cp)); + + if (instance) + len = create_instance_scan_rsp_data(hdev, instance, + cp.data); + else + len = create_default_scan_rsp_data(hdev, cp.data); + + if (hdev->scan_rsp_data_len == len && + !memcmp(cp.data, hdev->scan_rsp_data, len)) + return; - hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); + memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + hdev->scan_rsp_data_len = len; + + cp.length = len; + + hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); + } } static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) @@ -1160,15 +1292,27 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) ptr += adv_instance->adv_data_len; } - /* Provide Tx Power only if we can provide a valid value for it */ - if (hdev->adv_tx_power != HCI_TX_POWER_INVALID && - (instance_flags & MGMT_ADV_FLAG_TX_POWER)) { - ptr[0] = 0x02; - ptr[1] = EIR_TX_POWER; - ptr[2] = (u8)hdev->adv_tx_power; + if (instance_flags & MGMT_ADV_FLAG_TX_POWER) { + s8 adv_tx_power; - ad_len += 3; - ptr += 3; + if (ext_adv_capable(hdev)) { + if (adv_instance) + adv_tx_power = adv_instance->tx_power; + else + adv_tx_power = hdev->adv_tx_power; + } else { + adv_tx_power = hdev->adv_tx_power; + } + + /* Provide Tx Power only if we can provide a valid value for it */ + if (adv_tx_power != HCI_TX_POWER_INVALID) { + ptr[0] = 0x02; + ptr[1] = EIR_TX_POWER; + ptr[2] = (u8)adv_tx_power; + + ad_len += 3; + ptr += 3; + } } return ad_len; @@ -1177,27 +1321,51 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) void __hci_req_update_adv_data(struct hci_request *req, u8 instance) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_data cp; u8 len; if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; - memset(&cp, 0, sizeof(cp)); + if (ext_adv_capable(hdev)) { + struct hci_cp_le_set_ext_adv_data cp; - len = create_instance_adv_data(hdev, instance, cp.data); + memset(&cp, 0, sizeof(cp)); - /* There's nothing to do if the data hasn't changed */ - if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) - return; + len = create_instance_adv_data(hdev, instance, cp.data); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return; + + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + cp.handle = 0; + cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, sizeof(cp), &cp); + } else { + struct hci_cp_le_set_adv_data cp; + + memset(&cp, 0, sizeof(cp)); + + len = create_instance_adv_data(hdev, instance, cp.data); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return; - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); - hdev->adv_data_len = len; + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; - cp.length = len; + cp.length = len; - hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); + } } int hci_req_update_adv_data(struct hci_dev *hdev, u8 instance) @@ -1229,9 +1397,13 @@ void hci_req_reenable_advertising(struct hci_dev *hdev) __hci_req_schedule_adv_instance(&req, hdev->cur_adv_instance, true); } else { - __hci_req_update_adv_data(&req, 0x00); - __hci_req_update_scan_rsp_data(&req, 0x00); - __hci_req_enable_advertising(&req); + if (ext_adv_capable(hdev)) { + __hci_req_start_ext_adv(&req, 0x00); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + __hci_req_enable_advertising(&req); + } } hci_req_run(&req, adv_enable_complete); @@ -1268,6 +1440,245 @@ unlock: hci_dev_unlock(hdev); } +int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, + bool use_rpa, struct adv_info *adv_instance, + u8 *own_addr_type, bdaddr_t *rand_addr) +{ + int err; + + bacpy(rand_addr, BDADDR_ANY); + + /* If privacy is enabled use a resolvable private address. If + * current RPA has expired then generate a new one. + */ + if (use_rpa) { + int to; + + *own_addr_type = ADDR_LE_DEV_RANDOM; + + if (adv_instance) { + if (!adv_instance->rpa_expired && + !bacmp(&adv_instance->random_addr, &hdev->rpa)) + return 0; + + adv_instance->rpa_expired = false; + } else { + if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) && + !bacmp(&hdev->random_addr, &hdev->rpa)) + return 0; + } + + err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa); + if (err < 0) { + BT_ERR("%s failed to generate new RPA", hdev->name); + return err; + } + + bacpy(rand_addr, &hdev->rpa); + + to = msecs_to_jiffies(hdev->rpa_timeout * 1000); + if (adv_instance) + queue_delayed_work(hdev->workqueue, + &adv_instance->rpa_expired_cb, to); + else + queue_delayed_work(hdev->workqueue, + &hdev->rpa_expired, to); + + return 0; + } + + /* In case of required privacy without resolvable private address, + * use an non-resolvable private address. This is useful for + * non-connectable advertising. + */ + if (require_privacy) { + bdaddr_t nrpa; + + while (true) { + /* The non-resolvable private address is generated + * from random six bytes with the two most significant + * bits cleared. + */ + get_random_bytes(&nrpa, 6); + nrpa.b[5] &= 0x3f; + + /* The non-resolvable private address shall not be + * equal to the public address. + */ + if (bacmp(&hdev->bdaddr, &nrpa)) + break; + } + + *own_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(rand_addr, &nrpa); + + return 0; + } + + /* No privacy so use a public address. */ + *own_addr_type = ADDR_LE_DEV_PUBLIC; + + return 0; +} + +void __hci_req_clear_ext_adv_sets(struct hci_request *req) +{ + hci_req_add(req, HCI_OP_LE_CLEAR_ADV_SETS, 0, NULL); +} + +int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) +{ + struct hci_cp_le_set_ext_adv_params cp; + struct hci_dev *hdev = req->hdev; + bool connectable; + u32 flags; + bdaddr_t random_addr; + u8 own_addr_type; + int err; + struct adv_info *adv_instance; + bool secondary_adv; + /* In ext adv set param interval is 3 octets */ + const u8 adv_interval[3] = { 0x00, 0x08, 0x00 }; + + if (instance > 0) { + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return -EINVAL; + } else { + adv_instance = NULL; + } + + flags = get_adv_instance_flags(hdev, instance); + + /* If the "connectable" instance flag was not set, then choose between + * ADV_IND and ADV_NONCONN_IND based on the global connectable setting. + */ + connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) || + mgmt_get_connectable(hdev); + + if (!is_advertising_allowed(hdev, connectable)) + return -EPERM; + + /* Set require_privacy to true only when non-connectable + * advertising is used. In that case it is fine to use a + * non-resolvable private address. + */ + err = hci_get_random_address(hdev, !connectable, + adv_use_rpa(hdev, flags), adv_instance, + &own_addr_type, &random_addr); + if (err < 0) + return err; + + memset(&cp, 0, sizeof(cp)); + + memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval)); + memcpy(cp.max_interval, adv_interval, sizeof(cp.max_interval)); + + secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK); + + if (connectable) { + if (secondary_adv) + cp.evt_properties = cpu_to_le16(LE_EXT_ADV_CONN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND); + } else if (get_adv_instance_scan_rsp_len(hdev, instance)) { + if (secondary_adv) + cp.evt_properties = cpu_to_le16(LE_EXT_ADV_SCAN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND); + } else { + if (secondary_adv) + cp.evt_properties = cpu_to_le16(LE_EXT_ADV_NON_CONN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND); + } + + cp.own_addr_type = own_addr_type; + cp.channel_map = hdev->le_adv_channel_map; + cp.tx_power = 127; + cp.handle = 0; + + if (flags & MGMT_ADV_FLAG_SEC_2M) { + cp.primary_phy = HCI_ADV_PHY_1M; + cp.secondary_phy = HCI_ADV_PHY_2M; + } else if (flags & MGMT_ADV_FLAG_SEC_CODED) { + cp.primary_phy = HCI_ADV_PHY_CODED; + cp.secondary_phy = HCI_ADV_PHY_CODED; + } else { + /* In all other cases use 1M */ + cp.primary_phy = HCI_ADV_PHY_1M; + cp.secondary_phy = HCI_ADV_PHY_1M; + } + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); + + if (own_addr_type == ADDR_LE_DEV_RANDOM && + bacmp(&random_addr, BDADDR_ANY)) { + struct hci_cp_le_set_adv_set_rand_addr cp; + + /* Check if random address need to be updated */ + if (adv_instance) { + if (!bacmp(&random_addr, &adv_instance->random_addr)) + return 0; + } else { + if (!bacmp(&random_addr, &hdev->random_addr)) + return 0; + } + + memset(&cp, 0, sizeof(cp)); + + cp.handle = 0; + bacpy(&cp.bdaddr, &random_addr); + + hci_req_add(req, + HCI_OP_LE_SET_ADV_SET_RAND_ADDR, + sizeof(cp), &cp); + } + + return 0; +} + +void __hci_req_enable_ext_advertising(struct hci_request *req) +{ + struct hci_cp_le_set_ext_adv_enable *cp; + struct hci_cp_ext_adv_set *adv_set; + u8 data[sizeof(*cp) + sizeof(*adv_set) * 1]; + + cp = (void *) data; + adv_set = (void *) cp->data; + + memset(cp, 0, sizeof(*cp)); + + cp->enable = 0x01; + cp->num_of_sets = 0x01; + + memset(adv_set, 0, sizeof(*adv_set)); + + adv_set->handle = 0; + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, + sizeof(*cp) + sizeof(*adv_set) * cp->num_of_sets, + data); +} + +int __hci_req_start_ext_adv(struct hci_request *req, u8 instance) +{ + struct hci_dev *hdev = req->hdev; + int err; + + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) + __hci_req_disable_advertising(req); + + err = __hci_req_setup_ext_adv_instance(req, instance); + if (err < 0) + return err; + + __hci_req_update_scan_rsp_data(req, instance); + __hci_req_enable_ext_advertising(req); + + return 0; +} + int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, bool force) { @@ -1321,9 +1732,13 @@ int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, return 0; hdev->cur_adv_instance = instance; - __hci_req_update_adv_data(req, instance); - __hci_req_update_scan_rsp_data(req, instance); - __hci_req_enable_advertising(req); + if (ext_adv_capable(hdev)) { + __hci_req_start_ext_adv(req, instance); + } else { + __hci_req_update_adv_data(req, instance); + __hci_req_update_scan_rsp_data(req, instance); + __hci_req_enable_advertising(req); + } return 0; } @@ -1594,8 +2009,12 @@ static int connectable_update(struct hci_request *req, unsigned long opt) /* Update the advertising parameters if necessary */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || - !list_empty(&hdev->adv_instances)) - __hci_req_enable_advertising(req); + !list_empty(&hdev->adv_instances)) { + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(req, hdev->cur_adv_instance); + else + __hci_req_enable_advertising(req); + } __hci_update_background_scan(req); @@ -1704,8 +2123,12 @@ static int discoverable_update(struct hci_request *req, unsigned long opt) /* Discoverable mode affects the local advertising * address in limited privacy mode. */ - if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) - __hci_req_enable_advertising(req); + if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) { + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(req, 0x00); + else + __hci_req_enable_advertising(req); + } } hci_dev_unlock(hdev); @@ -1940,7 +2363,6 @@ discov_stopped: static int le_scan_restart(struct hci_request *req, unsigned long opt) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_enable cp; /* If controller is not scanning we are done. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) @@ -1948,10 +2370,23 @@ static int le_scan_restart(struct hci_request *req, unsigned long opt) hci_req_add_le_scan_disable(req); - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_ENABLE; - cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + if (use_ext_scan(hdev)) { + struct hci_cp_le_set_ext_scan_enable ext_enable_cp; + + memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); + ext_enable_cp.enable = LE_SCAN_ENABLE; + ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, + sizeof(ext_enable_cp), &ext_enable_cp); + } else { + struct hci_cp_le_set_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_ENABLE; + cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + } return 0; } @@ -2010,8 +2445,6 @@ static int active_scan(struct hci_request *req, unsigned long opt) { uint16_t interval = opt; struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_param param_cp; - struct hci_cp_le_set_scan_enable enable_cp; u8 own_addr_type; int err; @@ -2050,22 +2483,8 @@ static int active_scan(struct hci_request *req, unsigned long opt) if (err < 0) own_addr_type = ADDR_LE_DEV_PUBLIC; - memset(¶m_cp, 0, sizeof(param_cp)); - param_cp.type = LE_SCAN_ACTIVE; - param_cp.interval = cpu_to_le16(interval); - param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN); - param_cp.own_address_type = own_addr_type; - - hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), - ¶m_cp); - - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), - &enable_cp); - + hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, DISCOV_LE_SCAN_WIN, + own_addr_type, 0); return 0; } @@ -2302,11 +2721,26 @@ static int powered_update_hci(struct hci_request *req, unsigned long opt) */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || list_empty(&hdev->adv_instances)) { - __hci_req_update_adv_data(req, 0x00); - __hci_req_update_scan_rsp_data(req, 0x00); - - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) - __hci_req_enable_advertising(req); + int err; + + if (ext_adv_capable(hdev)) { + err = __hci_req_setup_ext_adv_instance(req, + 0x00); + if (!err) + __hci_req_update_scan_rsp_data(req, + 0x00); + } else { + err = 0; + __hci_req_update_adv_data(req, 0x00); + __hci_req_update_scan_rsp_data(req, 0x00); + } + + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) { + if (!ext_adv_capable(hdev)) + __hci_req_enable_advertising(req); + else if (!err) + __hci_req_enable_ext_advertising(req); + } } else if (!list_empty(&hdev->adv_instances)) { struct adv_info *adv_instance; diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 702beb140d9f..692cc8b13368 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -80,6 +80,14 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, struct hci_request *req, u8 instance, bool force); +int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance); +int __hci_req_start_ext_adv(struct hci_request *req, u8 instance); +void __hci_req_enable_ext_advertising(struct hci_request *req); +void __hci_req_clear_ext_adv_sets(struct hci_request *req); +int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, + bool use_rpa, struct adv_info *adv_instance, + u8 *own_addr_type, bdaddr_t *rand_addr); + void __hci_req_update_class(struct hci_request *req); /* Returns true if HCI commands were queued */ diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 1036e4fa1ea2..253975cce943 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -431,8 +431,8 @@ static void hidp_del_timer(struct hidp_session *session) del_timer(&session->timer); } -static void hidp_process_report(struct hidp_session *session, - int type, const u8 *data, int len, int intr) +static void hidp_process_report(struct hidp_session *session, int type, + const u8 *data, unsigned int len, int intr) { if (len > HID_MAX_BUFFER_SIZE) len = HID_MAX_BUFFER_SIZE; @@ -775,7 +775,7 @@ static int hidp_setup_hid(struct hidp_session *session, hid->version = req->version; hid->country = req->country; - strncpy(hid->name, req->name, sizeof(req->name) - 1); + strncpy(hid->name, req->name, sizeof(hid->name)); snprintf(hid->phys, sizeof(hid->phys), "%pMR", &l2cap_pi(session->ctrl_sock->sk)->chan->src); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 8a80d48d89c4..231602f7cb66 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -617,6 +617,127 @@ static int read_config_info(struct sock *sk, struct hci_dev *hdev, &rp, sizeof(rp)); } +static u32 get_supported_phys(struct hci_dev *hdev) +{ + u32 supported_phys = 0; + + if (lmp_bredr_capable(hdev)) { + supported_phys |= MGMT_PHY_BR_1M_1SLOT; + + if (hdev->features[0][0] & LMP_3SLOT) + supported_phys |= MGMT_PHY_BR_1M_3SLOT; + + if (hdev->features[0][0] & LMP_5SLOT) + supported_phys |= MGMT_PHY_BR_1M_5SLOT; + + if (lmp_edr_2m_capable(hdev)) { + supported_phys |= MGMT_PHY_EDR_2M_1SLOT; + + if (lmp_edr_3slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_2M_3SLOT; + + if (lmp_edr_5slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_2M_5SLOT; + + if (lmp_edr_3m_capable(hdev)) { + supported_phys |= MGMT_PHY_EDR_3M_1SLOT; + + if (lmp_edr_3slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_3M_3SLOT; + + if (lmp_edr_5slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_3M_5SLOT; + } + } + } + + if (lmp_le_capable(hdev)) { + supported_phys |= MGMT_PHY_LE_1M_TX; + supported_phys |= MGMT_PHY_LE_1M_RX; + + if (hdev->le_features[1] & HCI_LE_PHY_2M) { + supported_phys |= MGMT_PHY_LE_2M_TX; + supported_phys |= MGMT_PHY_LE_2M_RX; + } + + if (hdev->le_features[1] & HCI_LE_PHY_CODED) { + supported_phys |= MGMT_PHY_LE_CODED_TX; + supported_phys |= MGMT_PHY_LE_CODED_RX; + } + } + + return supported_phys; +} + +static u32 get_selected_phys(struct hci_dev *hdev) +{ + u32 selected_phys = 0; + + if (lmp_bredr_capable(hdev)) { + selected_phys |= MGMT_PHY_BR_1M_1SLOT; + + if (hdev->pkt_type & (HCI_DM3 | HCI_DH3)) + selected_phys |= MGMT_PHY_BR_1M_3SLOT; + + if (hdev->pkt_type & (HCI_DM5 | HCI_DH5)) + selected_phys |= MGMT_PHY_BR_1M_5SLOT; + + if (lmp_edr_2m_capable(hdev)) { + if (!(hdev->pkt_type & HCI_2DH1)) + selected_phys |= MGMT_PHY_EDR_2M_1SLOT; + + if (lmp_edr_3slot_capable(hdev) && + !(hdev->pkt_type & HCI_2DH3)) + selected_phys |= MGMT_PHY_EDR_2M_3SLOT; + + if (lmp_edr_5slot_capable(hdev) && + !(hdev->pkt_type & HCI_2DH5)) + selected_phys |= MGMT_PHY_EDR_2M_5SLOT; + + if (lmp_edr_3m_capable(hdev)) { + if (!(hdev->pkt_type & HCI_3DH1)) + selected_phys |= MGMT_PHY_EDR_3M_1SLOT; + + if (lmp_edr_3slot_capable(hdev) && + !(hdev->pkt_type & HCI_3DH3)) + selected_phys |= MGMT_PHY_EDR_3M_3SLOT; + + if (lmp_edr_5slot_capable(hdev) && + !(hdev->pkt_type & HCI_3DH5)) + selected_phys |= MGMT_PHY_EDR_3M_5SLOT; + } + } + } + + if (lmp_le_capable(hdev)) { + if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_1M) + selected_phys |= MGMT_PHY_LE_1M_TX; + + if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_1M) + selected_phys |= MGMT_PHY_LE_1M_RX; + + if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_2M) + selected_phys |= MGMT_PHY_LE_2M_TX; + + if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_2M) + selected_phys |= MGMT_PHY_LE_2M_RX; + + if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_CODED) + selected_phys |= MGMT_PHY_LE_CODED_TX; + + if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_CODED) + selected_phys |= MGMT_PHY_LE_CODED_RX; + } + + return selected_phys; +} + +static u32 get_configurable_phys(struct hci_dev *hdev) +{ + return (get_supported_phys(hdev) & ~MGMT_PHY_BR_1M_1SLOT & + ~MGMT_PHY_LE_1M_TX & ~MGMT_PHY_LE_1M_RX); +} + static u32 get_supported_settings(struct hci_dev *hdev) { u32 settings = 0; @@ -654,6 +775,8 @@ static u32 get_supported_settings(struct hci_dev *hdev) hdev->set_bdaddr) settings |= MGMT_SETTING_CONFIGURATION; + settings |= MGMT_SETTING_PHY_CONFIGURATION; + return settings; } @@ -817,7 +940,10 @@ static void rpa_expired(struct work_struct *work) * function. */ hci_req_init(&req, hdev); - __hci_req_enable_advertising(&req); + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(&req, hdev->cur_adv_instance); + else + __hci_req_enable_advertising(&req); hci_req_run(&req, NULL); } @@ -1721,10 +1847,17 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) */ if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { struct hci_request req; - hci_req_init(&req, hdev); - __hci_req_update_adv_data(&req, 0x00); - __hci_req_update_scan_rsp_data(&req, 0x00); + if (ext_adv_capable(hdev)) { + int err; + + err = __hci_req_setup_ext_adv_instance(&req, 0x00); + if (!err) + __hci_req_update_scan_rsp_data(&req, 0x00); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + } hci_req_run(&req, NULL); hci_update_background_scan(hdev); } @@ -1823,6 +1956,9 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) } else { if (hci_dev_test_flag(hdev, HCI_LE_ADV)) __hci_req_disable_advertising(&req); + + if (ext_adv_capable(hdev)) + __hci_req_clear_ext_adv_sets(&req); } hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp), @@ -3184,6 +3320,228 @@ static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data, return err; } +static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_rp_get_phy_confguration rp; + + BT_DBG("sock %p %s", sk, hdev->name); + + hci_dev_lock(hdev); + + memset(&rp, 0, sizeof(rp)); + + rp.supported_phys = cpu_to_le32(get_supported_phys(hdev)); + rp.selected_phys = cpu_to_le32(get_selected_phys(hdev)); + rp.configurable_phys = cpu_to_le32(get_configurable_phys(hdev)); + + hci_dev_unlock(hdev); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_PHY_CONFIGURATION, 0, + &rp, sizeof(rp)); +} + +int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip) +{ + struct mgmt_ev_phy_configuration_changed ev; + + memset(&ev, 0, sizeof(ev)); + + ev.selected_phys = cpu_to_le32(get_selected_phys(hdev)); + + return mgmt_event(MGMT_EV_PHY_CONFIGURATION_CHANGED, hdev, &ev, + sizeof(ev), skip); +} + +static void set_default_phy_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct mgmt_cp_set_phy_confguration *cp; + struct mgmt_pending_cmd *cmd; + + BT_DBG("status 0x%02x", status); + + hci_dev_lock(hdev); + + cmd = pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev); + if (!cmd) + goto unlock; + + cp = cmd->param; + + if (status) { + mgmt_cmd_status(cmd->sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + mgmt_status(status)); + } else { + mgmt_cmd_complete(cmd->sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, 0, + NULL, 0); + + mgmt_phy_configuration_changed(hdev, cmd->sk); + } + + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); +} + +static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_set_phy_confguration *cp = data; + struct hci_cp_le_set_default_phy cp_phy; + struct mgmt_pending_cmd *cmd; + struct hci_request req; + u32 selected_phys, configurable_phys, supported_phys, unconfigure_phys; + u16 pkt_type = (HCI_DH1 | HCI_DM1); + bool changed = false; + int err; + + BT_DBG("sock %p %s", sk, hdev->name); + + configurable_phys = get_configurable_phys(hdev); + supported_phys = get_supported_phys(hdev); + selected_phys = __le32_to_cpu(cp->selected_phys); + + if (selected_phys & ~supported_phys) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_INVALID_PARAMS); + + unconfigure_phys = supported_phys & ~configurable_phys; + + if ((selected_phys & unconfigure_phys) != unconfigure_phys) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_INVALID_PARAMS); + + if (selected_phys == get_selected_phys(hdev)) + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + 0, NULL, 0); + + hci_dev_lock(hdev); + + if (!hdev_is_powered(hdev)) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_REJECTED); + goto unlock; + } + + if (pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_BUSY); + goto unlock; + } + + if (selected_phys & MGMT_PHY_BR_1M_3SLOT) + pkt_type |= (HCI_DH3 | HCI_DM3); + else + pkt_type &= ~(HCI_DH3 | HCI_DM3); + + if (selected_phys & MGMT_PHY_BR_1M_5SLOT) + pkt_type |= (HCI_DH5 | HCI_DM5); + else + pkt_type &= ~(HCI_DH5 | HCI_DM5); + + if (selected_phys & MGMT_PHY_EDR_2M_1SLOT) + pkt_type &= ~HCI_2DH1; + else + pkt_type |= HCI_2DH1; + + if (selected_phys & MGMT_PHY_EDR_2M_3SLOT) + pkt_type &= ~HCI_2DH3; + else + pkt_type |= HCI_2DH3; + + if (selected_phys & MGMT_PHY_EDR_2M_5SLOT) + pkt_type &= ~HCI_2DH5; + else + pkt_type |= HCI_2DH5; + + if (selected_phys & MGMT_PHY_EDR_3M_1SLOT) + pkt_type &= ~HCI_3DH1; + else + pkt_type |= HCI_3DH1; + + if (selected_phys & MGMT_PHY_EDR_3M_3SLOT) + pkt_type &= ~HCI_3DH3; + else + pkt_type |= HCI_3DH3; + + if (selected_phys & MGMT_PHY_EDR_3M_5SLOT) + pkt_type &= ~HCI_3DH5; + else + pkt_type |= HCI_3DH5; + + if (pkt_type != hdev->pkt_type) { + hdev->pkt_type = pkt_type; + changed = true; + } + + if ((selected_phys & MGMT_PHY_LE_MASK) == + (get_selected_phys(hdev) & MGMT_PHY_LE_MASK)) { + if (changed) + mgmt_phy_configuration_changed(hdev, sk); + + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + 0, NULL, 0); + + goto unlock; + } + + cmd = mgmt_pending_add(sk, MGMT_OP_SET_PHY_CONFIGURATION, hdev, data, + len); + if (!cmd) { + err = -ENOMEM; + goto unlock; + } + + hci_req_init(&req, hdev); + + memset(&cp_phy, 0, sizeof(cp_phy)); + + if (!(selected_phys & MGMT_PHY_LE_TX_MASK)) + cp_phy.all_phys |= 0x01; + + if (!(selected_phys & MGMT_PHY_LE_RX_MASK)) + cp_phy.all_phys |= 0x02; + + if (selected_phys & MGMT_PHY_LE_1M_TX) + cp_phy.tx_phys |= HCI_LE_SET_PHY_1M; + + if (selected_phys & MGMT_PHY_LE_2M_TX) + cp_phy.tx_phys |= HCI_LE_SET_PHY_2M; + + if (selected_phys & MGMT_PHY_LE_CODED_TX) + cp_phy.tx_phys |= HCI_LE_SET_PHY_CODED; + + if (selected_phys & MGMT_PHY_LE_1M_RX) + cp_phy.rx_phys |= HCI_LE_SET_PHY_1M; + + if (selected_phys & MGMT_PHY_LE_2M_RX) + cp_phy.rx_phys |= HCI_LE_SET_PHY_2M; + + if (selected_phys & MGMT_PHY_LE_CODED_RX) + cp_phy.rx_phys |= HCI_LE_SET_PHY_CODED; + + hci_req_add(&req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp_phy), &cp_phy); + + err = hci_req_run_skb(&req, set_default_phy_complete); + if (err < 0) + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); + + return err; +} + static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -4037,9 +4395,14 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, * HCI_ADVERTISING flag is not yet set. */ hdev->cur_adv_instance = 0x00; - __hci_req_update_adv_data(&req, 0x00); - __hci_req_update_scan_rsp_data(&req, 0x00); - __hci_req_enable_advertising(&req); + + if (ext_adv_capable(hdev)) { + __hci_req_start_ext_adv(&req, 0x00); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + __hci_req_enable_advertising(&req); + } } else { __hci_req_disable_advertising(&req); } @@ -4609,6 +4972,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, changed = !hci_dev_test_and_set_flag(hdev, HCI_PRIVACY); memcpy(hdev->irk, cp->irk, sizeof(hdev->irk)); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, true); if (cp->privacy == 0x02) hci_dev_set_flag(hdev, HCI_LIMITED_PRIVACY); else @@ -4617,6 +4981,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, changed = hci_dev_test_and_clear_flag(hdev, HCI_PRIVACY); memset(hdev->irk, 0, sizeof(hdev->irk)); hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, false); hci_dev_clear_flag(hdev, HCI_LIMITED_PRIVACY); } @@ -5967,9 +6332,23 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev) flags |= MGMT_ADV_FLAG_APPEARANCE; flags |= MGMT_ADV_FLAG_LOCAL_NAME; - if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) + /* In extended adv TX_POWER returned from Set Adv Param + * will be always valid. + */ + if ((hdev->adv_tx_power != HCI_TX_POWER_INVALID) || + ext_adv_capable(hdev)) flags |= MGMT_ADV_FLAG_TX_POWER; + if (ext_adv_capable(hdev)) { + flags |= MGMT_ADV_FLAG_SEC_1M; + + if (hdev->le_features[1] & HCI_LE_PHY_2M) + flags |= MGMT_ADV_FLAG_SEC_2M; + + if (hdev->le_features[1] & HCI_LE_PHY_CODED) + flags |= MGMT_ADV_FLAG_SEC_CODED; + } + return flags; } @@ -6175,7 +6554,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, struct mgmt_cp_add_advertising *cp = data; struct mgmt_rp_add_advertising rp; u32 flags; - u32 supported_flags; + u32 supported_flags, phy_flags; u8 status; u16 timeout, duration; unsigned int prev_instance_cnt = hdev->adv_instance_cnt; @@ -6205,10 +6584,12 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, duration = __le16_to_cpu(cp->duration); /* The current implementation only supports a subset of the specified - * flags. + * flags. Also need to check mutual exclusiveness of sec flags. */ supported_flags = get_supported_adv_flags(hdev); - if (flags & ~supported_flags) + phy_flags = flags & MGMT_ADV_FLAG_SEC_MASK; + if (flags & ~supported_flags || + ((phy_flags && (phy_flags ^ (phy_flags & -phy_flags))))) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); @@ -6544,6 +6925,8 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { read_ext_controller_info,MGMT_READ_EXT_INFO_SIZE, HCI_MGMT_UNTRUSTED }, { set_appearance, MGMT_SET_APPEARANCE_SIZE }, + { get_phy_configuration, MGMT_GET_PHY_CONFIGURATION_SIZE }, + { set_phy_configuration, MGMT_SET_PHY_CONFIGURATION_SIZE }, }; void mgmt_index_added(struct hci_dev *hdev) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 413b8ee49fec..8f0f9279eac9 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -393,7 +393,8 @@ static void sco_sock_cleanup_listen(struct sock *parent) */ static void sco_sock_kill(struct sock *sk) { - if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) + if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || + sock_flag(sk, SOCK_DEAD)) return; BT_DBG("sk %p state %d", sk, sk->sk_state); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 9b16eaf33819..6e0dc6bcd32a 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -26,6 +26,7 @@ #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/netfilter_bridge.h> +#include <uapi/linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_arp.h> diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index c41da5fac84f..550324c516ee 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -9,6 +9,7 @@ */ #include <linux/netfilter_bridge/ebtables.h> +#include <uapi/linux/netfilter_bridge.h> #include <linux/module.h> #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \ diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 08df7406ecb3..c0fb3ca518af 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -9,6 +9,7 @@ */ #include <linux/netfilter_bridge/ebtables.h> +#include <uapi/linux/netfilter_bridge.h> #include <linux/module.h> #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e0adcd123f48..711d7156efd8 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb) caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); - if (caifd == NULL) + if (!caifd) { + rcu_read_unlock(); return; + } caifd_hold(caifd); rcu_read_unlock(); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index a6fb1b3bcad9..d18965f3291f 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -941,7 +941,7 @@ static __poll_t caif_poll(struct file *file, __poll_t mask; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ diff --git a/net/core/datagram.c b/net/core/datagram.c index 9938952c5c78..9aac0d63d53e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -837,7 +837,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ diff --git a/net/core/dev.c b/net/core/dev.c index 87c42c8249ae..f68122f0ab02 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4252,7 +4252,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_cloned(skb)) + if (skb_cloned(skb) || skb_is_tc_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom @@ -4602,6 +4602,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, __skb_push(skb, skb->mac_len); skb_do_redirect(skb); return NULL; + case TC_ACT_REINSERT: + /* this does not scrub the packet, and updates stats on error */ + skb_tc_reinsert(skb, &cl_res); + return NULL; default: break; } @@ -7523,13 +7527,15 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) EXPORT_SYMBOL(__dev_set_mtu); /** - * dev_set_mtu - Change maximum transfer unit + * dev_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit + * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ -int dev_set_mtu(struct net_device *dev, int new_mtu) +int dev_set_mtu_ext(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) { int err, orig_mtu; @@ -7538,14 +7544,12 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { - net_err_ratelimited("%s: Invalid MTU %d requested, hw min %d\n", - dev->name, new_mtu, dev->min_mtu); + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - net_err_ratelimited("%s: Invalid MTU %d requested, hw max %d\n", - dev->name, new_mtu, dev->max_mtu); + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } @@ -7573,6 +7577,18 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) } return err; } + +int dev_set_mtu(struct net_device *dev, int new_mtu) +{ + struct netlink_ext_ack extack; + int err; + + memset(&extack, 0, sizeof(extack)); + err = dev_set_mtu_ext(dev, new_mtu, &extack); + if (err && extack._msg) + net_err_ratelimited("%s: %s\n", dev->name, extack._msg); + return err; +} EXPORT_SYMBOL(dev_set_mtu); /** @@ -7592,16 +7608,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) dev->tx_queue_len = new_len; res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); - if (res) { - netdev_err(dev, - "refused to change device tx_queue_len\n"); - dev->tx_queue_len = orig_len; - return res; - } - return dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; + res = dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; } return 0; + +err_rollback: + netdev_err(dev, "refused to change device tx_queue_len\n"); + dev->tx_queue_len = orig_len; + return res; } /** diff --git a/net/core/dst.c b/net/core/dst.c index 2d9b37f8944a..81ccf20e2826 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -307,6 +307,7 @@ void metadata_dst_free(struct metadata_dst *md_dst) #endif kfree(md_dst); } +EXPORT_SYMBOL_GPL(metadata_dst_free); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index f64aa13811ea..0ff3953f64aa 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -924,8 +924,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; errout: - if (nlrule) - kfree(nlrule); + kfree(nlrule); rules_ops_put(ops); return err; } diff --git a/net/core/filter.c b/net/core/filter.c index 104d560946da..7509bb7f0694 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1712,24 +1712,26 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { + u8 *end = skb_tail_pointer(skb); + u8 *net = skb_network_header(skb); + u8 *mac = skb_mac_header(skb); u8 *ptr; - if (unlikely(offset > 0xffff || len > skb_headlen(skb))) + if (unlikely(offset > 0xffff || len > (end - mac))) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = skb_mac_header(skb) + offset; + ptr = mac + offset; break; case BPF_HDR_START_NET: - ptr = skb_network_header(skb) + offset; + ptr = net + offset; break; default: goto err_clear; } - if (likely(ptr >= skb_mac_header(skb) && - ptr + len <= skb_tail_pointer(skb))) { + if (likely(ptr >= mac && ptr + len <= end)) { memcpy(to, ptr, len); return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index e7e626fb87bb..e45098593dc0 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -217,7 +217,7 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog, if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME]) return -EINVAL; - prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL); + prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC); if (!prog->name) return -ENOMEM; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 68bf07206744..43a932cb609b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) struct page *page; /* Empty recycle ring */ - while ((page = ptr_ring_consume(&pool->ring))) { + while ((page = ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ if (!(page_ref_count(page) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 308ed04984de..7f6938405fa1 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2253,7 +2253,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); } else { /* slow path: we dont already have xfrm_state */ - x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, AF_INET, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 92b6fa5d5f6e..24431e578310 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1015,6 +1015,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_IF_NETNSID */ + nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */ + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + + nla_total_size(4) /* IFLA_MIN_MTU */ + + nla_total_size(4) /* IFLA_MAX_MTU */ + 0; } @@ -1601,6 +1603,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, netif_running(dev) ? dev->operstate : IF_OPER_DOWN) || nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u32(skb, IFLA_MIN_MTU, dev->min_mtu) || + nla_put_u32(skb, IFLA_MAX_MTU, dev->max_mtu) || nla_put_u32(skb, IFLA_GROUP, dev->group) || nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || @@ -1732,6 +1736,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_IF_NETNSID] = { .type = NLA_S32 }, [IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 }, [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, + [IFLA_MIN_MTU] = { .type = NLA_U32 }, + [IFLA_MAX_MTU] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2376,7 +2382,7 @@ static int do_setlink(const struct sk_buff *skb, } if (tb[IFLA_MTU]) { - err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack); if (err < 0) goto errout; status |= DO_SETLINK_MODIFIED; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0c1a00672ba9..8d574a88125d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1715,7 +1715,7 @@ void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; - if (unlikely(skb->data<skb->head)) + if (unlikely(skb->data < skb->head)) skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data; } @@ -2858,23 +2858,27 @@ EXPORT_SYMBOL(skb_queue_purge); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty + * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ -void skb_rbtree_purge(struct rb_root *root) +unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); + unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); + sum += skb->truesize; kfree_skb(skb); } + return sum; } /** @@ -3720,6 +3724,7 @@ normal: net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); + err = -EINVAL; goto err; } @@ -3753,11 +3758,10 @@ skip_fraglist: perform_csum_check: if (!csum) { - if (skb_has_shared_frag(nskb)) { - err = __skb_linearize(nskb); - if (err) - goto err; - } + if (skb_has_shared_frag(nskb) && + __skb_linearize(nskb)) + goto err; + if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = diff --git a/net/core/sock.c b/net/core/sock.c index 03fdea5b0f57..e31233f5ba39 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -250,58 +250,13 @@ static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { - "rlock-AF_UNSPEC", "rlock-AF_UNIX" , "rlock-AF_INET" , - "rlock-AF_AX25" , "rlock-AF_IPX" , "rlock-AF_APPLETALK", - "rlock-AF_NETROM", "rlock-AF_BRIDGE" , "rlock-AF_ATMPVC" , - "rlock-AF_X25" , "rlock-AF_INET6" , "rlock-AF_ROSE" , - "rlock-AF_DECnet", "rlock-AF_NETBEUI" , "rlock-AF_SECURITY" , - "rlock-AF_KEY" , "rlock-AF_NETLINK" , "rlock-AF_PACKET" , - "rlock-AF_ASH" , "rlock-AF_ECONET" , "rlock-AF_ATMSVC" , - "rlock-AF_RDS" , "rlock-AF_SNA" , "rlock-AF_IRDA" , - "rlock-AF_PPPOX" , "rlock-AF_WANPIPE" , "rlock-AF_LLC" , - "rlock-27" , "rlock-28" , "rlock-AF_CAN" , - "rlock-AF_TIPC" , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV" , - "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , - "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , - "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , - "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_XDP" , - "rlock-AF_MAX" + _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { - "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , - "wlock-AF_AX25" , "wlock-AF_IPX" , "wlock-AF_APPLETALK", - "wlock-AF_NETROM", "wlock-AF_BRIDGE" , "wlock-AF_ATMPVC" , - "wlock-AF_X25" , "wlock-AF_INET6" , "wlock-AF_ROSE" , - "wlock-AF_DECnet", "wlock-AF_NETBEUI" , "wlock-AF_SECURITY" , - "wlock-AF_KEY" , "wlock-AF_NETLINK" , "wlock-AF_PACKET" , - "wlock-AF_ASH" , "wlock-AF_ECONET" , "wlock-AF_ATMSVC" , - "wlock-AF_RDS" , "wlock-AF_SNA" , "wlock-AF_IRDA" , - "wlock-AF_PPPOX" , "wlock-AF_WANPIPE" , "wlock-AF_LLC" , - "wlock-27" , "wlock-28" , "wlock-AF_CAN" , - "wlock-AF_TIPC" , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV" , - "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , - "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , - "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , - "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_XDP" , - "wlock-AF_MAX" + _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { - "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , - "elock-AF_AX25" , "elock-AF_IPX" , "elock-AF_APPLETALK", - "elock-AF_NETROM", "elock-AF_BRIDGE" , "elock-AF_ATMPVC" , - "elock-AF_X25" , "elock-AF_INET6" , "elock-AF_ROSE" , - "elock-AF_DECnet", "elock-AF_NETBEUI" , "elock-AF_SECURITY" , - "elock-AF_KEY" , "elock-AF_NETLINK" , "elock-AF_PACKET" , - "elock-AF_ASH" , "elock-AF_ECONET" , "elock-AF_ATMSVC" , - "elock-AF_RDS" , "elock-AF_SNA" , "elock-AF_IRDA" , - "elock-AF_PPPOX" , "elock-AF_WANPIPE" , "elock-AF_LLC" , - "elock-27" , "elock-28" , "elock-AF_CAN" , - "elock-AF_TIPC" , "elock-AF_BLUETOOTH", "elock-AF_IUCV" , - "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , - "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , - "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , - "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_XDP" , - "elock-AF_MAX" + _sock_locks("elock-") }; /* @@ -2316,9 +2271,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, pfrag->offset += use; sge = sg + sg_curr - 1; - if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page && - sg->offset + sg->length == orig_offset) { - sg->length += use; + if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page && + sge->offset + sge->length == orig_offset) { + sge->length += use; } else { sge = sg + sg_curr; sg_unmark_end(sge); diff --git a/net/core/utils.c b/net/core/utils.c index d47863b07a60..2a597ac7808e 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -397,7 +397,7 @@ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, break; default: pr_err("unexpected address family %d\n", af); - }; + } return ret; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 57285383ed00..c013b836006b 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -348,7 +348,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - xa->zc_alloc->free(xa->zc_alloc, handle); + if (!WARN_ON_ONCE(!xa)) + xa->zc_alloc->free(xa->zc_alloc, handle); rcu_read_unlock(); default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 2589a6b78aa1..a556cd708885 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1786,7 +1786,7 @@ static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, if (itr->app.selector == app->selector && itr->app.protocol == app->protocol && itr->ifindex == ifindex && - (!prio || itr->app.priority == prio)) + ((prio == -1) || itr->app.priority == prio)) return itr; } @@ -1821,7 +1821,8 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) u8 prio = 0; spin_lock_bh(&dcb_lock); - if ((itr = dcb_app_lookup(app, dev->ifindex, 0))) + itr = dcb_app_lookup(app, dev->ifindex, -1); + if (itr) prio = itr->app.priority; spin_unlock_bh(&dcb_lock); @@ -1849,7 +1850,8 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) spin_lock_bh(&dcb_lock); /* Search for existing match and replace */ - if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) { + itr = dcb_app_lookup(new, dev->ifindex, -1); + if (itr) { if (new->priority) itr->app.priority = new->priority; else { @@ -1882,7 +1884,8 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) u8 prio = 0; spin_lock_bh(&dcb_lock); - if ((itr = dcb_app_lookup(app, dev->ifindex, 0))) + itr = dcb_app_lookup(app, dev->ifindex, -1); + if (itr) prio |= 1 << itr->app.priority; spin_unlock_bh(&dcb_lock); @@ -1955,6 +1958,92 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) } EXPORT_SYMBOL(dcb_ieee_delapp); +/** + * 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 + * such that each map element holds a bit mask of DSCP values configured for + * that priority by APP entries. + */ +void dcb_ieee_getapp_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_app_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_ieee_getapp_prio_dscp_mask_map); + +/** + * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from + * DSCP values to the priorities assigned to that DSCP value. Initialize p_map + * such that each map element holds a bit mask of priorities configured for a + * given DSCP value by APP entries. + */ +void +dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, + struct dcb_ieee_app_dscp_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_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) + p_map->map[itr->app.protocol] |= 1 << itr->app.priority; + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map); + +/** + * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet + * type, with valid PID values >= 1536. A special meaning is then assigned to + * protocol value of 0: "default priority. For use when priority is not + * otherwise specified". + * + * dcb_ieee_getapp_default_prio_mask - For a given device, find all APP entries + * of the form {$PRIO, ETHERTYPE, 0} and construct a bit mask of all default + * priorities set by these entries. + */ +u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 mask = 0; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + itr->app.protocol == 0 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) + mask |= 1 << itr->app.priority; + } + spin_unlock_bh(&dcb_lock); + + return mask; +} +EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); + static int __init dcbnl_init(void) { INIT_LIST_HEAD(&dcb_app_list); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 0d56e36a6db7..875858c8b059 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -325,7 +325,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, __poll_t mask; struct sock *sk = sock->sk; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_state == DCCP_LISTEN) return inet_csk_listen_poll(sk); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 71536c435132..1ba3bde96b55 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1248,6 +1248,9 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_detach(slave_dev); rtnl_lock(); @@ -1261,6 +1264,9 @@ int dsa_slave_resume(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_attach(slave_dev); rtnl_lock(); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f2a0a3bab6b5..20fda8fb8ffd 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -486,8 +486,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, * is temporarily down) */ err = -EADDRNOTAVAIL; - if (!net->ipv4.sysctl_ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!inet_can_nonlocal_bind(net, inet) && addr->sin_addr.s_addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && @@ -1802,6 +1801,7 @@ static __net_init int inet_init_net(struct net *net) * We set them here, in case sysctl is not compiled. */ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; + net->ipv4.sysctl_ip_fwd_update_priority = 1; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d7585ab1a77a..ea4bd8a52422 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1827,6 +1827,8 @@ static int inet_netconf_msgsize_devconf(int type) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); + if (all || type == NETCONFA_BC_FORWARDING) + size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) @@ -1873,6 +1875,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; + if ((all || type == NETCONFA_BC_FORWARDING) && + nla_put_s32(skb, NETCONFA_BC_FORWARDING, + IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0) + goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) @@ -2143,6 +2149,10 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); + if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && + new_value != old_value) + rt_cache_flush(net); + if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); @@ -2259,6 +2269,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), + DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index bbeecd13e534..58834a10c0be 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -135,8 +135,7 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb, skb->encap_hdr_csum = 1; - if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle || - (x->xso.dev != skb->dev)) + if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) esp_features = features & ~NETIF_F_CSUM_MASK; @@ -179,8 +178,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ if (!xo) return -EINVAL; - if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle || - (x->xso.dev != skb->dev)) { + if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) { xo->flags |= CRYPTO_FALLBACK; hw_offload = false; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e46cdd310e5f..2998b0e47d4b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -292,19 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); - BUG_ON(!in_dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { + bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), .flowi4_scope = scope, - .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 598333b123b9..cf75f8944b05 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1200,8 +1200,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; - im->sfmode = pmc->sfmode; - if (pmc->sfmode == MCAST_INCLUDE) { + if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; im->sources = pmc->sources; for (psf = im->sources; psf; psf = psf->sf_next) @@ -1388,7 +1387,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ -void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode) +static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode) { struct ip_mc_list *im; #ifdef CONFIG_IP_MULTICAST diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d3162baca9f1..6d258a5669e7 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -137,12 +137,16 @@ void inet_frag_destroy(struct inet_frag_queue *q) fp = q->fragments; nf = q->net; f = nf->f; - while (fp) { - struct sk_buff *xp = fp->next; - - sum_truesize += fp->truesize; - kfree_skb(fp); - fp = xp; + if (fp) { + do { + struct sk_buff *xp = fp->next; + + sum_truesize += fp->truesize; + kfree_skb(fp); + fp = xp; + } while (fp); + } else { + sum_truesize = skb_rbtree_purge(&q->rb_fragments); } sum = sum_truesize + f->qsize; @@ -158,9 +162,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, { struct inet_frag_queue *q; - if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) - return NULL; - q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; @@ -205,6 +206,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { struct inet_frag_queue *fq; + if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) + return NULL; + rcu_read_lock(); fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index b54b948b0596..32662e9e5d21 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -143,7 +143,8 @@ int ip_forward(struct sk_buff *skb) !skb_sec_path(skb)) ip_rt_send_redirect(skb); - skb->priority = rt_tos2priority(iph->tos); + if (net->ipv4.sysctl_ip_fwd_update_priority) + skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, net, NULL, skb, skb->dev, rt->dst.dev, diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8e9528ebaa8e..0e8f8de77e71 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -136,7 +136,7 @@ static void ip_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); const struct iphdr *iph; - struct sk_buff *head; + struct sk_buff *head = NULL; struct net *net; struct ipq *qp; int err; @@ -152,14 +152,31 @@ static void ip_expire(struct timer_list *t) ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); - - head = qp->q.fragments; - __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); - if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head) + if (!qp->q.flags & INET_FRAG_FIRST_IN) goto out; + /* sk_buff::dev and sk_buff::rbnode are unionized. So we + * pull the head out of the tree in order to be able to + * deal with head->dev. + */ + if (qp->q.fragments) { + head = qp->q.fragments; + qp->q.fragments = head->next; + } else { + head = skb_rb_first(&qp->q.rb_fragments); + if (!head) + goto out; + rb_erase(&head->rbnode, &qp->q.rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == qp->q.fragments_tail) + qp->q.fragments_tail = NULL; + + sub_frag_mem_limit(qp->q.net, head->truesize); + head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -179,16 +196,16 @@ static void ip_expire(struct timer_list *t) (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out; - skb_get(head); spin_unlock(&qp->q.lock); icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); - kfree_skb(head); goto out_rcu_unlock; out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); + if (head) + kfree_skb(head); ipq_put(qp); } @@ -231,7 +248,7 @@ static int ip_frag_too_far(struct ipq *qp) end = atomic_inc_return(&peer->rid); qp->rid = end; - rc = qp->q.fragments && (end - start) > max; + rc = qp->q.fragments_tail && (end - start) > max; if (rc) { struct net *net; @@ -245,7 +262,6 @@ static int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { - struct sk_buff *fp; unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { @@ -253,20 +269,14 @@ static int ip_frag_reinit(struct ipq *qp) return -ETIMEDOUT; } - fp = qp->q.fragments; - do { - struct sk_buff *xp = fp->next; - - sum_truesize += fp->truesize; - kfree_skb(fp); - fp = xp; - } while (fp); + sum_truesize = skb_rbtree_purge(&qp->q.rb_fragments); sub_frag_mem_limit(qp->q.net, sum_truesize); qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.fragments = NULL; + qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->iif = 0; qp->ecn = 0; @@ -277,7 +287,9 @@ static int ip_frag_reinit(struct ipq *qp) /* Add new segment to existing queue. */ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { - struct sk_buff *prev, *next; + struct net *net = container_of(qp->q.net, struct net, ipv4.frags); + struct rb_node **rbn, *parent; + struct sk_buff *skb1; struct net_device *dev; unsigned int fragsize; int flags, offset; @@ -340,95 +352,58 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (err) goto err; - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = qp->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = qp->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; + /* Makes sure compiler wont do silly aliasing games */ + barrier(); -found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * We do the same here for IPv4 (and increment an snmp counter). */ - if (prev) { - int i = (prev->ip_defrag_offset + prev->len) - offset; - if (i > 0) { - offset += i; - err = -EINVAL; - if (end <= offset) - goto err; - err = -ENOMEM; - if (!pskb_pull(skb, i)) - goto err; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } - - err = -ENOMEM; - - while (next && next->ip_defrag_offset < end) { - int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */ - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - if (!pskb_pull(next, i)) - goto err; - next->ip_defrag_offset += i; - qp->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragment is completely overridden with - * new one drop it. - */ - next = next->next; - - if (prev) - prev->next = next; - else - qp->q.fragments = next; - - qp->q.meat -= free_it->len; - sub_frag_mem_limit(qp->q.net, free_it->truesize); - kfree_skb(free_it); - } + /* Find out where to put this fragment. */ + skb1 = qp->q.fragments_tail; + if (!skb1) { + /* This is the first fragment we've received. */ + rb_link_node(&skb->rbnode, NULL, &qp->q.rb_fragments.rb_node); + qp->q.fragments_tail = skb; + } else if ((skb1->ip_defrag_offset + skb1->len) < end) { + /* This is the common/special case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < (skb1->ip_defrag_offset + skb1->len)) + goto discard_qp; + /* Insert after skb1. */ + rb_link_node(&skb->rbnode, &skb1->rbnode, &skb1->rbnode.rb_right); + qp->q.fragments_tail = skb; + } else { + /* Binary search. Note that skb can become the first fragment, but + * not the last (covered above). */ + rbn = &qp->q.rb_fragments.rb_node; + do { + parent = *rbn; + skb1 = rb_to_skb(parent); + if (end <= skb1->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= skb1->ip_defrag_offset + skb1->len) + rbn = &parent->rb_right; + else /* Found an overlap with skb1. */ + goto discard_qp; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. */ + rb_link_node(&skb->rbnode, parent, rbn); } + rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - /* Note : skb->ip_defrag_offset and skb->dev share the same location */ - dev = skb->dev; if (dev) qp->iif = dev->ifindex; - /* Makes sure compiler wont do silly aliasing games */ - barrier(); skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - qp->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - qp->q.fragments = skb; - qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; @@ -450,7 +425,7 @@ found: unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - err = ip_frag_reasm(qp, prev, dev); + err = ip_frag_reasm(qp, skb, dev); skb->_skb_refdst = orefdst; return err; } @@ -458,20 +433,24 @@ found: skb_dst_drop(skb); return -EINPROGRESS; +discard_qp: + inet_frag_kill(&qp->q); + err = -EINVAL; + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); err: kfree_skb(skb); return err; } - /* Build a new IP datagram from all its fragments. */ - -static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, +static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct net_device *dev) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = qp->q.fragments; + struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); + struct sk_buff **nextp; /* To build frag_list. */ + struct rb_node *rbn; int len; int ihlen; int err; @@ -485,25 +464,20 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_fail; } /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); if (!fp) goto out_nomem; - - fp->next = head->next; - if (!fp->next) + rb_replace_node(&skb->rbnode, &fp->rbnode, &qp->q.rb_fragments); + if (qp->q.fragments_tail == skb) qp->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, qp->q.fragments); - head->next = qp->q.fragments->next; - - consume_skb(qp->q.fragments); - qp->q.fragments = head; + skb_morph(skb, head); + rb_replace_node(&head->rbnode, &skb->rbnode, + &qp->q.rb_fragments); + consume_skb(head); + head = skb; } - WARN_ON(!head); WARN_ON(head->ip_defrag_offset != 0); /* Allocate a new buffer for the datagram. */ @@ -528,24 +502,35 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) goto out_nomem; - clone->next = head->next; - head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; + skb->truesize += clone->truesize; clone->csum = 0; clone->ip_summed = head->ip_summed; add_frag_mem_limit(qp->q.net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; } - skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - for (fp=head->next; fp; fp = fp->next) { + /* Traverse the tree in order, to build frag_list. */ + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &qp->q.rb_fragments); + while (rbn) { + struct rb_node *rbnext = rb_next(rbn); + fp = rb_to_skb(rbn); + rb_erase(rbn, &qp->q.rb_fragments); + rbn = rbnext; + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) @@ -556,7 +541,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } sub_frag_mem_limit(qp->q.net, head->truesize); + *nextp = NULL; head->next = NULL; + head->prev = NULL; head->dev = dev; head->tstamp = qp->q.stamp; IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); @@ -584,6 +571,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, __IP_INC_STATS(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; + qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; return 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index c8ca5d8f0f75..51a5d06085ac 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -985,7 +985,6 @@ static void ipgre_tunnel_setup(struct net_device *dev) static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; - int t_hlen; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); @@ -993,8 +992,6 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; - t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1304,13 +1301,11 @@ static const struct net_device_ops gre_tap_netdev_ops = { static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - int t_hlen; tunnel->tun_hlen = 8; tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); - t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e2b6bd478afb..9c4e72e9c60a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -524,6 +524,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 64c76dcf7386..c0fe5ad996f2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; const struct iphdr *iph = ip_hdr(skb); - __be16 *ports = (__be16 *)skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 > (int)skb->len) + end = skb_transport_offset(skb) + 4; + if (end > 0 && !pskb_may_pull(skb, end)) return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; sin.sin_addr.s_addr = iph->daddr; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b54c964ad925..8d7aaf118a30 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -320,8 +320,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; - if ((net->ipv4.sysctl_ip_nonlocal_bind == 0 && - isk->freebind == 0 && isk->transparent == 0 && + if ((!inet_can_nonlocal_bind(net, isk) && chk_addr_ret != RTN_LOCAL) || chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) @@ -361,8 +360,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, scoped); rcu_read_unlock(); - if (!(net->ipv6.sysctl.ip_nonlocal_bind || - isk->freebind || isk->transparent || has_addr || + if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index b46e4cf9a55a..70289682a670 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -119,6 +119,7 @@ static const struct snmp_mib snmp4_ipextstats_list[] = { SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS), SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS), SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS), + SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1df6e97106d7..b678466da451 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1996,8 +1996,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto no_route; } - if (res->type == RTN_BROADCAST) + if (res->type == RTN_BROADCAST) { + if (IN_DEV_BFORWARD(in_dev)) + goto make_route; goto brd_input; + } if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, @@ -2014,6 +2017,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res->type != RTN_UNICAST) goto martian_destination; +make_route: err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5fa335fd3852..b92f422f2fa8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -201,6 +201,23 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, return ret; } +static int ipv4_fwd_update_priority(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv4.sysctl_ip_fwd_update_priority); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, + net); + + return ret; +} + static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -664,6 +681,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "ip_forward_update_priority", + .data = &init_net.ipv4.sysctl_ip_fwd_update_priority, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = ipv4_fwd_update_priority, + .extra1 = &zero, + .extra2 = &one, + }, + { .procname = "ip_nonlocal_bind", .data = &init_net.ipv4.sysctl_ip_nonlocal_bind, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 514aaac1626f..b8af2fec5ad5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -507,7 +507,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) const struct tcp_sock *tp = tcp_sk(sk); int state; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) @@ -2531,7 +2531,6 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int err = 0; int old_state = sk->sk_state; if (old_state != TCP_CLOSE) @@ -2594,6 +2593,10 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); tp->compressed_ack = 0; + tp->bytes_sent = 0; + tp->bytes_retrans = 0; + tp->dsack_dups = 0; + tp->reord_seen = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -2608,7 +2611,7 @@ int tcp_disconnect(struct sock *sk, int flags) } sk->sk_error_report(sk); - return err; + return 0; } EXPORT_SYMBOL(tcp_disconnect); @@ -3201,10 +3204,41 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; + info->tcpi_bytes_sent = tp->bytes_sent; + info->tcpi_bytes_retrans = tp->bytes_retrans; + info->tcpi_dsack_dups = tp->dsack_dups; + info->tcpi_reord_seen = tp->reord_seen; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); +static size_t tcp_opt_stats_get_size(void) +{ + return + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */ + nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */ + nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */ + nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ + 0; +} + struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -3213,9 +3247,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) u64 rate64; u32 rate; - stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + - 7 * nla_total_size(sizeof(u32)) + - 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); + stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC); if (!stats) return NULL; @@ -3251,6 +3283,13 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); + nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, + TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, + TCP_NLA_PAD); + nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); + nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); + return stats; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 3b5f45b9e81e..13d34427ca3d 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -358,6 +358,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; + /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ + if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + cwnd += 2; + return cwnd; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 5869f89ca656..8b637f9f23a2 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -129,24 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=0 to CE=1 and delayed - * ACK has not sent yet. - */ - if (!ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (!ca->ce_state) { + /* State has changed from CE=0 to CE=1, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -160,24 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=1 to CE=0 and delayed - * ACK has not sent yet. - */ - if (ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (ca->ce_state) { + /* State has changed from CE=1 to CE=0, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 91dbb9afb950..715d541b52dd 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -216,7 +216,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -224,6 +224,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } +EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. @@ -246,8 +247,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp) static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) { - if (tcp_hdr(skb)->cwr) + if (tcp_hdr(skb)->cwr) { tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + + /* If the sender is telling us it has entered CWR, then its + * cwnd may be very low (even just 1 packet), so we should ACK + * immediately. + */ + tcp_enter_quickack_mode((struct sock *)tp, 2); + } } static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) @@ -873,6 +881,7 @@ static void tcp_dsack_seen(struct tcp_sock *tp) { tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; tp->rack.dsack_seen = 1; + tp->dsack_dups++; } /* It's reordering when higher sequence was delivered (i.e. sacked) before @@ -904,8 +913,8 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, sock_net(sk)->ipv4.sysctl_tcp_max_reordering); } - tp->rack.reord = 1; /* This exciting event is worth to be remembered. 8) */ + tp->reord_seen++; NET_INC_STATS(sock_net(sk), ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER); } @@ -1869,6 +1878,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) tp->reordering = min_t(u32, tp->packets_out + addend, sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } @@ -4366,6 +4376,23 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static bool tcp_ooo_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + bool res = tcp_try_coalesce(sk, to, from, fragstolen); + + /* In case tcp_drop() is called later, update to->gso_segs */ + if (res) { + u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + + max_t(u16, 1, skb_shinfo(from)->gso_segs); + + skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); + } + return res; +} + static void tcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); @@ -4489,8 +4516,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, tp->ooo_last_skb, - skb, &fragstolen)) { + if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, + skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); @@ -4518,7 +4545,7 @@ coalesce_done: /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4537,11 +4564,11 @@ coalesce_done: TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, skb1, - skb, &fragstolen)) { + } else if (tcp_ooo_try_coalesce(sk, skb1, + skb, &fragstolen)) { goto coalesce_done; } p = &parent->rb_right; @@ -4924,6 +4951,7 @@ end: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 range_truesize, sum_tiny = 0; struct sk_buff *skb, *head; u32 start, end; @@ -4935,6 +4963,7 @@ new_range: } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; for (head = skb;;) { skb = skb_rb_next(skb); @@ -4945,11 +4974,20 @@ new_range: if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, NULL, &tp->out_of_order_queue, - head, skb, start, end); + /* Do not attempt collapsing tiny skbs */ + if (range_truesize != head->truesize || + end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + tcp_collapse(sk, NULL, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } goto new_range; } + range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) @@ -4964,6 +5002,7 @@ new_range: * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) + * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ @@ -4971,20 +5010,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_to_skb(node)); - sk_mem_reclaim(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !tcp_under_memory_pressure(sk)) - break; + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } node = prev; } while (node); tp->ooo_last_skb = rb_to_skb(prev); @@ -5019,6 +5064,9 @@ static int tcp_prune_queue(struct sock *sk) else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + return 0; + tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, NULL, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6cbab56e7407..597dbd749f05 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1009,8 +1013,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ -static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, - gfp_t gfp_mask) +static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, + int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; @@ -1086,7 +1090,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); - th->ack_seq = htonl(tp->rcv_nxt); + th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); @@ -1127,11 +1131,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); + tp->bytes_sent += skb->len - tcp_header_size; tcp_internal_pacing(sk, skb); } @@ -1164,6 +1169,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return err; } +static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, + gfp_t gfp_mask) +{ + return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, + tcp_sk(sk)->rcv_nxt); +} + /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, @@ -2686,9 +2698,8 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = skb_rb_next(skb); - int skb_size, next_skb_size; + int next_skb_size; - skb_size = skb->len; next_skb_size = next_skb->len; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); @@ -2859,6 +2870,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans += segs; + tp->bytes_retrans += skb->len; /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom @@ -3557,7 +3569,7 @@ void tcp_send_delayed_ack(struct sock *sk) } /* This routine sends an ack and also updates the window. */ -void tcp_send_ack(struct sock *sk) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; @@ -3590,9 +3602,14 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); +} +EXPORT_SYMBOL_GPL(__tcp_send_ack); + +void tcp_send_ack(struct sock *sk) +{ + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack); /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 71593e4400ab..c81aadff769b 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -25,7 +25,7 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - if (!tp->rack.reord) { + if (!tp->reord_seen) { /* If reordering has not been observed, be aggressive during * the recovery or starting the recovery by DUPACK threshold. */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a242f8874629..7fdf222a0bdf 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,7 +22,7 @@ #include <linux/gfp.h> #include <net/tcp.h> -u32 tcp_retransmit_stamp(const struct sock *sk) +static u32 tcp_retransmit_stamp(const struct sock *sk) { u32 start_ts = tcp_sk(sk)->retrans_stamp; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1659a6b3cf42..2fac4ad74867 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2372,7 +2372,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->fib6_flags & noflags) != 0) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c9535354149f..020f6e14a7af 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -322,8 +322,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; chk_addr_ret = inet_addr_type(net, v4addr); - if (!net->ipv4.sysctl_ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!inet_can_nonlocal_bind(net, inet) && v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && @@ -362,8 +361,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!net->ipv6.sysctl.ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!ipv6_can_nonlocal_bind(net, inet) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 201306b9b5ea..1ede7a16a0be 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports = (__be16 *) skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 <= (int)skb->len) { + end = skb_transport_offset(skb) + 4; + if (end <= 0 || pskb_may_pull(skb, end)) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; @@ -800,7 +803,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; - if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && + if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) && !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, dev, !strict, 0, IFA_F_TENTATIVE) && diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 97513f35bcc5..88a7579c23bd 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -669,8 +669,10 @@ skip_cow: sg_init_table(sg, nfrags); ret = skb_to_sgvec(skb, sg, 0, skb->len); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + kfree(tmp); goto out; + } skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index ddfa533a84e5..6177e2171171 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -162,8 +162,7 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb, skb->encap_hdr_csum = 1; - if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle || - (x->xso.dev != skb->dev)) + if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) esp_features = features & ~NETIF_F_CSUM_MASK; @@ -207,8 +206,7 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features if (!xo) return -EINVAL; - if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle || - (x->xso.dev != skb->dev)) { + if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) { xo->flags |= CRYPTO_FALLBACK; hw_offload = false; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 24611c8b0562..7f6b1f81c200 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -92,7 +92,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct net *net = dev_net(skb->dev); if (type == ICMPV6_PKT_TOOBIG) - ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); + ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); @@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb) /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so - * get the real device index. + * get the real device index. Same is needed for replies to a link + * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX)) { + if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); if (rt6) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8047fd41ba88..16f200f06500 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index b7f28deddaea..c72ae3a4fe09 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -480,10 +480,6 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } - skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); - skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; - mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); @@ -498,9 +494,14 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) htonl(mtu)); } - return -EMSGSIZE; + err = -EMSGSIZE; + goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; + err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 195ed2db2207..4ae54aaca373 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -790,8 +790,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_lock_bh(&im->mca_lock); if (pmc) { im->idev = pmc->idev; - im->mca_sfmode = pmc->mca_sfmode; - if (pmc->mca_sfmode == MCAST_INCLUDE) { + if (im->mca_sfmode == MCAST_INCLUDE) { im->mca_tomb = pmc->mca_tomb; im->mca_sources = pmc->mca_sources; for (psf = im->mca_sources; psf; psf = psf->sf_next) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0610bdab721c..2a14d8b65924 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -463,6 +463,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic head->csum); fq->q.fragments = NULL; + fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; return true; @@ -557,6 +558,10 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); + if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && + fhdr->frag_off & htons(IP6_MF)) + return -EINVAL; + skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 6edd2ac8ae4b..5c5b4f79296e 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -405,6 +405,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); rcu_read_unlock(); fq->q.fragments = NULL; + fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; return 1; @@ -455,6 +456,10 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } + if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && + fhdr->frag_off & htons(IP6_MF)) + goto fail_hdr; + iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2ce0bd17de4f..ec18b3ce8b6d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -972,10 +972,10 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.lastuse = jiffies; } +/* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; - fib6_info_hold(from); rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); if (from->fib6_metrics != &dst_default_metrics) { @@ -984,6 +984,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) } } +/* Caller must already hold reference to @ort */ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) { struct net_device *dev = fib6_info_nh_dev(ort); @@ -1044,9 +1045,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct net_device *dev = rt->fib6_nh.nh_dev; struct rt6_info *nrt; + if (!fib6_info_hold_safe(rt)) + return NULL; + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (nrt) ip6_rt_copy_init(nrt, rt); + else + fib6_info_release(rt); return nrt; } @@ -1178,10 +1184,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, * Clone the route. */ + if (!fib6_info_hold_safe(ort)) + return NULL; + dev = ip6_rt_get_dev_rcu(ort); rt = ip6_dst_alloc(dev_net(dev), dev, 0); - if (!rt) + if (!rt) { + fib6_info_release(ort); return NULL; + } ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; @@ -1210,12 +1221,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) struct net_device *dev; struct rt6_info *pcpu_rt; + if (!fib6_info_hold_safe(rt)) + return NULL; + rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); - if (!pcpu_rt) + if (!pcpu_rt) { + fib6_info_release(rt); return NULL; + } ip6_rt_copy_init(pcpu_rt, rt); pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; @@ -2486,7 +2502,7 @@ restart: out: if (ret) - dst_hold(&ret->dst); + ip6_hold_safe(net, &ret, true); else ret = ip6_create_rt_rcu(rt); @@ -3303,7 +3319,8 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3409,6 +3426,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); + /* This fib6_info_hold() is safe here because we hold reference to rt + * and rt already holds reference to fib6_info. + */ fib6_info_hold(from); rcu_read_unlock(); @@ -3470,7 +3490,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net, continue; if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -3530,8 +3551,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } - if (rt) - fib6_info_hold(rt); + if (rt && !fib6_info_hold_safe(rt)) + rt = NULL; rcu_read_unlock(); return rt; } @@ -3579,8 +3600,8 @@ restart: struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!idev || idev->cnf.accept_ra != 2)) { - fib6_info_hold(rt); + (!idev || idev->cnf.accept_ra != 2) && + fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt); goto restart; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7efa9fd7e109..03e6b7a2bc53 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), tcp_v6_iif(skb), + ntohs(th->source), + tcp_v6_iif_l3_slave(skb), tcp_v6_sdif(skb)); if (!sk1) goto out; @@ -1609,7 +1610,8 @@ do_time_wait: skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), tcp_v6_iif(skb), + ntohs(th->dest), + tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 07d36573f50b..da28e4407b8f 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -55,7 +55,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) __skb_pull(skb, hdr_len); memmove(ipv6_hdr(skb), iph, hdr_len); - x->lastused = get_seconds(); + x->lastused = ktime_get_real_seconds(); return 0; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 8d1c43f8fed4..92ee91e34395 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1494,7 +1494,7 @@ __poll_t iucv_sock_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask = 0; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_state == IUCV_LISTEN) return iucv_accept_poll(sk); diff --git a/net/key/af_key.c b/net/key/af_key.c index 5e1d2946ffbf..9d61266526e7 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1383,7 +1383,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ } if (!x) - x = xfrm_find_acq(net, &dummy_mark, mode, reqid, proto, xdaddr, xsaddr, 1, family); + x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family); if (x == NULL) return -ENOENT; @@ -2414,7 +2414,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2663,7 +2663,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c8fc0f7f0b4b..ac6a00bcec71 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -619,7 +619,7 @@ discard: */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, - int length, int (*payload_hook)(struct sk_buff *skb)) + int length) { struct l2tp_tunnel *tunnel = session->tunnel; int offset; @@ -740,13 +740,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, __skb_pull(skb, offset); - /* If caller wants to process the payload before we queue the - * packet, do so now. - */ - if (payload_hook) - if ((*payload_hook)(skb)) - goto discard; - /* Prepare skb for adding to the session's reorder_q. Hold * packets for max reorder_timeout or 1 second if not * reordering. @@ -800,8 +793,7 @@ static int l2tp_session_queue_purge(struct l2tp_session *session) * Returns 1 if the packet was not a good data packet and could not be * forwarded. All such packets are passed up to userspace to deal with. */ -static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, - int (*payload_hook)(struct sk_buff *skb)) +static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) { struct l2tp_session *session = NULL; unsigned char *ptr, *optr; @@ -892,7 +884,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, goto error; } - l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook); + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); return 0; @@ -921,7 +913,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", tunnel->name, skb->len); - if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) + if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up; return 0; @@ -1682,8 +1674,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn if (cfg) { session->pwtype = cfg->pw_type; session->debug = cfg->debug; - session->mtu = cfg->mtu; - session->mru = cfg->mru; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a5c09d3a5698..5804065dfbfb 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -12,6 +12,9 @@ #ifndef _L2TP_CORE_H_ #define _L2TP_CORE_H_ +#include <net/dst.h> +#include <net/sock.h> + /* Just some random numbers */ #define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D @@ -45,10 +48,6 @@ struct l2tp_tunnel; */ struct l2tp_session_cfg { enum l2tp_pwtype pw_type; - unsigned int data_seq:2; /* data sequencing level - * 0 => none, 1 => IP only, - * 2 => all - */ unsigned int recv_seq:1; /* expect receive packets with * sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence @@ -58,7 +57,6 @@ struct l2tp_session_cfg { * control of LNS. */ int debug; /* bitmask of debug message * categories */ - u16 vlan_id; /* VLAN pseudowire only */ u16 l2specific_type; /* Layer 2 specific type */ u8 cookie[8]; /* optional cookie */ int cookie_len; /* 0, 4 or 8 bytes */ @@ -66,8 +64,6 @@ struct l2tp_session_cfg { int peer_cookie_len; /* 0, 4 or 8 bytes */ int reorder_timeout; /* configured reorder timeout * (in jiffies) */ - int mtu; - int mru; char *ifname; }; @@ -99,10 +95,6 @@ struct l2tp_session { char name[32]; /* for logging */ char ifname[IFNAMSIZ]; - unsigned int data_seq:2; /* data sequencing level - * 0 => none, 1 => IP only, - * 2 => all - */ unsigned int recv_seq:1; /* expect receive packets with * sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence @@ -115,8 +107,6 @@ struct l2tp_session { int reorder_timeout; /* configured reorder timeout * (in jiffies) */ int reorder_skip; /* set if skip to next nr */ - int mtu; - int mru; enum l2tp_pwtype pwtype; struct l2tp_stats stats; struct hlist_node global_hlist; /* Global hash list node */ @@ -180,7 +170,6 @@ struct l2tp_tunnel { struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; - int (*recv_payload_hook)(struct sk_buff *skb); void (*old_sk_destruct)(struct sock *); struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket @@ -232,7 +221,7 @@ int l2tp_session_delete(struct l2tp_session *session); void l2tp_session_free(struct l2tp_session *session); void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, - int length, int (*payload_hook)(struct sk_buff *skb)); + int length); int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); void l2tp_session_set_header_len(struct l2tp_session *session, int version); @@ -280,6 +269,21 @@ static inline int l2tp_get_l2specific_len(struct l2tp_session *session) } } +static inline u32 l2tp_tunnel_dst_mtu(const struct l2tp_tunnel *tunnel) +{ + struct dst_entry *dst; + u32 mtu; + + dst = sk_dst_get(tunnel->sock); + if (!dst) + return 0; + + mtu = dst_mtu(dst); + dst_release(dst); + + return mtu; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b5d7dde003ef..9821a1458555 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -191,12 +191,9 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) if (session->send_seq || session->recv_seq) seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns); seq_printf(m, " refcnt %d\n", refcount_read(&session->ref_count)); - seq_printf(m, " config %d/%d/%c/%c/%s/%s %08x %u\n", - session->mtu, session->mru, + seq_printf(m, " config 0/0/%c/%c/-/%s %08x %u\n", session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', - session->data_seq == 1 ? "IPSEQ" : - session->data_seq == 2 ? "DATASEQ" : "-", session->lns_mode ? "LNS" : "LAC", session->debug, jiffies_to_msecs(session->reorder_timeout)); diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 5c366ecfa1cb..3728986ec885 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -226,22 +226,19 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel, struct net_device *dev) { unsigned int overhead = 0; - struct dst_entry *dst; u32 l3_overhead = 0; + u32 mtu; /* if the encap is UDP, account for UDP header size */ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { overhead += sizeof(struct udphdr); dev->needed_headroom += sizeof(struct udphdr); } - if (session->mtu != 0) { - dev->mtu = session->mtu; - dev->needed_headroom += session->hdr_len; - return; - } + lock_sock(tunnel->sock); l3_overhead = kernel_sock_ip_overhead(tunnel->sock); release_sock(tunnel->sock); + if (l3_overhead == 0) { /* L3 Overhead couldn't be identified, this could be * because tunnel->sock was NULL or the socket's @@ -255,18 +252,12 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel, */ overhead += session->hdr_len + ETH_HLEN + l3_overhead; - /* If PMTU discovery was enabled, use discovered MTU on L2TP device */ - dst = sk_dst_get(tunnel->sock); - if (dst) { - /* dst_mtu will use PMTU if found, else fallback to intf MTU */ - u32 pmtu = dst_mtu(dst); + mtu = l2tp_tunnel_dst_mtu(tunnel) - overhead; + if (mtu < dev->min_mtu || mtu > dev->max_mtu) + dev->mtu = ETH_DATA_LEN - overhead; + else + dev->mtu = mtu; - if (pmtu != 0) - dev->mtu = pmtu; - dst_release(dst); - } - session->mtu = dev->mtu - overhead; - dev->mtu = session->mtu; dev->needed_headroom += session->hdr_len; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index a9c05b2bc1b0..0bc39cc20a3f 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,7 +165,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } - l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook); + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 672e5b753738..42f828cf62fb 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,8 +178,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } - l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, - tunnel->recv_payload_hook); + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 5b9900889e31..2e1e92651545 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -560,9 +560,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf } if (tunnel->version > 2) { - if (info->attrs[L2TP_ATTR_DATA_SEQ]) - cfg.data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]); - if (info->attrs[L2TP_ATTR_L2SPEC_TYPE]) { cfg.l2specific_type = nla_get_u8(info->attrs[L2TP_ATTR_L2SPEC_TYPE]); if (cfg.l2specific_type != L2TP_L2SPECTYPE_DEFAULT && @@ -594,9 +591,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf } if (info->attrs[L2TP_ATTR_IFNAME]) cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); - - if (info->attrs[L2TP_ATTR_VLAN_ID]) - cfg.vlan_id = nla_get_u16(info->attrs[L2TP_ATTR_VLAN_ID]); } if (info->attrs[L2TP_ATTR_DEBUG]) @@ -614,12 +608,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_TIMEOUT]) cfg.reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]); - if (info->attrs[L2TP_ATTR_MTU]) - cfg.mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]); - - if (info->attrs[L2TP_ATTR_MRU]) - cfg.mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]); - #ifdef CONFIG_MODULES if (l2tp_nl_cmd_ops[cfg.pw_type] == NULL) { genl_unlock(); @@ -693,9 +681,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_DEBUG]) session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_DATA_SEQ]) - session->data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -710,12 +695,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_TIMEOUT]) session->reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]); - if (info->attrs[L2TP_ATTR_MTU]) - session->mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]); - - if (info->attrs[L2TP_ATTR_MRU]) - session->mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]); - ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); @@ -745,10 +724,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) || nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || - nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype) || - nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu) || - (session->mru && - nla_put_u16(skb, L2TP_ATTR_MRU, session->mru))) + nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype)) goto nla_put_failure; if ((session->ifname[0] && diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 9ac02c93df98..6e2c8e7595e0 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -93,7 +93,6 @@ #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> -#include <net/dst.h> #include <net/ip.h> #include <net/udp.h> #include <net/xfrm.h> @@ -127,8 +126,6 @@ struct pppol2tp_session { * PPPoX socket */ struct sock *__sk; /* Copy of .sk, for cleanup */ struct rcu_head rcu; /* For asynchronous release */ - int flags; /* accessed by PPPIOCGFLAGS. - * Unused. */ }; static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb); @@ -183,25 +180,6 @@ out: * Receive data handling *****************************************************************************/ -static int pppol2tp_recv_payload_hook(struct sk_buff *skb) -{ - /* Skip PPP header, if present. In testing, Microsoft L2TP clients - * don't send the PPP header (PPP header compression enabled), but - * other clients can include the header. So we cope with both cases - * here. The PPP header is always FF03 when using L2TP. - * - * Note that skb->data[] isn't dereferenced from a u16 ptr here since - * the field may be unaligned. - */ - if (!pskb_may_pull(skb, 2)) - return 1; - - if ((skb->data[0] == PPP_ALLSTATIONS) && (skb->data[1] == PPP_UI)) - skb_pull(skb, 2); - - return 0; -} - /* Receive message. This is the recvmsg for the PPPoL2TP socket. */ static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg, @@ -248,6 +226,17 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk == NULL) goto no_sock; + /* If the first two bytes are 0xFF03, consider that it is the PPP's + * Address and Control fields and skip them. The L2TP module has always + * worked this way, although, in theory, the use of these fields should + * be negociated and handled at the PPP layer. These fields are + * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered + * Information command with Poll/Final bit set to zero (RFC 1662). + */ + if (pskb_may_pull(skb, 2) && skb->data[0] == PPP_ALLSTATIONS && + skb->data[1] == PPP_UI) + skb_pull(skb, 2); + if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; @@ -564,7 +553,6 @@ static void pppol2tp_show(struct seq_file *m, void *arg) static void pppol2tp_session_init(struct l2tp_session *session) { struct pppol2tp_session *ps; - struct dst_entry *dst; session->recv_skb = pppol2tp_recv; #if IS_ENABLED(CONFIG_L2TP_DEBUGFS) @@ -574,18 +562,6 @@ static void pppol2tp_session_init(struct l2tp_session *session) ps = l2tp_session_priv(session); mutex_init(&ps->sk_lock); ps->owner = current->pid; - - /* If PMTU discovery was enabled, use the MTU that was discovered */ - dst = sk_dst_get(session->tunnel->sock); - if (dst) { - u32 pmtu = dst_mtu(dst); - - if (pmtu) { - session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD; - session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; - } - dst_release(dst); - } } struct l2tp_connect_info { @@ -672,6 +648,22 @@ static int pppol2tp_sockaddr_get_info(const void *sa, int sa_len, return 0; } +/* Rough estimation of the maximum payload size a tunnel can transmit without + * fragmenting at the lower IP layer. Assumes L2TPv2 with sequence + * numbers and no IP option. Not quite accurate, but the result is mostly + * unused anyway. + */ +static int pppol2tp_tunnel_mtu(const struct l2tp_tunnel *tunnel) +{ + int mtu; + + mtu = l2tp_tunnel_dst_mtu(tunnel); + if (mtu <= PPPOL2TP_HEADER_OVERHEAD) + return 1500 - PPPOL2TP_HEADER_OVERHEAD; + + return mtu - PPPOL2TP_HEADER_OVERHEAD; +} + /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket */ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, @@ -763,9 +755,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } - if (tunnel->recv_payload_hook == NULL) - tunnel->recv_payload_hook = pppol2tp_recv_payload_hook; - if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = info.peer_tunnel_id; @@ -792,9 +781,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } } else { - /* Default MTU must allow space for UDP/L2TP/PPP headers */ - cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD; - cfg.mru = cfg.mtu; cfg.pw_type = L2TP_PWTYPE_PPP; session = l2tp_session_create(sizeof(struct pppol2tp_session), @@ -839,7 +825,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, po->chan.private = sk; po->chan.ops = &pppol2tp_chan_ops; - po->chan.mtu = session->mtu; + po->chan.mtu = pppol2tp_tunnel_mtu(tunnel); error = ppp_register_net_channel(sock_net(sk), &po->chan); if (error) { @@ -895,12 +881,6 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, goto err; } - /* Default MTU values. */ - if (cfg->mtu == 0) - cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD; - if (cfg->mru == 0) - cfg->mru = cfg->mtu; - /* Allocate and initialize a new session context. */ session = l2tp_session_create(sizeof(struct pppol2tp_session), tunnel, session_id, @@ -1064,11 +1044,9 @@ static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest, static int pppol2tp_session_ioctl(struct l2tp_session *session, unsigned int cmd, unsigned long arg) { - struct ifreq ifr; int err = 0; struct sock *sk; int val = (int) arg; - struct pppol2tp_session *ps = l2tp_session_priv(session); struct l2tp_tunnel *tunnel = session->tunnel; struct pppol2tp_ioc_stats stats; @@ -1081,85 +1059,19 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, return -EBADR; switch (cmd) { - case SIOCGIFMTU: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - err = -EFAULT; - if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq))) - break; - ifr.ifr_mtu = session->mtu; - if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq))) - break; - - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mtu=%d\n", - session->name, session->mtu); - err = 0; - break; - - case SIOCSIFMTU: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - err = -EFAULT; - if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq))) - break; - - session->mtu = ifr.ifr_mtu; - - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mtu=%d\n", - session->name, session->mtu); - err = 0; - break; - case PPPIOCGMRU: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - err = -EFAULT; - if (put_user(session->mru, (int __user *) arg)) - break; - - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mru=%d\n", - session->name, session->mru); - err = 0; - break; - - case PPPIOCSMRU: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - err = -EFAULT; - if (get_user(val, (int __user *) arg)) - break; - - session->mru = val; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mru=%d\n", - session->name, session->mru); - err = 0; - break; - case PPPIOCGFLAGS: err = -EFAULT; - if (put_user(ps->flags, (int __user *) arg)) + if (put_user(0, (int __user *)arg)) break; - - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get flags=%d\n", - session->name, ps->flags); err = 0; break; + case PPPIOCSMRU: case PPPIOCSFLAGS: err = -EFAULT; - if (get_user(val, (int __user *) arg)) + if (get_user(val, (int __user *)arg)) break; - ps->flags = val; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set flags=%d\n", - session->name, ps->flags); err = 0; break; @@ -1227,13 +1139,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, l2tp_session_get(sock_net(sk), tunnel, stats.session_id); - if (session && session->pwtype == L2TP_PWTYPE_PPP) { - err = pppol2tp_session_ioctl(session, cmd, - arg); + if (!session) { + err = -EBADR; + break; + } + if (session->pwtype != L2TP_PWTYPE_PPP) { l2tp_session_dec_refcount(session); - } else { err = -EBADR; + break; } + + err = pppol2tp_session_ioctl(session, cmd, arg); + l2tp_session_dec_refcount(session); break; } #ifdef CONFIG_XFRM @@ -1743,8 +1660,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) tunnel->peer_tunnel_id, session->peer_session_id, state, user_data_ok); - seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n", - session->mtu, session->mru, + seq_printf(m, " 0/0/%c/%c/%s %08x %u\n", session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a16ba568e2a3..64742f2765c4 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2370,11 +2370,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); bool noencrypt = status->flag & RX_FLAG_DECRYPTED; - struct ethhdr *ehdr = eth_hdr(skb); - cfg80211_rx_control_port(dev, skb->data, skb->len, - ehdr->h_source, - be16_to_cpu(skb->protocol), noencrypt); + cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { /* deliver to local stack */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3e68132a41fa..88efda7c9f8a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2140,7 +2140,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!sta->uploaded) continue; - if (sta->sdata->vif.type != NL80211_IFTYPE_AP) + if (sta->sdata->vif.type != NL80211_IFTYPE_AP && + sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN) continue; for (state = IEEE80211_STA_NOTEXIST; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 6f6c959aeb8f..71709c104081 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -46,6 +46,14 @@ config NETFILTER_NETLINK_LOG and is also scheduled to replace the old syslog-based ipt_LOG and ip6t_LOG modules. +config NETFILTER_NETLINK_OSF + tristate "Netfilter OSF over NFNETLINK interface" + depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK + help + If this option is enabled, the kernel will include support + for passive OS fingerprint via NFNETLINK. + config NF_CONNTRACK tristate "Netfilter connection tracking support" default m if NETFILTER_ADVANCED=n @@ -98,7 +106,6 @@ config NF_CONNTRACK_SECMARK config NF_CONNTRACK_ZONES bool 'Connection tracking zones' depends on NETFILTER_ADVANCED - depends on NETFILTER_XT_TARGET_CT help This option enables support for connection tracking zones. Normally, each connection needs to have a unique system wide @@ -150,10 +157,11 @@ config NF_CONNTRACK_TIMESTAMP If unsure, say `N'. config NF_CONNTRACK_LABELS - bool + bool "Connection tracking labels" help This option enables support for assigning user-defined flag bits - to connection tracking entries. It selected by the connlabel match. + to connection tracking entries. It can be used with xtables connlabel + match and the nftables ct expression. config NF_CT_PROTO_DCCP bool 'DCCP protocol connection tracking support' @@ -357,6 +365,7 @@ config NF_CT_NETLINK_TIMEOUT tristate 'Connection tracking timeout tuning via Netlink' select NETFILTER_NETLINK depends on NETFILTER_ADVANCED + depends on NF_CONNTRACK_TIMEOUT help This option enables support for connection tracking timeout fine-grain tuning. This allows you to attach specific timeout @@ -442,9 +451,6 @@ config NETFILTER_SYNPROXY endif # NF_CONNTRACK -config NF_OSF - tristate - config NF_TABLES select NETFILTER_NETLINK tristate "Netfilter nf_tables support" @@ -553,6 +559,12 @@ config NFT_NAT This option adds the "nat" expression that you can use to perform typical Network Address Translation (NAT) packet transformations. +config NFT_TUNNEL + tristate "Netfilter nf_tables tunnel module" + help + This option adds the "tunnel" expression that you can use to set + tunneling policies. + config NFT_OBJREF tristate "Netfilter nf_tables stateful object reference module" help @@ -622,6 +634,23 @@ config NFT_SOCKET This option allows matching for the presence or absence of a corresponding socket and its attributes. +config NFT_OSF + tristate "Netfilter nf_tables passive OS fingerprint support" + depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK_OSF + help + This option allows matching packets from an specific OS. + +config NFT_TPROXY + tristate "Netfilter nf_tables tproxy support" + depends on IPV6 || IPV6=n + select NF_DEFRAG_IPV4 + select NF_DEFRAG_IPV6 if NF_TABLES_IPV6 + select NF_TPROXY_IPV4 + select NF_TPROXY_IPV6 if NF_TABLES_IPV6 + help + This makes transparent proxy support available in nftables. + if NF_TABLES_NETDEV config NF_DUP_NETDEV @@ -1368,8 +1397,8 @@ config NETFILTER_XT_MATCH_NFACCT config NETFILTER_XT_MATCH_OSF tristate '"osf" Passive OS fingerprint match' - depends on NETFILTER_ADVANCED && NETFILTER_NETLINK - select NF_OSF + depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK_OSF help This option selects the Passive OS Fingerprinting match module that allows to passively match the remote operating system by diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index dd26e4961f43..16895e045b66 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o +obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o # connection tracking obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o @@ -100,6 +101,7 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o +obj-$(CONFIG_NFT_TUNNEL) += nft_tunnel.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o @@ -108,8 +110,9 @@ obj-$(CONFIG_NFT_HASH) += nft_hash.o obj-$(CONFIG_NFT_FIB) += nft_fib.o obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o -obj-$(CONFIG_NF_OSF) += nf_osf.o obj-$(CONFIG_NFT_SOCKET) += nft_socket.o +obj-$(CONFIG_NFT_OSF) += nft_osf.o +obj-$(CONFIG_NFT_TPROXY) += nft_tproxy.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index dd21782e2f12..62eefea48973 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -134,7 +134,7 @@ static void update_defense_level(struct netns_ipvs *ipvs) } else { atomic_set(&ipvs->dropentry, 0); ipvs->sysctl_drop_entry = 1; - }; + } break; case 3: atomic_set(&ipvs->dropentry, 1); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8a113ca1eea2..a676d5f76bdc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2022,16 +2022,6 @@ static int kill_all(struct nf_conn *i, void *data) return net_eq(nf_ct_net(i), data); } -void nf_ct_free_hashtable(void *hash, unsigned int size) -{ - if (is_vmalloc_addr(hash)) - vfree(hash); - else - free_pages((unsigned long)hash, - get_order(sizeof(struct hlist_head) * size)); -} -EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); - void nf_conntrack_cleanup_start(void) { conntrack_gc_work.exiting = true; @@ -2042,7 +2032,7 @@ void nf_conntrack_cleanup_end(void) { RCU_INIT_POINTER(nf_ct_hook, NULL); cancel_delayed_work_sync(&conntrack_gc_work.dwork); - nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); + kvfree(nf_conntrack_hash); nf_conntrack_proto_fini(); nf_conntrack_seqadj_fini(); @@ -2108,7 +2098,6 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; unsigned int nr_slots, i; - size_t sz; if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) return NULL; @@ -2116,14 +2105,8 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); - if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head))) - return NULL; - - sz = nr_slots * sizeof(struct hlist_nulls_head); - hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, - get_order(sz)); - if (!hash) - hash = vzalloc(sz); + hash = kvmalloc_array(nr_slots, sizeof(struct hlist_nulls_head), + GFP_KERNEL | __GFP_ZERO); if (hash && nulls) for (i = 0; i < nr_slots; i++) @@ -2150,7 +2133,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize) old_size = nf_conntrack_htable_size; if (old_size == hashsize) { - nf_ct_free_hashtable(hash, hashsize); + kvfree(hash); return 0; } @@ -2186,7 +2169,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize) local_bh_enable(); synchronize_net(); - nf_ct_free_hashtable(old_hash, old_size); + kvfree(old_hash); return 0; } @@ -2350,7 +2333,7 @@ err_acct: err_expect: kmem_cache_destroy(nf_conntrack_cachep); err_cachep: - nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); + kvfree(nf_conntrack_hash); return ret; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 3f586ba23d92..27b84231db10 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -712,5 +712,5 @@ void nf_conntrack_expect_fini(void) { rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); - nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_hsize); + kvfree(nf_ct_expect_hash); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index d557a425289d..e24b762ffa1d 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -562,12 +562,12 @@ int nf_conntrack_helper_init(void) return 0; out_extend: - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); + kvfree(nf_ct_helper_hash); return ret; } void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); + kvfree(nf_ct_helper_hash); } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 803607a90102..30070732ee50 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -940,14 +940,13 @@ void nf_conntrack_proto_fini(void) { unsigned int i; - nf_ct_l4proto_unregister(builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); nf_unregister_sockopt(&so_getorigdst); #if IS_ENABLED(CONFIG_IPV6) nf_unregister_sockopt(&so_getorigdst6); #endif - - /* free l3proto protocol tables */ + /* No need to call nf_ct_l4proto_unregister(), the register + * tables are free'd here anyway. + */ for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) kfree(nf_ct_protos[i]); } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index f476d116c816..8c58f96b59e7 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -244,14 +244,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { @@ -372,14 +372,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6366f0c0b8c1..e2b196054dfc 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1056,7 +1056,7 @@ static int __init nf_nat_init(void) ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + kvfree(nf_nat_bysource); pr_err("Unable to register extension\n"); return ret; } @@ -1094,7 +1094,7 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); synchronize_net(); - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + kvfree(nf_nat_bysource); unregister_pernet_subsys(&nat_net_ops); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c0fb2bcd30fe..67cdd5c4f4f5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -76,6 +76,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, { ctx->net = net; ctx->family = family; + ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; @@ -1441,7 +1442,7 @@ struct nft_chain_hook { static int nft_chain_parse_hook(struct net *net, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, - bool create) + bool autoload) { struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; @@ -1466,7 +1467,7 @@ static int nft_chain_parse_hook(struct net *net, type = chain_type[family][NFT_CHAIN_T_DEFAULT]; if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], - family, create); + family, autoload); if (IS_ERR(type)) return PTR_ERR(type); } @@ -1533,7 +1534,7 @@ static struct nft_rule **nf_tables_chain_alloc_rules(const struct nft_chain *cha } static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, - u8 policy, bool create) + u8 policy) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -1551,7 +1552,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_chain_hook hook; struct nf_hook_ops *ops; - err = nft_chain_parse_hook(net, nla, &hook, family, create); + err = nft_chain_parse_hook(net, nla, &hook, family, true); if (err < 0) return err; @@ -1642,8 +1643,7 @@ err1: return err; } -static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, - bool create) +static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -1651,7 +1651,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_base_chain *basechain; struct nft_stats *stats = NULL; struct nft_chain_hook hook; - const struct nlattr *name; struct nf_hook_ops *ops; struct nft_trans *trans; int err; @@ -1661,7 +1660,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return -EBUSY; err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family, - create); + false); if (err < 0) return err; @@ -1700,12 +1699,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return PTR_ERR(stats); } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); - if (trans == NULL) { - free_percpu(stats); - return -ENOMEM; - } + if (trans == NULL) + goto err; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -1715,19 +1713,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, else nft_trans_chain_policy(trans) = -1; - name = nla[NFTA_CHAIN_NAME]; - if (nla[NFTA_CHAIN_HANDLE] && name) { - nft_trans_chain_name(trans) = - nla_strdup(name, GFP_KERNEL); - if (!nft_trans_chain_name(trans)) { - kfree(trans); - free_percpu(stats); - return -ENOMEM; + if (nla[NFTA_CHAIN_HANDLE] && + nla[NFTA_CHAIN_NAME]) { + struct nft_trans *tmp; + char *name; + + err = -ENOMEM; + name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + if (!name) + goto err; + + err = -EEXIST; + list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + if (tmp->msg_type == NFT_MSG_NEWCHAIN && + tmp->ctx.table == table && + nft_trans_chain_update(tmp) && + nft_trans_chain_name(tmp) && + strcmp(name, nft_trans_chain_name(tmp)) == 0) { + kfree(name); + goto err; + } } + + nft_trans_chain_name(trans) = name; } list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; +err: + free_percpu(stats); + kfree(trans); + return err; } static int nf_tables_newchain(struct net *net, struct sock *nlsk, @@ -1744,9 +1760,6 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, u8 policy = NF_ACCEPT; struct nft_ctx ctx; u64 handle = 0; - bool create; - - create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; lockdep_assert_held(&net->nft.commit_mutex); @@ -1811,10 +1824,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - return nf_tables_updchain(&ctx, genmask, policy, create); + return nf_tables_updchain(&ctx, genmask, policy); } - return nf_tables_addchain(&ctx, family, genmask, policy, create); + return nf_tables_addchain(&ctx, family, genmask, policy); } static int nf_tables_delchain(struct net *net, struct sock *nlsk, @@ -2309,6 +2322,39 @@ done: return skb->len; } +static int nf_tables_dump_rules_start(struct netlink_callback *cb) +{ + const struct nlattr * const *nla = cb->data; + struct nft_rule_dump_ctx *ctx = NULL; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], + GFP_ATOMIC); + if (!ctx->table) { + kfree(ctx); + return -ENOMEM; + } + } + if (nla[NFTA_RULE_CHAIN]) { + ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], + GFP_ATOMIC); + if (!ctx->chain) { + kfree(ctx->table); + kfree(ctx); + return -ENOMEM; + } + } + } + + cb->data = ctx; + return 0; +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = cb->data; @@ -2338,38 +2384,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { - struct nft_rule_dump_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); - if (!ctx) - return -ENOMEM; - - if (nla[NFTA_RULE_TABLE]) { - ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], - GFP_ATOMIC); - if (!ctx->table) { - kfree(ctx); - return -ENOMEM; - } - } - if (nla[NFTA_RULE_CHAIN]) { - ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], - GFP_ATOMIC); - if (!ctx->chain) { - kfree(ctx->table); - kfree(ctx); - return -ENOMEM; - } - } - c.data = ctx; - } - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -2440,6 +2461,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) struct nft_rule *rule; int err; + if (ctx->level == NFT_JUMP_STACK_SIZE) + return -EMLINK; + list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; @@ -2501,13 +2525,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, struct nlattr *tmp; unsigned int size, i, n, ulen = 0, usize = 0; int err, rem; - bool create; u64 handle, pos_handle; lockdep_assert_held(&net->nft.commit_mutex); - create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); @@ -2537,7 +2558,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, else return -EOPNOTSUPP; } else { - if (!create || nlh->nlmsg_flags & NLM_F_REPLACE) + if (!(nlh->nlmsg_flags & NLM_F_CREATE) || + nlh->nlmsg_flags & NLM_F_REPLACE) return -EINVAL; handle = nf_tables_alloc_handle(table); @@ -3227,6 +3249,18 @@ done: return skb->len; } +static int nf_tables_dump_sets_start(struct netlink_callback *cb) +{ + struct nft_ctx *ctx_dump = NULL; + + ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); + if (ctx_dump == NULL) + return -ENOMEM; + + cb->data = ctx_dump; + return 0; +} + static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); @@ -3254,18 +3288,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, + .data = &ctx, .module = THIS_MODULE, }; - struct nft_ctx *ctx_dump; - - ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC); - if (ctx_dump == NULL) - return -ENOMEM; - - *ctx_dump = ctx; - c.data = ctx_dump; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -3327,7 +3355,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, struct nft_ctx ctx; char *name; unsigned int size; - bool create; u64 timeout; u32 ktype, dtype, flags, policy, gc_int, objtype; struct nft_set_desc desc; @@ -3428,8 +3455,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, return err; } - create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); @@ -3915,6 +3940,15 @@ nla_put_failure: return -ENOSPC; } +static int nf_tables_dump_set_start(struct netlink_callback *cb) +{ + struct nft_set_dump_ctx *dump_ctx = cb->data; + + cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); + + return cb->data ? 0 : -ENOMEM; +} + static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); @@ -3986,7 +4020,6 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; - const struct nft_set_ext *ext; struct nft_data_desc desc; struct nft_set_elem elem; struct sk_buff *skb; @@ -4020,7 +4053,6 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return PTR_ERR(priv); elem.priv = priv; - ext = nft_set_elem_ext(set, &elem); err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); @@ -4068,20 +4100,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; - struct nft_set_dump_ctx *dump_ctx; - - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC); - if (!dump_ctx) - return -ENOMEM; - - dump_ctx->set = set; - dump_ctx->ctx = ctx; + struct nft_set_dump_ctx dump_ctx = { + .set = set, + .ctx = ctx, + }; - c.data = dump_ctx; + c.data = &dump_ctx; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5041,38 +5070,42 @@ done: return skb->len; } -static int nf_tables_dump_obj_done(struct netlink_callback *cb) +static int nf_tables_dump_obj_start(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_obj_filter *filter = NULL; - if (filter) { - kfree(filter->table); - kfree(filter); + if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; + + if (nla[NFTA_OBJ_TABLE]) { + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + + if (nla[NFTA_OBJ_TYPE]) + filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); } + cb->data = filter; return 0; } -static struct nft_obj_filter * -nft_obj_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter; - - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) - return ERR_PTR(-ENOMEM); + struct nft_obj_filter *filter = cb->data; - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } + if (filter) { + kfree(filter->table); + kfree(filter); } - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - return filter; + return 0; } /* called with rcu_read_lock held */ @@ -5093,21 +5126,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_OBJ_TABLE] || - nla[NFTA_OBJ_TYPE]) { - struct nft_obj_filter *filter; - - filter = nft_obj_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5386,8 +5411,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; - flowtable->dev_name[i] = kstrdup(dev_array[i]->name, - GFP_KERNEL); } return err; @@ -5545,10 +5568,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, err6: i = flowtable->ops_len; err5: - for (k = i - 1; k >= 0; k--) { - kfree(flowtable->dev_name[k]); + for (k = i - 1; k >= 0; k--) nf_unregister_net_hook(net, &flowtable->ops[k]); - } kfree(flowtable->ops); err4: @@ -5647,9 +5668,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; for (i = 0; i < flowtable->ops_len; i++) { - if (flowtable->dev_name[i][0] && - nla_put_string(skb, NFTA_DEVICE_NAME, - flowtable->dev_name[i])) + const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev); + + if (dev && + nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -5716,37 +5738,39 @@ done: return skb->len; } -static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) +static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_flowtable_filter *filter = NULL; - if (!filter) - return 0; + if (nla[NFTA_FLOWTABLE_TABLE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; - kfree(filter->table); - kfree(filter); + filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], + GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + cb->data = filter; return 0; } -static struct nft_flowtable_filter * -nft_flowtable_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter; + struct nft_flowtable_filter *filter = cb->data; - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) - return ERR_PTR(-ENOMEM); + return 0; - if (nla[NFTA_FLOWTABLE_TABLE]) { - filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], - GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } - } - return filter; + kfree(filter->table); + kfree(filter); + + return 0; } /* called with rcu_read_lock held */ @@ -5766,20 +5790,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_FLOWTABLE_TABLE]) { - struct nft_flowtable_filter *filter; - - filter = nft_flowtable_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5849,6 +5866,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); + kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, @@ -5891,7 +5909,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev, continue; nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]); - flowtable->dev_name[i][0] = '\0'; flowtable->ops[i].dev = NULL; break; } @@ -5912,13 +5929,13 @@ static int nf_tables_flowtable_event(struct notifier_block *this, if (!net) return 0; - nfnl_lock(NFNL_SUBSYS_NFTABLES); + mutex_lock(&net->nft.commit_mutex); list_for_each_entry(table, &net->nft.tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } - nfnl_unlock(NFNL_SUBSYS_NFTABLES); + mutex_unlock(&net->nft.commit_mutex); put_net(net); return NOTIFY_DONE; } @@ -6152,6 +6169,9 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DELTABLE: nf_tables_table_destroy(&trans->ctx); break; + case NFT_MSG_NEWCHAIN: + kfree(nft_trans_chain_name(trans)); + break; case NFT_MSG_DELCHAIN: nf_tables_chain_destroy(&trans->ctx); break; @@ -6381,13 +6401,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); break; case NFT_MSG_NEWCHAIN: - if (nft_trans_chain_update(trans)) + if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); - else + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + /* trans destroyed after rcu grace period */ + } else { nft_clear(net, trans->ctx.chain); - - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); - nft_trans_destroy(trans); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nft_trans_destroy(trans); + } break; case NFT_MSG_DELCHAIN: nft_chain_del(trans->ctx.chain); @@ -6538,7 +6560,7 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { free_percpu(nft_trans_chain_stats(trans)); - + kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -6918,13 +6940,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx, err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; - - if (ctx->chain->level + 1 > - data->verdict.chain->level) { - if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE) - return -EMLINK; - data->verdict.chain->level = ctx->chain->level + 1; - } } return 0; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 8de912ca53d3..ffd5c0f9412b 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -120,6 +120,20 @@ struct nft_jumpstack { struct nft_rule *const *rules; }; +static void expr_call_ops_eval(const struct nft_expr *expr, + struct nft_regs *regs, + struct nft_pktinfo *pkt) +{ + unsigned long e = (unsigned long)expr->ops->eval; + + if (e == (unsigned long)nft_meta_get_eval) + nft_meta_get_eval(expr, regs, pkt); + else if (e == (unsigned long)nft_lookup_eval) + nft_lookup_eval(expr, regs, pkt); + else + expr->ops->eval(expr, regs, pkt); +} + unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv) { @@ -153,7 +167,7 @@ next_rule: nft_cmp_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || !nft_payload_fast_eval(expr, ®s, pkt)) - expr->ops->eval(expr, ®s, pkt); + expr_call_ops_eval(expr, ®s, pkt); if (regs.verdict.code != NFT_CONTINUE) break; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index d9d952fad3e0..4199e5300575 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -503,7 +503,6 @@ err: return err; } -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT static struct ctnl_timeout * ctnl_timeout_find_get(struct net *net, const char *name) { @@ -534,7 +533,6 @@ static void ctnl_timeout_put(struct ctnl_timeout *timeout) module_put(THIS_MODULE); } -#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = { [IPCTNL_MSG_TIMEOUT_NEW] = { .call = cttimeout_new_timeout, @@ -605,10 +603,8 @@ static int __init cttimeout_init(void) "nfnetlink.\n"); goto err_out; } -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, ctnl_timeout_find_get); RCU_INIT_POINTER(nf_ct_timeout_put_hook, ctnl_timeout_put); -#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ return 0; err_out: @@ -621,11 +617,9 @@ static void __exit cttimeout_exit(void) nfnetlink_subsys_unregister(&cttimeout_subsys); unregister_pernet_subsys(&cttimeout_ops); -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL); RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL); synchronize_rcu(); -#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ } module_init(cttimeout_init); diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nfnetlink_osf.c index b44d62d5d9a9..f9dba62c450f 100644 --- a/net/netfilter/nf_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -18,7 +18,14 @@ #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> -#include <linux/netfilter/nf_osf.h> +#include <linux/netfilter/nfnetlink_osf.h> + +/* + * Indexed by dont-fragment bit. + * It is the only constant value in the fingerprint. + */ +struct list_head nf_osf_fingers[2]; +EXPORT_SYMBOL_GPL(nf_osf_fingers); static inline int nf_osf_ttl(const struct sk_buff *skb, int ttl_check, unsigned char f_ttl) @@ -249,4 +256,181 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, } EXPORT_SYMBOL_GPL(nf_osf_match); +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers) +{ + const struct iphdr *ip = ip_hdr(skb); + const struct nf_osf_user_finger *f; + unsigned char opts[MAX_IPOPTLEN]; + const struct nf_osf_finger *kf; + struct nf_osf_hdr_ctx ctx; + const struct tcphdr *tcp; + const char *genre = NULL; + + memset(&ctx, 0, sizeof(ctx)); + + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + if (!tcp) + return false; + + list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { + f = &kf->finger; + if (!nf_osf_match_one(skb, f, -1, &ctx)) + continue; + + genre = f->genre; + break; + } + + return genre; +} +EXPORT_SYMBOL_GPL(nf_osf_find); + +static const struct nla_policy nfnl_osf_policy[OSF_ATTR_MAX + 1] = { + [OSF_ATTR_FINGER] = { .len = sizeof(struct nf_osf_user_finger) }, +}; + +static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) +{ + struct nf_osf_user_finger *f; + struct nf_osf_finger *kf = NULL, *sf; + int err = 0; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!osf_attrs[OSF_ATTR_FINGER]) + return -EINVAL; + + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + return -EINVAL; + + f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + + kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL); + if (!kf) + return -ENOMEM; + + memcpy(&kf->finger, f, sizeof(struct nf_osf_user_finger)); + + list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) { + if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger))) + continue; + + kfree(kf); + kf = NULL; + + if (nlh->nlmsg_flags & NLM_F_EXCL) + err = -EEXIST; + break; + } + + /* + * We are protected by nfnl mutex. + */ + if (kf) + list_add_tail_rcu(&kf->finger_entry, &nf_osf_fingers[!!f->df]); + + return err; +} + +static int nfnl_osf_remove_callback(struct net *net, struct sock *ctnl, + struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) +{ + struct nf_osf_user_finger *f; + struct nf_osf_finger *sf; + int err = -ENOENT; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!osf_attrs[OSF_ATTR_FINGER]) + return -EINVAL; + + f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + + list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) { + if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger))) + continue; + + /* + * We are protected by nfnl mutex. + */ + list_del_rcu(&sf->finger_entry); + kfree_rcu(sf, rcu_head); + + err = 0; + break; + } + + return err; +} + +static const struct nfnl_callback nfnl_osf_callbacks[OSF_MSG_MAX] = { + [OSF_MSG_ADD] = { + .call = nfnl_osf_add_callback, + .attr_count = OSF_ATTR_MAX, + .policy = nfnl_osf_policy, + }, + [OSF_MSG_REMOVE] = { + .call = nfnl_osf_remove_callback, + .attr_count = OSF_ATTR_MAX, + .policy = nfnl_osf_policy, + }, +}; + +static const struct nfnetlink_subsystem nfnl_osf_subsys = { + .name = "osf", + .subsys_id = NFNL_SUBSYS_OSF, + .cb_count = OSF_MSG_MAX, + .cb = nfnl_osf_callbacks, +}; + +static int __init nfnl_osf_init(void) +{ + int err = -EINVAL; + int i; + + for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) + INIT_LIST_HEAD(&nf_osf_fingers[i]); + + err = nfnetlink_subsys_register(&nfnl_osf_subsys); + if (err < 0) { + pr_err("Failed to register OSF nsfnetlink helper (%d)\n", err); + goto err_out_exit; + } + return 0; + +err_out_exit: + return err; +} + +static void __exit nfnl_osf_fini(void) +{ + struct nf_osf_finger *f; + int i; + + nfnetlink_subsys_unregister(&nfnl_osf_subsys); + + rcu_read_lock(); + for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) { + list_for_each_entry_rcu(f, &nf_osf_fingers[i], finger_entry) { + list_del_rcu(&f->finger_entry); + kfree_rcu(f, rcu_head); + } + } + rcu_read_unlock(); + + rcu_barrier(); +} + +module_init(nfnl_osf_init); +module_exit(nfnl_osf_fini); + MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 15adf8ca82c3..0777a93211e2 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_data **d) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: + pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; + pctx->level--; break; default: break; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 42e6fadf1417..ad13e8643599 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -26,9 +26,9 @@ struct nft_lookup { struct nft_set_binding binding; }; -static void nft_lookup_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_lookup_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; @@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; + int err; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) @@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - return nft_chain_validate(ctx, data->verdict.chain); + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; default: - return 0; + break; } + + return 0; } static int nft_lookup_validate(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 2b94dcc43456..297fe7d97c18 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -41,9 +41,9 @@ static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); #include "../bridge/br_private.h" #endif -static void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 1f4d0854cf70..649d1700ec5b 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -237,10 +237,8 @@ static int nft_ng_random_map_init(const struct nft_ctx *ctx, priv->map = nft_set_lookup_global(ctx->net, ctx->table, tb[NFTA_NG_SET_NAME], tb[NFTA_NG_SET_ID], genmask); - if (IS_ERR(priv->map)) - return PTR_ERR(priv->map); - return 0; + return PTR_ERR_OR_ZERO(priv->map); } static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c new file mode 100644 index 000000000000..9b2f3de7be4f --- /dev/null +++ b/net/netfilter/nft_osf.c @@ -0,0 +1,106 @@ +#include <net/ip.h> +#include <net/tcp.h> + +#include <net/netfilter/nf_tables.h> +#include <linux/netfilter/nfnetlink_osf.h> + +#define OSF_GENRE_SIZE 32 + +struct nft_osf { + enum nft_registers dreg:8; +}; + +static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = { + [NFTA_OSF_DREG] = { .type = NLA_U32 }, +}; + +static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_osf *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + struct sk_buff *skb = pkt->skb; + const struct tcphdr *tcp; + struct tcphdr _tcph; + const char *os_name; + + tcp = skb_header_pointer(skb, ip_hdrlen(skb), + sizeof(struct tcphdr), &_tcph); + if (!tcp) { + regs->verdict.code = NFT_BREAK; + return; + } + if (!tcp->syn) { + regs->verdict.code = NFT_BREAK; + return; + } + + os_name = nf_osf_find(skb, nf_osf_fingers); + if (!os_name) + strncpy((char *)dest, "unknown", IFNAMSIZ); + else + strncpy((char *)dest, os_name, IFNAMSIZ); +} + +static int nft_osf_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_osf *priv = nft_expr_priv(expr); + int err; + + priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFTA_DATA_VALUE, OSF_GENRE_SIZE); + if (err < 0) + return err; + + return 0; +} + +static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_osf *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_osf_type; +static const struct nft_expr_ops nft_osf_op = { + .eval = nft_osf_eval, + .size = NFT_EXPR_SIZE(sizeof(struct nft_osf)), + .init = nft_osf_init, + .dump = nft_osf_dump, + .type = &nft_osf_type, +}; + +static struct nft_expr_type nft_osf_type __read_mostly = { + .ops = &nft_osf_op, + .name = "osf", + .owner = THIS_MODULE, + .policy = nft_osf_policy, + .maxattr = NFTA_OSF_MAX, +}; + +static int __init nft_osf_module_init(void) +{ + return nft_register_expr(&nft_osf_type); +} + +static void __exit nft_osf_module_exit(void) +{ + return nft_unregister_expr(&nft_osf_type); +} + +module_init(nft_osf_module_init); +module_exit(nft_osf_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); +MODULE_ALIAS_NFT_EXPR("osf"); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 72ef35b51cac..90c3e7e6cacb 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set) struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 1f8f257cb518..9873d734b494 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) - goto out; + break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); @@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(prev, struct nft_rbtree_elem, node); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + prev = NULL; } node = rb_next(node); + if (!node) + break; } -out: if (gcb) { for (i = 0; i < gcb->head.cnt; i++) { rbe = gcb->elems[i]; @@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) struct rb_node *node; cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c new file mode 100644 index 000000000000..eff99dffc842 --- /dev/null +++ b/net/netfilter/nft_tproxy.c @@ -0,0 +1,316 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/module.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_tproxy.h> +#include <net/inet_sock.h> +#include <net/tcp.h> +#include <linux/if_ether.h> +#include <net/netfilter/ipv4/nf_defrag_ipv4.h> +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#endif + +struct nft_tproxy { + enum nft_registers sreg_addr:8; + enum nft_registers sreg_port:8; + u8 family; +}; + +static void nft_tproxy_eval_v4(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + const struct iphdr *iph = ip_hdr(skb); + struct udphdr _hdr, *hp; + __be32 taddr = 0; + __be16 tport = 0; + struct sock *sk; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); + if (!hp) { + regs->verdict.code = NFT_BREAK; + return; + } + + /* check if there's an ongoing connection on the packet addresses, this + * happens if the redirect already happened and the current packet + * belongs to an already established connection + */ + sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol, + iph->saddr, iph->daddr, + hp->source, hp->dest, + skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); + + if (priv->sreg_addr) + taddr = regs->data[priv->sreg_addr]; + taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr); + + if (priv->sreg_port) + tport = regs->data[priv->sreg_port]; + if (!tport) + tport = hp->dest; + + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ + if (sk && sk->sk_state == TCP_TIME_WAIT) { + /* reopening a TIME_WAIT connection needs special handling */ + sk = nf_tproxy_handle_time_wait4(nft_net(pkt), skb, taddr, tport, sk); + } else if (!sk) { + /* no, there's no established connection, check if + * there's a listener on the redirected addr/port + */ + sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol, + iph->saddr, taddr, + hp->source, tport, + skb->dev, NF_TPROXY_LOOKUP_LISTENER); + } + + if (sk && nf_tproxy_sk_is_transparent(sk)) + nf_tproxy_assign_sock(skb, sk); + else + regs->verdict.code = NFT_BREAK; +} + +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) +static void nft_tproxy_eval_v6(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct in6_addr taddr = {0}; + int thoff = pkt->xt.thoff; + struct udphdr _hdr, *hp; + __be16 tport = 0; + struct sock *sk; + int l4proto; + + if (!pkt->tprot_set) { + regs->verdict.code = NFT_BREAK; + return; + } + l4proto = pkt->tprot; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + regs->verdict.code = NFT_BREAK; + return; + } + + /* check if there's an ongoing connection on the packet addresses, this + * happens if the redirect already happened and the current packet + * belongs to an already established connection + */ + sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff, l4proto, + &iph->saddr, &iph->daddr, + hp->source, hp->dest, + nft_in(pkt), NF_TPROXY_LOOKUP_ESTABLISHED); + + if (priv->sreg_addr) + memcpy(&taddr, ®s->data[priv->sreg_addr], sizeof(taddr)); + taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr); + + if (priv->sreg_port) + tport = regs->data[priv->sreg_port]; + if (!tport) + tport = hp->dest; + + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ + if (sk && sk->sk_state == TCP_TIME_WAIT) { + /* reopening a TIME_WAIT connection needs special handling */ + sk = nf_tproxy_handle_time_wait6(skb, l4proto, thoff, + nft_net(pkt), + &taddr, + tport, + sk); + } else if (!sk) { + /* no there's no established connection, check if + * there's a listener on the redirected addr/port + */ + sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff, + l4proto, &iph->saddr, &taddr, + hp->source, tport, + nft_in(pkt), NF_TPROXY_LOOKUP_LISTENER); + } + + /* NOTE: assign_sock consumes our sk reference */ + if (sk && nf_tproxy_sk_is_transparent(sk)) + nf_tproxy_assign_sock(skb, sk); + else + regs->verdict.code = NFT_BREAK; +} +#endif + +static void nft_tproxy_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + switch (priv->family) { + case NFPROTO_IPV4: + case NFPROTO_UNSPEC: + nft_tproxy_eval_v4(expr, regs, pkt); + return; + } + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + switch (priv->family) { + case NFPROTO_IPV6: + case NFPROTO_UNSPEC: + nft_tproxy_eval_v6(expr, regs, pkt); + return; + } +#endif + } + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_tproxy_policy[NFTA_TPROXY_MAX + 1] = { + [NFTA_TPROXY_FAMILY] = { .type = NLA_U32 }, + [NFTA_TPROXY_REG_ADDR] = { .type = NLA_U32 }, + [NFTA_TPROXY_REG_PORT] = { .type = NLA_U32 }, +}; + +static int nft_tproxy_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_tproxy *priv = nft_expr_priv(expr); + unsigned int alen = 0; + int err; + + if (!tb[NFTA_TPROXY_FAMILY] || + (!tb[NFTA_TPROXY_REG_ADDR] && !tb[NFTA_TPROXY_REG_PORT])) + return -EINVAL; + + priv->family = ntohl(nla_get_be32(tb[NFTA_TPROXY_FAMILY])); + + switch (ctx->family) { + case NFPROTO_IPV4: + if (priv->family != NFPROTO_IPV4) + return -EINVAL; + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + if (priv->family != NFPROTO_IPV6) + return -EINVAL; + break; +#endif + case NFPROTO_INET: + break; + default: + return -EOPNOTSUPP; + } + + /* Address is specified but the rule family is not set accordingly */ + if (priv->family == NFPROTO_UNSPEC && tb[NFTA_TPROXY_REG_ADDR]) + return -EINVAL; + + switch (priv->family) { + case NFPROTO_IPV4: + alen = FIELD_SIZEOF(union nf_inet_addr, in); + err = nf_defrag_ipv4_enable(ctx->net); + if (err) + return err; + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + alen = FIELD_SIZEOF(union nf_inet_addr, in6); + err = nf_defrag_ipv6_enable(ctx->net); + if (err) + return err; + break; +#endif + case NFPROTO_UNSPEC: + /* No address is specified here */ + err = nf_defrag_ipv4_enable(ctx->net); + if (err) + return err; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + err = nf_defrag_ipv6_enable(ctx->net); + if (err) + return err; +#endif + break; + default: + return -EOPNOTSUPP; + } + + if (tb[NFTA_TPROXY_REG_ADDR]) { + priv->sreg_addr = nft_parse_register(tb[NFTA_TPROXY_REG_ADDR]); + err = nft_validate_register_load(priv->sreg_addr, alen); + if (err < 0) + return err; + } + + if (tb[NFTA_TPROXY_REG_PORT]) { + priv->sreg_port = nft_parse_register(tb[NFTA_TPROXY_REG_PORT]); + err = nft_validate_register_load(priv->sreg_port, sizeof(u16)); + if (err < 0) + return err; + } + + return 0; +} + +static int nft_tproxy_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_TPROXY_FAMILY, htonl(priv->family))) + return -1; + + if (priv->sreg_addr && + nft_dump_register(skb, NFTA_TPROXY_REG_ADDR, priv->sreg_addr)) + return -1; + + if (priv->sreg_port && + nft_dump_register(skb, NFTA_TPROXY_REG_PORT, priv->sreg_port)) + return -1; + + return 0; +} + +static struct nft_expr_type nft_tproxy_type; +static const struct nft_expr_ops nft_tproxy_ops = { + .type = &nft_tproxy_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_tproxy)), + .eval = nft_tproxy_eval, + .init = nft_tproxy_init, + .dump = nft_tproxy_dump, +}; + +static struct nft_expr_type nft_tproxy_type __read_mostly = { + .name = "tproxy", + .ops = &nft_tproxy_ops, + .policy = nft_tproxy_policy, + .maxattr = NFTA_TPROXY_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_tproxy_module_init(void) +{ + return nft_register_expr(&nft_tproxy_type); +} + +static void __exit nft_tproxy_module_exit(void) +{ + nft_unregister_expr(&nft_tproxy_type); +} + +module_init(nft_tproxy_module_init); +module_exit(nft_tproxy_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Máté Eckl"); +MODULE_DESCRIPTION("nf_tables tproxy support module"); +MODULE_ALIAS_NFT_EXPR("tproxy"); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c new file mode 100644 index 000000000000..3a15f219e4e7 --- /dev/null +++ b/net/netfilter/nft_tunnel.c @@ -0,0 +1,566 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/seqlock.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/dst_metadata.h> +#include <net/ip_tunnels.h> +#include <net/vxlan.h> +#include <net/erspan.h> + +struct nft_tunnel { + enum nft_tunnel_keys key:8; + enum nft_registers dreg:8; +}; + +static void nft_tunnel_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + struct ip_tunnel_info *tun_info; + + tun_info = skb_tunnel_info(pkt->skb); + + switch (priv->key) { + case NFT_TUNNEL_PATH: + nft_reg_store8(dest, !!tun_info); + break; + case NFT_TUNNEL_ID: + if (!tun_info) { + regs->verdict.code = NFT_BREAK; + return; + } + *dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id)); + break; + default: + WARN_ON(1); + regs->verdict.code = NFT_BREAK; + } +} + +static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = { + [NFTA_TUNNEL_KEY] = { .type = NLA_U32 }, + [NFTA_TUNNEL_DREG] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_tunnel *priv = nft_expr_priv(expr); + u32 len; + + if (!tb[NFTA_TUNNEL_KEY] && + !tb[NFTA_TUNNEL_DREG]) + return -EINVAL; + + priv->key = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY])); + switch (priv->key) { + case NFT_TUNNEL_PATH: + len = sizeof(u8); + break; + case NFT_TUNNEL_ID: + len = sizeof(u32); + break; + default: + return -EOPNOTSUPP; + } + + priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]); + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); +} + +static int nft_tunnel_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY, htonl(priv->key))) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_TUNNEL_DREG, priv->dreg)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_tunnel_type; +static const struct nft_expr_ops nft_tunnel_get_ops = { + .type = &nft_tunnel_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_tunnel)), + .eval = nft_tunnel_get_eval, + .init = nft_tunnel_get_init, + .dump = nft_tunnel_get_dump, +}; + +static struct nft_expr_type nft_tunnel_type __read_mostly = { + .name = "tunnel", + .ops = &nft_tunnel_get_ops, + .policy = nft_tunnel_policy, + .maxattr = NFTA_TUNNEL_MAX, + .owner = THIS_MODULE, +}; + +struct nft_tunnel_opts { + union { + struct vxlan_metadata vxlan; + struct erspan_metadata erspan; + } u; + u32 len; + __be16 flags; +}; + +struct nft_tunnel_obj { + struct metadata_dst *md; + struct nft_tunnel_opts opts; +}; + +static const struct nla_policy nft_tunnel_ip_policy[NFTA_TUNNEL_KEY_IP_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP_SRC] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_IP_DST] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_obj_ip_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_IP_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP_MAX, attr, + nft_tunnel_ip_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_IP_DST]) + return -EINVAL; + + if (tb[NFTA_TUNNEL_KEY_IP_SRC]) + info->key.u.ipv4.src = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_SRC]); + if (tb[NFTA_TUNNEL_KEY_IP_DST]) + info->key.u.ipv4.dst = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_DST]); + + return 0; +} + +static const struct nla_policy nft_tunnel_ip6_policy[NFTA_TUNNEL_KEY_IP6_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP6_SRC] = { .len = sizeof(struct in6_addr), }, + [NFTA_TUNNEL_KEY_IP6_DST] = { .len = sizeof(struct in6_addr), }, + [NFTA_TUNNEL_KEY_IP6_FLOWLABEL] = { .type = NLA_U32, } +}; + +static int nft_tunnel_obj_ip6_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_IP6_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP6_MAX, attr, + nft_tunnel_ip6_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_IP6_DST]) + return -EINVAL; + + if (tb[NFTA_TUNNEL_KEY_IP6_SRC]) { + memcpy(&info->key.u.ipv6.src, + nla_data(tb[NFTA_TUNNEL_KEY_IP6_SRC]), + sizeof(struct in6_addr)); + } + if (tb[NFTA_TUNNEL_KEY_IP6_DST]) { + memcpy(&info->key.u.ipv6.dst, + nla_data(tb[NFTA_TUNNEL_KEY_IP6_DST]), + sizeof(struct in6_addr)); + } + if (tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]) + info->key.label = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]); + + info->mode |= IP_TUNNEL_INFO_IPV6; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_vxlan_policy[NFTA_TUNNEL_KEY_VXLAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_VXLAN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_VXLAN_MAX, attr, + nft_tunnel_opts_vxlan_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_VXLAN_GBP]) + return -EINVAL; + + opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP])); + + opts->len = sizeof(struct vxlan_metadata); + opts->flags = TUNNEL_VXLAN_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_HWID] = { .type = NLA_U8 }, +}; + +static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1]; + uint8_t hwid, dir; + int err, version; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_ERSPAN_MAX, attr, + nft_tunnel_opts_erspan_policy, NULL); + if (err < 0) + return err; + + version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION])); + switch (version) { + case ERSPAN_VERSION: + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]) + return -EINVAL; + + opts->u.erspan.u.index = + nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]); + break; + case ERSPAN_VERSION2: + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] || + !tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]) + return -EINVAL; + + hwid = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]); + dir = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]); + + set_hwid(&opts->u.erspan.u.md2, hwid); + opts->u.erspan.u.md2.dir = dir; + break; + default: + return -EOPNOTSUPP; + } + opts->u.erspan.version = version; + + opts->len = sizeof(struct erspan_metadata); + opts->flags = TUNNEL_ERSPAN_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_policy[NFTA_TUNNEL_KEY_OPTS_MAX + 1] = { + [NFTA_TUNNEL_KEY_OPTS_VXLAN] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_OPTS_ERSPAN] = { .type = NLA_NESTED, }, +}; + +static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_OPTS_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_OPTS_MAX, attr, + nft_tunnel_opts_policy, NULL); + if (err < 0) + return err; + + if (tb[NFTA_TUNNEL_KEY_OPTS_VXLAN]) { + err = nft_tunnel_obj_vxlan_init(tb[NFTA_TUNNEL_KEY_OPTS_VXLAN], + opts); + } else if (tb[NFTA_TUNNEL_KEY_OPTS_ERSPAN]) { + err = nft_tunnel_obj_erspan_init(tb[NFTA_TUNNEL_KEY_OPTS_ERSPAN], + opts); + } else { + return -EOPNOTSUPP; + } + + return err; +} + +static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_IP6] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_ID] = { .type = NLA_U32, }, + [NFTA_TUNNEL_KEY_FLAGS] = { .type = NLA_U32, }, + [NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, }, +}; + +static int nft_tunnel_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct ip_tunnel_info info; + struct metadata_dst *md; + int err; + + if (!tb[NFTA_TUNNEL_KEY_ID]) + return -EINVAL; + + memset(&info, 0, sizeof(info)); + info.mode = IP_TUNNEL_INFO_TX; + info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID])); + info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + + if (tb[NFTA_TUNNEL_KEY_IP]) { + err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info); + if (err < 0) + return err; + } else if (tb[NFTA_TUNNEL_KEY_IP6]) { + err = nft_tunnel_obj_ip6_init(ctx, tb[NFTA_TUNNEL_KEY_IP6], &info); + if (err < 0) + return err; + } else { + return -EINVAL; + } + + if (tb[NFTA_TUNNEL_KEY_SPORT]) { + info.key.tp_src = nla_get_be16(tb[NFTA_TUNNEL_KEY_SPORT]); + } + if (tb[NFTA_TUNNEL_KEY_DPORT]) { + info.key.tp_dst = nla_get_be16(tb[NFTA_TUNNEL_KEY_DPORT]); + } + + if (tb[NFTA_TUNNEL_KEY_FLAGS]) { + u32 tun_flags; + + tun_flags = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_FLAGS])); + if (tun_flags & ~NFT_TUNNEL_F_MASK) + return -EOPNOTSUPP; + + if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX) + info.key.tun_flags &= ~TUNNEL_CSUM; + if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT) + info.key.tun_flags |= TUNNEL_DONT_FRAGMENT; + if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER) + info.key.tun_flags |= TUNNEL_SEQ; + } + if (tb[NFTA_TUNNEL_KEY_TOS]) + info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); + if (tb[NFTA_TUNNEL_KEY_TTL]) + info.key.ttl = nla_get_u8(tb[NFTA_TUNNEL_KEY_TTL]); + else + info.key.ttl = U8_MAX; + + if (tb[NFTA_TUNNEL_KEY_OPTS]) { + err = nft_tunnel_obj_opts_init(ctx, tb[NFTA_TUNNEL_KEY_OPTS], + &info, &priv->opts); + if (err < 0) + return err; + } + + md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL); + if (!md) + return -ENOMEM; + + memcpy(&md->u.tun_info, &info, sizeof(info)); + ip_tunnel_info_opts_set(&md->u.tun_info, &priv->opts.u, priv->opts.len, + priv->opts.flags); + priv->md = md; + + return 0; +} + +static inline void nft_tunnel_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct sk_buff *skb = pkt->skb; + + skb_dst_drop(skb); + dst_hold((struct dst_entry *) priv->md); + skb_dst_set(skb, (struct dst_entry *) priv->md); +} + +static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) +{ + struct nlattr *nest; + + if (info->mode & IP_TUNNEL_INFO_IPV6) { + nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP6); + if (!nest) + return -1; + + if (nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_SRC, &info->key.u.ipv6.src) < 0 || + nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_DST, &info->key.u.ipv6.dst) < 0 || + nla_put_be32(skb, NFTA_TUNNEL_KEY_IP6_FLOWLABEL, info->key.label)) + return -1; + + nla_nest_end(skb, nest); + } else { + nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP); + if (!nest) + return -1; + + if (nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_SRC, info->key.u.ipv4.src) < 0 || + nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_DST, info->key.u.ipv4.dst) < 0) + return -1; + + nla_nest_end(skb, nest); + } + + return 0; +} + +static int nft_tunnel_opts_dump(struct sk_buff *skb, + struct nft_tunnel_obj *priv) +{ + struct nft_tunnel_opts *opts = &priv->opts; + struct nlattr *nest; + + nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_OPTS); + if (!nest) + return -1; + + if (opts->flags & TUNNEL_VXLAN_OPT) { + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_VXLAN_GBP, + htonl(opts->u.vxlan.gbp))) + return -1; + } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + switch (opts->u.erspan.version) { + case ERSPAN_VERSION: + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX, + opts->u.erspan.u.index)) + return -1; + break; + case ERSPAN_VERSION2: + if (nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_HWID, + get_hwid(&opts->u.erspan.u.md2)) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_DIR, + opts->u.erspan.u.md2.dir)) + return -1; + break; + } + } + nla_nest_end(skb, nest); + + return 0; +} + +static int nft_tunnel_ports_dump(struct sk_buff *skb, + struct ip_tunnel_info *info) +{ + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 || + nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0) + return -1; + + return 0; +} + +static int nft_tunnel_flags_dump(struct sk_buff *skb, + struct ip_tunnel_info *info) +{ + u32 flags = 0; + + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + flags |= NFT_TUNNEL_F_DONT_FRAGMENT; + if (!(info->key.tun_flags & TUNNEL_CSUM)) + flags |= NFT_TUNNEL_F_ZERO_CSUM_TX; + if (info->key.tun_flags & TUNNEL_SEQ) + flags |= NFT_TUNNEL_F_SEQ_NUMBER; + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0) + return -1; + + return 0; +} + +static int nft_tunnel_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct ip_tunnel_info *info = &priv->md->u.tun_info; + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ID, + tunnel_id_to_key32(info->key.tun_id)) || + nft_tunnel_ip_dump(skb, info) < 0 || + nft_tunnel_ports_dump(skb, info) < 0 || + nft_tunnel_flags_dump(skb, info) < 0 || + nla_put_u8(skb, NFTA_TUNNEL_KEY_TOS, info->key.tos) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_TTL, info->key.ttl) || + nft_tunnel_opts_dump(skb, priv) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static void nft_tunnel_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + + metadata_dst_free(priv->md); +} + +static struct nft_object_type nft_tunnel_obj_type; +static const struct nft_object_ops nft_tunnel_obj_ops = { + .type = &nft_tunnel_obj_type, + .size = sizeof(struct nft_tunnel_obj), + .eval = nft_tunnel_obj_eval, + .init = nft_tunnel_obj_init, + .destroy = nft_tunnel_obj_destroy, + .dump = nft_tunnel_obj_dump, +}; + +static struct nft_object_type nft_tunnel_obj_type __read_mostly = { + .type = NFT_OBJECT_TUNNEL, + .ops = &nft_tunnel_obj_ops, + .maxattr = NFTA_TUNNEL_KEY_MAX, + .policy = nft_tunnel_key_policy, + .owner = THIS_MODULE, +}; + +static int __init nft_tunnel_module_init(void) +{ + int err; + + err = nft_register_expr(&nft_tunnel_type); + if (err < 0) + return err; + + err = nft_register_obj(&nft_tunnel_obj_type); + if (err < 0) + nft_unregister_expr(&nft_tunnel_type); + + return err; +} + +static void __exit nft_tunnel_module_exit(void) +{ + nft_unregister_obj(&nft_tunnel_obj_type); + nft_unregister_expr(&nft_tunnel_type); +} + +module_init(nft_tunnel_module_init); +module_exit(nft_tunnel_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_EXPR("tunnel"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 6275106ccf50..bc6c8ab0fa62 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -93,10 +93,8 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) /* init private data */ info->data = nf_conncount_init(par->net, par->family, keylen); - if (IS_ERR(info->data)) - return PTR_ERR(info->data); - return 0; + return PTR_ERR_OR_ZERO(info->data); } static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 9cfef73b4107..bf7bba80e24c 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -37,118 +37,6 @@ #include <net/netfilter/nf_log.h> #include <linux/netfilter/xt_osf.h> -/* - * Indexed by dont-fragment bit. - * It is the only constant value in the fingerprint. - */ -static struct list_head xt_osf_fingers[2]; - -static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { - [OSF_ATTR_FINGER] = { .len = sizeof(struct xt_osf_user_finger) }, -}; - -static int xt_osf_add_callback(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[], - struct netlink_ext_ack *extack) -{ - struct xt_osf_user_finger *f; - struct xt_osf_finger *kf = NULL, *sf; - int err = 0; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!osf_attrs[OSF_ATTR_FINGER]) - return -EINVAL; - - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) - return -EINVAL; - - f = nla_data(osf_attrs[OSF_ATTR_FINGER]); - - kf = kmalloc(sizeof(struct xt_osf_finger), GFP_KERNEL); - if (!kf) - return -ENOMEM; - - memcpy(&kf->finger, f, sizeof(struct xt_osf_user_finger)); - - list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) { - if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger))) - continue; - - kfree(kf); - kf = NULL; - - if (nlh->nlmsg_flags & NLM_F_EXCL) - err = -EEXIST; - break; - } - - /* - * We are protected by nfnl mutex. - */ - if (kf) - list_add_tail_rcu(&kf->finger_entry, &xt_osf_fingers[!!f->df]); - - return err; -} - -static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[], - struct netlink_ext_ack *extack) -{ - struct xt_osf_user_finger *f; - struct xt_osf_finger *sf; - int err = -ENOENT; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!osf_attrs[OSF_ATTR_FINGER]) - return -EINVAL; - - f = nla_data(osf_attrs[OSF_ATTR_FINGER]); - - list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) { - if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger))) - continue; - - /* - * We are protected by nfnl mutex. - */ - list_del_rcu(&sf->finger_entry); - kfree_rcu(sf, rcu_head); - - err = 0; - break; - } - - return err; -} - -static const struct nfnl_callback xt_osf_nfnetlink_callbacks[OSF_MSG_MAX] = { - [OSF_MSG_ADD] = { - .call = xt_osf_add_callback, - .attr_count = OSF_ATTR_MAX, - .policy = xt_osf_policy, - }, - [OSF_MSG_REMOVE] = { - .call = xt_osf_remove_callback, - .attr_count = OSF_ATTR_MAX, - .policy = xt_osf_policy, - }, -}; - -static const struct nfnetlink_subsystem xt_osf_nfnetlink = { - .name = "osf", - .subsys_id = NFNL_SUBSYS_OSF, - .cb_count = OSF_MSG_MAX, - .cb = xt_osf_nfnetlink_callbacks, -}; - static bool xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) { @@ -159,7 +47,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) return false; return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p), - xt_out(p), info, net, xt_osf_fingers); + xt_out(p), info, net, nf_osf_fingers); } static struct xt_match xt_osf_match = { @@ -177,52 +65,21 @@ static struct xt_match xt_osf_match = { static int __init xt_osf_init(void) { - int err = -EINVAL; - int i; - - for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i) - INIT_LIST_HEAD(&xt_osf_fingers[i]); - - err = nfnetlink_subsys_register(&xt_osf_nfnetlink); - if (err < 0) { - pr_err("Failed to register OSF nsfnetlink helper (%d)\n", err); - goto err_out_exit; - } + int err; err = xt_register_match(&xt_osf_match); if (err) { pr_err("Failed to register OS fingerprint " "matching module (%d)\n", err); - goto err_out_remove; + return err; } return 0; - -err_out_remove: - nfnetlink_subsys_unregister(&xt_osf_nfnetlink); -err_out_exit: - return err; } static void __exit xt_osf_fini(void) { - struct xt_osf_finger *f; - int i; - - nfnetlink_subsys_unregister(&xt_osf_nfnetlink); xt_unregister_match(&xt_osf_match); - - rcu_read_lock(); - for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i) { - - list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) { - list_del_rcu(&f->finger_entry); - kfree_rcu(f, rcu_head); - } - } - rcu_read_unlock(); - - rcu_barrier(); } module_init(xt_osf_init); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f6ac7693d2cc..930d17fa906c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -63,6 +63,7 @@ #include <linux/hash.h> #include <linux/genetlink.h> #include <linux/net_namespace.h> +#include <linux/nospec.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -679,6 +680,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; + protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES @@ -1009,6 +1011,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } + if (nlk->ngroups == 0) + groups = 0; + else if (nlk->ngroups < 8*sizeof(groups)) + groups &= (1UL << nlk->ngroups) - 1; + bound = nlk->bound; if (bound) { /* Ensure nlk->portid is up-to-date. */ diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ea0c0c6f1874..dd4adf8b1167 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -556,7 +556,7 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, pr_debug("%p\n", sk); - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_state == LLCP_LISTEN) return llcp_accept_poll(sk); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index b891a91577f8..c038e021a591 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -211,6 +211,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) if (!meter) return ERR_PTR(-ENOMEM); + meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]); meter->used = div_u64(ktime_get_ns(), 1000 * 1000); meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; @@ -280,6 +281,10 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) u32 meter_id; bool failed; + if (!a[OVS_METER_ATTR_ID]) { + return -ENODEV; + } + meter = dp_meter_create(a); if (IS_ERR_OR_NULL(meter)) return PTR_ERR(meter); @@ -298,11 +303,6 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - if (!a[OVS_METER_ATTR_ID]) { - err = -ENODEV; - goto exit_unlock; - } - meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); /* Cannot fail after this. */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e3e00d3a972e..345e38058ae5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1582,7 +1582,7 @@ static int fanout_set_data(struct packet_sock *po, char __user *data, return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; - }; + } } static void fanout_release_data(struct packet_fanout *f) @@ -1591,7 +1591,7 @@ static void fanout_release_data(struct packet_fanout *f) case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); - }; + } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index fc5c48b248fe..65387e1e6964 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -156,18 +156,20 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr, return sizeof(*sin); } - if (ipv6_addr_type(&rs->rs_conn_addr) & - IPV6_ADDR_MAPPED) { - sin = (struct sockaddr_in *)uaddr; - memset(sin, 0, sizeof(*sin)); - sin->sin_family = AF_INET; - return sizeof(*sin); +#if IS_ENABLED(CONFIG_IPV6) + if (!(ipv6_addr_type(&rs->rs_conn_addr) & + IPV6_ADDR_MAPPED)) { + sin6 = (struct sockaddr_in6 *)uaddr; + memset(sin6, 0, sizeof(*sin6)); + sin6->sin6_family = AF_INET6; + return sizeof(*sin6); } +#endif - sin6 = (struct sockaddr_in6 *)uaddr; - memset(sin6, 0, sizeof(*sin6)); - sin6->sin6_family = AF_INET6; - return sizeof(*sin6); + sin = (struct sockaddr_in *)uaddr; + memset(sin, 0, sizeof(*sin)); + sin->sin_family = AF_INET; + return sizeof(*sin); } if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) { sin = (struct sockaddr_in *)uaddr; @@ -501,9 +503,7 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, { struct sock *sk = sock->sk; struct sockaddr_in *sin; - struct sockaddr_in6 *sin6; struct rds_sock *rs = rds_sk_to_rs(sk); - int addr_type; int ret = 0; lock_sock(sk); @@ -528,7 +528,11 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, rs->rs_conn_port = sin->sin_port; break; - case AF_INET6: +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: { + struct sockaddr_in6 *sin6; + int addr_type; + sin6 = (struct sockaddr_in6 *)uaddr; if (addr_len < sizeof(struct sockaddr_in6)) { ret = -EINVAL; @@ -575,6 +579,8 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, rs->rs_conn_addr = sin6->sin6_addr; rs->rs_conn_port = sin6->sin6_port; break; + } +#endif default: ret = -EAFNOSUPPORT; diff --git a/net/rds/bind.c b/net/rds/bind.c index ba778760cbc2..3ab55784b637 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -165,7 +165,6 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct in6_addr v6addr, *binding_addr; struct rds_transport *trans; __u32 scope_id = 0; - int addr_type; int ret = 0; __be16 port; @@ -183,8 +182,10 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); binding_addr = &v6addr; port = sin->sin_port; +#if IS_ENABLED(CONFIG_IPV6) } else if (uaddr->sa_family == AF_INET6) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr; + int addr_type; if (addr_len < sizeof(struct sockaddr_in6)) return -EINVAL; @@ -212,6 +213,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } binding_addr = &sin6->sin6_addr; port = sin6->sin6_port; +#endif } else { return -EINVAL; } diff --git a/net/rds/connection.c b/net/rds/connection.c index 051e35c1e7c6..3bd2f4a5a30d 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -63,8 +63,12 @@ static struct hlist_head *rds_conn_bucket(const struct in6_addr *laddr, net_get_random_once(&rds6_hash_secret, sizeof(rds6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; +#if IS_ENABLED(CONFIG_IPV6) fhash = __ipv6_addr_jhash(faddr, rds6_hash_secret); - hash = __inet6_ehashfn(lhash, 0, fhash, 0, rds_hash_secret); +#else + fhash = (__force u32)faddr->s6_addr32[3]; +#endif + hash = __inet_ehashfn(lhash, 0, fhash, 0, rds_hash_secret); return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK]; } @@ -201,6 +205,8 @@ static struct rds_connection *__rds_conn_create(struct net *net, conn->c_isv6 = !ipv6_addr_v4mapped(laddr); conn->c_faddr = *faddr; conn->c_dev_if = dev_if; + +#if IS_ENABLED(CONFIG_IPV6) /* If the local address is link local, set c_bound_if to be the * index used for this connection. Otherwise, set it to 0 as * the socket is not bound to an interface. c_bound_if is used @@ -209,6 +215,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (ipv6_addr_type(laddr) & IPV6_ADDR_LINKLOCAL) conn->c_bound_if = dev_if; else +#endif conn->c_bound_if = 0; rds_conn_net_set(conn, net); @@ -500,9 +507,11 @@ static void __rds_inc_msg_cp(struct rds_incoming *inc, struct rds_info_iterator *iter, void *saddr, void *daddr, int flip, bool isv6) { +#if IS_ENABLED(CONFIG_IPV6) if (isv6) rds6_inc_info_copy(inc, iter, saddr, daddr, flip); else +#endif rds_inc_info_copy(inc, iter, *(__be32 *)saddr, *(__be32 *)daddr, flip); } @@ -581,6 +590,7 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, rds_conn_message_info_cmn(sock, len, iter, lens, want_send, false); } +#if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_message_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, @@ -588,6 +598,7 @@ static void rds6_conn_message_info(struct socket *sock, unsigned int len, { rds_conn_message_info_cmn(sock, len, iter, lens, want_send, true); } +#endif static void rds_conn_message_info_send(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -596,12 +607,14 @@ static void rds_conn_message_info_send(struct socket *sock, unsigned int len, rds_conn_message_info(sock, len, iter, lens, 1); } +#if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_message_info_send(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { rds6_conn_message_info(sock, len, iter, lens, 1); } +#endif static void rds_conn_message_info_retrans(struct socket *sock, unsigned int len, @@ -611,6 +624,7 @@ static void rds_conn_message_info_retrans(struct socket *sock, rds_conn_message_info(sock, len, iter, lens, 0); } +#if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_message_info_retrans(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -618,6 +632,7 @@ static void rds6_conn_message_info_retrans(struct socket *sock, { rds6_conn_message_info(sock, len, iter, lens, 0); } +#endif void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -734,6 +749,7 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer) return 1; } +#if IS_ENABLED(CONFIG_IPV6) static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer) { struct rds6_info_connection *cinfo6 = buffer; @@ -761,6 +777,7 @@ static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer) */ return 1; } +#endif static void rds_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -774,6 +791,7 @@ static void rds_conn_info(struct socket *sock, unsigned int len, sizeof(struct rds_info_connection)); } +#if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) @@ -785,6 +803,7 @@ static void rds6_conn_info(struct socket *sock, unsigned int len, buffer, sizeof(struct rds6_info_connection)); } +#endif int rds_conn_init(void) { @@ -807,12 +826,13 @@ int rds_conn_init(void) rds_conn_message_info_send); rds_info_register_func(RDS_INFO_RETRANS_MESSAGES, rds_conn_message_info_retrans); +#if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_CONNECTIONS, rds6_conn_info); rds_info_register_func(RDS6_INFO_SEND_MESSAGES, rds6_conn_message_info_send); rds_info_register_func(RDS6_INFO_RETRANS_MESSAGES, rds6_conn_message_info_retrans); - +#endif return 0; } @@ -830,11 +850,13 @@ void rds_conn_exit(void) rds_conn_message_info_send); rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES, rds_conn_message_info_retrans); +#if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_CONNECTIONS, rds6_conn_info); rds_info_deregister_func(RDS6_INFO_SEND_MESSAGES, rds6_conn_message_info_send); rds_info_deregister_func(RDS6_INFO_RETRANS_MESSAGES, rds6_conn_message_info_retrans); +#endif } /* diff --git a/net/rds/ib.c b/net/rds/ib.c index a4245c42d43b..89c6333ecd39 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -321,6 +321,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, return 1; } +#if IS_ENABLED(CONFIG_IPV6) /* IPv6 version of rds_ib_conn_info_visitor(). */ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) @@ -357,6 +358,7 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, } return 1; } +#endif static void rds_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -370,6 +372,7 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len, sizeof(struct rds_info_rdma_connection)); } +#if IS_ENABLED(CONFIG_IPV6) /* IPv6 version of rds_ib_ic_info(). */ static void rds6_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -382,6 +385,7 @@ static void rds6_ib_ic_info(struct socket *sock, unsigned int len, buffer, sizeof(struct rds6_info_rdma_connection)); } +#endif /* * Early RDS/IB was built to only bind to an address if there is an IPoIB @@ -398,7 +402,9 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, { int ret; struct rdma_cm_id *cm_id; +#if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 sin6; +#endif struct sockaddr_in sin; struct sockaddr *sa; bool isv4; @@ -418,6 +424,7 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, sin.sin_addr.s_addr = addr->s6_addr32[3]; sa = (struct sockaddr *)&sin; } else { +#if IS_ENABLED(CONFIG_IPV6) memset(&sin6, 0, sizeof(sin6)); sin6.sin6_family = AF_INET6; sin6.sin6_addr = *addr; @@ -432,21 +439,30 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, if (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL) { struct net_device *dev; - if (scope_id == 0) - return -EADDRNOTAVAIL; + if (scope_id == 0) { + ret = -EADDRNOTAVAIL; + goto out; + } /* Use init_net for now as RDS is not network * name space aware. */ dev = dev_get_by_index(&init_net, scope_id); - if (!dev) - return -EADDRNOTAVAIL; + if (!dev) { + ret = -EADDRNOTAVAIL; + goto out; + } if (!ipv6_chk_addr(&init_net, addr, dev, 1)) { dev_put(dev); - return -EADDRNOTAVAIL; + ret = -EADDRNOTAVAIL; + goto out; } dev_put(dev); } +#else + ret = -EADDRNOTAVAIL; + goto out; +#endif } /* rdma_bind_addr will only succeed for IB & iWARP devices */ @@ -461,6 +477,7 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, addr, scope_id, ret, cm_id->device ? cm_id->device->node_type : -1); +out: rdma_destroy_id(cm_id); return ret; @@ -491,7 +508,9 @@ void rds_ib_exit(void) rds_ib_set_unloading(); synchronize_rcu(); rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); +#if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); +#endif rds_ib_unregister_client(); rds_ib_destroy_nodev_conns(); rds_ib_sysctl_exit(); @@ -553,7 +572,9 @@ int rds_ib_init(void) rds_trans_register(&rds_ib_transport); rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); +#if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); +#endif goto out; diff --git a/net/rds/ib.h b/net/rds/ib.h index beb95b893f78..73427ff439f9 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -400,7 +400,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc); int rds_ib_recv_init(void); void rds_ib_recv_exit(void); int rds_ib_recv_path(struct rds_conn_path *conn); -int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic); +int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp); void rds_ib_recv_free_caches(struct rds_ib_connection *ic); void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp); void rds_ib_inc_free(struct rds_incoming *inc); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index a33b82dc0804..bfbb31f0c7fd 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -678,6 +678,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6) return version; } +#if IS_ENABLED(CONFIG_IPV6) /* Given an IPv6 address, find the net_device which hosts that address and * return its index. This is used by the rds_ib_cm_handle_connect() code to * find the interface index of where an incoming request comes from when @@ -704,6 +705,7 @@ static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr) return idx; } +#endif int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, struct rdma_cm_event *event, bool isv6) @@ -732,6 +734,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, dp = event->param.conn.private_data; if (isv6) { +#if IS_ENABLED(CONFIG_IPV6) dp_cmn = &dp->ricp_v6.dp_cmn; saddr6 = &dp->ricp_v6.dp_saddr; daddr6 = &dp->ricp_v6.dp_daddr; @@ -756,6 +759,10 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, goto out; } } +#else + err = -EOPNOTSUPP; + goto out; +#endif } else { dp_cmn = &dp->ricp_v4.dp_cmn; ipv6_addr_set_v4mapped(dp->ricp_v4.dp_saddr, &s_mapped_addr); @@ -893,9 +900,11 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp) /* XXX I wonder what affect the port space has */ /* delegate cm event handler to rdma_transport */ +#if IS_ENABLED(CONFIG_IPV6) if (conn->c_isv6) handler = rds6_rdma_cm_event_handler; else +#endif handler = rds_rdma_cm_event_handler; ic->i_cm_id = rdma_create_id(&init_net, handler, conn, RDMA_PS_TCP, IB_QPT_RC); @@ -1102,7 +1111,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) if (!ic) return -ENOMEM; - ret = rds_ib_recv_alloc_caches(ic); + ret = rds_ib_recv_alloc_caches(ic, gfp); if (ret) { kfree(ic); return ret; diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 48332a6ed738..d152e48ea371 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -344,6 +344,11 @@ struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev, struct rds_ib_frmr *frmr; int ret; + if (!ic) { + /* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/ + return ERR_PTR(-EOPNOTSUPP); + } + do { if (ibmr) rds_ib_free_frmr(ibmr, true); diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index f440ace584c8..5da12c248431 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -117,7 +117,8 @@ void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds6_info_rdma_connection *iinfo6); void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e3c8bbbdb43f..63c8d107adcf 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -180,6 +180,7 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_co iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages; } +#if IS_ENABLED(CONFIG_IPV6) void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds6_info_rdma_connection *iinfo6) { @@ -188,6 +189,7 @@ void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, iinfo6->rdma_mr_max = pool_1m->max_items; iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages; } +#endif struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool) { @@ -547,11 +549,12 @@ void rds_ib_flush_mrs(void) } void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret) + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; - struct rds_ib_connection *ic = rs->rs_conn->c_transport_data; + struct rds_ib_connection *ic = NULL; int ret; rds_ibdev = rds_ib_get_device(rs->rs_bound_addr.s6_addr32[3]); @@ -560,6 +563,9 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, goto out; } + if (conn) + ic = conn->c_transport_data; + if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) { ret = -ENODEV; goto out; @@ -569,17 +575,18 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret); else ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret); - if (ibmr) - rds_ibdev = NULL; - - out: - if (!ibmr) + if (IS_ERR(ibmr)) { + ret = PTR_ERR(ibmr); pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret); + } else { + return ibmr; + } + out: if (rds_ibdev) rds_ib_dev_put(rds_ibdev); - return ibmr; + return ERR_PTR(ret); } void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 557ccbb1ce00..d300186b8dc0 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -98,12 +98,12 @@ static void rds_ib_cache_xfer_to_ready(struct rds_ib_refill_cache *cache) } } -static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache) +static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache, gfp_t gfp) { struct rds_ib_cache_head *head; int cpu; - cache->percpu = alloc_percpu(struct rds_ib_cache_head); + cache->percpu = alloc_percpu_gfp(struct rds_ib_cache_head, gfp); if (!cache->percpu) return -ENOMEM; @@ -118,13 +118,13 @@ static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache) return 0; } -int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic) +int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp) { int ret; - ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs); + ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs, gfp); if (!ret) { - ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags); + ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags, gfp); if (ret) free_percpu(ic->i_cache_incs.percpu); } diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index c4cdfe491d96..c8dd3125d398 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -759,14 +759,11 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_send_work *send = NULL; struct ib_send_wr *failed_wr; - struct rds_ib_device *rds_ibdev; u32 pos; u32 work_alloc; int ret; int nr_sig = 0; - rds_ibdev = ib_get_client_data(ic->i_cm_id->device, &rds_ib_client); - work_alloc = rds_ib_ring_alloc(&ic->i_send_ring, 1, &pos); if (work_alloc != 1) { rds_ib_stats_inc(s_ib_tx_ring_full); diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 7b3998026825..98237feb607a 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -170,7 +170,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, - u64 *cookie_ret, struct rds_mr **mr_ret) + u64 *cookie_ret, struct rds_mr **mr_ret, + struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; unsigned int nr_pages; @@ -269,7 +270,8 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key); + &mr->r_key, + cp ? cp->cp_conn : NULL); if (IS_ERR(trans_private)) { for (i = 0 ; i < nents; i++) @@ -330,7 +332,7 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen) sizeof(struct rds_get_mr_args))) return -EFAULT; - return __rds_rdma_map(rs, &args, NULL, NULL); + return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) @@ -354,7 +356,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; - return __rds_rdma_map(rs, &new_args, NULL, NULL); + return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* @@ -782,7 +784,8 @@ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, rm->m_rdma_cookie != 0) return -EINVAL; - return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr); + return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, + &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index ad78929036ef..6b0f57c83a2a 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -39,7 +39,9 @@ /* Global IPv4 and IPv6 RDS RDMA listener cm_id */ static struct rdma_cm_id *rds_rdma_listen_id; +#if IS_ENABLED(CONFIG_IPV6) static struct rdma_cm_id *rds6_rdma_listen_id; +#endif static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, struct rdma_cm_event *event, @@ -155,11 +157,13 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, return rds_rdma_cm_event_handler_cmn(cm_id, event, false); } +#if IS_ENABLED(CONFIG_IPV6) int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { return rds_rdma_cm_event_handler_cmn(cm_id, event, true); } +#endif static int rds_rdma_listen_init_common(rdma_cm_event_handler handler, struct sockaddr *sa, @@ -214,7 +218,9 @@ out: static int rds_rdma_listen_init(void) { int ret; +#if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 sin6; +#endif struct sockaddr_in sin; sin.sin_family = PF_INET; @@ -226,6 +232,7 @@ static int rds_rdma_listen_init(void) if (ret != 0) return ret; +#if IS_ENABLED(CONFIG_IPV6) sin6.sin6_family = PF_INET6; sin6.sin6_addr = in6addr_any; sin6.sin6_port = htons(RDS_CM_PORT); @@ -237,6 +244,7 @@ static int rds_rdma_listen_init(void) /* Keep going even when IPv6 is not enabled in the system. */ if (ret != 0) rdsdebug("Cannot set up IPv6 RDMA listener\n"); +#endif return 0; } @@ -247,11 +255,13 @@ static void rds_rdma_listen_stop(void) rdma_destroy_id(rds_rdma_listen_id); rds_rdma_listen_id = NULL; } +#if IS_ENABLED(CONFIG_IPV6) if (rds6_rdma_listen_id) { rdsdebug("cm %p\n", rds6_rdma_listen_id); rdma_destroy_id(rds6_rdma_listen_id); rds6_rdma_listen_id = NULL; } +#endif } static int rds_rdma_init(void) diff --git a/net/rds/rds.h b/net/rds/rds.h index ff537bb11411..c4dcf654d8fe 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -470,6 +470,8 @@ struct rds_message { struct scatterlist *op_sg; } data; }; + + struct rds_conn_path *m_conn_path; }; /* @@ -551,7 +553,8 @@ struct rds_transport { unsigned int avail); void (*exit)(void); void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); diff --git a/net/rds/recv.c b/net/rds/recv.c index 03cd8df54c26..504cd6bcc54c 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -793,6 +793,7 @@ void rds_inc_info_copy(struct rds_incoming *inc, rds_info_copy(iter, &minfo, sizeof(minfo)); } +#if IS_ENABLED(CONFIG_IPV6) void rds6_inc_info_copy(struct rds_incoming *inc, struct rds_info_iterator *iter, struct in6_addr *saddr, struct in6_addr *daddr, @@ -817,3 +818,4 @@ void rds6_inc_info_copy(struct rds_incoming *inc, rds_info_copy(iter, &minfo6, sizeof(minfo6)); } +#endif diff --git a/net/rds/send.c b/net/rds/send.c index 9604e1faa564..57b3d5a8b2db 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1103,6 +1103,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) dport = usin->sin_port; break; +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { int addr_type; @@ -1126,7 +1127,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || IN_MULTICAST(ntohl(addr4))) { - return -EINVAL; + ret = -EINVAL; goto out; } } @@ -1142,6 +1143,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) dport = sin6->sin6_port; break; } +#endif default: ret = -EINVAL; @@ -1253,6 +1255,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rs->rs_conn = conn; } + if (conn->c_trans->t_mp_capable) + cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; + else + cpath = &conn->c_path[0]; + + rm->m_conn_path = cpath; + /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); if (ret) { @@ -1276,11 +1285,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - if (conn->c_trans->t_mp_capable) - cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; - else - cpath = &conn->c_path[0]; - if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index f23925af0b8d..2c7b7c352d3e 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -51,7 +51,9 @@ static LIST_HEAD(rds_tcp_tc_list); * rds6_tcp_tc_count counts both IPv4 and IPv6 connections. */ static unsigned int rds_tcp_tc_count; +#if IS_ENABLED(CONFIG_IPV6) static unsigned int rds6_tcp_tc_count; +#endif /* Track rds_tcp_connection structs so they can be cleaned up */ static DEFINE_SPINLOCK(rds_tcp_conn_lock); @@ -118,7 +120,9 @@ void rds_tcp_restore_callbacks(struct socket *sock, /* done under the callback_lock to serialize with write_space */ spin_lock(&rds_tcp_tc_list_lock); list_del_init(&tc->t_list_item); +#if IS_ENABLED(CONFIG_IPV6) rds6_tcp_tc_count--; +#endif if (!tc->t_cpath->cp_conn->c_isv6) rds_tcp_tc_count--; spin_unlock(&rds_tcp_tc_list_lock); @@ -207,7 +211,9 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp) /* done under the callback_lock to serialize with write_space */ spin_lock(&rds_tcp_tc_list_lock); list_add_tail(&tc->t_list_item, &rds_tcp_tc_list); +#if IS_ENABLED(CONFIG_IPV6) rds6_tcp_tc_count++; +#endif if (!tc->t_cpath->cp_conn->c_isv6) rds_tcp_tc_count++; spin_unlock(&rds_tcp_tc_list_lock); @@ -273,6 +279,7 @@ out: spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); } +#if IS_ENABLED(CONFIG_IPV6) /* Handle RDS6_INFO_TCP_SOCKETS socket option. It returns both IPv4 and * IPv6 connections. IPv4 connection address is returned in an IPv4 mapped * address. @@ -314,12 +321,15 @@ out: spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); } +#endif static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, __u32 scope_id) { struct net_device *dev = NULL; +#if IS_ENABLED(CONFIG_IPV6) int ret; +#endif if (ipv6_addr_v4mapped(addr)) { if (inet_addr_type(net, addr->s6_addr32[3]) == RTN_LOCAL) @@ -340,9 +350,11 @@ static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, } rcu_read_unlock(); } +#if IS_ENABLED(CONFIG_IPV6) ret = ipv6_chk_addr(net, addr, dev, 0); if (ret) return 0; +#endif return -EADDRNOTAVAIL; } @@ -545,18 +557,27 @@ static __net_init int rds_tcp_init_net(struct net *net) err = -ENOMEM; goto fail; } + +#if IS_ENABLED(CONFIG_IPV6) rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, true); +#else + rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, false); +#endif if (!rtn->rds_tcp_listen_sock) { pr_warn("could not set up IPv6 listen sock\n"); +#if IS_ENABLED(CONFIG_IPV6) /* Try IPv4 as some systems disable IPv6 */ rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, false); if (!rtn->rds_tcp_listen_sock) { +#endif unregister_net_sysctl_table(rtn->rds_tcp_sysctl); rtn->rds_tcp_sysctl = NULL; err = -EAFNOSUPPORT; goto fail; +#if IS_ENABLED(CONFIG_IPV6) } +#endif } INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker); return 0; @@ -670,7 +691,9 @@ static void rds_tcp_exit(void) rds_tcp_set_unloading(); synchronize_rcu(); rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); +#if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info); +#endif unregister_pernet_device(&rds_tcp_net_ops); rds_tcp_destroy_conns(); rds_trans_unregister(&rds_tcp_transport); @@ -702,7 +725,9 @@ static int rds_tcp_init(void) rds_trans_register(&rds_tcp_transport); rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); +#if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info); +#endif goto out; out_recv: diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 0cf0147117d8..c12203f646da 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -132,7 +132,10 @@ int rds_tcp_accept_one(struct socket *sock) int conn_state; struct rds_conn_path *cp; struct in6_addr *my_addr, *peer_addr; - int dev_if; +#if !IS_ENABLED(CONFIG_IPV6) + struct in6_addr saddr, daddr; +#endif + int dev_if = 0; if (!sock) /* module unload or netns delete in progress */ return -ENETUNREACH; @@ -165,12 +168,21 @@ int rds_tcp_accept_one(struct socket *sock) inet = inet_sk(new_sock->sk); +#if IS_ENABLED(CONFIG_IPV6) my_addr = &new_sock->sk->sk_v6_rcv_saddr; peer_addr = &new_sock->sk->sk_v6_daddr; - rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n", +#else + ipv6_addr_set_v4mapped(inet->inet_saddr, &saddr); + ipv6_addr_set_v4mapped(inet->inet_daddr, &daddr); + my_addr = &saddr; + peer_addr = &daddr; +#endif + rdsdebug("accepted family %d tcp %pI6c:%u -> %pI6c:%u\n", + sock->sk->sk_family, my_addr, ntohs(inet->inet_sport), peer_addr, ntohs(inet->inet_dport)); +#if IS_ENABLED(CONFIG_IPV6) /* sk_bound_dev_if is not set if the peer address is not link local * address. In this case, it happens that mcast_oif is set. So * just use it. @@ -184,9 +196,10 @@ int rds_tcp_accept_one(struct socket *sock) } else { dev_if = new_sock->sk->sk_bound_dev_if; } +#endif + conn = rds_conn_create(sock_net(sock->sk), - &new_sock->sk->sk_v6_rcv_saddr, - &new_sock->sk->sk_v6_daddr, + my_addr, peer_addr, &rds_tcp_transport, GFP_KERNEL, dev_if); if (IS_ERR(conn)) { diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 2b463047dd7b..ac44d8afffb1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -741,7 +741,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock, struct rxrpc_sock *rx = rxrpc_sk(sk); __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5fb7d3254d9e..9d9278a13d91 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -420,6 +420,7 @@ struct rxrpc_connection { struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call __rcu *call; /* Active call */ + unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ @@ -478,6 +479,7 @@ enum rxrpc_call_flag { RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ + RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ }; /* @@ -588,7 +590,7 @@ struct rxrpc_call { */ #define RXRPC_RXTX_BUFF_SIZE 64 #define RXRPC_RXTX_BUFF_MASK (RXRPC_RXTX_BUFF_SIZE - 1) -#define RXRPC_INIT_RX_WINDOW_SIZE 32 +#define RXRPC_INIT_RX_WINDOW_SIZE 63 struct sk_buff **rxtx_buffer; u8 *rxtx_annotations; #define RXRPC_TX_ANNO_ACK 0 diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a9a9be5519b9..9d1e298b784c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -116,9 +116,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, while (*pp) { parent = *pp; xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < call->user_call_ID) + if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) + else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else goto id_in_use; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 20210418904b..8e7434e92097 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -162,7 +162,6 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { - struct rxrpc_skb_priv *sp; struct sk_buff *skb; unsigned long resend_at; rxrpc_seq_t cursor, seq, top; @@ -207,7 +206,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) skb = call->rxtx_buffer[ix]; rxrpc_see_skb(skb, rxrpc_skb_tx_seen); - sp = rxrpc_skb(skb); if (anno_type == RXRPC_TX_ANNO_UNACK) { if (ktime_after(skb->tstamp, max_age)) { diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 5736f643c516..f8f37188a932 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -590,6 +590,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, */ smp_wmb(); chan->call_id = call_id; + chan->call_debug_id = call->debug_id; rcu_assign_pointer(chan->call, call); wake_up(&call->waitq); } @@ -1051,7 +1052,6 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work) container_of(work, struct rxrpc_net, client_conn_reaper); unsigned long expiry, conn_expires_at, now; unsigned int nr_conns; - bool did_discard = false; _enter(""); @@ -1113,7 +1113,6 @@ next: * If someone re-sets the flag and re-gets the ref, that's fine. */ rxrpc_put_connection(conn); - did_discard = true; nr_conns--; goto next; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 8229a52c2acd..84d40ba9856f 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -129,8 +129,10 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort); break; case RXRPC_PACKET_TYPE_ACK: - trace_rxrpc_tx_ack(NULL, serial, chan->last_seq, 0, - RXRPC_ACK_DUPLICATE, 0); + trace_rxrpc_tx_ack(chan->call_debug_id, serial, + ntohl(pkt.ack.firstPacket), + ntohl(pkt.ack.serial), + pkt.ack.reason, 0); _proto("Tx ACK %%%u [re]", serial); break; } @@ -138,8 +140,11 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); conn->params.peer->last_tx_at = ktime_get_real(); if (ret < 0) - trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_call_final_resend); + trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret, + rxrpc_tx_point_call_final_resend); + else + trace_rxrpc_tx_packet(chan->call_debug_id, &pkt.whdr, + rxrpc_tx_point_call_final_resend); _leave(""); } @@ -240,11 +245,13 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_conn_abort); + rxrpc_tx_point_conn_abort); _debug("sendmsg failed: %d", ret); return -EAGAIN; } + trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); + conn->params.peer->last_tx_at = ktime_get_real(); _leave(" = 0"); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 608d078a4981..cfdc199c6351 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -496,7 +496,7 @@ next_subpacket: return rxrpc_proto_abort("LSA", call, seq); } - trace_rxrpc_rx_data(call, seq, serial, flags, annotation); + trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); if (before_eq(seq, hard_ack)) { ack = RXRPC_ACK_DUPLICATE; ack_serial = serial; @@ -592,9 +592,15 @@ ack: rxrpc_propose_ACK(call, ack, skew, ack_serial, immediate_ack, true, rxrpc_propose_ack_input_data); + else + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, + false, true, + rxrpc_propose_ack_input_data); - if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) + if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) { + trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); + } _leave(" [queued]"); } @@ -1262,6 +1268,11 @@ void rxrpc_data_ready(struct sock *udp_sk) /* But otherwise we need to retransmit the final packet * from data cached in the connection record. */ + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) + trace_rxrpc_rx_data(chan->call_debug_id, + sp->hdr.seq, + sp->hdr.serial, + sp->hdr.flags, 0); rxrpc_post_packet_to_conn(conn, skb); goto out_unlock; } diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 8325f1b86840..13bd8a4dfac7 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -72,7 +72,10 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, - rxrpc_tx_fail_version_reply); + rxrpc_tx_point_version_reply); + else + trace_rxrpc_tx_packet(local->debug_id, &whdr, + rxrpc_tx_point_version_reply); _leave(""); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f03de1c59ba3..801dbf3d3478 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -183,7 +183,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, serial = atomic_inc_return(&conn->serial); pkt->whdr.serial = htonl(serial); - trace_rxrpc_tx_ack(call, serial, + trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(pkt->ack.firstPacket), ntohl(pkt->ack.serial), pkt->ack.reason, pkt->ack.nAcks); @@ -212,7 +212,10 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, conn->params.peer->last_tx_at = ktime_get_real(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_ack); + rxrpc_tx_point_call_ack); + else + trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, + rxrpc_tx_point_call_ack); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -299,7 +302,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) conn->params.peer->last_tx_at = ktime_get_real(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_abort); + rxrpc_tx_point_call_abort); + else + trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, + rxrpc_tx_point_call_abort); rxrpc_put_connection(conn); @@ -396,7 +402,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, up_read(&conn->params.local->defrag_sem); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_data_nofrag); + rxrpc_tx_point_call_data_nofrag); + else + trace_rxrpc_tx_packet(call->debug_id, &whdr, + rxrpc_tx_point_call_data_nofrag); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -488,7 +497,10 @@ send_fragmentable: if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_data_frag); + rxrpc_tx_point_call_data_frag); + else + trace_rxrpc_tx_packet(call->debug_id, &whdr, + rxrpc_tx_point_call_data_frag); up_write(&conn->params.local->defrag_sem); goto done; @@ -545,7 +557,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local) ret = kernel_sendmsg(local->socket, &msg, iov, 2, size); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, - rxrpc_tx_fail_reject); + rxrpc_tx_point_reject); + else + trace_rxrpc_tx_packet(local->debug_id, &whdr, + rxrpc_tx_point_reject); } rxrpc_free_skb(skb, rxrpc_skb_rx_freed); @@ -597,7 +612,10 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); if (ret < 0) trace_rxrpc_tx_fail(peer->debug_id, 0, ret, - rxrpc_tx_fail_version_keepalive); + rxrpc_tx_point_version_keepalive); + else + trace_rxrpc_tx_packet(peer->debug_id, &whdr, + rxrpc_tx_point_version_keepalive); peer->last_tx_at = ktime_get_real(); _leave(""); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index d9fca8c4bcdc..9805e3b85c36 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -63,6 +63,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_peer *peer; struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + unsigned long timeout = 0; rxrpc_seq_t tx_hard_ack, rx_hard_ack; char lbuff[50], rbuff[50]; @@ -71,7 +72,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) "Proto Local " " Remote " " SvID ConnID CallID End Use State Abort " - " UserID\n"); + " UserID TxSeq TW RxSeq RW RxSerial RxTimo\n"); return 0; } @@ -94,11 +95,16 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) else strcpy(rbuff, "no_connection"); + if (call->state != RXRPC_CALL_SERVER_PREALLOC) { + timeout = READ_ONCE(call->expect_rx_by); + timeout -= jiffies; + } + tx_hard_ack = READ_ONCE(call->tx_hard_ack); rx_hard_ack = READ_ONCE(call->rx_hard_ack); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" - " %-8.8s %08x %lx %08x %02x %08x %02x\n", + " %-8.8s %08x %lx %08x %02x %08x %02x %08x %06lx\n", lbuff, rbuff, call->service_id, @@ -110,7 +116,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->abort_code, call->user_call_ID, tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, - rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack); + rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, + call->rx_serial, + timeout); return 0; } @@ -179,7 +187,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) print: seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %s %3u" - " %s %08x %08x %08x\n", + " %s %08x %08x %08x %08x %08x %08x %08x\n", lbuff, rbuff, conn->service_id, @@ -189,7 +197,11 @@ print: rxrpc_conn_states[conn->state], key_serial(conn->params.key), atomic_read(&conn->serial), - conn->hi_serial); + conn->hi_serial, + conn->channels[0].call_id, + conn->channels[1].call_id, + conn->channels[2].call_id, + conn->channels[3].call_id); return 0; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7bff716e911e..816b19a78809 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -144,13 +144,11 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); -#if 0 // TODO: May want to transmit final ACK under some circumstances anyway if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true, rxrpc_propose_ack_terminal_ack); - rxrpc_send_ack_packet(call, false, NULL); + //rxrpc_send_ack_packet(call, false, NULL); } -#endif write_lock_bh(&call->state_lock); @@ -315,6 +313,10 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; + if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) && + call->ackr_reason) + rxrpc_send_ack_packet(call, false, NULL); + rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; @@ -414,6 +416,8 @@ out: done: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, rx_pkt_offset, rx_pkt_len, ret); + if (ret == -EAGAIN) + set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); return ret; } @@ -607,9 +611,7 @@ wait_error: * rxrpc_kernel_recv_data - Allow a kernel service to receive data/info * @sock: The socket that the call exists on * @call: The call to send data through - * @buf: The buffer to receive into - * @size: The size of the buffer, including data already read - * @_offset: The running offset into the buffer. + * @iter: The buffer to receive into * @want_more: True if more data is expected to be read * @_abort: Where the abort code is stored if -ECONNABORTED is returned * @_service: Where to store the actual service ID (may be upgraded) @@ -622,39 +624,30 @@ wait_error: * Note that we may return -EAGAIN to drain empty packets at the end of the * data, even if we've already copied over the requested data. * - * This function adds the amount it transfers to *_offset, so this should be - * precleared as appropriate. Note that the amount remaining in the buffer is - * taken to be size - *_offset. - * * *_abort should also be initialised to 0. */ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, - void *buf, size_t size, size_t *_offset, + struct iov_iter *iter, bool want_more, u32 *_abort, u16 *_service) { - struct iov_iter iter; - struct kvec iov; + size_t offset = 0; int ret; - _enter("{%d,%s},%zu/%zu,%d", + _enter("{%d,%s},%zu,%d", call->debug_id, rxrpc_call_states[call->state], - *_offset, size, want_more); + iov_iter_count(iter), want_more); - ASSERTCMP(*_offset, <=, size); ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING); - iov.iov_base = buf + *_offset; - iov.iov_len = size - *_offset; - iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset); - mutex_lock(&call->user_mutex); switch (READ_ONCE(call->state)) { case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = rxrpc_recvmsg_data(sock, call, NULL, &iter, size, 0, - _offset); + ret = rxrpc_recvmsg_data(sock, call, NULL, iter, + iov_iter_count(iter), 0, + &offset); if (ret < 0) goto out; @@ -663,7 +656,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, * full buffer or have been given -EAGAIN. */ if (ret == 1) { - if (*_offset < size) + if (iov_iter_count(iter) > 0) goto short_data; if (!want_more) goto read_phase_complete; @@ -686,10 +679,21 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: + switch (call->ackr_reason) { + case RXRPC_ACK_IDLE: + break; + case RXRPC_ACK_DELAY: + if (ret != -EAGAIN) + break; + /* Fall through */ + default: + rxrpc_send_ack_packet(call, false, NULL); + } + if (_service) *_service = call->service_id; mutex_unlock(&call->user_mutex); - _leave(" = %d [%zu,%d]", ret, *_offset, *_abort); + _leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort); return ret; short_data: @@ -705,7 +709,7 @@ call_complete: ret = call->error; if (call->completion == RXRPC_CALL_SUCCEEDED) { ret = 1; - if (size > 0) + if (iov_iter_count(iter) > 0) ret = -ECONNRESET; } goto out; diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 278ac0807a60..eaf8f4f446b0 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -146,10 +146,10 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) static int rxkad_secure_packet_auth(const struct rxrpc_call *call, struct sk_buff *skb, u32 data_size, - void *sechdr) + void *sechdr, + struct skcipher_request *req) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxkad_level1_hdr hdr; struct rxrpc_crypt iv; struct scatterlist sg; @@ -183,12 +183,12 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct sk_buff *skb, u32 data_size, - void *sechdr) + void *sechdr, + struct skcipher_request *req) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr rxkhdr; struct rxrpc_skb_priv *sp; - SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; struct scatterlist sg[16]; struct sk_buff *trailer; @@ -296,11 +296,12 @@ static int rxkad_secure_packet(struct rxrpc_call *call, ret = 0; break; case RXRPC_SECURITY_AUTH: - ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr); + ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr, + req); break; case RXRPC_SECURITY_ENCRYPT: ret = rxkad_secure_packet_encrypt(call, skb, data_size, - sechdr); + sechdr, req); break; default: ret = -EPERM; @@ -316,10 +317,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call, */ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, unsigned int offset, unsigned int len, - rxrpc_seq_t seq) + rxrpc_seq_t seq, + struct skcipher_request *req) { struct rxkad_level1_hdr sechdr; - SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; struct scatterlist sg[16]; struct sk_buff *trailer; @@ -402,11 +403,11 @@ nomem: */ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, unsigned int offset, unsigned int len, - rxrpc_seq_t seq) + rxrpc_seq_t seq, + struct skcipher_request *req) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; - SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; struct sk_buff *trailer; @@ -549,9 +550,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, case RXRPC_SECURITY_PLAIN: return 0; case RXRPC_SECURITY_AUTH: - return rxkad_verify_packet_1(call, skb, offset, len, seq); + return rxkad_verify_packet_1(call, skb, offset, len, seq, req); case RXRPC_SECURITY_ENCRYPT: - return rxkad_verify_packet_2(call, skb, offset, len, seq); + return rxkad_verify_packet_2(call, skb, offset, len, seq, req); default: return -ENOANO; } @@ -665,11 +666,13 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_conn_challenge); + rxrpc_tx_point_rxkad_challenge); return -EAGAIN; } conn->params.peer->last_tx_at = ktime_get_real(); + trace_rxrpc_tx_packet(conn->debug_id, &whdr, + rxrpc_tx_point_rxkad_challenge); _leave(" = 0"); return 0; } @@ -721,11 +724,12 @@ static int rxkad_send_response(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_conn_response); + rxrpc_tx_point_rxkad_response); return -EAGAIN; } conn->params.peer->last_tx_at = ktime_get_real(); + trace_rxrpc_tx_packet(0, &whdr, rxrpc_tx_point_rxkad_response); _leave(" = 0"); return 0; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 148a89ab789b..229d63c99be2 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -36,7 +36,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) if (!tp) return -EINVAL; - a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true); + a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index); if (!a->goto_chain) return -ENOMEM; return 0; @@ -44,7 +44,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) static void tcf_action_goto_chain_fini(struct tc_action *a) { - tcf_chain_put(a->goto_chain); + tcf_chain_put_by_act(a->goto_chain); } static void tcf_action_goto_chain_exec(const struct tc_action *a, @@ -786,6 +786,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } +static bool tcf_action_valid(int action) +{ + int opcode = TC_ACT_EXT_OPCODE(action); + + if (!opcode) + return action <= TC_ACT_VALUE_MAX; + return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC; +} + struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -895,6 +904,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, } } + if (!tcf_action_valid(a->tcfa_action)) { + NL_SET_ERR_MSG(extack, "invalid action value, using TC_ACT_UNSPEC instead"); + a->tcfa_action = TC_ACT_UNSPEC; + } + return a; err_mod: diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 06f743d8ed41..6203eb075c9a 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -196,12 +196,10 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS])) return -EINVAL; - bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; - memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size); - fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4e8c383f379e..648a3a35b720 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -561,15 +561,14 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, u32 update_flags; int action; - rcu_read_lock(); - params = rcu_dereference(p->params); + params = rcu_dereference_bh(p->params); tcf_lastuse_update(&p->tcf_tm); bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) - goto drop_stats; + goto drop; update_flags = params->update_flags; switch (tc_skb_protocol(skb)) { @@ -583,16 +582,11 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, break; } -unlock: - rcu_read_unlock(); return action; drop: - action = TC_ACT_SHOT; - -drop_stats: qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats)); - goto unlock; + return TC_ACT_SHOT; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3d6e265758c0..df4060e32d43 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -820,14 +820,11 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_ife_params *p; int ret; - rcu_read_lock(); - p = rcu_dereference(ife->params); + p = rcu_dereference_bh(ife->params); if (p->flags & IFE_ENCODE) { ret = tcf_ife_encode(skb, a, res, p); - rcu_read_unlock(); return ret; } - rcu_read_unlock(); return tcf_ife_decode(skb, a, res); } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6afd89a36c69..b26d060da08e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -25,6 +25,7 @@ #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> #include <net/tc_act/tc_mirred.h> @@ -49,6 +50,18 @@ static bool tcf_mirred_act_wants_ingress(int action) } } +static bool tcf_mirred_can_reinsert(int action) +{ + switch (action) { + case TC_ACT_SHOT: + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + return true; + } + return false; +} + static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); @@ -171,21 +184,23 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mirred *m = to_mirred(a); + struct sk_buff *skb2 = skb; bool m_mac_header_xmit; struct net_device *dev; - struct sk_buff *skb2; int retval, err = 0; + bool use_reinsert; + bool want_ingress; + bool is_redirect; int m_eaction; int mac_len; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); - rcu_read_lock(); m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); retval = READ_ONCE(m->tcf_action); - dev = rcu_dereference(m->tcfm_dev); + dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); goto out; @@ -197,16 +212,25 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, goto out; } - skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) - goto out; + /* we could easily avoid the clone only if called by ingress and clsact; + * since we can't easily detect the clsact caller, skip clone only for + * ingress - that covers the TC S/W datapath. + */ + is_redirect = tcf_mirred_is_act_redirect(m_eaction); + use_reinsert = skb_at_tc_ingress(skb) && is_redirect && + tcf_mirred_can_reinsert(retval); + if (!use_reinsert) { + skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + goto out; + } /* If action's target direction differs than filter's direction, * and devices expect a mac header on xmit, then mac push/pull is * needed. */ - if (skb_at_tc_ingress(skb) != tcf_mirred_act_wants_ingress(m_eaction) && - m_mac_header_xmit) { + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { if (!skb_at_tc_ingress(skb)) { /* caught at egress, act ingress: pull mac */ mac_len = skb_network_header(skb) - skb_mac_header(skb); @@ -217,15 +241,23 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, } } + skb2->skb_iif = skb->dev->ifindex; + skb2->dev = dev; + /* mirror is always swallowed */ - if (tcf_mirred_is_act_redirect(m_eaction)) { + if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; + + /* let's the caller reinsert the packet, if possible */ + if (use_reinsert) { + res->ingress = want_ingress; + res->qstats = this_cpu_ptr(m->common.cpu_qstats); + return TC_ACT_REINSERT; + } } - skb2->skb_iif = skb->dev->ifindex; - skb2->dev = dev; - if (!tcf_mirred_act_wants_ingress(m_eaction)) + if (!want_ingress) err = dev_queue_xmit(skb2); else err = netif_receive_skb(skb2); @@ -236,7 +268,6 @@ out: if (tcf_mirred_is_act_redirect(m_eaction)) retval = TC_ACT_SHOT; } - rcu_read_unlock(); return retval; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 9ab5d81aff1a..43ba999b2d23 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -286,7 +286,7 @@ static int pedit_skb_hdr_offset(struct sk_buff *skb, default: ret = -EINVAL; break; - }; + } return ret; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 3079e7be5bde..2608ccc83e5e 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -140,8 +140,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); - rcu_read_lock(); - psample_group = rcu_dereference(s->psample_group); + psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ if (psample_group && (prandom_u32() % s->rate == 0)) { @@ -165,7 +164,6 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, skb_pull(skb, skb->mac_len); } - rcu_read_unlock(); return retval; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index da56e6938c9e..a6db47ebec11 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -43,8 +43,7 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); - rcu_read_lock(); - params = rcu_dereference(d->params); + params = rcu_dereference_bh(d->params); action = READ_ONCE(d->tcf_action); if (params->flags & SKBEDIT_F_PRIORITY) @@ -77,14 +76,11 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, } if (params->flags & SKBEDIT_F_PTYPE) skb->pkt_type = params->ptype; - -unlock: - rcu_read_unlock(); return action; + err: qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats)); - action = TC_ACT_SHOT; - goto unlock; + return TC_ACT_SHOT; } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index cdc6bacfb190..c437c6d51a71 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -41,20 +41,14 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, * then MAX_EDIT_LEN needs to change appropriately */ err = skb_ensure_writable(skb, MAX_EDIT_LEN); - if (unlikely(err)) { /* best policy is to drop on the floor */ - qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); - return TC_ACT_SHOT; - } + if (unlikely(err)) /* best policy is to drop on the floor */ + goto drop; - rcu_read_lock(); action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) { - qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); - rcu_read_unlock(); - return action; - } + if (unlikely(action == TC_ACT_SHOT)) + goto drop; - p = rcu_dereference(d->skbmod_p); + p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC) ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); @@ -62,7 +56,6 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); if (flags & SKBMOD_F_ETYPE) eth_hdr(skb)->h_proto = p->eth_type; - rcu_read_unlock(); if (flags & SKBMOD_F_SWAPMAC) { u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ @@ -73,6 +66,10 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, } return action; + +drop: + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + return TC_ACT_SHOT; } static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index f811850fd1d0..d42d9e112789 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -31,9 +31,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_tunnel_key_params *params; int action; - rcu_read_lock(); - - params = rcu_dereference(t->params); + params = rcu_dereference_bh(t->params); tcf_lastuse_update(&t->tcf_tm); bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); @@ -53,8 +51,6 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, break; } - rcu_read_unlock(); - return action; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index ad37f308175a..15a0ee214c9c 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -40,11 +40,9 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); - rcu_read_lock(); - action = READ_ONCE(v->tcf_action); - p = rcu_dereference(v->vlan_p); + p = rcu_dereference_bh(v->vlan_p); switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: @@ -61,7 +59,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, case TCA_VLAN_ACT_MODIFY: /* No-op if no vlan tag (either hw-accel or in-payload) */ if (!skb_vlan_tagged(skb)) - goto unlock; + goto out; /* extract existing tag (and guarantee no hw-accel tag) */ if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); @@ -86,18 +84,15 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, BUG(); } - goto unlock; - -drop: - action = TC_ACT_SHOT; - qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); - -unlock: - rcu_read_unlock(); +out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); return action; + +drop: + qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); + return TC_ACT_SHOT; } static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 5f7098b5405e..194c2e0b2737 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -232,19 +232,6 @@ static void tcf_chain0_head_change(struct tcf_chain *chain, tcf_chain_head_change_item(item, tp_head); } -static void tcf_chain_flush(struct tcf_chain *chain) -{ - struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); - - tcf_chain0_head_change(chain, NULL); - while (tp) { - RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp, NULL); - tp = rtnl_dereference(chain->filter_chain); - tcf_chain_put(chain); - } -} - static void tcf_chain_destroy(struct tcf_chain *chain) { struct tcf_block *block = chain->block; @@ -262,6 +249,14 @@ static void tcf_chain_hold(struct tcf_chain *chain) ++chain->refcnt; } +static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain) +{ + /* In case all the references are action references, this + * chain should not be shown to the user. + */ + return chain->refcnt == chain->action_refcnt; +} + static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, u32 chain_index) { @@ -277,38 +272,77 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, u32 seq, u16 flags, int event, bool unicast); -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, - bool create) +static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, + u32 chain_index, bool create, + bool by_act) { struct tcf_chain *chain = tcf_chain_lookup(block, chain_index); if (chain) { tcf_chain_hold(chain); - return chain; + } else { + if (!create) + return NULL; + chain = tcf_chain_create(block, chain_index); + if (!chain) + return NULL; } - if (!create) - return NULL; - chain = tcf_chain_create(block, chain_index); - if (!chain) - return NULL; - tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + if (by_act) + ++chain->action_refcnt; + + /* Send notification only in case we got the first + * non-action reference. Until then, the chain acts only as + * a placeholder for actions pointing to it and user ought + * not know about them. + */ + if (chain->refcnt - chain->action_refcnt == 1 && !by_act) + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, + RTM_NEWCHAIN, false); + return chain; } -EXPORT_SYMBOL(tcf_chain_get); + +static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) +{ + return __tcf_chain_get(block, chain_index, create, false); +} + +struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) +{ + return __tcf_chain_get(block, chain_index, true, true); +} +EXPORT_SYMBOL(tcf_chain_get_by_act); static void tc_chain_tmplt_del(struct tcf_chain *chain); -void tcf_chain_put(struct tcf_chain *chain) +static void __tcf_chain_put(struct tcf_chain *chain, bool by_act) { - if (--chain->refcnt == 0) { + if (by_act) + chain->action_refcnt--; + chain->refcnt--; + + /* The last dropped non-action reference will trigger notification. */ + if (chain->refcnt - chain->action_refcnt == 0 && !by_act) tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false); + + if (chain->refcnt == 0) { tc_chain_tmplt_del(chain); tcf_chain_destroy(chain); } } -EXPORT_SYMBOL(tcf_chain_put); + +static void tcf_chain_put(struct tcf_chain *chain) +{ + __tcf_chain_put(chain, false); +} + +void tcf_chain_put_by_act(struct tcf_chain *chain) +{ + __tcf_chain_put(chain, true); +} +EXPORT_SYMBOL(tcf_chain_put_by_act); static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) { @@ -316,6 +350,19 @@ static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) tcf_chain_put(chain); } +static void tcf_chain_flush(struct tcf_chain *chain) +{ + struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); + + tcf_chain0_head_change(chain, NULL); + while (tp) { + RCU_INIT_POINTER(chain->filter_chain, tp->next); + tcf_proto_destroy(tp, NULL); + tp = rtnl_dereference(chain->filter_chain); + tcf_chain_put(chain); + } +} + static bool tcf_block_offload_in_use(struct tcf_block *block) { return block->offloadcnt; @@ -1342,6 +1389,13 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, } chain = tcf_chain_get(block, chain_index, false); if (!chain) { + /* User requested flush on non-existent chain. Nothing to do, + * so just return success. + */ + if (prio == 0) { + err = 0; + goto errout; + } NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); err = -EINVAL; goto errout; @@ -1803,20 +1857,28 @@ replay: chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { if (chain) { - NL_SET_ERR_MSG(extack, "Filter chain already exists"); - return -EEXIST; - } - if (!(n->nlmsg_flags & NLM_F_CREATE)) { - NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); - return -ENOENT; - } - chain = tcf_chain_create(block, chain_index); - if (!chain) { - NL_SET_ERR_MSG(extack, "Failed to create filter chain"); - return -ENOMEM; + if (tcf_chain_held_by_acts_only(chain)) { + /* The chain exists only because there is + * some action referencing it. + */ + tcf_chain_hold(chain); + } else { + NL_SET_ERR_MSG(extack, "Filter chain already exists"); + return -EEXIST; + } + } else { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); + return -ENOENT; + } + chain = tcf_chain_create(block, chain_index); + if (!chain) { + NL_SET_ERR_MSG(extack, "Failed to create filter chain"); + return -ENOMEM; + } } } else { - if (!chain) { + if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); return -EINVAL; } @@ -1844,9 +1906,9 @@ replay: * to the chain previously taken during addition. */ tcf_chain_put_explicitly_created(chain); + chain->explicitly_created = false; break; case RTM_GETCHAIN: - break; err = tc_chain_notify(chain, skb, n->nlmsg_seq, n->nlmsg_seq, n->nlmsg_type, true); if (err < 0) @@ -1944,6 +2006,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index++; continue; } + if (tcf_chain_held_by_acts_only(chain)) + continue; err = tc_chain_fill_node(chain, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 66e0ac9811f9..fa6fe2fe0f32 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -349,12 +349,10 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) if (bpf_size != nla_len(tb[TCA_BPF_OPS])) return -EINVAL; - bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + bpf_ops = kmemdup(nla_data(tb[TCA_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; - memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); - fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6ccf60364297..a3b69bb6f4b0 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1250,8 +1250,10 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, goto errout_tb; tmplt = kzalloc(sizeof(*tmplt), GFP_KERNEL); - if (!tmplt) + if (!tmplt) { + err = -ENOMEM; goto errout_tb; + } tmplt->chain = chain; err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack); if (err) @@ -1445,8 +1447,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, TCA_FLOWER_KEY_CVLAN_PRIO, &key->cvlan, &mask->cvlan) || (mask->cvlan.vlan_tpid && - nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, - key->cvlan.vlan_tpid))) + nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, + key->cvlan.vlan_tpid))) goto nla_put_failure; if (mask->basic.n_proto) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 539c9490c308..35fc7252187c 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -80,7 +80,6 @@ #define CAKE_QUEUES (1024) #define CAKE_FLOW_MASK 63 #define CAKE_FLOW_NAT_FLAG 64 -#define CAKE_SPLIT_GSO_THRESHOLD (125000000) /* 1Gbps */ /* struct cobalt_params - contains codel and blue parameters * @interval: codel initial drop rate @@ -2569,10 +2568,12 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_CAKE_MEMORY]) q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]); - if (q->rate_bps && q->rate_bps <= CAKE_SPLIT_GSO_THRESHOLD) - q->rate_flags |= CAKE_FLAG_SPLIT_GSO; - else - q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO; + if (tb[TCA_CAKE_SPLIT_GSO]) { + if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO])) + q->rate_flags |= CAKE_FLAG_SPLIT_GSO; + else + q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO; + } if (q->tins) { sch_tree_lock(sch); @@ -2608,7 +2609,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->target = 5000; /* 5ms: codel RFC argues * for 5 to 10% of interval */ - + q->rate_flags |= CAKE_FLAG_SPLIT_GSO; q->cur_tin = 0; q->cur_flow = 0; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index cdd96b9a27bc..e26a24017faa 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -78,18 +78,42 @@ struct cbs_sched_data { s64 sendslope; /* in bytes/s */ s64 idleslope; /* in bytes/s */ struct qdisc_watchdog watchdog; - int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch); + int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free); struct sk_buff *(*dequeue)(struct Qdisc *sch); + struct Qdisc *qdisc; }; -static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch) +static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, + struct sk_buff **to_free) { - return qdisc_enqueue_tail(skb, sch); + int err; + + err = child->ops->enqueue(skb, child, to_free); + if (err != NET_XMIT_SUCCESS) + return err; + + qdisc_qstats_backlog_inc(sch, skb); + sch->q.qlen++; + + return NET_XMIT_SUCCESS; } -static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch) +static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; + + return cbs_child_enqueue(skb, sch, qdisc, to_free); +} + +static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; if (sch->q.qlen == 0 && q->credits > 0) { /* We need to stop accumulating credits when there's @@ -99,7 +123,7 @@ static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch) q->last = ktime_get_ns(); } - return qdisc_enqueue_tail(skb, sch); + return cbs_child_enqueue(skb, sch, qdisc, to_free); } static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -107,7 +131,7 @@ static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct cbs_sched_data *q = qdisc_priv(sch); - return q->enqueue(skb, sch); + return q->enqueue(skb, sch, to_free); } /* timediff is in ns, slope is in bytes/s */ @@ -132,9 +156,25 @@ static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate) return div64_s64(len * slope, port_rate); } +static struct sk_buff *cbs_child_dequeue(struct Qdisc *sch, struct Qdisc *child) +{ + struct sk_buff *skb; + + skb = child->ops->dequeue(child); + if (!skb) + return NULL; + + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + sch->q.qlen--; + + return skb; +} + static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) { struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; s64 now = ktime_get_ns(); struct sk_buff *skb; s64 credits; @@ -157,8 +197,7 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) return NULL; } } - - skb = qdisc_dequeue_head(sch); + skb = cbs_child_dequeue(sch, qdisc); if (!skb) return NULL; @@ -178,7 +217,10 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch) { - return qdisc_dequeue_head(sch); + struct cbs_sched_data *q = qdisc_priv(sch); + struct Qdisc *qdisc = q->qdisc; + + return cbs_child_dequeue(sch, qdisc); } static struct sk_buff *cbs_dequeue(struct Qdisc *sch) @@ -310,6 +352,13 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; } + q->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + sch->handle, extack); + if (!q->qdisc) + return -ENOMEM; + + qdisc_hash_add(q->qdisc, false); + q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); q->enqueue = cbs_enqueue_soft; @@ -328,6 +377,9 @@ static void cbs_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); cbs_disable_offload(dev, q); + + if (q->qdisc) + qdisc_destroy(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -356,8 +408,72 @@ nla_put_failure: return -1; } +static int cbs_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (cl != 1 || !q->qdisc) /* only one class */ + return -ENOENT; + + tcm->tcm_handle |= TC_H_MIN(1); + tcm->tcm_info = q->qdisc->handle; + + return 0; +} + +static int cbs_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old, struct netlink_ext_ack *extack) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + sch->handle, NULL); + if (!new) + new = &noop_qdisc; + } + + *old = qdisc_replace(sch, new, &q->qdisc); + return 0; +} + +static struct Qdisc *cbs_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->qdisc; +} + +static unsigned long cbs_find(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void cbs_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + if (walker->count >= walker->skip) { + if (walker->fn(sch, 1, walker) < 0) { + walker->stop = 1; + return; + } + } + walker->count++; + } +} + +static const struct Qdisc_class_ops cbs_class_ops = { + .graft = cbs_graft, + .leaf = cbs_leaf, + .find = cbs_find, + .walk = cbs_walk, + .dump = cbs_dump_class, +}; + static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { .id = "cbs", + .cl_ops = &cbs_class_ops, .priv_size = sizeof(struct cbs_sched_data), .enqueue = cbs_enqueue, .dequeue = cbs_dequeue, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 7fc810ec31c5..0fc94f296e54 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -344,20 +344,17 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) rc = smc_ib_modify_qp_rts(link); if (rc) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_RDYLNK; smc_wr_remember_qp_attr(link); if (smc_reg_rmb(link, smc->conn.rmb_desc, false)) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_REGRMB; /* send CONFIRM LINK response over RoCE fabric */ - rc = smc_llc_send_confirm_link(link, - link->smcibdev->mac[link->ibport - 1], - &link->smcibdev->gid[link->ibport - 1], - SMC_LLC_RESP); + rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_CL; /* receive ADD LINK request from server over RoCE fabric */ rest = wait_for_completion_interruptible_timeout(&link->llc_add, @@ -373,10 +370,9 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) /* send add link reject message, only one link supported for now */ rc = smc_llc_send_add_link(link, link->smcibdev->mac[link->ibport - 1], - &link->smcibdev->gid[link->ibport - 1], - SMC_LLC_RESP); + link->gid, SMC_LLC_RESP); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_AL; smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time); @@ -428,9 +424,10 @@ static void smc_link_save_peer_info(struct smc_link *link, } /* fall back during connect */ -static int smc_connect_fallback(struct smc_sock *smc) +static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { smc->use_fallback = true; + smc->fallback_rsn = reason_code; smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) smc->sk.sk_state = SMC_ACTIVE; @@ -447,7 +444,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) sock_put(&smc->sk); /* passive closing */ return reason_code; } - if (reason_code != SMC_CLC_DECL_REPLY) { + if (reason_code != SMC_CLC_DECL_PEERDECL) { rc = smc_clc_send_decline(smc, reason_code); if (rc < 0) { if (smc->sk.sk_state == SMC_INIT) @@ -455,7 +452,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) return rc; } } - return smc_connect_fallback(smc); + return smc_connect_fallback(smc, reason_code); } /* abort connecting */ @@ -472,7 +469,7 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code, /* check if there is a rdma device available for this connection. */ /* called for connect and listen */ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev, - u8 *ibport) + u8 *ibport, unsigned short vlan_id, u8 gid[]) { int reason_code = 0; @@ -480,7 +477,8 @@ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev, * within same PNETID that also contains the ethernet device * used for the internal TCP socket */ - smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport); + smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id, + gid); if (!(*ibdev)) reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ @@ -526,12 +524,12 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd, static int smc_connect_clc(struct smc_sock *smc, int smc_type, struct smc_clc_msg_accept_confirm *aclc, struct smc_ib_device *ibdev, u8 ibport, - struct smcd_dev *ismdev) + u8 gid[], struct smcd_dev *ismdev) { int rc = 0; /* do inband token exchange */ - rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev); + rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev); if (rc) return rc; /* receive SMC Accept CLC message */ @@ -571,7 +569,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_link_save_peer_info(link, aclc); if (smc_rmb_rtoken_handling(&smc->conn, aclc)) - return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK, local_contact); smc_close_init(smc); @@ -579,12 +577,12 @@ static int smc_connect_rdma(struct smc_sock *smc, if (local_contact == SMC_FIRST_CONTACT) { if (smc_ib_ready_link(link)) - return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK, local_contact); } else { if (!smc->conn.rmb_desc->reused && smc_reg_rmb(link, smc->conn.rmb_desc, true)) - return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB, local_contact); } smc_rmb_sync_sg_for_device(&smc->conn); @@ -653,6 +651,7 @@ static int __smc_connect(struct smc_sock *smc) struct smc_clc_msg_accept_confirm aclc; struct smc_ib_device *ibdev; struct smcd_dev *ismdev; + u8 gid[SMC_GID_SIZE]; unsigned short vlan; int smc_type; int rc = 0; @@ -661,11 +660,11 @@ static int __smc_connect(struct smc_sock *smc) sock_hold(&smc->sk); /* sock put in passive closing */ if (smc->use_fallback) - return smc_connect_fallback(smc); + return smc_connect_fallback(smc, smc->fallback_rsn); /* if peer has not signalled SMC-capability, fall back */ if (!tcp_sk(smc->clcsock->sk)->syn_smc) - return smc_connect_fallback(smc); + return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC); /* IPSec connections opt out of SMC-R optimizations */ if (using_ipsec(smc)) @@ -684,7 +683,7 @@ static int __smc_connect(struct smc_sock *smc) } /* check if there is a rdma device available */ - if (!smc_check_rdma(smc, &ibdev, &ibport)) { + if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) { /* RDMA is supported for this connection */ rdma_supported = true; if (ism_supported) @@ -695,10 +694,10 @@ static int __smc_connect(struct smc_sock *smc) /* if neither ISM nor RDMA are supported, fallback */ if (!rdma_supported && !ism_supported) - return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR); + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV); /* perform CLC handshake */ - rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev); + rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev); if (rc) { smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan); return smc_connect_decline_fallback(smc, rc); @@ -710,7 +709,7 @@ static int __smc_connect(struct smc_sock *smc) else if (ism_supported && aclc.hdr.path == SMC_TYPE_D) rc = smc_connect_ism(smc, &aclc, ismdev); else - rc = SMC_CLC_DECL_CNFERR; + rc = SMC_CLC_DECL_MODEUNSUPP; if (rc) { smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan); return smc_connect_decline_fallback(smc, rc); @@ -948,15 +947,12 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) link = &lgr->lnk[SMC_SINGLE_LINK]; if (smc_reg_rmb(link, smc->conn.rmb_desc, false)) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_REGRMB; /* send CONFIRM LINK request to client over the RoCE fabric */ - rc = smc_llc_send_confirm_link(link, - link->smcibdev->mac[link->ibport - 1], - &link->smcibdev->gid[link->ibport - 1], - SMC_LLC_REQ); + rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_CL; /* receive CONFIRM LINK response from client over the RoCE fabric */ rest = wait_for_completion_interruptible_timeout( @@ -976,10 +972,9 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) /* send ADD LINK request to client over the RoCE fabric */ rc = smc_llc_send_add_link(link, link->smcibdev->mac[link->ibport - 1], - &link->smcibdev->gid[link->ibport - 1], - SMC_LLC_REQ); + link->gid, SMC_LLC_REQ); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_AL; /* receive ADD LINK response from client over the RoCE fabric */ rest = wait_for_completion_interruptible_timeout(&link->llc_add_resp, @@ -1054,7 +1049,8 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, } smc_conn_free(&new_smc->conn); new_smc->use_fallback = true; - if (reason_code && reason_code != SMC_CLC_DECL_REPLY) { + new_smc->fallback_rsn = reason_code; + if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code) < 0) { smc_listen_out_err(new_smc); return; @@ -1145,7 +1141,7 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) if (local_contact != SMC_FIRST_CONTACT) { if (!new_smc->conn.rmb_desc->reused) { if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true)) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_REGRMB; } } smc_rmb_sync_sg_for_device(&new_smc->conn); @@ -1165,13 +1161,13 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc, smc_link_save_peer_info(link, cclc); if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) { - reason_code = SMC_CLC_DECL_INTERR; + reason_code = SMC_CLC_DECL_ERR_RTOK; goto decline; } if (local_contact == SMC_FIRST_CONTACT) { if (smc_ib_ready_link(link)) { - reason_code = SMC_CLC_DECL_INTERR; + reason_code = SMC_CLC_DECL_ERR_RDYLNK; goto decline; } /* QP confirmation over RoCE fabric */ @@ -1199,6 +1195,7 @@ static void smc_listen_work(struct work_struct *work) struct smcd_dev *ismdev; u8 buf[SMC_CLC_MAX_LEN]; int local_contact = 0; + unsigned short vlan; int reason_code = 0; int rc = 0; u8 ibport; @@ -1211,6 +1208,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { new_smc->use_fallback = true; + new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; smc_listen_out_connected(new_smc); return; } @@ -1247,14 +1245,16 @@ static void smc_listen_work(struct work_struct *work) /* check if RDMA is available */ if (!ism_supported && ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) || - smc_check_rdma(new_smc, &ibdev, &ibport) || + smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) || + smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) || smc_listen_rdma_check(new_smc, pclc) || smc_listen_rdma_init(new_smc, pclc, ibdev, ibport, &local_contact) || smc_listen_rdma_reg(new_smc, local_contact))) { /* SMC not supported, decline */ mutex_unlock(&smc_create_lgr_pending); - smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact); + smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP, + local_contact); return; } @@ -1301,6 +1301,7 @@ static void smc_tcp_listen_work(struct work_struct *work) new_smc->listen_smc = lsmc; new_smc->use_fallback = lsmc->use_fallback; + new_smc->fallback_rsn = lsmc->fallback_rsn; sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); @@ -1455,6 +1456,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT) { smc->use_fallback = true; + smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { rc = -EINVAL; goto out; @@ -1533,7 +1535,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, mask |= EPOLLERR; } else { if (sk->sk_state != SMC_CLOSED) - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_err) mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || @@ -1652,6 +1654,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, /* option not supported by SMC */ if (sk->sk_state == SMC_INIT) { smc->use_fallback = true; + smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { if (!smc->use_fallback) rc = -EINVAL; @@ -1889,6 +1892,7 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); smc->use_fallback = false; /* assume rdma capability first */ + smc->fallback_rsn = 0; rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); if (rc) { diff --git a/net/smc/smc.h b/net/smc/smc.h index be20acd7b5ab..08786ace6010 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -208,6 +208,8 @@ struct smc_sock { /* smc sock container */ struct list_head accept_q; /* sockets to be accepted */ spinlock_t accept_q_lock; /* protects accept_q */ bool use_fallback; /* fallback to tcp */ + int fallback_rsn; /* reason for fallback */ + u32 peer_diagnosis; /* decline reason from peer */ int sockopt_defer_accept; /* sockopt TCP_DEFER_ACCEPT * value diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a7af2289cdff..ed5dcf03fe0b 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -278,7 +278,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, /* force immediate tx of current consumer cursor, but * under send_lock to guarantee arrival in seqno-order */ - smc_tx_sndbuf_nonempty(conn); + if (smc->sk.sk_state != SMC_INIT) + smc_tx_sndbuf_nonempty(conn); } } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index ad39efdb4f1c..83aba9ade060 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -334,7 +334,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, goto out; } if (clcm->type == SMC_CLC_DECLINE) { - reason_code = SMC_CLC_DECL_REPLY; + struct smc_clc_msg_decline *dclc; + + dclc = (struct smc_clc_msg_decline *)clcm; + reason_code = SMC_CLC_DECL_PEERDECL; + smc->peer_diagnosis = ntohl(dclc->peer_diagnosis); if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { smc->conn.lgr->sync_err = 1; smc_lgr_terminate(smc->conn.lgr); @@ -378,7 +382,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) /* send CLC PROPOSAL message across internal TCP socket */ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, - struct smc_ib_device *ibdev, u8 ibport, + struct smc_ib_device *ibdev, u8 ibport, u8 gid[], struct smcd_dev *ismdev) { struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX]; @@ -409,7 +413,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, /* add SMC-R specifics */ memcpy(pclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE); + memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE); memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN); pclc.iparea_offset = htons(0); } @@ -492,8 +496,7 @@ int smc_clc_send_confirm(struct smc_sock *smc) cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); memcpy(cclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1], - SMC_GID_SIZE); + memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE); memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(cclc.qpn, link->roce_qp->qp_num); @@ -566,8 +569,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) link = &conn->lgr->lnk[SMC_SINGLE_LINK]; memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1], - SMC_GID_SIZE); + memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE); memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(aclc.qpn, link->roce_qp->qp_num); diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 100e988ad1a8..18da89b681c2 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -28,15 +28,21 @@ #define SMC_TYPE_B 3 /* SMC-R and SMC-D */ #define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */ #define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */ -#define SMC_CLC_DECL_TIMEOUT 0x02000000 /* timeout */ +#define SMC_CLC_DECL_TIMEOUT_CL 0x02010000 /* timeout w4 QP confirm link */ +#define SMC_CLC_DECL_TIMEOUT_AL 0x02020000 /* timeout w4 QP add link */ #define SMC_CLC_DECL_CNFERR 0x03000000 /* configuration error */ -#define SMC_CLC_DECL_IPSEC 0x03030000 /* IPsec usage */ +#define SMC_CLC_DECL_PEERNOSMC 0x03010000 /* peer did not indicate SMC */ +#define SMC_CLC_DECL_IPSEC 0x03020000 /* IPsec usage */ +#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found */ +#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ +#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ +#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ -#define SMC_CLC_DECL_REPLY 0x06000000 /* reply to a received decline */ +#define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */ -#define SMC_CLC_DECL_TCL 0x02040000 /* timeout w4 QP confirm */ -#define SMC_CLC_DECL_SEND 0x07000000 /* sending problem */ -#define SMC_CLC_DECL_RMBE_EC 0x08000000 /* peer has eyecatcher in RMBE */ +#define SMC_CLC_DECL_ERR_RTOK 0x99990001 /* rtoken handling failed */ +#define SMC_CLC_DECL_ERR_RDYLNK 0x99990002 /* ib ready link failed */ +#define SMC_CLC_DECL_ERR_REGRMB 0x99990003 /* reg rmb failed */ struct smc_clc_msg_hdr { /* header1 of clc messages */ u8 eyecatcher[4]; /* eye catcher */ @@ -179,7 +185,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type); int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info); int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, - struct smc_ib_device *smcibdev, u8 ibport, + struct smc_ib_device *smcibdev, u8 ibport, u8 gid[], struct smcd_dev *ismdev); int smc_clc_send_confirm(struct smc_sock *smc); int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 66741e61a3b0..a46418f45ecd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -30,6 +30,7 @@ #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) +#define SMC_LGR_FREE_DELAY_FAST (8 * HZ) static struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), @@ -51,6 +52,11 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV); } +void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr) +{ + mod_delayed_work(system_wq, &lgr->free_work, SMC_LGR_FREE_DELAY_FAST); +} + /* Register connection's alert token in our lookup structure. * To use rbtrees we have to implement our own insert core. * Requires @conns_lock @@ -133,6 +139,20 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) smc_lgr_schedule_free_work(lgr); } +/* Send delete link, either as client to request the initiation + * of the DELETE LINK sequence from server; or as server to + * initiate the delete processing. See smc_llc_rx_delete_link(). + */ +static int smc_link_send_delete(struct smc_link *lnk) +{ + if (lnk->state == SMC_LNK_ACTIVE && + !smc_llc_send_delete_link(lnk, SMC_LLC_REQ, true)) { + smc_llc_link_deleting(lnk); + return 0; + } + return -ENOTCONN; +} + static void smc_lgr_free_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(to_delayed_work(work), @@ -153,10 +173,21 @@ static void smc_lgr_free_work(struct work_struct *work) list_del_init(&lgr->list); /* remove from smc_lgr_list */ free: spin_unlock_bh(&smc_lgr_list.lock); + + if (!lgr->is_smcd && !lgr->terminating) { + /* try to send del link msg, on error free lgr immediately */ + if (!smc_link_send_delete(&lgr->lnk[SMC_SINGLE_LINK])) { + /* reschedule in case we never receive a response */ + smc_lgr_schedule_free_work(lgr); + return; + } + } + if (!delayed_work_pending(&lgr->free_work)) { - if (!lgr->is_smcd && - lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE) - smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; + + if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE) + smc_llc_link_inactive(lnk); smc_lgr_free(lgr); } } @@ -219,6 +250,10 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd, get_random_bytes(rndvec, sizeof(rndvec)); lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); + rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport, + vlan_id, lnk->gid, &lnk->sgid_index); + if (rc) + goto free_lgr; rc = smc_llc_link_init(lnk); if (rc) goto free_lgr; @@ -522,37 +557,6 @@ out: return rc; } -/* determine the link gid matching the vlan id of the link group */ -static int smc_link_determine_gid(struct smc_link_group *lgr) -{ - struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; - struct ib_gid_attr gattr; - union ib_gid gid; - int i; - - if (!lgr->vlan_id) { - lnk->gid = lnk->smcibdev->gid[lnk->ibport - 1]; - return 0; - } - - for (i = 0; i < lnk->smcibdev->pattr[lnk->ibport - 1].gid_tbl_len; - i++) { - if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid, - &gattr)) - continue; - if (gattr.ndev) { - if (is_vlan_dev(gattr.ndev) && - vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) { - lnk->gid = gid; - dev_put(gattr.ndev); - return 0; - } - dev_put(gattr.ndev); - } - } - return -ENODEV; -} - static bool smcr_lgr_match(struct smc_link_group *lgr, struct smc_clc_msg_local *lcl, enum smc_lgr_role role) @@ -631,8 +635,6 @@ create: if (rc) goto out; smc_lgr_register_conn(conn); /* add smc conn to lgr */ - if (!is_smcd) - rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; @@ -1013,8 +1015,14 @@ void smc_core_exit(void) spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) { list_del_init(&lgr->list); - if (!lgr->is_smcd) - smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + if (!lgr->is_smcd) { + struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; + + if (lnk->state == SMC_LNK_ACTIVE) + smc_llc_send_delete_link(lnk, SMC_LLC_REQ, + false); + smc_llc_link_inactive(lnk); + } cancel_delayed_work_sync(&lgr->free_work); smc_lgr_free(lgr); /* free link group */ } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 1e8974c50550..c156674733c9 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -34,7 +34,8 @@ enum smc_lgr_role { /* possible roles of a link group */ enum smc_link_state { /* possible states of a link */ SMC_LNK_INACTIVE, /* link is inactive */ SMC_LNK_ACTIVATING, /* link is being activated */ - SMC_LNK_ACTIVE /* link is active */ + SMC_LNK_ACTIVE, /* link is active */ + SMC_LNK_DELETING, /* link is being deleted */ }; #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ @@ -84,14 +85,15 @@ struct smc_link { wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ - union ib_gid gid; /* gid matching used vlan id */ + u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ + u8 sgid_index; /* gid index for vlan id */ u32 peer_qpn; /* QP number of peer */ enum ib_mtu path_mtu; /* used mtu */ enum ib_mtu peer_mtu; /* mtu size of peer */ u32 psn_initial; /* QP tx initial packet seqno */ u32 peer_psn; /* QP rx initial packet seqno */ u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */ - u8 peer_gid[sizeof(union ib_gid)]; /* gid of peer*/ + u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/ u8 link_id; /* unique # within link group */ enum smc_link_state state; /* state of link */ @@ -264,6 +266,7 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, u64 peer_gid); void smcd_conn_free(struct smc_connection *conn); +void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr); void smc_core_exit(void); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index d772cd10297e..dbf64a93d68a 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -79,6 +79,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, struct nlattr *bc) { struct smc_sock *smc = smc_sk(sk); + struct smc_diag_fallback fallback; struct user_namespace *user_ns; struct smc_diag_msg *r; struct nlmsghdr *nlh; @@ -101,6 +102,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns)) goto errout; + fallback.reason = smc->fallback_rsn; + fallback.peer_diagnosis = smc->peer_diagnosis; + if (nla_put(skb, SMC_DIAG_FALLBACK, sizeof(fallback), &fallback) < 0) + goto errout; + if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) && smc->conn.alert_token_local) { struct smc_connection *conn = &smc->conn; @@ -154,7 +160,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, smc->conn.lgr->lnk[0].smcibdev->ibdev->name, sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name)); smc_gid_be16_convert(linfo.lnk[0].gid, - smc->conn.lgr->lnk[0].gid.raw); + smc->conn.lgr->lnk[0].gid); smc_gid_be16_convert(linfo.lnk[0].peer_gid, smc->conn.lgr->lnk[0].peer_gid); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 4706ab7092a9..2cc64bc8ae20 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -68,7 +68,7 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk) qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu); qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport); - rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, 0, 1, 0); + rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0); rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid); memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac, sizeof(lnk->peer_mac)); @@ -142,13 +142,13 @@ out: return rc; } -static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) +static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport) { struct ib_gid_attr gattr; + union ib_gid gid; int rc; - rc = ib_query_gid(smcibdev->ibdev, ibport, 0, - &smcibdev->gid[ibport - 1], &gattr); + rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr); if (rc || !gattr.ndev) return -ENODEV; @@ -175,6 +175,37 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } +/* determine the gid for an ib-device port and vlan id */ +int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, + unsigned short vlan_id, u8 gid[], u8 *sgid_index) +{ + struct ib_gid_attr gattr; + union ib_gid _gid; + int i; + + for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { + memset(&_gid, 0, SMC_GID_SIZE); + memset(&gattr, 0, sizeof(gattr)); + if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr)) + continue; + if (!gattr.ndev) + continue; + if (((!vlan_id && !is_vlan_dev(gattr.ndev)) || + (vlan_id && is_vlan_dev(gattr.ndev) && + vlan_dev_vlan_id(gattr.ndev) == vlan_id)) && + gattr.gid_type == IB_GID_TYPE_IB) { + if (gid) + memcpy(gid, &_gid, SMC_GID_SIZE); + if (sgid_index) + *sgid_index = i; + dev_put(gattr.ndev); + return 0; + } + dev_put(gattr.ndev); + } + return -ENODEV; +} + static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) { int rc; @@ -186,7 +217,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) if (rc) goto out; /* the SMC protocol requires specification of the RoCE MAC address */ - rc = smc_ib_fill_gid_and_mac(smcibdev, ibport); + rc = smc_ib_fill_mac(smcibdev, ibport); if (rc) goto out; if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET, diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 7c1223c91229..bac7fd65a4c0 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -40,7 +40,6 @@ struct smc_ib_device { /* ib-device infos for smc */ struct tasklet_struct recv_tasklet; /* called by recv cq handler */ char mac[SMC_MAX_PORTS][ETH_ALEN]; /* mac address per port*/ - union ib_gid gid[SMC_MAX_PORTS]; /* gid per port */ u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN]; /* pnetid per port */ u8 initialized : 1; /* ib dev CQ, evthdl done */ @@ -77,4 +76,6 @@ void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev, void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); +int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, + unsigned short vlan_id, u8 gid[], u8 *sgid_index); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index b7944aa1ffc3..9c916c709ca7 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -182,8 +182,7 @@ static int smc_llc_add_pending_send(struct smc_link *link, } /* high-level API to send LLC confirm link */ -int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], - union ib_gid *gid, +int smc_llc_send_confirm_link(struct smc_link *link, enum smc_llc_reqresp reqresp) { struct smc_link_group *lgr = smc_get_lgr(link); @@ -202,8 +201,9 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC; if (reqresp == SMC_LLC_RESP) confllc->hd.flags |= SMC_LLC_FLAG_RESP; - memcpy(confllc->sender_mac, mac, ETH_ALEN); - memcpy(confllc->sender_gid, gid, SMC_GID_SIZE); + memcpy(confllc->sender_mac, link->smcibdev->mac[link->ibport - 1], + ETH_ALEN); + memcpy(confllc->sender_gid, link->gid, SMC_GID_SIZE); hton24(confllc->sender_qp_num, link->roce_qp->qp_num); confllc->link_num = link->link_id; memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE); @@ -240,8 +240,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *link, /* prepare an add link message */ static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc, - struct smc_link *link, u8 mac[], - union ib_gid *gid, + struct smc_link *link, u8 mac[], u8 gid[], enum smc_llc_reqresp reqresp) { memset(addllc, 0, sizeof(*addllc)); @@ -258,8 +257,7 @@ static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc, } /* send ADD LINK request or response */ -int smc_llc_send_add_link(struct smc_link *link, u8 mac[], - union ib_gid *gid, +int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[], enum smc_llc_reqresp reqresp) { struct smc_llc_msg_add_link *addllc; @@ -280,7 +278,7 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], /* prepare a delete link message */ static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc, struct smc_link *link, - enum smc_llc_reqresp reqresp) + enum smc_llc_reqresp reqresp, bool orderly) { memset(delllc, 0, sizeof(*delllc)); delllc->hd.common.type = SMC_LLC_DELETE_LINK; @@ -289,13 +287,14 @@ static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc, delllc->hd.flags |= SMC_LLC_FLAG_RESP; /* DEL_LINK_ALL because only 1 link supported */ delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL; - delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; + if (orderly) + delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; delllc->link_num = link->link_id; } /* send DELETE LINK request or response */ int smc_llc_send_delete_link(struct smc_link *link, - enum smc_llc_reqresp reqresp) + enum smc_llc_reqresp reqresp, bool orderly) { struct smc_llc_msg_del_link *delllc; struct smc_wr_tx_pend_priv *pend; @@ -306,7 +305,7 @@ int smc_llc_send_delete_link(struct smc_link *link, if (rc) return rc; delllc = (struct smc_llc_msg_del_link *)wr_buf; - smc_llc_prep_delete_link(delllc, link, reqresp); + smc_llc_prep_delete_link(delllc, link, reqresp, orderly); /* send llc message */ rc = smc_wr_tx_send(link, pend); return rc; @@ -422,14 +421,12 @@ static void smc_llc_rx_add_link(struct smc_link *link, if (lgr->role == SMC_SERV) { smc_llc_prep_add_link(llc, link, link->smcibdev->mac[link->ibport - 1], - &link->smcibdev->gid[link->ibport - 1], - SMC_LLC_REQ); + link->gid, SMC_LLC_REQ); } else { smc_llc_prep_add_link(llc, link, link->smcibdev->mac[link->ibport - 1], - &link->smcibdev->gid[link->ibport - 1], - SMC_LLC_RESP); + link->gid, SMC_LLC_RESP); } smc_llc_send_message(link, llc, sizeof(*llc)); } @@ -442,17 +439,19 @@ static void smc_llc_rx_delete_link(struct smc_link *link, if (llc->hd.flags & SMC_LLC_FLAG_RESP) { if (lgr->role == SMC_SERV) - smc_lgr_terminate(lgr); + smc_lgr_schedule_free_work_fast(lgr); } else { + smc_lgr_forget(lgr); + smc_llc_link_deleting(link); if (lgr->role == SMC_SERV) { - smc_lgr_forget(lgr); - smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ); - smc_llc_send_message(link, llc, sizeof(*llc)); + /* client asks to delete this link, send request */ + smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ, true); } else { - smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP); - smc_llc_send_message(link, llc, sizeof(*llc)); - smc_lgr_terminate(lgr); + /* server requests to delete this link, send response */ + smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP, true); } + smc_llc_send_message(link, llc, sizeof(*llc)); + smc_lgr_schedule_free_work_fast(lgr); } } @@ -626,6 +625,11 @@ void smc_llc_link_active(struct smc_link *link, int testlink_time) } } +void smc_llc_link_deleting(struct smc_link *link) +{ + link->state = SMC_LNK_DELETING; +} + /* called in tasklet context */ void smc_llc_link_inactive(struct smc_link *link) { diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index 65c8645e96a1..9e2ff088e301 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -36,14 +36,15 @@ enum smc_llc_msg_type { }; /* transmit */ -int smc_llc_send_confirm_link(struct smc_link *lnk, u8 mac[], union ib_gid *gid, +int smc_llc_send_confirm_link(struct smc_link *lnk, enum smc_llc_reqresp reqresp); -int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid, +int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[], enum smc_llc_reqresp reqresp); int smc_llc_send_delete_link(struct smc_link *link, - enum smc_llc_reqresp reqresp); + enum smc_llc_reqresp reqresp, bool orderly); int smc_llc_link_init(struct smc_link *link); void smc_llc_link_active(struct smc_link *link, int testlink_time); +void smc_llc_link_deleting(struct smc_link *link); void smc_llc_link_inactive(struct smc_link *link); void smc_llc_link_clear(struct smc_link *link); int smc_llc_do_confirm_rkey(struct smc_link *link, diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 1b6c066d3495..01c6ce042a1c 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -535,11 +535,13 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) } /* Determine the corresponding IB device port based on the hardware PNETID. - * Searching stops at the first matching active IB device port. + * Searching stops at the first matching active IB device port with vlan_id + * configured. */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_ib_device **smcibdev, - u8 *ibport) + u8 *ibport, unsigned short vlan_id, + u8 gid[]) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smc_ib_device *ibdev; @@ -553,15 +555,20 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, spin_lock(&smc_ib_devices.lock); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (i = 1; i <= SMC_MAX_PORTS; i++) { + if (!rdma_is_port_valid(ibdev->ibdev, i)) + continue; if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid, SMC_MAX_PNETID_LEN) && - smc_ib_port_active(ibdev, i)) { + smc_ib_port_active(ibdev, i) && + !smc_ib_determine_gid(ibdev, i, vlan_id, gid, + NULL)) { *smcibdev = ibdev; *ibport = i; - break; + goto out; } } } +out: spin_unlock(&smc_ib_devices.lock); } @@ -589,7 +596,8 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, /* Lookup of coupled ib_device via SMC pnet table */ static void smc_pnet_find_roce_by_table(struct net_device *netdev, struct smc_ib_device **smcibdev, - u8 *ibport) + u8 *ibport, unsigned short vlan_id, + u8 gid[]) { struct smc_pnetentry *pnetelem; @@ -597,7 +605,10 @@ static void smc_pnet_find_roce_by_table(struct net_device *netdev, list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { if (netdev == pnetelem->ndev) { if (smc_ib_port_active(pnetelem->smcibdev, - pnetelem->ib_port)) { + pnetelem->ib_port) && + !smc_ib_determine_gid(pnetelem->smcibdev, + pnetelem->ib_port, vlan_id, + gid, NULL)) { *smcibdev = pnetelem->smcibdev; *ibport = pnetelem->ib_port; } @@ -612,7 +623,8 @@ static void smc_pnet_find_roce_by_table(struct net_device *netdev, * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, - struct smc_ib_device **smcibdev, u8 *ibport) + struct smc_ib_device **smcibdev, u8 *ibport, + unsigned short vlan_id, u8 gid[]) { struct dst_entry *dst = sk_dst_get(sk); @@ -625,12 +637,12 @@ void smc_pnet_find_roce_resource(struct sock *sk, goto out_rel; /* if possible, lookup via hardware-defined pnetid */ - smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport); + smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid); if (*smcibdev) goto out_rel; /* lookup via SMC PNET table */ - smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport); + smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport, vlan_id, gid); out_rel: dst_release(dst); diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h index 1e94fd4df7bc..8ff777636e32 100644 --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -33,7 +33,8 @@ int smc_pnet_init(void) __init; void smc_pnet_exit(void); int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev); void smc_pnet_find_roce_resource(struct sock *sk, - struct smc_ib_device **smcibdev, u8 *ibport); + struct smc_ib_device **smcibdev, u8 *ibport, + unsigned short vlan_id, u8 gid[]); void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev); #endif diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index b6df69756bef..f856b8402b3f 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -182,17 +182,14 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, if (rc) return rc; } else { - struct smc_link_group *lgr; - - lgr = smc_get_lgr(link); rc = wait_event_timeout( link->wr_tx_wait, - list_empty(&lgr->list) || /* lgr terminated */ + link->state == SMC_LNK_INACTIVE || (smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY), SMC_WR_TX_WAIT_FREE_SLOT_TIME); if (!rc) { /* timeout - terminate connections */ - smc_lgr_terminate(lgr); + smc_lgr_terminate(smc_get_lgr(link)); return -EPIPE; } if (idx == link->wr_tx_cnt) diff --git a/net/socket.c b/net/socket.c index 85633622c94d..b91949168a87 100644 --- a/net/socket.c +++ b/net/socket.c @@ -89,6 +89,7 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -251,7 +252,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb) init_waitqueue_head(&wq->wait); wq->fasync_list = NULL; wq->flags = 0; - RCU_INIT_POINTER(ei->socket.wq, wq); + ei->socket.wq = wq; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; @@ -265,11 +266,9 @@ static struct inode *sock_alloc_inode(struct super_block *sb) static void sock_destroy_inode(struct inode *inode) { struct socket_alloc *ei; - struct socket_wq *wq; ei = container_of(inode, struct socket_alloc, vfs_inode); - wq = rcu_dereference_protected(ei->socket.wq, 1); - kfree_rcu(wq, rcu); + kfree_rcu(ei->socket.wq, rcu); kmem_cache_free(sock_inode_cachep, ei); } @@ -603,7 +602,7 @@ static void __sock_release(struct socket *sock, struct inode *inode) module_put(owner); } - if (rcu_dereference_protected(sock->wq, 1)->fasync_list) + if (sock->wq->fasync_list) pr_err("%s: fasync list not empty!\n", __func__); if (!sock->file) { @@ -1130,12 +1129,21 @@ EXPORT_SYMBOL(sock_create_lite); static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; - __poll_t events = poll_requested_events(wait); + __poll_t events = poll_requested_events(wait), flag = 0; - sock_poll_busy_loop(sock, events); if (!sock->ops->poll) return 0; - return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock); + + if (sk_can_busy_loop(sock->sk)) { + /* poll once if requested by the syscall */ + if (events & POLL_BUSY_LOOP) + sk_busy_loop(sock->sk, 1); + + /* if this socket can poll_ll, tell the system call */ + flag = POLL_BUSY_LOOP; + } + + return sock->ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) @@ -1172,7 +1180,7 @@ static int sock_fasync(int fd, struct file *filp, int on) return -EINVAL; lock_sock(sk); - wq = rcu_dereference_protected(sock->wq, lockdep_sock_is_held(sk)); + wq = sock->wq; fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) @@ -2522,6 +2530,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; + call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) @@ -2688,7 +2697,8 @@ EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { - return family < NPROTO && rcu_access_pointer(net_families[family]); + return family < NPROTO && + rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]); } static int __init sock_init(void) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 3a512936eea9..da1a676860ca 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -408,8 +408,6 @@ EXPORT_SYMBOL_GPL(strp_data_ready); static void do_strp_work(struct strparser *strp) { - read_descriptor_t rd_desc; - /* We need the read lock to synchronize with strp_data_ready. We * need the socket lock for calling strp_read_sock. */ @@ -421,8 +419,6 @@ static void do_strp_work(struct strparser *strp) if (strp->paused) goto out; - rd_desc.arg.data = strp; - if (strp_read_sock(strp) == -ENOMEM) queue_work(strp_wq, &strp->work); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index be8f103d22fd..0fc397fae42b 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -517,7 +517,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); if (err) goto err_put_pipe_version; - }; + } kref_get(&gss_auth->kref); return gss_msg; err_put_pipe_version: diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index f3711176be45..9ee6cfea56dd 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -512,7 +512,7 @@ int tipc_bcast_init(struct net *net) struct tipc_bc_base *bb = NULL; struct tipc_link *l = NULL; - bb = kzalloc(sizeof(*bb), GFP_ATOMIC); + bb = kzalloc(sizeof(*bb), GFP_KERNEL); if (!bb) goto enomem; tn->bcbase = bb; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index fd6d8f18955c..418f03d0be90 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -395,6 +395,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, tipc_net_init(net, node_id, 0); } if (!tipc_own_id(net)) { + dev_put(dev); pr_warn("Failed to obtain node identity\n"); return -EINVAL; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bebe88cae07b..88f027b502f6 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -735,7 +735,7 @@ int tipc_nametbl_init(struct net *net) struct name_table *nt; int i; - nt = kzalloc(sizeof(*nt), GFP_ATOMIC); + nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return -ENOMEM; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3d21414ba357..c1e93c9515bc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -411,7 +411,6 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, int kern) { - struct tipc_net *tn; const struct proto_ops *ops; struct sock *sk; struct tipc_sock *tsk; @@ -446,7 +445,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, INIT_LIST_HEAD(&tsk->publications); INIT_LIST_HEAD(&tsk->cong_links); msg = &tsk->phdr; - tn = net_generic(sock_net(sk), tipc_net_id); /* Finish initializing socket data structures */ sock->ops = ops; @@ -716,7 +714,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, struct tipc_sock *tsk = tipc_sk(sk); __poll_t revents = 0; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_shutdown & RCV_SHUTDOWN) revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; @@ -1117,7 +1115,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, u32 self = tipc_own_addr(net); u32 type, lower, upper, scope; struct sk_buff *skb, *_skb; - u32 portid, oport, onode; + u32 portid, onode; struct sk_buff_head tmpq; struct list_head dports; struct tipc_msg *hdr; @@ -1133,7 +1131,6 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, user = msg_user(hdr); mtyp = msg_type(hdr); hlen = skb_headroom(skb) + msg_hdr_sz(hdr); - oport = msg_origport(hdr); onode = msg_orignode(hdr); type = msg_nametype(hdr); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1e968d238adf..292742e50bfa 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -716,12 +716,11 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); ctx->tx.rec_seq_size = rec_seq_size; - ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL); + ctx->tx.rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL); if (!ctx->tx.rec_seq) { rc = -ENOMEM; goto free_iv; } - memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size); rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info); if (rc) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0c2d029c9d4c..83d67df33f0c 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -263,7 +263,7 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from, int length, int *pages_used, unsigned int *size_used, struct scatterlist *to, int to_max_pages, - bool charge, bool revert) + bool charge) { struct page *pages[MAX_SKB_FRAGS]; @@ -311,11 +311,14 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from, } } + /* Mark the end in the last sg entry if newly added */ + if (num_elem > *pages_used) + sg_mark_end(&to[num_elem - 1]); out: + if (rc) + iov_iter_revert(from, size - *size_used); *size_used = size; *pages_used = num_elem; - if (revert) - iov_iter_revert(from, size); return rc; } @@ -362,6 +365,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int record_room; bool full_record; int orig_size; + bool is_kvec = msg->msg_iter.type & ITER_KVEC; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -ENOTSUPP; @@ -410,28 +414,23 @@ alloc_encrypted: try_to_copy -= required_size - ctx->sg_encrypted_size; full_record = true; } - - if (full_record || eor) { + if (!is_kvec && (full_record || eor)) { ret = zerocopy_from_iter(sk, &msg->msg_iter, try_to_copy, &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, ctx->sg_plaintext_data, ARRAY_SIZE(ctx->sg_plaintext_data), - true, false); + true); if (ret) goto fallback_to_reg_send; copied += try_to_copy; ret = tls_push_record(sk, msg->msg_flags, record_type); - if (!ret) - continue; - if (ret < 0) + if (ret) goto send_end; + continue; - copied -= try_to_copy; fallback_to_reg_send: - iov_iter_revert(&msg->msg_iter, - ctx->sg_plaintext_size - orig_size); trim_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, @@ -631,6 +630,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return NULL; } + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + if (sock_flag(sk, SOCK_DONE)) return NULL; @@ -776,6 +778,7 @@ int tls_sw_recvmsg(struct sock *sk, bool cmsg = false; int target, err = 0; long timeo; + bool is_kvec = msg->msg_iter.type & ITER_KVEC; flags |= nonblock; @@ -819,7 +822,7 @@ int tls_sw_recvmsg(struct sock *sk, page_count = iov_iter_npages(&msg->msg_iter, MAX_SKB_FRAGS); to_copy = rxm->full_len - tls_ctx->rx.overhead_size; - if (to_copy <= len && page_count < MAX_SKB_FRAGS && + if (!is_kvec && to_copy <= len && page_count < MAX_SKB_FRAGS && likely(!(flags & MSG_PEEK))) { struct scatterlist sgin[MAX_SKB_FRAGS + 1]; int pages = 0; @@ -832,7 +835,7 @@ int tls_sw_recvmsg(struct sock *sk, err = zerocopy_from_iter(sk, &msg->msg_iter, to_copy, &pages, &chunk, &sgin[1], - MAX_SKB_FRAGS, false, true); + MAX_SKB_FRAGS, false); if (err < 0) goto fallback_to_reg_recv; @@ -1028,7 +1031,7 @@ static void tls_queue(struct strparser *strp, struct sk_buff *skb) ctx->recv_pkt = skb; strp_pause(strp); - strp->sk->sk_state_change(strp->sk); + ctx->saved_data_ready(strp->sk); } static void tls_data_ready(struct sock *sk) @@ -1044,8 +1047,7 @@ void tls_sw_free_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - if (ctx->aead_send) - crypto_free_aead(ctx->aead_send); + crypto_free_aead(ctx->aead_send); tls_free_both_sg(sk); kfree(ctx); @@ -1057,10 +1059,8 @@ void tls_sw_release_resources_rx(struct sock *sk) struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); if (ctx->aead_recv) { - if (ctx->recv_pkt) { - kfree_skb(ctx->recv_pkt); - ctx->recv_pkt = NULL; - } + kfree_skb(ctx->recv_pkt); + ctx->recv_pkt = NULL; crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); write_lock_bh(&sk->sk_callback_lock); @@ -1176,12 +1176,11 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); cctx->rec_seq_size = rec_seq_size; - cctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL); + cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL); if (!cctx->rec_seq) { rc = -ENOMEM; goto free_iv; } - memcpy(cctx->rec_seq, rec_seq, rec_seq_size); if (sw_ctx_tx) { sg_init_table(sw_ctx_tx->sg_encrypted_data, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e5473c03d667..d1edfa3cad61 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -430,7 +430,12 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) connected = unix_dgram_peer_wake_connect(sk, other); - if (unix_recvq_full(other)) + /* If other is SOCK_DEAD, we want to make sure we signal + * POLLOUT, such that a subsequent write() can get a + * -ECONNREFUSED. Otherwise, if we haven't queued any skbs + * to other and its full, we will hang waiting for POLLOUT. + */ + if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD)) return 1; if (connected) @@ -2635,7 +2640,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa struct sock *sk = sock->sk; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ @@ -2672,7 +2677,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, unsigned int writable; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e4e5f025d16b..5fb9b7dd9831 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4466,6 +4466,7 @@ static int parse_station_flags(struct genl_info *info, params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHORIZED); + break; default: return -EINVAL; } @@ -15029,20 +15030,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, EXPORT_SYMBOL(cfg80211_mgmt_tx_status); static int __nl80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, + struct sk_buff *skb, bool unencrypted, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct ethhdr *ehdr = eth_hdr(skb); + const u8 *addr = ehdr->h_source; + u16 proto = be16_to_cpu(skb->protocol); struct sk_buff *msg; void *hdr; + struct nlattr *frame; + u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid); if (!nlportid) return -ENOENT; - msg = nlmsg_new(100 + len, gfp); + msg = nlmsg_new(100 + skb->len, gfp); if (!msg) return -ENOMEM; @@ -15056,13 +15061,17 @@ static int __nl80211_rx_control_port(struct net_device *dev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || - nla_put(msg, NL80211_ATTR_FRAME, len, buf) || nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) || (unencrypted && nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT))) goto nla_put_failure; + frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len); + if (!frame) + goto nla_put_failure; + + skb_copy_bits(skb, 0, nla_data(frame), skb->len); genlmsg_end(msg, hdr); return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); @@ -15073,14 +15082,12 @@ static int __nl80211_rx_control_port(struct net_device *dev, } bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted) + struct sk_buff *skb, bool unencrypted) { int ret; - trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted); - ret = __nl80211_rx_control_port(dev, buf, len, addr, proto, - unencrypted, GFP_ATOMIC); + trace_cfg80211_rx_control_port(dev, skb, unencrypted); + ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC); trace_cfg80211_return_bool(ret == 0); return ret == 0; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index bbe6298e4bb9..4fc66a117b7d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, * as some drivers used this to restore its orig_* reg domain. */ if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG && + !(wiphy->regulatory_flags & + REGULATORY_WIPHY_SELF_MANAGED)) reg_call_notifier(wiphy, lr); return; } @@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) } } -static bool reg_only_self_managed_wiphys(void) -{ - struct cfg80211_registered_device *rdev; - struct wiphy *wiphy; - bool self_managed_found = false; - - ASSERT_RTNL(); - - list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - wiphy = &rdev->wiphy; - if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) - self_managed_found = true; - else - return false; - } - - /* make sure at least one self-managed wiphy exists */ - return self_managed_found; -} - /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we @@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); notify_self_managed_wiphys(reg_request); - if (reg_only_self_managed_wiphys()) { - reg_free_request(reg_request); - return; - } reg_process_hint(reg_request); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2b417a2fe63f..7c73510b161f 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, ); TRACE_EVENT(cfg80211_rx_control_port, - TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted), - TP_ARGS(netdev, buf, len, addr, proto, unencrypted), + TP_PROTO(struct net_device *netdev, struct sk_buff *skb, + bool unencrypted), + TP_ARGS(netdev, skb, unencrypted), TP_STRUCT__entry( NETDEV_ENTRY - MAC_ENTRY(addr) + __field(int, len) + MAC_ENTRY(from) __field(u16, proto) __field(bool, unencrypted) ), TP_fast_assign( NETDEV_ASSIGN; - MAC_ASSIGN(addr, addr); - __entry->proto = proto; + __entry->len = skb->len; + MAC_ASSIGN(from, eth_hdr(skb)->h_source); + __entry->proto = be16_to_cpu(skb->protocol); __entry->unencrypted = unencrypted; ), - TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s", - NETDEV_PR_ARG, MAC_PR_ARG(addr), + TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", + NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from), __entry->proto, BOOL_TO_STR(__entry->unencrypted)) ); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index f47abb46c587..911ca6d3cb5a 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -11,6 +11,8 @@ #include <linux/slab.h> #include <linux/bpf.h> #include <linux/mm.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> #include "xdp_umem.h" #include "xsk_queue.h" @@ -40,6 +42,21 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) } } +int xdp_umem_query(struct net_device *dev, u16 queue_id) +{ + struct netdev_bpf bpf; + + ASSERT_RTNL(); + + memset(&bpf, 0, sizeof(bpf)); + bpf.command = XDP_QUERY_XSK_UMEM; + bpf.xsk.queue_id = queue_id; + + if (!dev->netdev_ops->ndo_bpf) + return 0; + return dev->netdev_ops->ndo_bpf(dev, &bpf) ?: !!bpf.xsk.umem; +} + int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, u32 queue_id, u16 flags) { @@ -56,41 +73,36 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, if (force_copy) return 0; - dev_hold(dev); - - if (dev->netdev_ops->ndo_bpf && dev->netdev_ops->ndo_xsk_async_xmit) { - bpf.command = XDP_QUERY_XSK_UMEM; + if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) + return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ - rtnl_lock(); - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - rtnl_unlock(); + bpf.command = XDP_QUERY_XSK_UMEM; - if (err) { - dev_put(dev); - return force_zc ? -ENOTSUPP : 0; - } - - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = umem; - bpf.xsk.queue_id = queue_id; + rtnl_lock(); + err = xdp_umem_query(dev, queue_id); + if (err) { + err = err < 0 ? -ENOTSUPP : -EBUSY; + goto err_rtnl_unlock; + } - rtnl_lock(); - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - rtnl_unlock(); + bpf.command = XDP_SETUP_XSK_UMEM; + bpf.xsk.umem = umem; + bpf.xsk.queue_id = queue_id; - if (err) { - dev_put(dev); - return force_zc ? err : 0; /* fail or fallback */ - } + err = dev->netdev_ops->ndo_bpf(dev, &bpf); + if (err) + goto err_rtnl_unlock; + rtnl_unlock(); - umem->dev = dev; - umem->queue_id = queue_id; - umem->zc = true; - return 0; - } + dev_hold(dev); + umem->dev = dev; + umem->queue_id = queue_id; + umem->zc = true; + return 0; - dev_put(dev); - return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ +err_rtnl_unlock: + rtnl_unlock(); + return force_zc ? err : 0; /* fail or fallback */ } static void xdp_umem_clear_dev(struct xdp_umem *umem) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 72335c2e8108..4e937cd7c17d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -84,10 +84,8 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len); - if (err) { - xdp_return_buff(xdp); + if (err) xs->rx_dropped++; - } return err; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 52ecaf770642..8a64b150be54 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -250,7 +250,7 @@ static inline bool xskq_full_desc(struct xsk_queue *q) static inline bool xskq_empty_desc(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, 1) == q->nentries; + return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index eab952cca7d0..4a9ee2d83158 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -25,6 +25,14 @@ config XFRM_USER If unsure, say Y. +config XFRM_INTERFACE + tristate "Transformation virtual interface" + depends on XFRM && IPV6 + ---help--- + This provides a virtual interface to route IPsec traffic. + + If unsure, say N. + config XFRM_SUB_POLICY bool "Transformation sub policy support" depends on XFRM diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 0bd2465a8c5a..fbc4552d17b8 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o +obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 175941e15a6e..5611b7521020 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -56,7 +56,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur if (skb_is_gso(skb)) { struct net_device *dev = skb->dev; - if (unlikely(!x->xso.offload_handle || (x->xso.dev != dev))) { + if (unlikely(x->xso.dev != dev)) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ @@ -162,7 +162,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, - x->props.family, x->props.output_mark); + x->props.family, + xfrm_smark_get(0, x)); if (IS_ERR(dst)) return 0; @@ -210,8 +211,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) if (!x->type_offload || x->encap) return false; - if ((!dev || (x->xso.offload_handle && (dev == xfrm_dst_path(dst)->dev))) && - (!xdst->child->xfrm && x->type->get_mtu)) { + if ((!dev || (dev == xfrm_dst_path(dst)->dev)) && + (!xdst->child->xfrm && x->type->get_mtu)) { mtu = x->type->get_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) @@ -306,12 +307,6 @@ static int xfrm_dev_register(struct net_device *dev) return xfrm_api_check(dev); } -static int xfrm_dev_unregister(struct net_device *dev) -{ - xfrm_policy_cache_flush(); - return NOTIFY_DONE; -} - static int xfrm_dev_feat_change(struct net_device *dev) { return xfrm_api_check(dev); @@ -322,7 +317,6 @@ static int xfrm_dev_down(struct net_device *dev) if (dev->features & NETIF_F_HW_ESP) xfrm_dev_state_flush(dev_net(dev), dev, true); - xfrm_policy_cache_flush(); return NOTIFY_DONE; } @@ -334,9 +328,6 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void case NETDEV_REGISTER: return xfrm_dev_register(dev); - case NETDEV_UNREGISTER: - return xfrm_dev_unregister(dev); - case NETDEV_FEAT_CHANGE: return xfrm_dev_feat_change(dev); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 352abca2605f..b89c9c7f8c5c 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -320,6 +320,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } @@ -328,17 +329,21 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SPI_SKB_CB(skb)->daddroff); do { if (skb->sp->len == XFRM_MAX_DEPTH) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); goto drop; } + skb->mark = xfrm_smark_get(skb->mark, x); + skb->sp->xvec[skb->sp->len++] = x; lock: diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c new file mode 100644 index 000000000000..31acc6f33d98 --- /dev/null +++ b/net/xfrm/xfrm_interface.c @@ -0,0 +1,975 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * XFRM virtual interface + * + * Copyright (C) 2018 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + */ + +#include <linux/module.h> +#include <linux/capability.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/sockios.h> +#include <linux/icmp.h> +#include <linux/if.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/net.h> +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/if_link.h> +#include <linux/if_arp.h> +#include <linux/icmpv6.h> +#include <linux/init.h> +#include <linux/route.h> +#include <linux/rtnetlink.h> +#include <linux/netfilter_ipv6.h> +#include <linux/slab.h> +#include <linux/hash.h> + +#include <linux/uaccess.h> +#include <linux/atomic.h> + +#include <net/icmp.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <linux/etherdevice.h> + +static int xfrmi_dev_init(struct net_device *dev); +static void xfrmi_dev_setup(struct net_device *dev); +static struct rtnl_link_ops xfrmi_link_ops __read_mostly; +static unsigned int xfrmi_net_id __read_mostly; + +struct xfrmi_net { + /* lists for storing interfaces in use */ + struct xfrm_if __rcu *xfrmi[1]; +}; + +#define for_each_xfrmi_rcu(start, xi) \ + for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) + +static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) +{ + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + struct xfrm_if *xi; + + for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { + if (x->if_id == xi->p.if_id && + (xi->dev->flags & IFF_UP)) + return xi; + } + + return NULL; +} + +static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) +{ + struct xfrmi_net *xfrmn; + int ifindex; + struct xfrm_if *xi; + + if (!skb->dev) + return NULL; + + xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + ifindex = skb->dev->ifindex; + + for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { + if (ifindex == xi->dev->ifindex && + (xi->dev->flags & IFF_UP)) + return xi; + } + + return NULL; +} + +static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) +{ + struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0]; + + rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); + rcu_assign_pointer(*xip, xi); +} + +static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi) +{ + struct xfrm_if __rcu **xip; + struct xfrm_if *iter; + + for (xip = &xfrmn->xfrmi[0]; + (iter = rtnl_dereference(*xip)) != NULL; + xip = &iter->next) { + if (xi == iter) { + rcu_assign_pointer(*xip, xi->next); + break; + } + } +} + +static void xfrmi_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); +} + +static int xfrmi_create2(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net *net = dev_net(dev); + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + int err; + + dev->rtnl_link_ops = &xfrmi_link_ops; + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(xi->p.name, dev->name); + + dev_hold(dev); + xfrmi_link(xfrmn, xi); + + return 0; + +out: + return err; +} + +static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p) +{ + struct net_device *dev; + struct xfrm_if *xi; + char name[IFNAMSIZ]; + int err; + + if (p->name[0]) { + strlcpy(name, p->name, IFNAMSIZ); + } else { + err = -EINVAL; + goto failed; + } + + dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup); + if (!dev) { + err = -EAGAIN; + goto failed; + } + + dev_net_set(dev, net); + + xi = netdev_priv(dev); + xi->p = *p; + xi->net = net; + xi->dev = dev; + xi->phydev = dev_get_by_index(net, p->link); + if (!xi->phydev) { + err = -ENODEV; + goto failed_free; + } + + err = xfrmi_create2(dev); + if (err < 0) + goto failed_dev_put; + + return xi; + +failed_dev_put: + dev_put(xi->phydev); +failed_free: + free_netdev(dev); +failed: + return ERR_PTR(err); +} + +static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p, + int create) +{ + struct xfrm_if __rcu **xip; + struct xfrm_if *xi; + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + + for (xip = &xfrmn->xfrmi[0]; + (xi = rtnl_dereference(*xip)) != NULL; + xip = &xi->next) { + if (xi->p.if_id == p->if_id) { + if (create) + return ERR_PTR(-EEXIST); + + return xi; + } + } + if (!create) + return ERR_PTR(-ENODEV); + return xfrmi_create(net, p); +} + +static void xfrmi_dev_uninit(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id); + + xfrmi_unlink(xfrmn, xi); + dev_put(xi->phydev); + dev_put(dev); +} + +static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) +{ + skb->tstamp = 0; + skb->pkt_type = PACKET_HOST; + skb->skb_iif = 0; + skb->ignore_df = 0; + skb_dst_drop(skb); + nf_reset(skb); + nf_reset_trace(skb); + + if (!xnet) + return; + + ipvs_reset(skb); + secpath_reset(skb); + skb_orphan(skb); + skb->mark = 0; +} + +static int xfrmi_rcv_cb(struct sk_buff *skb, int err) +{ + struct pcpu_sw_netstats *tstats; + struct xfrm_mode *inner_mode; + struct net_device *dev; + struct xfrm_state *x; + struct xfrm_if *xi; + bool xnet; + + if (err && !skb->sp) + return 0; + + x = xfrm_input_state(skb); + + xi = xfrmi_lookup(xs_net(x), x); + if (!xi) + return 1; + + dev = xi->dev; + skb->dev = dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; + } + + xnet = !net_eq(xi->net, dev_net(skb->dev)); + + if (xnet) { + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) { + XFRM_INC_STATS(dev_net(skb->dev), + LINUX_MIB_XFRMINSTATEMODEERROR); + return -EINVAL; + } + } + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, + inner_mode->afinfo->family)) + return -EPERM; + } + + xfrmi_scrub_packet(skb, xnet); + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; +} + +static int +xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device_stats *stats = &xi->dev->stats; + struct dst_entry *dst = skb_dst(skb); + unsigned int length = skb->len; + struct net_device *tdev; + struct xfrm_state *x; + int err = -1; + int mtu; + + if (!dst) + goto tx_err_link_failure; + + dst_hold(dst); + dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; + } + + x = dst->xfrm; + if (!x) + goto tx_err_link_failure; + + if (x->if_id != xi->p.if_id) + goto tx_err_link_failure; + + tdev = dst->dev; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + xi->p.name); + goto tx_err_dst_release; + } + + mtu = dst_mtu(dst); + if (!skb->ignore_df && skb->len > mtu) { + skb_dst_update_pmtu(skb, mtu); + + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + } else { + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + } + + dst_release(dst); + return -EMSGSIZE; + } + + xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = tdev; + + err = dst_output(xi->net, skb->sk, skb); + if (net_xmit_eval(err) == 0) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += length; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; + } + + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(dst); + return err; +} + +static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device_stats *stats = &xi->dev->stats; + struct flowi fl; + int ret; + + memset(&fl, 0, sizeof(fl)); + + switch (skb->protocol) { + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + default: + goto tx_err; + } + + fl.flowi_oif = xi->phydev->ifindex; + + ret = xfrmi_xmit2(skb, dev, &fl); + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int xfrmi4_err(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct net *net = dev_net(skb->dev); + int protocol = iph->protocol; + struct ip_comp_hdr *ipch; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct xfrm_state *x; + struct xfrm_if *xi; + __be32 spi; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + xi = xfrmi_lookup(net, x); + if (!xi) { + xfrm_state_put(x); + return -1; + } + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + +static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + struct net *net = dev_net(skb->dev); + int protocol = iph->nexthdr; + struct ip_comp_hdr *ipch; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct xfrm_state *x; + struct xfrm_if *xi; + __be32 spi; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data + offset); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data + offset); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data + offset); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET6); + if (!x) + return 0; + + xi = xfrmi_lookup(net, x); + if (!xi) { + xfrm_state_put(x); + return -1; + } + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else + ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); + xfrm_state_put(x); + + return 0; +} + +static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p) +{ + if (xi->p.link != p->link) + return -EINVAL; + + xi->p.if_id = p->if_id; + + return 0; +} + +static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) +{ + struct net *net = dev_net(xi->dev); + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + int err; + + xfrmi_unlink(xfrmn, xi); + synchronize_net(); + err = xfrmi_change(xi, p); + xfrmi_link(xfrmn, xi); + netdev_state_change(xi->dev); + return err; +} + +static void xfrmi_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + int cpu; + + if (!dev->tstats) + return; + + for_each_possible_cpu(cpu) { + struct pcpu_sw_netstats *stats; + struct pcpu_sw_netstats tmp; + int start; + + stats = per_cpu_ptr(dev->tstats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + tmp.rx_packets = stats->rx_packets; + tmp.rx_bytes = stats->rx_bytes; + tmp.tx_packets = stats->tx_packets; + tmp.tx_bytes = stats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + s->rx_packets += tmp.rx_packets; + s->rx_bytes += tmp.rx_bytes; + s->tx_packets += tmp.tx_packets; + s->tx_bytes += tmp.tx_bytes; + } + + s->rx_dropped = dev->stats.rx_dropped; + s->tx_dropped = dev->stats.tx_dropped; +} + +static int xfrmi_get_iflink(const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + + return xi->phydev->ifindex; +} + + +static const struct net_device_ops xfrmi_netdev_ops = { + .ndo_init = xfrmi_dev_init, + .ndo_uninit = xfrmi_dev_uninit, + .ndo_start_xmit = xfrmi_xmit, + .ndo_get_stats64 = xfrmi_get_stats64, + .ndo_get_iflink = xfrmi_get_iflink, +}; + +static void xfrmi_dev_setup(struct net_device *dev) +{ + dev->netdev_ops = &xfrmi_netdev_ops; + dev->type = ARPHRD_NONE; + dev->hard_header_len = ETH_HLEN; + dev->min_header_len = ETH_HLEN; + dev->mtu = ETH_DATA_LEN; + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_DATA_LEN; + dev->addr_len = ETH_ALEN; + dev->flags = IFF_NOARP; + dev->needs_free_netdev = true; + dev->priv_destructor = xfrmi_dev_free; + netif_keep_dst(dev); +} + +static int xfrmi_dev_init(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device *phydev = xi->phydev; + int err; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&xi->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + + dev->features |= NETIF_F_LLTX; + + dev->needed_headroom = phydev->needed_headroom; + dev->needed_tailroom = phydev->needed_tailroom; + + if (is_zero_ether_addr(dev->dev_addr)) + eth_hw_addr_inherit(dev, phydev); + if (is_zero_ether_addr(dev->broadcast)) + memcpy(dev->broadcast, phydev->broadcast, dev->addr_len); + + return 0; +} + +static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + return 0; +} + +static void xfrmi_netlink_parms(struct nlattr *data[], + struct xfrm_if_parms *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_XFRM_LINK]) + parms->link = nla_get_u32(data[IFLA_XFRM_LINK]); + + if (data[IFLA_XFRM_IF_ID]) + parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]); +} + +static int xfrmi_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct net *net = dev_net(dev); + struct xfrm_if_parms *p; + struct xfrm_if *xi; + + xi = netdev_priv(dev); + p = &xi->p; + + xfrmi_netlink_parms(data, p); + + if (!tb[IFLA_IFNAME]) + return -EINVAL; + + nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ); + + xi = xfrmi_locate(net, p, 1); + return PTR_ERR_OR_ZERO(xi); +} + +static void xfrmi_dellink(struct net_device *dev, struct list_head *head) +{ + unregister_netdevice_queue(dev, head); +} + +static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net *net = dev_net(dev); + + xfrmi_netlink_parms(data, &xi->p); + + xi = xfrmi_locate(net, &xi->p, 0); + + if (IS_ERR_OR_NULL(xi)) { + xi = netdev_priv(dev); + } else { + if (xi->dev != dev) + return -EEXIST; + } + + return xfrmi_update(xi, &xi->p); +} + +static size_t xfrmi_get_size(const struct net_device *dev) +{ + return + /* IFLA_XFRM_LINK */ + nla_total_size(4) + + /* IFLA_XFRM_IF_ID */ + nla_total_size(4) + + 0; +} + +static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct xfrm_if_parms *parm = &xi->p; + + if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) || + nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +struct net *xfrmi_get_link_net(const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + + return dev_net(xi->phydev); +} + +static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { + [IFLA_XFRM_LINK] = { .type = NLA_U32 }, + [IFLA_XFRM_IF_ID] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { + .kind = "xfrm", + .maxtype = IFLA_XFRM_MAX, + .policy = xfrmi_policy, + .priv_size = sizeof(struct xfrm_if), + .setup = xfrmi_dev_setup, + .validate = xfrmi_validate, + .newlink = xfrmi_newlink, + .dellink = xfrmi_dellink, + .changelink = xfrmi_changelink, + .get_size = xfrmi_get_size, + .fill_info = xfrmi_fill_info, + .get_link_net = xfrmi_get_link_net, +}; + +static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn) +{ + struct xfrm_if *xi; + LIST_HEAD(list); + + xi = rtnl_dereference(xfrmn->xfrmi[0]); + if (!xi) + return; + + unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_many(&list); +} + +static int __net_init xfrmi_init_net(struct net *net) +{ + return 0; +} + +static void __net_exit xfrmi_exit_net(struct net *net) +{ + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + + rtnl_lock(); + xfrmi_destroy_interfaces(xfrmn); + rtnl_unlock(); +} + +static struct pernet_operations xfrmi_net_ops = { + .init = xfrmi_init_net, + .exit = xfrmi_exit_net, + .id = &xfrmi_net_id, + .size = sizeof(struct xfrmi_net), +}; + +static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static int __init xfrmi4_init(void) +{ + int err; + + err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + return 0; + +xfrm_proto_comp_failed: + xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: + return err; +} + +static void xfrmi4_fini(void) +{ + xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); +} + +static int __init xfrmi6_init(void) +{ + int err; + + err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + return 0; + +xfrm_proto_comp_failed: + xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: + return err; +} + +static void xfrmi6_fini(void) +{ + xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); +} + +static const struct xfrm_if_cb xfrm_if_cb = { + .decode_session = xfrmi_decode_session, +}; + +static int __init xfrmi_init(void) +{ + const char *msg; + int err; + + pr_info("IPsec XFRM device driver\n"); + + msg = "tunnel device"; + err = register_pernet_device(&xfrmi_net_ops); + if (err < 0) + goto pernet_dev_failed; + + msg = "xfrm4 protocols"; + err = xfrmi4_init(); + if (err < 0) + goto xfrmi4_failed; + + msg = "xfrm6 protocols"; + err = xfrmi6_init(); + if (err < 0) + goto xfrmi6_failed; + + + msg = "netlink interface"; + err = rtnl_link_register(&xfrmi_link_ops); + if (err < 0) + goto rtnl_link_failed; + + xfrm_if_register_cb(&xfrm_if_cb); + + return err; + +rtnl_link_failed: + xfrmi6_fini(); +xfrmi6_failed: + xfrmi4_fini(); +xfrmi4_failed: + unregister_pernet_device(&xfrmi_net_ops); +pernet_dev_failed: + pr_err("xfrmi init: failed to register %s\n", msg); + return err; +} + +static void __exit xfrmi_fini(void) +{ + xfrm_if_unregister_cb(); + rtnl_link_unregister(&xfrmi_link_ops); + xfrmi4_fini(); + xfrmi6_fini(); + unregister_pernet_device(&xfrmi_net_ops); +} + +module_init(xfrmi_init); +module_exit(xfrmi_fini); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("xfrm"); +MODULE_ALIAS_NETDEV("xfrm0"); +MODULE_AUTHOR("Steffen Klassert"); +MODULE_DESCRIPTION("XFRM virtual interface"); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 89b178a78dc7..45ba07ab3e4f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -66,8 +66,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) goto error_nolock; } - if (x->props.output_mark) - skb->mark = x->props.output_mark; + skb->mark = xfrm_smark_get(skb->mark, x); err = x->outer_mode->output(x, skb); if (err) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5f48251c1319..3110c3fbee20 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -45,8 +45,9 @@ struct xfrm_flo { u8 flags; }; -static DEFINE_PER_CPU(struct xfrm_dst *, xfrm_last_dst); -static struct work_struct *xfrm_pcpu_work __read_mostly; +static DEFINE_SPINLOCK(xfrm_if_cb_lock); +static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; + static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; @@ -119,6 +120,12 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa return afinfo; } +/* Called with rcu_read_lock(). */ +static const struct xfrm_if_cb *xfrm_if_get_cb(void) +{ + return rcu_dereference(xfrm_if_cb); +} + struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, @@ -182,8 +189,8 @@ static inline unsigned long make_jiffies(long secs) static void xfrm_policy_timer(struct timer_list *t) { struct xfrm_policy *xp = from_timer(xp, t, timer); - unsigned long now = get_seconds(); - long next = LONG_MAX; + time64_t now = ktime_get_real_seconds(); + time64_t next = TIME64_MAX; int warn = 0; int dir; @@ -195,7 +202,7 @@ static void xfrm_policy_timer(struct timer_list *t) dir = xfrm_policy_id2dir(xp->index); if (xp->lft.hard_add_expires_seconds) { - long tmo = xp->lft.hard_add_expires_seconds + + time64_t tmo = xp->lft.hard_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) goto expired; @@ -203,7 +210,7 @@ static void xfrm_policy_timer(struct timer_list *t) next = tmo; } if (xp->lft.hard_use_expires_seconds) { - long tmo = xp->lft.hard_use_expires_seconds + + time64_t tmo = xp->lft.hard_use_expires_seconds + (xp->curlft.use_time ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; @@ -211,7 +218,7 @@ static void xfrm_policy_timer(struct timer_list *t) next = tmo; } if (xp->lft.soft_add_expires_seconds) { - long tmo = xp->lft.soft_add_expires_seconds + + time64_t tmo = xp->lft.soft_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) { warn = 1; @@ -221,7 +228,7 @@ static void xfrm_policy_timer(struct timer_list *t) next = tmo; } if (xp->lft.soft_use_expires_seconds) { - long tmo = xp->lft.soft_use_expires_seconds + + time64_t tmo = xp->lft.soft_use_expires_seconds + (xp->curlft.use_time ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; @@ -233,7 +240,7 @@ static void xfrm_policy_timer(struct timer_list *t) if (warn) km_policy_expired(xp, dir, 0, 0); - if (next != LONG_MAX && + if (next != TIME64_MAX && !mod_timer(&xp->timer, jiffies + make_jiffies(next))) xfrm_pol_hold(xp); @@ -747,6 +754,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) newpos = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && + pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(policy, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && @@ -783,7 +791,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); - policy->curlft.add_time = get_seconds(); + policy->curlft.add_time = ktime_get_real_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); @@ -798,8 +806,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } EXPORT_SYMBOL(xfrm_policy_insert); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, - int dir, struct xfrm_selector *sel, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, + u8 type, int dir, + struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { @@ -812,6 +821,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, ret = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && + pol->if_id == if_id && (mark & pol->mark.m) == pol->mark.v && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) { @@ -837,8 +847,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, - int dir, u32 id, int delete, int *err) +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, + u8 type, int dir, u32 id, int delete, + int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -853,6 +864,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && + pol->if_id == if_id && (mark & pol->mark.m) == pol->mark.v) { xfrm_pol_hold(pol); if (delete) { @@ -1056,13 +1068,14 @@ EXPORT_SYMBOL(xfrm_policy_walk_done); */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, - u8 type, u16 family, int dir) + u8 type, u16 family, int dir, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || + pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; @@ -1077,7 +1090,8 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, - u16 family, u8 dir) + u16 family, u8 dir, + u32 if_id) { int err; struct xfrm_policy *pol, *ret; @@ -1101,7 +1115,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, priority = ~0U; ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { - err = xfrm_policy_match(pol, fl, type, family, dir); + err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; @@ -1120,7 +1134,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if ((pol->priority >= priority) && ret) break; - err = xfrm_policy_match(pol, fl, type, family, dir); + err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; @@ -1145,21 +1159,25 @@ fail: return ret; } -static struct xfrm_policy * -xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir) +static struct xfrm_policy *xfrm_policy_lookup(struct net *net, + const struct flowi *fl, + u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; - pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, + dir, if_id); if (pol != NULL) return pol; #endif - return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); + return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, + dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, - const struct flowi *fl, u16 family) + const struct flowi *fl, + u16 family, u32 if_id) { struct xfrm_policy *pol; @@ -1177,7 +1195,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v) { + if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + pol->if_id != if_id) { pol = NULL; goto out; } @@ -1268,7 +1287,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) old_pol = rcu_dereference_protected(sk->sk_policy[dir], lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { - pol->curlft.add_time = get_seconds(); + pol->curlft.add_time = ktime_get_real_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } @@ -1305,6 +1324,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; + newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; @@ -1390,7 +1410,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, } } - x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family); + x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, + family, policy->if_id); if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; @@ -1607,10 +1628,11 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { + __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, - &saddr, &daddr, family, - xfrm[i]->props.output_mark); + &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; @@ -1692,7 +1714,8 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, - XFRM_POLICY_OUT); + XFRM_POLICY_OUT, + pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); @@ -1714,108 +1737,6 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, } -static void xfrm_last_dst_update(struct xfrm_dst *xdst, struct xfrm_dst *old) -{ - this_cpu_write(xfrm_last_dst, xdst); - if (old) - dst_release(&old->u.dst); -} - -static void __xfrm_pcpu_work_fn(void) -{ - struct xfrm_dst *old; - - old = this_cpu_read(xfrm_last_dst); - if (old && !xfrm_bundle_ok(old)) - xfrm_last_dst_update(NULL, old); -} - -static void xfrm_pcpu_work_fn(struct work_struct *work) -{ - local_bh_disable(); - rcu_read_lock(); - __xfrm_pcpu_work_fn(); - rcu_read_unlock(); - local_bh_enable(); -} - -void xfrm_policy_cache_flush(void) -{ - struct xfrm_dst *old; - bool found = false; - int cpu; - - might_sleep(); - - local_bh_disable(); - rcu_read_lock(); - for_each_possible_cpu(cpu) { - old = per_cpu(xfrm_last_dst, cpu); - if (old && !xfrm_bundle_ok(old)) { - if (smp_processor_id() == cpu) { - __xfrm_pcpu_work_fn(); - continue; - } - found = true; - break; - } - } - - rcu_read_unlock(); - local_bh_enable(); - - if (!found) - return; - - get_online_cpus(); - - for_each_possible_cpu(cpu) { - bool bundle_release; - - rcu_read_lock(); - old = per_cpu(xfrm_last_dst, cpu); - bundle_release = old && !xfrm_bundle_ok(old); - rcu_read_unlock(); - - if (!bundle_release) - continue; - - if (cpu_online(cpu)) { - schedule_work_on(cpu, &xfrm_pcpu_work[cpu]); - continue; - } - - rcu_read_lock(); - old = per_cpu(xfrm_last_dst, cpu); - if (old && !xfrm_bundle_ok(old)) { - per_cpu(xfrm_last_dst, cpu) = NULL; - dst_release(&old->u.dst); - } - rcu_read_unlock(); - } - - put_online_cpus(); -} - -static bool xfrm_xdst_can_reuse(struct xfrm_dst *xdst, - struct xfrm_state * const xfrm[], - int num) -{ - const struct dst_entry *dst = &xdst->u.dst; - int i; - - if (xdst->num_xfrms != num) - return false; - - for (i = 0; i < num; i++) { - if (!dst || dst->xfrm != xfrm[i]) - return false; - dst = xfrm_dst_child(dst); - } - - return xfrm_bundle_ok(xdst); -} - static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, const struct flowi *fl, u16 family, @@ -1824,34 +1745,21 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; - struct xfrm_dst *xdst, *old; + struct xfrm_dst *xdst; struct dst_entry *dst; int err; /* Try to instantiate a bundle */ err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); if (err <= 0) { - if (err != 0 && err != -EAGAIN) + if (err == 0) + return NULL; + + if (err != -EAGAIN) XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); return ERR_PTR(err); } - xdst = this_cpu_read(xfrm_last_dst); - if (xdst && - xdst->u.dst.dev == dst_orig->dev && - xdst->num_pols == num_pols && - memcmp(xdst->pols, pols, - sizeof(struct xfrm_policy *) * num_pols) == 0 && - xfrm_xdst_can_reuse(xdst, xfrm, err)) { - dst_hold(&xdst->u.dst); - xfrm_pols_put(pols, num_pols); - while (err > 0) - xfrm_state_put(xfrm[--err]); - return xdst; - } - - old = xdst; - dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); @@ -1864,9 +1772,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); - atomic_set(&xdst->u.dst.__refcnt, 2); - xfrm_last_dst_update(xdst, old); - return xdst; } @@ -2047,8 +1952,10 @@ free_dst: goto out; } -static struct xfrm_dst * -xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo) +static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, + const struct flowi *fl, + u16 family, u8 dir, + struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; @@ -2057,7 +1964,7 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; - pols[0] = xfrm_policy_lookup(net, fl, family, dir); + pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2067,13 +1974,15 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (num_xfrms <= 0) goto make_dummy_bundle; - local_bh_disable(); xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, xflo->dst_orig); - local_bh_enable(); - if (IS_ERR(xdst)) { err = PTR_ERR(xdst); + if (err == -EREMOTE) { + xfrm_pols_put(pols, num_pols); + return NULL; + } + if (err != -EAGAIN) goto error; goto make_dummy_bundle; @@ -2123,14 +2032,19 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family, return ret; } -/* Main function: finds/creates a bundle for given flow. +/* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. + * + * xfrm_lookup uses an if_id of 0 by default, and is provided for + * compatibility */ -struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, - const struct sock *sk, int flags) +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, + int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; @@ -2146,7 +2060,8 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; - pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family); + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, + if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2158,15 +2073,16 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } - local_bh_disable(); xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); - local_bh_enable(); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); + if (err == -EREMOTE) + goto nopol; + goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; @@ -2189,7 +2105,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; - xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo); + xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { @@ -2234,7 +2150,7 @@ no_transform: } for (i = 0; i < num_pols; i++) - pols[i]->curlft.use_time = get_seconds(); + pols[i]->curlft.use_time = ktime_get_real_seconds(); if (num_xfrms < 0) { /* Prohibit the flow */ @@ -2270,6 +2186,19 @@ dropdst: xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } +EXPORT_SYMBOL(xfrm_lookup_with_ifid); + +/* Main function: finds/creates a bundle for given flow. + * + * At the moment we eat a raw IP route. Mostly to speed up lookups + * on interfaces with disabled IPsec. + */ +struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags) +{ + return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); +} EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). @@ -2286,6 +2215,9 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); + if (IS_ERR(dst)) + dst_release(dst_orig); + return dst; } EXPORT_SYMBOL(xfrm_lookup_route); @@ -2365,6 +2297,7 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, return -EAFNOSUPPORT; afinfo->decode_session(skb, fl, reverse); + err = security_xfrm_decode_session(skb, &fl->flowi_secid); rcu_read_unlock(); return err; @@ -2395,6 +2328,19 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, int reverse; struct flowi fl; int xerr_idx = -1; + const struct xfrm_if_cb *ifcb; + struct xfrm_if *xi; + u32 if_id = 0; + + rcu_read_lock(); + ifcb = xfrm_if_get_cb(); + + if (ifcb) { + xi = ifcb->decode_session(skb); + if (xi) + if_id = xi->p.if_id; + } + rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; @@ -2422,7 +2368,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { - pol = xfrm_sk_policy_lookup(sk, dir, &fl, family); + pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; @@ -2430,7 +2376,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } if (!pol) - pol = xfrm_policy_lookup(net, &fl, family, dir); + pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); @@ -2446,7 +2392,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 1; } - pol->curlft.use_time = get_seconds(); + pol->curlft.use_time = ktime_get_real_seconds(); pols[0] = pol; npols++; @@ -2454,13 +2400,13 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, - XFRM_POLICY_IN); + XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } - pols[1]->curlft.use_time = get_seconds(); + pols[1]->curlft.use_time = ktime_get_real_seconds(); npols++; } } @@ -2819,6 +2765,21 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); +void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) +{ + spin_lock(&xfrm_if_cb_lock); + rcu_assign_pointer(xfrm_if_cb, ifcb); + spin_unlock(&xfrm_if_cb_lock); +} +EXPORT_SYMBOL(xfrm_if_register_cb); + +void xfrm_if_unregister_cb(void) +{ + RCU_INIT_POINTER(xfrm_if_cb, NULL); + synchronize_rcu(); +} +EXPORT_SYMBOL(xfrm_if_unregister_cb); + #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { @@ -2986,19 +2947,13 @@ static struct pernet_operations __net_initdata xfrm_net_ops = { void __init xfrm_init(void) { - int i; - - xfrm_pcpu_work = kmalloc_array(NR_CPUS, sizeof(*xfrm_pcpu_work), - GFP_KERNEL); - BUG_ON(!xfrm_pcpu_work); - - for (i = 0; i < NR_CPUS; i++) - INIT_WORK(&xfrm_pcpu_work[i], xfrm_pcpu_work_fn); - register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); + + RCU_INIT_POINTER(xfrm_if_cb, NULL); + synchronize_rcu(); } #ifdef CONFIG_AUDITSYSCALL diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 8308281f3253..b669262682c9 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -475,8 +475,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); - unsigned long now = get_seconds(); - long next = LONG_MAX; + time64_t now = ktime_get_real_seconds(); + time64_t next = TIME64_MAX; int warn = 0; int err = 0; @@ -537,7 +537,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (warn) km_state_expired(x, 0, 0); resched: - if (next != LONG_MAX) { + if (next != TIME64_MAX) { tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL); } @@ -577,7 +577,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler, CLOCK_BOOTTIME, HRTIMER_MODE_ABS); timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); - x->curlft.add_time = get_seconds(); + x->curlft.add_time = ktime_get_real_seconds(); x->lft.soft_byte_limit = XFRM_INF; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; @@ -735,10 +735,9 @@ restart: } out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); - if (cnt) { + if (cnt) err = 0; - xfrm_policy_cache_flush(); - } + return err; } EXPORT_SYMBOL(xfrm_state_flush); @@ -931,7 +930,7 @@ struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family) + unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); @@ -955,6 +954,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && @@ -971,6 +971,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && @@ -1010,6 +1011,7 @@ found: * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); + x->if_id = if_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { @@ -1067,7 +1069,7 @@ out: } struct xfrm_state * -xfrm_stateonly_find(struct net *net, u32 mark, +xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { @@ -1080,6 +1082,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && @@ -1160,11 +1163,13 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; + u32 if_id = xnew->if_id; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && + x->if_id == if_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) @@ -1187,7 +1192,7 @@ EXPORT_SYMBOL(xfrm_state_insert); static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, - u32 reqid, u8 proto, + u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) @@ -1242,6 +1247,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; + x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; @@ -1296,7 +1302,7 @@ int xfrm_state_add(struct xfrm_state *x) if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, - x->props.reqid, x->id.proto, + x->props.reqid, x->if_id, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); @@ -1395,6 +1401,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; @@ -1554,6 +1561,19 @@ out: if (x1->curlft.use_time) xfrm_state_check_expire(x1); + if (x->props.smark.m || x->props.smark.v || x->if_id) { + spin_lock_bh(&net->xfrm.xfrm_state_lock); + + if (x->props.smark.m || x->props.smark.v) + x1->props.smark = x->props.smark; + + if (x->if_id) + x1->if_id = x->if_id; + + __xfrm_state_bump_genids(x1); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + } + err = 0; x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); @@ -1571,7 +1591,7 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { if (!x->curlft.use_time) - x->curlft.use_time = get_seconds(); + x->curlft.use_time = ktime_get_real_seconds(); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { @@ -1619,13 +1639,13 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, - u8 proto, const xfrm_address_t *daddr, + u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); - x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create); + x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 09cceab450b8..4791aa8b8185 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -527,6 +527,19 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, x->replay_maxdiff = nla_get_u32(rt); } +static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) +{ + if (attrs[XFRMA_SET_MARK]) { + m->v = nla_get_u32(attrs[XFRMA_SET_MARK]); + if (attrs[XFRMA_SET_MARK_MASK]) + m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]); + else + m->m = 0xffffffff; + } else { + m->v = m->m = 0; + } +} + static struct xfrm_state *xfrm_state_construct(struct net *net, struct xfrm_usersa_info *p, struct nlattr **attrs, @@ -579,8 +592,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_mark_get(attrs, &x->mark); - if (attrs[XFRMA_OUTPUT_MARK]) - x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]); + xfrm_smark_init(attrs, &x->props.smark); + + if (attrs[XFRMA_IF_ID]) + x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]); if (err) @@ -824,6 +839,18 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) return 0; } +static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m) +{ + int ret = 0; + + if (m->v | m->m) { + ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v); + if (!ret) + ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m); + } + return ret; +} + /* Don't change this without updating xfrm_sa_len! */ static int copy_to_user_state_extra(struct xfrm_state *x, struct xfrm_usersa_info *p, @@ -887,6 +914,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = xfrm_mark_put(skb, &x->mark); if (ret) goto out; + + ret = xfrm_smark_put(skb, &x->props.smark); + if (ret) + goto out; + if (x->replay_esn) ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL, xfrm_replay_state_esn_len(x->replay_esn), @@ -900,8 +932,8 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = copy_user_offload(&x->xso, skb); if (ret) goto out; - if (x->props.output_mark) { - ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark); + if (x->if_id) { + ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id); if (ret) goto out; } @@ -1025,10 +1057,12 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, { struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); - if (nlsk) - return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); - else - return -1; + if (!nlsk) { + kfree_skb(skb); + return -EPIPE; + } + + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); } static inline unsigned int xfrm_spdinfo_msgsize(void) @@ -1253,6 +1287,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u32 mark; struct xfrm_mark m; + u32 if_id = 0; p = nlmsg_data(nlh); err = verify_spi_info(p->info.id.proto, p->min, p->max); @@ -1265,6 +1300,10 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, x = NULL; mark = xfrm_mark_get(attrs, &m); + + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->info.seq) { x = xfrm_find_acq_byseq(net, mark, p->info.seq); if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) { @@ -1275,7 +1314,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, if (!x) x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid, - p->info.id.proto, daddr, + if_id, p->info.id.proto, daddr, &p->info.saddr, 1, family); err = -ENOENT; @@ -1563,6 +1602,9 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us xfrm_mark_get(attrs, &xp->mark); + if (attrs[XFRMA_IF_ID]) + xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + return xp; error: *errp = err; @@ -1671,9 +1713,11 @@ static inline unsigned int userpolicy_type_attrsize(void) #ifdef CONFIG_XFRM_SUB_POLICY static int copy_to_user_policy_type(u8 type, struct sk_buff *skb) { - struct xfrm_userpolicy_type upt = { - .type = type, - }; + struct xfrm_userpolicy_type upt; + + /* Sadly there are two holes in struct xfrm_userpolicy_type */ + memset(&upt, 0, sizeof(upt)); + upt.type = type; return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); } @@ -1708,6 +1752,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -1789,6 +1835,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, int delete; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); + u32 if_id = 0; p = nlmsg_data(nlh); delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY; @@ -1801,8 +1848,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->index) - xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1819,7 +1869,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, &p->sel, + xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } @@ -1942,6 +1992,10 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; + err = xfrm_if_id_put(skb, x->if_id); + if (err) + goto out_cancel; + nlmsg_end(skb, nlh); return 0; @@ -2084,6 +2138,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, int err = -ENOENT; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); + u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); if (err) @@ -2093,8 +2148,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->index) - xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2111,7 +2169,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } @@ -2493,7 +2551,9 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, - [XFRMA_OUTPUT_MARK] = { .type = NLA_U32 }, + [XFRMA_SET_MARK] = { .type = NLA_U32 }, + [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, + [XFRMA_IF_ID] = { .type = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { @@ -2625,6 +2685,10 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; + err = xfrm_if_id_put(skb, x->if_id); + if (err) + return err; + nlmsg_end(skb, nlh); return 0; } @@ -2719,8 +2783,12 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(x->props.extra_flags)); if (x->xso.dev) l += nla_total_size(sizeof(x->xso)); - if (x->props.output_mark) - l += nla_total_size(sizeof(x->props.output_mark)); + if (x->props.smark.v | x->props.smark.m) { + l += nla_total_size(sizeof(x->props.smark.v)); + l += nla_total_size(sizeof(x->props.smark.m)); + } + if (x->if_id) + l += nla_total_size(sizeof(x->if_id)); /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); @@ -2850,6 +2918,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -2966,6 +3036,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -3047,6 +3119,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) goto out_free_skb; diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h index ac5ba55066dd..985534d0b448 100644 --- a/tools/arch/powerpc/include/uapi/asm/unistd.h +++ b/tools/arch/powerpc/include/uapi/asm/unistd.h @@ -399,5 +399,6 @@ #define __NR_pkey_free 385 #define __NR_pkey_mprotect 386 #define __NR_rseq 387 +#define __NR_io_pgetevents 388 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h new file mode 100644 index 000000000000..2ccd588fbad4 --- /dev/null +++ b/tools/arch/x86/include/asm/mcsafe_test.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MCSAFE_TEST_H_ +#define _MCSAFE_TEST_H_ + +.macro MCSAFE_TEST_CTL +.endm + +.macro MCSAFE_TEST_SRC reg count target +.endm + +.macro MCSAFE_TEST_DST reg count target +.endm +#endif /* _MCSAFE_TEST_H_ */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 9a53a06e5a3e..298ef1479240 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> +#include <asm/mcsafe_test.h> #include <asm/alternative-asm.h> #include <asm/export.h> @@ -183,12 +184,15 @@ ENTRY(memcpy_orig) ENDPROC(memcpy_orig) #ifndef CONFIG_UML + +MCSAFE_TEST_CTL + /* - * memcpy_mcsafe_unrolled - memory copy with machine check exception handling + * __memcpy_mcsafe - memory copy with machine check exception handling * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(memcpy_mcsafe_unrolled) +ENTRY(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled) subl $8, %ecx negl %ecx subl %ecx, %edx -.L_copy_leading_bytes: +.L_read_leading_bytes: movb (%rsi), %al + MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes + MCSAFE_TEST_DST %rdi 1 .E_leading_bytes +.L_write_leading_bytes: movb %al, (%rdi) incq %rsi incq %rdi decl %ecx - jnz .L_copy_leading_bytes + jnz .L_read_leading_bytes .L_8byte_aligned: - /* Figure out how many whole cache lines (64-bytes) to copy */ - movl %edx, %ecx - andl $63, %edx - shrl $6, %ecx - jz .L_no_whole_cache_lines - - /* Loop copying whole cache lines */ -.L_cache_w0: movq (%rsi), %r8 -.L_cache_w1: movq 1*8(%rsi), %r9 -.L_cache_w2: movq 2*8(%rsi), %r10 -.L_cache_w3: movq 3*8(%rsi), %r11 - movq %r8, (%rdi) - movq %r9, 1*8(%rdi) - movq %r10, 2*8(%rdi) - movq %r11, 3*8(%rdi) -.L_cache_w4: movq 4*8(%rsi), %r8 -.L_cache_w5: movq 5*8(%rsi), %r9 -.L_cache_w6: movq 6*8(%rsi), %r10 -.L_cache_w7: movq 7*8(%rsi), %r11 - movq %r8, 4*8(%rdi) - movq %r9, 5*8(%rdi) - movq %r10, 6*8(%rdi) - movq %r11, 7*8(%rdi) - leaq 64(%rsi), %rsi - leaq 64(%rdi), %rdi - decl %ecx - jnz .L_cache_w0 - - /* Are there any trailing 8-byte words? */ -.L_no_whole_cache_lines: movl %edx, %ecx andl $7, %edx shrl $3, %ecx jz .L_no_whole_words - /* Copy trailing words */ -.L_copy_trailing_words: +.L_read_words: movq (%rsi), %r8 - mov %r8, (%rdi) - leaq 8(%rsi), %rsi - leaq 8(%rdi), %rdi + MCSAFE_TEST_SRC %rsi 8 .E_read_words + MCSAFE_TEST_DST %rdi 8 .E_write_words +.L_write_words: + movq %r8, (%rdi) + addq $8, %rsi + addq $8, %rdi decl %ecx - jnz .L_copy_trailing_words + jnz .L_read_words /* Any trailing bytes? */ .L_no_whole_words: @@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled) /* Copy trailing bytes */ movl %edx, %ecx -.L_copy_trailing_bytes: +.L_read_trailing_bytes: movb (%rsi), %al + MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes + MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes +.L_write_trailing_bytes: movb %al, (%rdi) incq %rsi incq %rdi decl %ecx - jnz .L_copy_trailing_bytes + jnz .L_read_trailing_bytes /* Copy successful. Return zero */ .L_done_memcpy_trap: xorq %rax, %rax ret -ENDPROC(memcpy_mcsafe_unrolled) -EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) +ENDPROC(__memcpy_mcsafe) +EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" - /* Return -EFAULT for any failure */ -.L_memcpy_mcsafe_fail: - mov $-EFAULT, %rax + /* + * Return number of bytes not copied for any failure. Note that + * there is no "tail" handling since the source buffer is 8-byte + * aligned and poison is cacheline aligned. + */ +.E_read_words: + shll $3, %ecx +.E_leading_bytes: + addl %edx, %ecx +.E_trailing_bytes: + mov %ecx, %eax ret + /* + * For write fault handling, given the destination is unaligned, + * we handle faults on multi-byte writes with a byte-by-byte + * copy up to the write-protected page. + */ +.E_write_words: + shll $3, %ecx + addl %edx, %ecx + movl %ecx, %edx + jmp mcsafe_handle_tail + .previous - _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) + _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) + _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE(.L_write_words, .E_write_words) + _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) #endif diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index b432daea4520..b3a0709ea7ed 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -215,6 +215,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) int err; int fd; + if (argc < 3) { + p_err("too few arguments, id ID and FILE path is required"); + return -1; + } else if (argc > 3) { + p_err("too many arguments"); + return -1; + } + if (!is_prefix(*argv, "id")) { p_err("expected 'id' got %s", *argv); return -1; @@ -228,9 +236,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) } NEXT_ARG(); - if (argc != 1) - usage(); - fd = get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 9c8191845585..e860ca859b28 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -35,6 +35,7 @@ #include <errno.h> #include <fcntl.h> #include <linux/err.h> +#include <linux/kernel.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -91,7 +92,8 @@ static bool map_is_map_of_progs(__u32 type) static void *alloc_value(struct bpf_map_info *info) { if (map_is_per_cpu(info->type)) - return malloc(info->value_size * get_possible_cpus()); + return malloc(round_up(info->value_size, 8) * + get_possible_cpus()); else return malloc(info->value_size); } @@ -273,9 +275,10 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, do_dump_btf(&d, info, key, value); } } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); jsonw_name(json_wtr, "key"); print_hex_data_json(key, info->key_size); @@ -288,7 +291,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_int_field(json_wtr, "cpu", i); jsonw_name(json_wtr, "value"); - print_hex_data_json(value + i * info->value_size, + print_hex_data_json(value + i * step, info->value_size); jsonw_end_object(json_wtr); @@ -319,9 +322,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, printf("\n"); } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); printf("key:\n"); fprint_hex(stdout, key, info->key_size, " "); @@ -329,7 +333,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - fprint_hex(stdout, value + i * info->value_size, + fprint_hex(stdout, value + i * step, info->value_size, " "); printf("\n"); } diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 03161be094b4..09ecf8162f7a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -2,7 +2,6 @@ /* Copyright (c) 2018 Facebook */ #include <stdlib.h> -#include <stdint.h> #include <string.h> #include <unistd.h> #include <errno.h> @@ -32,9 +31,9 @@ struct btf { struct btf_type **types; const char *strings; void *nohdr_data; - uint32_t nr_types; - uint32_t types_size; - uint32_t data_size; + __u32 nr_types; + __u32 types_size; + __u32 data_size; int fd; }; @@ -42,7 +41,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) { if (btf->types_size - btf->nr_types < 2) { struct btf_type **new_types; - u32 expand_by, new_size; + __u32 expand_by, new_size; if (btf->types_size == BTF_MAX_NR_TYPES) return -E2BIG; @@ -69,7 +68,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) { const struct btf_header *hdr = btf->hdr; - u32 meta_left; + __u32 meta_left; if (btf->data_size < sizeof(struct btf_header)) { elog("BTF header not found\n"); @@ -148,7 +147,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) while (next_type < end_type) { struct btf_type *t = next_type; - uint16_t vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = BTF_INFO_VLEN(t->info); int err; next_type += sizeof(*t); @@ -187,6 +186,14 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) return 0; } +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + static bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; @@ -197,7 +204,7 @@ static bool btf_type_is_void_or_null(const struct btf_type *t) return !t || btf_type_is_void(t); } -static int64_t btf_type_size(const struct btf_type *t) +static __s64 btf_type_size(const struct btf_type *t) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_INT: @@ -214,12 +221,12 @@ static int64_t btf_type_size(const struct btf_type *t) #define MAX_RESOLVE_DEPTH 32 -int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id) { const struct btf_array *array; const struct btf_type *t; - uint32_t nelems = 1; - int64_t size = -1; + __u32 nelems = 1; + __s64 size = -1; int i; t = btf__type_by_id(btf, type_id); @@ -279,9 +286,9 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) return type_id; } -int32_t btf__find_by_name(const struct btf *btf, const char *type_name) +__s32 btf__find_by_name(const struct btf *btf, const char *type_name) { - uint32_t i; + __u32 i; if (!strcmp(type_name, "void")) return 0; @@ -310,10 +317,9 @@ void btf__free(struct btf *btf) free(btf); } -struct btf *btf__new(uint8_t *data, uint32_t size, - btf_print_fn_t err_log) +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) { - uint32_t log_buf_size = 0; + __u32 log_buf_size = 0; char *log_buf = NULL; struct btf *btf; int err; @@ -387,12 +393,3 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset) else return NULL; } - -const struct btf_type *btf__type_by_id(const struct btf *btf, - __u32 type_id) -{ - if (type_id > btf->nr_types) - return NULL; - - return btf->types[type_id]; -} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 24f361d99a5e..43c658ccfc2b 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -4,22 +4,23 @@ #ifndef __BPF_BTF_H #define __BPF_BTF_H -#include <stdint.h> +#include <linux/types.h> #define BTF_ELF_SEC ".BTF" struct btf; +struct btf_type; typedef int (*btf_print_fn_t)(const char *, ...) __attribute__((format(printf, 1, 2))); void btf__free(struct btf *btf); -struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); -int32_t btf__find_by_name(const struct btf *btf, const char *type_name); -int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +__s32 btf__find_by_name(const struct btf *btf, const char *type_name); +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id); int btf__resolve_type(const struct btf *btf, __u32 type_id); int btf__fd(const struct btf *btf); const char *btf__name_by_offset(const struct btf *btf, __u32 offset); -const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 955f8eafbf41..26e9527ee464 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -37,6 +37,7 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/list.h> #include <linux/limits.h> #include <sys/stat.h> @@ -170,8 +171,8 @@ struct bpf_map { size_t offset; int map_ifindex; struct bpf_map_def def; - uint32_t btf_key_type_id; - uint32_t btf_value_type_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; }; @@ -969,68 +970,72 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { + const struct btf_type *container_type; + const struct btf_member *key, *value; struct bpf_map_def *def = &map->def; const size_t max_name = 256; - int64_t key_size, value_size; - int32_t key_id, value_id; - char name[max_name]; + char container_name[max_name]; + __s64 key_size, value_size; + __s32 container_id; - /* Find key type by name from BTF */ - if (snprintf(name, max_name, "%s_key", map->name) == max_name) { - pr_warning("map:%s length of BTF key_type:%s_key is too long\n", + if (snprintf(container_name, max_name, "____btf_map_%s", map->name) == + max_name) { + pr_warning("map:%s length of '____btf_map_%s' is too long\n", map->name, map->name); return -EINVAL; } - key_id = btf__find_by_name(btf, name); - if (key_id < 0) { - pr_debug("map:%s key_type:%s cannot be found in BTF\n", - map->name, name); - return key_id; + container_id = btf__find_by_name(btf, container_name); + if (container_id < 0) { + pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", + map->name, container_name); + return container_id; } - key_size = btf__resolve_size(btf, key_id); - if (key_size < 0) { - pr_warning("map:%s key_type:%s cannot get the BTF type_size\n", - map->name, name); - return key_size; + container_type = btf__type_by_id(btf, container_id); + if (!container_type) { + pr_warning("map:%s cannot find BTF type for container_id:%u\n", + map->name, container_id); + return -EINVAL; } - if (def->key_size != key_size) { - pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n", - map->name, name, (unsigned int)key_size, def->key_size); + if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(container_type->info) < 2) { + pr_warning("map:%s container_name:%s is an invalid container struct\n", + map->name, container_name); return -EINVAL; } - /* Find value type from BTF */ - if (snprintf(name, max_name, "%s_value", map->name) == max_name) { - pr_warning("map:%s length of BTF value_type:%s_value is too long\n", - map->name, map->name); - return -EINVAL; + key = (struct btf_member *)(container_type + 1); + value = key + 1; + + key_size = btf__resolve_size(btf, key->type); + if (key_size < 0) { + pr_warning("map:%s invalid BTF key_type_size\n", + map->name); + return key_size; } - value_id = btf__find_by_name(btf, name); - if (value_id < 0) { - pr_debug("map:%s value_type:%s cannot be found in BTF\n", - map->name, name); - return value_id; + if (def->key_size != key_size) { + pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map->name, (__u32)key_size, def->key_size); + return -EINVAL; } - value_size = btf__resolve_size(btf, value_id); + value_size = btf__resolve_size(btf, value->type); if (value_size < 0) { - pr_warning("map:%s value_type:%s cannot get the BTF type_size\n", - map->name, name); + pr_warning("map:%s invalid BTF value_type_size\n", map->name); return value_size; } if (def->value_size != value_size) { - pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n", - map->name, name, (unsigned int)value_size, def->value_size); + pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map->name, (__u32)value_size, def->value_size); return -EINVAL; } - map->btf_key_type_id = key_id; - map->btf_value_type_id = value_id; + map->btf_key_type_id = key->type; + map->btf_value_type_id = value->type; return 0; } @@ -2141,12 +2146,12 @@ const char *bpf_map__name(struct bpf_map *map) return map ? map->name : NULL; } -uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map) +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map) { return map ? map->btf_key_type_id : 0; } -uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map) +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map) { return map ? map->btf_value_type_id : 0; } @@ -2333,8 +2338,8 @@ bpf_perf_event_read_simple(void *mem, unsigned long size, volatile struct perf_event_mmap_page *header = mem; __u64 data_tail = header->data_tail; __u64 data_head = header->data_head; + int ret = LIBBPF_PERF_EVENT_ERROR; void *base, *begin, *end; - int ret; asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ if (data_head == data_tail) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 1f8fc2060460..413778a93499 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -254,8 +254,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__fd(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map); -uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map); -uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 0d1acb704f64..7ec85d567598 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -519,10 +519,12 @@ struct section *elf_create_section(struct elf *elf, const char *name, sec->sh.sh_flags = SHF_ALLOC; - /* Add section name to .shstrtab */ + /* Add section name to .shstrtab (or .strtab for Clang) */ shstrtab = find_section_by_name(elf, ".shstrtab"); + if (!shstrtab) + shstrtab = find_section_by_name(elf, ".strtab"); if (!shstrtab) { - WARN("can't find .shstrtab section"); + WARN("can't find .shstrtab or .strtab section"); return NULL; } diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 63a74c32ddc5..e33ef5bc31c5 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../util/intel-pt.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 06bae7023a51..950539f9a4f7 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -2,6 +2,7 @@ #include <stdbool.h> #include <errno.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../perf.h" diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 60bf11943047..eafce1a130a1 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o perf-y += futex-requeue.o perf-y += futex-lock-pi.o +perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index b43f8d2a34ec..9ad015a1e202 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -6,6 +6,7 @@ #define altinstr_replacement text #define globl p2align 4; .globl #define _ASM_EXTABLE_FAULT(x, y) +#define _ASM_EXTABLE(x, y) #include "../../arch/x86/lib/memcpy_64.S" /* diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c new file mode 100644 index 000000000000..4130734dde84 --- /dev/null +++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c @@ -0,0 +1,24 @@ +/* + * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy + * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' + * happy. + */ +#include <linux/types.h> + +unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); + +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) { + /* + * Call the assembly routine back directly since + * memcpy_mcsafe() may silently fallback to memcpy. + */ + unsigned long rem = __memcpy_mcsafe(to, from, 1); + + if (rem) + break; + } + return len; +} diff --git a/tools/perf/perf.h b/tools/perf/perf.h index a1a97956136f..d215714f48df 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -5,6 +5,7 @@ #include <time.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> extern bool test_attr__enabled; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 90d4577a92dc..6d7fe44aadc0 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -2,6 +2,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H +#include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 760558dcfd18..cae1a9a39722 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -10,6 +10,7 @@ #define __PERF_NAMESPACES_H #include <sys/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/refcount.h> #include <linux/types.h> diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index d39e4ff7d0bf..a6db83a88e85 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -106,7 +106,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved. \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters. \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor. -\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. +\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. \fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. \fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. @@ -114,7 +114,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBCorWatt\fP Watts consumed by the core part of the package. \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors. \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. -\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. +\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. .fi .SH TOO MUCH INFORMATION EXAMPLE diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 4d14bbbf9b63..980bd9d20646 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1163,9 +1163,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ if (!printed || !summary_only) print_header("\t"); - if (topo.num_cpus > 1) - format_counters(&average.threads, &average.cores, - &average.packages); + format_counters(&average.threads, &average.cores, &average.packages); printed = 1; @@ -1692,7 +1690,7 @@ void get_apic_id(struct thread_data *t) t->x2apic_id = edx; if (debug && (t->apic_id != t->x2apic_id)) - fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); + fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); } /* @@ -2473,55 +2471,43 @@ int get_core_id(int cpu) void set_node_data(void) { - char path[80]; - FILE *filep; - int pkg, node, cpu; - - struct pkg_node_info { - int count; - int min; - } *pni; - - pni = calloc(topo.num_packages, sizeof(struct pkg_node_info)); - if (!pni) - err(1, "calloc pkg_node_count"); - - for (pkg = 0; pkg < topo.num_packages; pkg++) - pni[pkg].min = topo.num_cpus; - - for (node = 0; node <= topo.max_node_num; node++) { - /* find the "first" cpu in the node */ - sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node); - filep = fopen(path, "r"); - if (!filep) - continue; - fscanf(filep, "%d", &cpu); - fclose(filep); - - pkg = cpus[cpu].physical_package_id; - pni[pkg].count++; - - if (node < pni[pkg].min) - pni[pkg].min = node; - } - - for (pkg = 0; pkg < topo.num_packages; pkg++) - if (pni[pkg].count > topo.nodes_per_pkg) - topo.nodes_per_pkg = pni[0].count; - - /* Fake 1 node per pkg for machines that don't - * expose nodes and thus avoid -nan results - */ - if (topo.nodes_per_pkg == 0) - topo.nodes_per_pkg = 1; - - for (cpu = 0; cpu < topo.num_cpus; cpu++) { - pkg = cpus[cpu].physical_package_id; - node = cpus[cpu].physical_node_id; - cpus[cpu].logical_node_id = node - pni[pkg].min; + int pkg, node, lnode, cpu, cpux; + int cpu_count; + + /* initialize logical_node_id */ + for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) + cpus[cpu].logical_node_id = -1; + + cpu_count = 0; + for (pkg = 0; pkg < topo.num_packages; pkg++) { + lnode = 0; + for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) { + if (cpus[cpu].physical_package_id != pkg) + continue; + /* find a cpu with an unset logical_node_id */ + if (cpus[cpu].logical_node_id != -1) + continue; + cpus[cpu].logical_node_id = lnode; + node = cpus[cpu].physical_node_id; + cpu_count++; + /* + * find all matching cpus on this pkg and set + * the logical_node_id + */ + for (cpux = cpu; cpux <= topo.max_cpu_num; cpux++) { + if ((cpus[cpux].physical_package_id == pkg) && + (cpus[cpux].physical_node_id == node)) { + cpus[cpux].logical_node_id = lnode; + cpu_count++; + } + } + lnode++; + if (lnode > topo.nodes_per_pkg) + topo.nodes_per_pkg = lnode; + } + if (cpu_count >= topo.max_cpu_num) + break; } - free(pni); - } int get_physical_node_id(struct cpu_topology *thiscpu) @@ -4471,7 +4457,9 @@ void process_cpuid() family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; stepping = fms & 0xf; - if (family == 6 || family == 0xf) + if (family == 0xf) + family += (fms >> 20) & 0xff; + if (family >= 6) model += ((fms >> 16) & 0xf) << 4; if (!quiet) { @@ -4840,16 +4828,8 @@ void topology_probe() siblings = get_thread_siblings(&cpus[i]); if (siblings > max_siblings) max_siblings = siblings; - if (cpus[i].thread_id != -1) + if (cpus[i].thread_id == 0) topo.num_cores++; - - if (debug > 1) - fprintf(outf, - "cpu %d pkg %d node %d core %d thread %d\n", - i, cpus[i].physical_package_id, - cpus[i].physical_node_id, - cpus[i].physical_core_id, - cpus[i].thread_id); } topo.cores_per_node = max_core_id + 1; @@ -4875,6 +4855,20 @@ void topology_probe() topo.threads_per_core = max_siblings; if (debug > 1) fprintf(outf, "max_siblings %d\n", max_siblings); + + if (debug < 1) + return; + + for (i = 0; i <= topo.max_cpu_num; ++i) { + fprintf(outf, + "cpu %d pkg %d node %d lnode %d core %d thread %d\n", + i, cpus[i].physical_package_id, + cpus[i].physical_node_id, + cpus[i].logical_node_id, + cpus[i].physical_core_id, + cpus[i].thread_id); + } + } void @@ -5102,7 +5096,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.06.20" + fprintf(outf, "turbostat version 18.07.27" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 478bf1bcbbf5..5169a97eb68b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -106,7 +106,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) -BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') ifneq ($(BTF_LLC_PROBE),) ifneq ($(BTF_PAHOLE_PROBE),) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index f2f28b6c8915..810de20e8e26 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -158,6 +158,15 @@ struct bpf_map_def { unsigned int numa_node; }; +#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ + struct ____btf_map_##name { \ + type_key key; \ + type_val value; \ + }; \ + struct ____btf_map_##name \ + __attribute__ ((section(".maps." #name), used)) \ + ____btf_map_##name = { } + static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) = (void *) BPF_FUNC_skb_load_bytes; static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 3619f3023088..ffdd27737c9e 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -247,6 +247,34 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 4, }, +{ + .descr = "struct test #3 Invalid member offset", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int64 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), + + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 16), + BTF_MEMBER_ENC(NAME_TBD, 1, 64), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* int64 n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0", + .str_sec_size = sizeof("\0A\0m\0n\0"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test3_map", + .key_size = sizeof(int), + .value_size = 16, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid member bits_offset", +}, + /* Test member exceeds the size of struct. * * struct A { @@ -479,7 +507,7 @@ static struct btf_raw_test raw_tests[] = { .key_size = sizeof(int), .value_size = sizeof(void *) * 4, .key_type_id = 1, - .value_type_id = 4, + .value_type_id = 5, .max_entries = 4, }, @@ -1264,6 +1292,88 @@ static struct btf_raw_test raw_tests[] = { .err_str = "type != 0", }, +{ + .descr = "arraymap invalid btf key (a bit field)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* 32 bit int with 32 bit offset */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 32, 32, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 2, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf key (!= 32 bits)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* 16 bit int with 0 bit offset */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 16, 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 2, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf value (too small)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + /* btf_value_size < map->value_size */ + .value_size = sizeof(__u64), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf value (too big)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + /* btf_value_size > map->value_size */ + .value_size = sizeof(__u16), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -2023,7 +2133,7 @@ static struct btf_raw_test pprint_test = { BTF_ENUM_ENC(NAME_TBD, 2), BTF_ENUM_ENC(NAME_TBD, 3), /* struct pprint_mapv */ /* [16] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 32), BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c index 8c7ca096ecf2..b21b876f475d 100644 --- a/tools/testing/selftests/bpf/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -10,11 +10,6 @@ struct ipv_counts { unsigned int v6; }; -typedef int btf_map_key; -typedef struct ipv_counts btf_map_value; -btf_map_key dumm_key; -btf_map_value dummy_value; - struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), @@ -22,6 +17,8 @@ struct bpf_map_def SEC("maps") btf_map = { .max_entries = 4, }; +BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); + struct dummy_tracepoint_args { unsigned long long pad; struct sock *sock; diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 270fa8f49573..785eabf2a593 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -115,14 +115,14 @@ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4 +ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 -ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 ip netns exec ns4 ip -6 addr add fc42::1 dev lo ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8 +ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index f5f7bcc96046..41106d9d5cc7 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -12005,6 +12005,46 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_XDP, }, { + "xadd/w check whether src/dst got mangled, 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { + "xadd/w check whether src/dst got mangled, 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { "bpf_get_stack return R0 within range", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh new file mode 100755 index 000000000000..1ca631d5aaba --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -0,0 +1,189 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for DSCP prioritization and rewrite. Packets ingress $swp1 with a DSCP +# tag and are prioritized according to the map at $swp1. They egress $swp2 and +# the DSCP value is updated to match the map at that interface. The updated DSCP +# tag is verified at $h2. +# +# ICMP responses are produced with the same DSCP tag that arrived at $h2. They +# go through prioritization at $swp2 and DSCP retagging at $swp1. The tag is +# verified at $h1--it should match the original tag. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | | APP=0,5,10 .. 7,5,17 APP=0,5,20 .. 7,5,27 | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + test_dscp +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=4 +source $lib_dir/lib.sh + +h1_create() +{ + local dscp; + + simple_if_init $h1 192.0.2.1/28 + tc qdisc add dev $h1 clsact + dscp_capture_install $h1 10 +} + +h1_destroy() +{ + dscp_capture_uninstall $h1 10 + tc qdisc del dev $h1 clsact + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 + tc qdisc add dev $h2 clsact + dscp_capture_install $h2 20 +} + +h2_destroy() +{ + dscp_capture_uninstall $h2 20 + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 +} + +dscp_map() +{ + local base=$1; shift + + for prio in {0..7}; do + echo app=$prio,5,$((base + prio)) + done +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null + lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null + lldpad_app_wait_set $swp1 + lldpad_app_wait_set $swp2 +} + +switch_destroy() +{ + lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null + lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null + lldpad_app_wait_del + + ip link set dev $swp2 nomaster + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +dscp_ping_test() +{ + local vrf_name=$1; shift + local sip=$1; shift + local dip=$1; shift + local prio=$1; shift + local dev_10=$1; shift + local dev_20=$1; shift + + local dscp_10=$(((prio + 10) << 2)) + local dscp_20=$(((prio + 20) << 2)) + + RET=0 + + local -A t0s + eval "t0s=($(dscp_fetch_stats $dev_10 10) + $(dscp_fetch_stats $dev_20 20))" + + ip vrf exec $vrf_name \ + ${PING} -Q $dscp_10 ${sip:+-I $sip} $dip \ + -c 10 -i 0.1 -w 2 &> /dev/null + + local -A t1s + eval "t1s=($(dscp_fetch_stats $dev_10 10) + $(dscp_fetch_stats $dev_20 20))" + + for key in ${!t0s[@]}; do + local expect + if ((key == prio+10 || key == prio+20)); then + expect=10 + else + expect=0 + fi + + local delta=$((t1s[$key] - t0s[$key])) + ((expect == delta)) + check_err $? "DSCP $key: Expected to capture $expect packets, got $delta." + done + + log_test "DSCP rewrite: $dscp_10-(prio $prio)-$dscp_20" +} + +test_dscp() +{ + for prio in {0..7}; do + dscp_ping_test v$h1 192.0.2.1 192.0.2.2 $prio $h1 $h2 + done +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh new file mode 100755 index 000000000000..281d90766e12 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh @@ -0,0 +1,233 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for DSCP prioritization in the router. +# +# With ip_forward_update_priority disabled, the packets are expected to keep +# their DSCP (which in this test uses only values 0..7) intact as they are +# forwarded by the switch. That is verified at $h2. ICMP responses are formed +# with the same DSCP as the requests, and likewise pass through the switch +# intact, which is verified at $h1. +# +# With ip_forward_update_priority enabled, router reprioritizes the packets +# according to the table in reprioritize(). Thus, say, DSCP 7 maps to priority +# 4, which on egress maps back to DSCP 4. The response packet then gets +# reprioritized to 6, getting DSCP 6 on egress. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.18/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | + $swp1 $swp2 + | +# | 192.0.2.2/28 192.0.2.17/28 | +# | APP=0,5,0 .. 7,5,7 APP=0,5,0 .. 7,5,7 | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + test_update + test_no_update +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=4 +source $lib_dir/lib.sh + +reprioritize() +{ + local in=$1; shift + + # This is based on rt_tos2priority in include/net/route.h. Assuming 1:1 + # mapping between priorities and TOS, it yields a new priority for a + # packet with ingress priority of $in. + local -a reprio=(0 0 2 2 6 6 4 4) + + echo ${reprio[$in]} +} + +h1_create() +{ + local dscp; + + simple_if_init $h1 192.0.2.1/28 + tc qdisc add dev $h1 clsact + dscp_capture_install $h1 0 + ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2 +} + +h1_destroy() +{ + ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2 + dscp_capture_uninstall $h1 0 + tc qdisc del dev $h1 clsact + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.18/28 + tc qdisc add dev $h2 clsact + dscp_capture_install $h2 0 + ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17 +} + +h2_destroy() +{ + ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17 + dscp_capture_uninstall $h2 0 + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.18/28 +} + +dscp_map() +{ + local base=$1; shift + + for prio in {0..7}; do + echo app=$prio,5,$((base + prio)) + done +} + +switch_create() +{ + simple_if_init $swp1 192.0.2.2/28 + __simple_if_init $swp2 v$swp1 192.0.2.17/28 + + lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null + lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null + lldpad_app_wait_set $swp1 + lldpad_app_wait_set $swp2 +} + +switch_destroy() +{ + lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null + lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null + lldpad_app_wait_del + + __simple_if_fini $swp2 192.0.2.17/28 + simple_if_fini $swp1 192.0.2.2/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + sysctl_set net.ipv4.ip_forward_update_priority 1 + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + sysctl_restore net.ipv4.ip_forward_update_priority + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.18 +} + +dscp_ping_test() +{ + local vrf_name=$1; shift + local sip=$1; shift + local dip=$1; shift + local prio=$1; shift + local reprio=$1; shift + local dev1=$1; shift + local dev2=$1; shift + + local prio2=$($reprio $prio) # ICMP Request egress prio + local prio3=$($reprio $prio2) # ICMP Response egress prio + + local dscp=$((prio << 2)) # ICMP Request ingress DSCP + local dscp2=$((prio2 << 2)) # ICMP Request egress DSCP + local dscp3=$((prio3 << 2)) # ICMP Response egress DSCP + + RET=0 + + eval "local -A dev1_t0s=($(dscp_fetch_stats $dev1 0))" + eval "local -A dev2_t0s=($(dscp_fetch_stats $dev2 0))" + + ip vrf exec $vrf_name \ + ${PING} -Q $dscp ${sip:+-I $sip} $dip \ + -c 10 -i 0.1 -w 2 &> /dev/null + + eval "local -A dev1_t1s=($(dscp_fetch_stats $dev1 0))" + eval "local -A dev2_t1s=($(dscp_fetch_stats $dev2 0))" + + for i in {0..7}; do + local dscpi=$((i << 2)) + local expect2=0 + local expect3=0 + + if ((i == prio2)); then + expect2=10 + fi + if ((i == prio3)); then + expect3=10 + fi + + local delta=$((dev2_t1s[$i] - dev2_t0s[$i])) + ((expect2 == delta)) + check_err $? "DSCP $dscpi@$dev2: Expected to capture $expect2 packets, got $delta." + + delta=$((dev1_t1s[$i] - dev1_t0s[$i])) + ((expect3 == delta)) + check_err $? "DSCP $dscpi@$dev1: Expected to capture $expect3 packets, got $delta." + done + + log_test "DSCP rewrite: $dscp-(prio $prio2)-$dscp2-(prio $prio3)-$dscp3" +} + +__test_update() +{ + local update=$1; shift + local reprio=$1; shift + + sysctl_restore net.ipv4.ip_forward_update_priority + sysctl_set net.ipv4.ip_forward_update_priority $update + + for prio in {0..7}; do + dscp_ping_test v$h1 192.0.2.1 192.0.2.18 $prio $reprio $h1 $h2 + done +} + +test_update() +{ + __test_update 1 reprioritize +} + +test_no_update() +{ + __test_update 0 echo +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc new file mode 100644 index 000000000000..3b1f45e13a2e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc @@ -0,0 +1,28 @@ +#!/bin/sh +# description: Snapshot and tracing setting +# flags: instance + +[ ! -f snapshot ] && exit_unsupported + +echo "Set tracing off" +echo 0 > tracing_on + +echo "Allocate and take a snapshot" +echo 1 > snapshot + +# Since trace buffer is empty, snapshot is also empty, but allocated +grep -q "Snapshot is allocated" snapshot + +echo "Ensure keep tracing off" +test `cat tracing_on` -eq 0 + +echo "Set tracing on" +echo 1 > tracing_on + +echo "Take a snapshot again" +echo 1 > snapshot + +echo "Ensure keep tracing on" +test `cat tracing_on` -eq 1 + +exit 0 diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 1a0ac3a29ec5..78b24cf76f40 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -13,3 +13,4 @@ udpgso udpgso_bench_rx udpgso_bench_tx tcp_inq +tls diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 158d59ffee40..ca53b539aa2d 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -8,6 +8,8 @@ PING=${PING:=ping} PING6=${PING6:=ping6} MZ=${MZ:=mausezahn} +ARPING=${ARPING:=arping} +TEAMD=${TEAMD:=teamd} WAIT_TIME=${WAIT_TIME:=5} PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no} @@ -62,15 +64,18 @@ if [[ "$CHECK_TC" = "yes" ]]; then check_tc_version fi -if [[ ! -x "$(command -v jq)" ]]; then - echo "SKIP: jq not installed" - exit 1 -fi +require_command() +{ + local cmd=$1; shift -if [[ ! -x "$(command -v $MZ)" ]]; then - echo "SKIP: $MZ not installed" - exit 1 -fi + if [[ ! -x "$(command -v "$cmd")" ]]; then + echo "SKIP: $cmd not installed" + exit 1 + fi +} + +require_command jq +require_command $MZ if [[ ! -v NUM_NETIFS ]]; then echo "SKIP: importer does not define \"NUM_NETIFS\"" @@ -242,6 +247,27 @@ setup_wait() sleep $WAIT_TIME } +lldpad_app_wait_set() +{ + local dev=$1; shift + + while lldptool -t -i $dev -V APP -c app | grep -q pending; do + echo "$dev: waiting for lldpad to push pending APP updates" + sleep 5 + done +} + +lldpad_app_wait_del() +{ + # Give lldpad a chance to push down the changes. If the device is downed + # too soon, the updates will be left pending. However, they will have + # been struck off the lldpad's DB already, so we won't be able to tell + # they are pending. Then on next test iteration this would cause + # weirdness as newly-added APP rules conflict with the old ones, + # sometimes getting stuck in an "unknown" state. + sleep 5 +} + pre_cleanup() { if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then @@ -422,6 +448,28 @@ vlan_destroy() ip link del dev $name } +team_create() +{ + local if_name=$1; shift + local mode=$1; shift + + require_command $TEAMD + $TEAMD -t $if_name -d -c '{"runner": {"name": "'$mode'"}}' + for slave in "$@"; do + ip link set dev $slave down + ip link set dev $slave master $if_name + ip link set dev $slave up + done + ip link set dev $if_name up +} + +team_destroy() +{ + local if_name=$1; shift + + $TEAMD -t $if_name -k +} + master_name_get() { local if_name=$1 @@ -605,6 +653,48 @@ vlan_capture_uninstall() __vlan_capture_add_del del 100 "$@" } +__dscp_capture_add_del() +{ + local add_del=$1; shift + local dev=$1; shift + local base=$1; shift + local dscp; + + for prio in {0..7}; do + dscp=$((base + prio)) + __icmp_capture_add_del $add_del $((dscp + 100)) "" $dev \ + "skip_hw ip_tos $((dscp << 2))" + done +} + +dscp_capture_install() +{ + local dev=$1; shift + local base=$1; shift + + __dscp_capture_add_del add $dev $base +} + +dscp_capture_uninstall() +{ + local dev=$1; shift + local base=$1; shift + + __dscp_capture_add_del del $dev $base +} + +dscp_fetch_stats() +{ + local dev=$1; shift + local base=$1; shift + + for prio in {0..7}; do + local dscp=$((base + prio)) + local t=$(tc_rule_stats_get $dev $((dscp + 100))) + echo "[$dscp]=$t " + done +} + matchall_sink_create() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh new file mode 100755 index 000000000000..61844caf671e --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for "tc action mirred egress mirror" when the underlay route points at a +# bridge device with vlan filtering (802.1q), and the egress device is a team +# device. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1.333 | | $h1.555 + | +# | | 192.0.2.1/28 | | 192.0.2.18/28 | | +# +-----|----------------+ +----------------|-----+ +# | $h1 | +# +--------------------------------+------------------------------+ +# | +# +--------------------------------------|------------------------------------+ +# | SW o---> mirror | +# | | | +# | +--------------------------------+------------------------------+ | +# | | $swp1 | | +# | + $swp1.333 $swp1.555 + | +# | 192.0.2.2/28 192.0.2.17/28 | +# | | +# | +-----------------------------------------------------------------------+ | +# | | BR1 (802.1q) | | +# | | + lag (team) 192.0.2.129/28 | | +# | | / \ 2001:db8:2::1/64 | | +# | +---/---\---------------------------------------------------------------+ | +# | / \ ^ | +# | | \ + gt4 (gretap) | | +# | | \ loc=192.0.2.129 | | +# | | \ rem=192.0.2.130 -+ | +# | | \ ttl=100 | +# | | \ tos=inherit | +# | | \ | +# | | \_________________________________ | +# | | \ | +# | + $swp3 + $swp4 | +# +---|------------------------------------------------|----------------------+ +# | | +# +---|----------------------+ +---|----------------------+ +# | + $h3 H3 | | + $h4 H4 | +# | 192.0.2.130/28 | | 192.0.2.130/28 | +# | 2001:db8:2::2/64 | | 2001:db8:2::2/64 | +# +--------------------------+ +--------------------------+ + +ALL_TESTS=" + test_mirror_gretap_first + test_mirror_gretap_second +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +require_command $ARPING + +vlan_host_create() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + local ips=("${@}") + + vrf_create $vrf_name + ip link set dev $vrf_name up + vlan_create $if_name $vid $vrf_name "${ips[@]}" +} + +vlan_host_destroy() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + + vlan_destroy $if_name $vid + ip link set dev $vrf_name down + vrf_destroy $vrf_name +} + +h1_create() +{ + vlan_host_create $h1 333 vrf-h1 192.0.2.1/28 + ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2 +} + +h1_destroy() +{ + ip -4 route del 192.0.2.16/28 vrf vrf-h1 + vlan_host_destroy $h1 333 vrf-h1 +} + +h2_create() +{ + vlan_host_create $h1 555 vrf-h2 192.0.2.18/28 + ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17 +} + +h2_destroy() +{ + ip -4 route del 192.0.2.0/28 vrf vrf-h2 + vlan_host_destroy $h1 555 vrf-h2 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.130/28 + tc qdisc add dev $h3 clsact +} + +h3_destroy() +{ + tc qdisc del dev $h3 clsact + simple_if_fini $h3 192.0.2.130/28 +} + +h4_create() +{ + simple_if_init $h4 192.0.2.130/28 + tc qdisc add dev $h4 clsact +} + +h4_destroy() +{ + tc qdisc del dev $h4 clsact + simple_if_fini $h4 192.0.2.130/28 +} + +switch_create() +{ + ip link set dev $swp1 up + tc qdisc add dev $swp1 clsact + vlan_create $swp1 333 "" 192.0.2.2/28 + vlan_create $swp1 555 "" 192.0.2.17/28 + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + ip link set dev $swp3 up + ip link set dev $swp4 up + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + __addr_add_del br1 add 192.0.2.129/32 + ip -4 route add 192.0.2.130/32 dev br1 + + team_create lag loadbalance $swp3 $swp4 + ip link set dev lag master br1 +} + +switch_destroy() +{ + ip link set dev lag nomaster + team_destroy lag + + ip -4 route del 192.0.2.130/32 dev br1 + __addr_add_del br1 del 192.0.2.129/32 + ip link set dev br1 down + ip link del dev br1 + + ip link set dev $swp4 down + ip link set dev $swp3 down + + tunnel_destroy gt4 + + vlan_destroy $swp1 555 + vlan_destroy $swp1 333 + tc qdisc del dev $swp1 clsact + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp3=${NETIFS[p3]} + h3=${NETIFS[p4]} + + swp4=${NETIFS[p5]} + h4=${NETIFS[p6]} + + vrf_prepare + + ip link set dev $h1 up + h1_create + h2_create + h3_create + h4_create + switch_create + + trap_install $h3 ingress + trap_install $h4 ingress +} + +cleanup() +{ + pre_cleanup + + trap_uninstall $h4 ingress + trap_uninstall $h3 ingress + + switch_destroy + h4_destroy + h3_destroy + h2_destroy + h1_destroy + ip link set dev $h1 down + + vrf_cleanup +} + +test_lag_slave() +{ + local host_dev=$1; shift + local up_dev=$1; shift + local down_dev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress gt4 \ + "proto 802.1q flower vlan_id 333 $tcflags" + + # Test connectivity through $up_dev when $down_dev is set down. + ip link set dev $down_dev down + setup_wait_dev $up_dev + setup_wait_dev $host_dev + $ARPING -I br1 192.0.2.130 -qfc 1 + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $host_dev 1 10 + + # Test lack of connectivity when both slaves are down. + ip link set dev $up_dev down + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0 + + ip link set dev $up_dev up + ip link set dev $down_dev up + mirror_uninstall $swp1 ingress + + log_test "$what ($tcflags)" +} + +test_mirror_gretap_first() +{ + test_lag_slave $h3 $swp3 $swp4 "mirror to gretap: LAG first slave" +} + +test_mirror_gretap_second() +{ + test_lag_slave $h4 $swp4 $swp3 "mirror to gretap: LAG second slave" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh new file mode 100755 index 000000000000..9edf4cb104a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh @@ -0,0 +1,285 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for "tc action mirred egress mirror" when the underlay route points at a +# team device. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1.333 | | $h1.555 + | +# | | 192.0.2.1/28 | | 192.0.2.18/28 | | +# +----|-----------------+ +----------------|-----+ +# | $h1 | +# +---------------------------------+------------------------------+ +# | +# +--------------------------------------|------------------------------------+ +# | SW o---> mirror | +# | | | +# | +----------------------------------+------------------------------+ | +# | | $swp1 | | +# | + $swp1.333 $swp1.555 + | +# | 192.0.2.2/28 192.0.2.17/28 | +# | | +# | | +# | + gt4 (gretap) ,-> + lag1 (team) | +# | loc=192.0.2.129 | | 192.0.2.129/28 | +# | rem=192.0.2.130 --' | | +# | ttl=100 | | +# | tos=inherit | | +# | _____________________|______________________ | +# | / \ | +# | / \ | +# | + $swp3 + $swp4 | +# +---|------------------------------------------------|----------------------+ +# | | +# +---|------------------------------------------------|----------------------+ +# | + $h3 + $h4 H3 | +# | \ / | +# | \____________________________________________/ | +# | | | +# | + lag2 (team) | +# | 192.0.2.130/28 | +# | | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + test_mirror_gretap_first + test_mirror_gretap_second +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +require_command $ARPING + +vlan_host_create() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + local ips=("${@}") + + vrf_create $vrf_name + ip link set dev $vrf_name up + vlan_create $if_name $vid $vrf_name "${ips[@]}" +} + +vlan_host_destroy() +{ + local if_name=$1; shift + local vid=$1; shift + local vrf_name=$1; shift + + vlan_destroy $if_name $vid + ip link set dev $vrf_name down + vrf_destroy $vrf_name +} + +h1_create() +{ + vlan_host_create $h1 333 vrf-h1 192.0.2.1/28 + ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2 +} + +h1_destroy() +{ + ip -4 route del 192.0.2.16/28 vrf vrf-h1 + vlan_host_destroy $h1 333 vrf-h1 +} + +h2_create() +{ + vlan_host_create $h1 555 vrf-h2 192.0.2.18/28 + ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17 +} + +h2_destroy() +{ + ip -4 route del 192.0.2.0/28 vrf vrf-h2 + vlan_host_destroy $h1 555 vrf-h2 +} + +h3_create_team() +{ + team_create lag2 lacp $h3 $h4 + __simple_if_init lag2 vrf-h3 192.0.2.130/32 + ip -4 route add vrf vrf-h3 192.0.2.129/32 dev lag2 +} + +h3_destroy_team() +{ + ip -4 route del vrf vrf-h3 192.0.2.129/32 dev lag2 + __simple_if_fini lag2 192.0.2.130/32 + team_destroy lag2 + + ip link set dev $h3 down + ip link set dev $h4 down +} + +h3_create() +{ + vrf_create vrf-h3 + ip link set dev vrf-h3 up + tc qdisc add dev $h3 clsact + tc qdisc add dev $h4 clsact + h3_create_team +} + +h3_destroy() +{ + h3_destroy_team + tc qdisc del dev $h4 clsact + tc qdisc del dev $h3 clsact + ip link set dev vrf-h3 down + vrf_destroy vrf-h3 +} + +switch_create() +{ + ip link set dev $swp1 up + tc qdisc add dev $swp1 clsact + vlan_create $swp1 333 "" 192.0.2.2/28 + vlan_create $swp1 555 "" 192.0.2.17/28 + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + ip link set dev $swp3 up + ip link set dev $swp4 up + team_create lag1 lacp $swp3 $swp4 + __addr_add_del lag1 add 192.0.2.129/32 + ip -4 route add 192.0.2.130/32 dev lag1 +} + +switch_destroy() +{ + ip -4 route del 192.0.2.130/32 dev lag1 + __addr_add_del lag1 del 192.0.2.129/32 + team_destroy lag1 + + ip link set dev $swp4 down + ip link set dev $swp3 down + + tunnel_destroy gt4 + + vlan_destroy $swp1 555 + vlan_destroy $swp1 333 + tc qdisc del dev $swp1 clsact + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp3=${NETIFS[p3]} + h3=${NETIFS[p4]} + + swp4=${NETIFS[p5]} + h4=${NETIFS[p6]} + + vrf_prepare + + ip link set dev $h1 up + h1_create + h2_create + h3_create + switch_create + + trap_install $h3 ingress + trap_install $h4 ingress +} + +cleanup() +{ + pre_cleanup + + trap_uninstall $h4 ingress + trap_uninstall $h3 ingress + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + ip link set dev $h1 down + + vrf_cleanup +} + +test_lag_slave() +{ + local up_dev=$1; shift + local down_dev=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress gt4 \ + "proto 802.1q flower vlan_id 333 $tcflags" + + # Move $down_dev away from the team. That will prompt change in + # txability of the connected device, without changing its upness. The + # driver should notice the txability change and move the traffic to the + # other slave. + ip link set dev $down_dev nomaster + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $up_dev 1 10 + + # Test lack of connectivity when neither slave is txable. + ip link set dev $up_dev nomaster + sleep 2 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0 + mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0 + mirror_uninstall $swp1 ingress + + # Recreate H3's team device, because mlxsw, which this test is + # predominantly mean to test, requires a bottom-up construction and + # doesn't allow enslavement to a device that already has an upper. + h3_destroy_team + h3_create_team + # Wait for ${h,swp}{3,4}. + setup_wait + + log_test "$what ($tcflags)" +} + +test_mirror_gretap_first() +{ + test_lag_slave $h3 $h4 "mirror to gretap: LAG first slave" +} + +test_mirror_gretap_second() +{ + test_lag_slave $h4 $h3 "mirror to gretap: LAG second slave" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index d3e75bb6a2d8..204b25f13934 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -28,6 +28,8 @@ source mirror_lib.sh source mirror_gre_lib.sh source mirror_gre_topo_lib.sh +require_command $ARPING + setup_prepare() { h1=${NETIFS[p1]} @@ -149,7 +151,7 @@ test_span_gre_forbidden_egress() bridge vlan add dev $swp3 vid 555 # Re-prime FDB - arping -I br1.555 192.0.2.130 -fqc 1 + $ARPING -I br1.555 192.0.2.130 -fqc 1 sleep 1 quick_test_span_gre_dir $tundev ingress @@ -223,7 +225,7 @@ test_span_gre_fdb_roaming() bridge fdb del dev $swp2 $h3mac vlan 555 master # Re-prime FDB - arping -I br1.555 192.0.2.130 -fqc 1 + $ARPING -I br1.555 192.0.2.130 -fqc 1 sleep 1 quick_test_span_gre_dir $tundev ingress diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh new file mode 100755 index 000000000000..7bd2ebb6e9de --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh @@ -0,0 +1,233 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="ping_ipv4" +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + vrf_create "vrf-h1" + ip link set dev $h1 master vrf-h1 + + ip link set dev vrf-h1 up + ip link set dev $h1 up + + ip address add 192.0.2.2/24 dev $h1 + + ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1 + ip route add 198.51.200.0/24 vrf vrf-h1 nexthop via 192.0.2.1 +} + +h1_destroy() +{ + ip route del 198.51.200.0/24 vrf vrf-h1 + ip route del 198.51.100.0/24 vrf vrf-h1 + + ip address del 192.0.2.2/24 dev $h1 + + ip link set dev $h1 down + vrf_destroy "vrf-h1" +} + +h2_create() +{ + vrf_create "vrf-h2" + ip link set dev $h2 master vrf-h2 + + ip link set dev vrf-h2 up + ip link set dev $h2 up + + ip address add 198.51.100.2/24 dev $h2 + + ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1 + ip route add 198.51.200.0/24 vrf vrf-h2 nexthop via 198.51.100.1 +} + +h2_destroy() +{ + ip route del 198.51.200.0/24 vrf vrf-h2 + ip route del 192.0.2.0/24 vrf vrf-h2 + + ip address del 198.51.100.2/24 dev $h2 + + ip link set dev $h2 down + vrf_destroy "vrf-h2" +} + +h3_create() +{ + vrf_create "vrf-h3" + ip link set dev $h3 master vrf-h3 + + ip link set dev vrf-h3 up + ip link set dev $h3 up + + ip address add 198.51.200.2/24 dev $h3 + + ip route add 192.0.2.0/24 vrf vrf-h3 nexthop via 198.51.200.1 + ip route add 198.51.100.0/24 vrf vrf-h3 nexthop via 198.51.200.1 +} + +h3_destroy() +{ + ip route del 198.51.100.0/24 vrf vrf-h3 + ip route del 192.0.2.0/24 vrf vrf-h3 + + ip address del 198.51.200.2/24 dev $h3 + + ip link set dev $h3 down + vrf_destroy "vrf-h3" +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + ip link set dev $rp3 up + + ip address add 192.0.2.1/24 dev $rp1 + + ip address add 198.51.100.1/24 dev $rp2 + ip address add 198.51.200.1/24 dev $rp3 +} + +router_destroy() +{ + ip address del 198.51.200.1/24 dev $rp3 + ip address del 198.51.100.1/24 dev $rp2 + + ip address del 192.0.2.1/24 dev $rp1 + + ip link set dev $rp3 down + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + + h1_create + h2_create + h3_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +bc_forwarding_disable() +{ + sysctl_set net.ipv4.conf.all.bc_forwarding 0 + sysctl_set net.ipv4.conf.$rp1.bc_forwarding 0 +} + +bc_forwarding_enable() +{ + sysctl_set net.ipv4.conf.all.bc_forwarding 1 + sysctl_set net.ipv4.conf.$rp1.bc_forwarding 1 +} + +bc_forwarding_restore() +{ + sysctl_restore net.ipv4.conf.$rp1.bc_forwarding + sysctl_restore net.ipv4.conf.all.bc_forwarding +} + +ping_test_from() +{ + local oif=$1 + local dip=$2 + local from=$3 + local fail=${4:-0} + + RET=0 + + log_info "ping $dip, expected reply from $from" + ip vrf exec $(master_name_get $oif) \ + $PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null + check_err_fail $fail $? +} + +ping_ipv4() +{ + sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0 + + bc_forwarding_disable + log_info "bc_forwarding disabled on r1 =>" + ping_test_from $h1 198.51.100.255 192.0.2.1 + log_test "h1 -> net2: reply from r1 (not forwarding)" + ping_test_from $h1 198.51.200.255 192.0.2.1 + log_test "h1 -> net3: reply from r1 (not forwarding)" + ping_test_from $h1 192.0.2.255 192.0.2.1 + log_test "h1 -> net1: reply from r1 (not dropping)" + ping_test_from $h1 255.255.255.255 192.0.2.1 + log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)" + + ping_test_from $h2 192.0.2.255 198.51.100.1 + log_test "h2 -> net1: reply from r1 (not forwarding)" + ping_test_from $h2 198.51.200.255 198.51.100.1 + log_test "h2 -> net3: reply from r1 (not forwarding)" + ping_test_from $h2 198.51.100.255 198.51.100.1 + log_test "h2 -> net2: reply from r1 (not dropping)" + ping_test_from $h2 255.255.255.255 198.51.100.1 + log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)" + bc_forwarding_restore + + bc_forwarding_enable + log_info "bc_forwarding enabled on r1 =>" + ping_test_from $h1 198.51.100.255 198.51.100.2 + log_test "h1 -> net2: reply from h2 (forwarding)" + ping_test_from $h1 198.51.200.255 198.51.200.2 + log_test "h1 -> net3: reply from h3 (forwarding)" + ping_test_from $h1 192.0.2.255 192.0.2.1 1 + log_test "h1 -> net1: no reply (dropping)" + ping_test_from $h1 255.255.255.255 192.0.2.1 + log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)" + + ping_test_from $h2 192.0.2.255 192.0.2.2 + log_test "h2 -> net1: reply from h1 (forwarding)" + ping_test_from $h2 198.51.200.255 198.51.200.2 + log_test "h2 -> net3: reply from h3 (forwarding)" + ping_test_from $h2 198.51.100.255 198.51.100.1 1 + log_test "h2 -> net2: no reply (dropping)" + ping_test_from $h2 255.255.255.255 198.51.100.1 + log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)" + bc_forwarding_restore + + sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh index 031e322e28b3..2934fb5ed2a2 100755 --- a/tools/testing/selftests/net/forwarding/tc_chains.sh +++ b/tools/testing/selftests/net/forwarding/tc_chains.sh @@ -88,9 +88,30 @@ create_destroy_chain() tc chain add dev $h2 ingress check_err $? "Failed to create default chain" + output="$(tc -j chain get dev $h2 ingress)" + check_err $? "Failed to get default chain" + + echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null + check_err $? "Unexpected output for default chain" + tc chain add dev $h2 ingress chain 1 check_err $? "Failed to create chain 1" + output="$(tc -j chain get dev $h2 ingress chain 1)" + check_err $? "Failed to get chain 1" + + echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null + check_err $? "Unexpected output for chain 1" + + output="$(tc -j chain show dev $h2 ingress)" + check_err $? "Failed to dump chains" + + echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null + check_err $? "Can't find default chain in dump" + + echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null + check_err $? "Can't find chain 1 in dump" + tc chain del dev $h2 ingress check_err $? "Failed to destroy default chain" diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 77f762780199..e8c5dff448eb 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -402,7 +402,7 @@ int main(int argc, char *argv[]) exit(1); } - fd = socket(AF_INET6, SOCK_STREAM, 0); + fd = socket(cfg_family, SOCK_STREAM, 0); if (fd == -1) { perror("socket"); exit(1); diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index 95dd14648ba5..0f395dfb7774 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -44,12 +44,25 @@ /******************** Little Endian Handling ********************************/ -#define cpu_to_le16(x) htole16(x) -#define cpu_to_le32(x) htole32(x) +/* + * cpu_to_le16/32 are used when initializing structures, a context where a + * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way + * that allows them to be used when initializing structures. + */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define cpu_to_le16(x) (x) +#define cpu_to_le32(x) (x) +#else +#define cpu_to_le16(x) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)) +#define cpu_to_le32(x) \ + ((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >> 8) | \ + (((x) & 0x0000ff00u) << 8) | (((x) & 0x000000ffu) << 24)) +#endif + #define le32_to_cpu(x) le32toh(x) #define le16_to_cpu(x) le16toh(x) - /******************** Messages and Errors ***********************************/ static const char argv0[] = "ffs-test"; diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index 0ac3caf90877..d0351f83aebe 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -13,8 +13,8 @@ } while (0); /* Weak barriers should be used. If not - it's a bug */ # define mb() abort() -# define rmb() abort() -# define wmb() abort() +# define dma_rmb() abort() +# define dma_wmb() abort() #else #error Please fill in barrier macros #endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index fca8381bbe04..fb22bccfbc8a 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -52,6 +52,11 @@ static inline void *kmalloc(size_t s, gfp_t gfp) return __kmalloc_fake; return malloc(s); } +static inline void *kmalloc_array(unsigned n, size_t s, gfp_t gfp) +{ + return kmalloc(n * s, gfp); +} + static inline void *kzalloc(size_t s, gfp_t gfp) { void *p = kmalloc(s, gfp); |