diff options
645 files changed, 19169 insertions, 4099 deletions
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs index f6d9c2a8d528..2e9ae311e02d 100644 --- a/Documentation/ABI/testing/debugfs-driver-habanalabs +++ b/Documentation/ABI/testing/debugfs-driver-habanalabs @@ -16,7 +16,16 @@ Description: Allow the root user to disable/enable in runtime the clock gating mechanism in Gaudi. Due to how Gaudi is built, the clock gating needs to be disabled in order to access the registers of the TPC and MME engines. This is sometimes needed - during debug by the user and hence the user needs this option + during debug by the user and hence the user needs this option. + The user can supply a bitmask value, each bit represents + a different engine to disable/enable its clock gating feature. + The bitmask is composed of 20 bits: + 0 - 7 : DMA channels + 8 - 11 : MME engines + 12 - 19 : TPC engines + The bit's location of a specific engine can be determined + using (1 << GAUDI_ENGINE_ID_*). GAUDI_ENGINE_ID_* values + are defined in uapi habanalabs.h file in enum gaudi_engine_id What: /sys/kernel/debug/habanalabs/hl<n>/command_buffers Date: Jan 2019 diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml index 526593c8c614..4cc1a670c986 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml @@ -47,6 +47,9 @@ properties: $ref: /schemas/types.yaml#/definitions/phandle-array description: Phandle to the device SRAM + iommus: + maxItems: 1 + memory-region: description: CMA pool to use for buffers allocation instead of the default diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index d6a3bf8550eb..26afb556dfae 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -39,6 +39,13 @@ properties: and must therefore be appropriately determined based on all devices requirements (maximum value of all per-device RESET pulse widths). + reset-post-delay-us: + description: + Delay after reset deassert in microseconds. It applies to all MDIO + devices and it's determined by how fast all devices are ready for + communication. This delay happens just before e.g. Ethernet PHY + type ID auto detection. + clock-frequency: description: Desired MDIO bus clock frequency in Hz. Values greater than IEEE 802.3 diff --git a/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml b/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml index f15a5e5e4859..c488f24ed38f 100644 --- a/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml +++ b/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml @@ -44,7 +44,7 @@ examples: uart1 { pinctrl-names = "default"; pinctrl-0 = <&uart1_pins>, <&uart1_rts_cts_pins>; - uart-has-rtscts = <1>; + uart-has-rtscts; bluetooth { compatible = "realtek,rtl8723bs-bt"; diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 6567187e7687..7fc1e0cccae7 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -95,6 +95,7 @@ available subsections can be seen below. phy/index pti_intel_mid pwm + pldmfw/index rfkill serial/index sm501 diff --git a/Documentation/driver-api/pldmfw/driver-ops.rst b/Documentation/driver-api/pldmfw/driver-ops.rst new file mode 100644 index 000000000000..f0654783d3b3 --- /dev/null +++ b/Documentation/driver-api/pldmfw/driver-ops.rst @@ -0,0 +1,56 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +========================= +Driver-specific callbacks +========================= + +The ``pldmfw`` module relies on the device driver for implementing device +specific behavior using the following operations. + +``.match_record`` +----------------- + +The ``.match_record`` operation is used to determine whether a given PLDM +record matches the device being updated. This requires comparing the record +descriptors in the record with information from the device. Many record +descriptors are defined by the PLDM standard, but it is also allowed for +devices to implement their own descriptors. + +The ``.match_record`` operation should return true if a given record matches +the device. + +``.send_package_data`` +---------------------- + +The ``.send_package_data`` operation is used to send the device-specific +package data in a record to the device firmware. If the matching record +provides package data, ``pldmfw`` will call the ``.send_package_data`` +function with a pointer to the package data and with the package data +length. The device driver should send this data to firmware. + +``.send_component_table`` +------------------------- + +The ``.send_component_table`` operation is used to forward component +information to the device. It is called once for each applicable component, +that is, for each component indicated by the matching record. The +device driver should send the component information to the device firmware, +and wait for a response. The provided transfer flag indicates whether this +is the first, last, or a middle component, and is expected to be forwarded +to firmware as part of the component table information. The driver should an +error in the case when the firmware indicates that the component cannot be +updated, or return zero if the component can be updated. + +``.flash_component`` +-------------------- + +The ``.flash_component`` operation is used to inform the device driver to +flash a given component. The driver must perform any steps necessary to send +the component data to the device. + +``.finalize_update`` +-------------------- + +The ``.finalize_update`` operation is used by the ``pldmfw`` library in +order to allow the device driver to perform any remaining device specific +logic needed to finish the update. diff --git a/Documentation/driver-api/pldmfw/file-format.rst b/Documentation/driver-api/pldmfw/file-format.rst new file mode 100644 index 000000000000..b7a9cebe09c6 --- /dev/null +++ b/Documentation/driver-api/pldmfw/file-format.rst @@ -0,0 +1,203 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +================================== +PLDM Firmware file format overview +================================== + +A PLDM firmware package is a binary file which contains a header that +describes the contents of the firmware package. This includes an initial +package header, one or more firmware records, and one or more components +describing the actual flash contents to program. + +This diagram provides an overview of the file format:: + + overall file layout + +----------------------+ + | | + | Package Header | + | | + +----------------------+ + | | + | Device Records | + | | + +----------------------+ + | | + | Component Info | + | | + +----------------------+ + | | + | Package Header CRC | + | | + +----------------------+ + | | + | Component Image 1 | + | | + +----------------------+ + | | + | Component Image 2 | + | | + +----------------------+ + | | + | ... | + | | + +----------------------+ + | | + | Component Image N | + | | + +----------------------+ + +Package Header +============== + +The package header begins with the UUID of the PLDM file format, and +contains information about the version of the format that the file uses. It +also includes the total header size, a release date, the size of the +component bitmap, and an overall package version. + +The following diagram provides an overview of the package header:: + + header layout + +-------------------------+ + | PLDM UUID | + +-------------------------+ + | Format Revision | + +-------------------------+ + | Header Size | + +-------------------------+ + | Release Date | + +-------------------------+ + | Component Bitmap Length | + +-------------------------+ + | Package Version Info | + +-------------------------+ + +Device Records +============== + +The device firmware records area starts with a count indicating the total +number of records in the file, followed by each record. A single device +record describes what device matches this record. All valid PLDM firmware +files must contain at least one record, but optionally may contain more than +one record if they support multiple devices. + +Each record will identify the device it supports via TLVs that describe the +device, such as the PCI device and vendor information. It will also indicate +which set of components that are used by this device. It is possible that +only subset of provided components will be used by a given record. A record +may also optionally contain device-specific package data that will be used +by the device firmware during the update process. + +The following diagram provides an overview of the device record area:: + + area layout + +---------------+ + | | + | Record Count | + | | + +---------------+ + | | + | Record 1 | + | | + +---------------+ + | | + | Record 2 | + | | + +---------------+ + | | + | ... | + | | + +---------------+ + | | + | Record N | + | | + +---------------+ + + record layout + +-----------------------+ + | Record Length | + +-----------------------+ + | Descriptor Count | + +-----------------------+ + | Option Flags | + +-----------------------+ + | Version Settings | + +-----------------------+ + | Package Data Length | + +-----------------------+ + | Applicable Components | + +-----------------------+ + | Version String | + +-----------------------+ + | Descriptor TLVs | + +-----------------------+ + | Package Data | + +-----------------------+ + +Component Info +============== + +The component information area begins with a count of the number of +components. Following this count is a description for each component. The +component information points to the location in the file where the component +data is stored, and includes version data used to identify the version of +the component. + +The following diagram provides an overview of the component area:: + + area layout + +-----------------+ + | | + | Component Count | + | | + +-----------------+ + | | + | Component 1 | + | | + +-----------------+ + | | + | Component 2 | + | | + +-----------------+ + | | + | ... | + | | + +-----------------+ + | | + | Component N | + | | + +-----------------+ + + component layout + +------------------------+ + | Classification | + +------------------------+ + | Component Identifier | + +------------------------+ + | Comparison Stamp | + +------------------------+ + | Component Options | + +------------------------+ + | Activation Method | + +------------------------+ + | Location Offset | + +------------------------+ + | Component Size | + +------------------------+ + | Component Version Info | + +------------------------+ + | Package Data | + +------------------------+ + + +Package Header CRC +================== + +Following the component information is a short 4-byte CRC calculated over +the contents of all of the header information. + +Component Images +================ + +The component images follow the package header information in the PLDM +firmware file. Each of these is simply a binary chunk with its start and +size defined by the matching component structure in the component info area. diff --git a/Documentation/driver-api/pldmfw/index.rst b/Documentation/driver-api/pldmfw/index.rst new file mode 100644 index 000000000000..ad2c33ece30f --- /dev/null +++ b/Documentation/driver-api/pldmfw/index.rst @@ -0,0 +1,72 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +================================== +PLDM Firmware Flash Update Library +================================== + +``pldmfw`` implements functionality for updating the flash on a device using +the PLDM for Firmware Update standard +<https://www.dmtf.org/documents/pmci/pldm-firmware-update-specification-100>. + +.. toctree:: + :maxdepth: 1 + + file-format + driver-ops + +================================== +Overview of the ``pldmfw`` library +================================== + +The ``pldmfw`` library is intended to be used by device drivers for +implementing device flash update based on firmware files following the PLDM +firwmare file format. + +It is implemented using an ops table that allows device drivers to provide +the underlying device specific functionality. + +``pldmfw`` implements logic to parse the packed binary format of the PLDM +firmware file into data structures, and then uses the provided function +operations to determine if the firmware file is a match for the device. If +so, it sends the record and component data to the firmware using the device +specific implementations provided by device drivers. Once the device +firmware indicates that the update may be performed, the firmware data is +sent to the device for programming. + +Parsing the PLDM file +===================== + +The PLDM file format uses packed binary data, with most multi-byte fields +stored in the Little Endian format. Several pieces of data are variable +length, including version strings and the number of records and components. +Due to this, it is not straight forward to index the record, record +descriptors, or components. + +To avoid proliferating access to the packed binary data, the ``pldmfw`` +library parses and extracts this data into simpler structures for ease of +access. + +In order to safely process the firmware file, care is taken to avoid +unaligned access of multi-byte fields, and to properly convert from Little +Endian to CPU host format. Additionally the records, descriptors, and +components are stored in linked lists. + +Performing a flash update +========================= + +To perform a flash update, the ``pldmfw`` module performs the following +steps + +1. Parse the firmware file for record and component information +2. Scan through the records and determine if the device matches any record + in the file. The first matched record will be used. +3. If the matching record provides package data, send this package data to + the device. +4. For each component that the record indicates, send the component data to + the device. For each component, the firmware may respond with an + indication of whether the update is suitable or not. If any component is + not suitable, the update is canceled. +5. For each component, send the binary data to the device firmware for + updating. +6. After all components are programmed, perform any final device-specific + actions to finalize the update. diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst index ff406563ea88..b9d04ee6dac1 100644 --- a/Documentation/networking/bareudp.rst +++ b/Documentation/networking/bareudp.rst @@ -8,9 +8,8 @@ There are various L3 encapsulation standards using UDP being discussed to leverage the UDP based load balancing capability of different networks. MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them. -The Bareudp tunnel module provides a generic L3 encapsulation tunnelling -support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside -a UDP tunnel. +The Bareudp tunnel module provides a generic L3 encapsulation support for +tunnelling different L3 protocols like MPLS, IP, NSH etc. inside a UDP tunnel. Special Handling ---------------- diff --git a/Documentation/networking/device_drivers/ethernet/intel/e100.rst b/Documentation/networking/device_drivers/ethernet/intel/e100.rst index 3ac21e7119a7..3d4a9ba21946 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/e100.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/e100.rst @@ -41,7 +41,7 @@ Identifying Your Adapter For information on how to identify your adapter, and for the latest Intel network drivers, refer to the Intel Support website: -http://www.intel.com/support +https://www.intel.com/support Driver Configuration Parameters =============================== @@ -179,7 +179,7 @@ filtering by Support ======= For general information, go to the Intel support website at: -http://www.intel.com/support/ +https://www.intel.com/support/ or the Intel Wired Networking project hosted by Sourceforge at: http://sourceforge.net/projects/e1000 diff --git a/Documentation/networking/device_drivers/ethernet/intel/fm10k.rst b/Documentation/networking/device_drivers/ethernet/intel/fm10k.rst index 4d279e64e221..9258ef6f515c 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/fm10k.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/fm10k.rst @@ -22,7 +22,7 @@ Ethernet Multi-host Controller. For information on how to identify your adapter, and for the latest Intel network drivers, refer to the Intel Support website: -http://www.intel.com/support +https://www.intel.com/support Flow Control diff --git a/Documentation/networking/device_drivers/ethernet/intel/iavf.rst b/Documentation/networking/device_drivers/ethernet/intel/iavf.rst index 84ac7e75f363..52e037b11c97 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/iavf.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/iavf.rst @@ -43,7 +43,7 @@ device. For information on how to identify your adapter, and for the latest NVM/FW images and Intel network drivers, refer to the Intel Support website: -http://www.intel.com/support +https://www.intel.com/support Additional Features and Configurations diff --git a/Documentation/networking/device_drivers/ethernet/intel/igb.rst b/Documentation/networking/device_drivers/ethernet/intel/igb.rst index 87e560fe5eaa..d46289e182cf 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/igb.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/igb.rst @@ -20,7 +20,7 @@ Identifying Your Adapter ======================== For information on how to identify your adapter, and for the latest Intel network drivers, refer to the Intel Support website: -http://www.intel.com/support +https://www.intel.com/support Command Line Parameters diff --git a/Documentation/networking/device_drivers/ethernet/intel/igbvf.rst b/Documentation/networking/device_drivers/ethernet/intel/igbvf.rst index 557fc020ef31..40fa210c5e14 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/igbvf.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/igbvf.rst @@ -35,7 +35,7 @@ Identifying Your Adapter ======================== For information on how to identify your adapter, and for the latest Intel network drivers, refer to the Intel Support website: -http://www.intel.com/support +https://www.intel.com/support Additional Features and Configurations diff --git a/Documentation/networking/device_drivers/ethernet/intel/ixgb.rst b/Documentation/networking/device_drivers/ethernet/intel/ixgb.rst index ab624f1a44a8..c6a233e68ad6 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ixgb.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ixgb.rst @@ -203,7 +203,7 @@ With the 10 Gigabit server adapters, the default Linux configuration will very likely limit the total available throughput artificially. There is a set of configuration changes that, when applied together, will increase the ability of Linux to transmit and receive data. The following enhancements were -originally acquired from settings published at http://www.spec.org/web99/ for +originally acquired from settings published at https://www.spec.org/web99/ for various submitted results using Linux. NOTE: diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 1e3f3ffee248..7a798352b45d 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -405,6 +405,10 @@ be added to the following table: - ``control`` - Traps packets logged during processing of flow action trap (e.g., via tc's trap action) + * - ``early_drop`` + - ``drop`` + - Traps packets dropped due to the RED (Random Early Detection) algorithm + (i.e., early drops) Driver-specific Packet Traps ============================ @@ -486,6 +490,10 @@ narrow. The description of these groups must be added to the following table: - Contains packet traps for packets that should be locally delivered after routing, but do not match more specific packet traps (e.g., ``ipv4_bgp``) + * - ``external_delivery`` + - Contains packet traps for packets that should be routed through an + external interface (e.g., management interface) that does not belong to + the same device (e.g., switch ASIC) as the ingress interface * - ``ipv6`` - Contains packet traps for various IPv6 control packets (e.g., Router Advertisements) diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 7d75f1e32152..d53bcb31645a 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1263,6 +1263,9 @@ Kernel response contents: | | | | ``ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE`` | u32 | tunnel type | +-+-+-+---------------------------------------+--------+---------------------+ +For UDP tunnel table empty ``ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES`` indicates that +the table contains static entries, hard-coded by the NIC. + Request translation =================== diff --git a/MAINTAINERS b/MAINTAINERS index b61f9063faf2..b4cf52caf4f4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -782,7 +782,7 @@ F: include/dt-bindings/reset/altr,rst-mgr-a10sr.h F: include/linux/mfd/altera-a10sr.h ALTERA TRIPLE SPEED ETHERNET DRIVER -M: Thor Thayer <thor.thayer@linux.intel.com> +M: Joyce Ooi <joyce.ooi@intel.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/altera/ @@ -1425,7 +1425,7 @@ F: arch/arm*/include/asm/perf_event.h F: arch/arm*/kernel/hw_breakpoint.c F: arch/arm*/kernel/perf_* F: arch/arm/oprofile/common.c -F: drivers/perf/* +F: drivers/perf/ F: include/linux/perf/arm_pmu.h ARM PORT @@ -13604,6 +13604,13 @@ S: Maintained F: Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml F: drivers/iio/chemical/pms7003.c +PLDMFW LIBRARY +M: Jacob Keller <jacob.e.keller@intel.com> +S: Maintained +F: Documentation/driver-api/pldmfw/ +F: include/linux/pldmfw.h +F: lib/pldmfw/ + PLX DMA DRIVER M: Logan Gunthorpe <logang@deltatee.com> S: Maintained @@ -14184,7 +14191,8 @@ F: Documentation/devicetree/bindings/net/qcom,ethqos.txt F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c QUALCOMM GENERIC INTERFACE I2C DRIVER -M: Alok Chauhan <alokc@codeaurora.org> +M: Akash Asthana <akashast@codeaurora.org> +M: Mukesh Savaliya <msavaliy@codeaurora.org> L: linux-i2c@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Supported @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -568,7 +568,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) ifneq ($(CROSS_COMPILE),) CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) -CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) +CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) endif ifneq ($(GCC_TOOLCHAIN),) @@ -1769,7 +1769,7 @@ PHONY += descend $(build-dirs) descend: $(build-dirs) $(build-dirs): prepare $(Q)$(MAKE) $(build)=$@ \ - single-build=$(if $(filter-out $@/, $(filter $@/%, $(single-no-ko))),1) \ + single-build=$(if $(filter-out $@/, $(filter $@/%, $(KBUILD_SINGLE_TARGETS))),1) \ need-builtin=1 need-modorder=1 clean-dirs := $(addprefix _clean_, $(clean-dirs)) diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 348116501aa2..9b1a24cc5e91 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -342,7 +342,8 @@ comphy: phy@18300 { compatible = "marvell,armada-380-comphy"; - reg = <0x18300 0x100>; + reg-names = "comphy", "conf"; + reg = <0x18300 0x100>, <0x18460 4>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi index 756f3a9f1b4f..12997dae35d9 100644 --- a/arch/arm/boot/dts/imx6qdl-icore.dtsi +++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi @@ -397,7 +397,7 @@ pinctrl_usbotg: usbotggrp { fsl,pins = < - MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059 + MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059 >; }; @@ -409,6 +409,7 @@ MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070 MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070 MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070 + MX6QDL_PAD_GPIO_1__GPIO1_IO01 0x1b0b0 >; }; diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts index 825924448ab4..14fd1de52a68 100644 --- a/arch/arm/boot/dts/imx6sx-sabreauto.dts +++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts @@ -99,7 +99,7 @@ &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy0>; fsl,magic-packet; status = "okay"; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index 3e5fb72f21fc..c99aa273c296 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -213,7 +213,7 @@ &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy2>; status = "okay"; }; diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts index db640bab8c1d..8b3d64c913d8 100644 --- a/arch/arm/boot/dts/keystone-k2g-evm.dts +++ b/arch/arm/boot/dts/keystone-k2g-evm.dts @@ -402,7 +402,7 @@ &gbe0 { phy-handle = <ðphy0>; - phy-mode = "rgmii-id"; + phy-mode = "rgmii-rxid"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index bf531efc0610..0f95a6ef8543 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -198,7 +198,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi index e6b036734a64..c2b4fbf552a3 100644 --- a/arch/arm/boot/dts/sun5i.dtsi +++ b/arch/arm/boot/dts/sun5i.dtsi @@ -117,7 +117,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index ffe1d10a1a84..6d6a37940db2 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -181,7 +181,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index f44f448537f2..1a3eedbac4a2 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -5,6 +5,8 @@ #ifndef _ASM_ARM_PERCPU_H_ #define _ASM_ARM_PERCPU_H_ +#include <asm/thread_info.h> + /* * Same as asm-generic/percpu.h, except that we store the per cpu offset * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7 diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 02ca7adf5375..7fff88e61252 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -683,6 +683,12 @@ static void disable_single_step(struct perf_event *bp) arch_install_hw_breakpoint(bp); } +static int watchpoint_fault_on_uaccess(struct pt_regs *regs, + struct arch_hw_breakpoint *info) +{ + return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER; +} + static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { @@ -742,16 +748,27 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, } pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + + /* + * If we triggered a user watchpoint from a uaccess routine, + * then handle the stepping ourselves since userspace really + * can't help us with this. + */ + if (watchpoint_fault_on_uaccess(regs, info)) + goto step; + perf_bp_event(wp, regs); /* - * If no overflow handler is present, insert a temporary - * mismatch breakpoint so we can single-step over the - * watchpoint trigger. + * Defer stepping to the overflow handler if one is installed. + * Otherwise, insert a temporary mismatch breakpoint so that + * we can single-step over the watchpoint trigger. */ - if (is_default_overflow_handler(wp)) - enable_single_step(wp, instruction_pointer(regs)); + if (!is_default_overflow_handler(wp)) + goto unlock; +step: + enable_single_step(wp, instruction_pointer(regs)); unlock: rcu_read_unlock(); } diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 6bfdca4769a7..fddd08a6e063 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -184,6 +184,7 @@ static void __init patch_vdso(void *ehdr) if (!cntvct_ok) { vdso_nullpatch_one(&einfo, "__vdso_gettimeofday"); vdso_nullpatch_one(&einfo, "__vdso_clock_gettime"); + vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64"); } } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 628028bfbb92..bcd82614c25d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -966,7 +966,7 @@ void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md, pud_t *pud; p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual); - if (!WARN_ON(!p4d)) + if (WARN_ON(!p4d)) return; pud = pud_alloc(mm, p4d, md->virtual); if (WARN_ON(!pud)) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index 78b1361dfbb9..9ce78a7b117d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -161,6 +161,7 @@ resets = <&ccu RST_BUS_VE>; interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>; allwinner,sram = <&ve_sram 1>; + iommus = <&iommu 3>; }; gpu: gpu@1800000 { diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 12f0eb56a1cc..619db9b4c9d5 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -77,9 +77,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".previous\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index b6f7bc6da5fb..93a161b3bf3f 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -24,16 +24,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; + int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; - ihl -= 4; + n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; - } while (--ihl); + } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force u32)(sum >> 32)); diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index ea268d88b6f7..a0c8a0b65259 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -30,7 +30,6 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/thread_info.h> -#include <asm/pointer_auth.h> DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 118953d41763..6dd4171c9530 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -212,6 +212,8 @@ atomic64_set(atomic64_t *v, s64 i) _atomic_spin_unlock_irqrestore(v, flags); } +#define atomic64_set_release(v, i) atomic64_set((v), (i)) + static __inline__ s64 atomic64_read(const atomic64_t *v) { diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index ab5c215cf46c..068958575871 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void); extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_); extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_); +extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_); /* don't worry...optimizer will get rid of most of this */ static inline unsigned long @@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size) #endif case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int)old, (unsigned int)new_); + case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_); } __cmpxchg_called_with_bad_pointer(); return old; diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c index 70ffbcf889b8..2e4d1f05a926 100644 --- a/arch/parisc/lib/bitops.c +++ b/arch/parisc/lib/bitops.c @@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign _atomic_spin_unlock_irqrestore(ptr, flags); return (unsigned long)prev; } + +u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new) +{ + unsigned long flags; + u8 prev; + + _atomic_spin_lock_irqsave(ptr, flags); + if ((prev = *ptr) == old) + *ptr = new; + _atomic_spin_unlock_irqrestore(ptr, flags); + return prev; +} diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 0fc8bad878b2..446e54c3f71e 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -3072,10 +3072,18 @@ do_hash_page: ori r0,r0,DSISR_BAD_FAULT_64S@l and. r0,r5,r0 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ + + /* + * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then + * don't call hash_page, just fail the fault. This is required to + * prevent re-entrancy problems in the hash code, namely perf + * interrupts hitting while something holds H_PAGE_BUSY, and taking a + * hash fault. See the comment in hash_preload(). + */ ld r11, PACA_THREAD_INFO(r13) - lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ - andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ - bne 77f /* then don't call hash_page now */ + lwz r0,TI_PREEMPT(r11) + andis. r0,r0,NMI_MASK@h + bne 77f /* * r3 contains the trap number diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 468169e33c86..9b9f92ad0e7a 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1559,6 +1559,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, pgd_t *pgdir; int rc, ssize, update_flags = 0; unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0); + unsigned long flags; BUG_ON(get_region_id(ea) != USER_REGION_ID); @@ -1592,6 +1593,28 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, return; #endif /* CONFIG_PPC_64K_PAGES */ + /* + * __hash_page_* must run with interrupts off, as it sets the + * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any + * time and may take a hash fault reading the user stack, see + * read_user_stack_slow() in the powerpc/perf code. + * + * If that takes a hash fault on the same page as we lock here, it + * will bail out when seeing H_PAGE_BUSY set, and retry the access + * leading to an infinite loop. + * + * Disabling interrupts here does not prevent perf interrupts, but it + * will prevent them taking hash faults (see the NMI test in + * do_hash_page), then read_user_stack's copy_from_user_nofault will + * fail and perf will fall back to read_user_stack_slow(), which + * walks the Linux page tables. + * + * Interrupts must also be off for the duration of the + * mm_is_thread_local test and update, to prevent preempt running the + * mm on another CPU (XXX: this may be racy vs kthread_use_mm). + */ + local_irq_save(flags); + /* Is that local to this CPU ? */ if (mm_is_thread_local(mm)) update_flags |= HPTE_LOCAL_UPDATE; @@ -1614,6 +1637,8 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, mm_ctx_user_psize(&mm->context), mm_ctx_user_psize(&mm->context), pte_val(*ptep)); + + local_irq_restore(flags); } /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index cd6a742ac6ef..01d70280d287 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2179,6 +2179,12 @@ static void __perf_event_interrupt(struct pt_regs *regs) perf_read_regs(regs); + /* + * If perf interrupts hit in a local_irq_disable (soft-masked) region, + * we consider them as NMIs. This is required to prevent hash faults on + * user addresses when reading callchains. See the NMI test in + * do_hash_page. + */ nmi = perf_intr_is_nmi(regs); if (nmi) nmi_enter(); diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 22d968bfe9bb..d770da3f8b6f 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -12,6 +12,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address); extern void pmd_free(struct mm_struct *mm, pmd_t *pmd); +#define __pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, (pmdp)) #endif static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, @@ -33,13 +34,4 @@ do { \ tlb_remove_page((tlb), (pte)); \ } while (0) -#if CONFIG_PGTABLE_LEVELS > 2 -#define __pmd_free_tlb(tlb, pmdp, addr) \ -do { \ - struct page *page = virt_to_page(pmdp); \ - pgtable_pmd_page_dtor(page); \ - tlb_remove_page((tlb), page); \ -} while (0); -#endif - #endif /* __ASM_SH_PGALLOC_H */ diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index 956a7a03b0c8..9bac5bbb67f3 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -199,7 +199,7 @@ syscall_trace_entry: mov.l @(OFF_R7,r15), r7 ! arg3 mov.l @(OFF_R3,r15), r3 ! syscall_nr ! - mov.l 2f, r10 ! Number of syscalls + mov.l 6f, r10 ! Number of syscalls cmp/hs r10, r3 bf syscall_call mov #-ENOSYS, r0 @@ -353,7 +353,7 @@ ENTRY(system_call) tst r9, r8 bf syscall_trace_entry ! - mov.l 2f, r8 ! Number of syscalls + mov.l 6f, r8 ! Number of syscalls cmp/hs r8, r3 bt syscall_badsys ! @@ -392,7 +392,7 @@ syscall_exit: #if !defined(CONFIG_CPU_SH2) 1: .long TRA #endif -2: .long NR_syscalls +6: .long NR_syscalls 3: .long sys_call_table 7: .long do_syscall_trace_enter 8: .long do_syscall_trace_leave diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 42c672f1584e..cbe6aa77d50d 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -947,7 +947,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_user_end(alloc, index); } mmap_read_unlock(mm); - mmput(mm); + mmput_async(mm); trace_binder_unmap_kernel_start(alloc, index); diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index d9fd70280482..7f814da3c2d0 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -433,9 +433,15 @@ static int atmtcp_remove_persistent(int itf) return -EMEDIUMTYPE; } dev_data = PRIV(dev); - if (!dev_data->persist) return 0; + if (!dev_data->persist) { + atm_dev_put(dev); + return 0; + } dev_data->persist = 0; - if (PRIV(dev)->vcc) return 0; + if (PRIV(dev)->vcc) { + atm_dev_put(dev); + return 0; + } kfree(dev_data); atm_dev_put(dev); atm_dev_deregister(dev); diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index b3d8e00e7671..39be444534d0 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -1034,6 +1034,7 @@ static enum enq_res do_tx(struct sk_buff *skb) u32 dma_rd,dma_wr; u32 size; /* in words */ int aal5,dma_size,i,j; + unsigned char skb_data3; DPRINTK(">do_tx\n"); NULLCHECK(skb); @@ -1108,6 +1109,7 @@ DPRINTK("iovcnt = %d\n",skb_shinfo(skb)->nr_frags); vcc->dev->number); return enq_jam; } + skb_data3 = skb->data[3]; paddr = dma_map_single(&eni_dev->pci_dev->dev,skb->data,skb->len, DMA_TO_DEVICE); ENI_PRV_PADDR(skb) = paddr; @@ -1150,7 +1152,7 @@ DPRINTK("doing direct send\n"); /* @@@ well, this doesn't work anyway */ (size/(ATM_CELL_PAYLOAD/4)),tx->send+tx->tx_pos*4); /*printk("dsc = 0x%08lx\n",(unsigned long) readl(tx->send+tx->tx_pos*4));*/ writel((vcc->vci << MID_SEG_VCI_SHIFT) | - (aal5 ? 0 : (skb->data[3] & 0xf)) | + (aal5 ? 0 : (skb_data3 & 0xf)) | (ATM_SKB(skb)->atm_options & ATM_ATMOPT_CLP ? MID_SEG_CLP : 0), tx->send+((tx->tx_pos+1) & (tx->words-1))*4); DPRINTK("size: %d, len:%d\n",size,skb->len); diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index df51680e8931..65a3886f68c9 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -835,6 +835,7 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc, unsigned long flags; int error; int aal; + u32 word4; if (skb->len == 0) { printk("%s: invalid skb->len (%d)\n", card->name, skb->len); @@ -846,6 +847,8 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc, tbd = &IDT77252_PRV_TBD(skb); vcc = ATM_SKB(skb)->vcc; + word4 = (skb->data[0] << 24) | (skb->data[1] << 16) | + (skb->data[2] << 8) | (skb->data[3] << 0); IDT77252_PRV_PADDR(skb) = dma_map_single(&card->pcidev->dev, skb->data, skb->len, DMA_TO_DEVICE); @@ -859,8 +862,7 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc, tbd->word_1 = SAR_TBD_OAM | ATM_CELL_PAYLOAD | SAR_TBD_EPDU; tbd->word_2 = IDT77252_PRV_PADDR(skb) + 4; tbd->word_3 = 0x00000000; - tbd->word_4 = (skb->data[0] << 24) | (skb->data[1] << 16) | - (skb->data[2] << 8) | (skb->data[3] << 0); + tbd->word_4 = word4; if (test_bit(VCF_RSV, &vc->flags)) vc = card->vcs[0]; @@ -890,8 +892,7 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc, tbd->word_2 = IDT77252_PRV_PADDR(skb) + 4; tbd->word_3 = 0x00000000; - tbd->word_4 = (skb->data[0] << 24) | (skb->data[1] << 16) | - (skb->data[2] << 8) | (skb->data[3] << 0); + tbd->word_4 = word4; break; case ATM_AAL5: diff --git a/drivers/base/property.c b/drivers/base/property.c index 1e6d75e65938..d58aa98fe964 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -721,7 +721,7 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev, return next; /* When no more children in primary, continue with secondary */ - if (!IS_ERR_OR_NULL(fwnode->secondary)) + if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) next = fwnode_get_next_child_node(fwnode->secondary, child); return next; diff --git a/drivers/bluetooth/bcm203x.c b/drivers/bluetooth/bcm203x.c index 3b176257b993..e667933c3d70 100644 --- a/drivers/bluetooth/bcm203x.c +++ b/drivers/bluetooth/bcm203x.c @@ -106,7 +106,7 @@ static void bcm203x_complete(struct urb *urb) } data->state = BCM203X_LOAD_FIRMWARE; - /* fall through */ + fallthrough; case BCM203X_LOAD_FIRMWARE: if (data->fw_sent == data->fw_size) { usb_fill_int_urb(urb, udev, usb_rcvintpipe(udev, BCM203X_IN_EP), diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c index cc6e56223656..36eabf61717f 100644 --- a/drivers/bluetooth/bluecard_cs.c +++ b/drivers/bluetooth/bluecard_cs.c @@ -295,7 +295,6 @@ static void bluecard_write_wakeup(struct bluecard_info *info) baud_reg = REG_CONTROL_BAUD_RATE_115200; break; case PKT_BAUD_RATE_57600: - /* Fall through... */ default: baud_reg = REG_CONTROL_BAUD_RATE_57600; break; @@ -585,7 +584,6 @@ static int bluecard_hci_set_baud_rate(struct hci_dev *hdev, int baud) hci_skb_pkt_type(skb) = PKT_BAUD_RATE_115200; break; case 57600: - /* Fall through... */ default: cmd[4] = 0x03; hci_skb_pkt_type(skb) = PKT_BAUD_RATE_57600; diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 6a0e2c5a8beb..5fa5be3c5598 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -754,6 +754,65 @@ void btintel_reset_to_bootloader(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(btintel_reset_to_bootloader); +int btintel_read_debug_features(struct hci_dev *hdev, + struct intel_debug_features *features) +{ + struct sk_buff *skb; + u8 page_no = 1; + + /* Intel controller supports two pages, each page is of 128-bit + * feature bit mask. And each bit defines specific feature support + */ + skb = __hci_cmd_sync(hdev, 0xfca6, sizeof(page_no), &page_no, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Reading supported features failed (%ld)", + PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != (sizeof(features->page1) + 3)) { + bt_dev_err(hdev, "Supported features event size mismatch"); + kfree_skb(skb); + return -EILSEQ; + } + + memcpy(features->page1, skb->data + 3, sizeof(features->page1)); + + /* Read the supported features page2 if required in future. + */ + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL_GPL(btintel_read_debug_features); + +int btintel_set_debug_features(struct hci_dev *hdev, + const struct intel_debug_features *features) +{ + u8 mask[11] = { 0x0a, 0x92, 0x02, 0x07, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00 }; + struct sk_buff *skb; + + if (!features) + return -EINVAL; + + if (!(features->page1[0] & 0x3f)) { + bt_dev_info(hdev, "Telemetry exception format not supported"); + return 0; + } + + skb = __hci_cmd_sync(hdev, 0xfc8b, 11, mask, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Setting Intel telemetry ddc write event mask failed (%ld)", + PTR_ERR(skb)); + return PTR_ERR(skb); + } + + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL_GPL(btintel_set_debug_features); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth support for Intel devices ver " VERSION); MODULE_VERSION(VERSION); diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index a69ea8a87b9b..08e20606fb58 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -62,6 +62,10 @@ struct intel_reset { __le32 boot_param; } __packed; +struct intel_debug_features { + __u8 page1[16]; +} __packed; + #if IS_ENABLED(CONFIG_BT_INTEL) int btintel_check_bdaddr(struct hci_dev *hdev); @@ -88,6 +92,10 @@ int btintel_read_boot_params(struct hci_dev *hdev, int btintel_download_firmware(struct hci_dev *dev, const struct firmware *fw, u32 *boot_param); void btintel_reset_to_bootloader(struct hci_dev *hdev); +int btintel_read_debug_features(struct hci_dev *hdev, + struct intel_debug_features *features); +int btintel_set_debug_features(struct hci_dev *hdev, + const struct intel_debug_features *features); #else static inline int btintel_check_bdaddr(struct hci_dev *hdev) @@ -186,4 +194,17 @@ static inline int btintel_download_firmware(struct hci_dev *dev, static inline void btintel_reset_to_bootloader(struct hci_dev *hdev) { } + +static inline int btintel_read_debug_features(struct hci_dev *hdev, + struct intel_debug_features *features) +{ + return -EOPNOTSUPP; +} + +static inline int btintel_set_debug_features(struct hci_dev *hdev, + const struct intel_debug_features *features) +{ + return -EOPNOTSUPP; +} + #endif diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 708ad21683eb..8b9d78ce6bb2 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -587,6 +587,14 @@ static int btmrvl_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) return 0; } +static bool btmrvl_prevent_wake(struct hci_dev *hdev) +{ + struct btmrvl_private *priv = hci_get_drvdata(hdev); + struct btmrvl_sdio_card *card = priv->btmrvl_dev.card; + + return !device_may_wakeup(&card->func->dev); +} + /* * This function handles the event generated by firmware, rx data * received from firmware, and tx data sent from kernel. @@ -669,6 +677,7 @@ static int btmrvl_service_main_thread(void *data) int btmrvl_register_hdev(struct btmrvl_private *priv) { struct hci_dev *hdev = NULL; + struct btmrvl_sdio_card *card = priv->btmrvl_dev.card; int ret; hdev = hci_alloc_dev(); @@ -687,6 +696,8 @@ int btmrvl_register_hdev(struct btmrvl_private *priv) hdev->send = btmrvl_send_frame; hdev->setup = btmrvl_setup; hdev->set_bdaddr = btmrvl_set_bdaddr; + hdev->prevent_wake = btmrvl_prevent_wake; + SET_HCIDEV_DEV(hdev, &card->func->dev); hdev->dev_type = priv->btmrvl_dev.dev_type; diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index a296f8526433..d15fd5be0216 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -111,6 +111,9 @@ static int btmrvl_sdio_probe_of(struct device *dev, "Failed to request irq_bt %d (%d)\n", cfg->irq_bt, ret); } + + /* Configure wakeup (enabled by default) */ + device_init_wakeup(dev, true); disable_irq(cfg->irq_bt); } } @@ -328,7 +331,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8897 = { static const struct btmrvl_sdio_device btmrvl_sdio_sd8977 = { .helper = NULL, - .firmware = "mrvl/sd8977_uapsta.bin", + .firmware = "mrvl/sdsd8977_combo_v2.bin", .reg = &btmrvl_reg_8977, .support_pscan_win_report = true, .sd_blksz_fw_dl = 256, @@ -346,7 +349,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8987 = { static const struct btmrvl_sdio_device btmrvl_sdio_sd8997 = { .helper = NULL, - .firmware = "mrvl/sd8997_uapsta.bin", + .firmware = "mrvl/sdsd8997_combo_v4.bin", .reg = &btmrvl_reg_8997, .support_pscan_win_report = true, .sd_blksz_fw_dl = 256, @@ -1654,6 +1657,7 @@ static void btmrvl_sdio_remove(struct sdio_func *func) MODULE_SHUTDOWN_REQ); btmrvl_sdio_disable_host_int(card); } + BT_DBG("unregister dev"); card->priv->surprise_removed = true; btmrvl_sdio_unregister_dev(card); @@ -1690,7 +1694,8 @@ static int btmrvl_sdio_suspend(struct device *dev) } /* Enable platform specific wakeup interrupt */ - if (card->plt_wake_cfg && card->plt_wake_cfg->irq_bt >= 0) { + if (card->plt_wake_cfg && card->plt_wake_cfg->irq_bt >= 0 && + device_may_wakeup(dev)) { card->plt_wake_cfg->wake_by_bt = false; enable_irq(card->plt_wake_cfg->irq_bt); enable_irq_wake(card->plt_wake_cfg->irq_bt); @@ -1707,7 +1712,8 @@ static int btmrvl_sdio_suspend(struct device *dev) BT_ERR("HS not activated, suspend failed!"); /* Disable platform specific wakeup interrupt */ if (card->plt_wake_cfg && - card->plt_wake_cfg->irq_bt >= 0) { + card->plt_wake_cfg->irq_bt >= 0 && + device_may_wakeup(dev)) { disable_irq_wake(card->plt_wake_cfg->irq_bt); disable_irq(card->plt_wake_cfg->irq_bt); } @@ -1767,7 +1773,8 @@ static int btmrvl_sdio_resume(struct device *dev) hci_resume_dev(hcidev); /* Disable platform specific wakeup interrupt */ - if (card->plt_wake_cfg && card->plt_wake_cfg->irq_bt >= 0) { + if (card->plt_wake_cfg && card->plt_wake_cfg->irq_bt >= 0 && + device_may_wakeup(dev)) { disable_irq_wake(card->plt_wake_cfg->irq_bt); disable_irq(card->plt_wake_cfg->irq_bt); if (card->plt_wake_cfg->wake_by_bt) @@ -1831,6 +1838,6 @@ MODULE_FIRMWARE("mrvl/sd8787_uapsta.bin"); MODULE_FIRMWARE("mrvl/sd8797_uapsta.bin"); MODULE_FIRMWARE("mrvl/sd8887_uapsta.bin"); MODULE_FIRMWARE("mrvl/sd8897_uapsta.bin"); -MODULE_FIRMWARE("mrvl/sd8977_uapsta.bin"); +MODULE_FIRMWARE("mrvl/sdsd8977_combo_v2.bin"); MODULE_FIRMWARE("mrvl/sd8987_uapsta.bin"); -MODULE_FIRMWARE("mrvl/sd8997_uapsta.bin"); +MODULE_FIRMWARE("mrvl/sdsd8997_combo_v4.bin"); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index bff095be2f97..c7ab7a23bd67 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -685,7 +685,7 @@ static int mtk_setup_firmware(struct hci_dev *hdev, const char *fwname) const u8 *fw_ptr; size_t fw_size; int err, dlen; - u8 flag; + u8 flag, param; err = request_firmware(&fw, fwname, &hdev->dev); if (err < 0) { @@ -693,6 +693,20 @@ static int mtk_setup_firmware(struct hci_dev *hdev, const char *fwname) return err; } + /* Power on data RAM the firmware relies on. */ + param = 1; + wmt_params.op = MTK_WMT_FUNC_CTRL; + wmt_params.flag = 3; + wmt_params.dlen = sizeof(param); + wmt_params.data = ¶m; + wmt_params.status = NULL; + + err = mtk_hci_wmt_sync(hdev, &wmt_params); + if (err < 0) { + bt_dev_err(hdev, "Failed to power on data RAM (%d)", err); + return err; + } + fw_ptr = fw->data; fw_size = fw->size; diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index c5984966f315..ce9dcffdc5bf 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -400,6 +400,27 @@ out: return ret; } +static int qca_disable_soc_logging(struct hci_dev *hdev) +{ + struct sk_buff *skb; + u8 cmd[2]; + int err; + + cmd[0] = QCA_DISABLE_LOGGING_SUB_OP; + cmd[1] = 0x00; + skb = __hci_cmd_sync_ev(hdev, QCA_DISABLE_LOGGING, sizeof(cmd), cmd, + HCI_EV_CMD_COMPLETE, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + bt_dev_err(hdev, "QCA Failed to disable soc logging(%d)", err); + return err; + } + + kfree_skb(skb); + + return 0; +} + int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) { struct sk_buff *skb; @@ -486,6 +507,12 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; } + if (soc_type >= QCA_WCN3991) { + err = qca_disable_soc_logging(hdev); + if (err < 0) + return err; + } + /* Perform HCI reset */ err = qca_send_reset(hdev); if (err < 0) { diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index 6e1e62dd4b95..d81b74c408a5 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -14,6 +14,7 @@ #define EDL_NVM_ACCESS_SET_REQ_CMD (0x01) #define MAX_SIZE_PER_TLV_SEGMENT (243) #define QCA_PRE_SHUTDOWN_CMD (0xFC08) +#define QCA_DISABLE_LOGGING (0xFC17) #define EDL_CMD_REQ_RES_EVT (0x00) #define EDL_PATCH_VER_RES_EVT (0x19) @@ -22,6 +23,7 @@ #define EDL_CMD_EXE_STATUS_EVT (0x00) #define EDL_SET_BAUDRATE_RSP_EVT (0x92) #define EDL_NVM_ACCESS_CODE_EVT (0x0B) +#define QCA_DISABLE_LOGGING_SUB_OP (0x14) #define EDL_TAG_ID_HCI (17) #define EDL_TAG_ID_DEEP_SLEEP (27) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5f022e9cf667..8d2608ddfd08 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -359,6 +359,10 @@ static const struct usb_device_id blacklist_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01), .driver_info = BTUSB_IGNORE }, + /* Realtek 8822CE Bluetooth devices */ + { USB_DEVICE(0x0bda, 0xb00c), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), .driver_info = BTUSB_REALTEK }, @@ -453,6 +457,7 @@ static const struct dmi_system_id btusb_needs_reset_resume_table[] = { #define BTUSB_HW_RESET_ACTIVE 12 #define BTUSB_TX_WAIT_VND_EVT 13 #define BTUSB_WAKEUP_DISABLE 14 +#define BTUSB_USE_ALT1_FOR_WBS 15 struct btusb_data { struct hci_dev *hdev; @@ -511,7 +516,6 @@ struct btusb_data { unsigned cmd_timeout_cnt; }; - static void btusb_intel_cmd_timeout(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); @@ -573,6 +577,23 @@ static void btusb_rtl_cmd_timeout(struct hci_dev *hdev) gpiod_set_value_cansleep(reset_gpio, 0); } +static void btusb_qca_cmd_timeout(struct hci_dev *hdev) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + int err; + + if (++data->cmd_timeout_cnt < 5) + return; + + bt_dev_err(hdev, "Multiple cmd timeouts seen. Resetting usb device."); + /* This is not an unbalanced PM reference since the device will reset */ + err = usb_autopm_get_interface(data->intf); + if (!err) + usb_queue_reset_device(data->intf); + else + bt_dev_err(hdev, "Failed usb_autopm_get_interface with %d", err); +} + static inline void btusb_free_frags(struct btusb_data *data) { unsigned long flags; @@ -1666,14 +1687,15 @@ static void btusb_work(struct work_struct *work) new_alts = data->sco_num; } } else if (data->air_mode == HCI_NOTIFY_ENABLE_SCO_TRANSP) { - - data->usb_alt6_packet_flow = true; - /* Check if Alt 6 is supported for Transparent audio */ - if (btusb_find_altsetting(data, 6)) + if (btusb_find_altsetting(data, 6)) { + data->usb_alt6_packet_flow = true; new_alts = 6; - else + } else if (test_bit(BTUSB_USE_ALT1_FOR_WBS, &data->flags)) { + new_alts = 1; + } else { bt_dev_err(hdev, "Device does not support ALT setting 6"); + } } if (btusb_switch_alt_setting(hdev, new_alts) < 0) @@ -1720,6 +1742,7 @@ static int btusb_setup_csr(struct hci_dev *hdev) { struct hci_rp_read_local_version *rp; struct sk_buff *skb; + bool is_fake = false; BT_DBG("%s", hdev->name); @@ -1739,18 +1762,69 @@ static int btusb_setup_csr(struct hci_dev *hdev) rp = (struct hci_rp_read_local_version *)skb->data; - /* Detect controllers which aren't real CSR ones. */ + /* Detect a wide host of Chinese controllers that aren't CSR. + * + * Known fake bcdDevices: 0x0100, 0x0134, 0x1915, 0x2520, 0x7558, 0x8891 + * + * The main thing they have in common is that these are really popular low-cost + * options that support newer Bluetooth versions but rely on heavy VID/PID + * squatting of this poor old Bluetooth 1.1 device. Even sold as such. + * + * We detect actual CSR devices by checking that the HCI manufacturer code + * is Cambridge Silicon Radio (10) and ensuring that LMP sub-version and + * HCI rev values always match. As they both store the firmware number. + */ if (le16_to_cpu(rp->manufacturer) != 10 || - le16_to_cpu(rp->lmp_subver) == 0x0c5c) { + le16_to_cpu(rp->hci_rev) != le16_to_cpu(rp->lmp_subver)) + is_fake = true; + + /* Known legit CSR firmware build numbers and their supported BT versions: + * - 1.1 (0x1) -> 0x0073, 0x020d, 0x033c, 0x034e + * - 1.2 (0x2) -> 0x04d9, 0x0529 + * - 2.0 (0x3) -> 0x07a6, 0x07ad, 0x0c5c + * - 2.1 (0x4) -> 0x149c, 0x1735, 0x1899 (0x1899 is a BlueCore4-External) + * - 4.0 (0x6) -> 0x1d86, 0x2031, 0x22bb + * + * e.g. Real CSR dongles with LMP subversion 0x73 are old enough that + * support BT 1.1 only; so it's a dead giveaway when some + * third-party BT 4.0 dongle reuses it. + */ + else if (le16_to_cpu(rp->lmp_subver) <= 0x034e && + le16_to_cpu(rp->hci_ver) > BLUETOOTH_VER_1_1) + is_fake = true; + + else if (le16_to_cpu(rp->lmp_subver) <= 0x0529 && + le16_to_cpu(rp->hci_ver) > BLUETOOTH_VER_1_2) + is_fake = true; + + else if (le16_to_cpu(rp->lmp_subver) <= 0x0c5c && + le16_to_cpu(rp->hci_ver) > BLUETOOTH_VER_2_0) + is_fake = true; + + else if (le16_to_cpu(rp->lmp_subver) <= 0x1899 && + le16_to_cpu(rp->hci_ver) > BLUETOOTH_VER_2_1) + is_fake = true; + + else if (le16_to_cpu(rp->lmp_subver) <= 0x22bb && + le16_to_cpu(rp->hci_ver) > BLUETOOTH_VER_4_0) + is_fake = true; + + if (is_fake) { + bt_dev_warn(hdev, "CSR: Unbranded CSR clone detected; adding workarounds..."); + + /* Generally these clones have big discrepancies between + * advertised features and what's actually supported. + * Probably will need to be expanded in the future; + * without these the controller will lock up. + */ + set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); + set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks); + /* Clear the reset quirk since this is not an actual * early Bluetooth 1.1 device from CSR. */ clear_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); - - /* These fake CSR controllers have all a broken - * stored link key handling and so just disable it. - */ - set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); + clear_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); } kfree_skb(skb); @@ -2262,45 +2336,25 @@ static bool btusb_setup_intel_new_get_fw_name(struct intel_version *ver, return true; } -static int btusb_setup_intel_new(struct hci_dev *hdev) +static int btusb_intel_download_firmware(struct hci_dev *hdev, + struct intel_version *ver, + struct intel_boot_params *params) { - struct btusb_data *data = hci_get_drvdata(hdev); - struct intel_version ver; - struct intel_boot_params params; const struct firmware *fw; u32 boot_param; char fwname[64]; - ktime_t calltime, delta, rettime; - unsigned long long duration; int err; + struct btusb_data *data = hci_get_drvdata(hdev); - BT_DBG("%s", hdev->name); - - /* Set the default boot parameter to 0x0 and it is updated to - * SKU specific boot parameter after reading Intel_Write_Boot_Params - * command while downloading the firmware. - */ - boot_param = 0x00000000; - - calltime = ktime_get(); - - /* Read the Intel version information to determine if the device - * is in bootloader mode or if it already has operational firmware - * loaded. - */ - err = btintel_read_version(hdev, &ver); - if (err) { - bt_dev_err(hdev, "Intel Read version failed (%d)", err); - btintel_reset_to_bootloader(hdev); - return err; - } + if (!ver || !params) + return -EINVAL; /* The hardware platform number has a fixed value of 0x37 and * for now only accept this single value. */ - if (ver.hw_platform != 0x37) { + if (ver->hw_platform != 0x37) { bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)", - ver.hw_platform); + ver->hw_platform); return -EINVAL; } @@ -2310,7 +2364,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * This check has been put in place to ensure correct forward * compatibility options when newer hardware variants come along. */ - switch (ver.hw_variant) { + switch (ver->hw_variant) { case 0x0b: /* SfP */ case 0x0c: /* WsP */ case 0x11: /* JfP */ @@ -2320,11 +2374,11 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) break; default: bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)", - ver.hw_variant); + ver->hw_variant); return -EINVAL; } - btintel_version_info(hdev, &ver); + btintel_version_info(hdev, ver); /* The firmware variant determines if the device is in bootloader * mode or is running operational firmware. The value 0x06 identifies @@ -2339,25 +2393,25 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * It is not possible to use the Secure Boot Parameters in this * case since that command is only available in bootloader mode. */ - if (ver.fw_variant == 0x23) { + if (ver->fw_variant == 0x23) { clear_bit(BTUSB_BOOTLOADER, &data->flags); btintel_check_bdaddr(hdev); - goto finish; + return 0; } /* If the device is not in bootloader mode, then the only possible * choice is to return an error and abort the device initialization. */ - if (ver.fw_variant != 0x06) { + if (ver->fw_variant != 0x06) { bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)", - ver.fw_variant); + ver->fw_variant); return -ENODEV; } /* Read the secure boot parameters to identify the operating * details of the bootloader. */ - err = btintel_read_boot_params(hdev, ¶ms); + err = btintel_read_boot_params(hdev, params); if (err) return err; @@ -2365,16 +2419,16 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * with a command complete event. If the boot parameters indicate * that this bootloader does not send them, then abort the setup. */ - if (params.limited_cce != 0x00) { + if (params->limited_cce != 0x00) { bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)", - params.limited_cce); + params->limited_cce); return -EINVAL; } /* If the OTP has no valid Bluetooth device address, then there will * also be no valid address for the operational firmware. */ - if (!bacmp(¶ms.otp_bdaddr, BDADDR_ANY)) { + if (!bacmp(¶ms->otp_bdaddr, BDADDR_ANY)) { bt_dev_info(hdev, "No device address configured"); set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); } @@ -2400,7 +2454,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) * ibt-<hw_variant>-<hw_revision>-<fw_revision>.sfi. * */ - err = btusb_setup_intel_new_get_fw_name(&ver, ¶ms, fwname, + err = btusb_setup_intel_new_get_fw_name(ver, params, fwname, sizeof(fwname), "sfi"); if (!err) { bt_dev_err(hdev, "Unsupported Intel firmware naming"); @@ -2415,16 +2469,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) bt_dev_info(hdev, "Found device firmware: %s", fwname); - /* Save the DDC file name for later use to apply once the firmware - * downloading is done. - */ - err = btusb_setup_intel_new_get_fw_name(&ver, ¶ms, fwname, - sizeof(fwname), "ddc"); - if (!err) { - bt_dev_err(hdev, "Unsupported Intel firmware naming"); - return -EINVAL; - } - if (fw->size < 644) { bt_dev_err(hdev, "Invalid size of firmware file (%zu)", fw->size); @@ -2479,18 +2523,58 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) goto done; } +done: + release_firmware(fw); + return err; +} + +static int btusb_setup_intel_new(struct hci_dev *hdev) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + struct intel_version ver; + struct intel_boot_params params; + u32 boot_param; + char ddcname[64]; + ktime_t calltime, delta, rettime; + unsigned long long duration; + int err; + struct intel_debug_features features; + + BT_DBG("%s", hdev->name); + + /* Set the default boot parameter to 0x0 and it is updated to + * SKU specific boot parameter after reading Intel_Write_Boot_Params + * command while downloading the firmware. + */ + boot_param = 0x00000000; + + calltime = ktime_get(); + + /* Read the Intel version information to determine if the device + * is in bootloader mode or if it already has operational firmware + * loaded. + */ + err = btintel_read_version(hdev, &ver); + if (err) { + bt_dev_err(hdev, "Intel Read version failed (%d)", err); + btintel_reset_to_bootloader(hdev); + return err; + } + + err = btusb_intel_download_firmware(hdev, &ver, ¶ms); + if (err) + return err; + + /* controller is already having an operational firmware */ + if (ver.fw_variant == 0x23) + goto finish; + rettime = ktime_get(); delta = ktime_sub(rettime, calltime); duration = (unsigned long long) ktime_to_ns(delta) >> 10; bt_dev_info(hdev, "Firmware loaded in %llu usecs", duration); -done: - release_firmware(fw); - - if (err < 0) - return err; - calltime = ktime_get(); set_bit(BTUSB_BOOTING, &data->flags); @@ -2534,13 +2618,28 @@ done: clear_bit(BTUSB_BOOTLOADER, &data->flags); - /* Once the device is running in operational mode, it needs to apply - * the device configuration (DDC) parameters. - * - * The device can work without DDC parameters, so even if it fails - * to load the file, no need to fail the setup. + err = btusb_setup_intel_new_get_fw_name(&ver, ¶ms, ddcname, + sizeof(ddcname), "ddc"); + + if (!err) { + bt_dev_err(hdev, "Unsupported Intel firmware naming"); + } else { + /* Once the device is running in operational mode, it needs to + * apply the device configuration (DDC) parameters. + * + * The device can work without DDC parameters, so even if it + * fails to load the file, no need to fail the setup. + */ + btintel_load_ddc_config(hdev, ddcname); + } + + /* Read the Intel supported features and if new exception formats + * supported, need to load the additional DDC config to enable. */ - btintel_load_ddc_config(hdev, fwname); + btintel_read_debug_features(hdev, &features); + + /* Set DDC mask for available debug features */ + btintel_set_debug_features(hdev, &features); /* Read the Intel version information after loading the FW */ err = btintel_read_version(hdev, &ver); @@ -2925,7 +3024,7 @@ static int btusb_mtk_setup_firmware(struct hci_dev *hdev, const char *fwname) const u8 *fw_ptr; size_t fw_size; int err, dlen; - u8 flag; + u8 flag, param; err = request_firmware(&fw, fwname, &hdev->dev); if (err < 0) { @@ -2933,6 +3032,20 @@ static int btusb_mtk_setup_firmware(struct hci_dev *hdev, const char *fwname) return err; } + /* Power on data RAM the firmware relies on. */ + param = 1; + wmt_params.op = BTMTK_WMT_FUNC_CTRL; + wmt_params.flag = 3; + wmt_params.dlen = sizeof(param); + wmt_params.data = ¶m; + wmt_params.status = NULL; + + err = btusb_mtk_hci_wmt_sync(hdev, &wmt_params); + if (err < 0) { + bt_dev_err(hdev, "Failed to power on data RAM (%d)", err); + return err; + } + fw_ptr = fw->data; fw_size = fw->size; @@ -3704,6 +3817,9 @@ static bool btusb_prevent_wake(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); + if (test_bit(BTUSB_WAKEUP_DISABLE, &data->flags)) + return true; + return !device_may_wakeup(&data->udev->dev); } @@ -3941,10 +4057,20 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_QCA_ROME) { data->setup_on_usb = btusb_setup_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; + hdev->cmd_timeout = btusb_qca_cmd_timeout; set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); btusb_check_needs_reset_resume(intf); } + if (id->driver_info & BTUSB_AMP) { + /* AMP controllers do not support SCO packets */ + data->isoc = NULL; + } else { + /* Interface orders are hardcoded in the specification */ + data->isoc = usb_ifnum_to_if(data->udev, ifnum_base + 1); + data->isoc_ifnum = ifnum_base + 1; + } + if (IS_ENABLED(CONFIG_BT_HCIBTUSB_RTL) && (id->driver_info & BTUSB_REALTEK)) { hdev->setup = btrtl_setup_realtek; @@ -3956,19 +4082,10 @@ static int btusb_probe(struct usb_interface *intf, * (DEVICE_REMOTE_WAKEUP) */ set_bit(BTUSB_WAKEUP_DISABLE, &data->flags); - - err = usb_autopm_get_interface(intf); - if (err < 0) - goto out_free_dev; - } - - if (id->driver_info & BTUSB_AMP) { - /* AMP controllers do not support SCO packets */ - data->isoc = NULL; - } else { - /* Interface orders are hardcoded in the specification */ - data->isoc = usb_ifnum_to_if(data->udev, ifnum_base + 1); - data->isoc_ifnum = ifnum_base + 1; + if (btusb_find_altsetting(data, 1)) + set_bit(BTUSB_USE_ALT1_FOR_WBS, &data->flags); + else + bt_dev_err(hdev, "Device does not support ALT setting 1"); } if (!reset) @@ -4001,11 +4118,13 @@ static int btusb_probe(struct usb_interface *intf, if (bcdDevice < 0x117) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + /* This must be set first in case we disable it for fakes */ + set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + /* Fake CSR devices with broken commands */ - if (bcdDevice <= 0x100 || bcdDevice == 0x134) + if (le16_to_cpu(udev->descriptor.idVendor) == 0x0a12 && + le16_to_cpu(udev->descriptor.idProduct) == 0x0001) hdev->setup = btusb_setup_csr; - - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); } if (id->driver_info & BTUSB_SNIFFER) { diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index e60b2e0773db..e41854e0d79a 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -793,7 +793,7 @@ static int h5_serdev_probe(struct serdev_device *serdev) if (!h5) return -ENOMEM; - set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.flags); + set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.hdev_flags); h5->hu = &h5->serdev_hu; h5->serdev_hu.serdev = serdev; diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index d9a4c6c691e0..8bfe024d1fcd 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -219,7 +219,7 @@ static void ll_device_want_to_wakeup(struct hci_uart *hu) * perfectly safe to always send one. */ BT_DBG("dual wake-up-indication"); - /* fall through */ + fallthrough; case HCILL_ASLEEP: /* acknowledge device wake up */ if (send_hcill_cmd(HCILL_WAKE_UP_ACK, hu) < 0) { diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 81c3c38baba1..20e1dedbc58c 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -46,7 +46,7 @@ #define HCI_MAX_IBS_SIZE 10 #define IBS_WAKE_RETRANS_TIMEOUT_MS 100 -#define IBS_BTSOC_TX_IDLE_TIMEOUT_MS 40 +#define IBS_BTSOC_TX_IDLE_TIMEOUT_MS 200 #define IBS_HOST_TX_IDLE_TIMEOUT_MS 2000 #define CMD_TRANS_TIMEOUT_MS 100 #define MEMDUMP_TIMEOUT_MS 8000 @@ -72,7 +72,8 @@ enum qca_flags { QCA_DROP_VENDOR_EVENT, QCA_SUSPENDING, QCA_MEMDUMP_COLLECTION, - QCA_HW_ERROR_EVENT + QCA_HW_ERROR_EVENT, + QCA_SSR_TRIGGERED }; enum qca_capabilities { @@ -289,25 +290,21 @@ static void serial_clock_vote(unsigned long vote, struct hci_uart *hu) case HCI_IBS_TX_VOTE_CLOCK_ON: qca->tx_vote = true; qca->tx_votes_on++; - new_vote = true; break; case HCI_IBS_RX_VOTE_CLOCK_ON: qca->rx_vote = true; qca->rx_votes_on++; - new_vote = true; break; case HCI_IBS_TX_VOTE_CLOCK_OFF: qca->tx_vote = false; qca->tx_votes_off++; - new_vote = qca->rx_vote | qca->tx_vote; break; case HCI_IBS_RX_VOTE_CLOCK_OFF: qca->rx_vote = false; qca->rx_votes_off++; - new_vote = qca->rx_vote | qca->tx_vote; break; default: @@ -315,6 +312,8 @@ static void serial_clock_vote(unsigned long vote, struct hci_uart *hu) return; } + new_vote = qca->rx_vote | qca->tx_vote; + if (new_vote != old_vote) { if (new_vote) __serial_clock_on(hu->tty); @@ -474,8 +473,6 @@ static void hci_ibs_tx_idle_timeout(struct timer_list *t) case HCI_IBS_TX_ASLEEP: case HCI_IBS_TX_WAKING: - /* Fall through */ - default: BT_ERR("Spurious timeout tx state %d", qca->tx_ibs_state); break; @@ -518,8 +515,6 @@ static void hci_ibs_wake_retrans_timeout(struct timer_list *t) case HCI_IBS_TX_ASLEEP: case HCI_IBS_TX_AWAKE: - /* Fall through */ - default: BT_ERR("Spurious timeout tx state %d", qca->tx_ibs_state); break; @@ -837,8 +832,6 @@ static void device_woke_up(struct hci_uart *hu) break; case HCI_IBS_TX_ASLEEP: - /* Fall through */ - default: BT_ERR("Received HCI_IBS_WAKE_ACK in tx state %d", qca->tx_ibs_state); @@ -862,6 +855,13 @@ static int qca_enqueue(struct hci_uart *hu, struct sk_buff *skb) BT_DBG("hu %p qca enq skb %p tx_ibs_state %d", hu, skb, qca->tx_ibs_state); + if (test_bit(QCA_SSR_TRIGGERED, &qca->flags)) { + /* As SSR is in progress, ignore the packets */ + bt_dev_dbg(hu->hdev, "SSR is in progress"); + kfree_skb(skb); + return 0; + } + /* Prepend skb with frame type */ memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); @@ -983,8 +983,11 @@ static void qca_controller_memdump(struct work_struct *work) while ((skb = skb_dequeue(&qca->rx_memdump_q))) { mutex_lock(&qca->hci_memdump_lock); - /* Skip processing the received packets if timeout detected. */ - if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT) { + /* Skip processing the received packets if timeout detected + * or memdump collection completed. + */ + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT || + qca->memdump_state == QCA_MEMDUMP_COLLECTED) { mutex_unlock(&qca->hci_memdump_lock); return; } @@ -1128,6 +1131,7 @@ static int qca_controller_memdump_event(struct hci_dev *hdev, struct hci_uart *hu = hci_get_drvdata(hdev); struct qca_data *qca = hu->priv; + set_bit(QCA_SSR_TRIGGERED, &qca->flags); skb_queue_tail(&qca->rx_memdump_q, skb); queue_work(qca->workqueue, &qca->ctrl_memdump_evt); @@ -1485,9 +1489,8 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code) { struct hci_uart *hu = hci_get_drvdata(hdev); struct qca_data *qca = hu->priv; - struct qca_memdump_data *qca_memdump = qca->qca_memdump; - char *memdump_buf = NULL; + set_bit(QCA_SSR_TRIGGERED, &qca->flags); set_bit(QCA_HW_ERROR_EVENT, &qca->flags); bt_dev_info(hdev, "mem_dump_status: %d", qca->memdump_state); @@ -1509,19 +1512,23 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code) qca_wait_for_dump_collection(hdev); } + mutex_lock(&qca->hci_memdump_lock); if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) { bt_dev_err(hu->hdev, "clearing allocated memory due to memdump timeout"); - mutex_lock(&qca->hci_memdump_lock); - if (qca_memdump) - memdump_buf = qca_memdump->memdump_buf_head; - vfree(memdump_buf); - kfree(qca_memdump); - qca->qca_memdump = NULL; + if (qca->qca_memdump) { + vfree(qca->qca_memdump->memdump_buf_head); + kfree(qca->qca_memdump); + qca->qca_memdump = NULL; + } qca->memdump_state = QCA_MEMDUMP_TIMEOUT; cancel_delayed_work(&qca->ctrl_memdump_timeout); - skb_queue_purge(&qca->rx_memdump_q); - mutex_unlock(&qca->hci_memdump_lock); + } + mutex_unlock(&qca->hci_memdump_lock); + + if (qca->memdump_state == QCA_MEMDUMP_TIMEOUT || + qca->memdump_state == QCA_MEMDUMP_COLLECTED) { cancel_work_sync(&qca->ctrl_memdump_evt); + skb_queue_purge(&qca->rx_memdump_q); } clear_bit(QCA_HW_ERROR_EVENT, &qca->flags); @@ -1532,10 +1539,30 @@ static void qca_cmd_timeout(struct hci_dev *hdev) struct hci_uart *hu = hci_get_drvdata(hdev); struct qca_data *qca = hu->priv; - if (qca->memdump_state == QCA_MEMDUMP_IDLE) + set_bit(QCA_SSR_TRIGGERED, &qca->flags); + if (qca->memdump_state == QCA_MEMDUMP_IDLE) { + set_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); qca_send_crashbuffer(hu); - else - bt_dev_info(hdev, "Dump collection is in process"); + qca_wait_for_dump_collection(hdev); + } else if (qca->memdump_state == QCA_MEMDUMP_COLLECTING) { + /* Let us wait here until memory dump collected or + * memory dump timer expired. + */ + bt_dev_info(hdev, "waiting for dump to complete"); + qca_wait_for_dump_collection(hdev); + } + + mutex_lock(&qca->hci_memdump_lock); + if (qca->memdump_state != QCA_MEMDUMP_COLLECTED) { + qca->memdump_state = QCA_MEMDUMP_TIMEOUT; + if (!test_bit(QCA_HW_ERROR_EVENT, &qca->flags)) { + /* Inject hw error event to reset the device + * and driver. + */ + hci_reset_dev(hu->hdev); + } + } + mutex_unlock(&qca->hci_memdump_lock); } static int qca_wcn3990_init(struct hci_uart *hu) @@ -1641,11 +1668,15 @@ static int qca_setup(struct hci_uart *hu) bt_dev_info(hdev, "setting up %s", qca_is_wcn399x(soc_type) ? "wcn399x" : "ROME/QCA6390"); + qca->memdump_state = QCA_MEMDUMP_IDLE; + retry: ret = qca_power_on(hdev); if (ret) return ret; + clear_bit(QCA_SSR_TRIGGERED, &qca->flags); + if (qca_is_wcn399x(soc_type)) { set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); @@ -1788,9 +1819,6 @@ static void qca_power_shutdown(struct hci_uart *hu) qca_flush(hu); spin_unlock_irqrestore(&qca->hci_ibs_lock, flags); - hu->hdev->hw_error = NULL; - hu->hdev->cmd_timeout = NULL; - /* Non-serdev device usually is powered by external power * and don't need additional action in driver for power down */ @@ -1812,6 +1840,9 @@ static int qca_power_off(struct hci_dev *hdev) struct qca_data *qca = hu->priv; enum qca_btsoc_type soc_type = qca_soc_type(hu); + hu->hdev->hw_error = NULL; + hu->hdev->cmd_timeout = NULL; + /* Stop sending shutdown command if soc crashes. */ if (soc_type != QCA_ROME && qca->memdump_state == QCA_MEMDUMP_IDLE) { @@ -1819,7 +1850,6 @@ static int qca_power_off(struct hci_dev *hdev) usleep_range(8000, 10000); } - qca->memdump_state = QCA_MEMDUMP_IDLE; qca_power_shutdown(hu); return 0; } @@ -1962,17 +1992,17 @@ static int qca_serdev_probe(struct serdev_device *serdev) } qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); - if (!qcadev->susclk) { + if (IS_ERR(qcadev->susclk)) { dev_warn(&serdev->dev, "failed to acquire clk\n"); - } else { - err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ); - if (err) - return err; - - err = clk_prepare_enable(qcadev->susclk); - if (err) - return err; + return PTR_ERR(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) { @@ -2050,6 +2080,7 @@ static int __maybe_unused qca_suspend(struct device *dev) struct hci_uart *hu = &qcadev->serdev_hu; struct qca_data *qca = hu->priv; unsigned long flags; + bool tx_pending = false; int ret = 0; u8 cmd; @@ -2068,7 +2099,7 @@ static int __maybe_unused qca_suspend(struct device *dev) switch (qca->tx_ibs_state) { case HCI_IBS_TX_WAKING: del_timer(&qca->wake_retrans_timer); - /* Fall through */ + fallthrough; case HCI_IBS_TX_AWAKE: del_timer(&qca->tx_idle_timer); @@ -2083,8 +2114,7 @@ static int __maybe_unused qca_suspend(struct device *dev) qca->tx_ibs_state = HCI_IBS_TX_ASLEEP; qca->ibs_sent_slps++; - - qca_wq_serial_tx_clock_vote_off(&qca->ws_tx_vote_off); + tx_pending = true; break; case HCI_IBS_TX_ASLEEP: @@ -2101,22 +2131,24 @@ static int __maybe_unused qca_suspend(struct device *dev) if (ret < 0) goto error; - serdev_device_wait_until_sent(hu->serdev, - msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS)); + if (tx_pending) { + serdev_device_wait_until_sent(hu->serdev, + msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS)); + serial_clock_vote(HCI_IBS_TX_VOTE_CLOCK_OFF, hu); + } /* Wait for HCI_IBS_SLEEP_IND sent by device to indicate its Tx is going * to sleep, so that the packet does not wake the system later. */ - ret = wait_event_interruptible_timeout(qca->suspend_wait_q, qca->rx_ibs_state == HCI_IBS_RX_ASLEEP, msecs_to_jiffies(IBS_BTSOC_TX_IDLE_TIMEOUT_MS)); - - if (ret > 0) - return 0; - - if (ret == 0) + if (ret == 0) { ret = -ETIMEDOUT; + goto error; + } + + return 0; error: clear_bit(QCA_SUSPENDING, &qca->flags); diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 599855e4c57c..7b233312e723 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -355,7 +355,8 @@ void hci_uart_unregister_device(struct hci_uart *hu) struct hci_dev *hdev = hu->hdev; clear_bit(HCI_UART_PROTO_READY, &hu->flags); - hci_unregister_dev(hdev); + if (test_bit(HCI_UART_REGISTERED, &hu->flags)) + hci_unregister_dev(hdev); hci_free_dev(hdev); cancel_work_sync(&hu->write_work); diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 934c92dcb9ab..687d4af6945d 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -814,7 +814,8 @@ static struct inode *devmem_inode; #ifdef CONFIG_IO_STRICT_DEVMEM void revoke_devmem(struct resource *res) { - struct inode *inode = READ_ONCE(devmem_inode); + /* pairs with smp_store_release() in devmem_init_inode() */ + struct inode *inode = smp_load_acquire(&devmem_inode); /* * Check that the initialization has completed. Losing the race @@ -1028,8 +1029,11 @@ static int devmem_init_inode(void) return rc; } - /* publish /dev/mem initialized */ - WRITE_ONCE(devmem_inode, inode); + /* + * Publish /dev/mem initialized. + * Pairs with smp_load_acquire() in revoke_devmem(). + */ + smp_store_release(&devmem_inode, inode); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 2a41b21623ae..d20ba1b104ca 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1277,6 +1277,7 @@ void add_interrupt_randomness(int irq, int irq_flags) fast_mix(fast_pool); add_interrupt_bench(cycles); + this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]); if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c index f924c335a195..05520dccd906 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -1348,7 +1348,7 @@ static void chtls_pass_accept_request(struct sock *sk, oreq->rsk_rcv_wnd = 0; oreq->rsk_window_clamp = 0; - oreq->cookie_ts = 0; + oreq->syncookie = 0; oreq->mss = 0; oreq->ts_recent = 0; diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c index c3058dcdb33c..66d247efd561 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -525,9 +525,9 @@ static int do_chtls_setsockopt(struct sock *sk, int optname, /* Obtain version and type from previous copy */ crypto_info[0] = tmp_crypto_info; /* Now copy the following data */ - sockptr_advance(optval, sizeof(*crypto_info)); - rc = copy_from_sockptr((char *)crypto_info + sizeof(*crypto_info), - optval, + rc = copy_from_sockptr_offset((char *)crypto_info + + sizeof(*crypto_info), + optval, sizeof(*crypto_info), sizeof(struct tls12_crypto_info_aes_gcm_128) - sizeof(*crypto_info)); @@ -542,9 +542,9 @@ static int do_chtls_setsockopt(struct sock *sk, int optname, } case TLS_CIPHER_AES_GCM_256: { crypto_info[0] = tmp_crypto_info; - sockptr_advance(optval, sizeof(*crypto_info)); - rc = copy_from_sockptr((char *)crypto_info + sizeof(*crypto_info), - optval, + rc = copy_from_sockptr_offset((char *)crypto_info + + sizeof(*crypto_info), + optval, sizeof(*crypto_info), sizeof(struct tls12_crypto_info_aes_gcm_256) - sizeof(*crypto_info)); diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 039e0f91dba8..6945c3c96637 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -605,8 +605,10 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) /* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */ err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype, fw_cfg_sel_ko, "%d", entry->select); - if (err) - goto err_register; + if (err) { + kobject_put(&entry->kobj); + return err; + } /* add raw binary content access */ err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw); @@ -622,7 +624,6 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) err_add_raw: kobject_del(&entry->kobj); -err_register: kfree(entry); return err; } diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c index b0c31789a909..3fa2c5992173 100644 --- a/drivers/fpga/dfl-afu-main.c +++ b/drivers/fpga/dfl-afu-main.c @@ -83,7 +83,8 @@ int __afu_port_disable(struct platform_device *pdev) * on this port and minimum soft reset pulse width has elapsed. * Driver polls port_soft_reset_ack to determine if reset done by HW. */ - if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST, + if (readq_poll_timeout(base + PORT_HDR_CTRL, v, + v & PORT_CTRL_SFTRST_ACK, RST_POLL_INVL, RST_POLL_TIMEOUT)) { dev_err(&pdev->dev, "timeout, fail to reset device\n"); return -ETIMEDOUT; diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c index 538755062ab7..a78c409bf2c4 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -227,7 +227,6 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs) { struct cci_drvdata *drvdata = pci_get_drvdata(pcidev); struct dfl_fpga_cdev *cdev = drvdata->cdev; - int ret = 0; if (!num_vfs) { /* @@ -239,6 +238,8 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs) dfl_fpga_cdev_config_ports_pf(cdev); } else { + int ret; + /* * before enable SRIOV, put released ports into VF access mode * first of all. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d7e17e34fee1..21292098bc02 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -692,9 +692,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return n ? -EFAULT : 0; } case AMDGPU_INFO_DEV_INFO: { - struct drm_amdgpu_info_device dev_info = {}; + struct drm_amdgpu_info_device dev_info; uint64_t vm_size; + memset(&dev_info, 0, sizeof(dev_info)); dev_info.device_id = dev->pdev->device; dev_info.chip_rev = adev->rev_id; dev_info.external_rev = adev->external_rev_id; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index ebb8a28ff002..02e6f8c4dde0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -778,7 +778,8 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, tmp_str++; while (isspace(*++tmp_str)); - while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) { + while (tmp_str[0]) { + sub_str = strsep(&tmp_str, delimiter); ret = kstrtol(sub_str, 0, ¶meter[parameter_size]); if (ret) return -EINVAL; @@ -1038,7 +1039,8 @@ static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask) memcpy(buf_cpy, buf, bytes); buf_cpy[bytes] = '\0'; tmp = buf_cpy; - while ((sub_str = strsep(&tmp, delimiter)) != NULL) { + while (tmp[0]) { + sub_str = strsep(&tmp, delimiter); if (strlen(sub_str)) { ret = kstrtol(sub_str, 0, &level); if (ret) @@ -1635,7 +1637,8 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev, i++; memcpy(buf_cpy, buf, count-i); tmp_str = buf_cpy; - while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) { + while (tmp_str[0]) { + sub_str = strsep(&tmp_str, delimiter); ret = kstrtol(sub_str, 0, ¶meter[parameter_size]); if (ret) return -EINVAL; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 86ffa0c2880f..710edc70e37e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8717,20 +8717,38 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * the same resource. If we have a new DC context as part of * the DM atomic state from validation we need to free it and * retain the existing one instead. + * + * Furthermore, since the DM atomic state only contains the DC + * context and can safely be annulled, we can free the state + * and clear the associated private object now to free + * some memory and avoid a possible use-after-free later. */ - struct dm_atomic_state *new_dm_state, *old_dm_state; - new_dm_state = dm_atomic_get_new_state(state); - old_dm_state = dm_atomic_get_old_state(state); + for (i = 0; i < state->num_private_objs; i++) { + struct drm_private_obj *obj = state->private_objs[i].ptr; - if (new_dm_state && old_dm_state) { - if (new_dm_state->context) - dc_release_state(new_dm_state->context); + if (obj->funcs == adev->dm.atomic_obj.funcs) { + int j = state->num_private_objs-1; - new_dm_state->context = old_dm_state->context; + dm_atomic_destroy_state(obj, + state->private_objs[i].state); + + /* If i is not at the end of the array then the + * last element needs to be moved to where i was + * before the array can safely be truncated. + */ + if (i != j) + state->private_objs[i] = + state->private_objs[j]; - if (old_dm_state->context) - dc_retain_state(old_dm_state->context); + state->private_objs[j].ptr = NULL; + state->private_objs[j].state = NULL; + state->private_objs[j].old_state = NULL; + state->private_objs[j].new_state = NULL; + + state->num_private_objs = j; + break; + } } } diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 05d8373888e8..079f46f5cdb6 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -146,6 +146,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs->dev->mode_config.preferred_depth = 24; bochs->dev->mode_config.prefer_shadow = 0; bochs->dev->mode_config.prefer_shadow_fbdev = 1; + bochs->dev->mode_config.fbdev_use_iomem = true; bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; bochs->dev->mode_config.funcs = &bochs_mode_funcs; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 87b58c1acff4..648eb23d0784 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1224,6 +1224,7 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) adv7511->bridge.funcs = &adv7511_bridge_funcs; adv7511->bridge.of_node = dev->of_node; + adv7511->bridge.type = DRM_MODE_CONNECTOR_HDMIA; drm_bridge_add(&adv7511->bridge); diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index b14d725bf609..c7bc194bbce3 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -917,11 +917,6 @@ static int nwl_dsi_bridge_attach(struct drm_bridge *bridge, struct drm_panel *panel; int ret; - if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) { - DRM_ERROR("Fix bridge driver to make connector optional!"); - return -EINVAL; - } - ret = drm_of_find_panel_or_bridge(dsi->dev->of_node, 1, 0, &panel, &panel_bridge); if (ret) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 5609e164805f..89cfd68ef400 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -399,7 +399,11 @@ static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper, unsigned int y; for (y = clip->y1; y < clip->y2; y++) { - memcpy(dst, src, len); + if (!fb_helper->dev->mode_config.fbdev_use_iomem) + memcpy(dst, src, len); + else + memcpy_toio((void __iomem *)dst, src, len); + src += fb->pitches[0]; dst += fb->pitches[0]; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 7bf628e13023..ee2058ad482c 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -871,9 +871,6 @@ err: * @file_priv: drm file-private structure * * Open an object using the global name, returning a handle and the size. - * - * This handle (of course) holds a reference to the object, so the object - * will not go away until the handle is deleted. */ int drm_gem_open_ioctl(struct drm_device *dev, void *data, @@ -898,14 +895,15 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data, /* drm_gem_handle_create_tail unlocks dev->object_name_lock. */ ret = drm_gem_handle_create_tail(file_priv, obj, &handle); - drm_gem_object_put_unlocked(obj); if (ret) - return ret; + goto err; args->handle = handle; args->size = obj->size; - return 0; +err: + drm_gem_object_put_unlocked(obj); + return ret; } /** diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c index bb27c82757f1..bf7888ad9ad4 100644 --- a/drivers/gpu/drm/drm_mipi_dbi.c +++ b/drivers/gpu/drm/drm_mipi_dbi.c @@ -923,7 +923,7 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *dbi, int dc, } } - tr.len = chunk; + tr.len = chunk * 2; len -= chunk; ret = spi_sync(spi, &m); diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index b50b44e76279..8fc3f67e3e76 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -322,10 +322,8 @@ static int drm_of_lvds_get_remote_pixels_type( * configurations by passing the endpoints explicitly to * drm_of_lvds_get_dual_link_pixel_order(). */ - if (!current_pt || pixels_type != current_pt) { - of_node_put(remote_port); + if (!current_pt || pixels_type != current_pt) return -EINVAL; - } } return pixels_type; diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 08802e5177f6..4d2290f88edb 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -1060,9 +1060,14 @@ static void mcde_display_update(struct drm_simple_display_pipe *pipe, */ if (fb) { mcde_set_extsrc(mcde, drm_fb_cma_get_gem_addr(fb, pstate, 0)); - if (!mcde->video_mode) - /* Send a single frame using software sync */ - mcde_display_send_one_frame(mcde); + if (!mcde->video_mode) { + /* + * Send a single frame using software sync if the flow + * is not active yet. + */ + if (mcde->flow_active == 0) + mcde_display_send_one_frame(mcde); + } dev_info_once(mcde->dev, "sent first display update\n"); } else { /* diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 519f99868e35..800b7757252e 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2073,7 +2073,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) */ if (core->assign_windows) { core->func->wndw.owner(core); - core->func->update(core, interlock, false); + nv50_disp_atomic_commit_core(state, interlock); core->assign_windows = false; interlock[NV50_DISP_INTERLOCK_CORE] = 0; } @@ -2506,7 +2506,7 @@ nv50_display_create(struct drm_device *dev) if (disp->disp->object.oclass >= TU102_DISP) nouveau_display(dev)->format_modifiers = wndwc57e_modifiers; else - if (disp->disp->object.oclass >= GF110_DISP) + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI) nouveau_display(dev)->format_modifiers = disp90xx_modifiers; else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 496c4621cc78..07373bbc2acf 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -191,6 +191,7 @@ nouveau_decode_mod(struct nouveau_drm *drm, uint32_t *tile_mode, uint8_t *kind) { + struct nouveau_display *disp = nouveau_display(drm->dev); BUG_ON(!tile_mode || !kind); if (modifier == DRM_FORMAT_MOD_LINEAR) { @@ -202,6 +203,12 @@ nouveau_decode_mod(struct nouveau_drm *drm, * Extract the block height and kind from the corresponding * modifier fields. See drm_fourcc.h for details. */ + + if ((modifier & (0xffull << 12)) == 0ull) { + /* Legacy modifier. Translate to this dev's 'kind.' */ + modifier |= disp->format_modifiers[0] & (0xffull << 12); + } + *tile_mode = (uint32_t)(modifier & 0xF); *kind = (uint8_t)((modifier >> 12) & 0xFF); @@ -227,6 +234,16 @@ nouveau_framebuffer_get_layout(struct drm_framebuffer *fb, } } +static const u64 legacy_modifiers[] = { + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5), + DRM_FORMAT_MOD_INVALID +}; + static int nouveau_validate_decode_mod(struct nouveau_drm *drm, uint64_t modifier, @@ -247,8 +264,14 @@ nouveau_validate_decode_mod(struct nouveau_drm *drm, (disp->format_modifiers[mod] != modifier); mod++); - if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) - return -EINVAL; + if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) { + for (mod = 0; + (legacy_modifiers[mod] != DRM_FORMAT_MOD_INVALID) && + (legacy_modifiers[mod] != modifier); + mod++); + if (legacy_modifiers[mod] == DRM_FORMAT_MOD_INVALID) + return -EINVAL; + } nouveau_decode_mod(drm, modifier, tile_mode, kind); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 3d11b84d4cf9..d5c23d1c20d8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -315,7 +315,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, struct drm_framebuffer *fb; struct nouveau_channel *chan; struct nouveau_bo *nvbo; - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {}; int ret; mode_cmd.width = sizes->surface_width; @@ -590,6 +590,7 @@ fini: drm_fb_helper_fini(&fbcon->helper); free: kfree(fbcon); + drm->fbcon = NULL; return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c index dcf08249374a..dffcac249211 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c @@ -117,15 +117,6 @@ nvkm_outp_acquire_hda(struct nvkm_outp *outp, enum nvkm_ior_type type, { struct nvkm_ior *ior; - /* First preference is to reuse the OR that is currently armed - * on HW, if any, in order to prevent unnecessary switching. - */ - list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->identity && !!ior->func->hda.hpd == hda && - !ior->asy.outp && ior->arm.outp == outp) - return nvkm_outp_acquire_ior(outp, user, ior); - } - /* Failing that, a completely unused OR is the next best thing. */ list_for_each_entry(ior, &outp->disp->ior, head) { if (!ior->identity && !!ior->func->hda.hpd == hda && @@ -173,6 +164,27 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user, bool hda) return nvkm_outp_acquire_ior(outp, user, ior); } + /* First preference is to reuse the OR that is currently armed + * on HW, if any, in order to prevent unnecessary switching. + */ + list_for_each_entry(ior, &outp->disp->ior, head) { + if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) { + /*XXX: For various complicated reasons, we can't outright switch + * the boot-time OR on the first modeset without some fairly + * invasive changes. + * + * The systems that were fixed by modifying the OR selection + * code to account for HDA support shouldn't regress here as + * the HDA-enabled ORs match the relevant output's pad macro + * index, and the firmware seems to select an OR this way. + * + * This warning is to make it obvious if that proves wrong. + */ + WARN_ON(hda && !ior->func->hda.hpd); + return nvkm_outp_acquire_ior(outp, user, ior); + } + } + /* If we don't need HDA, first try to acquire an OR that doesn't * support it to leave free the ones that do. */ diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 46fe1805c588..2649469070aa 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -615,9 +615,9 @@ static const struct panel_desc boe_tv101wum_nl6_desc = { static const struct drm_display_mode auo_kd101n80_45na_default_mode = { .clock = 157000, .hdisplay = 1200, - .hsync_start = 1200 + 80, - .hsync_end = 1200 + 80 + 24, - .htotal = 1200 + 80 + 24 + 36, + .hsync_start = 1200 + 60, + .hsync_end = 1200 + 60 + 24, + .htotal = 1200 + 60 + 24 + 56, .vdisplay = 1920, .vsync_start = 1920 + 16, .vsync_end = 1920 + 16 + 4, diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 5178f87d6574..4aeb960ccf15 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1250,7 +1250,21 @@ static const struct panel_desc boe_nv133fhm_n61 = { .height = 165, }, .delay = { - .hpd_absent_delay = 200, + /* + * When power is first given to the panel there's a short + * spike on the HPD line. It was explained that this spike + * was until the TCON data download was complete. On + * one system this was measured at 8 ms. We'll put 15 ms + * in the prepare delay just to be safe and take it away + * from the hpd_absent_delay (which would otherwise be 200 ms) + * to handle this. That means: + * - If HPD isn't hooked up you still have 200 ms delay. + * - If HPD is hooked up we won't try to look at it for the + * first 15 ms. + */ + .prepare = 15, + .hpd_absent_delay = 185, + .unprepare = 500, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c index 5427f047faf0..1589179d5eb9 100644 --- a/drivers/i2c/i2c-core-slave.c +++ b/drivers/i2c/i2c-core-slave.c @@ -18,10 +18,8 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb) { int ret; - if (!client || !slave_cb) { - WARN(1, "insufficient data\n"); + if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n")) return -EINVAL; - } if (!(client->flags & I2C_CLIENT_SLAVE)) dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n", @@ -60,6 +58,9 @@ int i2c_slave_unregister(struct i2c_client *client) { int ret; + if (IS_ERR_OR_NULL(client)) + return -EINVAL; + if (!client->adapter->algo->unreg_slave) { dev_err(&client->dev, "%s: not supported by adapter\n", __func__); return -EOPNOTSUPP; diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index 655795bfa0ee..513825e424bf 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -72,6 +72,15 @@ static void rdma_dim_init(struct ib_cq *cq) INIT_WORK(&dim->work, ib_cq_rdma_dim_work); } +static void rdma_dim_destroy(struct ib_cq *cq) +{ + if (!cq->dim) + return; + + cancel_work_sync(&cq->dim->work); + kfree(cq->dim); +} + static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { int rc; @@ -266,6 +275,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, return cq; out_destroy_cq: + rdma_dim_destroy(cq); rdma_restrack_del(&cq->res); cq->device->ops.destroy_cq(cq, udata); out_free_wc: @@ -331,12 +341,10 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata) WARN_ON_ONCE(1); } + rdma_dim_destroy(cq); trace_cq_free(cq); rdma_restrack_del(&cq->res); cq->device->ops.destroy_cq(cq, udata); - if (cq->dim) - cancel_work_sync(&cq->dim->work); - kfree(cq->dim); kfree(cq->wc); kfree(cq); } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 5b87eee8ccc8..d03dacaef788 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1084,6 +1084,8 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, size_t in_size; int ret; + if (in_len < offsetofend(typeof(cmd), reserved)) + return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; @@ -1141,6 +1143,8 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, size_t in_size; int ret; + if (in_len < offsetofend(typeof(cmd), reserved)) + return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c index 3421a0b15983..5f5408cdf008 100644 --- a/drivers/infiniband/hw/bnxt_re/hw_counters.c +++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c @@ -132,7 +132,7 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev, stats->value[BNXT_RE_RECOVERABLE_ERRORS] = le64_to_cpu(bnxt_re_stats->tx_bcast_pkts); stats->value[BNXT_RE_RX_DROPS] = - le64_to_cpu(bnxt_re_stats->rx_drop_pkts); + le64_to_cpu(bnxt_re_stats->rx_error_pkts); stats->value[BNXT_RE_RX_DISCARDS] = le64_to_cpu(bnxt_re_stats->rx_discard_pkts); stats->value[BNXT_RE_RX_PKTS] = diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 1ab676b66894..77dca1e05bba 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1797,9 +1797,7 @@ static bool init_prefetch_work(struct ib_pd *pd, work->frags[i].mr = get_prefetchable_mr(pd, advice, sg_list[i].lkey); if (!work->frags[i].mr) { - work->num_sge = i - 1; - if (i) - destroy_prefetch_work(work); + work->num_sge = i; return false; } @@ -1865,6 +1863,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, srcu_key = srcu_read_lock(&dev->odp_srcu); if (!init_prefetch_work(pd, advice, pf_flags, work, sg_list, num_sge)) { srcu_read_unlock(&dev->odp_srcu, srcu_key); + destroy_prefetch_work(work); return -EINVAL; } queue_work(system_unbound_wq, &work->work); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index e050eade97a1..1225b8d77510 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1766,15 +1766,14 @@ err: } static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev, + struct mlx5_ib_qp *qp, struct ib_qp_init_attr *init_attr, - struct mlx5_ib_create_qp *ucmd, void *qpc) { int scqe_sz; bool allow_scat_cqe = false; - if (ucmd) - allow_scat_cqe = ucmd->flags & MLX5_QP_FLAG_ALLOW_SCATTER_CQE; + allow_scat_cqe = qp->flags_en & MLX5_QP_FLAG_ALLOW_SCATTER_CQE; if (!allow_scat_cqe && init_attr->sq_sig_type != IB_SIGNAL_ALL_WR) return; @@ -1853,8 +1852,6 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, u32 *in; int err; - mutex_init(&qp->mutex); - if (attr->sq_sig_type == IB_SIGNAL_ALL_WR) qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE; @@ -1938,7 +1935,6 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -2012,7 +2008,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, } if ((qp->flags_en & MLX5_QP_FLAG_SCATTER_CQE) && (qp->type == MLX5_IB_QPT_DCI || qp->type == IB_QPT_RC)) - configure_requester_scat_cqe(dev, init_attr, ucmd, qpc); + configure_requester_scat_cqe(dev, qp, init_attr, qpc); if (qp->rq.wqe_cnt) { MLX5_SET(qpc, qpc, log_rq_stride, qp->rq.wqe_shift - 4); @@ -2129,7 +2125,6 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -2543,13 +2538,18 @@ static void process_vendor_flag(struct mlx5_ib_dev *dev, int *flags, int flag, return; } - if (flag == MLX5_QP_FLAG_SCATTER_CQE) { + switch (flag) { + case MLX5_QP_FLAG_SCATTER_CQE: + case MLX5_QP_FLAG_ALLOW_SCATTER_CQE: /* - * We don't return error if this flag was provided, - * and mlx5 doesn't have right capability. - */ - *flags &= ~MLX5_QP_FLAG_SCATTER_CQE; + * We don't return error if these flags were provided, + * and mlx5 doesn't have right capability. + */ + *flags &= ~(MLX5_QP_FLAG_SCATTER_CQE | + MLX5_QP_FLAG_ALLOW_SCATTER_CQE); return; + default: + break; } mlx5_ib_dbg(dev, "Vendor create QP flag 0x%X is not supported\n", flag); } @@ -2589,6 +2589,8 @@ static int process_vendor_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SIGNATURE, true, qp); process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SCATTER_CQE, MLX5_CAP_GEN(mdev, sctr_data_cqe), qp); + process_vendor_flag(dev, &flags, MLX5_QP_FLAG_ALLOW_SCATTER_CQE, + MLX5_CAP_GEN(mdev, sctr_data_cqe), qp); if (qp->type == IB_QPT_RAW_PACKET) { cond = MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || @@ -2963,6 +2965,7 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attr, goto free_ucmd; } + mutex_init(&qp->mutex); qp->type = type; if (udata) { err = process_vendor_flags(dev, qp, params.ucmd, attr); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 49b8a43e3fa2..f5aa85a5377c 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1923,7 +1923,7 @@ qedr_roce_create_kernel_qp(struct qedr_dev *dev, in_params->sq_pbl_ptr = qed_chain_get_pbl_phys(&qp->sq.pbl); params.intended_use = QED_CHAIN_USE_TO_CONSUME_PRODUCE; - params.elem_size = n_rq_elems; + params.num_elems = n_rq_elems; params.elem_size = QEDR_RQE_ELEMENT_SIZE; rc = dev->ops->common->chain_alloc(dev->cdev, &qp->rq.pbl, ¶ms); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 7db35dd6ad74..332a8ba94b81 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -901,8 +901,6 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, qp->s_tail_ack_queue = 0; qp->s_acked_ack_queue = 0; qp->s_num_rd_atomic = 0; - if (qp->r_rq.kwq) - qp->r_rq.kwq->count = qp->r_rq.size; qp->r_sge.num_sge = 0; atomic_set(&qp->s_reserved_used, 0); } @@ -2367,31 +2365,6 @@ bad_lkey: } /** - * get_count - count numbers of request work queue entries - * in circular buffer - * @rq: data structure for request queue entry - * @tail: tail indices of the circular buffer - * @head: head indices of the circular buffer - * - * Return - total number of entries in the circular buffer - */ -static u32 get_count(struct rvt_rq *rq, u32 tail, u32 head) -{ - u32 count; - - count = head; - - if (count >= rq->size) - count = 0; - if (count < tail) - count += rq->size - tail; - else - count -= tail; - - return count; -} - -/** * get_rvt_head - get head indices of the circular buffer * @rq: data structure for request queue entry * @ip: the QP @@ -2465,7 +2438,7 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) if (kwq->count < RVT_RWQ_COUNT_THRESHOLD) { head = get_rvt_head(rq, ip); - kwq->count = get_count(rq, tail, head); + kwq->count = rvt_get_rq_count(rq, head, tail); } if (unlikely(kwq->count == 0)) { ret = 0; @@ -2500,7 +2473,9 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) * the number of remaining WQEs. */ if (kwq->count < srq->limit) { - kwq->count = get_count(rq, tail, get_rvt_head(rq, ip)); + kwq->count = + rvt_get_rq_count(rq, + get_rvt_head(rq, ip), tail); if (kwq->count < srq->limit) { struct ib_event ev; diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c index 977906cc0d11..c58735f4c94a 100644 --- a/drivers/infiniband/sw/rdmavt/rc.c +++ b/drivers/infiniband/sw/rdmavt/rc.c @@ -127,9 +127,7 @@ __be32 rvt_compute_aeth(struct rvt_qp *qp) * not atomic, which is OK, since the fuzziness is * resolved as further ACKs go out. */ - credits = head - tail; - if ((int)credits < 0) - credits += qp->r_rq.size; + credits = rvt_get_rq_count(&qp->r_rq, head, tail); } /* * Binary search the credit table to find the code to diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index e5f998744501..9e1ab701785c 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -243,6 +243,7 @@ static int aggregate_requests(struct icc_node *node) { struct icc_provider *p = node->provider; struct icc_req *r; + u32 avg_bw, peak_bw; node->avg_bw = 0; node->peak_bw = 0; @@ -251,9 +252,14 @@ static int aggregate_requests(struct icc_node *node) p->pre_aggregate(node); hlist_for_each_entry(r, &node->req_list, req_node) { - if (!r->enabled) - continue; - p->aggregate(node, r->tag, r->avg_bw, r->peak_bw, + if (r->enabled) { + avg_bw = r->avg_bw; + peak_bw = r->peak_bw; + } else { + avg_bw = 0; + peak_bw = 0; + } + p->aggregate(node, r->tag, avg_bw, peak_bw, &node->avg_bw, &node->peak_bw); } diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c index e94f3c5228b7..42c6c5581662 100644 --- a/drivers/interconnect/qcom/msm8916.c +++ b/drivers/interconnect/qcom/msm8916.c @@ -197,13 +197,13 @@ DEFINE_QNODE(pcnoc_int_0, MSM8916_PNOC_INT_0, 8, -1, -1, MSM8916_PNOC_SNOC_MAS, DEFINE_QNODE(pcnoc_int_1, MSM8916_PNOC_INT_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS); DEFINE_QNODE(pcnoc_m_0, MSM8916_PNOC_MAS_0, 8, -1, -1, MSM8916_PNOC_INT_0); DEFINE_QNODE(pcnoc_m_1, MSM8916_PNOC_MAS_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS); -DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 8, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS); -DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 8, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG); -DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 8, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB); -DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 8, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG); -DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 8, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG); -DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 8, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1); -DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 8, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG); +DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 4, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS); +DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 4, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG); +DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 4, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB); +DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 4, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG); +DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 4, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG); +DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 4, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1); +DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 4, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG); DEFINE_QNODE(pcnoc_snoc_mas, MSM8916_PNOC_SNOC_MAS, 8, 29, -1, MSM8916_PNOC_SNOC_SLV); DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC); diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index b0f62cbbdc87..f3a8f113865d 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -499,11 +499,19 @@ static int validate_queue_index(struct hl_device *hdev, struct asic_fixed_properties *asic = &hdev->asic_prop; struct hw_queue_properties *hw_queue_prop; + /* This must be checked here to prevent out-of-bounds access to + * hw_queues_props array + */ + if (chunk->queue_index >= HL_MAX_QUEUES) { + dev_err(hdev->dev, "Queue index %d is invalid\n", + chunk->queue_index); + return -EINVAL; + } + hw_queue_prop = &asic->hw_queues_props[chunk->queue_index]; - if ((chunk->queue_index >= HL_MAX_QUEUES) || - (hw_queue_prop->type == QUEUE_TYPE_NA)) { - dev_err(hdev->dev, "Queue index %d is invalid\n", + if (hw_queue_prop->type == QUEUE_TYPE_NA) { + dev_err(hdev->dev, "Queue index %d is not applicable\n", chunk->queue_index); return -EINVAL; } diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index fc4372c18ce2..0bc036e01ee8 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -36,7 +36,7 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.i2c_reg = i2c_reg; rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, (long *) val); + 0, (long *) val); if (rc) dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc); @@ -63,7 +63,7 @@ static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.value = cpu_to_le64(val); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to write to I2C, error %d\n", rc); @@ -87,7 +87,7 @@ static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state) pkt.value = cpu_to_le64(state); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to set LED %d, error %d\n", led, rc); @@ -981,7 +981,7 @@ static ssize_t hl_clk_gate_read(struct file *f, char __user *buf, if (*ppos) return 0; - sprintf(tmp_buf, "%d\n", hdev->clock_gating); + sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask); rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf, strlen(tmp_buf) + 1); @@ -993,7 +993,7 @@ static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf, { struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; - u32 value; + u64 value; ssize_t rc; if (atomic_read(&hdev->in_reset)) { @@ -1002,19 +1002,12 @@ static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf, return 0; } - rc = kstrtouint_from_user(buf, count, 10, &value); + rc = kstrtoull_from_user(buf, count, 16, &value); if (rc) return rc; - if (value) { - hdev->clock_gating = 1; - if (hdev->asic_funcs->enable_clock_gating) - hdev->asic_funcs->enable_clock_gating(hdev); - } else { - if (hdev->asic_funcs->disable_clock_gating) - hdev->asic_funcs->disable_clock_gating(hdev); - hdev->clock_gating = 0; - } + hdev->clock_gating_mask = value; + hdev->asic_funcs->set_clock_gating(hdev); return count; } diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 2b38a119704c..59608d1bac88 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -608,7 +608,7 @@ int hl_device_set_debug_mode(struct hl_device *hdev, bool enable) hdev->in_debug = 0; if (!hdev->hard_reset_pending) - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); goto out; } diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c index baf790cf4b78..d27841cb5bcb 100644 --- a/drivers/misc/habanalabs/firmware_if.c +++ b/drivers/misc/habanalabs/firmware_if.c @@ -61,7 +61,7 @@ int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode) pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT); return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, - sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL); + sizeof(pkt), 0, NULL); } int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, @@ -144,7 +144,7 @@ int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type) pkt.value = cpu_to_le64(event_type); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); @@ -183,7 +183,7 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr, ARMCP_PKT_CTL_OPCODE_SHIFT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, - total_pkt_size, HL_DEVICE_TIMEOUT_USEC, &result); + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -204,7 +204,7 @@ int hl_fw_test_cpu_queue(struct hl_device *hdev) test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt, - sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + sizeof(test_pkt), 0, &result); if (!rc) { if (result != ARMCP_PACKET_FENCE_VAL) @@ -248,7 +248,7 @@ int hl_fw_send_heartbeat(struct hl_device *hdev) hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt, - sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + sizeof(hb_pkt), 0, &result); if ((rc) || (result != ARMCP_PACKET_FENCE_VAL)) rc = -EIO; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 834470d10b46..637a9d608707 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -80,6 +80,7 @@ #define GAUDI_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GAUDI_PLDM_TPC_KERNEL_WAIT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GAUDI_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GAUDI_QMAN0_FENCE_VAL 0x72E91AB9 @@ -98,6 +99,11 @@ #define GAUDI_ARB_WDT_TIMEOUT 0x1000000 +#define GAUDI_CLK_GATE_DEBUGFS_MASK (\ + BIT(GAUDI_ENGINE_ID_MME_0) |\ + BIT(GAUDI_ENGINE_ID_MME_2) |\ + GENMASK_ULL(GAUDI_ENGINE_ID_TPC_7, GAUDI_ENGINE_ID_TPC_0)) + static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { "gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3", "gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3", @@ -106,14 +112,14 @@ static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { }; static const u8 gaudi_dma_assignment[GAUDI_DMA_MAX] = { - [GAUDI_PCI_DMA_1] = 0, - [GAUDI_PCI_DMA_2] = 1, - [GAUDI_PCI_DMA_3] = 5, - [GAUDI_HBM_DMA_1] = 2, - [GAUDI_HBM_DMA_2] = 3, - [GAUDI_HBM_DMA_3] = 4, - [GAUDI_HBM_DMA_4] = 6, - [GAUDI_HBM_DMA_5] = 7 + [GAUDI_PCI_DMA_1] = GAUDI_ENGINE_ID_DMA_0, + [GAUDI_PCI_DMA_2] = GAUDI_ENGINE_ID_DMA_1, + [GAUDI_PCI_DMA_3] = GAUDI_ENGINE_ID_DMA_5, + [GAUDI_HBM_DMA_1] = GAUDI_ENGINE_ID_DMA_2, + [GAUDI_HBM_DMA_2] = GAUDI_ENGINE_ID_DMA_3, + [GAUDI_HBM_DMA_3] = GAUDI_ENGINE_ID_DMA_4, + [GAUDI_HBM_DMA_4] = GAUDI_ENGINE_ID_DMA_6, + [GAUDI_HBM_DMA_5] = GAUDI_ENGINE_ID_DMA_7 }; static const u8 gaudi_cq_assignment[NUMBER_OF_CMPLT_QUEUES] = { @@ -1819,7 +1825,7 @@ static void gaudi_init_golden_registers(struct hl_device *hdev) gaudi_init_rate_limiter(hdev); - gaudi_disable_clock_gating(hdev); + hdev->asic_funcs->disable_clock_gating(hdev); for (tpc_id = 0, tpc_offset = 0; tpc_id < TPC_NUMBER_OF_ENGINES; @@ -2531,46 +2537,55 @@ static void gaudi_tpc_stall(struct hl_device *hdev) WREG32(mmTPC7_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT); } -static void gaudi_enable_clock_gating(struct hl_device *hdev) +static void gaudi_set_clock_gating(struct hl_device *hdev) { struct gaudi_device *gaudi = hdev->asic_specific; u32 qman_offset; int i; - if (!hdev->clock_gating) - return; - - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) - return; - /* In case we are during debug session, don't enable the clock gate * as it may interfere */ if (hdev->in_debug) return; - for (i = 0, qman_offset = 0 ; i < PCI_DMA_NUMBER_OF_CHNLS ; i++) { + for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i])))) + continue; + qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, QMAN_UPPER_CP_CGM_PWR_GATE_EN); } - for (; i < HBM_DMA_NUMBER_OF_CHNLS ; i++) { + for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i])))) + continue; + qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, QMAN_COMMON_CP_CGM_PWR_GATE_EN); } - WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME0_QM_CGM_CFG, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); + if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))) { + WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmMME0_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); + } + + if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))) { + WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmMME2_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); + } for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i)))) + continue; + WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmTPC0_QM_CGM_CFG + qman_offset, @@ -2663,7 +2678,7 @@ static void gaudi_halt_engines(struct hl_device *hdev, bool hard_reset) gaudi_stop_hbm_dma_qmans(hdev); gaudi_stop_pci_dma_qmans(hdev); - gaudi_disable_clock_gating(hdev); + hdev->asic_funcs->disable_clock_gating(hdev); msleep(wait_timeout_ms); @@ -3003,7 +3018,7 @@ static int gaudi_hw_init(struct hl_device *hdev) gaudi_init_tpc_qmans(hdev); - gaudi_enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); gaudi_enable_timestamp(hdev); @@ -3112,7 +3127,9 @@ static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset) HW_CAP_HBM_DMA | HW_CAP_PLL | HW_CAP_MMU | HW_CAP_SRAM_SCRAMBLER | - HW_CAP_HBM_SCRAMBLER); + HW_CAP_HBM_SCRAMBLER | + HW_CAP_CLK_GATE); + memset(gaudi->events_stat, 0, sizeof(gaudi->events_stat)); } @@ -3463,6 +3480,9 @@ static int gaudi_send_cpu_message(struct hl_device *hdev, u32 *msg, return 0; } + if (!timeout) + timeout = GAUDI_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GAUDI_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -3865,6 +3885,12 @@ static int gaudi_validate_cb(struct hl_device *hdev, rc = -EPERM; break; + case PACKET_WREG_BULK: + dev_err(hdev->dev, + "User not allowed to use WREG_BULK\n"); + rc = -EPERM; + break; + case PACKET_LOAD_AND_EXE: rc = gaudi_validate_load_and_exe_pkt(hdev, parser, (struct packet_load_and_exe *) user_pkt); @@ -3880,7 +3906,6 @@ static int gaudi_validate_cb(struct hl_device *hdev, break; case PACKET_WREG_32: - case PACKET_WREG_BULK: case PACKET_MSG_LONG: case PACKET_MSG_SHORT: case PACKET_REPEAT: @@ -4521,13 +4546,18 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't read register - clock gating is enabled!\n"); rc = -EFAULT; } else { *val = RREG32(addr - CFG_BASE); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) { *val = readl(hdev->pcie_bar[SRAM_BAR_ID] + @@ -4563,13 +4593,18 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't write register - clock gating is enabled!\n"); rc = -EFAULT; } else { WREG32(addr - CFG_BASE, val); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) { writel(val, hdev->pcie_bar[SRAM_BAR_ID] + @@ -4605,7 +4640,11 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) int rc = 0; if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't read register - clock gating is enabled!\n"); rc = -EFAULT; @@ -4615,6 +4654,7 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) *val = (((u64) val_h) << 32) | val_l; } + } else if ((addr >= SRAM_BASE_ADDR) && (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) { *val = readq(hdev->pcie_bar[SRAM_BAR_ID] + @@ -4651,7 +4691,11 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) int rc = 0; if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't write register - clock gating is enabled!\n"); rc = -EFAULT; @@ -4660,6 +4704,7 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) WREG32(addr + sizeof(u32) - CFG_BASE, upper_32_bits(val)); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) { writeq(val, hdev->pcie_bar[SRAM_BAR_ID] + @@ -4881,7 +4926,7 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid) gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid); gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); } @@ -5262,7 +5307,7 @@ static void gaudi_print_ecc_info_generic(struct hl_device *hdev, } if (disable_clock_gating) { - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); } } @@ -5749,7 +5794,7 @@ static bool gaudi_tpc_read_interrupts(struct hl_device *hdev, u8 tpc_id, /* Clear interrupts */ WREG32(mmTPC0_CFG_TPC_INTR_CAUSE + tpc_offset, 0); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -6265,7 +6310,7 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask, if (s) seq_puts(s, "\n"); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -6366,7 +6411,7 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel, dev_err(hdev->dev, "Timeout while waiting for TPC%d icache prefetch\n", tpc_id); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); return -EIO; } @@ -6395,7 +6440,7 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel, 1000, kernel_timeout); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); if (rc) { @@ -6736,7 +6781,7 @@ static const struct hl_asic_funcs gaudi_funcs = { .mmu_invalidate_cache = gaudi_mmu_invalidate_cache, .mmu_invalidate_cache_range = gaudi_mmu_invalidate_cache_range, .send_heartbeat = gaudi_send_heartbeat, - .enable_clock_gating = gaudi_enable_clock_gating, + .set_clock_gating = gaudi_set_clock_gating, .disable_clock_gating = gaudi_disable_clock_gating, .debug_coresight = gaudi_debug_coresight, .is_device_idle = gaudi_is_device_idle, diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 0d2952bb58df..88460b2138d8 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -88,6 +88,7 @@ #define GOYA_PLDM_MMU_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 100) #define GOYA_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GOYA_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GOYA_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GOYA_QMAN0_FENCE_VAL 0xD169B243 @@ -2830,6 +2831,9 @@ int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, return 0; } + if (!timeout) + timeout = GOYA_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GOYA_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -4431,8 +4435,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY << ARMCP_PKT_CTL_OPCODE_SHIFT); - rc = goya_send_cpu_message(hdev, (u32 *) pkt, total_pkt_size, - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -4464,8 +4468,8 @@ static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) ARMCP_PKT_CTL_OPCODE_SHIFT); pkt.value = cpu_to_le64(event_type); - rc = goya_send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); @@ -5028,14 +5032,14 @@ int goya_armcp_info_get(struct hl_device *hdev) return 0; } -static void goya_enable_clock_gating(struct hl_device *hdev) +static void goya_set_clock_gating(struct hl_device *hdev) { - + /* clock gating not supported in Goya */ } static void goya_disable_clock_gating(struct hl_device *hdev) { - + /* clock gating not supported in Goya */ } static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask, @@ -5259,7 +5263,7 @@ static const struct hl_asic_funcs goya_funcs = { .mmu_invalidate_cache = goya_mmu_invalidate_cache, .mmu_invalidate_cache_range = goya_mmu_invalidate_cache_range, .send_heartbeat = goya_send_heartbeat, - .enable_clock_gating = goya_enable_clock_gating, + .set_clock_gating = goya_set_clock_gating, .disable_clock_gating = goya_disable_clock_gating, .debug_coresight = goya_debug_coresight, .is_device_idle = goya_is_device_idle, diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 1ecdcf8b763a..194d83352696 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -578,8 +578,9 @@ enum hl_pll_frequency { * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with * ASID-VA-size mask. * @send_heartbeat: send is-alive packet to ArmCP and verify response. - * @enable_clock_gating: enable clock gating for reducing power consumption. - * @disable_clock_gating: disable clock for accessing registers on HBW. + * @set_clock_gating: enable/disable clock gating per engine according to + * clock gating mask in hdev + * @disable_clock_gating: disable clock gating completely * @debug_coresight: perform certain actions on Coresight for debugging. * @is_device_idle: return true if device is idle, false otherwise. * @soft_reset_late_init: perform certain actions needed after soft reset. @@ -587,7 +588,11 @@ enum hl_pll_frequency { * @hw_queues_unlock: release H/W queues lock. * @get_pci_id: retrieve PCI ID. * @get_eeprom_data: retrieve EEPROM data from F/W. - * @send_cpu_message: send buffer to ArmCP. + * @send_cpu_message: send message to F/W. If the message is timedout, the + * driver will eventually reset the device. The timeout can + * be determined by the calling function or it can be 0 and + * then the timeout is the default timeout for the specific + * ASIC * @get_hw_state: retrieve the H/W state * @pci_bars_map: Map PCI BARs. * @set_dram_bar_base: Set DRAM BAR to map specific device address. Returns @@ -680,7 +685,7 @@ struct hl_asic_funcs { int (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard, u32 asid, u64 va, u64 size); int (*send_heartbeat)(struct hl_device *hdev); - void (*enable_clock_gating)(struct hl_device *hdev); + void (*set_clock_gating)(struct hl_device *hdev); void (*disable_clock_gating)(struct hl_device *hdev); int (*debug_coresight)(struct hl_device *hdev, void *data); bool (*is_device_idle)(struct hl_device *hdev, u32 *mask, @@ -1398,6 +1403,9 @@ struct hl_device_idle_busy_ts { * @max_power: the max power of the device, as configured by the sysadmin. This * value is saved so in case of hard-reset, the driver will restore * this value and update the F/W after the re-initialization + * @clock_gating_mask: is clock gating enabled. bitmask that represents the + * different engines. See debugfs-driver-habanalabs for + * details. * @in_reset: is device in reset flow. * @curr_pll_profile: current PLL profile. * @cs_active_cnt: number of active command submissions on this device (active @@ -1425,7 +1433,6 @@ struct hl_device_idle_busy_ts { * @init_done: is the initialization of the device done. * @mmu_enable: is MMU enabled. * @mmu_huge_page_opt: is MMU huge pages optimization enabled. - * @clock_gating: is clock gating enabled. * @device_cpu_disabled: is the device CPU disabled (due to timeouts) * @dma_mask: the dma mask that was set for this device * @in_debug: is device under debug. This, together with fpriv_list, enforces @@ -1493,6 +1500,7 @@ struct hl_device { atomic64_t dram_used_mem; u64 timeout_jiffies; u64 max_power; + u64 clock_gating_mask; atomic_t in_reset; enum hl_pll_frequency curr_pll_profile; int cs_active_cnt; @@ -1514,7 +1522,6 @@ struct hl_device { u8 dram_default_page_mapping; u8 pmmu_huge_range; u8 init_done; - u8 clock_gating; u8 device_cpu_disabled; u8 dma_mask; u8 in_debug; diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index 8652c7e5d7f1..22716da9f85f 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -232,7 +232,7 @@ static void set_driver_behavior_per_device(struct hl_device *hdev) hdev->fw_loading = 1; hdev->cpu_queues_enable = 1; hdev->heartbeat = 1; - hdev->clock_gating = 1; + hdev->clock_gating_mask = ULONG_MAX; hdev->reset_pcilink = 0; hdev->axi_drain = 0; diff --git a/drivers/misc/habanalabs/hwmon.c b/drivers/misc/habanalabs/hwmon.c index 8c6cd77e6af6..b997336fa75f 100644 --- a/drivers/misc/habanalabs/hwmon.c +++ b/drivers/misc/habanalabs/hwmon.c @@ -10,7 +10,6 @@ #include <linux/pci.h> #include <linux/hwmon.h> -#define SENSORS_PKT_TIMEOUT 1000000 /* 1s */ #define HWMON_NR_SENSOR_TYPES (hwmon_pwm + 1) int hl_build_hwmon_channel_info(struct hl_device *hdev, @@ -323,7 +322,7 @@ int hl_get_temperature(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -350,7 +349,7 @@ int hl_set_temperature(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -374,7 +373,7 @@ int hl_get_voltage(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -400,7 +399,7 @@ int hl_get_current(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -426,7 +425,7 @@ int hl_get_fan_speed(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -452,7 +451,7 @@ int hl_get_pwm_info(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -479,7 +478,7 @@ void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, pkt.value = cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -502,7 +501,7 @@ int hl_set_voltage(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -527,7 +526,7 @@ int hl_set_current(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, diff --git a/drivers/misc/habanalabs/sysfs.c b/drivers/misc/habanalabs/sysfs.c index 5d78d5e1c782..70b6b1863c2e 100644 --- a/drivers/misc/habanalabs/sysfs.c +++ b/drivers/misc/habanalabs/sysfs.c @@ -9,9 +9,6 @@ #include <linux/pci.h> -#define SET_CLK_PKT_TIMEOUT 1000000 /* 1s */ -#define SET_PWR_PKT_TIMEOUT 1000000 /* 1s */ - long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr) { struct armcp_packet pkt; @@ -29,7 +26,7 @@ long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr) pkt.pll_index = cpu_to_le32(pll_index); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_CLK_PKT_TIMEOUT, &result); + 0, &result); if (rc) { dev_err(hdev->dev, @@ -54,7 +51,7 @@ void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq) pkt.value = cpu_to_le64(freq); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_CLK_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -74,7 +71,7 @@ u64 hl_get_max_power(struct hl_device *hdev) ARMCP_PKT_CTL_OPCODE_SHIFT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_PWR_PKT_TIMEOUT, &result); + 0, &result); if (rc) { dev_err(hdev->dev, "Failed to get max power, error %d\n", rc); @@ -96,7 +93,7 @@ void hl_set_max_power(struct hl_device *hdev, u64 value) pkt.value = cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_PWR_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to set max power, error %d\n", rc); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 44eb2b1d0416..3b6664c7e73c 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -406,19 +406,34 @@ free_dst: return err; } +static bool bareudp_proto_valid(struct bareudp_dev *bareudp, __be16 proto) +{ + if (bareudp->ethertype == proto) + return true; + + if (!bareudp->multi_proto_mode) + return false; + + if (bareudp->ethertype == htons(ETH_P_MPLS_UC) && + proto == htons(ETH_P_MPLS_MC)) + return true; + + if (bareudp->ethertype == htons(ETH_P_IP) && + proto == htons(ETH_P_IPV6)) + return true; + + return false; +} + static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; - if (skb->protocol != bareudp->ethertype) { - if (!bareudp->multi_proto_mode || - (skb->protocol != htons(ETH_P_MPLS_MC) && - skb->protocol != htons(ETH_P_IPV6))) { - err = -EINVAL; - goto tx_error; - } + if (!bareudp_proto_valid(bareudp, skb->protocol)) { + err = -EINVAL; + goto tx_error; } info = skb_tunnel_info(skb); diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index f8bc85a6e670..eb600b3dbf26 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -14,28 +14,11 @@ #include <linux/workqueue.h> #include <linux/module.h> #include <linux/if_bridge.h> +#include <linux/dsa/loop.h> #include <net/dsa.h> #include "dsa_loop.h" -struct dsa_loop_vlan { - u16 members; - u16 untagged; -}; - -struct dsa_loop_mib_entry { - char name[ETH_GSTRING_LEN]; - unsigned long val; -}; - -enum dsa_loop_mib_counters { - DSA_LOOP_PHY_READ_OK, - DSA_LOOP_PHY_READ_ERR, - DSA_LOOP_PHY_WRITE_OK, - DSA_LOOP_PHY_WRITE_ERR, - __DSA_LOOP_CNT_MAX, -}; - static struct dsa_loop_mib_entry dsa_loop_mibs[] = { [DSA_LOOP_PHY_READ_OK] = { "phy_read_ok", }, [DSA_LOOP_PHY_READ_ERR] = { "phy_read_err", }, @@ -43,21 +26,6 @@ static struct dsa_loop_mib_entry dsa_loop_mibs[] = { [DSA_LOOP_PHY_WRITE_ERR] = { "phy_write_err", }, }; -struct dsa_loop_port { - struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX]; -}; - -#define DSA_LOOP_VLANS 5 - -struct dsa_loop_priv { - struct mii_bus *bus; - unsigned int port_base; - struct dsa_loop_vlan vlans[DSA_LOOP_VLANS]; - struct net_device *netdev; - struct dsa_loop_port ports[DSA_MAX_PORTS]; - u16 pvid; -}; - static struct phy_device *phydevs[PHY_MAX_ADDR]; static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds, @@ -191,7 +159,7 @@ dsa_loop_port_vlan_prepare(struct dsa_switch *ds, int port, /* Just do a sleeping operation to make lockdep checks effective */ mdiobus_read(bus, ps->port_base + port, MII_BMSR); - if (vlan->vid_end > DSA_LOOP_VLANS) + if (vlan->vid_end > ARRAY_SIZE(ps->vlans)) return -ERANGE; return 0; @@ -224,7 +192,7 @@ static void dsa_loop_port_vlan_add(struct dsa_switch *ds, int port, } if (pvid) - ps->pvid = vid; + ps->ports[port].pvid = vid; } static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port, @@ -234,7 +202,7 @@ static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port, struct dsa_loop_priv *ps = ds->priv; struct mii_bus *bus = ps->bus; struct dsa_loop_vlan *vl; - u16 vid, pvid = ps->pvid; + u16 vid, pvid = ps->ports[port].pvid; /* Just do a sleeping operation to make lockdep checks effective */ mdiobus_read(bus, ps->port_base + port, MII_BMSR); @@ -252,11 +220,26 @@ static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port, dev_dbg(ds->dev, "%s: port: %d vlan: %d, %stagged, pvid: %d\n", __func__, port, vid, untagged ? "un" : "", pvid); } - ps->pvid = pvid; + ps->ports[port].pvid = pvid; + + return 0; +} + +static int dsa_loop_port_change_mtu(struct dsa_switch *ds, int port, + int new_mtu) +{ + struct dsa_loop_priv *priv = ds->priv; + + priv->ports[port].mtu = new_mtu; return 0; } +static int dsa_loop_port_max_mtu(struct dsa_switch *ds, int port) +{ + return ETH_MAX_MTU; +} + static const struct dsa_switch_ops dsa_loop_driver = { .get_tag_protocol = dsa_loop_get_protocol, .setup = dsa_loop_setup, @@ -273,6 +256,8 @@ static const struct dsa_switch_ops dsa_loop_driver = { .port_vlan_prepare = dsa_loop_port_vlan_prepare, .port_vlan_add = dsa_loop_port_vlan_add, .port_vlan_del = dsa_loop_port_vlan_del, + .port_change_mtu = dsa_loop_port_change_mtu, + .port_max_mtu = dsa_loop_port_max_mtu, }; static int dsa_loop_drv_probe(struct mdio_device *mdiodev) @@ -290,7 +275,7 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) return -ENOMEM; ds->dev = &mdiodev->dev; - ds->num_ports = DSA_MAX_PORTS; + ds->num_ports = DSA_LOOP_NUM_PORTS; ps = devm_kzalloc(&mdiodev->dev, sizeof(*ps), GFP_KERNEL); if (!ps) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a5566de82853..f1e484477e35 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -408,6 +408,112 @@ qca8k_fdb_flush(struct qca8k_priv *priv) mutex_unlock(&priv->reg_mutex); } +static int +qca8k_vlan_access(struct qca8k_priv *priv, enum qca8k_vlan_cmd cmd, u16 vid) +{ + u32 reg; + + /* Set the command and VLAN index */ + reg = QCA8K_VTU_FUNC1_BUSY; + reg |= cmd; + reg |= vid << QCA8K_VTU_FUNC1_VID_S; + + /* Write the function register triggering the table access */ + qca8k_write(priv, QCA8K_REG_VTU_FUNC1, reg); + + /* wait for completion */ + if (qca8k_busy_wait(priv, QCA8K_REG_VTU_FUNC1, QCA8K_VTU_FUNC1_BUSY)) + return -ETIMEDOUT; + + /* Check for table full violation when adding an entry */ + if (cmd == QCA8K_VLAN_LOAD) { + reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC1); + if (reg & QCA8K_VTU_FUNC1_FULL) + return -ENOMEM; + } + + return 0; +} + +static int +qca8k_vlan_add(struct qca8k_priv *priv, u8 port, u16 vid, bool untagged) +{ + u32 reg; + int ret; + + /* + We do the right thing with VLAN 0 and treat it as untagged while + preserving the tag on egress. + */ + if (vid == 0) + return 0; + + mutex_lock(&priv->reg_mutex); + ret = qca8k_vlan_access(priv, QCA8K_VLAN_READ, vid); + if (ret < 0) + goto out; + + reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC0); + reg |= QCA8K_VTU_FUNC0_VALID | QCA8K_VTU_FUNC0_IVL_EN; + reg &= ~(QCA8K_VTU_FUNC0_EG_MODE_MASK << QCA8K_VTU_FUNC0_EG_MODE_S(port)); + if (untagged) + reg |= QCA8K_VTU_FUNC0_EG_MODE_UNTAG << + QCA8K_VTU_FUNC0_EG_MODE_S(port); + else + reg |= QCA8K_VTU_FUNC0_EG_MODE_TAG << + QCA8K_VTU_FUNC0_EG_MODE_S(port); + + qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg); + ret = qca8k_vlan_access(priv, QCA8K_VLAN_LOAD, vid); + +out: + mutex_unlock(&priv->reg_mutex); + + return ret; +} + +static int +qca8k_vlan_del(struct qca8k_priv *priv, u8 port, u16 vid) +{ + u32 reg, mask; + int ret, i; + bool del; + + mutex_lock(&priv->reg_mutex); + ret = qca8k_vlan_access(priv, QCA8K_VLAN_READ, vid); + if (ret < 0) + goto out; + + reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC0); + reg &= ~(3 << QCA8K_VTU_FUNC0_EG_MODE_S(port)); + reg |= QCA8K_VTU_FUNC0_EG_MODE_NOT << + QCA8K_VTU_FUNC0_EG_MODE_S(port); + + /* Check if we're the last member to be removed */ + del = true; + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + mask = QCA8K_VTU_FUNC0_EG_MODE_NOT; + mask <<= QCA8K_VTU_FUNC0_EG_MODE_S(i); + + if ((reg & mask) != mask) { + del = false; + break; + } + } + + if (del) { + ret = qca8k_vlan_access(priv, QCA8K_VLAN_PURGE, vid); + } else { + qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg); + ret = qca8k_vlan_access(priv, QCA8K_VLAN_LOAD, vid); + } + +out: + mutex_unlock(&priv->reg_mutex); + + return ret; +} + static void qca8k_mib_init(struct qca8k_priv *priv) { @@ -663,10 +769,11 @@ qca8k_setup(struct dsa_switch *ds) * default egress vid */ qca8k_rmw(priv, QCA8K_EGRESS_VLAN(i), - 0xffff << shift, 1 << shift); + 0xfff << shift, + QCA8K_PORT_VID_DEF << shift); qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(i), - QCA8K_PORT_VLAN_CVID(1) | - QCA8K_PORT_VLAN_SVID(1)); + QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) | + QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF)); } } @@ -1133,7 +1240,7 @@ qca8k_port_fdb_insert(struct qca8k_priv *priv, const u8 *addr, { /* Set the vid to the port vlan id if no vid is set */ if (!vid) - vid = 1; + vid = QCA8K_PORT_VID_DEF; return qca8k_fdb_add(priv, addr, port_mask, vid, QCA8K_ATU_STATUS_STATIC); @@ -1157,7 +1264,7 @@ qca8k_port_fdb_del(struct dsa_switch *ds, int port, u16 port_mask = BIT(port); if (!vid) - vid = 1; + vid = QCA8K_PORT_VID_DEF; return qca8k_fdb_del(priv, addr, port_mask, vid); } @@ -1186,6 +1293,76 @@ qca8k_port_fdb_dump(struct dsa_switch *ds, int port, return 0; } +static int +qca8k_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering) +{ + struct qca8k_priv *priv = ds->priv; + + if (vlan_filtering) { + qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_VLAN_MODE, + QCA8K_PORT_LOOKUP_VLAN_MODE_SECURE); + } else { + qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_VLAN_MODE, + QCA8K_PORT_LOOKUP_VLAN_MODE_NONE); + } + + return 0; +} + +static int +qca8k_port_vlan_prepare(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + return 0; +} + +static void +qca8k_port_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + struct qca8k_priv *priv = ds->priv; + int ret = 0; + u16 vid; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end && !ret; ++vid) + ret = qca8k_vlan_add(priv, port, vid, untagged); + + if (ret) + dev_err(priv->dev, "Failed to add VLAN to port %d (%d)", port, ret); + + if (pvid) { + int shift = 16 * (port % 2); + + qca8k_rmw(priv, QCA8K_EGRESS_VLAN(port), + 0xfff << shift, + vlan->vid_end << shift); + qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(port), + QCA8K_PORT_VLAN_CVID(vlan->vid_end) | + QCA8K_PORT_VLAN_SVID(vlan->vid_end)); + } +} + +static int +qca8k_port_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct qca8k_priv *priv = ds->priv; + int ret = 0; + u16 vid; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end && !ret; ++vid) + ret = qca8k_vlan_del(priv, port, vid); + + if (ret) + dev_err(priv->dev, "Failed to delete VLAN from port %d (%d)", port, ret); + + return ret; +} + static enum dsa_tag_protocol qca8k_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -1211,6 +1388,10 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .port_fdb_add = qca8k_port_fdb_add, .port_fdb_del = qca8k_port_fdb_del, .port_fdb_dump = qca8k_port_fdb_dump, + .port_vlan_filtering = qca8k_port_vlan_filtering, + .port_vlan_prepare = qca8k_port_vlan_prepare, + .port_vlan_add = qca8k_port_vlan_add, + .port_vlan_del = qca8k_port_vlan_del, .phylink_validate = qca8k_phylink_validate, .phylink_mac_link_state = qca8k_phylink_mac_link_state, .phylink_mac_config = qca8k_phylink_mac_config, @@ -1261,6 +1442,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev) priv->ds->dev = &mdiodev->dev; priv->ds->num_ports = QCA8K_NUM_PORTS; + priv->ds->configure_vlan_while_not_filtering = true; priv->ds->priv = priv; priv->ops = qca8k_switch_ops; priv->ds->ops = &priv->ops; diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index 31439396401c..7ca4b93e0bb5 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -22,6 +22,8 @@ #define QCA8K_CPU_PORT 0 +#define QCA8K_PORT_VID_DEF 1 + /* Global control registers */ #define QCA8K_REG_MASK_CTRL 0x000 #define QCA8K_MASK_CTRL_ID_M 0xff @@ -126,6 +128,19 @@ #define QCA8K_ATU_FUNC_FULL BIT(12) #define QCA8K_ATU_FUNC_PORT_M 0xf #define QCA8K_ATU_FUNC_PORT_S 8 +#define QCA8K_REG_VTU_FUNC0 0x610 +#define QCA8K_VTU_FUNC0_VALID BIT(20) +#define QCA8K_VTU_FUNC0_IVL_EN BIT(19) +#define QCA8K_VTU_FUNC0_EG_MODE_S(_i) (4 + (_i) * 2) +#define QCA8K_VTU_FUNC0_EG_MODE_MASK 3 +#define QCA8K_VTU_FUNC0_EG_MODE_UNMOD 0 +#define QCA8K_VTU_FUNC0_EG_MODE_UNTAG 1 +#define QCA8K_VTU_FUNC0_EG_MODE_TAG 2 +#define QCA8K_VTU_FUNC0_EG_MODE_NOT 3 +#define QCA8K_REG_VTU_FUNC1 0x614 +#define QCA8K_VTU_FUNC1_BUSY BIT(31) +#define QCA8K_VTU_FUNC1_VID_S 16 +#define QCA8K_VTU_FUNC1_FULL BIT(4) #define QCA8K_REG_GLOBAL_FW_CTRL0 0x620 #define QCA8K_GLOBAL_FW_CTRL0_CPU_PORT_EN BIT(10) #define QCA8K_REG_GLOBAL_FW_CTRL1 0x624 @@ -135,6 +150,11 @@ #define QCA8K_GLOBAL_FW_CTRL1_UC_DP_S 0 #define QCA8K_PORT_LOOKUP_CTRL(_i) (0x660 + (_i) * 0xc) #define QCA8K_PORT_LOOKUP_MEMBER GENMASK(6, 0) +#define QCA8K_PORT_LOOKUP_VLAN_MODE GENMASK(9, 8) +#define QCA8K_PORT_LOOKUP_VLAN_MODE_NONE (0 << 8) +#define QCA8K_PORT_LOOKUP_VLAN_MODE_FALLBACK (1 << 8) +#define QCA8K_PORT_LOOKUP_VLAN_MODE_CHECK (2 << 8) +#define QCA8K_PORT_LOOKUP_VLAN_MODE_SECURE (3 << 8) #define QCA8K_PORT_LOOKUP_STATE_MASK GENMASK(18, 16) #define QCA8K_PORT_LOOKUP_STATE_DISABLED (0 << 16) #define QCA8K_PORT_LOOKUP_STATE_BLOCKING (1 << 16) @@ -178,6 +198,15 @@ enum qca8k_fdb_cmd { QCA8K_FDB_SEARCH = 7, }; +enum qca8k_vlan_cmd { + QCA8K_VLAN_FLUSH = 1, + QCA8K_VLAN_LOAD = 2, + QCA8K_VLAN_PURGE = 3, + QCA8K_VLAN_REMOVE_PORT = 4, + QCA8K_VLAN_NEXT = 5, + QCA8K_VLAN_READ = 6, +}; + struct ar8xxx_port_status { int enabled; }; diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index 993cf3ac59d9..8f40fbf70a82 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -43,18 +43,26 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, int ret; int i; + dev_dbg(smi->dev, + "setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", + vid, member, untag); + /* Update the 4K table */ ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); if (ret) return ret; - vlan4k.member = member; - vlan4k.untag = untag; + vlan4k.member |= member; + vlan4k.untag |= untag; vlan4k.fid = fid; ret = smi->ops->set_vlan_4k(smi, &vlan4k); if (ret) return ret; + dev_dbg(smi->dev, + "resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", + vid, vlan4k.member, vlan4k.untag); + /* Try to find an existing MC entry for this VID */ for (i = 0; i < smi->num_vlan_mc; i++) { struct rtl8366_vlan_mc vlanmc; @@ -65,11 +73,16 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, if (vid == vlanmc.vid) { /* update the MC entry */ - vlanmc.member = member; - vlanmc.untag = untag; + vlanmc.member |= member; + vlanmc.untag |= untag; vlanmc.fid = fid; ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + + dev_dbg(smi->dev, + "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", + vid, vlanmc.member, vlanmc.untag); + break; } } @@ -384,7 +397,7 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) dev_err(smi->dev, "port is DSA or CPU port\n"); - for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { int pvid_val = 0; dev_info(smi->dev, "add VLAN %04x\n", vid); @@ -407,13 +420,13 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, if (ret < 0) return; } - } - ret = rtl8366_set_vlan(smi, port, member, untag, 0); - if (ret) - dev_err(smi->dev, - "failed to set up VLAN %04x", - vid); + ret = rtl8366_set_vlan(smi, vid, member, untag, 0); + if (ret) + dev_err(smi->dev, + "failed to set up VLAN %04x", + vid); + } } EXPORT_SYMBOL_GPL(rtl8366_vlan_add); diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 177134596458..1b90570b257b 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -24,7 +24,7 @@ * this hardware can do (but may be enough for some setups). Anything of higher * frequency than 1 Hz will be lost, since there is no timestamp FIFO. */ -#define SJA1105_EXTTS_INTERVAL (HZ / 4) +#define SJA1105_EXTTS_INTERVAL (HZ / 6) /* This range is actually +/- SJA1105_MAX_ADJ_PPB * divided by 1000 (ppb -> ppm) and with a 16-bit @@ -51,8 +51,8 @@ enum sja1105_ptp_clk_mode { PTP_SET_MODE = 0, }; -#define extts_to_data(d) \ - container_of((d), struct sja1105_ptp_data, extts_work) +#define extts_to_data(t) \ + container_of((t), struct sja1105_ptp_data, extts_timer) #define ptp_caps_to_data(d) \ container_of((d), struct sja1105_ptp_data, caps) #define ptp_data_to_sja1105(d) \ @@ -350,6 +350,30 @@ static int sja1105_ptpclkval_write(struct sja1105_private *priv, u64 ticks, ptp_sts); } +static void sja1105_extts_poll(struct sja1105_private *priv) +{ + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + const struct sja1105_regs *regs = priv->info->regs; + struct ptp_clock_event event; + u64 ptpsyncts = 0; + int rc; + + rc = sja1105_xfer_u64(priv, SPI_READ, regs->ptpsyncts, &ptpsyncts, + NULL); + if (rc < 0) + dev_err_ratelimited(priv->ds->dev, + "Failed to read PTPSYNCTS: %d\n", rc); + + if (ptpsyncts && ptp_data->ptpsyncts != ptpsyncts) { + event.index = 0; + event.type = PTP_CLOCK_EXTTS; + event.timestamp = ns_to_ktime(sja1105_ticks_to_ns(ptpsyncts)); + ptp_clock_event(ptp_data->clock, &event); + + ptp_data->ptpsyncts = ptpsyncts; + } +} + static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) { struct sja1105_ptp_data *ptp_data = ptp_caps_to_data(ptp); @@ -380,6 +404,9 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) netif_rx_ni(skb); } + if (ptp_data->extts_enabled) + sja1105_extts_poll(priv); + mutex_unlock(&ptp_data->lock); /* Don't restart */ @@ -595,36 +622,21 @@ static int sja1105_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return rc; } -static void sja1105_ptp_extts_work(struct work_struct *work) +static void sja1105_ptp_extts_setup_timer(struct sja1105_ptp_data *ptp_data) { - struct delayed_work *dw = to_delayed_work(work); - struct sja1105_ptp_data *ptp_data = extts_to_data(dw); - struct sja1105_private *priv = ptp_data_to_sja1105(ptp_data); - const struct sja1105_regs *regs = priv->info->regs; - struct ptp_clock_event event; - u64 ptpsyncts = 0; - int rc; - - mutex_lock(&ptp_data->lock); - - rc = sja1105_xfer_u64(priv, SPI_READ, regs->ptpsyncts, &ptpsyncts, - NULL); - if (rc < 0) - dev_err_ratelimited(priv->ds->dev, - "Failed to read PTPSYNCTS: %d\n", rc); + unsigned long expires = ((jiffies / SJA1105_EXTTS_INTERVAL) + 1) * + SJA1105_EXTTS_INTERVAL; - if (ptpsyncts && ptp_data->ptpsyncts != ptpsyncts) { - event.index = 0; - event.type = PTP_CLOCK_EXTTS; - event.timestamp = ns_to_ktime(sja1105_ticks_to_ns(ptpsyncts)); - ptp_clock_event(ptp_data->clock, &event); + mod_timer(&ptp_data->extts_timer, expires); +} - ptp_data->ptpsyncts = ptpsyncts; - } +static void sja1105_ptp_extts_timer(struct timer_list *t) +{ + struct sja1105_ptp_data *ptp_data = extts_to_data(t); - mutex_unlock(&ptp_data->lock); + ptp_schedule_worker(ptp_data->clock, 0); - schedule_delayed_work(&ptp_data->extts_work, SJA1105_EXTTS_INTERVAL); + sja1105_ptp_extts_setup_timer(ptp_data); } static int sja1105_change_ptp_clk_pin_func(struct sja1105_private *priv, @@ -771,11 +783,12 @@ static int sja1105_extts_enable(struct sja1105_private *priv, if (rc) return rc; + priv->ptp_data.extts_enabled = on; + if (on) - schedule_delayed_work(&priv->ptp_data.extts_work, - SJA1105_EXTTS_INTERVAL); + sja1105_ptp_extts_setup_timer(&priv->ptp_data); else - cancel_delayed_work_sync(&priv->ptp_data.extts_work); + del_timer_sync(&priv->ptp_data.extts_timer); return 0; } @@ -858,7 +871,7 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) ptp_data->cmd.corrclk4ts = true; ptp_data->cmd.ptpclkadd = PTP_SET_MODE; - INIT_DELAYED_WORK(&ptp_data->extts_work, sja1105_ptp_extts_work); + timer_setup(&ptp_data->extts_timer, sja1105_ptp_extts_timer, 0); return sja1105_ptp_reset(ds); } @@ -871,7 +884,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) if (IS_ERR_OR_NULL(ptp_data->clock)) return; - cancel_delayed_work_sync(&ptp_data->extts_work); + del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 6408d1158f2d..3daa33e98e77 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -4,6 +4,8 @@ #ifndef _SJA1105_PTP_H #define _SJA1105_PTP_H +#include <linux/timer.h> + #if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) /* Timestamps are in units of 8 ns clock ticks (equivalent to @@ -72,13 +74,14 @@ struct sja1105_ptp_cmd { }; struct sja1105_ptp_data { - struct delayed_work extts_work; + struct timer_list extts_timer; struct sk_buff_head skb_rxtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; /* Serializes all operations on the PTP hardware clock */ struct mutex lock; + bool extts_enabled; u64 ptpsyncts; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index c38a4b8a14cb..611875ef2cd1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -786,7 +786,7 @@ static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self, int err = 0; if (count > (HW_ATL_A0_MAC_MAX - HW_ATL_A0_MAC_MIN)) { - err = EBADRQC; + err = -EBADRQC; goto err_exit; } for (cfg->mc_list_count = 0U; cfg->mc_list_count < count; ++cfg->mc_list_count) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b4f0c638c467..31fb5a28e1c4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3711,67 +3711,189 @@ static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp) return 0; } -static void bnxt_free_port_stats(struct bnxt *bp) +static void bnxt_free_stats_mem(struct bnxt *bp, struct bnxt_stats_mem *stats) { - struct pci_dev *pdev = bp->pdev; + kfree(stats->hw_masks); + stats->hw_masks = NULL; + kfree(stats->sw_stats); + stats->sw_stats = NULL; + if (stats->hw_stats) { + dma_free_coherent(&bp->pdev->dev, stats->len, stats->hw_stats, + stats->hw_stats_map); + stats->hw_stats = NULL; + } +} - bp->flags &= ~BNXT_FLAG_PORT_STATS; - bp->flags &= ~BNXT_FLAG_PORT_STATS_EXT; +static int bnxt_alloc_stats_mem(struct bnxt *bp, struct bnxt_stats_mem *stats, + bool alloc_masks) +{ + stats->hw_stats = dma_alloc_coherent(&bp->pdev->dev, stats->len, + &stats->hw_stats_map, GFP_KERNEL); + if (!stats->hw_stats) + return -ENOMEM; - if (bp->hw_rx_port_stats) { - dma_free_coherent(&pdev->dev, bp->hw_port_stats_size, - bp->hw_rx_port_stats, - bp->hw_rx_port_stats_map); - bp->hw_rx_port_stats = NULL; - } + stats->sw_stats = kzalloc(stats->len, GFP_KERNEL); + if (!stats->sw_stats) + goto stats_mem_err; - if (bp->hw_tx_port_stats_ext) { - dma_free_coherent(&pdev->dev, sizeof(struct tx_port_stats_ext), - bp->hw_tx_port_stats_ext, - bp->hw_tx_port_stats_ext_map); - bp->hw_tx_port_stats_ext = NULL; + if (alloc_masks) { + stats->hw_masks = kzalloc(stats->len, GFP_KERNEL); + if (!stats->hw_masks) + goto stats_mem_err; } + return 0; + +stats_mem_err: + bnxt_free_stats_mem(bp, stats); + return -ENOMEM; +} + +static void bnxt_fill_masks(u64 *mask_arr, u64 mask, int count) +{ + int i; + + for (i = 0; i < count; i++) + mask_arr[i] = mask; +} + +static void bnxt_copy_hw_masks(u64 *mask_arr, __le64 *hw_mask_arr, int count) +{ + int i; + + for (i = 0; i < count; i++) + mask_arr[i] = le64_to_cpu(hw_mask_arr[i]); +} + +static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp, + struct bnxt_stats_mem *stats) +{ + struct hwrm_func_qstats_ext_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_func_qstats_ext_input req = {0}; + __le64 *hw_masks; + int rc; + + if (!(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED) || + !(bp->flags & BNXT_FLAG_CHIP_P5)) + return -EOPNOTSUPP; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QSTATS_EXT, -1, -1); + req.flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + goto qstat_exit; + + hw_masks = &resp->rx_ucast_pkts; + bnxt_copy_hw_masks(stats->hw_masks, hw_masks, stats->len / 8); + +qstat_exit: + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +static int bnxt_hwrm_port_qstats(struct bnxt *bp, u8 flags); +static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp, u8 flags); - if (bp->hw_rx_port_stats_ext) { - dma_free_coherent(&pdev->dev, sizeof(struct rx_port_stats_ext), - bp->hw_rx_port_stats_ext, - bp->hw_rx_port_stats_ext_map); - bp->hw_rx_port_stats_ext = NULL; +static void bnxt_init_stats(struct bnxt *bp) +{ + struct bnxt_napi *bnapi = bp->bnapi[0]; + struct bnxt_cp_ring_info *cpr; + struct bnxt_stats_mem *stats; + __le64 *rx_stats, *tx_stats; + int rc, rx_count, tx_count; + u64 *rx_masks, *tx_masks; + u64 mask; + u8 flags; + + cpr = &bnapi->cp_ring; + stats = &cpr->stats; + rc = bnxt_hwrm_func_qstat_ext(bp, stats); + if (rc) { + if (bp->flags & BNXT_FLAG_CHIP_P5) + mask = (1ULL << 48) - 1; + else + mask = -1ULL; + bnxt_fill_masks(stats->hw_masks, mask, stats->len / 8); } + if (bp->flags & BNXT_FLAG_PORT_STATS) { + stats = &bp->port_stats; + rx_stats = stats->hw_stats; + rx_masks = stats->hw_masks; + rx_count = sizeof(struct rx_port_stats) / 8; + tx_stats = rx_stats + BNXT_TX_PORT_STATS_BYTE_OFFSET / 8; + tx_masks = rx_masks + BNXT_TX_PORT_STATS_BYTE_OFFSET / 8; + tx_count = sizeof(struct tx_port_stats) / 8; + + flags = PORT_QSTATS_REQ_FLAGS_COUNTER_MASK; + rc = bnxt_hwrm_port_qstats(bp, flags); + if (rc) { + mask = (1ULL << 40) - 1; - if (bp->hw_pcie_stats) { - dma_free_coherent(&pdev->dev, sizeof(struct pcie_ctx_hw_stats), - bp->hw_pcie_stats, bp->hw_pcie_stats_map); - bp->hw_pcie_stats = NULL; + bnxt_fill_masks(rx_masks, mask, rx_count); + bnxt_fill_masks(tx_masks, mask, tx_count); + } else { + bnxt_copy_hw_masks(rx_masks, rx_stats, rx_count); + bnxt_copy_hw_masks(tx_masks, tx_stats, tx_count); + bnxt_hwrm_port_qstats(bp, 0); + } + } + if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { + stats = &bp->rx_port_stats_ext; + rx_stats = stats->hw_stats; + rx_masks = stats->hw_masks; + rx_count = sizeof(struct rx_port_stats_ext) / 8; + stats = &bp->tx_port_stats_ext; + tx_stats = stats->hw_stats; + tx_masks = stats->hw_masks; + tx_count = sizeof(struct tx_port_stats_ext) / 8; + + flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; + rc = bnxt_hwrm_port_qstats_ext(bp, flags); + if (rc) { + mask = (1ULL << 40) - 1; + + bnxt_fill_masks(rx_masks, mask, rx_count); + if (tx_stats) + bnxt_fill_masks(tx_masks, mask, tx_count); + } else { + bnxt_copy_hw_masks(rx_masks, rx_stats, rx_count); + if (tx_stats) + bnxt_copy_hw_masks(tx_masks, tx_stats, + tx_count); + bnxt_hwrm_port_qstats_ext(bp, 0); + } } } +static void bnxt_free_port_stats(struct bnxt *bp) +{ + bp->flags &= ~BNXT_FLAG_PORT_STATS; + bp->flags &= ~BNXT_FLAG_PORT_STATS_EXT; + + bnxt_free_stats_mem(bp, &bp->port_stats); + bnxt_free_stats_mem(bp, &bp->rx_port_stats_ext); + bnxt_free_stats_mem(bp, &bp->tx_port_stats_ext); +} + static void bnxt_free_ring_stats(struct bnxt *bp) { - struct pci_dev *pdev = bp->pdev; - int size, i; + int i; if (!bp->bnapi) return; - size = bp->hw_ring_stats_size; - for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - if (cpr->hw_stats) { - dma_free_coherent(&pdev->dev, size, cpr->hw_stats, - cpr->hw_stats_map); - cpr->hw_stats = NULL; - } + bnxt_free_stats_mem(bp, &cpr->stats); } } static int bnxt_alloc_stats(struct bnxt *bp) { u32 size, i; - struct pci_dev *pdev = bp->pdev; + int rc; size = bp->hw_ring_stats_size; @@ -3779,11 +3901,10 @@ static int bnxt_alloc_stats(struct bnxt *bp) struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - cpr->hw_stats = dma_alloc_coherent(&pdev->dev, size, - &cpr->hw_stats_map, - GFP_KERNEL); - if (!cpr->hw_stats) - return -ENOMEM; + cpr->stats.len = size; + rc = bnxt_alloc_stats_mem(bp, &cpr->stats, !i); + if (rc) + return rc; cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID; } @@ -3791,22 +3912,14 @@ static int bnxt_alloc_stats(struct bnxt *bp) if (BNXT_VF(bp) || bp->chip_num == CHIP_NUM_58700) return 0; - if (bp->hw_rx_port_stats) + if (bp->port_stats.hw_stats) goto alloc_ext_stats; - bp->hw_port_stats_size = sizeof(struct rx_port_stats) + - sizeof(struct tx_port_stats) + 1024; - - bp->hw_rx_port_stats = - dma_alloc_coherent(&pdev->dev, bp->hw_port_stats_size, - &bp->hw_rx_port_stats_map, - GFP_KERNEL); - if (!bp->hw_rx_port_stats) - return -ENOMEM; + bp->port_stats.len = BNXT_PORT_STATS_SIZE; + rc = bnxt_alloc_stats_mem(bp, &bp->port_stats, true); + if (rc) + return rc; - bp->hw_tx_port_stats = (void *)(bp->hw_rx_port_stats + 1) + 512; - bp->hw_tx_port_stats_map = bp->hw_rx_port_stats_map + - sizeof(struct rx_port_stats) + 512; bp->flags |= BNXT_FLAG_PORT_STATS; alloc_ext_stats: @@ -3815,41 +3928,28 @@ alloc_ext_stats: if (!(bp->fw_cap & BNXT_FW_CAP_EXT_STATS_SUPPORTED)) return 0; - if (bp->hw_rx_port_stats_ext) + if (bp->rx_port_stats_ext.hw_stats) goto alloc_tx_ext_stats; - bp->hw_rx_port_stats_ext = - dma_alloc_coherent(&pdev->dev, sizeof(struct rx_port_stats_ext), - &bp->hw_rx_port_stats_ext_map, GFP_KERNEL); - if (!bp->hw_rx_port_stats_ext) + bp->rx_port_stats_ext.len = sizeof(struct rx_port_stats_ext); + rc = bnxt_alloc_stats_mem(bp, &bp->rx_port_stats_ext, true); + /* Extended stats are optional */ + if (rc) return 0; alloc_tx_ext_stats: - if (bp->hw_tx_port_stats_ext) - goto alloc_pcie_stats; + if (bp->tx_port_stats_ext.hw_stats) + return 0; if (bp->hwrm_spec_code >= 0x10902 || (bp->fw_cap & BNXT_FW_CAP_EXT_STATS_SUPPORTED)) { - bp->hw_tx_port_stats_ext = - dma_alloc_coherent(&pdev->dev, - sizeof(struct tx_port_stats_ext), - &bp->hw_tx_port_stats_ext_map, - GFP_KERNEL); + bp->tx_port_stats_ext.len = sizeof(struct tx_port_stats_ext); + rc = bnxt_alloc_stats_mem(bp, &bp->tx_port_stats_ext, true); + /* Extended stats are optional */ + if (rc) + return 0; } bp->flags |= BNXT_FLAG_PORT_STATS_EXT; - -alloc_pcie_stats: - if (bp->hw_pcie_stats || - !(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED)) - return 0; - - bp->hw_pcie_stats = - dma_alloc_coherent(&pdev->dev, sizeof(struct pcie_ctx_hw_stats), - &bp->hw_pcie_stats_map, GFP_KERNEL); - if (!bp->hw_pcie_stats) - return 0; - - bp->flags |= BNXT_FLAG_PCIE_STATS; return 0; } @@ -3949,6 +4049,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init) bnxt_free_ntp_fltrs(bp, irq_re_init); if (irq_re_init) { bnxt_free_ring_stats(bp); + if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET)) + bnxt_free_port_stats(bp); bnxt_free_ring_grps(bp); bnxt_free_vnics(bp); kfree(bp->tx_ring_map); @@ -4052,6 +4154,7 @@ static int bnxt_alloc_mem(struct bnxt *bp, bool irq_re_init) rc = bnxt_alloc_stats(bp); if (rc) goto alloc_mem_err; + bnxt_init_stats(bp); rc = bnxt_alloc_ntp_fltrs(bp); if (rc) @@ -6458,7 +6561,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - req.stats_dma_addr = cpu_to_le64(cpr->hw_stats_map); + req.stats_dma_addr = cpu_to_le64(cpr->stats.hw_stats_map); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -7489,7 +7592,89 @@ int bnxt_hwrm_fw_set_time(struct bnxt *bp) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } -static int bnxt_hwrm_port_qstats(struct bnxt *bp) +static void bnxt_add_one_ctr(u64 hw, u64 *sw, u64 mask) +{ + u64 sw_tmp; + + sw_tmp = (*sw & ~mask) | hw; + if (hw < (*sw & mask)) + sw_tmp += mask + 1; + WRITE_ONCE(*sw, sw_tmp); +} + +static void __bnxt_accumulate_stats(__le64 *hw_stats, u64 *sw_stats, u64 *masks, + int count, bool ignore_zero) +{ + int i; + + for (i = 0; i < count; i++) { + u64 hw = le64_to_cpu(READ_ONCE(hw_stats[i])); + + if (ignore_zero && !hw) + continue; + + if (masks[i] == -1ULL) + sw_stats[i] = hw; + else + bnxt_add_one_ctr(hw, &sw_stats[i], masks[i]); + } +} + +static void bnxt_accumulate_stats(struct bnxt_stats_mem *stats) +{ + if (!stats->hw_stats) + return; + + __bnxt_accumulate_stats(stats->hw_stats, stats->sw_stats, + stats->hw_masks, stats->len / 8, false); +} + +static void bnxt_accumulate_all_stats(struct bnxt *bp) +{ + struct bnxt_stats_mem *ring0_stats; + bool ignore_zero = false; + int i; + + /* Chip bug. Counter intermittently becomes 0. */ + if (bp->flags & BNXT_FLAG_CHIP_P5) + ignore_zero = true; + + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_napi *bnapi = bp->bnapi[i]; + struct bnxt_cp_ring_info *cpr; + struct bnxt_stats_mem *stats; + + cpr = &bnapi->cp_ring; + stats = &cpr->stats; + if (!i) + ring0_stats = stats; + __bnxt_accumulate_stats(stats->hw_stats, stats->sw_stats, + ring0_stats->hw_masks, + ring0_stats->len / 8, ignore_zero); + } + if (bp->flags & BNXT_FLAG_PORT_STATS) { + struct bnxt_stats_mem *stats = &bp->port_stats; + __le64 *hw_stats = stats->hw_stats; + u64 *sw_stats = stats->sw_stats; + u64 *masks = stats->hw_masks; + int cnt; + + cnt = sizeof(struct rx_port_stats) / 8; + __bnxt_accumulate_stats(hw_stats, sw_stats, masks, cnt, false); + + hw_stats += BNXT_TX_PORT_STATS_BYTE_OFFSET / 8; + sw_stats += BNXT_TX_PORT_STATS_BYTE_OFFSET / 8; + masks += BNXT_TX_PORT_STATS_BYTE_OFFSET / 8; + cnt = sizeof(struct tx_port_stats) / 8; + __bnxt_accumulate_stats(hw_stats, sw_stats, masks, cnt, false); + } + if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { + bnxt_accumulate_stats(&bp->rx_port_stats_ext); + bnxt_accumulate_stats(&bp->tx_port_stats_ext); + } +} + +static int bnxt_hwrm_port_qstats(struct bnxt *bp, u8 flags) { struct bnxt_pf_info *pf = &bp->pf; struct hwrm_port_qstats_input req = {0}; @@ -7497,14 +7682,19 @@ static int bnxt_hwrm_port_qstats(struct bnxt *bp) if (!(bp->flags & BNXT_FLAG_PORT_STATS)) return 0; + if (flags && !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED)) + return -EOPNOTSUPP; + + req.flags = flags; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_QSTATS, -1, -1); req.port_id = cpu_to_le16(pf->port_id); - req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_map); - req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_map); + req.tx_stat_host_addr = cpu_to_le64(bp->port_stats.hw_stats_map + + BNXT_TX_PORT_STATS_BYTE_OFFSET); + req.rx_stat_host_addr = cpu_to_le64(bp->port_stats.hw_stats_map); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } -static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp) +static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp, u8 flags) { struct hwrm_port_qstats_ext_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_queue_pri2cos_qcfg_input req2 = {0}; @@ -7516,14 +7706,18 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp) if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT)) return 0; + if (flags && !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED)) + return -EOPNOTSUPP; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_QSTATS_EXT, -1, -1); + req.flags = flags; req.port_id = cpu_to_le16(pf->port_id); req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext)); - req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map); - tx_stat_size = bp->hw_tx_port_stats_ext ? - sizeof(*bp->hw_tx_port_stats_ext) : 0; + req.rx_stat_host_addr = cpu_to_le64(bp->rx_port_stats_ext.hw_stats_map); + tx_stat_size = bp->tx_port_stats_ext.hw_stats ? + sizeof(struct tx_port_stats_ext) : 0; req.tx_stat_size = cpu_to_le16(tx_stat_size); - req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map); + req.tx_stat_host_addr = cpu_to_le64(bp->tx_port_stats_ext.hw_stats_map); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { @@ -7534,6 +7728,9 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp) bp->fw_rx_stats_ext_size = 0; bp->fw_tx_stats_ext_size = 0; } + if (flags) + goto qstats_done; + if (bp->fw_tx_stats_ext_size <= offsetof(struct tx_port_stats_ext, pfc_pri0_tx_duration_us) / 8) { mutex_unlock(&bp->hwrm_cmd_lock); @@ -7574,19 +7771,6 @@ qstats_done: return rc; } -static int bnxt_hwrm_pcie_qstats(struct bnxt *bp) -{ - struct hwrm_pcie_qstats_input req = {0}; - - if (!(bp->flags & BNXT_FLAG_PCIE_STATS)) - return 0; - - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PCIE_QSTATS, -1, -1); - req.pcie_stat_size = cpu_to_le16(sizeof(struct pcie_ctx_hw_stats)); - req.pcie_stat_host_addr = cpu_to_le64(bp->hw_pcie_stats_map); - return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); -} - static void bnxt_hwrm_free_tunnel_ports(struct bnxt *bp) { if (bp->vxlan_fw_dst_port_id != INVALID_HW_RING_ID) @@ -8608,6 +8792,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) if (BNXT_PF(bp)) bp->fw_cap |= BNXT_FW_CAP_SHARED_PORT_CFG; } + if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET) + bp->fw_cap |= BNXT_FW_CAP_PORT_STATS_NO_RESET; + if (resp->supported_speeds_auto_mode) link_info->support_auto_speeds = le16_to_cpu(resp->supported_speeds_auto_mode); @@ -9610,34 +9797,33 @@ static void bnxt_get_ring_stats(struct bnxt *bp, { int i; - for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - struct ctx_hw_stats *hw_stats = cpr->hw_stats; + u64 *sw = cpr->stats.sw_stats; - stats->rx_packets += le64_to_cpu(hw_stats->rx_ucast_pkts); - stats->rx_packets += le64_to_cpu(hw_stats->rx_mcast_pkts); - stats->rx_packets += le64_to_cpu(hw_stats->rx_bcast_pkts); + stats->rx_packets += BNXT_GET_RING_STATS64(sw, rx_ucast_pkts); + stats->rx_packets += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts); + stats->rx_packets += BNXT_GET_RING_STATS64(sw, rx_bcast_pkts); - stats->tx_packets += le64_to_cpu(hw_stats->tx_ucast_pkts); - stats->tx_packets += le64_to_cpu(hw_stats->tx_mcast_pkts); - stats->tx_packets += le64_to_cpu(hw_stats->tx_bcast_pkts); + stats->tx_packets += BNXT_GET_RING_STATS64(sw, tx_ucast_pkts); + stats->tx_packets += BNXT_GET_RING_STATS64(sw, tx_mcast_pkts); + stats->tx_packets += BNXT_GET_RING_STATS64(sw, tx_bcast_pkts); - stats->rx_bytes += le64_to_cpu(hw_stats->rx_ucast_bytes); - stats->rx_bytes += le64_to_cpu(hw_stats->rx_mcast_bytes); - stats->rx_bytes += le64_to_cpu(hw_stats->rx_bcast_bytes); + stats->rx_bytes += BNXT_GET_RING_STATS64(sw, rx_ucast_bytes); + stats->rx_bytes += BNXT_GET_RING_STATS64(sw, rx_mcast_bytes); + stats->rx_bytes += BNXT_GET_RING_STATS64(sw, rx_bcast_bytes); - stats->tx_bytes += le64_to_cpu(hw_stats->tx_ucast_bytes); - stats->tx_bytes += le64_to_cpu(hw_stats->tx_mcast_bytes); - stats->tx_bytes += le64_to_cpu(hw_stats->tx_bcast_bytes); + stats->tx_bytes += BNXT_GET_RING_STATS64(sw, tx_ucast_bytes); + stats->tx_bytes += BNXT_GET_RING_STATS64(sw, tx_mcast_bytes); + stats->tx_bytes += BNXT_GET_RING_STATS64(sw, tx_bcast_bytes); stats->rx_missed_errors += - le64_to_cpu(hw_stats->rx_discard_pkts); + BNXT_GET_RING_STATS64(sw, rx_discard_pkts); - stats->multicast += le64_to_cpu(hw_stats->rx_mcast_pkts); + stats->multicast += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts); - stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts); + stats->tx_dropped += BNXT_GET_RING_STATS64(sw, tx_error_pkts); } } @@ -9675,19 +9861,26 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) bnxt_add_prev_stats(bp, stats); if (bp->flags & BNXT_FLAG_PORT_STATS) { - struct rx_port_stats *rx = bp->hw_rx_port_stats; - struct tx_port_stats *tx = bp->hw_tx_port_stats; - - stats->rx_crc_errors = le64_to_cpu(rx->rx_fcs_err_frames); - stats->rx_frame_errors = le64_to_cpu(rx->rx_align_err_frames); - stats->rx_length_errors = le64_to_cpu(rx->rx_undrsz_frames) + - le64_to_cpu(rx->rx_ovrsz_frames) + - le64_to_cpu(rx->rx_runt_frames); - stats->rx_errors = le64_to_cpu(rx->rx_false_carrier_frames) + - le64_to_cpu(rx->rx_jbr_frames); - stats->collisions = le64_to_cpu(tx->tx_total_collisions); - stats->tx_fifo_errors = le64_to_cpu(tx->tx_fifo_underruns); - stats->tx_errors = le64_to_cpu(tx->tx_err); + u64 *rx = bp->port_stats.sw_stats; + u64 *tx = bp->port_stats.sw_stats + + BNXT_TX_PORT_STATS_BYTE_OFFSET / 8; + + stats->rx_crc_errors = + BNXT_GET_RX_PORT_STATS64(rx, rx_fcs_err_frames); + stats->rx_frame_errors = + BNXT_GET_RX_PORT_STATS64(rx, rx_align_err_frames); + stats->rx_length_errors = + BNXT_GET_RX_PORT_STATS64(rx, rx_undrsz_frames) + + BNXT_GET_RX_PORT_STATS64(rx, rx_ovrsz_frames) + + BNXT_GET_RX_PORT_STATS64(rx, rx_runt_frames); + stats->rx_errors = + BNXT_GET_RX_PORT_STATS64(rx, rx_false_carrier_frames) + + BNXT_GET_RX_PORT_STATS64(rx, rx_jbr_frames); + stats->collisions = + BNXT_GET_TX_PORT_STATS64(tx, tx_total_collisions); + stats->tx_fifo_errors = + BNXT_GET_TX_PORT_STATS64(tx, tx_fifo_underruns); + stats->tx_errors = BNXT_GET_TX_PORT_STATS64(tx, tx_err); } clear_bit(BNXT_STATE_READ_STATS, &bp->state); } @@ -10033,6 +10226,38 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) return rc; } +int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words, + u32 *reg_buf) +{ + struct hwrm_dbg_read_direct_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_dbg_read_direct_input req = {0}; + __le32 *dbg_reg_buf; + dma_addr_t mapping; + int rc, i; + + dbg_reg_buf = dma_alloc_coherent(&bp->pdev->dev, num_words * 4, + &mapping, GFP_KERNEL); + if (!dbg_reg_buf) + return -ENOMEM; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_READ_DIRECT, -1, -1); + req.host_dest_addr = cpu_to_le64(mapping); + req.read_addr = cpu_to_le32(reg_off + CHIMP_REG_VIEW_ADDR); + req.read_len32 = cpu_to_le32(num_words); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc || resp->error_code) { + rc = -EIO; + goto dbg_rd_reg_exit; + } + for (i = 0; i < num_words; i++) + reg_buf[i] = le32_to_cpu(dbg_reg_buf[i]); + +dbg_rd_reg_exit: + mutex_unlock(&bp->hwrm_cmd_lock); + dma_free_coherent(&bp->pdev->dev, num_words * 4, dbg_reg_buf, mapping); + return rc; +} + static int bnxt_dbg_hwrm_ring_info_get(struct bnxt *bp, u8 ring_type, u32 ring_id, u32 *prod, u32 *cons) { @@ -10177,8 +10402,7 @@ static void bnxt_timer(struct timer_list *t) if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) bnxt_fw_health_check(bp); - if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) && - bp->stats_coal_ticks) { + if (bp->link_info.link_up && bp->stats_coal_ticks) { set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event); bnxt_queue_sp_work(bp); } @@ -10464,9 +10688,9 @@ static void bnxt_sp_task(struct work_struct *work) if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) { - bnxt_hwrm_port_qstats(bp); - bnxt_hwrm_port_qstats_ext(bp); - bnxt_hwrm_pcie_qstats(bp); + bnxt_hwrm_port_qstats(bp, 0); + bnxt_hwrm_port_qstats_ext(bp, 0); + bnxt_accumulate_all_stats(bp); } if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 2acd7f958246..5a13eb66beda 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -919,6 +919,14 @@ struct bnxt_sw_stats { struct bnxt_cmn_sw_stats cmn; }; +struct bnxt_stats_mem { + u64 *sw_stats; + u64 *hw_masks; + void *hw_stats; + dma_addr_t hw_stats_map; + int len; +}; + struct bnxt_cp_ring_info { struct bnxt_napi *bnapi; u32 cp_raw_cons; @@ -943,8 +951,7 @@ struct bnxt_cp_ring_info { dma_addr_t cp_desc_mapping[MAX_CP_PAGES]; - struct ctx_hw_stats *hw_stats; - dma_addr_t hw_stats_map; + struct bnxt_stats_mem stats; u32 hw_stats_ctx_id; struct bnxt_sw_stats sw_stats; @@ -1135,6 +1142,50 @@ struct bnxt_ntuple_filter { #define BNXT_FLTR_UPDATE 1 }; +struct hwrm_port_phy_qcfg_output_compat { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 link; + u8 link_signal_mode; + __le16 link_speed; + u8 duplex_cfg; + u8 pause; + __le16 support_speeds; + __le16 force_link_speed; + u8 auto_mode; + u8 auto_pause; + __le16 auto_link_speed; + __le16 auto_link_speed_mask; + u8 wirespeed; + u8 lpbk; + u8 force_pause; + u8 module_status; + __le32 preemphasis; + u8 phy_maj; + u8 phy_min; + u8 phy_bld; + u8 phy_type; + u8 media_type; + u8 xcvr_pkg_type; + u8 eee_config_phy_addr; + u8 parallel_detect; + __le16 link_partner_adv_speeds; + u8 link_partner_adv_auto_mode; + u8 link_partner_adv_pause; + __le16 adv_eee_link_speed_mask; + __le16 link_partner_adv_eee_link_speed_mask; + __le32 xcvr_identifier_type_tx_lpi_timer; + __le16 fec_cfg; + u8 duplex_state; + u8 option_flags; + char phy_vendor_name[16]; + char phy_vendor_partnumber[16]; + u8 unused_0[7]; + u8 valid; +}; + struct bnxt_link_info { u8 phy_type; u8 media_type; @@ -1253,6 +1304,9 @@ struct bnxt_test_info { char string[BNXT_MAX_TEST][ETH_GSTRING_LEN]; }; +#define CHIMP_REG_VIEW_ADDR \ + ((bp->flags & BNXT_FLAG_CHIP_P5) ? 0x80000000 : 0xb1000000) + #define BNXT_GRCPF_REG_CHIMP_COMM 0x0 #define BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER 0x100 #define BNXT_GRCPF_REG_WINDOW_BASE_OUT 0x400 @@ -1566,7 +1620,6 @@ struct bnxt { #define BNXT_FLAG_DIM 0x2000000 #define BNXT_FLAG_ROCE_MIRROR_CAP 0x4000000 #define BNXT_FLAG_PORT_STATS_EXT 0x10000000 - #define BNXT_FLAG_PCIE_STATS 0x40000000 #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ BNXT_FLAG_RFS | \ @@ -1719,6 +1772,7 @@ struct bnxt { #define BNXT_FW_CAP_VLAN_RX_STRIP 0x01000000 #define BNXT_FW_CAP_VLAN_TX_INSERT 0x02000000 #define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED 0x04000000 + #define BNXT_FW_CAP_PORT_STATS_NO_RESET 0x10000000 #define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; @@ -1733,17 +1787,9 @@ struct bnxt { dma_addr_t hwrm_cmd_kong_resp_dma_addr; struct rtnl_link_stats64 net_stats_prev; - struct rx_port_stats *hw_rx_port_stats; - struct tx_port_stats *hw_tx_port_stats; - struct rx_port_stats_ext *hw_rx_port_stats_ext; - struct tx_port_stats_ext *hw_tx_port_stats_ext; - struct pcie_ctx_hw_stats *hw_pcie_stats; - dma_addr_t hw_rx_port_stats_map; - dma_addr_t hw_tx_port_stats_map; - dma_addr_t hw_rx_port_stats_ext_map; - dma_addr_t hw_tx_port_stats_ext_map; - dma_addr_t hw_pcie_stats_map; - int hw_port_stats_size; + struct bnxt_stats_mem port_stats; + struct bnxt_stats_mem rx_port_stats_ext; + struct bnxt_stats_mem tx_port_stats_ext; u16 fw_rx_stats_ext_size; u16 fw_tx_stats_ext_size; u16 hw_ring_stats_size; @@ -1885,12 +1931,27 @@ struct bnxt { struct device *hwmon_dev; }; +#define BNXT_GET_RING_STATS64(sw, counter) \ + (*((sw) + offsetof(struct ctx_hw_stats, counter) / 8)) + +#define BNXT_GET_RX_PORT_STATS64(sw, counter) \ + (*((sw) + offsetof(struct rx_port_stats, counter) / 8)) + +#define BNXT_GET_TX_PORT_STATS64(sw, counter) \ + (*((sw) + offsetof(struct tx_port_stats, counter) / 8)) + +#define BNXT_PORT_STATS_SIZE \ + (sizeof(struct rx_port_stats) + sizeof(struct tx_port_stats) + 1024) + +#define BNXT_TX_PORT_STATS_BYTE_OFFSET \ + (sizeof(struct rx_port_stats) + 512) + #define BNXT_RX_STATS_OFFSET(counter) \ (offsetof(struct rx_port_stats, counter) / 8) #define BNXT_TX_STATS_OFFSET(counter) \ ((offsetof(struct tx_port_stats, counter) + \ - sizeof(struct rx_port_stats) + 512) / 8) + BNXT_TX_PORT_STATS_BYTE_OFFSET) / 8) #define BNXT_RX_STATS_EXT_OFFSET(counter) \ (offsetof(struct rx_port_stats_ext, counter) / 8) @@ -1898,9 +1959,6 @@ struct bnxt { #define BNXT_TX_STATS_EXT_OFFSET(counter) \ (offsetof(struct tx_port_stats_ext, counter) / 8) -#define BNXT_PCIE_STATS_OFFSET(counter) \ - (offsetof(struct pcie_ctx_hw_stats, counter) / 8) - #define BNXT_HW_FEATURE_VLAN_ALL_RX \ (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX) #define BNXT_HW_FEATURE_VLAN_ALL_TX \ @@ -2062,6 +2120,8 @@ int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); int bnxt_close_nic(struct bnxt *, bool, bool); +int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words, + u32 *reg_buf); void bnxt_fw_exception(struct bnxt *bp); void bnxt_fw_reset(struct bnxt *bp); int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 02b27551d34d..8e90224c43a2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -544,7 +544,7 @@ static int bnxt_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) static int bnxt_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct bnxt *bp = netdev_priv(dev); - __le64 *stats = (__le64 *)bp->hw_rx_port_stats; + __le64 *stats = bp->port_stats.hw_stats; struct ieee_pfc *my_pfc = bp->ieee_pfc; long rx_off, tx_off; int i, rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 25252d5beec8..64da654f1038 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -142,7 +142,7 @@ static const char * const bnxt_ring_rx_stats_str[] = { "rx_mcast_packets", "rx_bcast_packets", "rx_discards", - "rx_drops", + "rx_errors", "rx_ucast_bytes", "rx_mcast_bytes", "rx_bcast_bytes", @@ -152,8 +152,8 @@ static const char * const bnxt_ring_tx_stats_str[] = { "tx_ucast_packets", "tx_mcast_packets", "tx_bcast_packets", + "tx_errors", "tx_discards", - "tx_drops", "tx_ucast_bytes", "tx_mcast_bytes", "tx_bcast_bytes", @@ -293,9 +293,6 @@ static const char * const bnxt_cmn_sw_stats_str[] = { BNXT_TX_STATS_PRI_ENTRY(counter, 6), \ BNXT_TX_STATS_PRI_ENTRY(counter, 7) -#define BNXT_PCIE_STATS_ENTRY(counter) \ - { BNXT_PCIE_STATS_OFFSET(counter), __stringify(counter) } - enum { RX_TOTAL_DISCARDS, TX_TOTAL_DISCARDS, @@ -454,24 +451,6 @@ static const struct { BNXT_TX_STATS_PRI_ENTRIES(tx_packets), }; -static const struct { - long offset; - char string[ETH_GSTRING_LEN]; -} bnxt_pcie_stats_arr[] = { - BNXT_PCIE_STATS_ENTRY(pcie_pl_signal_integrity), - BNXT_PCIE_STATS_ENTRY(pcie_dl_signal_integrity), - BNXT_PCIE_STATS_ENTRY(pcie_tl_signal_integrity), - BNXT_PCIE_STATS_ENTRY(pcie_link_integrity), - BNXT_PCIE_STATS_ENTRY(pcie_tx_traffic_rate), - BNXT_PCIE_STATS_ENTRY(pcie_rx_traffic_rate), - BNXT_PCIE_STATS_ENTRY(pcie_tx_dllp_statistics), - BNXT_PCIE_STATS_ENTRY(pcie_rx_dllp_statistics), - BNXT_PCIE_STATS_ENTRY(pcie_equalization_time), - BNXT_PCIE_STATS_ENTRY(pcie_ltssm_histogram[0]), - BNXT_PCIE_STATS_ENTRY(pcie_ltssm_histogram[2]), - BNXT_PCIE_STATS_ENTRY(pcie_recovery_histogram), -}; - #define BNXT_NUM_SW_FUNC_STATS ARRAY_SIZE(bnxt_sw_func_stats) #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr) #define BNXT_NUM_STATS_PRI \ @@ -479,7 +458,6 @@ static const struct { ARRAY_SIZE(bnxt_rx_pkts_pri_arr) + \ ARRAY_SIZE(bnxt_tx_bytes_pri_arr) + \ ARRAY_SIZE(bnxt_tx_pkts_pri_arr)) -#define BNXT_NUM_PCIE_STATS ARRAY_SIZE(bnxt_pcie_stats_arr) static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp) { @@ -526,9 +504,6 @@ static int bnxt_get_num_stats(struct bnxt *bp) num_stats += BNXT_NUM_STATS_PRI; } - if (bp->flags & BNXT_FLAG_PCIE_STATS) - num_stats += BNXT_NUM_PCIE_STATS; - return num_stats; } @@ -584,19 +559,19 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - __le64 *hw_stats = (__le64 *)cpr->hw_stats; + u64 *sw_stats = cpr->stats.sw_stats; u64 *sw; int k; if (is_rx_ring(bp, i)) { for (k = 0; k < NUM_RING_RX_HW_STATS; j++, k++) - buf[j] = le64_to_cpu(hw_stats[k]); + buf[j] = sw_stats[k]; } if (is_tx_ring(bp, i)) { k = NUM_RING_RX_HW_STATS; for (; k < NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS; j++, k++) - buf[j] = le64_to_cpu(hw_stats[k]); + buf[j] = sw_stats[k]; } if (!tpa_stats || !is_rx_ring(bp, i)) goto skip_tpa_ring_stats; @@ -604,7 +579,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, k = NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS; for (; k < NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS + tpa_stats; j++, k++) - buf[j] = le64_to_cpu(hw_stats[k]); + buf[j] = sw_stats[k]; skip_tpa_ring_stats: sw = (u64 *)&cpr->sw_stats.rx; @@ -618,9 +593,9 @@ skip_tpa_ring_stats: buf[j] = sw[k]; bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter += - le64_to_cpu(cpr->hw_stats->rx_discard_pkts); + BNXT_GET_RING_STATS64(sw_stats, rx_discard_pkts); bnxt_sw_func_stats[TX_TOTAL_DISCARDS].counter += - le64_to_cpu(cpr->hw_stats->tx_discard_pkts); + BNXT_GET_RING_STATS64(sw_stats, tx_discard_pkts); } for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++) @@ -628,60 +603,50 @@ skip_tpa_ring_stats: skip_ring_stats: if (bp->flags & BNXT_FLAG_PORT_STATS) { - __le64 *port_stats = (__le64 *)bp->hw_rx_port_stats; + u64 *port_stats = bp->port_stats.sw_stats; - for (i = 0; i < BNXT_NUM_PORT_STATS; i++, j++) { - buf[j] = le64_to_cpu(*(port_stats + - bnxt_port_stats_arr[i].offset)); - } + for (i = 0; i < BNXT_NUM_PORT_STATS; i++, j++) + buf[j] = *(port_stats + bnxt_port_stats_arr[i].offset); } if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { - __le64 *rx_port_stats_ext = (__le64 *)bp->hw_rx_port_stats_ext; - __le64 *tx_port_stats_ext = (__le64 *)bp->hw_tx_port_stats_ext; + u64 *rx_port_stats_ext = bp->rx_port_stats_ext.sw_stats; + u64 *tx_port_stats_ext = bp->tx_port_stats_ext.sw_stats; for (i = 0; i < bp->fw_rx_stats_ext_size; i++, j++) { - buf[j] = le64_to_cpu(*(rx_port_stats_ext + - bnxt_port_stats_ext_arr[i].offset)); + buf[j] = *(rx_port_stats_ext + + bnxt_port_stats_ext_arr[i].offset); } for (i = 0; i < bp->fw_tx_stats_ext_size; i++, j++) { - buf[j] = le64_to_cpu(*(tx_port_stats_ext + - bnxt_tx_port_stats_ext_arr[i].offset)); + buf[j] = *(tx_port_stats_ext + + bnxt_tx_port_stats_ext_arr[i].offset); } if (bp->pri2cos_valid) { for (i = 0; i < 8; i++, j++) { long n = bnxt_rx_bytes_pri_arr[i].base_off + bp->pri2cos_idx[i]; - buf[j] = le64_to_cpu(*(rx_port_stats_ext + n)); + buf[j] = *(rx_port_stats_ext + n); } for (i = 0; i < 8; i++, j++) { long n = bnxt_rx_pkts_pri_arr[i].base_off + bp->pri2cos_idx[i]; - buf[j] = le64_to_cpu(*(rx_port_stats_ext + n)); + buf[j] = *(rx_port_stats_ext + n); } for (i = 0; i < 8; i++, j++) { long n = bnxt_tx_bytes_pri_arr[i].base_off + bp->pri2cos_idx[i]; - buf[j] = le64_to_cpu(*(tx_port_stats_ext + n)); + buf[j] = *(tx_port_stats_ext + n); } for (i = 0; i < 8; i++, j++) { long n = bnxt_tx_pkts_pri_arr[i].base_off + bp->pri2cos_idx[i]; - buf[j] = le64_to_cpu(*(tx_port_stats_ext + n)); + buf[j] = *(tx_port_stats_ext + n); } } } - if (bp->flags & BNXT_FLAG_PCIE_STATS) { - __le64 *pcie_stats = (__le64 *)bp->hw_pcie_stats; - - for (i = 0; i < BNXT_NUM_PCIE_STATS; i++, j++) { - buf[j] = le64_to_cpu(*(pcie_stats + - bnxt_pcie_stats_arr[i].offset)); - } - } } static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) @@ -782,12 +747,6 @@ skip_tpa_stats: } } } - if (bp->flags & BNXT_FLAG_PCIE_STATS) { - for (i = 0; i < BNXT_NUM_PCIE_STATS; i++) { - strcpy(buf, bnxt_pcie_stats_arr[i].string); - buf += ETH_GSTRING_LEN; - } - } break; case ETH_SS_TEST: if (bp->num_tests) @@ -1365,6 +1324,59 @@ static void bnxt_get_drvinfo(struct net_device *dev, info->regdump_len = 0; } +static int bnxt_get_regs_len(struct net_device *dev) +{ + struct bnxt *bp = netdev_priv(dev); + int reg_len; + + reg_len = BNXT_PXP_REG_LEN; + + if (bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED) + reg_len += sizeof(struct pcie_ctx_hw_stats); + + return reg_len; +} + +static void bnxt_get_regs(struct net_device *dev, struct ethtool_regs *regs, + void *_p) +{ + struct pcie_ctx_hw_stats *hw_pcie_stats; + struct hwrm_pcie_qstats_input req = {0}; + struct bnxt *bp = netdev_priv(dev); + dma_addr_t hw_pcie_stats_addr; + int rc; + + regs->version = 0; + bnxt_dbg_hwrm_rd_reg(bp, 0, BNXT_PXP_REG_LEN / 4, _p); + + if (!(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED)) + return; + + hw_pcie_stats = dma_alloc_coherent(&bp->pdev->dev, + sizeof(*hw_pcie_stats), + &hw_pcie_stats_addr, GFP_KERNEL); + if (!hw_pcie_stats) + return; + + regs->version = 1; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PCIE_QSTATS, -1, -1); + req.pcie_stat_size = cpu_to_le16(sizeof(*hw_pcie_stats)); + req.pcie_stat_host_addr = cpu_to_le64(hw_pcie_stats_addr); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) { + __le64 *src = (__le64 *)hw_pcie_stats; + u64 *dst = (u64 *)(_p + BNXT_PXP_REG_LEN); + int i; + + for (i = 0; i < sizeof(*hw_pcie_stats) / sizeof(__le64); i++) + dst[i] = le64_to_cpu(src[i]); + } + mutex_unlock(&bp->hwrm_cmd_lock); + dma_free_coherent(&bp->pdev->dev, sizeof(*hw_pcie_stats), hw_pcie_stats, + hw_pcie_stats_addr); +} + static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bnxt *bp = netdev_priv(dev); @@ -3640,6 +3652,8 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_pauseparam = bnxt_get_pauseparam, .set_pauseparam = bnxt_set_pauseparam, .get_drvinfo = bnxt_get_drvinfo, + .get_regs_len = bnxt_get_regs_len, + .get_regs = bnxt_get_regs, .get_wol = bnxt_get_wol, .set_wol = bnxt_set_wol, .get_coalesce = bnxt_get_coalesce, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index dddbca1d052c..34f44ddfad79 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -84,6 +84,8 @@ struct hwrm_dbg_cmn_output { ETH_RESET_PHY | ETH_RESET_RAM) \ << ETH_RESET_SHARED_SHIFT) +#define BNXT_PXP_REG_LEN 0x3110 + extern const struct ethtool_ops bnxt_ethtool_ops; u32 bnxt_get_rxfh_indir_size(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 7e9235c8d21e..c4af6bf15e36 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -169,9 +169,14 @@ struct cmd_nums { #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_SCHQ_ALLOC 0x55UL + #define HWRM_RING_SCHQ_CFG 0x56UL + #define HWRM_RING_SCHQ_FREE 0x57UL #define HWRM_RING_RESET 0x5eUL #define HWRM_RING_GRP_ALLOC 0x60UL #define HWRM_RING_GRP_FREE 0x61UL + #define HWRM_RING_CFG 0x62UL + #define HWRM_RING_QCFG 0x63UL #define HWRM_RESERVED5 0x64UL #define HWRM_RESERVED6 0x65UL #define HWRM_VNIC_RSS_COS_LB_CTX_ALLOC 0x70UL @@ -224,6 +229,7 @@ struct cmd_nums { #define HWRM_FW_IPC_MAILBOX 0xccUL #define HWRM_FW_ECN_CFG 0xcdUL #define HWRM_FW_ECN_QCFG 0xceUL + #define HWRM_FW_SECURE_CFG 0xcfUL #define HWRM_EXEC_FWD_RESP 0xd0UL #define HWRM_REJECT_FWD_RESP 0xd1UL #define HWRM_FWD_RESP 0xd2UL @@ -337,6 +343,7 @@ struct cmd_nums { #define HWRM_FUNC_VF_BW_QCFG 0x196UL #define HWRM_FUNC_HOST_PF_IDS_QUERY 0x197UL #define HWRM_FUNC_QSTATS_EXT 0x198UL + #define HWRM_STAT_EXT_CTX_QUERY 0x199UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -353,24 +360,30 @@ struct cmd_nums { #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL #define HWRM_TF_SESSION_ATTACH 0x2c7UL - #define HWRM_TF_SESSION_CLOSE 0x2c8UL - #define HWRM_TF_SESSION_QCFG 0x2c9UL - #define HWRM_TF_SESSION_RESC_QCAPS 0x2caUL - #define HWRM_TF_SESSION_RESC_ALLOC 0x2cbUL - #define HWRM_TF_SESSION_RESC_FREE 0x2ccUL - #define HWRM_TF_SESSION_RESC_FLUSH 0x2cdUL - #define HWRM_TF_TBL_TYPE_GET 0x2d0UL - #define HWRM_TF_TBL_TYPE_SET 0x2d1UL - #define HWRM_TF_CTXT_MEM_RGTR 0x2daUL - #define HWRM_TF_CTXT_MEM_UNRGTR 0x2dbUL - #define HWRM_TF_EXT_EM_QCAPS 0x2dcUL - #define HWRM_TF_EXT_EM_OP 0x2ddUL - #define HWRM_TF_EXT_EM_CFG 0x2deUL - #define HWRM_TF_EXT_EM_QCFG 0x2dfUL - #define HWRM_TF_TCAM_SET 0x2eeUL - #define HWRM_TF_TCAM_GET 0x2efUL - #define HWRM_TF_TCAM_MOVE 0x2f0UL - #define HWRM_TF_TCAM_FREE 0x2f1UL + #define HWRM_TF_SESSION_REGISTER 0x2c8UL + #define HWRM_TF_SESSION_UNREGISTER 0x2c9UL + #define HWRM_TF_SESSION_CLOSE 0x2caUL + #define HWRM_TF_SESSION_QCFG 0x2cbUL + #define HWRM_TF_SESSION_RESC_QCAPS 0x2ccUL + #define HWRM_TF_SESSION_RESC_ALLOC 0x2cdUL + #define HWRM_TF_SESSION_RESC_FREE 0x2ceUL + #define HWRM_TF_SESSION_RESC_FLUSH 0x2cfUL + #define HWRM_TF_TBL_TYPE_GET 0x2daUL + #define HWRM_TF_TBL_TYPE_SET 0x2dbUL + #define HWRM_TF_CTXT_MEM_RGTR 0x2e4UL + #define HWRM_TF_CTXT_MEM_UNRGTR 0x2e5UL + #define HWRM_TF_EXT_EM_QCAPS 0x2e6UL + #define HWRM_TF_EXT_EM_OP 0x2e7UL + #define HWRM_TF_EXT_EM_CFG 0x2e8UL + #define HWRM_TF_EXT_EM_QCFG 0x2e9UL + #define HWRM_TF_EM_INSERT 0x2eaUL + #define HWRM_TF_EM_DELETE 0x2ebUL + #define HWRM_TF_TCAM_SET 0x2f8UL + #define HWRM_TF_TCAM_GET 0x2f9UL + #define HWRM_TF_TCAM_MOVE 0x2faUL + #define HWRM_TF_TCAM_FREE 0x2fbUL + #define HWRM_TF_GLOBAL_CFG_SET 0x2fcUL + #define HWRM_TF_GLOBAL_CFG_GET 0x2fdUL #define HWRM_SV 0x400UL #define HWRM_DBG_READ_DIRECT 0xff10UL #define HWRM_DBG_READ_INDIRECT 0xff11UL @@ -391,6 +404,7 @@ struct cmd_nums { #define HWRM_DBG_QCAPS 0xff20UL #define HWRM_DBG_QCFG 0xff21UL #define HWRM_DBG_CRASHDUMP_MEDIUM_CFG 0xff22UL + #define HWRM_NVM_REQ_ARBITRATION 0xffedUL #define HWRM_NVM_FACTORY_DEFAULTS 0xffeeUL #define HWRM_NVM_VALIDATE_OPTION 0xffefUL #define HWRM_NVM_FLUSH 0xfff0UL @@ -464,8 +478,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 1 -#define HWRM_VERSION_RSVD 33 -#define HWRM_VERSION_STR "1.10.1.33" +#define HWRM_VERSION_RSVD 54 +#define HWRM_VERSION_STR "1.10.1.54" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -1094,6 +1108,8 @@ struct hwrm_func_vf_cfg_input { #define FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST 0x20UL #define FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST 0x40UL #define FUNC_VF_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST 0x80UL + #define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE 0x100UL + #define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE 0x200UL __le16 num_rsscos_ctxs; __le16 num_cmpl_rings; __le16 num_tx_rings; @@ -1189,10 +1205,16 @@ struct hwrm_func_qcaps_output { __le16 max_sp_tx_rings; u8 unused_0[2]; __le32 flags_ext; - #define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED 0x1UL - #define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED 0x2UL - #define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED 0x4UL - u8 unused_1[3]; + #define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED 0x1UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED 0x2UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED 0x4UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT 0x8UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PROXY_MODE_SUPPORT 0x10UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_TX_PROXY_SRC_INTF_OVERRIDE_SUPPORT 0x20UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_SCHQ_SUPPORTED 0x40UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PPP_PUSH_MODE_SUPPORTED 0x80UL + u8 max_schqs; + u8 unused_1[2]; u8 valid; }; @@ -1226,6 +1248,8 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF 0x40UL #define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED 0x80UL #define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS 0x100UL + #define FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED 0x200UL + #define FUNC_QCFG_RESP_FLAGS_PPP_PUSH_MODE_ENABLED 0x400UL u8 mac_address[6]; __le16 pci_id; __le16 alloc_rsscos_ctx; @@ -1321,7 +1345,7 @@ struct hwrm_func_qcfg_output { u8 valid; }; -/* hwrm_func_cfg_input (size:704b/88B) */ +/* hwrm_func_cfg_input (size:768b/96B) */ struct hwrm_func_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -1352,30 +1376,35 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST 0x800000UL #define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE 0x1000000UL #define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS 0x2000000UL + #define FUNC_CFG_REQ_FLAGS_HOT_RESET_IF_EN_DIS 0x4000000UL + #define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE 0x8000000UL + #define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE 0x10000000UL __le32 enables; - #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL - #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL - #define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS 0x4UL - #define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS 0x8UL - #define FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS 0x10UL - #define FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS 0x20UL - #define FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS 0x40UL - #define FUNC_CFG_REQ_ENABLES_NUM_VNICS 0x80UL - #define FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS 0x100UL - #define FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR 0x200UL - #define FUNC_CFG_REQ_ENABLES_DFLT_VLAN 0x400UL - #define FUNC_CFG_REQ_ENABLES_DFLT_IP_ADDR 0x800UL - #define FUNC_CFG_REQ_ENABLES_MIN_BW 0x1000UL - #define FUNC_CFG_REQ_ENABLES_MAX_BW 0x2000UL - #define FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR 0x4000UL - #define FUNC_CFG_REQ_ENABLES_VLAN_ANTISPOOF_MODE 0x8000UL - #define FUNC_CFG_REQ_ENABLES_ALLOWED_VLAN_PRIS 0x10000UL - #define FUNC_CFG_REQ_ENABLES_EVB_MODE 0x20000UL - #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 + #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL + #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL + #define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS 0x4UL + #define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS 0x8UL + #define FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS 0x10UL + #define FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS 0x20UL + #define FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS 0x40UL + #define FUNC_CFG_REQ_ENABLES_NUM_VNICS 0x80UL + #define FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS 0x100UL + #define FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR 0x200UL + #define FUNC_CFG_REQ_ENABLES_DFLT_VLAN 0x400UL + #define FUNC_CFG_REQ_ENABLES_DFLT_IP_ADDR 0x800UL + #define FUNC_CFG_REQ_ENABLES_MIN_BW 0x1000UL + #define FUNC_CFG_REQ_ENABLES_MAX_BW 0x2000UL + #define FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR 0x4000UL + #define FUNC_CFG_REQ_ENABLES_VLAN_ANTISPOOF_MODE 0x8000UL + #define FUNC_CFG_REQ_ENABLES_ALLOWED_VLAN_PRIS 0x10000UL + #define FUNC_CFG_REQ_ENABLES_EVB_MODE 0x20000UL + #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 + #define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT 0x800000UL + #define FUNC_CFG_REQ_ENABLES_SCHQ_ID 0x1000000UL __le16 mtu; __le16 mru; __le16 num_rsscos_ctxs; @@ -1449,6 +1478,8 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_OPTIONS_RSVD_MASK 0xf0UL #define FUNC_CFG_REQ_OPTIONS_RSVD_SFT 4 __le16 num_mcast_filters; + __le16 schq_id; + u8 unused_0[6]; }; /* hwrm_func_cfg_output (size:128b/16B) */ @@ -1507,7 +1538,7 @@ struct hwrm_func_qstats_output { u8 valid; }; -/* hwrm_func_qstats_ext_input (size:192b/24B) */ +/* hwrm_func_qstats_ext_input (size:256b/32B) */ struct hwrm_func_qstats_ext_input { __le16 req_type; __le16 cmpl_ring; @@ -1520,7 +1551,12 @@ struct hwrm_func_qstats_ext_input { #define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY 0x1UL #define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x2UL #define FUNC_QSTATS_EXT_REQ_FLAGS_LAST FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK - u8 unused_0[5]; + u8 unused_0[1]; + __le32 enables; + #define FUNC_QSTATS_EXT_REQ_ENABLES_SCHQ_ID 0x1UL + __le16 schq_id; + __le16 traffic_class; + u8 unused_1[4]; }; /* hwrm_func_qstats_ext_output (size:1472b/184B) */ @@ -1533,15 +1569,15 @@ struct hwrm_func_qstats_ext_output { __le64 rx_mcast_pkts; __le64 rx_bcast_pkts; __le64 rx_discard_pkts; - __le64 rx_drop_pkts; + __le64 rx_error_pkts; __le64 rx_ucast_bytes; __le64 rx_mcast_bytes; __le64 rx_bcast_bytes; __le64 tx_ucast_pkts; __le64 tx_mcast_pkts; __le64 tx_bcast_pkts; + __le64 tx_error_pkts; __le64 tx_discard_pkts; - __le64 tx_drop_pkts; __le64 tx_ucast_bytes; __le64 tx_mcast_bytes; __le64 tx_bcast_bytes; @@ -2376,33 +2412,39 @@ struct hwrm_port_phy_cfg_input { __le16 target_id; __le64 resp_addr; __le32 flags; - #define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY 0x1UL - #define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED 0x2UL - #define PORT_PHY_CFG_REQ_FLAGS_FORCE 0x4UL - #define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG 0x8UL - #define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE 0x10UL - #define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE 0x20UL - #define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE 0x40UL - #define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE 0x80UL - #define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE 0x100UL - #define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE 0x200UL - #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE 0x400UL - #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE 0x800UL - #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE 0x1000UL - #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE 0x2000UL - #define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN 0x4000UL + #define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY 0x1UL + #define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED 0x2UL + #define PORT_PHY_CFG_REQ_FLAGS_FORCE 0x4UL + #define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG 0x8UL + #define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE 0x10UL + #define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE 0x20UL + #define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE 0x40UL + #define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE 0x80UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE 0x100UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE 0x200UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE 0x400UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE 0x800UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE 0x1000UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE 0x2000UL + #define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN 0x4000UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE 0x8000UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE 0x10000UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_2XN_ENABLE 0x20000UL + #define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_2XN_DISABLE 0x40000UL __le32 enables; - #define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE 0x1UL - #define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX 0x2UL - #define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE 0x4UL - #define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED 0x8UL - #define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK 0x10UL - #define PORT_PHY_CFG_REQ_ENABLES_WIRESPEED 0x20UL - #define PORT_PHY_CFG_REQ_ENABLES_LPBK 0x40UL - #define PORT_PHY_CFG_REQ_ENABLES_PREEMPHASIS 0x80UL - #define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE 0x100UL - #define PORT_PHY_CFG_REQ_ENABLES_EEE_LINK_SPEED_MASK 0x200UL - #define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER 0x400UL + #define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE 0x1UL + #define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX 0x2UL + #define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE 0x4UL + #define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED 0x8UL + #define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK 0x10UL + #define PORT_PHY_CFG_REQ_ENABLES_WIRESPEED 0x20UL + #define PORT_PHY_CFG_REQ_ENABLES_LPBK 0x40UL + #define PORT_PHY_CFG_REQ_ENABLES_PREEMPHASIS 0x80UL + #define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE 0x100UL + #define PORT_PHY_CFG_REQ_ENABLES_EEE_LINK_SPEED_MASK 0x200UL + #define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER 0x400UL + #define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED 0x800UL + #define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK 0x1000UL __le16 port_id; __le16 force_link_speed; #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL @@ -2415,7 +2457,6 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB 0x190UL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB 0x1f4UL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB 0x3e8UL - #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_200GB 0x7d0UL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB 0xffffUL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB u8 auto_mode; @@ -2446,7 +2487,6 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_40GB 0x190UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB 0x1f4UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB 0x3e8UL - #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_200GB 0x7d0UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB 0xffffUL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_LAST PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB __le16 auto_link_speed_mask; @@ -2464,7 +2504,6 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100GB 0x800UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MBHD 0x1000UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MB 0x2000UL - #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_200GB 0x4000UL u8 wirespeed; #define PORT_PHY_CFG_REQ_WIRESPEED_OFF 0x0UL #define PORT_PHY_CFG_REQ_WIRESPEED_ON 0x1UL @@ -2488,11 +2527,19 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD3 0x10UL #define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD4 0x20UL #define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_10GB 0x40UL - u8 unused_2[2]; + __le16 force_pam4_link_speed; + #define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB 0x1f4UL + #define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL + #define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL + #define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB __le32 tx_lpi_timer; #define PORT_PHY_CFG_REQ_TX_LPI_TIMER_MASK 0xffffffUL #define PORT_PHY_CFG_REQ_TX_LPI_TIMER_SFT 0 - __le32 unused_3; + __le16 auto_link_pam4_speed_mask; + #define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G 0x1UL + #define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G 0x2UL + #define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G 0x4UL + u8 unused_2[2]; }; /* hwrm_port_phy_cfg_output (size:128b/16B) */ @@ -2526,7 +2573,7 @@ struct hwrm_port_phy_qcfg_input { u8 unused_0[6]; }; -/* hwrm_port_phy_qcfg_output (size:768b/96B) */ +/* hwrm_port_phy_qcfg_output (size:832b/104B) */ struct hwrm_port_phy_qcfg_output { __le16 error_code; __le16 req_type; @@ -2537,7 +2584,10 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_LINK_SIGNAL 0x1UL #define PORT_PHY_QCFG_RESP_LINK_LINK 0x2UL #define PORT_PHY_QCFG_RESP_LINK_LAST PORT_PHY_QCFG_RESP_LINK_LINK - u8 unused_0; + u8 link_signal_mode; + #define PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_NRZ 0x0UL + #define PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_PAM4 0x1UL + #define PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_LAST PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_PAM4 __le16 link_speed; #define PORT_PHY_QCFG_RESP_LINK_SPEED_100MB 0x1UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_1GB 0xaUL @@ -2574,7 +2624,6 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB 0x800UL #define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MBHD 0x1000UL #define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MB 0x2000UL - #define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_200GB 0x4000UL __le16 force_link_speed; #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100MB 0x1UL #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_1GB 0xaUL @@ -2586,7 +2635,6 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_40GB 0x190UL #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_50GB 0x1f4UL #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100GB 0x3e8UL - #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_200GB 0x7d0UL #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB 0xffffUL #define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB u8 auto_mode; @@ -2611,7 +2659,6 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_40GB 0x190UL #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_50GB 0x1f4UL #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100GB 0x3e8UL - #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_200GB 0x7d0UL #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB 0xffffUL #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB __le16 auto_link_speed_mask; @@ -2629,7 +2676,6 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100GB 0x800UL #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MBHD 0x1000UL #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MB 0x2000UL - #define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_200GB 0x4000UL u8 wirespeed; #define PORT_PHY_QCFG_RESP_WIRESPEED_OFF 0x0UL #define PORT_PHY_QCFG_RESP_WIRESPEED_ON 0x1UL @@ -2763,13 +2809,21 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28 (0x11UL << 24) #define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28 __le16 fec_cfg; - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED 0x1UL - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED 0x2UL - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED 0x4UL - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED 0x8UL - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED 0x10UL - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED 0x20UL - #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED 0x40UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED 0x1UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED 0x2UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED 0x4UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED 0x8UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED 0x10UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED 0x20UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED 0x40UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED 0x80UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED 0x100UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_2XN_SUPPORTED 0x200UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_2XN_ENABLED 0x400UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ACTIVE 0x800UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ACTIVE 0x1000UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ACTIVE 0x2000UL + #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_2XN_ACTIVE 0x4000UL u8 duplex_state; #define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL #define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL @@ -2778,7 +2832,24 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT 0x1UL char phy_vendor_name[16]; char phy_vendor_partnumber[16]; - u8 unused_2[7]; + __le16 support_pam4_speeds; + #define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G 0x1UL + #define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G 0x2UL + #define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G 0x4UL + __le16 force_pam4_link_speed; + #define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_50GB 0x1f4UL + #define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL + #define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL + #define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB + __le16 auto_pam4_link_speed_mask; + #define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_50G 0x1UL + #define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_100G 0x2UL + #define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_200G 0x4UL + __le16 link_partner_pam4_adv_speeds; + #define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB 0x1UL + #define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB 0x2UL + #define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB 0x4UL + u8 unused_0[7]; u8 valid; }; @@ -3304,19 +3375,20 @@ struct hwrm_port_phy_qcaps_input { u8 unused_0[6]; }; -/* hwrm_port_phy_qcaps_output (size:192b/24B) */ +/* hwrm_port_phy_qcaps_output (size:256b/32B) */ struct hwrm_port_phy_qcaps_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; u8 flags; - #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_AUTONEG_LPBK_SUPPORTED 0x4UL - #define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED 0x8UL - #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK 0xf0UL - #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT 4 + #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_AUTONEG_LPBK_SUPPORTED 0x4UL + #define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED 0x8UL + #define PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET 0x10UL + #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK 0xe0UL + #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT 5 u8 port_cnt; #define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL #define PORT_PHY_QCAPS_RESP_PORT_CNT_1 0x1UL @@ -3339,7 +3411,6 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB 0x800UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD 0x1000UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB 0x2000UL - #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_200GB 0x4000UL __le16 supported_speeds_auto_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB 0x2UL @@ -3355,7 +3426,6 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB 0x800UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD 0x1000UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB 0x2000UL - #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_200GB 0x4000UL __le16 supported_speeds_eee_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB 0x2UL @@ -3372,8 +3442,18 @@ struct hwrm_port_phy_qcaps_output { __le32 valid_tx_lpi_timer_high; #define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK 0xffffffUL #define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_SFT 0 - #define PORT_PHY_QCAPS_RESP_VALID_MASK 0xff000000UL - #define PORT_PHY_QCAPS_RESP_VALID_SFT 24 + #define PORT_PHY_QCAPS_RESP_RSVD_MASK 0xff000000UL + #define PORT_PHY_QCAPS_RESP_RSVD_SFT 24 + __le16 supported_pam4_speeds_auto_mode; + #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_50G 0x1UL + #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_100G 0x2UL + #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_200G 0x4UL + __le16 supported_pam4_speeds_force_mode; + #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_50G 0x1UL + #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G 0x2UL + #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G 0x4UL + u8 unused_0[3]; + u8 valid; }; /* hwrm_port_phy_i2c_read_input (size:320b/40B) */ @@ -3812,7 +3892,7 @@ struct hwrm_queue_qportcfg_input { u8 unused_0; }; -/* hwrm_queue_qportcfg_output (size:256b/32B) */ +/* hwrm_queue_qportcfg_output (size:1344b/168B) */ struct hwrm_queue_qportcfg_output { __le16 error_code; __le16 req_type; @@ -3898,6 +3978,49 @@ struct hwrm_queue_qportcfg_output { #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC 0x3UL #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN 0xffUL #define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LAST QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN + u8 unused_0; + char qid0_name[16]; + char qid1_name[16]; + char qid2_name[16]; + char qid3_name[16]; + char qid4_name[16]; + char qid5_name[16]; + char qid6_name[16]; + char qid7_name[16]; + u8 unused_1[7]; + u8 valid; +}; + +/* hwrm_queue_qcfg_input (size:192b/24B) */ +struct hwrm_queue_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 flags; + #define QUEUE_QCFG_REQ_FLAGS_PATH 0x1UL + #define QUEUE_QCFG_REQ_FLAGS_PATH_TX 0x0UL + #define QUEUE_QCFG_REQ_FLAGS_PATH_RX 0x1UL + #define QUEUE_QCFG_REQ_FLAGS_PATH_LAST QUEUE_QCFG_REQ_FLAGS_PATH_RX + __le32 queue_id; +}; + +/* hwrm_queue_qcfg_output (size:128b/16B) */ +struct hwrm_queue_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 queue_len; + u8 service_profile; + #define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSY 0x0UL + #define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSLESS 0x1UL + #define QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN 0xffUL + #define QUEUE_QCFG_RESP_SERVICE_PROFILE_LAST QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN + u8 queue_cfg_info; + #define QUEUE_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG 0x1UL + u8 unused_0; u8 valid; }; @@ -4938,6 +5061,7 @@ struct hwrm_vnic_cfg_input { #define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID 0x20UL #define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID 0x40UL #define VNIC_CFG_REQ_ENABLES_QUEUE_ID 0x80UL + #define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE 0x100UL __le16 vnic_id; __le16 dflt_ring_grp; __le16 rss_rule; @@ -4947,7 +5071,12 @@ struct hwrm_vnic_cfg_input { __le16 default_rx_ring_id; __le16 default_cmpl_ring_id; __le16 queue_id; - u8 unused0[6]; + u8 rx_csum_v2_mode; + #define VNIC_CFG_REQ_RX_CSUM_V2_MODE_DEFAULT 0x0UL + #define VNIC_CFG_REQ_RX_CSUM_V2_MODE_ALL_OK 0x1UL + #define VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX 0x2UL + #define VNIC_CFG_REQ_RX_CSUM_V2_MODE_LAST VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX + u8 unused0[5]; }; /* hwrm_vnic_cfg_output (size:128b/16B) */ @@ -4989,6 +5118,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP 0x40UL #define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP 0x80UL #define VNIC_QCAPS_RESP_FLAGS_COS_ASSIGNMENT_CAP 0x100UL + #define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V2_CAP 0x200UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -5155,15 +5285,18 @@ struct hwrm_vnic_plcmodes_cfg_input { #define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6 0x8UL #define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_FCOE 0x10UL #define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_ROCE 0x20UL + #define VNIC_PLCMODES_CFG_REQ_FLAGS_VIRTIO_PLACEMENT 0x40UL __le32 enables; #define VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID 0x1UL #define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_OFFSET_VALID 0x2UL #define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID 0x4UL + #define VNIC_PLCMODES_CFG_REQ_ENABLES_MAX_BDS_VALID 0x8UL __le32 vnic_id; __le16 jumbo_thresh; __le16 hds_offset; __le16 hds_threshold; - u8 unused_0[6]; + __le16 max_bds; + u8 unused_0[4]; }; /* hwrm_vnic_plcmodes_cfg_output (size:128b/16B) */ @@ -5231,6 +5364,7 @@ struct hwrm_ring_alloc_input { #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 + #define RING_ALLOC_REQ_ENABLES_SCHQ_ID 0x200UL u8 ring_type; #define RING_ALLOC_REQ_RING_TYPE_L2_CMPL 0x0UL #define RING_ALLOC_REQ_RING_TYPE_TX 0x1UL @@ -5246,7 +5380,7 @@ struct hwrm_ring_alloc_input { __le32 fbo; u8 page_size; u8 page_tbl_depth; - u8 unused_1[2]; + __le16 schq_id; __le32 length; __le16 logical_id; __le16 cmpl_ring_id; @@ -5344,11 +5478,12 @@ struct hwrm_ring_reset_input { __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 + #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_RX_RING_GRP 0x6UL + #define RING_RESET_REQ_RING_TYPE_LAST RING_RESET_REQ_RING_TYPE_RX_RING_GRP u8 unused_0; __le16 ring_id; u8 unused_1[4]; @@ -5529,6 +5664,7 @@ struct hwrm_ring_grp_free_output { u8 unused_0[7]; u8 valid; }; + #define DEFAULT_FLOW_ID 0xFFFFFFFFUL #define ROCEV1_FLOW_ID 0xFFFFFFFEUL #define ROCEV2_FLOW_ID 0xFFFFFFFDUL @@ -6816,15 +6952,15 @@ struct ctx_hw_stats { __le64 rx_mcast_pkts; __le64 rx_bcast_pkts; __le64 rx_discard_pkts; - __le64 rx_drop_pkts; + __le64 rx_error_pkts; __le64 rx_ucast_bytes; __le64 rx_mcast_bytes; __le64 rx_bcast_bytes; __le64 tx_ucast_pkts; __le64 tx_mcast_pkts; __le64 tx_bcast_pkts; + __le64 tx_error_pkts; __le64 tx_discard_pkts; - __le64 tx_drop_pkts; __le64 tx_ucast_bytes; __le64 tx_mcast_bytes; __le64 tx_bcast_bytes; @@ -6840,15 +6976,15 @@ struct ctx_hw_stats_ext { __le64 rx_mcast_pkts; __le64 rx_bcast_pkts; __le64 rx_discard_pkts; - __le64 rx_drop_pkts; + __le64 rx_error_pkts; __le64 rx_ucast_bytes; __le64 rx_mcast_bytes; __le64 rx_bcast_bytes; __le64 tx_ucast_pkts; __le64 tx_mcast_pkts; __le64 tx_bcast_pkts; + __le64 tx_error_pkts; __le64 tx_discard_pkts; - __le64 tx_drop_pkts; __le64 tx_ucast_bytes; __le64 tx_mcast_bytes; __le64 tx_bcast_bytes; @@ -6915,7 +7051,9 @@ struct hwrm_stat_ctx_query_input { __le16 target_id; __le64 resp_addr; __le32 stat_ctx_id; - u8 unused_0[4]; + u8 flags; + #define STAT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK 0x1UL + u8 unused_0[3]; }; /* hwrm_stat_ctx_query_output (size:1408b/176B) */ @@ -6948,6 +7086,50 @@ struct hwrm_stat_ctx_query_output { u8 valid; }; +/* hwrm_stat_ext_ctx_query_input (size:192b/24B) */ +struct hwrm_stat_ext_ctx_query_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 stat_ctx_id; + u8 flags; + #define STAT_EXT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK 0x1UL + u8 unused_0[3]; +}; + +/* hwrm_stat_ext_ctx_query_output (size:1472b/184B) */ +struct hwrm_stat_ext_ctx_query_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le64 rx_ucast_pkts; + __le64 rx_mcast_pkts; + __le64 rx_bcast_pkts; + __le64 rx_discard_pkts; + __le64 rx_error_pkts; + __le64 rx_ucast_bytes; + __le64 rx_mcast_bytes; + __le64 rx_bcast_bytes; + __le64 tx_ucast_pkts; + __le64 tx_mcast_pkts; + __le64 tx_bcast_pkts; + __le64 tx_error_pkts; + __le64 tx_discard_pkts; + __le64 tx_ucast_bytes; + __le64 tx_mcast_bytes; + __le64 tx_bcast_bytes; + __le64 rx_tpa_eligible_pkt; + __le64 rx_tpa_eligible_bytes; + __le64 rx_tpa_pkt; + __le64 rx_tpa_bytes; + __le64 rx_tpa_errors; + u8 unused_0[7]; + u8 valid; +}; + /* hwrm_stat_ctx_clr_stats_input (size:192b/24B) */ struct hwrm_stat_ctx_clr_stats_input { __le16 req_type; @@ -7497,6 +7679,29 @@ struct hwrm_wol_reason_qcfg_output { u8 valid; }; +/* hwrm_dbg_read_direct_input (size:256b/32B) */ +struct hwrm_dbg_read_direct_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 host_dest_addr; + __le32 read_addr; + __le32 read_len32; +}; + +/* hwrm_dbg_read_direct_output (size:128b/16B) */ +struct hwrm_dbg_read_direct_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 crc32; + u8 unused_0[3]; + u8 valid; +}; + /* coredump_segment_record (size:128b/16B) */ struct coredump_segment_record { __le16 component_id; @@ -7507,7 +7712,8 @@ struct coredump_segment_record { u8 seg_flags; u8 compress_flags; #define SFLAG_COMPRESSED_ZLIB 0x1UL - u8 unused_0[6]; + u8 unused_0[2]; + __le32 segment_len; }; /* hwrm_dbg_coredump_list_input (size:256b/32B) */ @@ -7620,7 +7826,8 @@ struct hwrm_dbg_ring_info_get_input { #define DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL 0x0UL #define DBG_RING_INFO_GET_REQ_RING_TYPE_TX 0x1UL #define DBG_RING_INFO_GET_REQ_RING_TYPE_RX 0x2UL - #define DBG_RING_INFO_GET_REQ_RING_TYPE_LAST DBG_RING_INFO_GET_REQ_RING_TYPE_RX + #define DBG_RING_INFO_GET_REQ_RING_TYPE_NQ 0x3UL + #define DBG_RING_INFO_GET_REQ_RING_TYPE_LAST DBG_RING_INFO_GET_REQ_RING_TYPE_NQ u8 unused_0[3]; __le32 fw_ring_id; }; @@ -7633,7 +7840,8 @@ struct hwrm_dbg_ring_info_get_output { __le16 resp_len; __le32 producer_index; __le32 consumer_index; - u8 unused_0[7]; + __le32 cag_vector_ctrl; + u8 unused_0[3]; u8 valid; }; @@ -7922,6 +8130,7 @@ struct hwrm_nvm_install_update_input { #define NVM_INSTALL_UPDATE_REQ_FLAGS_ERASE_UNUSED_SPACE 0x1UL #define NVM_INSTALL_UPDATE_REQ_FLAGS_REMOVE_UNUSED_PKG 0x2UL #define NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG 0x4UL + #define NVM_INSTALL_UPDATE_REQ_FLAGS_VERIFY_ONLY 0x8UL u8 unused_0[2]; }; @@ -8101,7 +8310,14 @@ struct hwrm_selftest_qlist_output { char test5_name[32]; char test6_name[32]; char test7_name[32]; - u8 unused_2[7]; + u8 eyescope_target_BER_support; + #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED 0x0UL + #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED 0x1UL + #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E10_SUPPORTED 0x2UL + #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E11_SUPPORTED 0x3UL + #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED 0x4UL + #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_LAST SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED + u8 unused_2[6]; u8 valid; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 392e32c7122a..cc2ee4d0bd18 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1029,7 +1029,7 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) rc = bnxt_hwrm_exec_fwd_resp( bp, vf, sizeof(struct hwrm_port_phy_qcfg_input)); } else { - struct hwrm_port_phy_qcfg_output phy_qcfg_resp; + struct hwrm_port_phy_qcfg_output_compat phy_qcfg_resp = {0}; struct hwrm_port_phy_qcfg_input *phy_qcfg_req; phy_qcfg_req = diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 43d11c38b38a..4cddd628d41b 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1167,7 +1167,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct) oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) & CN23XX_PCIE_SRIOV_FDL_MASK); } else { - ret = EINVAL; + ret = -EINVAL; /* Under some virtual environments, extended PCI regs are * inaccessible, in which case the above read will have failed. diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index 934115d18488..ac32facaa427 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -1056,7 +1056,7 @@ void octeon_delete_dispatch_list(struct octeon_device *oct) list_for_each_safe(temp, tmp2, &freelist) { list_del(temp); - vfree(temp); + kfree(temp); } } @@ -1152,13 +1152,10 @@ octeon_register_dispatch_fn(struct octeon_device *oct, dev_dbg(&oct->pci_dev->dev, "Adding opcode to dispatch list linked list\n"); - dispatch = (struct octeon_dispatch *) - vmalloc(sizeof(struct octeon_dispatch)); - if (!dispatch) { - dev_err(&oct->pci_dev->dev, - "No memory to add dispatch function\n"); + dispatch = kmalloc(sizeof(*dispatch), GFP_KERNEL); + if (!dispatch) return 1; - } + dispatch->opcode = combined_opcode; dispatch->dispatch_fn = fn; dispatch->arg = fn_arg; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index adbc0d088070..9cb8b229c1b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1438,6 +1438,8 @@ enum { NAT_MODE_ALL /* NAT on entire 4-tuple */ }; +#define CXGB4_FILTER_TYPE_MAX 2 + /* Host shadow copy of ingress filter entry. This is in host native format * and doesn't match the ordering or bit order, etc. of the hardware of the * firmware command. The use of bit-field structure elements is purely to diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 12ef9ddd1e54..9f3173f86eed 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -31,7 +31,7 @@ enum cxgb4_ethtool_tests { }; static const char cxgb4_selftest_strings[CXGB4_ETHTOOL_MAX_TEST][ETH_GSTRING_LEN] = { - "Loop back test", + "Loop back test (offline)", }; static const char * const flash_region_strings[] = { @@ -2095,12 +2095,13 @@ static void cxgb4_self_test(struct net_device *netdev, memset(data, 0, sizeof(u64) * CXGB4_ETHTOOL_MAX_TEST); - if (!(adap->flags & CXGB4_FW_OK)) { + if (!(adap->flags & CXGB4_FULL_INIT_DONE) || + !(adap->flags & CXGB4_FW_OK)) { eth_test->flags |= ETH_TEST_FL_FAILED; return; } - if (eth_test->flags == ETH_TEST_FL_OFFLINE) + if (eth_test->flags & ETH_TEST_FL_OFFLINE) cxgb4_lb_test(netdev, &data[CXGB4_ETHTOOL_LB_TEST]); if (data[CXGB4_ETHTOOL_LB_TEST]) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 6251444ffa58..f642c1b475c4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -80,6 +80,19 @@ static void cxgb4_process_flow_match(struct net_device *dev, struct flow_rule *rule, struct ch_filter_specification *fs) { + u16 addr_type = 0; + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { struct flow_match_basic match; u16 ethtype_key, ethtype_mask; @@ -102,7 +115,7 @@ static void cxgb4_process_flow_match(struct net_device *dev, fs->mask.proto = match.mask->ip_proto; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_match_ipv4_addrs match; flow_rule_match_ipv4_addrs(rule, &match); @@ -117,7 +130,7 @@ static void cxgb4_process_flow_match(struct net_device *dev, memcpy(&fs->nat_fip[0], &match.key->src, sizeof(match.key->src)); } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { struct flow_match_ipv6_addrs match; flow_rule_match_ipv6_addrs(rule, &match); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c index e377e50c2492..2e309f6673f7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c @@ -231,8 +231,26 @@ static void cxgb4_matchall_mirror_free(struct net_device *dev) tc_port_matchall->ingress.viid_mirror = 0; } -static int cxgb4_matchall_alloc_filter(struct net_device *dev, - struct tc_cls_matchall_offload *cls) +static int cxgb4_matchall_del_filter(struct net_device *dev, u8 filter_type) +{ + struct cxgb4_tc_port_matchall *tc_port_matchall; + struct port_info *pi = netdev2pinfo(dev); + struct adapter *adap = netdev2adap(dev); + int ret; + + tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id]; + ret = cxgb4_del_filter(dev, tc_port_matchall->ingress.tid[filter_type], + &tc_port_matchall->ingress.fs[filter_type]); + if (ret) + return ret; + + tc_port_matchall->ingress.tid[filter_type] = 0; + return 0; +} + +static int cxgb4_matchall_add_filter(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + u8 filter_type) { struct netlink_ext_ack *extack = cls->common.extack; struct cxgb4_tc_port_matchall *tc_port_matchall; @@ -244,28 +262,24 @@ static int cxgb4_matchall_alloc_filter(struct net_device *dev, /* Get a free filter entry TID, where we can insert this new * rule. Only insert rule if its prio doesn't conflict with * existing rules. - * - * 1 slot is enough to create a wildcard matchall VIID rule. */ - fidx = cxgb4_get_free_ftid(dev, PF_INET, false, cls->common.prio); + fidx = cxgb4_get_free_ftid(dev, filter_type ? PF_INET6 : PF_INET, + false, cls->common.prio); if (fidx < 0) { NL_SET_ERR_MSG_MOD(extack, "No free LETCAM index available"); return -ENOMEM; } - ret = cxgb4_matchall_mirror_alloc(dev, cls); - if (ret) - return ret; - tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id]; - fs = &tc_port_matchall->ingress.fs; + fs = &tc_port_matchall->ingress.fs[filter_type]; memset(fs, 0, sizeof(*fs)); if (fidx < adap->tids.nhpftids) fs->prio = 1; fs->tc_prio = cls->common.prio; fs->tc_cookie = cls->cookie; + fs->type = filter_type; fs->hitcnts = 1; fs->val.pfvf_vld = 1; @@ -276,13 +290,39 @@ static int cxgb4_matchall_alloc_filter(struct net_device *dev, ret = cxgb4_set_filter(dev, fidx, fs); if (ret) - goto out_free; + return ret; + + tc_port_matchall->ingress.tid[filter_type] = fidx; + return 0; +} + +static int cxgb4_matchall_alloc_filter(struct net_device *dev, + struct tc_cls_matchall_offload *cls) +{ + struct cxgb4_tc_port_matchall *tc_port_matchall; + struct port_info *pi = netdev2pinfo(dev); + struct adapter *adap = netdev2adap(dev); + int ret, i; + + tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id]; + + ret = cxgb4_matchall_mirror_alloc(dev, cls); + if (ret) + return ret; + + for (i = 0; i < CXGB4_FILTER_TYPE_MAX; i++) { + ret = cxgb4_matchall_add_filter(dev, cls, i); + if (ret) + goto out_free; + } - tc_port_matchall->ingress.tid = fidx; tc_port_matchall->ingress.state = CXGB4_MATCHALL_STATE_ENABLED; return 0; out_free: + while (i-- > 0) + cxgb4_matchall_del_filter(dev, i); + cxgb4_matchall_mirror_free(dev); return ret; } @@ -293,20 +333,21 @@ static int cxgb4_matchall_free_filter(struct net_device *dev) struct port_info *pi = netdev2pinfo(dev); struct adapter *adap = netdev2adap(dev); int ret; + u8 i; tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id]; - ret = cxgb4_del_filter(dev, tc_port_matchall->ingress.tid, - &tc_port_matchall->ingress.fs); - if (ret) - return ret; + for (i = 0; i < CXGB4_FILTER_TYPE_MAX; i++) { + ret = cxgb4_matchall_del_filter(dev, i); + if (ret) + return ret; + } cxgb4_matchall_mirror_free(dev); tc_port_matchall->ingress.packets = 0; tc_port_matchall->ingress.bytes = 0; tc_port_matchall->ingress.last_used = 0; - tc_port_matchall->ingress.tid = 0; tc_port_matchall->ingress.state = CXGB4_MATCHALL_STATE_DISABLED; return 0; } @@ -362,8 +403,12 @@ int cxgb4_tc_matchall_destroy(struct net_device *dev, tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id]; if (ingress) { + /* All the filter types of this matchall rule save the + * same cookie. So, checking for the first one is + * enough. + */ if (cls_matchall->cookie != - tc_port_matchall->ingress.fs.tc_cookie) + tc_port_matchall->ingress.fs[0].tc_cookie) return -ENOENT; return cxgb4_matchall_free_filter(dev); @@ -379,21 +424,29 @@ int cxgb4_tc_matchall_destroy(struct net_device *dev, int cxgb4_tc_matchall_stats(struct net_device *dev, struct tc_cls_matchall_offload *cls_matchall) { + u64 tmp_packets, tmp_bytes, packets = 0, bytes = 0; struct cxgb4_tc_port_matchall *tc_port_matchall; + struct cxgb4_matchall_ingress_entry *ingress; struct port_info *pi = netdev2pinfo(dev); struct adapter *adap = netdev2adap(dev); - u64 packets, bytes; int ret; + u8 i; tc_port_matchall = &adap->tc_matchall->port_matchall[pi->port_id]; if (tc_port_matchall->ingress.state == CXGB4_MATCHALL_STATE_DISABLED) return -ENOENT; - ret = cxgb4_get_filter_counters(dev, tc_port_matchall->ingress.tid, - &packets, &bytes, - tc_port_matchall->ingress.fs.hash); - if (ret) - return ret; + ingress = &tc_port_matchall->ingress; + for (i = 0; i < CXGB4_FILTER_TYPE_MAX; i++) { + ret = cxgb4_get_filter_counters(dev, ingress->tid[i], + &tmp_packets, &tmp_bytes, + ingress->fs[i].hash); + if (ret) + return ret; + + packets += tmp_packets; + bytes += tmp_bytes; + } if (tc_port_matchall->ingress.packets != packets) { flow_stats_update(&cls_matchall->stats, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.h index e264b6e606c4..fe7ec423a4c9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.h @@ -19,8 +19,9 @@ struct cxgb4_matchall_egress_entry { struct cxgb4_matchall_ingress_entry { enum cxgb4_matchall_state state; /* Current MATCHALL offload state */ - u32 tid; /* Index to hardware filter entry */ - struct ch_filter_specification fs; /* Filter entry */ + u32 tid[CXGB4_FILTER_TYPE_MAX]; /* Index to hardware filter entries */ + /* Filter entries */ + struct ch_filter_specification fs[CXGB4_FILTER_TYPE_MAX]; u16 viid_mirror; /* Identifier for allocated Mirror VI */ u64 bytes; /* # of bytes hitting the filter */ u64 packets; /* # of packets hitting the filter */ diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 8d13ea370db1..66e67b24a887 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2446,6 +2446,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->reset = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(port->reset)) { dev_err(dev, "no reset\n"); + clk_disable_unprepare(port->pclk); return PTR_ERR(port->reset); } reset_control_reset(port->reset); @@ -2501,8 +2502,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) IRQF_SHARED, port_names[port->id], port); - if (ret) + if (ret) { + clk_disable_unprepare(port->pclk); return ret; + } ret = register_netdev(netdev); if (!ret) { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 17f6bcafc944..83b1e974bff0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -2325,7 +2325,7 @@ static void cdan_cb(struct dpaa2_io_notification_ctx *ctx) /* Update NAPI statistics */ ch->stats.cdan++; - napi_schedule_irqoff(&ch->napi); + napi_schedule(&ch->napi); } /* Allocate and configure a DPCON object */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index f50353cbb4db..f78ca7b343d2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -270,7 +270,7 @@ static irqreturn_t enetc_msix(int irq, void *data) for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0); - napi_schedule_irqoff(&v->napi); + napi_schedule(&v->napi); return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index a9939550fa8f..1c4a535890da 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -1130,7 +1130,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv, !is_zero_ether_addr(match.mask->src)) { NL_SET_ERR_MSG_MOD(extack, "Cannot match on both source and destination MAC"); - err = EINVAL; + err = -EINVAL; goto free_filter; } @@ -1138,7 +1138,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv, if (!is_broadcast_ether_addr(match.mask->dst)) { NL_SET_ERR_MSG_MOD(extack, "Masked matching on destination MAC not supported"); - err = EINVAL; + err = -EINVAL; goto free_filter; } ether_addr_copy(filter->sid.dst_mac, match.key->dst); @@ -1149,7 +1149,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv, if (!is_broadcast_ether_addr(match.mask->src)) { NL_SET_ERR_MSG_MOD(extack, "Masked matching on source MAC not supported"); - err = EINVAL; + err = -EINVAL; goto free_filter; } ether_addr_copy(filter->sid.src_mac, match.key->src); @@ -1157,7 +1157,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv, } } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported, must include ETH_ADDRS"); - err = EINVAL; + err = -EINVAL; goto free_filter; } diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index f151d6e111dd..ef67e8599b39 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -1398,8 +1398,7 @@ static void enable_time_stamp(struct fman *fman) { struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs; u16 fm_clk_freq = fman->state->fm_clk_freq; - u32 tmp, intgr, ts_freq; - u64 frac; + u32 tmp, intgr, ts_freq, frac; ts_freq = (u32)(1 << fman->state->count1_micro_bit); /* configure timestamp so that bit 8 will count 1 microsecond diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 004c266802a8..bce3c9398887 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -1200,7 +1200,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) list_for_each(pos, &dtsec->multicast_addr_hash->lsts[bucket]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; @@ -1213,7 +1213,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) list_for_each(pos, &dtsec->unicast_addr_hash->lsts[bucket]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h index dd6d0526f6c1..19f327efdaff 100644 --- a/drivers/net/ethernet/freescale/fman/fman_mac.h +++ b/drivers/net/ethernet/freescale/fman/fman_mac.h @@ -252,7 +252,7 @@ static inline struct eth_hash_t *alloc_hash_table(u16 size) struct eth_hash_t *hash; /* Allocate address hash table */ - hash = kmalloc_array(size, sizeof(struct eth_hash_t *), GFP_KERNEL); + hash = kmalloc(sizeof(*hash), GFP_KERNEL); if (!hash) return NULL; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index a5500ede4070..645764abdaae 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -852,7 +852,6 @@ int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority, tmp = ioread32be(®s->command_config); tmp &= ~CMD_CFG_PFC_MODE; - priority = 0; iowrite32be(tmp, ®s->command_config); @@ -982,7 +981,7 @@ int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) list_for_each(pos, &memac->multicast_addr_hash->lsts[hash]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 87b26f063cc8..c27df153f895 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1767,6 +1767,7 @@ static int fman_port_probe(struct platform_device *of_dev) struct fman_port *port; struct fman *fman; struct device_node *fm_node, *port_node; + struct platform_device *fm_pdev; struct resource res; struct resource *dev_res; u32 val; @@ -1791,8 +1792,14 @@ static int fman_port_probe(struct platform_device *of_dev) goto return_err; } - fman = dev_get_drvdata(&of_find_device_by_node(fm_node)->dev); + fm_pdev = of_find_device_by_node(fm_node); of_node_put(fm_node); + if (!fm_pdev) { + err = -EINVAL; + goto return_err; + } + + fman = dev_get_drvdata(&fm_pdev->dev); if (!fman) { err = -EINVAL; goto return_err; diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 8c7eb878d5b4..41946b16f6c7 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -626,7 +626,7 @@ int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) list_for_each(pos, &tgec->multicast_addr_hash->lsts[hash]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b1bea0309a7c..87776ce3539b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1093,16 +1093,8 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, int k, sizeoflast; dma_addr_t dma; - if (type == DESC_TYPE_SKB) { - struct sk_buff *skb = (struct sk_buff *)priv; - int ret; - - ret = hns3_fill_skb_desc(ring, skb, desc); - if (unlikely(ret < 0)) - return ret; - - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); - } else if (type == DESC_TYPE_FRAGLIST_SKB) { + if (type == DESC_TYPE_FRAGLIST_SKB || + type == DESC_TYPE_SKB) { struct sk_buff *skb = (struct sk_buff *)priv; dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); @@ -1439,6 +1431,10 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) next_to_use_head = ring->next_to_use; + ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use]); + if (unlikely(ret < 0)) + goto fill_err; + ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); if (unlikely(ret < 0)) goto fill_err; @@ -4153,8 +4149,8 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) return; if (linkup) { - netif_carrier_on(netdev); netif_tx_wake_all_queues(netdev); + netif_carrier_on(netdev); if (netif_msg_link(handle)) netdev_info(netdev, "link up\n"); } else { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bb4a6327035d..36575e72a915 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5806,9 +5806,9 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle, /* to avoid rule conflict, when user configure rule by ethtool, * we need to clear all arfs rules */ + spin_lock_bh(&hdev->fd_rule_lock); hclge_clear_arfs_rules(handle); - spin_lock_bh(&hdev->fd_rule_lock); ret = hclge_fd_config_rule(hdev, rule); spin_unlock_bh(&hdev->fd_rule_lock); @@ -5851,6 +5851,7 @@ static int hclge_del_fd_entry(struct hnae3_handle *handle, return ret; } +/* make sure being called after lock up with fd_rule_lock */ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, bool clear_list) { @@ -5863,7 +5864,6 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, if (!hnae3_dev_fd_supported(hdev)) return; - spin_lock_bh(&hdev->fd_rule_lock); for_each_set_bit(location, hdev->fd_bmap, hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, location, @@ -5880,8 +5880,6 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, bitmap_zero(hdev->fd_bmap, hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]); } - - spin_unlock_bh(&hdev->fd_rule_lock); } static int hclge_restore_fd_entries(struct hnae3_handle *handle) @@ -6263,7 +6261,7 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, u16 flow_id, struct flow_keys *fkeys) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_fd_rule_tuples new_tuples; + struct hclge_fd_rule_tuples new_tuples = {}; struct hclge_dev *hdev = vport->back; struct hclge_fd_rule *rule; u16 tmp_queue_id; @@ -6273,19 +6271,17 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, if (!hnae3_dev_fd_supported(hdev)) return -EOPNOTSUPP; - memset(&new_tuples, 0, sizeof(new_tuples)); - hclge_fd_get_flow_tuples(fkeys, &new_tuples); - - spin_lock_bh(&hdev->fd_rule_lock); - /* when there is already fd rule existed add by user, * arfs should not work */ + spin_lock_bh(&hdev->fd_rule_lock); if (hdev->fd_active_type == HCLGE_FD_EP_ACTIVE) { spin_unlock_bh(&hdev->fd_rule_lock); return -EOPNOTSUPP; } + hclge_fd_get_flow_tuples(fkeys, &new_tuples); + /* check is there flow director filter existed for this flow, * if not, create a new filter for it; * if filter exist with different queue id, modify the filter; @@ -6368,6 +6364,7 @@ static void hclge_rfs_filter_expire(struct hclge_dev *hdev) #endif } +/* make sure being called after lock up with fd_rule_lock */ static void hclge_clear_arfs_rules(struct hnae3_handle *handle) { #ifdef CONFIG_RFS_ACCEL @@ -6420,10 +6417,14 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) hdev->fd_en = enable; clear = hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE; - if (!enable) + + if (!enable) { + spin_lock_bh(&hdev->fd_rule_lock); hclge_del_all_fd_entries(handle, clear); - else + spin_unlock_bh(&hdev->fd_rule_lock); + } else { hclge_restore_fd_entries(handle); + } } static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) @@ -6886,8 +6887,9 @@ static void hclge_ae_stop(struct hnae3_handle *handle) int i; set_bit(HCLGE_STATE_DOWN, &hdev->state); - + spin_lock_bh(&hdev->fd_rule_lock); hclge_clear_arfs_rules(handle); + spin_unlock_bh(&hdev->fd_rule_lock); /* If it is not PF reset, the firmware will disable the MAC, * so it only need to stop phy here. @@ -9040,11 +9042,12 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, bool writen_to_tbl = false; int ret = 0; - /* When device is resetting, firmware is unable to handle - * mailbox. Just record the vlan id, and remove it after + /* When device is resetting or reset failed, firmware is unable to + * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && is_kill) { + if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, vport->vlan_del_fail_bmap); return -EBUSY; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a10b022d1951..9162856de1b1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1592,11 +1592,12 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, if (proto != htons(ETH_P_8021Q)) return -EPROTONOSUPPORT; - /* When device is resetting, firmware is unable to handle - * mailbox. Just record the vlan id, and remove it after + /* When device is resetting or reset failed, firmware is unable to + * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ - if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) && is_kill) { + if ((test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, hdev->vlan_del_fail_bmap); return -EBUSY; } @@ -3439,23 +3440,36 @@ void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, { struct hnae3_handle *nic = &hdev->nic; struct hclge_vf_to_pf_msg send_msg; + int ret; rtnl_lock(); - hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); - rtnl_unlock(); + + if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) { + dev_warn(&hdev->pdev->dev, + "is resetting when updating port based vlan info\n"); + rtnl_unlock(); + return; + } + + ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); + if (ret) { + rtnl_unlock(); + return; + } /* send msg to PF and wait update port based vlan info */ hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, HCLGE_MBX_PORT_BASE_VLAN_CFG); memcpy(send_msg.data, port_base_vlan_info, data_size); - hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); - - if (state == HNAE3_PORT_BASE_VLAN_DISABLE) - nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE; - else - nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; + ret = hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); + if (!ret) { + if (state == HNAE3_PORT_BASE_VLAN_DISABLE) + nic->port_base_vlan_state = state; + else + nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; + } - rtnl_lock(); hclgevf_notify_client(hdev, HNAE3_UP_CLIENT); rtnl_unlock(); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h index befd925c03dc..0a1e20edf7cf 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -98,10 +98,14 @@ struct hinic_dev { int lb_pkt_len; u8 *lb_test_rx_buf; struct devlink *devlink; + bool cable_unplugged; + bool module_unrecognized; }; struct hinic_devlink_priv { struct hinic_hwdev *hwdev; + struct devlink_health_reporter *hw_fault_reporter; + struct devlink_health_reporter *fw_fault_reporter; }; #endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c index a40a10ac1ee9..c6adc776f3c8 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c @@ -16,9 +16,9 @@ #include <net/devlink.h> #include <linux/firmware.h> -#include "hinic_dev.h" #include "hinic_port.h" #include "hinic_devlink.h" +#include "hinic_hw_dev.h" static bool check_image_valid(struct hinic_devlink_priv *priv, const u8 *buf, u32 image_size, struct host_image_st *host_image) @@ -317,12 +317,292 @@ void hinic_devlink_free(struct devlink *devlink) devlink_free(devlink); } -int hinic_devlink_register(struct devlink *devlink, struct device *dev) +int hinic_devlink_register(struct hinic_devlink_priv *priv, struct device *dev) { + struct devlink *devlink = priv_to_devlink(priv); + return devlink_register(devlink, dev); } -void hinic_devlink_unregister(struct devlink *devlink) +void hinic_devlink_unregister(struct hinic_devlink_priv *priv) { + struct devlink *devlink = priv_to_devlink(priv); + devlink_unregister(devlink); } + +static int chip_fault_show(struct devlink_fmsg *fmsg, + struct hinic_fault_event *event) +{ + char fault_level[FAULT_TYPE_MAX][FAULT_SHOW_STR_LEN + 1] = { + "fatal", "reset", "flr", "general", "suggestion"}; + char level_str[FAULT_SHOW_STR_LEN + 1] = {0}; + u8 level; + int err; + + level = event->event.chip.err_level; + if (level < FAULT_LEVEL_MAX) + strncpy(level_str, fault_level[level], strlen(fault_level[level])); + else + strncpy(level_str, "Unknown", strlen("Unknown")); + + if (level == FAULT_LEVEL_SERIOUS_FLR) { + err = devlink_fmsg_u32_pair_put(fmsg, "Function level err func_id", + (u32)event->event.chip.func_id); + if (err) + return err; + } + + err = devlink_fmsg_u8_pair_put(fmsg, "module_id", event->event.chip.node_id); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "err_type", (u32)event->event.chip.err_type); + if (err) + return err; + + err = devlink_fmsg_string_pair_put(fmsg, "err_level", level_str); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "err_csr_addr", + event->event.chip.err_csr_addr); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "err_csr_value", + event->event.chip.err_csr_value); + if (err) + return err; + + return 0; +} + +static int fault_report_show(struct devlink_fmsg *fmsg, + struct hinic_fault_event *event) +{ + char fault_type[FAULT_TYPE_MAX][FAULT_SHOW_STR_LEN + 1] = { + "chip", "ucode", "mem rd timeout", "mem wr timeout", + "reg rd timeout", "reg wr timeout", "phy fault"}; + char type_str[FAULT_SHOW_STR_LEN + 1] = {0}; + int err; + + if (event->type < FAULT_TYPE_MAX) + strncpy(type_str, fault_type[event->type], strlen(fault_type[event->type])); + else + strncpy(type_str, "Unknown", strlen("Unknown")); + + err = devlink_fmsg_string_pair_put(fmsg, "Fault type", type_str); + if (err) + return err; + + err = devlink_fmsg_binary_pair_put(fmsg, "Fault raw data", + event->event.val, sizeof(event->event.val)); + if (err) + return err; + + switch (event->type) { + case FAULT_TYPE_CHIP: + err = chip_fault_show(fmsg, event); + if (err) + return err; + break; + case FAULT_TYPE_UCODE: + err = devlink_fmsg_u8_pair_put(fmsg, "Cause_id", event->event.ucode.cause_id); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "core_id", event->event.ucode.core_id); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "c_id", event->event.ucode.c_id); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "epc", event->event.ucode.epc); + if (err) + return err; + break; + case FAULT_TYPE_MEM_RD_TIMEOUT: + case FAULT_TYPE_MEM_WR_TIMEOUT: + err = devlink_fmsg_u32_pair_put(fmsg, "Err_csr_ctrl", + event->event.mem_timeout.err_csr_ctrl); + if (err) + return err; + err = devlink_fmsg_u32_pair_put(fmsg, "err_csr_data", + event->event.mem_timeout.err_csr_data); + if (err) + return err; + err = devlink_fmsg_u32_pair_put(fmsg, "ctrl_tab", + event->event.mem_timeout.ctrl_tab); + if (err) + return err; + err = devlink_fmsg_u32_pair_put(fmsg, "mem_index", + event->event.mem_timeout.mem_index); + if (err) + return err; + break; + case FAULT_TYPE_REG_RD_TIMEOUT: + case FAULT_TYPE_REG_WR_TIMEOUT: + err = devlink_fmsg_u32_pair_put(fmsg, "Err_csr", event->event.reg_timeout.err_csr); + if (err) + return err; + break; + case FAULT_TYPE_PHY_FAULT: + err = devlink_fmsg_u8_pair_put(fmsg, "Op_type", event->event.phy_fault.op_type); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "port_id", event->event.phy_fault.port_id); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "dev_ad", event->event.phy_fault.dev_ad); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "csr_addr", event->event.phy_fault.csr_addr); + if (err) + return err; + err = devlink_fmsg_u32_pair_put(fmsg, "op_data", event->event.phy_fault.op_data); + if (err) + return err; + break; + default: + break; + } + + return 0; +} + +static int hinic_hw_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + if (priv_ctx) + return fault_report_show(fmsg, priv_ctx); + + return 0; +} + +static int mgmt_watchdog_report_show(struct devlink_fmsg *fmsg, + struct hinic_mgmt_watchdog_info *watchdog_info) +{ + int err; + + err = devlink_fmsg_u32_pair_put(fmsg, "Mgmt deadloop time_h", watchdog_info->curr_time_h); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "time_l", watchdog_info->curr_time_l); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "task_id", watchdog_info->task_id); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "sp", watchdog_info->sp); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "stack_current_used", watchdog_info->curr_used); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "peak_used", watchdog_info->peak_used); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "\n Overflow_flag", watchdog_info->is_overflow); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "stack_top", watchdog_info->stack_top); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "stack_bottom", watchdog_info->stack_bottom); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "mgmt_pc", watchdog_info->pc); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "lr", watchdog_info->lr); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "cpsr", watchdog_info->cpsr); + if (err) + return err; + + err = devlink_fmsg_binary_pair_put(fmsg, "Mgmt register info", + watchdog_info->reg, sizeof(watchdog_info->reg)); + if (err) + return err; + + err = devlink_fmsg_binary_pair_put(fmsg, "Mgmt dump stack(start from sp)", + watchdog_info->data, sizeof(watchdog_info->data)); + if (err) + return err; + + return 0; +} + +static int hinic_fw_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + if (priv_ctx) + return mgmt_watchdog_report_show(fmsg, priv_ctx); + + return 0; +} + +static const struct devlink_health_reporter_ops hinic_hw_fault_reporter_ops = { + .name = "hw", + .dump = hinic_hw_reporter_dump, +}; + +static const struct devlink_health_reporter_ops hinic_fw_fault_reporter_ops = { + .name = "fw", + .dump = hinic_fw_reporter_dump, +}; + +int hinic_health_reporters_create(struct hinic_devlink_priv *priv) +{ + struct devlink *devlink = priv_to_devlink(priv); + + priv->hw_fault_reporter = + devlink_health_reporter_create(devlink, &hinic_hw_fault_reporter_ops, + 0, priv); + if (IS_ERR(priv->hw_fault_reporter)) { + dev_warn(&priv->hwdev->hwif->pdev->dev, "Failed to create hw fault reporter, err: %ld\n", + PTR_ERR(priv->hw_fault_reporter)); + return PTR_ERR(priv->hw_fault_reporter); + } + + priv->fw_fault_reporter = + devlink_health_reporter_create(devlink, &hinic_fw_fault_reporter_ops, + 0, priv); + if (IS_ERR(priv->fw_fault_reporter)) { + dev_warn(&priv->hwdev->hwif->pdev->dev, "Failed to create fw fault reporter, err: %ld\n", + PTR_ERR(priv->fw_fault_reporter)); + devlink_health_reporter_destroy(priv->hw_fault_reporter); + priv->hw_fault_reporter = NULL; + return PTR_ERR(priv->fw_fault_reporter); + } + + return 0; +} + +void hinic_health_reporters_destroy(struct hinic_devlink_priv *priv) +{ + if (!IS_ERR_OR_NULL(priv->fw_fault_reporter)) { + devlink_health_reporter_destroy(priv->fw_fault_reporter); + priv->fw_fault_reporter = NULL; + } + + if (!IS_ERR_OR_NULL(priv->hw_fault_reporter)) { + devlink_health_reporter_destroy(priv->hw_fault_reporter); + priv->hw_fault_reporter = NULL; + } +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.h b/drivers/net/ethernet/huawei/hinic/hinic_devlink.h index 604e95a7c5ce..a090ebcfaabb 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.h @@ -7,6 +7,7 @@ #define __HINIC_DEVLINK_H__ #include <net/devlink.h> +#include "hinic_dev.h" #define MAX_FW_TYPE_NUM 30 #define HINIC_MAGIC_NUM 0x18221100 @@ -109,7 +110,10 @@ struct host_image_st { struct devlink *hinic_devlink_alloc(void); void hinic_devlink_free(struct devlink *devlink); -int hinic_devlink_register(struct devlink *devlink, struct device *dev); -void hinic_devlink_unregister(struct devlink *devlink); +int hinic_devlink_register(struct hinic_devlink_priv *priv, struct device *dev); +void hinic_devlink_unregister(struct hinic_devlink_priv *priv); + +int hinic_health_reporters_create(struct hinic_devlink_priv *priv); +void hinic_health_reporters_destroy(struct hinic_devlink_priv *priv); #endif /* __HINIC_DEVLINK_H__ */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index cb5ebae54f73..6bb65ade1d77 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1766,6 +1766,25 @@ static int hinic_get_module_eeprom(struct net_device *netdev, return 0; } +static int +hinic_get_link_ext_state(struct net_device *netdev, + struct ethtool_link_ext_state_info *link_ext_state_info) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + + if (netif_carrier_ok(netdev)) + return -ENODATA; + + if (nic_dev->cable_unplugged) + link_ext_state_info->link_ext_state = + ETHTOOL_LINK_EXT_STATE_NO_CABLE; + else if (nic_dev->module_unrecognized) + link_ext_state_info->link_ext_state = + ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH; + + return 0; +} + static const struct ethtool_ops hinic_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_RX_MAX_FRAMES | @@ -1776,6 +1795,7 @@ static const struct ethtool_ops hinic_ethtool_ops = { .set_link_ksettings = hinic_set_link_ksettings, .get_drvinfo = hinic_get_drvinfo, .get_link = ethtool_op_get_link, + .get_link_ext_state = hinic_get_link_ext_state, .get_ringparam = hinic_get_ringparam, .set_ringparam = hinic_set_ringparam, .get_coalesce = hinic_get_coalesce, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c index 583fd24c29cf..29e88e25a4a4 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c @@ -112,6 +112,26 @@ static u32 get_hw_cons_idx(struct hinic_api_cmd_chain *chain) return HINIC_API_CMD_STATUS_GET(val, CONS_IDX); } +static void dump_api_chain_reg(struct hinic_api_cmd_chain *chain) +{ + u32 addr, val; + + addr = HINIC_CSR_API_CMD_STATUS_ADDR(chain->chain_type); + val = hinic_hwif_read_reg(chain->hwif, addr); + + dev_err(&chain->hwif->pdev->dev, "Chain type: 0x%x, cpld error: 0x%x, check error: 0x%x, current fsm: 0x%x\n", + chain->chain_type, HINIC_API_CMD_STATUS_GET(val, CPLD_ERR), + HINIC_API_CMD_STATUS_GET(val, CHKSUM_ERR), + HINIC_API_CMD_STATUS_GET(val, FSM)); + + dev_err(&chain->hwif->pdev->dev, "Chain hw current ci: 0x%x\n", + HINIC_API_CMD_STATUS_GET(val, CONS_IDX)); + + addr = HINIC_CSR_API_CMD_CHAIN_PI_ADDR(chain->chain_type); + val = hinic_hwif_read_reg(chain->hwif, addr); + dev_err(&chain->hwif->pdev->dev, "Chain hw current pi: 0x%x\n", val); +} + /** * chain_busy - check if the chain is still processing last requests * @chain: chain to check @@ -131,8 +151,10 @@ static int chain_busy(struct hinic_api_cmd_chain *chain) /* check for a space for a new command */ if (chain->cons_idx == MASKED_IDX(chain, prod_idx + 1)) { - dev_err(&pdev->dev, "API CMD chain %d is busy\n", - chain->chain_type); + dev_err(&pdev->dev, "API CMD chain %d is busy, cons_idx: %d, prod_idx: %d\n", + chain->chain_type, chain->cons_idx, + chain->prod_idx); + dump_api_chain_reg(chain); return -EBUSY; } break; @@ -332,6 +354,7 @@ static int wait_for_api_cmd_completion(struct hinic_api_cmd_chain *chain) err = wait_for_status_poll(chain); if (err) { dev_err(&pdev->dev, "API CMD Poll status timeout\n"); + dump_api_chain_reg(chain); break; } break; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h index 0ba00fd828df..6d1654b050ad 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h @@ -103,10 +103,14 @@ HINIC_API_CMD_STATUS_HEADER_##member##_MASK) #define HINIC_API_CMD_STATUS_CONS_IDX_SHIFT 0 +#define HINIC_API_CMD_STATUS_FSM_SHIFT 24 #define HINIC_API_CMD_STATUS_CHKSUM_ERR_SHIFT 28 +#define HINIC_API_CMD_STATUS_CPLD_ERR_SHIFT 30 #define HINIC_API_CMD_STATUS_CONS_IDX_MASK 0xFFFFFF +#define HINIC_API_CMD_STATUS_FSM_MASK 0xFU #define HINIC_API_CMD_STATUS_CHKSUM_ERR_MASK 0x3 +#define HINIC_API_CMD_STATUS_CPLD_ERR_MASK 0x1U #define HINIC_API_CMD_STATUS_GET(val, member) \ (((val) >> HINIC_API_CMD_STATUS_##member##_SHIFT) & \ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c index cb5b6e5f787f..e0eb294779ec 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c @@ -401,6 +401,7 @@ static int cmdq_sync_cmd_direct_resp(struct hinic_cmdq *cmdq, spin_unlock_bh(&cmdq->cmdq_lock); + hinic_dump_ceq_info(cmdq->hwdev); return -ETIMEDOUT; } @@ -807,6 +808,7 @@ static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev, cmdq_type = HINIC_CMDQ_SYNC; for (; cmdq_type < HINIC_MAX_CMDQ_TYPES; cmdq_type++) { + cmdqs->cmdq[cmdq_type].hwdev = hwdev; err = init_cmdq(&cmdqs->cmdq[cmdq_type], &cmdqs->saved_wqs[cmdq_type], cmdq_type, db_area[cmdq_type]); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h index 3e4b0aef9fe6..f40c31e1879f 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h @@ -130,6 +130,8 @@ struct hinic_cmdq_ctxt { }; struct hinic_cmdq { + struct hinic_hwdev *hwdev; + struct hinic_wq *wq; enum hinic_cmdq_type cmdq_type; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 9831c14324e6..0c737765d113 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -16,8 +16,11 @@ #include <linux/log2.h> #include <linux/err.h> #include <linux/netdevice.h> +#include <net/devlink.h> +#include "hinic_devlink.h" #include "hinic_sriov.h" +#include "hinic_dev.h" #include "hinic_hw_if.h" #include "hinic_hw_eqs.h" #include "hinic_hw_mgmt.h" @@ -255,9 +258,9 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev) &fw_ctxt, sizeof(fw_ctxt), &fw_ctxt, &out_size); if (err || (out_size != sizeof(fw_ctxt)) || fw_ctxt.status) { - dev_err(&pdev->dev, "Failed to init FW ctxt, ret = %d\n", - fw_ctxt.status); - return -EFAULT; + dev_err(&pdev->dev, "Failed to init FW ctxt, err: %d, status: 0x%x, out size: 0x%x\n", + err, fw_ctxt.status, out_size); + return -EIO; } return 0; @@ -422,9 +425,9 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn) &cmd_base_qpn, sizeof(cmd_base_qpn), &cmd_base_qpn, &out_size); if (err || (out_size != sizeof(cmd_base_qpn)) || cmd_base_qpn.status) { - dev_err(&pdev->dev, "Failed to get base qpn, status = %d\n", - cmd_base_qpn.status); - return -EFAULT; + dev_err(&pdev->dev, "Failed to get base qpn, err: %d, status: 0x%x, out size: 0x%x\n", + err, cmd_base_qpn.status, out_size); + return -EIO; } *base_qpn = cmd_base_qpn.qpn; @@ -621,6 +624,113 @@ static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in, nic_cb->cb_state &= ~HINIC_CB_RUNNING; } +static void hinic_comm_recv_mgmt_self_cmd_reg(struct hinic_pfhwdev *pfhwdev, + u8 cmd, + comm_mgmt_self_msg_proc proc) +{ + u8 cmd_idx; + + cmd_idx = pfhwdev->proc.cmd_num; + if (cmd_idx >= HINIC_COMM_SELF_CMD_MAX) { + dev_err(&pfhwdev->hwdev.hwif->pdev->dev, + "Register recv mgmt process failed, cmd: 0x%x\n", cmd); + return; + } + + pfhwdev->proc.info[cmd_idx].cmd = cmd; + pfhwdev->proc.info[cmd_idx].proc = proc; + pfhwdev->proc.cmd_num++; +} + +static void hinic_comm_recv_mgmt_self_cmd_unreg(struct hinic_pfhwdev *pfhwdev, + u8 cmd) +{ + u8 cmd_idx; + + cmd_idx = pfhwdev->proc.cmd_num; + if (cmd_idx >= HINIC_COMM_SELF_CMD_MAX) { + dev_err(&pfhwdev->hwdev.hwif->pdev->dev, "Unregister recv mgmt process failed, cmd: 0x%x\n", + cmd); + return; + } + + for (cmd_idx = 0; cmd_idx < HINIC_COMM_SELF_CMD_MAX; cmd_idx++) { + if (cmd == pfhwdev->proc.info[cmd_idx].cmd) { + pfhwdev->proc.info[cmd_idx].cmd = 0; + pfhwdev->proc.info[cmd_idx].proc = NULL; + pfhwdev->proc.cmd_num--; + } + } +} + +static void comm_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size) +{ + struct hinic_pfhwdev *pfhwdev = handle; + u8 cmd_idx; + + for (cmd_idx = 0; cmd_idx < pfhwdev->proc.cmd_num; cmd_idx++) { + if (cmd == pfhwdev->proc.info[cmd_idx].cmd) { + if (!pfhwdev->proc.info[cmd_idx].proc) { + dev_warn(&pfhwdev->hwdev.hwif->pdev->dev, + "PF recv mgmt comm msg handle null, cmd: 0x%x\n", + cmd); + } else { + pfhwdev->proc.info[cmd_idx].proc + (&pfhwdev->hwdev, buf_in, in_size, + buf_out, out_size); + } + + return; + } + } + + dev_warn(&pfhwdev->hwdev.hwif->pdev->dev, "Received unknown mgmt cpu event: 0x%x\n", + cmd); + + *out_size = 0; +} + +/* pf fault report event */ +static void pf_fault_event_handler(void *dev, void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_cmd_fault_event *fault_event = buf_in; + struct hinic_hwdev *hwdev = dev; + + if (in_size != sizeof(*fault_event)) { + dev_err(&hwdev->hwif->pdev->dev, "Invalid fault event report, length: %d, should be %zu\n", + in_size, sizeof(*fault_event)); + return; + } + + if (!hwdev->devlink_dev || IS_ERR_OR_NULL(hwdev->devlink_dev->hw_fault_reporter)) + return; + + devlink_health_report(hwdev->devlink_dev->hw_fault_reporter, + "HW fatal error reported", &fault_event->event); +} + +static void mgmt_watchdog_timeout_event_handler(void *dev, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_mgmt_watchdog_info *watchdog_info = buf_in; + struct hinic_hwdev *hwdev = dev; + + if (in_size != sizeof(*watchdog_info)) { + dev_err(&hwdev->hwif->pdev->dev, "Invalid mgmt watchdog report, length: %d, should be %zu\n", + in_size, sizeof(*watchdog_info)); + return; + } + + if (!hwdev->devlink_dev || IS_ERR_OR_NULL(hwdev->devlink_dev->fw_fault_reporter)) + return; + + devlink_health_report(hwdev->devlink_dev->fw_fault_reporter, + "FW fatal error reported", watchdog_info); +} + /** * init_pfhwdev - Initialize the extended components of PF * @pfhwdev: the HW device for PF @@ -640,20 +750,37 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev) return err; } + err = hinic_devlink_register(hwdev->devlink_dev, &pdev->dev); + if (err) { + dev_err(&hwif->pdev->dev, "Failed to register devlink\n"); + hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); + return err; + } + err = hinic_func_to_func_init(hwdev); if (err) { dev_err(&hwif->pdev->dev, "Failed to init mailbox\n"); + hinic_devlink_unregister(hwdev->devlink_dev); hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); return err; } - if (!HINIC_IS_VF(hwif)) + if (!HINIC_IS_VF(hwif)) { hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, pfhwdev, nic_mgmt_msg_handler); - else + hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + pfhwdev, comm_mgmt_msg_handler); + hinic_comm_recv_mgmt_self_cmd_reg(pfhwdev, + HINIC_COMM_CMD_FAULT_REPORT, + pf_fault_event_handler); + hinic_comm_recv_mgmt_self_cmd_reg + (pfhwdev, HINIC_COMM_CMD_WATCHDOG_INFO, + mgmt_watchdog_timeout_event_handler); + } else { hinic_register_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC, nic_mgmt_msg_handler); + } hinic_set_pf_action(hwif, HINIC_PF_MGMT_ACTIVE); @@ -670,14 +797,23 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev) hinic_set_pf_action(hwdev->hwif, HINIC_PF_MGMT_INIT); - if (!HINIC_IS_VF(hwdev->hwif)) + if (!HINIC_IS_VF(hwdev->hwif)) { + hinic_comm_recv_mgmt_self_cmd_unreg(pfhwdev, + HINIC_COMM_CMD_WATCHDOG_INFO); + hinic_comm_recv_mgmt_self_cmd_unreg(pfhwdev, + HINIC_COMM_CMD_FAULT_REPORT); + hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, + HINIC_MOD_COMM); hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC); - else + } else { hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC); + } hinic_func_to_func_free(hwdev); + hinic_devlink_unregister(hwdev->devlink_dev); + hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); } @@ -777,7 +913,7 @@ int hinic_set_interrupt_cfg(struct hinic_hwdev *hwdev, * * Initialize the NIC HW device and return a pointer to it **/ -struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev) +struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev, struct devlink *devlink) { struct hinic_pfhwdev *pfhwdev; struct hinic_hwdev *hwdev; @@ -802,6 +938,8 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev) hwdev = &pfhwdev->hwdev; hwdev->hwif = hwif; + hwdev->devlink_dev = devlink_priv(devlink); + hwdev->devlink_dev->hwdev = hwdev; err = init_msix(hwdev); if (err) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index 94593a8ad667..2fb5f784f116 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -10,6 +10,7 @@ #include <linux/pci.h> #include <linux/types.h> #include <linux/bitops.h> +#include <net/devlink.h> #include "hinic_hw_if.h" #include "hinic_hw_eqs.h" @@ -164,9 +165,12 @@ enum hinic_ucode_cmd { #define NIC_RSS_CMD_TEMP_FREE 0x02 enum hinic_mgmt_msg_cmd { - HINIC_MGMT_MSG_CMD_BASE = 160, + HINIC_MGMT_MSG_CMD_BASE = 0xA0, - HINIC_MGMT_MSG_CMD_LINK_STATUS = 160, + HINIC_MGMT_MSG_CMD_LINK_STATUS = 0xA0, + + HINIC_MGMT_MSG_CMD_CABLE_PLUG_EVENT = 0xE5, + HINIC_MGMT_MSG_CMD_LINK_ERR_EVENT = 0xE6, HINIC_MGMT_MSG_CMD_MAX, }; @@ -348,6 +352,7 @@ struct hinic_hwdev { struct hinic_cap nic_cap; u8 port_id; + struct hinic_devlink_priv *devlink_dev; }; struct hinic_nic_cb { @@ -359,12 +364,29 @@ struct hinic_nic_cb { unsigned long cb_state; }; +#define HINIC_COMM_SELF_CMD_MAX 4 + +typedef void (*comm_mgmt_self_msg_proc)(void *handle, void *buf_in, u16 in_size, + void *buf_out, u16 *out_size); + +struct comm_mgmt_self_msg_sub_info { + u8 cmd; + comm_mgmt_self_msg_proc proc; +}; + +struct comm_mgmt_self_msg_info { + u8 cmd_num; + struct comm_mgmt_self_msg_sub_info info[HINIC_COMM_SELF_CMD_MAX]; +}; + struct hinic_pfhwdev { struct hinic_hwdev hwdev; struct hinic_pf_to_mgmt pf_to_mgmt; struct hinic_nic_cb nic_cb[HINIC_MGMT_NUM_MSG_CMD]; + + struct comm_mgmt_self_msg_info proc; }; struct hinic_dev_cap { @@ -386,6 +408,126 @@ struct hinic_dev_cap { u8 rsvd3[204]; }; +union hinic_fault_hw_mgmt { + u32 val[4]; + /* valid only type == FAULT_TYPE_CHIP */ + struct { + u8 node_id; + u8 err_level; + u16 err_type; + u32 err_csr_addr; + u32 err_csr_value; + /* func_id valid only if err_level == FAULT_LEVEL_SERIOUS_FLR */ + u16 func_id; + u16 rsvd2; + } chip; + + /* valid only if type == FAULT_TYPE_UCODE */ + struct { + u8 cause_id; + u8 core_id; + u8 c_id; + u8 rsvd3; + u32 epc; + u32 rsvd4; + u32 rsvd5; + } ucode; + + /* valid only if type == FAULT_TYPE_MEM_RD_TIMEOUT || + * FAULT_TYPE_MEM_WR_TIMEOUT + */ + struct { + u32 err_csr_ctrl; + u32 err_csr_data; + u32 ctrl_tab; + u32 mem_index; + } mem_timeout; + + /* valid only if type == FAULT_TYPE_REG_RD_TIMEOUT || + * FAULT_TYPE_REG_WR_TIMEOUT + */ + struct { + u32 err_csr; + u32 rsvd6; + u32 rsvd7; + u32 rsvd8; + } reg_timeout; + + struct { + /* 0: read; 1: write */ + u8 op_type; + u8 port_id; + u8 dev_ad; + u8 rsvd9; + u32 csr_addr; + u32 op_data; + u32 rsvd10; + } phy_fault; +}; + +struct hinic_fault_event { + u8 type; + u8 fault_level; + u8 rsvd0[2]; + union hinic_fault_hw_mgmt event; +}; + +struct hinic_cmd_fault_event { + u8 status; + u8 version; + u8 rsvd0[6]; + + struct hinic_fault_event event; +}; + +enum hinic_fault_type { + FAULT_TYPE_CHIP, + FAULT_TYPE_UCODE, + FAULT_TYPE_MEM_RD_TIMEOUT, + FAULT_TYPE_MEM_WR_TIMEOUT, + FAULT_TYPE_REG_RD_TIMEOUT, + FAULT_TYPE_REG_WR_TIMEOUT, + FAULT_TYPE_PHY_FAULT, + FAULT_TYPE_MAX, +}; + +#define FAULT_SHOW_STR_LEN 16 + +enum hinic_fault_err_level { + FAULT_LEVEL_FATAL, + FAULT_LEVEL_SERIOUS_RESET, + FAULT_LEVEL_SERIOUS_FLR, + FAULT_LEVEL_GENERAL, + FAULT_LEVEL_SUGGESTION, + FAULT_LEVEL_MAX +}; + +struct hinic_mgmt_watchdog_info { + u8 status; + u8 version; + u8 rsvd0[6]; + + u32 curr_time_h; + u32 curr_time_l; + u32 task_id; + u32 rsv; + + u32 reg[13]; + u32 pc; + u32 lr; + u32 cpsr; + + u32 stack_top; + u32 stack_bottom; + u32 sp; + u32 curr_used; + u32 peak_used; + u32 is_overflow; + + u32 stack_actlen; + u8 data[1024]; +}; + void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev, enum hinic_mgmt_msg_cmd cmd, void *handle, void (*handler)(void *handle, void *buf_in, @@ -407,7 +549,7 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev, u16 sq_depth, u16 rq_depth); void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev); -struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev); +struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev, struct devlink *devlink); void hinic_free_hwdev(struct hinic_hwdev *hwdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c index 397936cac304..ca8cb68a8d20 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c @@ -953,3 +953,42 @@ void hinic_ceqs_free(struct hinic_ceqs *ceqs) for (q_id = 0; q_id < ceqs->num_ceqs; q_id++) remove_eq(&ceqs->ceq[q_id]); } + +void hinic_dump_ceq_info(struct hinic_hwdev *hwdev) +{ + struct hinic_eq *eq = NULL; + u32 addr, ci, pi; + int q_id; + + for (q_id = 0; q_id < hwdev->func_to_io.ceqs.num_ceqs; q_id++) { + eq = &hwdev->func_to_io.ceqs.ceq[q_id]; + addr = EQ_CONS_IDX_REG_ADDR(eq); + ci = hinic_hwif_read_reg(hwdev->hwif, addr); + addr = EQ_PROD_IDX_REG_ADDR(eq); + pi = hinic_hwif_read_reg(hwdev->hwif, addr); + dev_err(&hwdev->hwif->pdev->dev, "Ceq id: %d, ci: 0x%08x, sw_ci: 0x%08x, pi: 0x%x, tasklet_state: 0x%lx, wrap: %d, ceqe: 0x%x\n", + q_id, ci, eq->cons_idx, pi, + eq->ceq_tasklet.state, + eq->wrapped, be32_to_cpu(*(__be32 *)(GET_CURR_CEQ_ELEM(eq)))); + } +} + +void hinic_dump_aeq_info(struct hinic_hwdev *hwdev) +{ + struct hinic_aeq_elem *aeqe_pos = NULL; + struct hinic_eq *eq = NULL; + u32 addr, ci, pi; + int q_id; + + for (q_id = 0; q_id < hwdev->aeqs.num_aeqs; q_id++) { + eq = &hwdev->aeqs.aeq[q_id]; + addr = EQ_CONS_IDX_REG_ADDR(eq); + ci = hinic_hwif_read_reg(hwdev->hwif, addr); + addr = EQ_PROD_IDX_REG_ADDR(eq); + pi = hinic_hwif_read_reg(hwdev->hwif, addr); + aeqe_pos = GET_CURR_AEQ_ELEM(eq); + dev_err(&hwdev->hwif->pdev->dev, "Aeq id: %d, ci: 0x%08x, pi: 0x%x, work_state: 0x%x, wrap: %d, desc: 0x%x\n", + q_id, ci, pi, work_busy(&eq->aeq_work.work), + eq->wrapped, be32_to_cpu(aeqe_pos->desc)); + } +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h index 74b9ff90640c..43065fc70869 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h @@ -162,7 +162,7 @@ enum hinic_eqe_state { struct hinic_aeq_elem { u8 data[HINIC_AEQE_DATA_SIZE]; - u32 desc; + __be32 desc; }; struct hinic_eq_work { @@ -254,4 +254,8 @@ int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif, void hinic_ceqs_free(struct hinic_ceqs *ceqs); +void hinic_dump_ceq_info(struct hinic_hwdev *hwdev); + +void hinic_dump_aeq_info(struct hinic_hwdev *hwdev); + #endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c index cf127d896ba6..bc8925c0c982 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c @@ -21,6 +21,8 @@ #define WAIT_HWIF_READY_TIMEOUT 10000 +#define HINIC_SELFTEST_RESULT 0x883C + /** * hinic_msix_attr_set - set message attribute for msix entry * @hwif: the HW interface of a pci function device @@ -369,6 +371,26 @@ u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif) return HINIC_FA0_GET(attr0, PF_IDX); } +static void __print_selftest_reg(struct hinic_hwif *hwif) +{ + u32 addr, attr0, attr1; + + addr = HINIC_CSR_FUNC_ATTR1_ADDR; + attr1 = hinic_hwif_read_reg(hwif, addr); + + if (attr1 == HINIC_PCIE_LINK_DOWN) { + dev_err(&hwif->pdev->dev, "PCIE is link down\n"); + return; + } + + addr = HINIC_CSR_FUNC_ATTR0_ADDR; + attr0 = hinic_hwif_read_reg(hwif, addr); + if (HINIC_FA0_GET(attr0, FUNC_TYPE) != HINIC_VF && + !HINIC_FA0_GET(attr0, PCI_INTF_IDX)) + dev_err(&hwif->pdev->dev, "Selftest reg: 0x%08x\n", + hinic_hwif_read_reg(hwif, HINIC_SELFTEST_RESULT)); +} + /** * hinic_init_hwif - initialize the hw interface * @hwif: the HW interface of a pci function device @@ -398,6 +420,7 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev) err = wait_hwif_ready(hwif); if (err) { dev_err(&pdev->dev, "HW interface is not ready\n"); + __print_selftest_reg(hwif); goto err_hwif_ready; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h index 0872e035faa1..c06f2253151e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -12,6 +12,8 @@ #include <linux/types.h> #include <asm/byteorder.h> +#define HINIC_PCIE_LINK_DOWN 0xFFFFFFFF + #define HINIC_DMA_ATTR_ST_SHIFT 0 #define HINIC_DMA_ATTR_AT_SHIFT 8 #define HINIC_DMA_ATTR_PH_SHIFT 10 @@ -249,13 +251,17 @@ struct hinic_hwif { static inline u32 hinic_hwif_read_reg(struct hinic_hwif *hwif, u32 reg) { - return be32_to_cpu(readl(hwif->cfg_regs_bar + reg)); + u32 out = readl(hwif->cfg_regs_bar + reg); + + return be32_to_cpu(*(__be32 *)&out); } static inline void hinic_hwif_write_reg(struct hinic_hwif *hwif, u32 reg, u32 val) { - writel(cpu_to_be32(val), hwif->cfg_regs_bar + reg); + __be32 in = cpu_to_be32(val); + + writel(*(u32 *)&in, hwif->cfg_regs_bar + reg); } int hinic_msix_attr_set(struct hinic_hwif *hwif, u16 msix_index, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c index bc2f87e6cb5d..47c93f946b94 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c @@ -650,6 +650,7 @@ wait_for_mbox_seg_completion(struct hinic_mbox_func_to_func *func_to_func, if (!wait_for_completion_timeout(done, jif)) { dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment timeout\n"); dump_mox_reg(hwdev); + hinic_dump_aeq_info(hwdev); return -ETIMEDOUT; } @@ -897,6 +898,7 @@ int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func, set_mbox_to_func_event(func_to_func, EVENT_TIMEOUT); dev_err(&func_to_func->hwif->pdev->dev, "Send mbox msg timeout, msg_id: %d\n", msg_info.msg_id); + hinic_dump_aeq_info(func_to_func->hwdev); err = -ETIMEDOUT; goto err_send_mbox; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index e0f5a81d8620..c6ce5966284c 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -12,8 +12,10 @@ #include <linux/semaphore.h> #include <linux/completion.h> #include <linux/slab.h> +#include <net/devlink.h> #include <asm/barrier.h> +#include "hinic_devlink.h" #include "hinic_hw_if.h" #include "hinic_hw_eqs.h" #include "hinic_hw_api_cmd.h" @@ -274,6 +276,7 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, if (!wait_for_completion_timeout(recv_done, timeo)) { dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id); + hinic_dump_aeq_info(pf_to_mgmt->hwdev); err = -ETIMEDOUT; goto unlock_sync_msg; } @@ -617,10 +620,15 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt, if (HINIC_IS_VF(hwif)) return 0; + err = hinic_health_reporters_create(hwdev->devlink_dev); + if (err) + return err; + sema_init(&pf_to_mgmt->sync_msg_lock, 1); pf_to_mgmt->workq = create_singlethread_workqueue("hinic_mgmt"); if (!pf_to_mgmt->workq) { dev_err(&pdev->dev, "Failed to initialize MGMT workqueue\n"); + hinic_health_reporters_destroy(hwdev->devlink_dev); return -ENOMEM; } pf_to_mgmt->sync_msg_id = 0; @@ -628,12 +636,14 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt, err = alloc_msg_buf(pf_to_mgmt); if (err) { dev_err(&pdev->dev, "Failed to allocate msg buffers\n"); + hinic_health_reporters_destroy(hwdev->devlink_dev); return err; } err = hinic_api_cmd_init(pf_to_mgmt->cmd_chain, hwif); if (err) { dev_err(&pdev->dev, "Failed to initialize cmd chains\n"); + hinic_health_reporters_destroy(hwdev->devlink_dev); return err; } @@ -658,4 +668,5 @@ void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt) hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU); hinic_api_cmd_free(pf_to_mgmt->cmd_chain); destroy_workqueue(pf_to_mgmt->workq); + hinic_health_reporters_destroy(hwdev->devlink_dev); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h index 21b93b654d6b..f626100b85c1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h @@ -81,6 +81,8 @@ enum hinic_comm_cmd { HINIC_COMM_CMD_MSI_CTRL_REG_WR_BY_UP, HINIC_COMM_CMD_MSI_CTRL_REG_RD_BY_UP, + HINIC_COMM_CMD_FAULT_REPORT = 0x37, + HINIC_COMM_CMD_SET_LED_STATUS = 0x4a, HINIC_COMM_CMD_L2NIC_RESET = 0x4b, @@ -89,6 +91,8 @@ enum hinic_comm_cmd { HINIC_COMM_CMD_GET_BOARD_INFO = 0x52, + HINIC_COMM_CMD_WATCHDOG_INFO = 0x56, + HINIC_COMM_CMD_MAX, }; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index c4c6f9c29f0e..501056fd32ee 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -444,8 +444,11 @@ int hinic_open(struct net_device *netdev) if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) hinic_notify_all_vfs_link_changed(nic_dev->hwdev, link_state); - if (link_state == HINIC_LINK_STATE_UP) + if (link_state == HINIC_LINK_STATE_UP) { nic_dev->flags |= HINIC_LINK_UP; + nic_dev->cable_unplugged = false; + nic_dev->module_unrecognized = false; + } nic_dev->flags |= HINIC_INTF_UP; @@ -935,6 +938,8 @@ static void link_status_event_handler(void *handle, void *buf_in, u16 in_size, down(&nic_dev->mgmt_lock); nic_dev->flags |= HINIC_LINK_UP; + nic_dev->cable_unplugged = false; + nic_dev->module_unrecognized = false; if ((nic_dev->flags & (HINIC_LINK_UP | HINIC_INTF_UP)) == (HINIC_LINK_UP | HINIC_INTF_UP)) { @@ -971,6 +976,39 @@ static void link_status_event_handler(void *handle, void *buf_in, u16 in_size, *out_size = sizeof(*ret_link_status); } +static void cable_plug_event(void *handle, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_cable_plug_event *plug_event = buf_in; + struct hinic_dev *nic_dev = handle; + + nic_dev->cable_unplugged = plug_event->plugged ? false : true; + + *out_size = sizeof(*plug_event); + plug_event = buf_out; + plug_event->status = 0; +} + +static void link_err_event(void *handle, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_link_err_event *link_err = buf_in; + struct hinic_dev *nic_dev = handle; + + if (link_err->err_type >= LINK_ERR_NUM) + netif_info(nic_dev, link, nic_dev->netdev, + "Link failed, Unknown error type: 0x%x\n", + link_err->err_type); + else + nic_dev->module_unrecognized = true; + + *out_size = sizeof(*link_err); + link_err = buf_out; + link_err->status = 0; +} + static int set_features(struct hinic_dev *nic_dev, netdev_features_t pre_features, netdev_features_t features, bool force_change) @@ -1077,28 +1115,24 @@ static int nic_dev_init(struct pci_dev *pdev) struct hinic_rx_mode_work *rx_mode_work; struct hinic_txq_stats *tx_stats; struct hinic_rxq_stats *rx_stats; - struct hinic_devlink_priv *priv; struct hinic_dev *nic_dev; struct net_device *netdev; struct hinic_hwdev *hwdev; struct devlink *devlink; int err, num_qps; - hwdev = hinic_init_hwdev(pdev); - if (IS_ERR(hwdev)) { - dev_err(&pdev->dev, "Failed to initialize HW device\n"); - return PTR_ERR(hwdev); - } - devlink = hinic_devlink_alloc(); if (!devlink) { dev_err(&pdev->dev, "Hinic devlink alloc failed\n"); - err = -ENOMEM; - goto err_devlink_alloc; + return -ENOMEM; } - priv = devlink_priv(devlink); - priv->hwdev = hwdev; + hwdev = hinic_init_hwdev(pdev, devlink); + if (IS_ERR(hwdev)) { + dev_err(&pdev->dev, "Failed to initialize HW device\n"); + hinic_devlink_free(devlink); + return PTR_ERR(hwdev); + } num_qps = hinic_hwdev_num_qps(hwdev); if (num_qps <= 0) { @@ -1161,10 +1195,6 @@ static int nic_dev_init(struct pci_dev *pdev) goto err_workq; } - err = hinic_devlink_register(devlink, &pdev->dev); - if (err) - goto err_devlink_reg; - pci_set_drvdata(pdev, netdev); err = hinic_port_get_mac(nic_dev, netdev->dev_addr); @@ -1206,6 +1236,12 @@ 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); + hinic_hwdev_cb_register(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_CABLE_PLUG_EVENT, + nic_dev, cable_plug_event); + hinic_hwdev_cb_register(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_LINK_ERR_EVENT, + nic_dev, link_err_event); err = set_features(nic_dev, 0, nic_dev->netdev->features, true); if (err) @@ -1238,6 +1274,10 @@ err_init_intr: err_set_pfc: err_set_features: hinic_hwdev_cb_unregister(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_LINK_ERR_EVENT); + hinic_hwdev_cb_unregister(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_CABLE_PLUG_EVENT); + hinic_hwdev_cb_unregister(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS); cancel_work_sync(&rx_mode_work->work); @@ -1246,17 +1286,15 @@ err_set_mtu: err_add_mac: err_get_mac: pci_set_drvdata(pdev, NULL); -err_devlink_reg: destroy_workqueue(nic_dev->workq); - err_workq: err_vlan_bitmap: free_netdev(netdev); err_alloc_etherdev: err_num_qps: -err_devlink_alloc: hinic_free_hwdev(hwdev); + hinic_devlink_free(devlink); return err; } @@ -1343,6 +1381,7 @@ static void hinic_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct hinic_dev *nic_dev = netdev_priv(netdev); + struct devlink *devlink = nic_dev->devlink; struct hinic_rx_mode_work *rx_mode_work; if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) { @@ -1357,6 +1396,10 @@ static void hinic_remove(struct pci_dev *pdev) hinic_port_del_mac(nic_dev, netdev->dev_addr, 0); hinic_hwdev_cb_unregister(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_LINK_ERR_EVENT); + hinic_hwdev_cb_unregister(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_CABLE_PLUG_EVENT); + hinic_hwdev_cb_unregister(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS); rx_mode_work = &nic_dev->rx_mode_work; @@ -1364,16 +1407,14 @@ static void hinic_remove(struct pci_dev *pdev) pci_set_drvdata(pdev, NULL); - hinic_devlink_unregister(nic_dev->devlink); - destroy_workqueue(nic_dev->workq); - hinic_devlink_free(nic_dev->devlink); - hinic_free_hwdev(nic_dev->hwdev); free_netdev(netdev); + hinic_devlink_free(devlink); + pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index ba358bbb74a2..02cd635d6914 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -61,8 +61,8 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr, (port_mac_cmd.status && port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY && port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) { - dev_err(&pdev->dev, "Failed to change MAC, ret = %d\n", - port_mac_cmd.status); + dev_err(&pdev->dev, "Failed to change MAC, err: %d, status: 0x%x, out size: 0x%x\n", + err, port_mac_cmd.status, out_size); return -EFAULT; } @@ -129,8 +129,8 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr) &port_mac_cmd, sizeof(port_mac_cmd), &port_mac_cmd, &out_size); if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) { - dev_err(&pdev->dev, "Failed to get mac, ret = %d\n", - port_mac_cmd.status); + dev_err(&pdev->dev, "Failed to get mac, err: %d, status: 0x%x, out size: 0x%x\n", + err, port_mac_cmd.status, out_size); return -EFAULT; } @@ -172,9 +172,9 @@ int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu) err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_CHANGE_MTU, &port_mtu_cmd, sizeof(port_mtu_cmd), &port_mtu_cmd, &out_size); - if (err || (out_size != sizeof(port_mtu_cmd)) || port_mtu_cmd.status) { - dev_err(&pdev->dev, "Failed to set mtu, ret = %d\n", - port_mtu_cmd.status); + if (err || out_size != sizeof(port_mtu_cmd) || port_mtu_cmd.status) { + dev_err(&pdev->dev, "Failed to set mtu, err: %d, status: 0x%x, out size: 0x%x\n", + err, port_mtu_cmd.status, out_size); return -EFAULT; } @@ -264,8 +264,8 @@ int hinic_port_link_state(struct hinic_dev *nic_dev, &link_cmd, sizeof(link_cmd), &link_cmd, &out_size); if (err || (out_size != sizeof(link_cmd)) || link_cmd.status) { - dev_err(&pdev->dev, "Failed to get link state, ret = %d\n", - link_cmd.status); + dev_err(&pdev->dev, "Failed to get link state, err: %d, status: 0x%x, out size: 0x%x\n", + err, link_cmd.status, out_size); return -EINVAL; } @@ -298,8 +298,8 @@ int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state) &port_state, sizeof(port_state), &port_state, &out_size); if (err || (out_size != sizeof(port_state)) || port_state.status) { - dev_err(&pdev->dev, "Failed to set port state, ret = %d\n", - port_state.status); + dev_err(&pdev->dev, "Failed to set port state, err: %d, status: 0x%x, out size: 0x%x\n", + err, port_state.status, out_size); return -EFAULT; } @@ -330,8 +330,8 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev, &func_state, sizeof(func_state), &func_state, &out_size); if (err || (out_size != sizeof(func_state)) || func_state.status) { - dev_err(&pdev->dev, "Failed to set port func state, ret = %d\n", - func_state.status); + dev_err(&pdev->dev, "Failed to set port func state, err: %d, status: 0x%x, out size: 0x%x\n", + err, func_state.status, out_size); return -EFAULT; } @@ -361,9 +361,9 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev, port_cap, &out_size); if (err || (out_size != sizeof(*port_cap)) || port_cap->status) { dev_err(&pdev->dev, - "Failed to get port capabilities, ret = %d\n", - port_cap->status); - return -EINVAL; + "Failed to get port capabilities, err: %d, status: 0x%x, out size: 0x%x\n", + err, port_cap->status, out_size); + return -EIO; } return 0; @@ -393,9 +393,9 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state) &tso_cfg, &out_size); if (err || out_size != sizeof(tso_cfg) || tso_cfg.status) { dev_err(&pdev->dev, - "Failed to set port tso, ret = %d\n", - tso_cfg.status); - return -EINVAL; + "Failed to set port tso, err: %d, status: 0x%x, out size: 0x%x\n", + err, tso_cfg.status, out_size); + return -EIO; } return 0; @@ -423,9 +423,9 @@ int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en) &rx_csum_cfg, &out_size); if (err || !out_size || rx_csum_cfg.status) { dev_err(&pdev->dev, - "Failed to set rx csum offload, ret = %d\n", - rx_csum_cfg.status); - return -EINVAL; + "Failed to set rx csum offload, err: %d, status: 0x%x, out size: 0x%x\n", + err, rx_csum_cfg.status, out_size); + return -EIO; } return 0; @@ -480,9 +480,9 @@ int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs) &rq_num, &out_size); if (err || !out_size || rq_num.status) { dev_err(&pdev->dev, - "Failed to rxq number, ret = %d\n", - rq_num.status); - return -EINVAL; + "Failed to set rxq number, err: %d, status: 0x%x, out size: 0x%x\n", + err, rq_num.status, out_size); + return -EIO; } return 0; @@ -508,9 +508,9 @@ static int hinic_set_rx_lro(struct hinic_dev *nic_dev, u8 ipv4_en, u8 ipv6_en, &lro_cfg, &out_size); if (err || !out_size || lro_cfg.status) { dev_err(&pdev->dev, - "Failed to set lro offload, ret = %d\n", - lro_cfg.status); - return -EINVAL; + "Failed to set lro offload, err: %d, status: 0x%x, out size: 0x%x\n", + err, lro_cfg.status, out_size); + return -EIO; } return 0; @@ -542,10 +542,10 @@ static int hinic_set_rx_lro_timer(struct hinic_dev *nic_dev, u32 timer_value) if (err || !out_size || lro_timer.status) { dev_err(&pdev->dev, - "Failed to set lro timer, ret = %d\n", - lro_timer.status); + "Failed to set lro timer, err: %d, status: 0x%x, out size: 0x%x\n", + err, lro_timer.status, out_size); - return -EINVAL; + return -EIO; } return 0; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h index 14931adaffb8..9c3cbe45c9ec 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h @@ -189,6 +189,31 @@ struct hinic_port_link_status { u8 port_id; }; +struct hinic_cable_plug_event { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_id; + u8 plugged; /* 0: unplugged, 1: plugged */ + u8 port_id; +}; + +enum link_err_type { + LINK_ERR_MODULE_UNRECOGENIZED, + LINK_ERR_NUM, +}; + +struct hinic_link_err_event { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_id; + u8 err_type; + u8 port_id; +}; + struct hinic_port_func_state_cmd { u8 status; u8 version; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index caf7e81e3f62..141206917e4d 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -40,9 +40,9 @@ static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr, if (err || out_size != sizeof(mac_info) || (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY && mac_info.status != HINIC_MGMT_STATUS_EXIST)) { - dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to change MAC, ret = %d\n", - mac_info.status); - return -EFAULT; + dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set MAC, err: %d, status: 0x%x, out size: 0x%x\n", + err, mac_info.status, out_size); + return -EIO; } return 0; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 0fd7eae25fe9..5afb3c9c52d2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3206,7 +3206,7 @@ req_rx_irq_failed: req_tx_irq_failed: for (j = 0; j < i; j++) { free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); - irq_dispose_mapping(adapter->rx_scrq[j]->irq); + irq_dispose_mapping(adapter->tx_scrq[j]->irq); } release_sub_crqs(adapter, 1); return rc; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 3cd13fd55011..5aa86318ed3e 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -295,6 +295,7 @@ config ICE default n depends on PCI_MSI select NET_DEVLINK + select PLDMFW help This driver supports Intel(R) Ethernet Connection E800 Series of devices. For more information on how to identify your adapter, go diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 91c64f91a835..36da059388dc 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2993,8 +2993,6 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) e100_down(nic); netif_device_detach(netdev); - pci_save_state(pdev); - if ((nic->flags & wol_magic) | e100_asf(nic)) { /* enable reverse auto-negotiation */ if (nic->phy == phy_82552_v) { @@ -3024,24 +3022,22 @@ static int __e100_power_off(struct pci_dev *pdev, bool wake) return 0; } -#ifdef CONFIG_PM -static int e100_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused e100_suspend(struct device *dev_d) { bool wake; - __e100_shutdown(pdev, &wake); - return __e100_power_off(pdev, wake); + + __e100_shutdown(to_pci_dev(dev_d), &wake); + + device_wakeup_disable(dev_d); + + return 0; } -static int e100_resume(struct pci_dev *pdev) +static int __maybe_unused e100_resume(struct device *dev_d) { - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev_d); struct nic *nic = netdev_priv(netdev); - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* ack any pending wake events, disable PME */ - pci_enable_wake(pdev, PCI_D0, 0); - /* disable reverse auto-negotiation */ if (nic->phy == phy_82552_v) { u16 smartspeed = mdio_read(netdev, nic->mii.phy_id, @@ -3058,7 +3054,6 @@ static int e100_resume(struct pci_dev *pdev) return 0; } -#endif /* CONFIG_PM */ static void e100_shutdown(struct pci_dev *pdev) { @@ -3146,16 +3141,17 @@ static const struct pci_error_handlers e100_err_handler = { .resume = e100_io_resume, }; +static SIMPLE_DEV_PM_OPS(e100_pm_ops, e100_suspend, e100_resume); + static struct pci_driver e100_driver = { .name = DRV_NAME, .id_table = e100_id_table, .probe = e100_probe, .remove = e100_remove, -#ifdef CONFIG_PM + /* Power Management hooks */ - .suspend = e100_suspend, - .resume = e100_resume, -#endif + .driver.pm = &e100_pm_ops, + .shutdown = e100_shutdown, .err_handler = &e100_err_handler, }; diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 0b4196d2cdd4..f976e9daa3d8 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -1356,8 +1356,8 @@ static void e1000_create_lbtest_frame(struct sk_buff *skb, memset(skb->data, 0xFF, frame_size); frame_size &= ~1; memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); - memset(&skb->data[frame_size / 2 + 10], 0xBE, 1); - memset(&skb->data[frame_size / 2 + 12], 0xAF, 1); + skb->data[frame_size / 2 + 10] = 0xBE; + skb->data[frame_size / 2 + 12] = 0xAF; } static int e1000_check_lbtest_frame(const unsigned char *data, diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 64f684dc6c7a..a8fc9208382c 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1608,8 +1608,8 @@ static void e1000_create_lbtest_frame(struct sk_buff *skb, memset(skb->data, 0xFF, frame_size); frame_size &= ~1; memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); - memset(&skb->data[frame_size / 2 + 10], 0xBE, 1); - memset(&skb->data[frame_size / 2 + 12], 0xAF, 1); + skb->data[frame_size / 2 + 10] = 0xBE; + skb->data[frame_size / 2 + 12] = 0xAF; } static int e1000_check_lbtest_frame(struct sk_buff *skb, diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index ae0a6332fd30..b2f2fcfdf732 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -301,10 +301,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) */ hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_unknown; ret_val = e1000_disable_ulp_lpt_lp(hw, true); - if (ret_val) { + if (ret_val) e_warn("Failed to disable ULP\n"); - goto out; - } ret_val = hw->phy.ops.acquire(hw); if (ret_val) { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 48c956d90b90..d870343cf689 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3766,7 +3766,6 @@ err_dma: return err; } -#ifdef CONFIG_PM /** * iavf_suspend - Power management suspend routine * @pdev: PCI device information struct @@ -3774,11 +3773,10 @@ err_dma: * * Called when the system (VM) is entering sleep/suspend. **/ -static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused iavf_suspend(struct device *dev_d) { - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev_d); struct iavf_adapter *adapter = netdev_priv(netdev); - int retval = 0; netif_device_detach(netdev); @@ -3796,12 +3794,6 @@ static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); - retval = pci_save_state(pdev); - if (retval) - return retval; - - pci_disable_device(pdev); - return 0; } @@ -3811,24 +3803,13 @@ static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) * * Called when the system (VM) is resumed from sleep/suspend. **/ -static int iavf_resume(struct pci_dev *pdev) +static int __maybe_unused iavf_resume(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); struct iavf_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; u32 err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); - - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend.\n"); - return err; - } pci_set_master(pdev); rtnl_lock(); @@ -3852,7 +3833,6 @@ static int iavf_resume(struct pci_dev *pdev) return err; } -#endif /* CONFIG_PM */ /** * iavf_remove - Device Removal Routine * @pdev: PCI device information struct @@ -3954,16 +3934,15 @@ static void iavf_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); + static struct pci_driver iavf_driver = { - .name = iavf_driver_name, - .id_table = iavf_pci_tbl, - .probe = iavf_probe, - .remove = iavf_remove, -#ifdef CONFIG_PM - .suspend = iavf_suspend, - .resume = iavf_resume, -#endif - .shutdown = iavf_shutdown, + .name = iavf_driver_name, + .id_table = iavf_pci_tbl, + .probe = iavf_probe, + .remove = iavf_remove, + .driver.pm = &iavf_pm_ops, + .shutdown = iavf_shutdown, }; /** diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 980bbcc64b4b..6da4f43f2348 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -23,6 +23,7 @@ ice-y := ice_main.o \ ice_flex_pipe.o \ ice_flow.o \ ice_devlink.o \ + ice_fw_update.o \ ice_ethtool.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index c665220bb637..fe140ff38f74 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -19,6 +19,7 @@ #include <linux/dma-mapping.h> #include <linux/pci.h> #include <linux/workqueue.h> +#include <linux/wait.h> #include <linux/aer.h> #include <linux/interrupt.h> #include <linux/ethtool.h> @@ -255,6 +256,7 @@ struct ice_vsi { u32 tx_busy; u32 rx_buf_failed; u32 rx_page_failed; + u32 rx_gro_dropped; u16 num_q_vectors; u16 base_vector; /* IRQ base for OS reserved vectors */ enum ice_vsi_type type; @@ -412,6 +414,12 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ u32 msg_enable; + + /* spinlock to protect the AdminQ wait list */ + spinlock_t aq_wait_lock; + struct hlist_head aq_wait_list; + wait_queue_head_t aq_wait_queue; + u32 hw_csum_rx_error; u16 oicr_idx; /* Other interrupt cause MSIX vector index */ u16 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ @@ -593,6 +601,8 @@ void ice_fdir_release_flows(struct ice_hw *hw); void ice_fdir_replay_flows(struct ice_hw *hw); void ice_fdir_replay_fltrs(struct ice_pf *pf); int ice_fdir_create_dflt_rules(struct ice_pf *pf); +int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, + struct ice_rq_event_info *event); int ice_open(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index b363e0223670..ba9375218fef 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -109,6 +109,13 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_MSIX 0x0043 #define ICE_AQC_CAPS_FD 0x0045 #define ICE_AQC_CAPS_MAX_MTU 0x0047 +#define ICE_AQC_CAPS_NVM_VER 0x0048 +#define ICE_AQC_CAPS_PENDING_NVM_VER 0x0049 +#define ICE_AQC_CAPS_OROM_VER 0x004A +#define ICE_AQC_CAPS_PENDING_OROM_VER 0x004B +#define ICE_AQC_CAPS_NET_VER 0x004C +#define ICE_AQC_CAPS_PENDING_NET_VER 0x004D +#define ICE_AQC_CAPS_NVM_MGMT 0x0080 u8 major_ver; u8 minor_ver; @@ -1298,7 +1305,14 @@ struct ice_aqc_nvm { #define ICE_AQC_NVM_PRESERVATION_M (3 << ICE_AQC_NVM_PRESERVATION_S) #define ICE_AQC_NVM_NO_PRESERVATION (0 << ICE_AQC_NVM_PRESERVATION_S) #define ICE_AQC_NVM_PRESERVE_ALL BIT(1) +#define ICE_AQC_NVM_FACTORY_DEFAULT (2 << ICE_AQC_NVM_PRESERVATION_S) #define ICE_AQC_NVM_PRESERVE_SELECTED (3 << ICE_AQC_NVM_PRESERVATION_S) +#define ICE_AQC_NVM_ACTIV_SEL_NVM BIT(3) /* Write Activate/SR Dump only */ +#define ICE_AQC_NVM_ACTIV_SEL_OROM BIT(4) +#define ICE_AQC_NVM_ACTIV_SEL_NETLIST BIT(5) +#define ICE_AQC_NVM_SPECIAL_UPDATE BIT(6) +#define ICE_AQC_NVM_REVERT_LAST_ACTIV BIT(6) /* Write Activate only */ +#define ICE_AQC_NVM_ACTIV_SEL_MASK ICE_M(0x7, 3) #define ICE_AQC_NVM_FLASH_ONLY BIT(7) __le16 module_typeid; __le16 length; @@ -1347,6 +1361,67 @@ struct ice_aqc_nvm_checksum { #define ICE_AQC_NVM_NETLIST_ID_BLK_SHA_HASH 0xA #define ICE_AQC_NVM_NETLIST_ID_BLK_CUST_VER 0x2F +/* Used for NVM Set Package Data command - 0x070A */ +struct ice_aqc_nvm_pkg_data { + u8 reserved[3]; + u8 cmd_flags; +#define ICE_AQC_NVM_PKG_DELETE BIT(0) /* used for command call */ +#define ICE_AQC_NVM_PKG_SKIPPED BIT(0) /* used for command response */ + + u32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +/* Used for Pass Component Table command - 0x070B */ +struct ice_aqc_nvm_pass_comp_tbl { + u8 component_response; /* Response only */ +#define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED 0x0 +#define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE 0x1 +#define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED 0x2 + u8 component_response_code; /* Response only */ +#define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE 0x0 +#define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE 0x1 +#define ICE_AQ_NVM_PASS_COMP_STAMP_LOWER 0x2 +#define ICE_AQ_NVM_PASS_COMP_INVALID_STAMP_CODE 0x3 +#define ICE_AQ_NVM_PASS_COMP_CONFLICT_CODE 0x4 +#define ICE_AQ_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE 0x5 +#define ICE_AQ_NVM_PASS_COMP_NOT_SUPPORTED_CODE 0x6 +#define ICE_AQ_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE 0x7 +#define ICE_AQ_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE 0x8 +#define ICE_AQ_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE 0xA +#define ICE_AQ_NVM_PASS_COMP_VER_STR_LOWER_CODE 0xB + u8 reserved; + u8 transfer_flag; +#define ICE_AQ_NVM_PASS_COMP_TBL_START 0x1 +#define ICE_AQ_NVM_PASS_COMP_TBL_MIDDLE 0x2 +#define ICE_AQ_NVM_PASS_COMP_TBL_END 0x4 +#define ICE_AQ_NVM_PASS_COMP_TBL_START_AND_END 0x5 + __le32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_aqc_nvm_comp_tbl { + __le16 comp_class; +#define NVM_COMP_CLASS_ALL_FW 0x000A + + __le16 comp_id; +#define NVM_COMP_ID_OROM 0x5 +#define NVM_COMP_ID_NVM 0x6 +#define NVM_COMP_ID_NETLIST 0x8 + + u8 comp_class_idx; +#define FWU_COMP_CLASS_IDX_NOT_USE 0x0 + + __le32 comp_cmp_stamp; + u8 cvs_type; +#define NVM_CVS_TYPE_ASCII 0x1 + + u8 cvs_len; + u8 cvs[]; /* Component Version String */ +} __packed; + /** * Send to PF command (indirect 0x0801) ID is only used by PF * @@ -1506,7 +1581,7 @@ struct ice_aqc_get_set_rss_keys { struct ice_aqc_get_set_rss_lut { #define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15) #define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x1FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S) +#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S) __le16 vsi_id; #define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S 0 #define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M \ @@ -1794,6 +1869,8 @@ struct ice_aq_desc { struct ice_aqc_rl_profile rl_profile; struct ice_aqc_nvm nvm; struct ice_aqc_nvm_checksum nvm_checksum; + struct ice_aqc_nvm_pkg_data pkg_data; + struct ice_aqc_nvm_pass_comp_tbl pass_comp_tbl; struct ice_aqc_pf_vf_msg virt; struct ice_aqc_lldp_get_mib lldp_get_mib; struct ice_aqc_lldp_set_mib_change lldp_set_event; @@ -1922,7 +1999,13 @@ enum ice_adminq_opc { /* NVM commands */ ice_aqc_opc_nvm_read = 0x0701, + ice_aqc_opc_nvm_erase = 0x0702, + ice_aqc_opc_nvm_write = 0x0703, ice_aqc_opc_nvm_checksum = 0x0706, + ice_aqc_opc_nvm_write_activate = 0x0707, + ice_aqc_opc_nvm_update_empr = 0x0709, + ice_aqc_opc_nvm_pkg_data = 0x070A, + ice_aqc_opc_nvm_pass_component_tbl = 0x070B, /* PF/VF mailbox commands */ ice_mbx_opc_send_msg_to_pf = 0x0801, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index c72cc77b8d67..34abfcea9858 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -611,8 +611,6 @@ static enum ice_status ice_get_fw_log_cfg(struct ice_hw *hw) ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging_info); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - status = ice_aq_send_cmd(hw, &desc, config, size, NULL); if (!status) { u16 i; @@ -1029,23 +1027,23 @@ void ice_deinit_hw(struct ice_hw *hw) */ enum ice_status ice_check_reset(struct ice_hw *hw) { - u32 cnt, reg = 0, grst_delay, uld_mask; + u32 cnt, reg = 0, grst_timeout, uld_mask; /* Poll for Device Active state in case a recent CORER, GLOBR, * or EMPR has occurred. The grst delay value is in 100ms units. * Add 1sec for outstanding AQ commands that can take a long time. */ - grst_delay = ((rd32(hw, GLGEN_RSTCTL) & GLGEN_RSTCTL_GRSTDEL_M) >> - GLGEN_RSTCTL_GRSTDEL_S) + 10; + grst_timeout = ((rd32(hw, GLGEN_RSTCTL) & GLGEN_RSTCTL_GRSTDEL_M) >> + GLGEN_RSTCTL_GRSTDEL_S) + 10; - for (cnt = 0; cnt < grst_delay; cnt++) { + for (cnt = 0; cnt < grst_timeout; cnt++) { mdelay(100); reg = rd32(hw, GLGEN_RSTAT); if (!(reg & GLGEN_RSTAT_DEVSTATE_M)) break; } - if (cnt == grst_delay) { + if (cnt == grst_timeout) { ice_debug(hw, ICE_DBG_INIT, "Global reset polling failed to complete.\n"); return ICE_ERR_RESET_FAILED; @@ -1720,8 +1718,7 @@ ice_alloc_res_exit: * @num: number of resources * @res: pointer to array that contains the resources to free */ -enum ice_status -ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) +enum ice_status ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) { struct ice_aqc_alloc_free_res_elem *buf; enum ice_status status; @@ -1857,6 +1854,25 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, "%s: msix_vector_first_id = %d\n", prefix, caps->msix_vector_first_id); break; + case ICE_AQC_CAPS_PENDING_NVM_VER: + caps->nvm_update_pending_nvm = true; + ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_nvm\n", prefix); + break; + case ICE_AQC_CAPS_PENDING_OROM_VER: + caps->nvm_update_pending_orom = true; + ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_orom\n", prefix); + break; + case ICE_AQC_CAPS_PENDING_NET_VER: + caps->nvm_update_pending_netlist = true; + ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_netlist\n", prefix); + break; + case ICE_AQC_CAPS_NVM_MGMT: + caps->nvm_unified_update = + (number & ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ? + true : false; + ice_debug(hw, ICE_DBG_INIT, "%s: nvm_unified_update = %d\n", prefix, + caps->nvm_unified_update); + break; case ICE_AQC_CAPS_MAX_MTU: caps->max_mtu = number; ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n", @@ -2104,7 +2120,7 @@ ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, * @cap_count: the number of capabilities * * Helper device to parse device (0x000B) capabilities list. For - * capabilities shared between device and device, this relies on + * capabilities shared between device and function, this relies on * ice_parse_common_caps. * * Loop through the list of provided capabilities and extract the relevant @@ -2204,7 +2220,7 @@ ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, * Read the device capabilities and extract them into the dev_caps structure * for later use. */ -static enum ice_status +enum ice_status ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps) { enum ice_status status; @@ -3888,7 +3904,18 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, * Without setting the generic section as valid in valid_sections, the * Admin queue command will fail with error code ICE_AQ_RC_EINVAL. */ - buf->txqs[0].info.valid_sections = ICE_AQC_ELEM_VALID_GENERIC; + buf->txqs[0].info.valid_sections = + ICE_AQC_ELEM_VALID_GENERIC | ICE_AQC_ELEM_VALID_CIR | + ICE_AQC_ELEM_VALID_EIR; + buf->txqs[0].info.generic = 0; + buf->txqs[0].info.cir_bw.bw_profile_idx = + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->txqs[0].info.cir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); + buf->txqs[0].info.eir_bw.bw_profile_idx = + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->txqs[0].info.eir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); /* add the LAN queue */ status = ice_aq_add_lan_txq(hw, num_qgrps, buf, buf_size, cd); @@ -4338,3 +4365,36 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps) return false; } + +/** + * ice_aq_set_lldp_mib - Set the LLDP MIB + * @hw: pointer to the HW struct + * @mib_type: Local, Remote or both Local and Remote MIBs + * @buf: pointer to the caller-supplied buffer to store the MIB block + * @buf_size: size of the buffer (in bytes) + * @cd: pointer to command details structure or NULL + * + * Set the LLDP MIB. (0x0A08) + */ +enum ice_status +ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, + struct ice_sq_cd *cd) +{ + struct ice_aqc_lldp_set_local_mib *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.lldp_set_mib; + + if (buf_size == 0 || !buf) + return ICE_ERR_PARAM; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib); + + desc.flags |= cpu_to_le16((u16)ICE_AQ_FLAG_RD); + desc.datalen = cpu_to_le16(buf_size); + + cmd->type = mib_type; + cmd->length = cpu_to_le16(buf_size); + + return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); +} diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 33a681a75439..3ebb973878c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -11,8 +11,6 @@ #include "ice_switch.h" #include <linux/avf/virtchnl.h> -enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw); - enum ice_status ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); enum ice_status ice_check_reset(struct ice_hw *hw); @@ -90,6 +88,8 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, enum ice_status ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd); +enum ice_status +ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps); void ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high, u16 link_speeds_bitmap); @@ -172,4 +172,7 @@ ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, enum ice_status ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); +enum ice_status +ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, + struct ice_sq_cd *cd); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 1e18021aa073..1f46a7828be8 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -312,9 +312,10 @@ ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) #define ICE_FREE_CQ_BUFS(hw, qi, ring) \ do { \ - int i; \ /* free descriptors */ \ - if ((qi)->ring.r.ring##_bi) \ + if ((qi)->ring.r.ring##_bi) { \ + int i; \ + \ for (i = 0; i < (qi)->num_##ring##_entries; i++) \ if ((qi)->ring.r.ring##_bi[i].pa) { \ dmam_free_coherent(ice_hw_to_dev(hw), \ @@ -325,6 +326,7 @@ do { \ (qi)->ring.r.ring##_bi[i].pa = 0;\ (qi)->ring.r.ring##_bi[i].size = 0;\ } \ + } \ /* free the buffer info list */ \ if ((qi)->ring.cmd_buf) \ devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf); \ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 2cecc9d08005..2a3147ee0bbb 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -135,39 +135,6 @@ ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd) } /** - * ice_aq_set_lldp_mib - Set the LLDP MIB - * @hw: pointer to the HW struct - * @mib_type: Local, Remote or both Local and Remote MIBs - * @buf: pointer to the caller-supplied buffer to store the MIB block - * @buf_size: size of the buffer (in bytes) - * @cd: pointer to command details structure or NULL - * - * Set the LLDP MIB. (0x0A08) - */ -static enum ice_status -ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, - struct ice_sq_cd *cd) -{ - struct ice_aqc_lldp_set_local_mib *cmd; - struct ice_aq_desc desc; - - cmd = &desc.params.lldp_set_mib; - - if (buf_size == 0 || !buf) - return ICE_ERR_PARAM; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib); - - desc.flags |= cpu_to_le16((u16)ICE_AQ_FLAG_RD); - desc.datalen = cpu_to_le16(buf_size); - - cmd->type = mib_type; - cmd->length = cpu_to_le16(buf_size); - - return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); -} - -/** * ice_get_dcbx_status * @hw: pointer to the HW struct * diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 979af197f8a3..36abd6b7280c 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -444,10 +444,6 @@ void ice_dcb_rebuild(struct ice_pf *pf) goto dcb_error; } - /* If DCB was not enabled previously, we are done */ - if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags)) - return; - mutex_lock(&pf->tc_mutex); if (!pf->hw.port_info->is_sw_lldp) @@ -467,7 +463,7 @@ void ice_dcb_rebuild(struct ice_pf *pf) } } - dev_info(dev, "DCB restored after reset\n"); + dev_info(dev, "DCB info restored\n"); ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { dev_err(dev, "Query Port ETS failed\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 323238669572..35c21d9ae009 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -53,6 +53,12 @@ ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { tlan_ctx->cgd_num = ring->dcb_tc; } + +static inline bool ice_is_dcb_active(struct ice_pf *pf) +{ + return (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) || + test_bit(ICE_FLAG_DCB_ENA, pf->flags)); +} #else #define ice_dcb_rebuild(pf) do {} while (0) @@ -95,6 +101,11 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring, return 0; } +static inline bool ice_is_dcb_active(struct ice_pf __always_unused *pf) +{ + return false; +} + static inline bool ice_is_pfc_causing_hung_q(struct ice_pf __always_unused *pf, unsigned int __always_unused txqueue) diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 43da2dcb0cbc..111d6bfe4222 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -4,6 +4,7 @@ #include "ice.h" #include "ice_lib.h" #include "ice_devlink.h" +#include "ice_fw_update.h" static int ice_info_get_dsn(struct ice_pf *pf, char *buf, size_t len) { @@ -229,8 +230,61 @@ static int ice_devlink_info_get(struct devlink *devlink, return 0; } +/** + * ice_devlink_flash_update - Update firmware stored in flash on the device + * @devlink: pointer to devlink associated with device to update + * @path: the path of the firmware file to use via request_firmware + * @component: name of the component to update, or NULL + * @extack: netlink extended ACK structure + * + * Perform a device flash update. The bulk of the update logic is contained + * within the ice_flash_pldm_image function. + * + * Returns: zero on success, or an error code on failure. + */ +static int +ice_devlink_flash_update(struct devlink *devlink, const char *path, + const char *component, struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = &pf->pdev->dev; + struct ice_hw *hw = &pf->hw; + const struct firmware *fw; + int err; + + /* individual component update is not yet supported */ + if (component) + return -EOPNOTSUPP; + + if (!hw->dev_caps.common_cap.nvm_unified_update) { + NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); + return -EOPNOTSUPP; + } + + err = ice_check_for_pending_update(pf, component, extack); + if (err) + return err; + + err = request_firmware(&fw, path, dev); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Unable to read file from disk"); + return err; + } + + devlink_flash_update_begin_notify(devlink); + devlink_flash_update_status_notify(devlink, "Preparing to flash", + component, 0, 0); + err = ice_flash_pldm_image(pf, fw, extack); + devlink_flash_update_end_notify(devlink); + + release_firmware(fw); + + return err; +} + static const struct devlink_ops ice_devlink_ops = { .info_get = ice_devlink_info_get, + .flash_update = ice_devlink_flash_update, }; static void ice_devlink_free(void *devlink_ptr) @@ -303,7 +357,7 @@ void ice_devlink_unregister(struct ice_pf *pf) * * Create and register a devlink_port for this PF. Note that although each * physical function is connected to a separate devlink instance, the port - * will still be numbered according to the physical function id. + * will still be numbered according to the physical function ID. * * Return: zero on success or an error code on failure. */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 06b93e97892d..9e8e9531cd87 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -59,8 +59,11 @@ static const struct ice_stats ice_gstrings_vsi_stats[] = { ICE_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol), ICE_VSI_STAT("rx_alloc_fail", rx_buf_failed), ICE_VSI_STAT("rx_pg_alloc_fail", rx_page_failed), + ICE_VSI_STAT("rx_gro_dropped", rx_gro_dropped), ICE_VSI_STAT("tx_errors", eth_stats.tx_errors), ICE_VSI_STAT("tx_linearize", tx_linearize), + ICE_VSI_STAT("tx_busy", tx_busy), + ICE_VSI_STAT("tx_restart", tx_restart), }; enum ice_ethtool_test_id { @@ -100,6 +103,7 @@ static const struct ice_stats ice_gstrings_pf_stats[] = { ICE_PF_STAT("rx_broadcast.nic", stats.eth.rx_broadcast), ICE_PF_STAT("tx_broadcast.nic", stats.eth.tx_broadcast), ICE_PF_STAT("tx_errors.nic", stats.eth.tx_errors), + ICE_PF_STAT("tx_timeout.nic", tx_timeout_count), ICE_PF_STAT("rx_size_64.nic", stats.rx_size_64), ICE_PF_STAT("tx_size_64.nic", stats.tx_size_64), ICE_PF_STAT("rx_size_127.nic", stats.rx_size_127), diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 3c217e51b27e..b17ae3e20157 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -644,7 +644,7 @@ static bool ice_bits_max_set(const u8 *mask, u16 size, u16 max) * This function generates a key from a value, a don't care mask and a never * match mask. * upd, dc, and nm are optional parameters, and can be NULL: - * upd == NULL --> udp mask is all 1's (update all bits) + * upd == NULL --> upd mask is all 1's (update all bits) * dc == NULL --> dc mask is all 0's (no don't care bits) * nm == NULL --> nm mask is all 0's (no never match bits) */ @@ -2921,6 +2921,8 @@ static void ice_free_flow_profs(struct ice_hw *hw, u8 blk_idx) ICE_FLOW_ENTRY_HNDL(e)); list_del(&p->l_entry); + + mutex_destroy(&p->entries_lock); devm_kfree(ice_hw_to_dev(hw), p); } mutex_unlock(&hw->fl_profs_locks[blk_idx]); @@ -3038,7 +3040,7 @@ void ice_clear_hw_tbls(struct ice_hw *hw) memset(prof_redir->t, 0, prof_redir->count * sizeof(*prof_redir->t)); - memset(es->t, 0, es->count * sizeof(*es->t)); + memset(es->t, 0, es->count * sizeof(*es->t) * es->fvw); memset(es->ref_count, 0, es->count * sizeof(*es->ref_count)); memset(es->written, 0, es->count * sizeof(*es->written)); } @@ -3149,10 +3151,12 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw) es->ref_count = devm_kcalloc(ice_hw_to_dev(hw), es->count, sizeof(*es->ref_count), GFP_KERNEL); + if (!es->ref_count) + goto err; es->written = devm_kcalloc(ice_hw_to_dev(hw), es->count, sizeof(*es->written), GFP_KERNEL); - if (!es->ref_count) + if (!es->written) goto err; } return 0; @@ -3874,16 +3878,16 @@ err_ice_add_prof: } /** - * ice_search_prof_id_low - Search for a profile tracking ID low level + * ice_search_prof_id - Search for a profile tracking ID * @hw: pointer to the HW struct * @blk: hardware block * @id: profile tracking ID * - * This will search for a profile tracking ID which was previously added. This - * version assumes that the caller has already acquired the prof map lock. + * This will search for a profile tracking ID which was previously added. + * The profile map lock should be held before calling this function. */ static struct ice_prof_map * -ice_search_prof_id_low(struct ice_hw *hw, enum ice_block blk, u64 id) +ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id) { struct ice_prof_map *entry = NULL; struct ice_prof_map *map; @@ -3898,26 +3902,6 @@ ice_search_prof_id_low(struct ice_hw *hw, enum ice_block blk, u64 id) } /** - * ice_search_prof_id - Search for a profile tracking ID - * @hw: pointer to the HW struct - * @blk: hardware block - * @id: profile tracking ID - * - * This will search for a profile tracking ID which was previously added. - */ -static struct ice_prof_map * -ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id) -{ - struct ice_prof_map *entry; - - mutex_lock(&hw->blk[blk].es.prof_map_lock); - entry = ice_search_prof_id_low(hw, blk, id); - mutex_unlock(&hw->blk[blk].es.prof_map_lock); - - return entry; -} - -/** * ice_vsig_prof_id_count - count profiles in a VSIG * @hw: pointer to the HW struct * @blk: hardware block @@ -4133,7 +4117,7 @@ enum ice_status ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id) mutex_lock(&hw->blk[blk].es.prof_map_lock); - pmap = ice_search_prof_id_low(hw, blk, id); + pmap = ice_search_prof_id(hw, blk, id); if (!pmap) { status = ICE_ERR_DOES_NOT_EXIST; goto err_ice_rem_prof; @@ -4166,22 +4150,28 @@ static enum ice_status ice_get_prof(struct ice_hw *hw, enum ice_block blk, u64 hdl, struct list_head *chg) { + enum ice_status status = 0; struct ice_prof_map *map; struct ice_chs_chg *p; u16 i; + mutex_lock(&hw->blk[blk].es.prof_map_lock); /* Get the details on the profile specified by the handle ID */ map = ice_search_prof_id(hw, blk, hdl); - if (!map) - return ICE_ERR_DOES_NOT_EXIST; + if (!map) { + status = ICE_ERR_DOES_NOT_EXIST; + goto err_ice_get_prof; + } for (i = 0; i < map->ptg_cnt; i++) if (!hw->blk[blk].es.written[map->prof_id]) { /* add ES to change list */ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); - if (!p) + if (!p) { + status = ICE_ERR_NO_MEMORY; goto err_ice_get_prof; + } p->type = ICE_PTG_ES_ADD; p->ptype = 0; @@ -4196,11 +4186,10 @@ ice_get_prof(struct ice_hw *hw, enum ice_block blk, u64 hdl, list_add(&p->list_entry, chg); } - return 0; - err_ice_get_prof: + mutex_unlock(&hw->blk[blk].es.prof_map_lock); /* let caller clean up the change list */ - return ICE_ERR_NO_MEMORY; + return status; } /** @@ -4254,17 +4243,23 @@ static enum ice_status ice_add_prof_to_lst(struct ice_hw *hw, enum ice_block blk, struct list_head *lst, u64 hdl) { + enum ice_status status = 0; struct ice_prof_map *map; struct ice_vsig_prof *p; u16 i; + mutex_lock(&hw->blk[blk].es.prof_map_lock); map = ice_search_prof_id(hw, blk, hdl); - if (!map) - return ICE_ERR_DOES_NOT_EXIST; + if (!map) { + status = ICE_ERR_DOES_NOT_EXIST; + goto err_ice_add_prof_to_lst; + } p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); - if (!p) - return ICE_ERR_NO_MEMORY; + if (!p) { + status = ICE_ERR_NO_MEMORY; + goto err_ice_add_prof_to_lst; + } p->profile_cookie = map->profile_cookie; p->prof_id = map->prof_id; @@ -4278,7 +4273,9 @@ ice_add_prof_to_lst(struct ice_hw *hw, enum ice_block blk, list_add(&p->list, lst); - return 0; +err_ice_add_prof_to_lst: + mutex_unlock(&hw->blk[blk].es.prof_map_lock); + return status; } /** @@ -4496,16 +4493,12 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0x00, 0x00, 0x00 }; u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x00, 0x00, 0x00, 0x00, 0x00 }; + enum ice_status status = 0; struct ice_prof_map *map; struct ice_vsig_prof *t; struct ice_chs_chg *p; u16 vsig_idx, i; - /* Get the details on the profile specified by the handle ID */ - map = ice_search_prof_id(hw, blk, hdl); - if (!map) - return ICE_ERR_DOES_NOT_EXIST; - /* Error, if this VSIG already has this profile */ if (ice_has_prof_vsig(hw, blk, vsig, hdl)) return ICE_ERR_ALREADY_EXISTS; @@ -4515,19 +4508,28 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, if (!t) return ICE_ERR_NO_MEMORY; + mutex_lock(&hw->blk[blk].es.prof_map_lock); + /* Get the details on the profile specified by the handle ID */ + map = ice_search_prof_id(hw, blk, hdl); + if (!map) { + status = ICE_ERR_DOES_NOT_EXIST; + goto err_ice_add_prof_id_vsig; + } + t->profile_cookie = map->profile_cookie; t->prof_id = map->prof_id; t->tcam_count = map->ptg_cnt; /* create TCAM entries */ for (i = 0; i < map->ptg_cnt; i++) { - enum ice_status status; u16 tcam_idx; /* add TCAM to change list */ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); - if (!p) + if (!p) { + status = ICE_ERR_NO_MEMORY; goto err_ice_add_prof_id_vsig; + } /* allocate the TCAM entry index */ status = ice_alloc_tcam_ent(hw, blk, &tcam_idx); @@ -4571,12 +4573,14 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, list_add(&t->list, &hw->blk[blk].xlt2.vsig_tbl[vsig_idx].prop_lst); - return 0; + mutex_unlock(&hw->blk[blk].es.prof_map_lock); + return status; err_ice_add_prof_id_vsig: + mutex_unlock(&hw->blk[blk].es.prof_map_lock); /* let caller clean up the change list */ devm_kfree(ice_hw_to_dev(hw), t); - return ICE_ERR_NO_MEMORY; + return status; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index d74e5290677f..fe677621dd51 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1187,7 +1187,7 @@ enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle) if (list_empty(&hw->fl_profs[blk])) return 0; - mutex_lock(&hw->fl_profs_locks[blk]); + mutex_lock(&hw->rss_locks); list_for_each_entry_safe(p, t, &hw->fl_profs[blk], l_entry) if (test_bit(vsi_handle, p->vsis)) { status = ice_flow_disassoc_prof(hw, blk, p, vsi_handle); @@ -1195,12 +1195,12 @@ enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle) break; if (bitmap_empty(p->vsis, ICE_MAX_VSI)) { - status = ice_flow_rem_prof_sync(hw, blk, p); + status = ice_flow_rem_prof(hw, blk, p->id); if (status) break; } } - mutex_unlock(&hw->fl_profs_locks[blk]); + mutex_unlock(&hw->rss_locks); return status; } @@ -1597,7 +1597,8 @@ enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle) */ u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs) { - struct ice_rss_cfg *r, *rss_cfg = NULL; + u64 rss_hash = ICE_HASH_INVALID; + struct ice_rss_cfg *r; /* verify if the protocol header is non zero and VSI is valid */ if (hdrs == ICE_FLOW_SEG_HDR_NONE || !ice_is_vsi_valid(hw, vsi_handle)) @@ -1607,10 +1608,10 @@ u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs) list_for_each_entry(r, &hw->rss_list_head, l_entry) if (test_bit(vsi_handle, r->vsis) && r->packet_hdr == hdrs) { - rss_cfg = r; + rss_hash = r->hashed_flds; break; } mutex_unlock(&hw->rss_locks); - return rss_cfg ? rss_cfg->hashed_flds : ICE_HASH_INVALID; + return rss_hash; } diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c new file mode 100644 index 000000000000..deaefe00c9c0 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -0,0 +1,773 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#include <asm/unaligned.h> +#include <linux/uuid.h> +#include <linux/crc32.h> +#include <linux/pldmfw.h> +#include "ice.h" +#include "ice_fw_update.h" + +struct ice_fwu_priv { + struct pldmfw context; + + struct ice_pf *pf; + struct netlink_ext_ack *extack; + + /* Track which NVM banks to activate at the end of the update */ + u8 activate_flags; +}; + +/** + * ice_send_package_data - Send record package data to firmware + * @context: PLDM fw update structure + * @data: pointer to the package data + * @length: length of the package data + * + * Send a copy of the package data associated with the PLDM record matching + * this device to the firmware. + * + * Note that this function sends an AdminQ command that will fail unless the + * NVM resource has been acquired. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_send_package_data(struct pldmfw *context, const u8 *data, u16 length) +{ + struct ice_fwu_priv *priv = container_of(context, struct ice_fwu_priv, context); + struct netlink_ext_ack *extack = priv->extack; + struct device *dev = context->dev; + struct ice_pf *pf = priv->pf; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + u8 *package_data; + + package_data = kmemdup(data, length, GFP_KERNEL); + if (!package_data) + return -ENOMEM; + + status = ice_nvm_set_pkg_data(hw, false, package_data, length, NULL); + + kfree(package_data); + + if (status) { + dev_err(dev, "Failed to send record package data to firmware, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to record package data to firmware"); + return -EIO; + } + + return 0; +} + +/** + * ice_check_component_response - Report firmware response to a component + * @pf: device private data structure + * @id: component id being checked + * @response: indicates whether this component can be updated + * @code: code indicating reason for response + * @extack: netlink extended ACK structure + * + * Check whether firmware indicates if this component can be updated. Report + * a suitable error message over the netlink extended ACK if the component + * cannot be updated. + * + * Returns: zero if the component can be updated, or -ECANCELED of the + * firmware indicates the component cannot be updated. + */ +static int +ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code, + struct netlink_ext_ack *extack) +{ + struct device *dev = ice_pf_to_dev(pf); + const char *component; + + switch (id) { + case NVM_COMP_ID_OROM: + component = "fw.undi"; + break; + case NVM_COMP_ID_NVM: + component = "fw.mgmt"; + break; + case NVM_COMP_ID_NETLIST: + component = "fw.netlist"; + break; + default: + WARN(1, "Unexpected unknown component identifier 0x%02x", id); + return -EINVAL; + } + + dev_dbg(dev, "%s: firmware response 0x%x, code 0x%x\n", + component, response, code); + + switch (response) { + case ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED: + /* firmware indicated this update is good to proceed */ + return 0; + case ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE: + dev_warn(dev, "firmware recommends not updating %s, as it may result in a downgrade. continuing anyways\n", component); + return 0; + case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED: + dev_info(dev, "firmware has rejected updating %s\n", component); + break; + } + + switch (code) { + case ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE: + dev_err(dev, "Component comparison stamp for %s is identical to the running image\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component comparison stamp is identical to running image"); + break; + case ICE_AQ_NVM_PASS_COMP_STAMP_LOWER: + dev_err(dev, "Component comparison stamp for %s is lower than the running image\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component comparison stamp is lower than running image"); + break; + case ICE_AQ_NVM_PASS_COMP_INVALID_STAMP_CODE: + dev_err(dev, "Component comparison stamp for %s is invalid\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component comparison stamp is invalid"); + break; + case ICE_AQ_NVM_PASS_COMP_CONFLICT_CODE: + dev_err(dev, "%s conflicts with a previous component table\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component table conflict occurred"); + break; + case ICE_AQ_NVM_PASS_COMP_PRE_REQ_NOT_MET_CODE: + dev_err(dev, "Pre-requisites for component %s have not been met\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component pre-requisites not met"); + break; + case ICE_AQ_NVM_PASS_COMP_NOT_SUPPORTED_CODE: + dev_err(dev, "%s is not a supported component\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component not supported"); + break; + case ICE_AQ_NVM_PASS_COMP_CANNOT_DOWNGRADE_CODE: + dev_err(dev, "Security restrictions prevent %s from being downgraded\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component cannot be downgraded"); + break; + case ICE_AQ_NVM_PASS_COMP_INCOMPLETE_IMAGE_CODE: + dev_err(dev, "Received an incomplete component image for %s\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Incomplete component image"); + break; + case ICE_AQ_NVM_PASS_COMP_VER_STR_IDENTICAL_CODE: + dev_err(dev, "Component version for %s is identical to the running image\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component version is identical to running image"); + break; + case ICE_AQ_NVM_PASS_COMP_VER_STR_LOWER_CODE: + dev_err(dev, "Component version for %s is lower than the running image\n", + component); + NL_SET_ERR_MSG_MOD(extack, "Component version is lower than the running image"); + break; + default: + dev_err(dev, "Unexpected response code 0x02%x for %s\n", + code, component); + NL_SET_ERR_MSG_MOD(extack, "Received unexpected response code from firmware"); + break; + } + + return -ECANCELED; +} + +/** + * ice_send_component_table - Send PLDM component table to firmware + * @context: PLDM fw update structure + * @component: the component to process + * @transfer_flag: relative transfer order of this component + * + * Read relevant data from the component and forward it to the device + * firmware. Check the response to determine if the firmware indicates that + * the update can proceed. + * + * This function sends AdminQ commands related to the NVM, and assumes that + * the NVM resource has been acquired. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_send_component_table(struct pldmfw *context, struct pldmfw_component *component, + u8 transfer_flag) +{ + struct ice_fwu_priv *priv = container_of(context, struct ice_fwu_priv, context); + struct netlink_ext_ack *extack = priv->extack; + struct ice_aqc_nvm_comp_tbl *comp_tbl; + u8 comp_response, comp_response_code; + struct device *dev = context->dev; + struct ice_pf *pf = priv->pf; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + size_t length; + + switch (component->identifier) { + case NVM_COMP_ID_OROM: + case NVM_COMP_ID_NVM: + case NVM_COMP_ID_NETLIST: + break; + default: + dev_err(dev, "Unable to update due to a firmware component with unknown ID %u\n", + component->identifier); + NL_SET_ERR_MSG_MOD(extack, "Unable to update due to unknown firmware component"); + return -EOPNOTSUPP; + } + + length = struct_size(comp_tbl, cvs, component->version_len); + comp_tbl = kzalloc(length, GFP_KERNEL); + if (!comp_tbl) + return -ENOMEM; + + comp_tbl->comp_class = cpu_to_le16(component->classification); + comp_tbl->comp_id = cpu_to_le16(component->identifier); + comp_tbl->comp_class_idx = FWU_COMP_CLASS_IDX_NOT_USE; + comp_tbl->comp_cmp_stamp = cpu_to_le32(component->comparison_stamp); + comp_tbl->cvs_type = component->version_type; + comp_tbl->cvs_len = component->version_len; + memcpy(comp_tbl->cvs, component->version_string, component->version_len); + + status = ice_nvm_pass_component_tbl(hw, (u8 *)comp_tbl, length, + transfer_flag, &comp_response, + &comp_response_code, NULL); + + kfree(comp_tbl); + + if (status) { + dev_err(dev, "Failed to transfer component table to firmware, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to transfer component table to firmware"); + return -EIO; + } + + return ice_check_component_response(pf, component->identifier, comp_response, + comp_response_code, extack); +} + +/** + * ice_write_one_nvm_block - Write an NVM block and await completion response + * @pf: the PF data structure + * @module: the module to write to + * @offset: offset in bytes + * @block_size: size of the block to write, up to 4k + * @block: pointer to block of data to write + * @last_cmd: whether this is the last command + * @extack: netlink extended ACK structure + * + * Write a block of data to a flash module, and await for the completion + * response message from firmware. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, + u16 block_size, u8 *block, bool last_cmd, + struct netlink_ext_ack *extack) +{ + u16 completion_module, completion_retval; + struct device *dev = ice_pf_to_dev(pf); + struct ice_rq_event_info event; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + u32 completion_offset; + int err; + + memset(&event, 0, sizeof(event)); + + status = ice_aq_update_nvm(hw, module, offset, block_size, block, + last_cmd, 0, NULL); + if (status) { + dev_err(dev, "Failed to program flash module 0x%02x at offset %u, err %s aq_err %s\n", + module, offset, ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to program flash module"); + return -EIO; + } + + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, HZ, &event); + if (err) { + dev_err(dev, "Timed out waiting for firmware write completion for module 0x%02x, err %d\n", + module, err); + NL_SET_ERR_MSG_MOD(extack, "Timed out waiting for firmware"); + return -EIO; + } + + completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); + completion_retval = le16_to_cpu(event.desc.retval); + + completion_offset = le16_to_cpu(event.desc.params.nvm.offset_low); + completion_offset |= event.desc.params.nvm.offset_high << 16; + + if (completion_module != module) { + dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n", + completion_module, module); + NL_SET_ERR_MSG_MOD(extack, "Unexpected firmware response"); + return -EIO; + } + + if (completion_offset != offset) { + dev_err(dev, "Unexpected offset in write completion: got %u, expected %u\n", + completion_offset, offset); + NL_SET_ERR_MSG_MOD(extack, "Unexpected firmware response"); + return -EIO; + } + + if (completion_retval) { + dev_err(dev, "Firmware failed to program flash module 0x%02x at offset %u, completion err %s\n", + module, offset, + ice_aq_str((enum ice_aq_err)completion_retval)); + NL_SET_ERR_MSG_MOD(extack, "Firmware failed to program flash module"); + return -EIO; + } + + return 0; +} + +/** + * ice_write_nvm_module - Write data to an NVM module + * @pf: the PF driver structure + * @module: the module id to program + * @component: the name of the component being updated + * @image: buffer of image data to write to the NVM + * @length: length of the buffer + * @extack: netlink extended ACK structure + * + * Loop over the data for a given NVM module and program it in 4 Kb + * blocks. Notify devlink core of progress after each block is programmed. + * Loops over a block of data and programs the NVM in 4k block chunks. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_write_nvm_module(struct ice_pf *pf, u16 module, const char *component, + const u8 *image, u32 length, + struct netlink_ext_ack *extack) +{ + struct devlink *devlink; + u32 offset = 0; + bool last_cmd; + u8 *block; + int err; + + devlink = priv_to_devlink(pf); + + devlink_flash_update_status_notify(devlink, "Flashing", + component, 0, length); + + block = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); + if (!block) + return -ENOMEM; + + do { + u32 block_size; + + block_size = min_t(u32, ICE_AQ_MAX_BUF_LEN, length - offset); + last_cmd = !(offset + block_size < length); + + /* ice_aq_update_nvm may copy the firmware response into the + * buffer, so we must make a copy since the source data is + * constant. + */ + memcpy(block, image + offset, block_size); + + err = ice_write_one_nvm_block(pf, module, offset, block_size, + block, last_cmd, extack); + if (err) + break; + + offset += block_size; + + devlink_flash_update_status_notify(devlink, "Flashing", + component, offset, length); + } while (!last_cmd); + + if (err) + devlink_flash_update_status_notify(devlink, "Flashing failed", + component, length, length); + else + devlink_flash_update_status_notify(devlink, "Flashing done", + component, length, length); + + kfree(block); + return err; +} + +/** + * ice_erase_nvm_module - Erase an NVM module and await firmware completion + * @pf: the PF data structure + * @module: the module to erase + * @component: name of the component being updated + * @extack: netlink extended ACK structure + * + * Erase the inactive NVM bank associated with this module, and await for + * a completion response message from firmware. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, + struct netlink_ext_ack *extack) +{ + u16 completion_module, completion_retval; + struct device *dev = ice_pf_to_dev(pf); + struct ice_rq_event_info event; + struct ice_hw *hw = &pf->hw; + struct devlink *devlink; + enum ice_status status; + int err; + + memset(&event, 0, sizeof(event)); + + devlink = priv_to_devlink(pf); + + devlink_flash_update_status_notify(devlink, "Erasing", component, 0, 0); + + status = ice_aq_erase_nvm(hw, module, NULL); + if (status) { + dev_err(dev, "Failed to erase %s (module 0x%02x), err %s aq_err %s\n", + component, module, ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to erase flash module"); + err = -EIO; + goto out_notify_devlink; + } + + /* Yes, this really can take minutes to complete */ + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_erase, 300 * HZ, &event); + if (err) { + dev_err(dev, "Timed out waiting for firmware to respond with erase completion for %s (module 0x%02x), err %d\n", + component, module, err); + NL_SET_ERR_MSG_MOD(extack, "Timed out waiting for firmware"); + goto out_notify_devlink; + } + + completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); + completion_retval = le16_to_cpu(event.desc.retval); + + if (completion_module != module) { + dev_err(dev, "Unexpected module_typeid in erase completion for %s: got 0x%x, expected 0x%x\n", + component, completion_module, module); + NL_SET_ERR_MSG_MOD(extack, "Unexpected firmware response"); + err = -EIO; + goto out_notify_devlink; + } + + if (completion_retval) { + dev_err(dev, "Firmware failed to erase %s (module 0x02%x), aq_err %s\n", + component, module, + ice_aq_str((enum ice_aq_err)completion_retval)); + NL_SET_ERR_MSG_MOD(extack, "Firmware failed to erase flash"); + err = -EIO; + goto out_notify_devlink; + } + +out_notify_devlink: + if (err) + devlink_flash_update_status_notify(devlink, "Erasing failed", + component, 0, 0); + else + devlink_flash_update_status_notify(devlink, "Erasing done", + component, 0, 0); + + return err; +} + +/** + * ice_switch_flash_banks - Tell firmware to switch NVM banks + * @pf: Pointer to the PF data structure + * @activate_flags: flags used for the activation command + * @extack: netlink extended ACK structure + * + * Notify firmware to activate the newly written flash banks, and wait for the + * firmware response. + * + * Returns: zero on success or an error code on failure. + */ +static int ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, + struct netlink_ext_ack *extack) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_rq_event_info event; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + u16 completion_retval; + int err; + + memset(&event, 0, sizeof(event)); + + status = ice_nvm_write_activate(hw, activate_flags); + if (status) { + dev_err(dev, "Failed to switch active flash banks, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to switch active flash banks"); + return -EIO; + } + + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, HZ, + &event); + if (err) { + dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n", + err); + NL_SET_ERR_MSG_MOD(extack, "Timed out waiting for firmware"); + return err; + } + + completion_retval = le16_to_cpu(event.desc.retval); + if (completion_retval) { + dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n", + ice_aq_str((enum ice_aq_err)completion_retval)); + NL_SET_ERR_MSG_MOD(extack, "Firmware failed to switch active flash banks"); + return -EIO; + } + + return 0; +} + +/** + * ice_flash_component - Flash a component of the NVM + * @context: PLDM fw update structure + * @component: the component table to program + * + * Program the flash contents for a given component. First, determine the + * module id. Then, erase the secondary bank for this module. Finally, write + * the contents of the component to the NVM. + * + * Note this function assumes the caller has acquired the NVM resource. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_flash_component(struct pldmfw *context, struct pldmfw_component *component) +{ + struct ice_fwu_priv *priv = container_of(context, struct ice_fwu_priv, context); + struct netlink_ext_ack *extack = priv->extack; + struct ice_pf *pf = priv->pf; + const char *name; + u16 module; + u8 flag; + int err; + + switch (component->identifier) { + case NVM_COMP_ID_OROM: + module = ICE_SR_1ST_OROM_BANK_PTR; + flag = ICE_AQC_NVM_ACTIV_SEL_OROM; + name = "fw.undi"; + break; + case NVM_COMP_ID_NVM: + module = ICE_SR_1ST_NVM_BANK_PTR; + flag = ICE_AQC_NVM_ACTIV_SEL_NVM; + name = "fw.mgmt"; + break; + case NVM_COMP_ID_NETLIST: + module = ICE_SR_NETLIST_BANK_PTR; + flag = ICE_AQC_NVM_ACTIV_SEL_NETLIST; + name = "fw.netlist"; + break; + default: + /* This should not trigger, since we check the id before + * sending the component table to firmware. + */ + WARN(1, "Unexpected unknown component identifier 0x%02x", + component->identifier); + return -EINVAL; + } + + /* Mark this component for activating at the end */ + priv->activate_flags |= flag; + + err = ice_erase_nvm_module(pf, module, name, extack); + if (err) + return err; + + return ice_write_nvm_module(pf, module, name, component->component_data, + component->component_size, extack); +} + +/** + * ice_finalize_update - Perform last steps to complete device update + * @context: PLDM fw update structure + * + * Called as the last step of the update process. Complete the update by + * telling the firmware to switch active banks, and perform a reset of + * configured. + * + * Returns: 0 on success, or an error code on failure. + */ +static int ice_finalize_update(struct pldmfw *context) +{ + struct ice_fwu_priv *priv = container_of(context, struct ice_fwu_priv, context); + struct netlink_ext_ack *extack = priv->extack; + struct ice_pf *pf = priv->pf; + int err; + + /* Finally, notify firmware to activate the written NVM banks */ + err = ice_switch_flash_banks(pf, priv->activate_flags, extack); + if (err) + return err; + + return 0; +} + +static const struct pldmfw_ops ice_fwu_ops = { + .match_record = &pldmfw_op_pci_match_record, + .send_package_data = &ice_send_package_data, + .send_component_table = &ice_send_component_table, + .flash_component = &ice_flash_component, + .finalize_update = &ice_finalize_update, +}; + +/** + * ice_flash_pldm_image - Write a PLDM-formatted firmware image to the device + * @pf: private device driver structure + * @fw: firmware object pointing to the relevant firmware file + * @extack: netlink extended ACK structure + * + * Parse the data for a given firmware file, verifying that it is a valid PLDM + * formatted image that matches this device. + * + * Extract the device record Package Data and Component Tables and send them + * to the firmware. Extract and write the flash data for each of the three + * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify + * firmware once the data is written to the inactive banks. + * + * Returns: zero on success or a negative error code on failure. + */ +int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw, + struct netlink_ext_ack *extack) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + struct ice_fwu_priv priv; + enum ice_status status; + int err; + + memset(&priv, 0, sizeof(priv)); + + priv.context.ops = &ice_fwu_ops; + priv.context.dev = dev; + priv.extack = extack; + priv.pf = pf; + priv.activate_flags = ICE_AQC_NVM_PRESERVE_ALL; + + status = ice_acquire_nvm(hw, ICE_RES_WRITE); + if (status) { + dev_err(dev, "Failed to acquire device flash lock, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock"); + return -EIO; + } + + err = pldmfw_flash_image(&priv.context, fw); + + ice_release_nvm(hw); + + return err; +} + +/** + * ice_check_for_pending_update - Check for a pending flash update + * @pf: the PF driver structure + * @component: if not NULL, the name of the component being updated + * @extack: Netlink extended ACK structure + * + * Check whether the device already has a pending flash update. If such an + * update is found, cancel it so that the requested update may proceed. + * + * Returns: zero on success, or a negative error code on failure. + */ +int ice_check_for_pending_update(struct ice_pf *pf, const char *component, + struct netlink_ext_ack *extack) +{ + struct devlink *devlink = priv_to_devlink(pf); + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw_dev_caps *dev_caps; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + u8 pending = 0; + int err; + + dev_caps = kzalloc(sizeof(*dev_caps), GFP_KERNEL); + if (!dev_caps) + return -ENOMEM; + + /* Read the most recent device capabilities from firmware. Do not use + * the cached values in hw->dev_caps, because the pending update flag + * may have changed, e.g. if an update was previously completed and + * the system has not yet rebooted. + */ + status = ice_discover_dev_caps(hw, dev_caps); + if (status) { + NL_SET_ERR_MSG_MOD(extack, "Unable to read device capabilities"); + kfree(dev_caps); + return -EIO; + } + + if (dev_caps->common_cap.nvm_update_pending_nvm) { + dev_info(dev, "The fw.mgmt flash component has a pending update\n"); + pending |= ICE_AQC_NVM_ACTIV_SEL_NVM; + } + + if (dev_caps->common_cap.nvm_update_pending_orom) { + dev_info(dev, "The fw.undi flash component has a pending update\n"); + pending |= ICE_AQC_NVM_ACTIV_SEL_OROM; + } + + if (dev_caps->common_cap.nvm_update_pending_netlist) { + dev_info(dev, "The fw.netlist flash component has a pending update\n"); + pending |= ICE_AQC_NVM_ACTIV_SEL_NETLIST; + } + + kfree(dev_caps); + + /* If the flash_update request is for a specific component, ignore all + * of the other components. + */ + if (component) { + if (strcmp(component, "fw.mgmt") == 0) + pending &= ICE_AQC_NVM_ACTIV_SEL_NVM; + else if (strcmp(component, "fw.undi") == 0) + pending &= ICE_AQC_NVM_ACTIV_SEL_OROM; + else if (strcmp(component, "fw.netlist") == 0) + pending &= ICE_AQC_NVM_ACTIV_SEL_NETLIST; + else + WARN(1, "Unexpected flash component %s", component); + } + + /* There is no previous pending update, so this request may continue */ + if (!pending) + return 0; + + /* In order to allow overwriting a previous pending update, notify + * firmware to cancel that update by issuing the appropriate command. + */ + devlink_flash_update_status_notify(devlink, + "Canceling previous pending update", + component, 0, 0); + + status = ice_acquire_nvm(hw, ICE_RES_WRITE); + if (status) { + dev_err(dev, "Failed to acquire device flash lock, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock"); + return -EIO; + } + + pending |= ICE_AQC_NVM_REVERT_LAST_ACTIV; + err = ice_switch_flash_banks(pf, pending, extack); + + ice_release_nvm(hw); + + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h new file mode 100644 index 000000000000..79472cc618b4 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#ifndef _ICE_FW_UPDATE_H_ +#define _ICE_FW_UPDATE_H_ + +int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw, + struct netlink_ext_ack *extack); +int ice_check_for_pending_update(struct ice_pf *pf, const char *component, + struct netlink_ext_ack *extack); + +#endif diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 92e4abca62a4..90abc8612a6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -57,7 +57,7 @@ #define PRTDCB_GENS 0x00083020 #define PRTDCB_GENS_DCBX_STATUS_S 0 #define PRTDCB_GENS_DCBX_STATUS_M ICE_M(0x7, 0) -#define PRTDCB_TUP2TC 0x001D26C0 /* Reset Source: CORER */ +#define PRTDCB_TUP2TC 0x001D26C0 #define GL_PREEXT_L2_PMASK0(_i) (0x0020F0FC + ((_i) * 4)) #define GL_PREEXT_L2_PMASK1(_i) (0x0020F108 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4)) @@ -362,6 +362,7 @@ #define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) +#define PRTRPB_RDPC 0x000AC260 #define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4)) #define VSIQF_FD_CNT_FD_GCNT_S 0 #define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0) @@ -378,6 +379,5 @@ #define PFPM_WUS_FW_RST_WK_M BIT(31) #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) -#define PRTRPB_RDPC 0x000AC260 #endif /* _ICE_HW_AUTOGEN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 14dfbbc1b2cf..4ec24c3e813f 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -601,6 +601,7 @@ struct ice_tlan_ctx { /* shorter macros makes the table fit but are terse */ #define ICE_RX_PTYPE_NOF ICE_RX_PTYPE_NOT_FRAG +#define ICE_RX_PTYPE_FRG ICE_RX_PTYPE_FRAG /* Lookup table mapping the HW PTYPE to the bit field for decoding */ static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = { @@ -608,6 +609,319 @@ static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = { ICE_PTT_UNUSED_ENTRY(0), ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), ICE_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + ICE_PTT_UNUSED_ENTRY(3), + ICE_PTT_UNUSED_ENTRY(4), + ICE_PTT_UNUSED_ENTRY(5), + ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + ICE_PTT_UNUSED_ENTRY(8), + ICE_PTT_UNUSED_ENTRY(9), + ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + ICE_PTT_UNUSED_ENTRY(12), + ICE_PTT_UNUSED_ENTRY(13), + ICE_PTT_UNUSED_ENTRY(14), + ICE_PTT_UNUSED_ENTRY(15), + ICE_PTT_UNUSED_ENTRY(16), + ICE_PTT_UNUSED_ENTRY(17), + ICE_PTT_UNUSED_ENTRY(18), + ICE_PTT_UNUSED_ENTRY(19), + ICE_PTT_UNUSED_ENTRY(20), + ICE_PTT_UNUSED_ENTRY(21), + + /* Non Tunneled IPv4 */ + ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), + ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), + ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(25), + ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), + ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), + ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv4 --> IPv4 */ + ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(32), + ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> IPv6 */ + ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(39), + ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT */ + ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> IPv4 */ + ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(47), + ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> IPv6 */ + ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(54), + ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC */ + ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ + ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(62), + ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ + ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(69), + ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC/VLAN */ + ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ + ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(77), + ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ + ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(84), + ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* Non Tunneled IPv6 */ + ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), + ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), + ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + ICE_PTT_UNUSED_ENTRY(91), + ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), + ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), + ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv6 --> IPv4 */ + ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(98), + ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> IPv6 */ + ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(105), + ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT */ + ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> IPv4 */ + ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(113), + ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> IPv6 */ + ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(120), + ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC */ + ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ + ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(128), + ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ + ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(135), + ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN */ + ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ + ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(143), + ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ + ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + ICE_PTT_UNUSED_ENTRY(150), + ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* unused entries */ + ICE_PTT_UNUSED_ENTRY(154), + ICE_PTT_UNUSED_ENTRY(155), + ICE_PTT_UNUSED_ENTRY(156), + ICE_PTT_UNUSED_ENTRY(157), + ICE_PTT_UNUSED_ENTRY(158), + ICE_PTT_UNUSED_ENTRY(159), + + ICE_PTT_UNUSED_ENTRY(160), + ICE_PTT_UNUSED_ENTRY(161), + ICE_PTT_UNUSED_ENTRY(162), + ICE_PTT_UNUSED_ENTRY(163), + ICE_PTT_UNUSED_ENTRY(164), + ICE_PTT_UNUSED_ENTRY(165), + ICE_PTT_UNUSED_ENTRY(166), + ICE_PTT_UNUSED_ENTRY(167), + ICE_PTT_UNUSED_ENTRY(168), + ICE_PTT_UNUSED_ENTRY(169), + + ICE_PTT_UNUSED_ENTRY(170), + ICE_PTT_UNUSED_ENTRY(171), + ICE_PTT_UNUSED_ENTRY(172), + ICE_PTT_UNUSED_ENTRY(173), + ICE_PTT_UNUSED_ENTRY(174), + ICE_PTT_UNUSED_ENTRY(175), + ICE_PTT_UNUSED_ENTRY(176), + ICE_PTT_UNUSED_ENTRY(177), + ICE_PTT_UNUSED_ENTRY(178), + ICE_PTT_UNUSED_ENTRY(179), + + ICE_PTT_UNUSED_ENTRY(180), + ICE_PTT_UNUSED_ENTRY(181), + ICE_PTT_UNUSED_ENTRY(182), + ICE_PTT_UNUSED_ENTRY(183), + ICE_PTT_UNUSED_ENTRY(184), + ICE_PTT_UNUSED_ENTRY(185), + ICE_PTT_UNUSED_ENTRY(186), + ICE_PTT_UNUSED_ENTRY(187), + ICE_PTT_UNUSED_ENTRY(188), + ICE_PTT_UNUSED_ENTRY(189), + + ICE_PTT_UNUSED_ENTRY(190), + ICE_PTT_UNUSED_ENTRY(191), + ICE_PTT_UNUSED_ENTRY(192), + ICE_PTT_UNUSED_ENTRY(193), + ICE_PTT_UNUSED_ENTRY(194), + ICE_PTT_UNUSED_ENTRY(195), + ICE_PTT_UNUSED_ENTRY(196), + ICE_PTT_UNUSED_ENTRY(197), + ICE_PTT_UNUSED_ENTRY(198), + ICE_PTT_UNUSED_ENTRY(199), + + ICE_PTT_UNUSED_ENTRY(200), + ICE_PTT_UNUSED_ENTRY(201), + ICE_PTT_UNUSED_ENTRY(202), + ICE_PTT_UNUSED_ENTRY(203), + ICE_PTT_UNUSED_ENTRY(204), + ICE_PTT_UNUSED_ENTRY(205), + ICE_PTT_UNUSED_ENTRY(206), + ICE_PTT_UNUSED_ENTRY(207), + ICE_PTT_UNUSED_ENTRY(208), + ICE_PTT_UNUSED_ENTRY(209), + + ICE_PTT_UNUSED_ENTRY(210), + ICE_PTT_UNUSED_ENTRY(211), + ICE_PTT_UNUSED_ENTRY(212), + ICE_PTT_UNUSED_ENTRY(213), + ICE_PTT_UNUSED_ENTRY(214), + ICE_PTT_UNUSED_ENTRY(215), + ICE_PTT_UNUSED_ENTRY(216), + ICE_PTT_UNUSED_ENTRY(217), + ICE_PTT_UNUSED_ENTRY(218), + ICE_PTT_UNUSED_ENTRY(219), + + ICE_PTT_UNUSED_ENTRY(220), + ICE_PTT_UNUSED_ENTRY(221), + ICE_PTT_UNUSED_ENTRY(222), + ICE_PTT_UNUSED_ENTRY(223), + ICE_PTT_UNUSED_ENTRY(224), + ICE_PTT_UNUSED_ENTRY(225), + ICE_PTT_UNUSED_ENTRY(226), + ICE_PTT_UNUSED_ENTRY(227), + ICE_PTT_UNUSED_ENTRY(228), + ICE_PTT_UNUSED_ENTRY(229), + + ICE_PTT_UNUSED_ENTRY(230), + ICE_PTT_UNUSED_ENTRY(231), + ICE_PTT_UNUSED_ENTRY(232), + ICE_PTT_UNUSED_ENTRY(233), + ICE_PTT_UNUSED_ENTRY(234), + ICE_PTT_UNUSED_ENTRY(235), + ICE_PTT_UNUSED_ENTRY(236), + ICE_PTT_UNUSED_ENTRY(237), + ICE_PTT_UNUSED_ENTRY(238), + ICE_PTT_UNUSED_ENTRY(239), + + ICE_PTT_UNUSED_ENTRY(240), + ICE_PTT_UNUSED_ENTRY(241), + ICE_PTT_UNUSED_ENTRY(242), + ICE_PTT_UNUSED_ENTRY(243), + ICE_PTT_UNUSED_ENTRY(244), + ICE_PTT_UNUSED_ENTRY(245), + ICE_PTT_UNUSED_ENTRY(246), + ICE_PTT_UNUSED_ENTRY(247), + ICE_PTT_UNUSED_ENTRY(248), + ICE_PTT_UNUSED_ENTRY(249), + + ICE_PTT_UNUSED_ENTRY(250), + ICE_PTT_UNUSED_ENTRY(251), + ICE_PTT_UNUSED_ENTRY(252), + ICE_PTT_UNUSED_ENTRY(253), + ICE_PTT_UNUSED_ENTRY(254), + ICE_PTT_UNUSED_ENTRY(255), }; static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 8f6a191839f1..f2682776f8c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -127,8 +127,14 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) case ICE_VSI_PF: case ICE_VSI_CTRL: case ICE_VSI_LB: - vsi->num_rx_desc = ICE_DFLT_NUM_RX_DESC; - vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC; + /* a user could change the values of num_[tr]x_desc using + * ethtool -G so we should keep those values instead of + * overwriting them with the defaults. + */ + if (!vsi->num_rx_desc) + vsi->num_rx_desc = ICE_DFLT_NUM_RX_DESC; + if (!vsi->num_tx_desc) + vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC; break; default: dev_dbg(ice_pf_to_dev(vsi->back), "Not setting number of Tx/Rx descriptors for VSI type %d\n", @@ -2011,6 +2017,13 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc) if (!vsi) return -EINVAL; + /* Don't enable VLAN pruning if the netdev is currently in promiscuous + * mode. VLAN pruning will be enabled when the interface exits + * promiscuous mode if any VLAN filters are active. + */ + if (vsi->netdev && vsi->netdev->flags & IFF_PROMISC && ena) + return 0; + pf = vsi->back; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (!ctxt) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 231f4b6e93d0..8437d72795b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -369,6 +369,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) ~IFF_PROMISC; goto out_promisc; } + ice_cfg_vlan_pruning(vsi, false, false); } } else { /* Clear Rx filter to remove traffic from wire */ @@ -381,6 +382,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) IFF_PROMISC; goto out_promisc; } + if (vsi->num_vlan > 1) + ice_cfg_vlan_pruning(vsi, true, false); } } } @@ -767,6 +770,100 @@ static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up) } /** + * ice_set_dflt_mib - send a default config MIB to the FW + * @pf: private PF struct + * + * This function sends a default configuration MIB to the FW. + * + * If this function errors out at any point, the driver is still able to + * function. The main impact is that LFC may not operate as expected. + * Therefore an error state in this function should be treated with a DBG + * message and continue on with driver rebuild/reenable. + */ +static void ice_set_dflt_mib(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + u8 mib_type, *buf, *lldpmib = NULL; + u16 len, typelen, offset = 0; + struct ice_lldp_org_tlv *tlv; + struct ice_hw *hw; + u32 ouisubtype; + + if (!pf) { + dev_dbg(dev, "%s NULL pf pointer\n", __func__); + return; + } + + hw = &pf->hw; + mib_type = SET_LOCAL_MIB_TYPE_LOCAL_MIB; + lldpmib = kzalloc(ICE_LLDPDU_SIZE, GFP_KERNEL); + if (!lldpmib) { + dev_dbg(dev, "%s Failed to allocate MIB memory\n", + __func__); + return; + } + + /* Add ETS CFG TLV */ + tlv = (struct ice_lldp_org_tlv *)lldpmib; + typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | + ICE_IEEE_ETS_TLV_LEN); + tlv->typelen = htons(typelen); + ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_IEEE_SUBTYPE_ETS_CFG); + tlv->ouisubtype = htonl(ouisubtype); + + buf = tlv->tlvinfo; + buf[0] = 0; + + /* ETS CFG all UPs map to TC 0. Next 4 (1 - 4) Octets = 0. + * Octets 5 - 12 are BW values, set octet 5 to 100% BW. + * Octets 13 - 20 are TSA values - leave as zeros + */ + buf[5] = 0x64; + len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + offset += len + 2; + tlv = (struct ice_lldp_org_tlv *) + ((char *)tlv + sizeof(tlv->typelen) + len); + + /* Add ETS REC TLV */ + buf = tlv->tlvinfo; + tlv->typelen = htons(typelen); + + ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_IEEE_SUBTYPE_ETS_REC); + tlv->ouisubtype = htonl(ouisubtype); + + /* First octet of buf is reserved + * Octets 1 - 4 map UP to TC - all UPs map to zero + * Octets 5 - 12 are BW values - set TC 0 to 100%. + * Octets 13 - 20 are TSA value - leave as zeros + */ + buf[5] = 0x64; + offset += len + 2; + tlv = (struct ice_lldp_org_tlv *) + ((char *)tlv + sizeof(tlv->typelen) + len); + + /* Add PFC CFG TLV */ + typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | + ICE_IEEE_PFC_TLV_LEN); + tlv->typelen = htons(typelen); + + ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_IEEE_SUBTYPE_PFC_CFG); + tlv->ouisubtype = htonl(ouisubtype); + + /* Octet 1 left as all zeros - PFC disabled */ + buf[0] = 0x08; + len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S; + offset += len + 2; + + if (ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, offset, NULL)) + dev_dbg(dev, "%s Failed to set default LLDP MIB\n", __func__); + + kfree(lldpmib); +} + +/** * ice_link_event - process the link event * @pf: PF that the link event is associated with * @pi: port_info for the port that the link event is associated with @@ -800,6 +897,12 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, dev_dbg(dev, "Failed to update link status and re-enable link events for port %d\n", pi->lport); + /* Check if the link state is up after updating link info, and treat + * this event as an UP event since the link is actually UP now. + */ + if (phy_info->link_info.link_info & ICE_AQ_LINK_UP) + link_up = true; + vsi = ice_get_main_vsi(pf); if (!vsi || !vsi->port_info) return -EINVAL; @@ -821,7 +924,13 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return result; - ice_dcb_rebuild(pf); + if (ice_is_dcb_active(pf)) { + if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) + ice_dcb_rebuild(pf); + } else { + if (link_up) + ice_set_dflt_mib(pf); + } ice_vsi_link_event(vsi, link_up); ice_print_link_msg(vsi, link_up); @@ -914,6 +1023,151 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) return status; } +enum ice_aq_task_state { + ICE_AQ_TASK_WAITING = 0, + ICE_AQ_TASK_COMPLETE, + ICE_AQ_TASK_CANCELED, +}; + +struct ice_aq_task { + struct hlist_node entry; + + u16 opcode; + struct ice_rq_event_info *event; + enum ice_aq_task_state state; +}; + +/** + * ice_wait_for_aq_event - Wait for an AdminQ event from firmware + * @pf: pointer to the PF private structure + * @opcode: the opcode to wait for + * @timeout: how long to wait, in jiffies + * @event: storage for the event info + * + * Waits for a specific AdminQ completion event on the ARQ for a given PF. The + * current thread will be put to sleep until the specified event occurs or + * until the given timeout is reached. + * + * To obtain only the descriptor contents, pass an event without an allocated + * msg_buf. If the complete data buffer is desired, allocate the + * event->msg_buf with enough space ahead of time. + * + * Returns: zero on success, or a negative error code on failure. + */ +int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, + struct ice_rq_event_info *event) +{ + struct ice_aq_task *task; + long ret; + int err; + + task = kzalloc(sizeof(*task), GFP_KERNEL); + if (!task) + return -ENOMEM; + + INIT_HLIST_NODE(&task->entry); + task->opcode = opcode; + task->event = event; + task->state = ICE_AQ_TASK_WAITING; + + spin_lock_bh(&pf->aq_wait_lock); + hlist_add_head(&task->entry, &pf->aq_wait_list); + spin_unlock_bh(&pf->aq_wait_lock); + + ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state, + timeout); + switch (task->state) { + case ICE_AQ_TASK_WAITING: + err = ret < 0 ? ret : -ETIMEDOUT; + break; + case ICE_AQ_TASK_CANCELED: + err = ret < 0 ? ret : -ECANCELED; + break; + case ICE_AQ_TASK_COMPLETE: + err = ret < 0 ? ret : 0; + break; + default: + WARN(1, "Unexpected AdminQ wait task state %u", task->state); + err = -EINVAL; + break; + } + + spin_lock_bh(&pf->aq_wait_lock); + hlist_del(&task->entry); + spin_unlock_bh(&pf->aq_wait_lock); + kfree(task); + + return err; +} + +/** + * ice_aq_check_events - Check if any thread is waiting for an AdminQ event + * @pf: pointer to the PF private structure + * @opcode: the opcode of the event + * @event: the event to check + * + * Loops over the current list of pending threads waiting for an AdminQ event. + * For each matching task, copy the contents of the event into the task + * structure and wake up the thread. + * + * If multiple threads wait for the same opcode, they will all be woken up. + * + * Note that event->msg_buf will only be duplicated if the event has a buffer + * with enough space already allocated. Otherwise, only the descriptor and + * message length will be copied. + * + * Returns: true if an event was found, false otherwise + */ +static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, + struct ice_rq_event_info *event) +{ + struct ice_aq_task *task; + bool found = false; + + spin_lock_bh(&pf->aq_wait_lock); + hlist_for_each_entry(task, &pf->aq_wait_list, entry) { + if (task->state || task->opcode != opcode) + continue; + + memcpy(&task->event->desc, &event->desc, sizeof(event->desc)); + task->event->msg_len = event->msg_len; + + /* Only copy the data buffer if a destination was set */ + if (task->event->msg_buf && + task->event->buf_len > event->buf_len) { + memcpy(task->event->msg_buf, event->msg_buf, + event->buf_len); + task->event->buf_len = event->buf_len; + } + + task->state = ICE_AQ_TASK_COMPLETE; + found = true; + } + spin_unlock_bh(&pf->aq_wait_lock); + + if (found) + wake_up(&pf->aq_wait_queue); +} + +/** + * ice_aq_cancel_waiting_tasks - Immediately cancel all waiting tasks + * @pf: the PF private structure + * + * Set all waiting tasks to ICE_AQ_TASK_CANCELED, and wake up their threads. + * This will then cause ice_aq_wait_for_event to exit with -ECANCELED. + */ +static void ice_aq_cancel_waiting_tasks(struct ice_pf *pf) +{ + struct ice_aq_task *task; + + spin_lock_bh(&pf->aq_wait_lock); + hlist_for_each_entry(task, &pf->aq_wait_list, entry) + task->state = ICE_AQ_TASK_CANCELED; + spin_unlock_bh(&pf->aq_wait_lock); + + wake_up(&pf->aq_wait_queue); +} + /** * __ice_clean_ctrlq - helper function to clean controlq rings * @pf: ptr to struct ice_pf @@ -1010,6 +1264,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) opcode = le16_to_cpu(event.desc.opcode); + /* Notify any thread that might be waiting for this event */ + ice_aq_check_events(pf, opcode, &event); + switch (opcode) { case ice_aqc_opc_get_link_status: if (ice_handle_link_event(pf, &event)) @@ -3086,6 +3343,10 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + /* setup service timer and periodic service task */ timer_setup(&pf->serv_tmr, ice_service_timer, 0); pf->serv_tmr_period = HZ; @@ -3323,6 +3584,60 @@ done: } /** + * ice_set_safe_mode_vlan_cfg - configure PF VSI to allow all VLANs in safe mode + * @pf: PF to configure + * + * No VLAN offloads/filtering are advertised in safe mode so make sure the PF + * VSI can still Tx/Rx VLAN tagged packets. + */ +static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct ice_vsi_ctx *ctxt; + enum ice_status status; + struct ice_hw *hw; + + if (!vsi) + return; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return; + + hw = &pf->hw; + ctxt->info = vsi->info; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SECURITY_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + /* disable VLAN anti-spoof */ + ctxt->info.sec_flags &= ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + + /* disable VLAN pruning and keep all other settings */ + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + /* allow all VLANs on Tx and don't strip on Rx */ + ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL | + ICE_AQ_VSI_VLAN_EMOD_NOTHING; + + status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (status) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to update VSI for safe mode VLANs, err %s aq_err %s\n", + ice_stat_str(status), + ice_aq_str(hw->adminq.sq_last_status)); + } else { + vsi->info.sec_flags = ctxt->info.sec_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + vsi->info.vlan_flags = ctxt->info.vlan_flags; + } + + kfree(ctxt); +} + +/** * ice_log_pkg_init - log result of DDP package load * @hw: pointer to hardware info * @status: status of package load @@ -3819,7 +4134,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) if (err) { dev_err(dev, "probe failed sending driver version %s. error: %d\n", UTS_RELEASE, err); - goto err_alloc_sw_unroll; + goto err_send_version_unroll; } /* since everything is good, start the service timer */ @@ -3828,19 +4143,19 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) err = ice_init_link_events(pf->hw.port_info); if (err) { dev_err(dev, "ice_init_link_events failed: %d\n", err); - goto err_alloc_sw_unroll; + goto err_send_version_unroll; } err = ice_init_nvm_phy_type(pf->hw.port_info); if (err) { dev_err(dev, "ice_init_nvm_phy_type failed: %d\n", err); - goto err_alloc_sw_unroll; + goto err_send_version_unroll; } err = ice_update_link_info(pf->hw.port_info); if (err) { dev_err(dev, "ice_update_link_info failed: %d\n", err); - goto err_alloc_sw_unroll; + goto err_send_version_unroll; } ice_init_link_dflt_override(pf->hw.port_info); @@ -3851,7 +4166,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) err = ice_init_phy_user_cfg(pf->hw.port_info); if (err) { dev_err(dev, "ice_init_phy_user_cfg failed: %d\n", err); - goto err_alloc_sw_unroll; + goto err_send_version_unroll; } if (!test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) { @@ -3878,9 +4193,10 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) /* Disable WoL at init, wait for user to enable */ device_set_wakeup_enable(dev, false); - /* If no DDP driven features have to be setup, we are done with probe */ - if (ice_is_safe_mode(pf)) + if (ice_is_safe_mode(pf)) { + ice_set_safe_mode_vlan_cfg(pf); goto probe_done; + } /* initialize DDP driven features */ @@ -3904,6 +4220,8 @@ probe_done: clear_bit(__ICE_DOWN, pf->state); return 0; +err_send_version_unroll: + ice_vsi_release_all(pf); err_alloc_sw_unroll: ice_devlink_destroy_port(pf); set_bit(__ICE_SERVICE_DIS, pf->state); @@ -4014,6 +4332,8 @@ static void ice_remove(struct pci_dev *pdev) set_bit(__ICE_DOWN, pf->state); ice_service_task_stop(pf); + ice_aq_cancel_waiting_tasks(pf); + mutex_destroy(&(&pf->hw)->fdir_fltr_lock); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); @@ -4147,7 +4467,7 @@ err_reinit: * Power Management callback to quiesce the device and prepare * for D3 transition. */ -static int ice_suspend(struct device *dev) +static int __maybe_unused ice_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct ice_pf *pf; @@ -4211,7 +4531,7 @@ static int ice_suspend(struct device *dev) * ice_resume - PM callback for waking up from D3 * @dev: generic device information structure */ -static int ice_resume(struct device *dev) +static int __maybe_unused ice_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); enum ice_reset_req reset_type; @@ -4360,6 +4680,8 @@ static void ice_pci_err_resume(struct pci_dev *pdev) return; } + ice_restore_all_vfs_msi_state(pdev); + ice_do_reset(pf, ICE_RESET_PFR); ice_service_task_restart(pf); mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); @@ -4968,6 +5290,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) vsi->tx_linearize = 0; vsi->rx_buf_failed = 0; vsi->rx_page_failed = 0; + vsi->rx_gro_dropped = 0; rcu_read_lock(); @@ -4982,6 +5305,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) vsi_stats->rx_bytes += bytes; vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed; vsi->rx_page_failed += ring->rx_stats.alloc_page_failed; + vsi->rx_gro_dropped += ring->rx_stats.gro_dropped; } /* update XDP Tx rings counters */ @@ -5013,7 +5337,7 @@ void ice_update_vsi_stats(struct ice_vsi *vsi) ice_update_eth_stats(vsi); cur_ns->tx_errors = cur_es->tx_errors; - cur_ns->rx_dropped = cur_es->rx_discards; + cur_ns->rx_dropped = cur_es->rx_discards + vsi->rx_gro_dropped; cur_ns->tx_dropped = cur_es->tx_discards; cur_ns->multicast = cur_es->rx_multicast; @@ -5656,10 +5980,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) if (err) goto err_sched_init_port; - err = ice_update_link_info(hw->port_info); - if (err) - dev_err(dev, "Get link status error %d\n", err); - /* start misc vector */ err = ice_req_irq_msix_misc(pf); if (err) { diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 7c2a06892bbb..5903a36763de 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -108,6 +108,76 @@ ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data, } /** + * ice_aq_update_nvm + * @hw: pointer to the HW struct + * @module_typeid: module pointer location in words from the NVM beginning + * @offset: byte offset from the module beginning + * @length: length of the section to be written (in bytes from the offset) + * @data: command buffer (size [bytes] = length) + * @last_command: tells if this is the last command in a series + * @command_flags: command parameters + * @cd: pointer to command details structure or NULL + * + * Update the NVM using the admin queue commands (0x0703) + */ +enum ice_status +ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, u8 command_flags, + struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + struct ice_aqc_nvm *cmd; + + cmd = &desc.params.nvm; + + /* In offset the highest byte must be zeroed. */ + if (offset & 0xFF000000) + return ICE_ERR_PARAM; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write); + + cmd->cmd_flags |= command_flags; + + /* If this is the last command in a series, set the proper flag. */ + if (last_command) + cmd->cmd_flags |= ICE_AQC_NVM_LAST_CMD; + cmd->module_typeid = cpu_to_le16(module_typeid); + cmd->offset_low = cpu_to_le16(offset & 0xFFFF); + cmd->offset_high = (offset >> 16) & 0xFF; + cmd->length = cpu_to_le16(length); + + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, data, length, cd); +} + +/** + * ice_aq_erase_nvm + * @hw: pointer to the HW struct + * @module_typeid: module pointer location in words from the NVM beginning + * @cd: pointer to command details structure or NULL + * + * Erase the NVM sector using the admin queue commands (0x0702) + */ +enum ice_status +ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + struct ice_aqc_nvm *cmd; + + cmd = &desc.params.nvm; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_erase); + + cmd->module_typeid = cpu_to_le16(module_typeid); + cmd->length = cpu_to_le16(ICE_AQC_NVM_ERASE_LEN); + cmd->offset_low = 0; + cmd->offset_high = 0; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); +} + +/** * ice_read_sr_word_aq - Reads Shadow RAM via AQ * @hw: pointer to the HW structure * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) @@ -634,3 +704,119 @@ enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw) return status; } + +/** + * ice_nvm_write_activate + * @hw: pointer to the HW struct + * @cmd_flags: NVM activate admin command bits (banks to be validated) + * + * Update the control word with the required banks' validity bits + * and dumps the Shadow RAM to flash (0x0707) + */ +enum ice_status ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags) +{ + struct ice_aqc_nvm *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.nvm; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write_activate); + + cmd->cmd_flags = cmd_flags; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** + * ice_aq_nvm_update_empr + * @hw: pointer to the HW struct + * + * Update empr (0x0709). This command allows SW to + * request an EMPR to activate new FW. + */ +enum ice_status ice_aq_nvm_update_empr(struct ice_hw *hw) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_update_empr); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/* ice_nvm_set_pkg_data + * @hw: pointer to the HW struct + * @del_pkg_data_flag: If is set then the current pkg_data store by FW + * is deleted. + * If bit is set to 1, then buffer should be size 0. + * @data: pointer to buffer + * @length: length of the buffer + * @cd: pointer to command details structure or NULL + * + * Set package data (0x070A). This command is equivalent to the reception + * of a PLDM FW Update GetPackageData cmd. This command should be sent + * as part of the NVM update as the first cmd in the flow. + */ + +enum ice_status +ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, + u16 length, struct ice_sq_cd *cd) +{ + struct ice_aqc_nvm_pkg_data *cmd; + struct ice_aq_desc desc; + + if (length != 0 && !data) + return ICE_ERR_PARAM; + + cmd = &desc.params.pkg_data; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_pkg_data); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (del_pkg_data_flag) + cmd->cmd_flags |= ICE_AQC_NVM_PKG_DELETE; + + return ice_aq_send_cmd(hw, &desc, data, length, cd); +} + +/* ice_nvm_pass_component_tbl + * @hw: pointer to the HW struct + * @data: pointer to buffer + * @length: length of the buffer + * @transfer_flag: parameter for determining stage of the update + * @comp_response: a pointer to the response from the 0x070B AQC. + * @comp_response_code: a pointer to the response code from the 0x070B AQC. + * @cd: pointer to command details structure or NULL + * + * Pass component table (0x070B). This command is equivalent to the reception + * of a PLDM FW Update PassComponentTable cmd. This command should be sent once + * per component. It can be only sent after Set Package Data cmd and before + * actual update. FW will assume these commands are going to be sent until + * the TransferFlag is set to End or StartAndEnd. + */ + +enum ice_status +ice_nvm_pass_component_tbl(struct ice_hw *hw, u8 *data, u16 length, + u8 transfer_flag, u8 *comp_response, + u8 *comp_response_code, struct ice_sq_cd *cd) +{ + struct ice_aqc_nvm_pass_comp_tbl *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + if (!data || !comp_response || !comp_response_code) + return ICE_ERR_PARAM; + + cmd = &desc.params.pass_comp_tbl; + + ice_fill_dflt_direct_cmd_desc(&desc, + ice_aqc_opc_nvm_pass_component_tbl); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + cmd->transfer_flag = transfer_flag; + status = ice_aq_send_cmd(hw, &desc, data, length, cd); + + if (!status) { + *comp_response = cmd->component_response; + *comp_response_code = cmd->component_response_code; + } + return status; +} diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h index 999f273ba6ad..8d430909f846 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.h +++ b/drivers/net/ethernet/intel/ice/ice_nvm.h @@ -17,4 +17,20 @@ enum ice_status ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size); enum ice_status ice_init_nvm(struct ice_hw *hw); enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data); +enum ice_status +ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, + u16 length, void *data, bool last_command, u8 command_flags, + struct ice_sq_cd *cd); +enum ice_status +ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd); +enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw); +enum ice_status ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags); +enum ice_status ice_aq_nvm_update_empr(struct ice_hw *hw); +enum ice_status +ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, + u16 length, struct ice_sq_cd *cd); +enum ice_status +ice_nvm_pass_component_tbl(struct ice_hw *hw, u8 *data, u16 length, + u8 transfer_flag, u8 *comp_response, + u8 *comp_response_code, struct ice_sq_cd *cd); #endif /* _ICE_NVM_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 1c29cfa1cf33..44a228530253 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -170,7 +170,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, return ICE_ERR_PARAM; } - /* query the current node information from FW before additing it + /* query the current node information from FW before adding it * to the SW DB */ status = ice_sched_query_elem(hw, le32_to_cpu(info->node_teid), &elem); @@ -578,7 +578,7 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) /** * ice_aq_rl_profile - performs a rate limiting task * @hw: pointer to the HW struct - * @opcode:opcode for add, query, or remove profile(s) + * @opcode: opcode for add, query, or remove profile(s) * @num_profiles: the number of profiles * @buf: pointer to buffer * @buf_size: buffer size in bytes @@ -1276,6 +1276,53 @@ ice_sched_find_node_in_subtree(struct ice_hw *hw, struct ice_sched_node *base, } /** + * ice_sched_get_free_qgrp - Scan all queue group siblings and find a free node + * @pi: port information structure + * @vsi_node: software VSI handle + * @qgrp_node: first queue group node identified for scanning + * @owner: LAN or RDMA + * + * This function retrieves a free LAN or RDMA queue group node by scanning + * qgrp_node and its siblings for the queue group with the fewest number + * of queues currently assigned. + */ +static struct ice_sched_node * +ice_sched_get_free_qgrp(struct ice_port_info *pi, + struct ice_sched_node *vsi_node, + struct ice_sched_node *qgrp_node, u8 owner) +{ + struct ice_sched_node *min_qgrp; + u8 min_children; + + if (!qgrp_node) + return qgrp_node; + min_children = qgrp_node->num_children; + if (!min_children) + return qgrp_node; + min_qgrp = qgrp_node; + /* scan all queue groups until find a node which has less than the + * minimum number of children. This way all queue group nodes get + * equal number of shares and active. The bandwidth will be equally + * distributed across all queues. + */ + while (qgrp_node) { + /* make sure the qgroup node is part of the VSI subtree */ + if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node)) + if (qgrp_node->num_children < min_children && + qgrp_node->owner == owner) { + /* replace the new min queue group node */ + min_qgrp = qgrp_node; + min_children = min_qgrp->num_children; + /* break if it has no children, */ + if (!min_children) + break; + } + qgrp_node = qgrp_node->sibling; + } + return min_qgrp; +} + +/** * ice_sched_get_free_qparent - Get a free LAN or RDMA queue group node * @pi: port information structure * @vsi_handle: software VSI handle @@ -1288,7 +1335,7 @@ struct ice_sched_node * ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 owner) { - struct ice_sched_node *vsi_node, *qgrp_node = NULL; + struct ice_sched_node *vsi_node, *qgrp_node; struct ice_vsi_ctx *vsi_ctx; u16 max_children; u8 qgrp_layer; @@ -1302,7 +1349,7 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, vsi_node = vsi_ctx->sched.vsi_node[tc]; /* validate invalid VSI ID */ if (!vsi_node) - goto lan_q_exit; + return NULL; /* get the first queue group node from VSI sub-tree */ qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer); @@ -1315,8 +1362,8 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, qgrp_node = qgrp_node->sibling; } -lan_q_exit: - return qgrp_node; + /* Select the best queue group */ + return ice_sched_get_free_qgrp(pi, vsi_node, qgrp_node, owner); } /** @@ -2153,8 +2200,8 @@ ice_sched_add_rl_profile(struct ice_port_info *pi, hw = pi->hw; list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], list_entry) - if (rl_prof_elem->profile.flags == profile_type && - rl_prof_elem->bw == bw) + if ((rl_prof_elem->profile.flags & ICE_AQC_RL_PROFILE_TYPE_M) == + profile_type && rl_prof_elem->bw == bw) /* Return existing profile ID info */ return rl_prof_elem; @@ -2384,7 +2431,8 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type, /* Check the existing list for RL profile */ list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], list_entry) - if (rl_prof_elem->profile.flags == profile_type && + if ((rl_prof_elem->profile.flags & ICE_AQC_RL_PROFILE_TYPE_M) == + profile_type && le16_to_cpu(rl_prof_elem->profile.profile_id) == profile_id) { if (rl_prof_elem->prof_id_ref) @@ -2546,8 +2594,8 @@ ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, return 0; return ice_sched_rm_rl_profile(pi, layer_num, - rl_prof_info->profile.flags, - old_id); + rl_prof_info->profile.flags & + ICE_AQC_RL_PROFILE_TYPE_M, old_id); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index ccbe1cc64295..c3a6c41385ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -495,6 +495,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd) { struct ice_aq_desc desc; + enum ice_status status; if (opc != ice_aqc_opc_add_sw_rules && opc != ice_aqc_opc_update_sw_rules && @@ -506,7 +507,12 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); desc.params.sw_rules.num_rules_fltr_entry_index = cpu_to_le16(num_rules); - return ice_aq_send_cmd(hw, &desc, rule_list, rule_list_sz, cd); + status = ice_aq_send_cmd(hw, &desc, rule_list, rule_list_sz, cd); + if (opc != ice_aqc_opc_add_sw_rules && + hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) + status = ICE_ERR_DOES_NOT_EXIST; + + return status; } /* ice_init_port_info - Initialize port_info with switch configuration data diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index abdb137c8bb7..9d0d6b0025cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -509,8 +509,8 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring) return 0; } -static unsigned int ice_rx_frame_truesize(struct ice_ring *rx_ring, - unsigned int size) +static unsigned int +ice_rx_frame_truesize(struct ice_ring *rx_ring, unsigned int __maybe_unused size) { unsigned int truesize; @@ -631,10 +631,8 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) dma_addr_t dma; /* since we are recycling buffers we should seldom need to alloc */ - if (likely(page)) { - rx_ring->rx_stats.page_reuse_count++; + if (likely(page)) return true; - } /* alloc new page for storage */ page = dev_alloc_pages(ice_rx_pg_order(rx_ring)); @@ -1033,7 +1031,6 @@ static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) if (ice_can_reuse_rx_page(rx_buf)) { /* hand second half of page back to the ring */ ice_reuse_rx_page(rx_ring, rx_buf); - rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma, @@ -1254,12 +1251,12 @@ construct_skb: * @itr: ITR value to update * * Calculate how big of an increment should be applied to the ITR value passed - * in based on wmem_default, SKB overhead, Ethernet overhead, and the current + * in based on wmem_default, SKB overhead, ethernet overhead, and the current * link speed. * * The following is a calculation derived from: * wmem_default / (size + overhead) = desired_pkts_per_int - * rate / bits_per_byte / (size + Ethernet overhead) = pkt_rate + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value * * Assuming wmem_default is 212992 and overhead is 640 bytes per @@ -2294,10 +2291,30 @@ static bool __ice_chk_linearize(struct sk_buff *skb) /* Walk through fragments adding latest fragment, testing it, and * then removing stale fragments from the sum. */ - stale = &skb_shinfo(skb)->frags[0]; - for (;;) { + for (stale = &skb_shinfo(skb)->frags[0];; stale++) { + int stale_size = skb_frag_size(stale); + sum += skb_frag_size(frag++); + /* The stale fragment may present us with a smaller + * descriptor than the actual fragment size. To account + * for that we need to remove all the data on the front and + * figure out what the remainder would be in the last + * descriptor associated with the fragment. + */ + if (stale_size > ICE_MAX_DATA_PER_TXD) { + int align_pad = -(skb_frag_off(stale)) & + (ICE_MAX_READ_REQ_SIZE - 1); + + sum -= align_pad; + stale_size -= align_pad; + + do { + sum -= ICE_MAX_DATA_PER_TXD_ALIGNED; + stale_size -= ICE_MAX_DATA_PER_TXD_ALIGNED; + } while (stale_size > ICE_MAX_DATA_PER_TXD); + } + /* if sum is negative we failed to make sufficient progress */ if (sum < 0) return true; @@ -2305,7 +2322,7 @@ static bool __ice_chk_linearize(struct sk_buff *skb) if (!nr_frags--) break; - sum -= skb_frag_size(stale++); + sum -= stale_size; } return false; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index e70c4619edc3..51b4df7a59d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -193,7 +193,7 @@ struct ice_rxq_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buf_failed; - u64 page_reuse_count; + u64 gro_dropped; /* GRO returned dropped */ }; /* this enum matches hardware bits and is meant to be used by DYN_CTLN diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 02b12736ea80..bc2f4390b51d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -191,7 +191,12 @@ ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && (vlan_tag & VLAN_VID_MASK)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - napi_gro_receive(&rx_ring->q_vector->napi, skb); + if (napi_gro_receive(&rx_ring->q_vector->napi, skb) == GRO_DROP) { + /* this is tracked separately to help us debug stack drops */ + rx_ring->rx_stats.gro_dropped++; + netdev_dbg(rx_ring->netdev, "Receive Queue %d: Dropped packet from GRO\n", + rx_ring->q_index); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 08c616d9fffd..4cdccfadf274 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -244,6 +244,15 @@ struct ice_hw_common_caps { u8 rss_table_entry_width; /* RSS Entry width in bits */ u8 dcb; + + bool nvm_update_pending_nvm; + bool nvm_update_pending_orom; + bool nvm_update_pending_netlist; +#define ICE_NVM_PENDING_NVM_IMAGE BIT(0) +#define ICE_NVM_PENDING_OROM BIT(1) +#define ICE_NVM_PENDING_NETLIST BIT(2) + bool nvm_unified_update; +#define ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT BIT(3) }; /* Function specific capabilities */ @@ -312,7 +321,7 @@ struct ice_nvm_info { u32 flash_size; /* Size of available flash in bytes */ u8 major_ver; /* major version of NVM package */ u8 minor_ver; /* minor version of dev starter */ - u8 blank_nvm_mode; /* is NVM empty (no FW present) */ + u8 blank_nvm_mode; /* is NVM empty (no FW present) */ }; struct ice_link_default_override_tlv { @@ -400,7 +409,7 @@ enum ice_rl_type { #define ICE_SCHED_DFLT_BW 0xFFFFFFFF /* unlimited */ #define ICE_SCHED_DFLT_RL_PROF_ID 0 #define ICE_SCHED_NO_SHARED_RL_PROF_ID 0xFFFF -#define ICE_SCHED_DFLT_BW_WT 1 +#define ICE_SCHED_DFLT_BW_WT 4 #define ICE_SCHED_INVAL_PROF_ID 0xFFFF #define ICE_SCHED_DFLT_BURST_SIZE (15 * 1024) /* in bytes (15k) */ @@ -771,6 +780,9 @@ struct ice_hw_port_stats { #define ICE_OROM_VER_SHIFT 24 #define ICE_OROM_VER_MASK (0xff << ICE_OROM_VER_SHIFT) #define ICE_SR_PFA_PTR 0x40 +#define ICE_SR_1ST_NVM_BANK_PTR 0x42 +#define ICE_SR_1ST_OROM_BANK_PTR 0x44 +#define ICE_SR_NETLIST_BANK_PTR 0x46 #define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800 /* Link override related */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 9df5ceb26ab9..71497776ac62 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -932,6 +932,8 @@ static int ice_set_per_vf_res(struct ice_pf *pf) num_msix_per_vf = ICE_NUM_VF_MSIX_MED; } else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_SMALL) { num_msix_per_vf = ICE_NUM_VF_MSIX_SMALL; + } else if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MULTIQ_MIN) { + num_msix_per_vf = ICE_NUM_VF_MSIX_MULTIQ_MIN; } else if (msix_avail_per_vf >= ICE_MIN_INTR_PER_VF) { num_msix_per_vf = ICE_MIN_INTR_PER_VF; } else { @@ -2972,8 +2974,8 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) vsi->max_frame = qpi->rxq.max_pkt_size; } - /* VF can request to configure less than allocated queues - * or default allocated queues. So update the VSI with new number + /* VF can request to configure less than allocated queues or default + * allocated queues. So update the VSI with new number */ vsi->num_txq = num_txq; vsi->num_rxq = num_rxq; @@ -4071,3 +4073,33 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) } } } + +/** + * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR + * @pdev: pointer to a pci_dev structure + * + * Called when recovering from a PF FLR to restore interrupt capability to + * the VFs. + */ +void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) +{ + struct pci_dev *vfdev; + u16 vf_id; + int pos; + + if (!pci_num_vf(pdev)) + return; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (pos) { + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, + &vf_id); + vfdev = pci_get_device(pdev->vendor, vf_id, NULL); + while (vfdev) { + if (vfdev->is_virtfn && vfdev->physfn == pdev) + pci_restore_msi_state(vfdev); + vfdev = pci_get_device(pdev->vendor, vf_id, + vfdev); + } + } +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 67aa9110fdd1..0f519fba3770 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -32,6 +32,7 @@ #define ICE_MAX_RSS_QS_PER_VF 16 #define ICE_NUM_VF_MSIX_MED 17 #define ICE_NUM_VF_MSIX_SMALL 5 +#define ICE_NUM_VF_MSIX_MULTIQ_MIN 3 #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_MAX_VF_RESET_TRIES 40 #define ICE_MAX_VF_RESET_SLEEP_MS 20 @@ -114,6 +115,7 @@ void ice_vc_notify_link_state(struct ice_pf *pf); void ice_vc_notify_reset(struct ice_pf *pf); bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); bool ice_reset_vf(struct ice_vf *vf, bool is_vflr); +void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -146,6 +148,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf); #define ice_vf_lan_overflow_event(pf, event) do {} while (0) #define ice_print_vfs_mdd_events(pf) do {} while (0) #define ice_print_vf_rx_mdd_event(vf) do {} while (0) +#define ice_restore_all_vfs_msi_state(pdev) do {} while (0) static inline bool ice_reset_all_vfs(struct ice_pf __always_unused *pf, diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 6badfd62dc63..20ac5fca68c6 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -298,7 +298,6 @@ static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid) } } - /** * ice_xsk_umem_disable - disable a UMEM region * @vsi: Current VSI @@ -594,7 +593,6 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) if (!size) break; - rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; rx_buf->xdp->data_end = rx_buf->xdp->data + size; xsk_buff_dma_sync_for_cpu(rx_buf->xdp); @@ -706,8 +704,6 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) if (tx_desc) { ice_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return budget > 0 && work_done; @@ -783,12 +779,8 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) if (xsk_frames) xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) { - if (xdp_ring->next_to_clean == xdp_ring->next_to_use) - xsk_set_tx_need_wakeup(xdp_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) + xsk_set_tx_need_wakeup(xdp_ring->xsk_umem); ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index c2cf414d126b..6e8231c1ddf0 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1782,8 +1782,8 @@ static void igb_create_lbtest_frame(struct sk_buff *skb, memset(skb->data, 0xFF, frame_size); frame_size /= 2; memset(&skb->data[frame_size], 0xAA, frame_size - 1); - memset(&skb->data[frame_size + 10], 0xBE, 1); - memset(&skb->data[frame_size + 12], 0xAF, 1); + skb->data[frame_size + 10] = 0xBE; + skb->data[frame_size + 12] = 0xAF; } static int igb_check_lbtest_frame(struct igb_rx_buffer *rx_buffer, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index ae8d64324619..4f05f6efe6af 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6215,9 +6215,18 @@ static void igb_reset_task(struct work_struct *work) struct igb_adapter *adapter; adapter = container_of(work, struct igb_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGB_DOWN, &adapter->state) || + test_bit(__IGB_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igb_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igb_reinit_locked(adapter); + rtnl_unlock(); } /** @@ -7159,7 +7168,7 @@ static void igb_flush_mac_table(struct igb_adapter *adapter) for (i = 0; i < hw->mac.rar_entry_count; i++) { adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + eth_zero_addr(adapter->mac_table[i].addr); adapter->mac_table[i].queue = 0; igb_rar_set_index(adapter, i); } @@ -7308,7 +7317,7 @@ static int igb_del_mac_filter_flags(struct igb_adapter *adapter, } else { adapter->mac_table[i].state = 0; adapter->mac_table[i].queue = 0; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + eth_zero_addr(adapter->mac_table[i].addr); } igb_rar_set_index(adapter, i); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 97a065928976..19269f5d52bc 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2457,13 +2457,10 @@ static int igbvf_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) } } -static int igbvf_suspend(struct pci_dev *pdev, pm_message_t state) +static int igbvf_suspend(struct device *dev_d) { - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev_d); struct igbvf_adapter *adapter = netdev_priv(netdev); -#ifdef CONFIG_PM - int retval = 0; -#endif netif_device_detach(netdev); @@ -2473,31 +2470,16 @@ static int igbvf_suspend(struct pci_dev *pdev, pm_message_t state) igbvf_free_irq(adapter); } -#ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; -#endif - - pci_disable_device(pdev); - return 0; } -#ifdef CONFIG_PM -static int igbvf_resume(struct pci_dev *pdev) +static int __maybe_unused igbvf_resume(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); struct net_device *netdev = pci_get_drvdata(pdev); struct igbvf_adapter *adapter = netdev_priv(netdev); u32 err; - pci_restore_state(pdev); - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); - return err; - } - pci_set_master(pdev); if (netif_running(netdev)) { @@ -2515,11 +2497,10 @@ static int igbvf_resume(struct pci_dev *pdev) return 0; } -#endif static void igbvf_shutdown(struct pci_dev *pdev) { - igbvf_suspend(pdev, PMSG_SUSPEND); + igbvf_suspend(&pdev->dev); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -2960,17 +2941,15 @@ static const struct pci_device_id igbvf_pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, igbvf_pci_tbl); +static SIMPLE_DEV_PM_OPS(igbvf_pm_ops, igbvf_suspend, igbvf_resume); + /* PCI Device API Driver */ static struct pci_driver igbvf_driver = { .name = igbvf_driver_name, .id_table = igbvf_pci_tbl, .probe = igbvf_probe, .remove = igbvf_remove, -#ifdef CONFIG_PM - /* Power Management Hooks */ - .suspend = igbvf_suspend, - .resume = igbvf_resume, -#endif + .driver.pm = &igbvf_pm_ops, .shutdown = igbvf_shutdown, .err_handler = &igbvf_err_handler }; diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index 2ab7d9fab6af..b9fe51b91c47 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -82,13 +82,7 @@ struct igc_mac_info { enum igc_mac_type type; - u32 collision_delta; - u32 ledctl_default; - u32 ledctl_mode1; - u32 ledctl_mode2; u32 mc_filter_type; - u32 tx_packet_delta; - u32 txcw; u16 mta_reg_count; u16 uta_reg_count; @@ -98,8 +92,6 @@ struct igc_mac_info { u8 forced_speed_duplex; - bool adaptive_ifs; - bool has_fwsm; bool asf_firmware_present; bool arc_subsystem_valid; @@ -276,21 +268,9 @@ struct igc_hw_stats { u64 tsctc; u64 tsctfc; u64 iac; - u64 icrxptc; - u64 icrxatc; - u64 ictxptc; - u64 ictxatc; - u64 ictxqec; - u64 ictxqmtc; - u64 icrxdmtc; - u64 icrxoc; - u64 cbtmpc; u64 htdpmc; - u64 cbrdpc; - u64 cbrmpc; u64 rpthc; u64 hgptc; - u64 htcbdpc; u64 hgorc; u64 hgotc; u64 lenerrs; diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c index b47e7b0a6398..09cd0ec7ee87 100644 --- a/drivers/net/ethernet/intel/igc/igc_mac.c +++ b/drivers/net/ethernet/intel/igc/igc_mac.c @@ -295,20 +295,12 @@ void igc_clear_hw_cntrs_base(struct igc_hw *hw) rd32(IGC_MGTPTC); rd32(IGC_IAC); - rd32(IGC_ICRXOC); - - rd32(IGC_ICRXPTC); - rd32(IGC_ICRXATC); - rd32(IGC_ICTXPTC); - rd32(IGC_ICTXATC); - rd32(IGC_ICTXQEC); - rd32(IGC_ICTXQMTC); - rd32(IGC_ICRXDMTC); rd32(IGC_RPTHC); rd32(IGC_TLPIC); rd32(IGC_RLPIC); rd32(IGC_HGPTC); + rd32(IGC_RXDMTC); rd32(IGC_HGORCL); rd32(IGC_HGORCH); rd32(IGC_HGOTCL); @@ -363,8 +355,8 @@ void igc_rar_set(struct igc_hw *hw, u8 *addr, u32 index) s32 igc_check_for_copper_link(struct igc_hw *hw) { struct igc_mac_info *mac = &hw->mac; + bool link = false; s32 ret_val; - bool link; /* We only want to go out to the PHY registers to see if Auto-Neg * has completed and/or if our link status has changed. The diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8d5869dcf798..7a6f2a0d413f 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3730,14 +3730,6 @@ void igc_update_stats(struct igc_adapter *adapter) adapter->stats.tsctc += rd32(IGC_TSCTC); adapter->stats.iac += rd32(IGC_IAC); - adapter->stats.icrxoc += rd32(IGC_ICRXOC); - adapter->stats.icrxptc += rd32(IGC_ICRXPTC); - adapter->stats.icrxatc += rd32(IGC_ICRXATC); - adapter->stats.ictxptc += rd32(IGC_ICTXPTC); - adapter->stats.ictxatc += rd32(IGC_ICTXATC); - adapter->stats.ictxqec += rd32(IGC_ICTXQEC); - adapter->stats.ictxqmtc += rd32(IGC_ICTXQMTC); - adapter->stats.icrxdmtc += rd32(IGC_ICRXDMTC); /* Fill out the OS statistics structure */ net_stats->multicast = adapter->stats.mprc; diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index 1c46cec5a799..b52dd9d737e8 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -58,16 +58,6 @@ #define IGC_IVAR_MISC 0x01740 /* IVAR for "other" causes - RW */ #define IGC_GPIE 0x01514 /* General Purpose Intr Enable - RW */ -/* Interrupt Cause */ -#define IGC_ICRXPTC 0x04104 /* Rx Packet Timer Expire Count */ -#define IGC_ICRXATC 0x04108 /* Rx Absolute Timer Expire Count */ -#define IGC_ICTXPTC 0x0410C /* Tx Packet Timer Expire Count */ -#define IGC_ICTXATC 0x04110 /* Tx Absolute Timer Expire Count */ -#define IGC_ICTXQEC 0x04118 /* Tx Queue Empty Count */ -#define IGC_ICTXQMTC 0x0411C /* Tx Queue Min Threshold Count */ -#define IGC_ICRXDMTC 0x04120 /* Rx Descriptor Min Threshold Count */ -#define IGC_ICRXOC 0x04124 /* Receiver Overrun Count */ - /* MSI-X Table Register Descriptions */ #define IGC_PBACL 0x05B68 /* MSIx PBA Clear - R/W 1 to clear */ @@ -182,10 +172,6 @@ #define IGC_BPTC 0x040F4 /* Broadcast Packets Tx Count - R/clr */ #define IGC_TSCTC 0x040F8 /* TCP Segmentation Context Tx - R/clr */ #define IGC_IAC 0x04100 /* Interrupt Assertion Count */ -#define IGC_ICTXPTC 0x0410C /* Interrupt Cause Tx Pkt Timer Expire Count */ -#define IGC_ICTXATC 0x04110 /* Interrupt Cause Tx Abs Timer Expire Count */ -#define IGC_ICTXQEC 0x04118 /* Interrupt Cause Tx Queue Empty Count */ -#define IGC_ICTXQMTC 0x0411C /* Interrupt Cause Tx Queue Min Thresh Count */ #define IGC_RPTHC 0x04104 /* Rx Packets To Host */ #define IGC_TLPIC 0x04148 /* EEE Tx LPI Count */ #define IGC_RLPIC 0x0414C /* EEE Rx LPI Count */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 6725d892336e..71ec908266a6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1951,8 +1951,8 @@ static void ixgbe_create_lbtest_frame(struct sk_buff *skb, memset(skb->data, 0xFF, frame_size); frame_size >>= 1; memset(&skb->data[frame_size], 0xAA, frame_size / 2 - 1); - memset(&skb->data[frame_size + 10], 0xBE, 1); - memset(&skb->data[frame_size + 12], 0xAF, 1); + skb->data[frame_size + 10] = 0xBE; + skb->data[frame_size + 12] = 0xAF; } static bool ixgbe_check_lbtest_frame(struct ixgbe_rx_buffer *rx_buffer, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6f32b1706ab9..2f8a4cfc5fa1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6877,32 +6877,20 @@ int ixgbe_close(struct net_device *netdev) return 0; } -#ifdef CONFIG_PM -static int ixgbe_resume(struct pci_dev *pdev) +static int __maybe_unused ixgbe_resume(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; u32 err; adapter->hw.hw_addr = adapter->io_addr; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* - * pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); - err = pci_enable_device_mem(pdev); - if (err) { - e_dev_err("Cannot enable PCI device from suspend\n"); - return err; - } smp_mb__before_atomic(); clear_bit(__IXGBE_DISABLED, &adapter->state); pci_set_master(pdev); - pci_wake_from_d3(pdev, false); + device_wakeup_disable(dev_d); ixgbe_reset(adapter); @@ -6920,7 +6908,6 @@ static int ixgbe_resume(struct pci_dev *pdev) return err; } -#endif /* CONFIG_PM */ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) { @@ -6929,9 +6916,6 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) struct ixgbe_hw *hw = &adapter->hw; u32 ctrl; u32 wufc = adapter->wol; -#ifdef CONFIG_PM - int retval = 0; -#endif rtnl_lock(); netif_device_detach(netdev); @@ -6942,12 +6926,6 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) ixgbe_clear_interrupt_scheme(adapter); rtnl_unlock(); -#ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; - -#endif if (hw->mac.ops.stop_link_on_d3) hw->mac.ops.stop_link_on_d3(hw); @@ -7002,26 +6980,18 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) return 0; } -#ifdef CONFIG_PM -static int ixgbe_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused ixgbe_suspend(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); int retval; bool wake; retval = __ixgbe_shutdown(pdev, &wake); - if (retval) - return retval; - if (wake) { - pci_prepare_to_sleep(pdev); - } else { - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - } + device_set_wakeup_enable(dev_d, wake); - return 0; + return retval; } -#endif /* CONFIG_PM */ static void ixgbe_shutdown(struct pci_dev *pdev) { @@ -11379,16 +11349,15 @@ static const struct pci_error_handlers ixgbe_err_handler = { .resume = ixgbe_io_resume, }; +static SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume); + static struct pci_driver ixgbe_driver = { - .name = ixgbe_driver_name, - .id_table = ixgbe_pci_tbl, - .probe = ixgbe_probe, - .remove = ixgbe_remove, -#ifdef CONFIG_PM - .suspend = ixgbe_suspend, - .resume = ixgbe_resume, -#endif - .shutdown = ixgbe_shutdown, + .name = ixgbe_driver_name, + .id_table = ixgbe_pci_tbl, + .probe = ixgbe_probe, + .remove = ixgbe_remove, + .driver.pm = &ixgbe_pm_ops, + .shutdown = ixgbe_shutdown, .sriov_configure = ixgbe_pci_sriov_configure, .err_handler = &ixgbe_err_handler }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 23a92656821d..988db46bff0e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -783,7 +783,7 @@ static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN); else - memset(adapter->vfinfo[vf].vf_mac_addresses, 0, ETH_ALEN); + eth_zero_addr(adapter->vfinfo[vf].vf_mac_addresses); return retval; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index a6267569bfa9..a428113e6d54 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4297,13 +4297,10 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused ixgbevf_suspend(struct device *dev_d) { - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev_d); struct ixgbevf_adapter *adapter = netdev_priv(netdev); -#ifdef CONFIG_PM - int retval = 0; -#endif rtnl_lock(); netif_device_detach(netdev); @@ -4314,37 +4311,16 @@ static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state) ixgbevf_clear_interrupt_scheme(adapter); rtnl_unlock(); -#ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; - -#endif - if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) - pci_disable_device(pdev); - return 0; } -#ifdef CONFIG_PM -static int ixgbevf_resume(struct pci_dev *pdev) +static int __maybe_unused ixgbevf_resume(struct device *dev_d) { + struct pci_dev *pdev = to_pci_dev(dev_d); struct net_device *netdev = pci_get_drvdata(pdev); struct ixgbevf_adapter *adapter = netdev_priv(netdev); u32 err; - pci_restore_state(pdev); - /* pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); - - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); - return err; - } - adapter->hw.hw_addr = adapter->io_addr; smp_mb__before_atomic(); clear_bit(__IXGBEVF_DISABLED, &adapter->state); @@ -4365,10 +4341,9 @@ static int ixgbevf_resume(struct pci_dev *pdev) return err; } -#endif /* CONFIG_PM */ static void ixgbevf_shutdown(struct pci_dev *pdev) { - ixgbevf_suspend(pdev, PMSG_SUSPEND); + ixgbevf_suspend(&pdev->dev); } static void ixgbevf_get_tx_ring_stats(struct rtnl_link_stats64 *stats, @@ -4882,16 +4857,17 @@ static const struct pci_error_handlers ixgbevf_err_handler = { .resume = ixgbevf_io_resume, }; +static SIMPLE_DEV_PM_OPS(ixgbevf_pm_ops, ixgbevf_suspend, ixgbevf_resume); + static struct pci_driver ixgbevf_driver = { .name = ixgbevf_driver_name, .id_table = ixgbevf_pci_tbl, .probe = ixgbevf_probe, .remove = ixgbevf_remove, -#ifdef CONFIG_PM + /* Power Management Hooks */ - .suspend = ixgbevf_suspend, - .resume = ixgbevf_resume, -#endif + .driver.pm = &ixgbevf_pm_ops, + .shutdown = ixgbevf_shutdown, .err_handler = &ixgbevf_err_handler }; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 6e3f9e2f883b..832bbb8b05c8 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3637,7 +3637,7 @@ static void mvneta_start_dev(struct mvneta_port *pp) phylink_start(pp->phylink); - /* We may have called phy_speed_down before */ + /* We may have called phylink_speed_down before */ phylink_speed_up(pp->phylink); netif_tx_start_all_queues(pp->dev); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index cd5e9d60307e..2a8a5842eaef 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3508,6 +3508,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, err = mvpp2_rx_refill(port, bm_pool, pp, pool); if (err) { netdev_err(port->dev, "failed to refill BM pools\n"); + dev_kfree_skb_any(skb); goto err_drop_frame; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 64786568af0d..75a8c407e815 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1730,10 +1730,12 @@ static void otx2_reset_task(struct work_struct *work) if (!netif_running(pf->netdev)) return; + rtnl_lock(); otx2_stop(pf->netdev); pf->reset_count++; otx2_open(pf->netdev); netif_trans_update(pf->netdev); + rtnl_unlock(); } static const struct net_device_ops otx2_netdev_ops = { @@ -2111,6 +2113,7 @@ static void otx2_remove(struct pci_dev *pdev) pf = netdev_priv(netdev); + cancel_work_sync(&pf->reset_task); /* Disable link notifications */ otx2_cgx_config_linkevents(pf, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index f4227517dc8e..92a3db69a6cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -617,6 +617,8 @@ static void otx2vf_remove(struct pci_dev *pdev) vf = netdev_priv(netdev); + cancel_work_sync(&vf->reset_task); + unregister_netdev(netdev); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 20db302d31ce..0870fe78ea38 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -171,11 +171,21 @@ static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth, return 0; } -static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed) +static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, + phy_interface_t interface, int speed) { u32 val; int ret; + if (interface == PHY_INTERFACE_MODE_TRGMII) { + mtk_w32(eth, TRGMII_MODE, INTF_MODE); + val = 500000000; + ret = clk_set_rate(eth->clks[MTK_CLK_TRGPLL], val); + if (ret) + dev_err(eth->dev, "Failed to set trgmii pll: %d\n", ret); + return; + } + val = (speed == SPEED_1000) ? INTF_MODE_RGMII_1000 : INTF_MODE_RGMII_10_100; mtk_w32(eth, val, INTF_MODE); @@ -262,10 +272,9 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, state->interface)) goto err_phy; } else { - if (state->interface != - PHY_INTERFACE_MODE_TRGMII) - mtk_gmac0_rgmii_adjust(mac->hw, - state->speed); + mtk_gmac0_rgmii_adjust(mac->hw, + state->interface, + state->speed); /* mt7623_pad_clk_setup */ for (i = 0 ; i < NUM_TRGMII_CTRL; i++) @@ -2887,6 +2896,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->irq = eth->irq[0]; eth->netdev[id]->dev.of_node = np; + eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN; + return 0; free_netdev: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 8a10285b0e10..b50c567ef508 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -806,10 +806,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud goto xdp_drop_no_cnt; /* Drop on xmit failure */ default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: ring->xdp_drop++; xdp_drop_no_cnt: diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index c790a5fcea73..ae305c2e9225 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -558,7 +558,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n", __func__, be32_to_cpu(eqe->event.srq.srqn), eq->eqn); - /* fall through */ + fallthrough; case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR: if (mlx4_is_master(dev)) { /* forward only to slave owning the SRQ */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 954c22c79f6b..258c7a96f269 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4356,12 +4356,14 @@ end: static void mlx4_shutdown(struct pci_dev *pdev) { struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); mutex_unlock(&persist->interface_state_mutex); + mlx4_pci_disable_device(dev); } static const struct pci_error_handlers mlx4_err_handler = { diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 9486caecfbdc..f1b4ad9c66d2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1412,7 +1412,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], case MLX4_STEERING_MODE_A0: if (prot == MLX4_PROT_ETH) return 0; - /* fall through */ + fallthrough; case MLX4_STEERING_MODE_B0: if (prot == MLX4_PROT_ETH) @@ -1442,7 +1442,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], case MLX4_STEERING_MODE_A0: if (prot == MLX4_PROT_ETH) return 0; - /* fall through */ + fallthrough; case MLX4_STEERING_MODE_B0: if (prot == MLX4_PROT_ETH) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index c44669102626..0cc2080fd847 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -45,6 +45,7 @@ #include <linux/mlx5/transobj.h> #include <linux/mlx5/fs.h> #include <linux/rhashtable.h> +#include <net/udp_tunnel.h> #include <net/switchdev.h> #include <net/xdp.h> #include <linux/dim.h> @@ -530,6 +531,8 @@ typedef struct sk_buff * typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq); typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16); +int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk); + enum mlx5e_rq_flag { MLX5E_RQ_FLAG_XDP_XMIT, MLX5E_RQ_FLAG_XDP_REDIRECT, @@ -790,6 +793,7 @@ struct mlx5e_priv { u16 drop_rq_q_counter; struct notifier_block events_nb; + struct udp_tunnel_nic_info nic_info; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx dcbx; #endif @@ -812,6 +816,13 @@ struct mlx5e_priv { struct mlx5e_scratchpad scratchpad; }; +struct mlx5e_rx_handlers { + mlx5e_fp_handle_rx_cqe handle_rx_cqe; + mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; +}; + +extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic; + struct mlx5e_profile { int (*init)(struct mlx5_core_dev *mdev, struct net_device *netdev, @@ -828,58 +839,17 @@ struct mlx5e_profile { void (*update_carrier)(struct mlx5e_priv *priv); unsigned int (*stats_grps_num)(struct mlx5e_priv *priv); mlx5e_stats_grp_t *stats_grps; - struct { - mlx5e_fp_handle_rx_cqe handle_rx_cqe; - mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; - } rx_handlers; + const struct mlx5e_rx_handlers *rx_handlers; int max_tc; u8 rq_groups; }; void mlx5e_build_ptys2ethtool_map(void); -u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev); -netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); -void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, - struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more); - -void mlx5e_trigger_irq(struct mlx5e_icosq *sq); -void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe); -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); -void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *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_dynamic(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); -void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); -bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); -int mlx5e_poll_ico_cq(struct mlx5e_cq *cq); -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); -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); -struct sk_buff * -mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, - u16 cqe_bcnt, u32 head_offset, u32 page_idx); -struct sk_buff * -mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, - struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); -struct sk_buff * -mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, - struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); - void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s); @@ -982,8 +952,6 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state); void mlx5e_activate_rq(struct mlx5e_rq *rq); void mlx5e_deactivate_rq(struct mlx5e_rq *rq); -void mlx5e_free_rx_descs(struct mlx5e_rq *rq); -void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq); void mlx5e_activate_icosq(struct mlx5e_icosq *icosq); void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq); @@ -1008,6 +976,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, bool enable_mc_lb); +void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc); /* common netdev helpers */ void mlx5e_create_q_counters(struct mlx5e_priv *priv); @@ -1045,6 +1014,7 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv); int mlx5e_set_dev_port_mtu_ctx(struct mlx5e_priv *priv, void *context); int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, mlx5e_fp_preactivate preactivate); +void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv); /* ethtool helpers */ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, @@ -1113,8 +1083,6 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); -void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti); -void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti); netdev_features_t mlx5e_features_check(struct sk_buff *skb, struct net_device *netdev, netdev_features_t features); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index bdb71332cbf2..3e44e4d820c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -183,13 +183,16 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw, static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) { - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *priv; /* A given netdev is not a representor or not a slave of LAG configuration */ if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev)) return false; + priv = netdev_priv(netdev); + rpriv = priv->ppriv; + /* Egress acl forward to vport is supported only non-uplink representor */ return rpriv->rep->vport != MLX5_VPORT_UPLINK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index f8af109d34cc..79cc42d88eec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -551,19 +551,31 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, } } - tun_dst = tun_rx_dst(enc_opts.key.len); + if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst, + key.enc_ip.tos, key.enc_ip.ttl, + key.enc_tp.dst, TUNNEL_KEY, + key32_to_tunnel_id(key.enc_key_id.keyid), + enc_opts.key.len); + } else if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst, + key.enc_ip.tos, key.enc_ip.ttl, + key.enc_tp.dst, 0, TUNNEL_KEY, + key32_to_tunnel_id(key.enc_key_id.keyid), + enc_opts.key.len); + } else { + netdev_dbg(priv->netdev, + "Couldn't restore tunnel, unsupported addr_type: %d\n", + key.enc_control.addr_type); + return false; + } + if (!tun_dst) { - WARN_ON_ONCE(true); + netdev_dbg(priv->netdev, "Couldn't restore tunnel, no tun_dst\n"); return false; } - ip_tunnel_key_init(&tun_dst->u.tun_info.key, - key.enc_ipv4.src, key.enc_ipv4.dst, - key.enc_ip.tos, key.enc_ip.ttl, - 0, /* label */ - key.enc_tp.src, key.enc_tp.dst, - key32_to_tunnel_id(key.enc_key_id.keyid), - TUNNEL_KEY); + tun_dst->u.tun_info.key.tp_src = key.enc_tp.src; if (enc_opts.key.len) ip_tunnel_info_opts_set(&tun_dst->u.tun_info, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 951ea26d96bc..e472ed0eacfb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -301,6 +301,8 @@ static int mlx5e_tc_tun_parse_geneve_params(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, geneve_protocol_type, ETH_P_TEB); } + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index 58b13192df23..2805416c32a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -80,6 +80,8 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, gre_key.key, be32_to_cpu(enc_keyid.key->keyid)); } + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 37b176801bcc..038a0f1cecec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -136,6 +136,8 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, be32_to_cpu(enc_keyid.key->keyid)); + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index cf425a60cddc..9334c9c3e208 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -5,6 +5,7 @@ #define __MLX5_EN_TXRX_H___ #include "en.h" +#include <linux/indirect_call_wrapper.h> #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start)) @@ -18,6 +19,33 @@ enum mlx5e_icosq_wqe_type { #endif }; +/* General */ +void mlx5e_trigger_irq(struct mlx5e_icosq *sq); +void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe); +void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); +int mlx5e_napi_poll(struct napi_struct *napi, int budget); +int mlx5e_poll_ico_cq(struct mlx5e_cq *cq); + +/* RX */ +void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info); +void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info, + bool recycle); +INDIRECT_CALLABLE_DECLARE(bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)); +INDIRECT_CALLABLE_DECLARE(bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)); +int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); +void mlx5e_free_rx_descs(struct mlx5e_rq *rq); +void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq); + +/* TX */ +u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev); +netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); +void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more); +bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); +void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); + static inline bool mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n) { @@ -360,7 +388,7 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, switch (swp_spec->tun_l4_proto) { case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - /* fall through */ + fallthrough; case IPPROTO_TCP: eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index e0c1b010d41a..0e6946fc121f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -34,7 +34,6 @@ #include <net/xdp_sock_drv.h> #include "en/xdp.h" #include "en/params.h" -#include <linux/indirect_call_wrapper.h> int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { @@ -153,11 +152,11 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, return true; default: bpf_warn_invalid_xdp_action(act); - /* fall through */ + fallthrough; case XDP_ABORTED: xdp_abort: trace_xdp_exception(rq->netdev, prog, act); - /* fall through */ + fallthrough; case XDP_DROP: rq->stats->xdp_drop++; return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index cc46414773b5..dd9df519d383 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -3,6 +3,7 @@ #include "setup.h" #include "en/params.h" +#include "en/txrx.h" /* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may * change unexpectedly, and mlx5e has a minimum valid stride size for striding diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 0dfbc96e952a..4d892f6cecb3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -6,7 +6,6 @@ #include "en/xdp.h" #include "en/params.h" #include <net/xdp_sock_drv.h> -#include <linux/indirect_call_wrapper.h> int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 2a47673da5a4..f96e786db158 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -47,7 +47,6 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb, u32 *cqe_bcnt); -void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_ipsec_inverse_table_init(void); bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 0e6698d1b4ca..f4861545b236 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -470,7 +470,7 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s if (likely(!skb->decrypted)) goto out; WARN_ON_ONCE(1); - /* fall-through */ + fallthrough; case MLX5E_KTLS_SYNC_FAIL: goto err_out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1e42c7ae621b..a6cf008057b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -60,6 +60,16 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, mutex_unlock(&mdev->mlx5e_res.td.list_lock); } +void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) +{ + bool ro_pci_enable = pcie_relaxed_ordering_enabled(mdev->pdev); + bool ro_write = MLX5_CAP_GEN(mdev, relaxed_ordering_write); + bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read); + + MLX5_SET(mkc, mkc, relaxed_ordering_read, ro_pci_enable && ro_read); + MLX5_SET(mkc, mkc, relaxed_ordering_write, ro_pci_enable && ro_write); +} + static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey) { @@ -76,7 +86,7 @@ static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA); MLX5_SET(mkc, mkc, lw, 1); MLX5_SET(mkc, mkc, lr, 1); - + mlx5e_mkey_set_relaxed_ordering(mdev, mkc); MLX5_SET(mkc, mkc, pd, pdn); MLX5_SET(mkc, mkc, length64, 1); MLX5_SET(mkc, mkc, qpn, 0xffffff); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index af849bc83c30..08270987c506 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -243,7 +243,7 @@ int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset) return MLX5E_NUM_PFLAGS; case ETH_SS_TEST: return mlx5e_self_test_num(priv); - /* fallthrough */ + fallthrough; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aa4fb503dac3..aebcf73f8546 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -45,7 +45,6 @@ #include "en_tc.h" #include "en_rep.h" #include "en_accel/ipsec.h" -#include "en_accel/ipsec_rxtx.h" #include "en_accel/en_accel.h" #include "en_accel/tls.h" #include "accel/ipsec.h" @@ -65,7 +64,6 @@ #include "en/hv_vhca_stats.h" #include "en/devlink.h" #include "lib/mlx5.h" -#include "fpga/ipsec.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { @@ -276,7 +274,7 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, MLX5_SET(mkc, mkc, lw, 1); MLX5_SET(mkc, mkc, lr, 1); MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT); - + mlx5e_mkey_set_relaxed_ordering(mdev, mkc); MLX5_SET(mkc, mkc, qpn, 0xffffff); MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn); MLX5_SET64(mkc, mkc, len, npages << page_shift); @@ -419,7 +417,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -428,29 +426,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params, xsk); - rq->post_wqes = mlx5e_post_rx_mpwqes; - rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; - - rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe; -#ifdef CONFIG_MLX5_EN_IPSEC - if (MLX5_IPSEC_DEV(mdev)) { - err = -EINVAL; - netdev_err(c->netdev, "MPWQE RQ with IPSec offload not supported\n"); - goto err_rq_wq_destroy; - } -#endif - if (!rq->handle_rx_cqe) { - err = -EINVAL; - netdev_err(c->netdev, "RX handler of MPWQE RQ is not set, err %d\n", err); - goto err_rq_wq_destroy; - } - - rq->mpwqe.skb_from_cqe_mpwrq = xsk ? - mlx5e_xsk_skb_from_cqe_mpwrq_linear : - mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ? - mlx5e_skb_from_cqe_mpwrq_linear : - mlx5e_skb_from_cqe_mpwrq_nonlinear; - rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk)); @@ -470,7 +445,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -492,30 +467,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (err) goto err_free; - rq->post_wqes = mlx5e_post_rx_wqes; - rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; - -#ifdef CONFIG_MLX5_EN_IPSEC - if ((mlx5_fpga_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) && - c->priv->ipsec) - rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe; - else -#endif - rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe; - if (!rq->handle_rx_cqe) { - err = -EINVAL; - netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err); - goto err_free; - } - - rq->wqe.skb_from_cqe = xsk ? - mlx5e_xsk_skb_from_cqe_linear : - mlx5e_rx_is_linear_skb(params, NULL) ? - mlx5e_skb_from_cqe_linear : - mlx5e_skb_from_cqe_nonlinear; rq->mkey_be = c->mkey_be; } + err = mlx5e_rq_set_handlers(rq, params, xsk); + if (err) + goto err_free; + if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); @@ -3104,6 +3062,25 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; } +static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, + enum mlx5_port_status state) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int vport_admin_state; + + mlx5_set_port_admin_status(mdev, state); + + if (!MLX5_ESWITCH_MANAGER(mdev) || mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) + return; + + if (state == MLX5_PORT_UP) + vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO; + else + vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN; + + mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state); +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3136,7 +3113,7 @@ int mlx5e_open(struct net_device *netdev) mutex_lock(&priv->state_lock); err = mlx5e_open_locked(netdev); if (!err) - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); return err; @@ -3170,7 +3147,7 @@ int mlx5e_close(struct net_device *netdev) return -ENODEV; mutex_lock(&priv->state_lock); - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN); err = mlx5e_close_locked(netdev); mutex_unlock(&priv->state_lock); @@ -4214,83 +4191,6 @@ 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); -} - -void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti) -{ - struct mlx5e_priv *priv = netdev_priv(netdev); - - if (ti->type != UDP_TUNNEL_TYPE_VXLAN) - return; - - if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) - return; - - mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1); -} - -void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti) -{ - struct mlx5e_priv *priv = netdev_priv(netdev); - - if (ti->type != UDP_TUNNEL_TYPE_VXLAN) - return; - - if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) - return; - - mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0); -} - static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) @@ -4602,8 +4502,8 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_change_mtu = mlx5e_change_nic_mtu, .ndo_do_ioctl = mlx5e_ioctl, .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, - .ndo_udp_tunnel_add = mlx5e_add_vxlan_port, - .ndo_udp_tunnel_del = mlx5e_del_vxlan_port, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_features_check = mlx5e_features_check, .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, @@ -4874,6 +4774,39 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) } } +static int mlx5e_vxlan_set_port(struct net_device *netdev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + return mlx5_vxlan_add_port(priv->mdev->vxlan, ntohs(ti->port)); +} + +static int mlx5e_vxlan_unset_port(struct net_device *netdev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + return mlx5_vxlan_del_port(priv->mdev->vxlan, ntohs(ti->port)); +} + +void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv) +{ + if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) + return; + + priv->nic_info.set_port = mlx5e_vxlan_set_port; + priv->nic_info.unset_port = mlx5e_vxlan_unset_port; + priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | + UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN; + priv->nic_info.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; + /* Don't count the space hard-coded to the IANA port */ + priv->nic_info.tables[0].n_entries = + mlx5_vxlan_max_udp_ports(priv->mdev) - 1; + + priv->netdev->udp_tunnel_nic_info = &priv->nic_info; +} + static void mlx5e_build_nic_netdev(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4917,6 +4850,8 @@ 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; + mlx5e_vxlan_set_netdev_info(priv); + if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) || mlx5e_any_tunnel_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; @@ -5201,7 +5136,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) /* Marking the link as currently not needed by the Driver */ if (!netif_running(netdev)) - mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN); mlx5e_set_netdev_mtu_boundaries(priv); mlx5e_set_dev_port_mtu(priv); @@ -5222,8 +5157,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) rtnl_lock(); if (netif_running(netdev)) mlx5e_open(netdev); - if (mlx5_vxlan_allowed(priv->mdev->vxlan)) - udp_tunnel_get_rx_info(netdev); + udp_tunnel_nic_reset_ntf(priv->netdev); netif_device_attach(netdev); rtnl_unlock(); } @@ -5238,8 +5172,6 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) rtnl_lock(); if (netif_running(priv->netdev)) mlx5e_close(priv->netdev); - if (mlx5_vxlan_allowed(priv->mdev->vxlan)) - udp_tunnel_drop_rx_info(priv->netdev); netif_device_detach(priv->netdev); rtnl_unlock(); @@ -5270,8 +5202,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .update_rx = mlx5e_update_nic_rx, .update_stats = mlx5e_update_ndo_stats, .update_carrier = mlx5e_update_carrier, - .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe, - .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, + .rx_handlers = &mlx5e_rx_handlers_nic, .max_tc = MLX5E_MAX_NUM_TC, .rq_groups = MLX5E_NUM_RQ_GROUPS(XSK), .stats_grps = mlx5e_nic_stats_grps, @@ -5409,6 +5340,8 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + cancel_work_sync(&priv->update_stats_work); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index c300729fb498..e13e5d1b3eae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -42,6 +42,7 @@ #include "esw/chains.h" #include "en.h" #include "en_rep.h" +#include "en/txrx.h" #include "en_tc.h" #include "en/rep/tc.h" #include "en/rep/neigh.h" @@ -610,6 +611,29 @@ static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *dev) return &rpriv->dl_port; } +static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch_rep *rep = rpriv->rep; + int err; + + if (new_carrier) { + err = mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, + rep->vport, 1, MLX5_VPORT_ADMIN_STATE_UP); + if (err) + return err; + netif_carrier_on(dev); + } else { + err = mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, + rep->vport, 1, MLX5_VPORT_ADMIN_STATE_DOWN); + if (err) + return err; + netif_carrier_off(dev); + } + return 0; +} + static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_open = mlx5e_rep_open, .ndo_stop = mlx5e_rep_close, @@ -620,6 +644,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, .ndo_change_mtu = mlx5e_rep_change_mtu, + .ndo_change_carrier = mlx5e_rep_change_carrier, }; static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { @@ -633,8 +658,8 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, .ndo_change_mtu = mlx5e_uplink_rep_change_mtu, - .ndo_udp_tunnel_add = mlx5e_add_vxlan_port, - .ndo_udp_tunnel_del = mlx5e_del_vxlan_port, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_features_check = mlx5e_features_check, .ndo_set_vf_mac = mlx5e_set_vf_mac, .ndo_set_vf_rate = mlx5e_set_vf_rate, @@ -699,12 +724,13 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) struct mlx5_eswitch_rep *rep = rpriv->rep; struct mlx5_core_dev *mdev = priv->mdev; + SET_NETDEV_DEV(netdev, mdev->device); if (rep->vport == MLX5_VPORT_UPLINK) { - SET_NETDEV_DEV(netdev, mdev->device); netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep; /* we want a persistent mac for the uplink rep */ mlx5_query_mac_address(mdev, netdev->dev_addr); netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops; + mlx5e_vxlan_set_netdev_info(priv); mlx5e_dcbnl_build_rep_netdev(netdev); } else { netdev->netdev_ops = &mlx5e_netdev_ops_rep; @@ -935,6 +961,7 @@ err_close_drop_rq: static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { + mlx5e_ethtool_cleanup_steering(priv); rep_vport_rx_rule_destroy(priv); mlx5e_destroy_rep_root_ft(priv); mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); @@ -1079,6 +1106,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5e_rep_tc_enable(priv); + mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, + 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); mlx5_lag_add(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); @@ -1143,8 +1172,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .enable = mlx5e_rep_enable, .update_rx = mlx5e_update_rep_rx, .update_stats = mlx5e_update_ndo_stats, - .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, - .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq_rep, + .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = 1, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), .stats_grps = mlx5e_rep_stats_grps, @@ -1163,8 +1191,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .update_rx = mlx5e_update_rep_rx, .update_stats = mlx5e_update_ndo_stats, .update_carrier = mlx5e_update_carrier, - .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, - .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq_rep, + .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = MLX5E_MAX_NUM_TC, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), .stats_grps = mlx5e_ul_rep_stats_grps, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 1d5669801484..622c27ae4ac7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -41,6 +41,8 @@ #include "lib/port_tun.h" #ifdef CONFIG_MLX5_ESWITCH +extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep; + struct mlx5e_neigh_update_table { struct rhashtable neigh_ht; /* Save the neigh hash entries in a list in addition to the hash table @@ -223,10 +225,6 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv); int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv); void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv); -void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); -void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, - struct mlx5_cqe64 *cqe); - void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv); bool mlx5e_eswitch_vf_rep(struct net_device *netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 74860f3827b1..65828af120b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -34,22 +34,39 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> -#include <linux/indirect_call_wrapper.h> #include <net/ip6_checksum.h> #include <net/page_pool.h> #include <net/inet_ecn.h> #include "en.h" +#include "en/txrx.h" #include "en_tc.h" #include "eswitch.h" #include "en_rep.h" #include "en/rep/tc.h" #include "ipoib/ipoib.h" +#include "accel/ipsec.h" +#include "fpga/ipsec.h" #include "en_accel/ipsec_rxtx.h" #include "en_accel/tls_rxtx.h" #include "lib/clock.h" #include "en/xdp.h" #include "en/xsk/rx.h" #include "en/health.h" +#include "en/params.h" + +static 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); +static struct sk_buff * +mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, + u16 cqe_bcnt, u32 head_offset, u32 page_idx); +static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); +static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); + +const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = { + .handle_rx_cqe = mlx5e_handle_rx_cqe, + .handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, +}; static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { @@ -370,7 +387,7 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, mlx5e_put_rx_frag(rq, wi, recycle); } -void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) +static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix); @@ -537,14 +554,14 @@ err: return err; } -void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) +static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; /* 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) +INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) { struct mlx5_wq_cyc *wq = &rq->wqe.wq; u8 wqe_bulk; @@ -685,7 +702,7 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) return i; } -bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) +INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) { struct mlx5e_icosq *sq = &rq->channel->icosq; struct mlx5_wq_ll *wq = &rq->mpwqe.wq; @@ -1106,7 +1123,7 @@ static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom, xdp->frame_sz = rq->buff.frame0_sz; } -struct sk_buff * +static struct sk_buff * mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) { @@ -1146,7 +1163,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, return skb; } -struct sk_buff * +static struct sk_buff * mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) { @@ -1201,7 +1218,7 @@ static void trigger_report(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) } } -void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; @@ -1244,7 +1261,7 @@ wq_cyc_pop: } #ifdef CONFIG_MLX5_ESWITCH -void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct net_device *netdev = rq->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); @@ -1299,8 +1316,7 @@ wq_cyc_pop: mlx5_wq_cyc_pop(wq); } -void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, - struct mlx5_cqe64 *cqe) +static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); u16 wqe_id = be16_to_cpu(cqe->wqe_id); @@ -1358,9 +1374,14 @@ mpwrq_cqe_out: mlx5e_free_rx_mpwqe(rq, wi, true); mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); } + +const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = { + .handle_rx_cqe = mlx5e_handle_rx_cqe_rep, + .handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq_rep, +}; #endif -struct sk_buff * +static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx) { @@ -1406,7 +1427,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w return skb; } -struct sk_buff * +static 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) { @@ -1456,7 +1477,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return skb; } -void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); u16 wqe_id = be16_to_cpu(cqe->wqe_id); @@ -1652,7 +1673,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, stats->bytes += cqe_bcnt; } -void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +static void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; @@ -1688,11 +1709,15 @@ wq_free_wqe: mlx5_wq_cyc_pop(wq); } +const struct mlx5e_rx_handlers mlx5i_rx_handlers = { + .handle_rx_cqe = mlx5i_handle_rx_cqe, + .handle_rx_cqe_mpwqe = NULL, /* Not supported */ +}; #endif /* CONFIG_MLX5_CORE_IPOIB */ #ifdef CONFIG_MLX5_EN_IPSEC -void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +static void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; @@ -1729,3 +1754,55 @@ wq_free_wqe: } #endif /* CONFIG_MLX5_EN_IPSEC */ + +int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk) +{ + struct mlx5_core_dev *mdev = rq->mdev; + struct mlx5e_channel *c = rq->channel; + + switch (rq->wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + rq->mpwqe.skb_from_cqe_mpwrq = xsk ? + mlx5e_xsk_skb_from_cqe_mpwrq_linear : + mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ? + mlx5e_skb_from_cqe_mpwrq_linear : + mlx5e_skb_from_cqe_mpwrq_nonlinear; + rq->post_wqes = mlx5e_post_rx_mpwqes; + rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; + + rq->handle_rx_cqe = c->priv->profile->rx_handlers->handle_rx_cqe_mpwqe; +#ifdef CONFIG_MLX5_EN_IPSEC + if (MLX5_IPSEC_DEV(mdev)) { + netdev_err(c->netdev, "MPWQE RQ with IPSec offload not supported\n"); + return -EINVAL; + } +#endif + if (!rq->handle_rx_cqe) { + netdev_err(c->netdev, "RX handler of MPWQE RQ is not set\n"); + return -EINVAL; + } + break; + default: /* MLX5_WQ_TYPE_CYCLIC */ + rq->wqe.skb_from_cqe = xsk ? + mlx5e_xsk_skb_from_cqe_linear : + mlx5e_rx_is_linear_skb(params, NULL) ? + mlx5e_skb_from_cqe_linear : + mlx5e_skb_from_cqe_nonlinear; + rq->post_wqes = mlx5e_post_rx_wqes; + rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; + +#ifdef CONFIG_MLX5_EN_IPSEC + if ((mlx5_fpga_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) && + c->priv->ipsec) + rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe; + else +#endif + rq->handle_rx_cqe = c->priv->profile->rx_handlers->handle_rx_cqe; + if (!rq->handle_rx_cqe) { + netdev_err(c->netdev, "RX handler of RQ is not set\n"); + return -EINVAL; + } + } + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 7a0c22d05575..fd53d101d8fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2247,6 +2247,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, match.key->vlan_priority); *match_level = MLX5_MATCH_L2; + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index e3dbab2a294c..de10b06bade5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -31,8 +31,8 @@ */ #include <linux/irq.h> -#include <linux/indirect_call_wrapper.h> #include "en.h" +#include "en/txrx.h" #include "en/xdp.h" #include "en/xsk/rx.h" #include "en/xsk/tx.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index e8f900e9577e..6e6a9a563992 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1632,7 +1632,7 @@ abort: mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } - + esw_destroy_tsar(esw); return err; } @@ -1687,8 +1687,6 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) else if (esw->mode == MLX5_ESWITCH_OFFLOADS) esw_offloads_disable(esw); - esw_destroy_tsar(esw); - old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; @@ -1698,6 +1696,8 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } + esw_destroy_tsar(esw); + if (clear_vf) mlx5_eswitch_clear_vf_vports_info(esw); } @@ -1949,6 +1949,8 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT; + int other_vport = 1; int err = 0; if (!ESW_ALLOWED(esw)) @@ -1956,15 +1958,17 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, if (IS_ERR(evport)) return PTR_ERR(evport); + if (vport == MLX5_VPORT_UPLINK) { + opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK; + other_vport = 0; + vport = 0; + } mutex_lock(&esw->state_lock); - err = mlx5_modify_vport_admin_state(esw->dev, - MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, 1, link_state); + err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state); if (err) { - mlx5_core_warn(esw->dev, - "Failed to set vport %d link state, err = %d", - vport, err); + mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d", + vport, opmod, err); goto unlock; } @@ -2006,8 +2010,6 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); int err = 0; - if (!ESW_ALLOWED(esw)) - return -EPERM; if (IS_ERR(evport)) return PTR_ERR(evport); if (vlan > 4095 || qos > 7) @@ -2035,6 +2037,9 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u8 set_flags = 0; int err; + if (!ESW_ALLOWED(esw)) + return -EPERM; + if (vlan || qos) set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index b68e02ad65e2..867d8120b8a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -271,7 +271,6 @@ struct mlx5_eswitch { struct mlx5_esw_offload offloads; int mode; - int nvports; u16 manager_vport; u16 first_host_vport; struct mlx5_esw_functions esw_funcs; @@ -686,6 +685,8 @@ static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { r static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {} static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; } static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } +static inline +int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) { return ERR_PTR(-EOPNOTSUPP); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index db856d70c4f8..d2516922d867 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -236,6 +236,15 @@ static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw, return &esw->offloads.vport_reps[idx]; } +static void +mlx5_eswitch_set_rule_flow_source(struct mlx5_eswitch *esw, + struct mlx5_flow_spec *spec, + struct mlx5_esw_flow_attr *attr) +{ + if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && + attr && attr->in_rep && attr->in_rep->vport == MLX5_VPORT_UPLINK) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; +} static void mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, @@ -259,9 +268,6 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, mlx5_eswitch_get_vport_metadata_mask()); spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; - misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc))) - spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } else { misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport); @@ -279,10 +285,6 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } - - if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && - attr->in_rep->vport == MLX5_VPORT_UPLINK) - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; } struct mlx5_flow_handle * @@ -396,6 +398,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, goto err_esw_get; } + mlx5_eswitch_set_rule_flow_source(esw, spec, attr); + if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr, &flow_act, dest, i); @@ -462,6 +466,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, i++; mlx5_eswitch_set_rule_source_port(esw, spec, attr); + mlx5_eswitch_set_rule_flow_source(esw, spec, attr); if (attr->outer_match_level != MLX5_MATCH_NONE) spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; @@ -1132,7 +1137,7 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, } } -static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) +static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_table_attr ft_attr = {}; @@ -1165,7 +1170,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) goto ns_err; } - table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + + table_size = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ + MLX5_ESW_MISS_FLOWS + esw->total_vports; /* create the slow path fdb with encap set, so further table instances @@ -1202,7 +1207,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn); MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); - ix = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ; + ix = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ; MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1); @@ -1270,7 +1275,6 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) if (err) goto miss_rule_err; - esw->nvports = nvports; kvfree(flow_group_in); return 0; @@ -1311,7 +1315,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) MLX5_FLOW_STEERING_MODE_DMFS); } -static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) +static int esw_create_offloads_table(struct mlx5_eswitch *esw) { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; @@ -1325,7 +1329,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) return -EOPNOTSUPP; } - ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS; + ft_attr.max_fte = esw->total_vports + MLX5_ESW_MISS_FLOWS; ft_attr.prio = 1; ft_offloads = mlx5_create_flow_table(ns, &ft_attr); @@ -1346,14 +1350,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw) mlx5_destroy_flow_table(offloads->ft_offloads); } -static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports) +static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *g; u32 *flow_group_in; + int nvports; int err = 0; - nvports = nvports + MLX5_ESW_MISS_FLOWS; + nvports = esw->total_vports + MLX5_ESW_MISS_FLOWS; flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) return -ENOMEM; @@ -1986,15 +1991,8 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) static int esw_offloads_steering_init(struct mlx5_eswitch *esw) { - int num_vfs = esw->esw_funcs.num_vfs; - int total_vports; int err; - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) - total_vports = esw->total_vports; - else - total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev); - memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb)); mutex_init(&esw->fdb_table.offloads.vports.lock); hash_init(esw->fdb_table.offloads.vports.table); @@ -2003,7 +2001,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) if (err) goto create_acl_err; - err = esw_create_offloads_table(esw, total_vports); + err = esw_create_offloads_table(esw); if (err) goto create_offloads_err; @@ -2011,11 +2009,11 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) if (err) goto create_restore_err; - err = esw_create_offloads_fdb_tables(esw, total_vports); + err = esw_create_offloads_fdb_tables(esw); if (err) goto create_fdb_err; - err = esw_create_vport_rx_group(esw, total_vports); + err = esw_create_vport_rx_group(esw); if (err) goto create_fg_err; @@ -2353,7 +2351,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE) goto out; - /* fall through */ + fallthrough; case MLX5_CAP_INLINE_MODE_L2: NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set"); err = -EOPNOTSUPP; @@ -2465,13 +2463,13 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, esw->offloads.encap = encap; - err = esw_create_offloads_fdb_tables(esw, esw->nvports); + err = esw_create_offloads_fdb_tables(esw); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed re-creating fast FDB table"); esw->offloads.encap = !encap; - (void)esw_create_offloads_fdb_tables(esw, esw->nvports); + (void)esw_create_offloads_fdb_tables(esw); } unlock: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 182d3ac3e73f..831d2c39e153 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -339,14 +339,14 @@ static void mlx5_fpga_conn_handle_cqe(struct mlx5_fpga_conn *conn, switch (opcode) { case MLX5_CQE_REQ_ERR: status = ((struct mlx5_err_cqe *)cqe)->syndrome; - /* Fall through */ + fallthrough; case MLX5_CQE_REQ: mlx5_fpga_conn_sq_cqe(conn, cqe, status); break; case MLX5_CQE_RESP_ERR: status = ((struct mlx5_err_cqe *)cqe)->syndrome; - /* Fall through */ + fallthrough; case MLX5_CQE_RESP_SEND: mlx5_fpga_conn_rq_cqe(conn, cqe, status); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 6904ad96af48..7e70a8178a46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -796,7 +796,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse if false then return the first flow table in next priority of +/* If reverse is false then return the first flow table in next priority of * prio in the tree, else return the last flow table in the previous priority * of prio in the tree. */ @@ -828,34 +828,16 @@ static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) return find_closest_ft(prio, true); } -static struct fs_prio *find_fwd_ns_prio(struct mlx5_flow_root_namespace *root, - struct mlx5_flow_namespace *ns) -{ - struct mlx5_flow_namespace *root_ns = &root->ns; - struct fs_prio *iter_prio; - struct fs_prio *prio; - - fs_get_obj(prio, ns->node.parent); - list_for_each_entry(iter_prio, &root_ns->node.children, node.list) { - if (iter_prio == prio && - !list_is_last(&prio->node.children, &iter_prio->node.list)) - return list_next_entry(iter_prio, node.list); - } - return NULL; -} - static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, struct mlx5_flow_act *flow_act) { - struct mlx5_flow_root_namespace *root = find_root(&ft->node); struct fs_prio *prio; + bool next_ns; - if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS) - prio = find_fwd_ns_prio(root, ft->ns); - else - fs_get_obj(prio, ft->node.parent); + next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; + fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return (prio) ? find_next_chained_ft(prio) : NULL; + return find_next_chained_ft(prio); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, @@ -864,18 +846,15 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root = find_root(&prio->node); struct mlx5_flow_table *iter; - int i = 0; int err; fs_for_each_ft(iter, prio) { - i++; err = root->cmds->modify_flow_table(root, iter, ft); if (err) { - mlx5_core_warn(dev, "Failed to modify flow table %d\n", - iter->id); + mlx5_core_err(dev, + "Failed to modify flow table id %d, type %d, err %d\n", + iter->id, iter->type, err); /* The driver is out of sync with the FW */ - if (i > 1) - WARN_ON(true); return err; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 690b822c6152..5763965d5ef3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -464,8 +464,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = { .update_rx = mlx5i_update_nic_rx, .update_stats = NULL, /* mlx5i_update_stats */ .update_carrier = NULL, /* no HW update in IB link */ - .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, - .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ + .rx_handlers = &mlx5i_rx_handlers, .max_tc = MLX5I_MAX_NUM_TC, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), .stats_grps = mlx5i_stats_grps, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 79071a15c4ca..b79dc1e28c41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -42,6 +42,7 @@ extern const struct ethtool_ops mlx5i_ethtool_ops; extern const struct ethtool_ops mlx5i_pkey_ethtool_ops; +extern const struct mlx5e_rx_handlers mlx5i_rx_handlers; #define MLX5_IB_GRH_BYTES 40 #define MLX5_IPOIB_ENCAP_LEN 4 @@ -117,7 +118,6 @@ struct mlx5i_tx_wqe { void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more); -void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); #endif /* CONFIG_MLX5_CORE_IPOIB */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index f70367018862..7163d9f6c4a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -349,8 +349,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = { .disable = NULL, .update_rx = mlx5i_update_nic_rx, .update_stats = NULL, - .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, - .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ + .rx_handlers = &mlx5i_rx_handlers, .max_tc = MLX5I_MAX_NUM_TC, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index e9089a793632..9e68f5926ab6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -198,13 +198,13 @@ static void mlx5_lag_fib_update(struct work_struct *work) /* Protect internal structures from changes */ rtnl_lock(); switch (fib_work->event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: mlx5_lag_fib_route_event(ldev, fib_work->event, fib_work->fen_info.fi); fib_info_put(fib_work->fen_info.fi); break; - case FIB_EVENT_NH_ADD: /* fall through */ + case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: fib_nh = fib_work->fnh_info.fib_nh; mlx5_lag_fib_nexthop_event(ldev, @@ -255,7 +255,7 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, return NOTIFY_DONE; switch (event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: fen_info = container_of(info, struct fib_entry_notifier_info, info); @@ -278,7 +278,7 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; - case FIB_EVENT_NH_ADD: /* fall through */ + case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: fnh_info = container_of(info, struct fib_nh_notifier_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index ef0706d15a5b..2d55b7c22c03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -273,17 +273,17 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp, if (rq->extts.index >= clock->ptp_info.n_pins) return -EINVAL; + pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); + if (pin < 0) + return -EBUSY; + if (on) { - pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); - if (pin < 0) - return -EBUSY; pin_mode = MLX5_PIN_MODE_IN; pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); field_select = MLX5_MTPPS_FS_PIN_MODE | MLX5_MTPPS_FS_PATTERN | MLX5_MTPPS_FS_ENABLE; } else { - pin = rq->extts.index; field_select = MLX5_MTPPS_FS_ENABLE; } @@ -331,12 +331,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if (rq->perout.index >= clock->ptp_info.n_pins) return -EINVAL; - if (on) { - pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, - rq->perout.index); - if (pin < 0) - return -EBUSY; + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + if (on) { pin_mode = MLX5_PIN_MODE_OUT; pattern = MLX5_OUT_PATTERN_PERIODIC; ts.tv_sec = rq->perout.period.sec; @@ -362,7 +362,6 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, MLX5_MTPPS_FS_ENABLE | MLX5_MTPPS_FS_TIME_STAMP; } else { - pin = rq->perout.index; field_select = MLX5_MTPPS_FS_ENABLE; } @@ -409,10 +408,31 @@ static int mlx5_ptp_enable(struct ptp_clock_info *ptp, return 0; } +enum { + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN = BIT(0), + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT = BIT(1), +}; + static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan) { - return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + + switch (func) { + case PTP_PF_NONE: + return 0; + case PTP_PF_EXTTS: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN); + case PTP_PF_PEROUT: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT); + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; } static const struct ptp_clock_info mlx5_ptp_clock_info = { @@ -432,6 +452,38 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .verify = NULL, }; +static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin, + u32 *mtpps, u32 mtpps_size) +{ + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {}; + + MLX5_SET(mtpps_reg, in, pin, pin); + + return mlx5_core_access_reg(mdev, in, sizeof(in), mtpps, + mtpps_size, MLX5_REG_MTPPS, 0, 0); +} + +static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin) +{ + struct mlx5_core_dev *mdev = clock->mdev; + u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {}; + u8 mode; + int err; + + err = mlx5_query_mtpps_pin_mode(mdev, pin, out, sizeof(out)); + if (err || !MLX5_GET(mtpps_reg, out, enable)) + return PTP_PF_NONE; + + mode = MLX5_GET(mtpps_reg, out, pin_mode); + + if (mode == MLX5_PIN_MODE_IN) + return PTP_PF_EXTTS; + else if (mode == MLX5_PIN_MODE_OUT) + return PTP_PF_PEROUT; + + return PTP_PF_NONE; +} + static int mlx5_init_pin_config(struct mlx5_clock *clock) { int i; @@ -451,8 +503,8 @@ static int mlx5_init_pin_config(struct mlx5_clock *clock) sizeof(clock->ptp_info.pin_config[i].name), "mlx5_pps%d", i); clock->ptp_info.pin_config[i].index = i; - clock->ptp_info.pin_config[i].func = PTP_PF_NONE; - clock->ptp_info.pin_config[i].chan = i; + clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i); + clock->ptp_info.pin_config[i].chan = 0; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index be34330d89cc..3315afe2f8dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -42,21 +42,14 @@ struct mlx5_vxlan { struct mlx5_core_dev *mdev; /* 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; - refcount_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)] = {}; @@ -109,48 +102,24 @@ static struct mlx5_vxlan_port *vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 p int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { struct mlx5_vxlan_port *vxlanp; - int ret = 0; - - mutex_lock(&vxlan->sync_lock); - vxlanp = vxlan_lookup_port(vxlan, port); - if (vxlanp) { - refcount_inc(&vxlanp->refcount); - goto unlock; - } + int ret; - 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; - } + vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL); + if (!vxlanp) + return -ENOMEM; + vxlanp->udp_port = port; 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; + if (ret) { + kfree(vxlanp); + return ret; } - vxlanp->udp_port = port; - refcount_set(&vxlanp->refcount, 1); - + mutex_lock(&vxlan->sync_lock); hash_add_rcu(vxlan->htable, &vxlanp->hlist, port); - - 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; + return 0; } int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) @@ -161,18 +130,15 @@ int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) mutex_lock(&vxlan->sync_lock); vxlanp = vxlan_lookup_port(vxlan, port); - if (!vxlanp) { + if (WARN_ON(!vxlanp)) { ret = -ENOENT; goto out_unlock; } - if (refcount_dec_and_test(&vxlanp->refcount)) { - hash_del_rcu(&vxlanp->hlist); - synchronize_rcu(); - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); - kfree(vxlanp); - vxlan->num_ports--; - } + hash_del_rcu(&vxlanp->hlist); + synchronize_rcu(); + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); + kfree(vxlanp); out_unlock: mutex_unlock(&vxlan->sync_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h index 6d599f4a8acd..ec766529f49b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h @@ -37,6 +37,11 @@ struct mlx5_vxlan; struct mlx5_vxlan_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 inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan) { /* not allowed reason is encoded in vxlan pointer as error, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 5ddd18639a1e..a4a23a27c368 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -35,6 +35,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/mlx5/driver.h> +#include <linux/xarray.h> #include "mlx5_core.h" #include "lib/eq.h" @@ -73,15 +74,45 @@ enum { MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, }; +static struct rb_root *page_root_per_func_id(struct mlx5_core_dev *dev, u16 func_id) +{ + struct rb_root *root; + int err; + + root = xa_load(&dev->priv.page_root_xa, func_id); + if (root) + return root; + + root = kzalloc(sizeof(*root), GFP_KERNEL); + if (!root) + return ERR_PTR(-ENOMEM); + + err = xa_insert(&dev->priv.page_root_xa, func_id, root, GFP_KERNEL); + if (err) { + kfree(root); + return ERR_PTR(err); + } + + *root = RB_ROOT; + + return root; +} + static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id) { - struct rb_root *root = &dev->priv.page_root; - struct rb_node **new = &root->rb_node; struct rb_node *parent = NULL; + struct rb_root *root; + struct rb_node **new; struct fw_page *nfp; struct fw_page *tfp; int i; + root = page_root_per_func_id(dev, func_id); + if (IS_ERR(root)) + return PTR_ERR(root); + + new = &root->rb_node; + while (*new) { parent = *new; tfp = rb_entry(parent, struct fw_page, rb_node); @@ -111,13 +142,20 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u return 0; } -static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr) +static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr, + u32 func_id) { - struct rb_root *root = &dev->priv.page_root; - struct rb_node *tmp = root->rb_node; struct fw_page *result = NULL; + struct rb_root *root; + struct rb_node *tmp; struct fw_page *tfp; + root = xa_load(&dev->priv.page_root_xa, func_id); + if (WARN_ON_ONCE(!root)) + return NULL; + + tmp = root->rb_node; + while (tmp) { tfp = rb_entry(tmp, struct fw_page, rb_node); if (tfp->addr < addr) { @@ -191,7 +229,13 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u16 func_id) static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp, bool in_free_list) { - rb_erase(&fwp->rb_node, &dev->priv.page_root); + struct rb_root *root; + + root = xa_load(&dev->priv.page_root_xa, fwp->func_id); + if (WARN_ON_ONCE(!root)) + return; + + rb_erase(&fwp->rb_node, root); if (in_free_list) list_del(&fwp->list); dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK, @@ -200,12 +244,12 @@ static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp, kfree(fwp); } -static void free_4k(struct mlx5_core_dev *dev, u64 addr) +static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 func_id) { struct fw_page *fwp; int n; - fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK); + fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK, func_id); if (!fwp) { mlx5_core_warn_rl(dev, "page not found\n"); return; @@ -340,7 +384,7 @@ retry: out_4k: for (i--; i >= 0; i--) - free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i])); + free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), func_id); out_free: kvfree(in); if (notify_fail) @@ -351,16 +395,19 @@ out_free: static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id, bool ec_function) { + struct rb_root *root; struct rb_node *p; int npages = 0; - p = rb_first(&dev->priv.page_root); + root = xa_load(&dev->priv.page_root_xa, func_id); + if (WARN_ON_ONCE(!root)) + return; + + p = rb_first(root); while (p) { struct fw_page *fwp = rb_entry(p, struct fw_page, rb_node); p = rb_next(p); - if (fwp->func_id != func_id) - continue; npages += (MLX5_NUM_4K_IN_PAGE - fwp->free_count); free_fwp(dev, fwp, fwp->free_count); } @@ -378,6 +425,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id, static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 *in, int in_size, u32 *out, int out_size) { + struct rb_root *root; struct fw_page *fwp; struct rb_node *p; u32 func_id; @@ -391,12 +439,14 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, npages = MLX5_GET(manage_pages_in, in, input_num_entries); func_id = MLX5_GET(manage_pages_in, in, function_id); - p = rb_first(&dev->priv.page_root); + root = xa_load(&dev->priv.page_root_xa, func_id); + if (WARN_ON_ONCE(!root)) + return -EEXIST; + + p = rb_first(root); while (p && i < npages) { fwp = rb_entry(p, struct fw_page, rb_node); p = rb_next(p); - if (fwp->func_id != func_id) - continue; MLX5_ARRAY_SET64(manage_pages_out, out, pas, i, fwp->addr); i++; @@ -430,7 +480,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, MLX5_SET(manage_pages_in, in, input_num_entries, npages); MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); - mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen); + mlx5_core_dbg(dev, "func 0x%x, npages %d, outlen %d\n", + func_id, npages, outlen); err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen); if (err) { mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err); @@ -446,7 +497,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, } for (i = 0; i < num_claimed; i++) - free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i])); + free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]), func_id); if (nclaimed) *nclaimed = num_claimed; @@ -560,35 +611,49 @@ static int optimal_reclaimed_pages(void) return ret; } -int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) +static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, + struct rb_root *root, u16 func_id) { unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); - struct fw_page *fwp; - struct rb_node *p; - int nclaimed = 0; - int err = 0; - do { - p = rb_first(&dev->priv.page_root); - if (p) { - fwp = rb_entry(p, struct fw_page, rb_node); - err = reclaim_pages(dev, fwp->func_id, - optimal_reclaimed_pages(), - &nclaimed, mlx5_core_is_ecpf(dev)); - - if (err) { - mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", - err); - return err; - } - if (nclaimed) - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + while (!RB_EMPTY_ROOT(root)) { + int nclaimed; + int err; + + err = reclaim_pages(dev, func_id, optimal_reclaimed_pages(), + &nclaimed, mlx5_core_is_ecpf(dev)); + if (err) { + mlx5_core_warn(dev, "failed reclaiming pages (%d) for func id 0x%x\n", + err, func_id); + return err; } + + if (nclaimed) + end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + if (time_after(jiffies, end)) { mlx5_core_warn(dev, "FW did not return all pages. giving up...\n"); break; } - } while (p); + } + + return 0; +} + +int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) +{ + struct rb_root *root; + unsigned long id; + void *entry; + + xa_for_each(&dev->priv.page_root_xa, id, entry) { + root = entry; + mlx5_reclaim_root_pages(dev, root, id); + xa_erase(&dev->priv.page_root_xa, id); + kfree(root); + } + + WARN_ON(!xa_empty(&dev->priv.page_root_xa)); WARN(dev->priv.fw_pages, "FW pages counter is %d after reclaiming all pages\n", @@ -605,17 +670,19 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) int mlx5_pagealloc_init(struct mlx5_core_dev *dev) { - dev->priv.page_root = RB_ROOT; INIT_LIST_HEAD(&dev->priv.free_list); dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator"); if (!dev->priv.pg_wq) return -ENOMEM; + xa_init(&dev->priv.page_root_xa); + return 0; } void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev) { + xa_destroy(&dev->priv.page_root_xa); destroy_workqueue(dev->priv.pg_wq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 31abcbb95ca2..c63f727273d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -395,7 +395,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, /* Check that all mask fields were consumed */ for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) { if (((u8 *)&mask)[i] != 0) { - mlx5dr_err(dmn, "Mask contains unsupported parameters\n"); + mlx5dr_dbg(dmn, "Mask contains unsupported parameters\n"); return -EOPNOTSUPP; } } @@ -474,14 +474,13 @@ static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher) int ret; next_matcher = NULL; - if (!list_empty(&tbl->matcher_list)) - list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) { - if (tmp_matcher->prio >= matcher->prio) { - next_matcher = tmp_matcher; - break; - } - first = false; + list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) { + if (tmp_matcher->prio >= matcher->prio) { + next_matcher = tmp_matcher; + break; } + first = false; + } prev_matcher = NULL; if (next_matcher && !first) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index cd708dcc2e3a..6ec5106bc472 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -574,9 +574,8 @@ void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste, { struct mlx5dr_rule_member *rule_mem; - if (!list_empty(&ste->rule_list)) - list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list) - rule_mem->ste = new_ste; + list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list) + rule_mem->ste = new_ste; } static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 8887b2440c7d..9b08eb557a31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -279,29 +279,9 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, /* The order of the actions are must to be keep, only the following * order is supported by SW steering: - * TX: push vlan -> modify header -> encap + * TX: modify header -> push vlan -> encap * RX: decap -> pop vlan -> modify header */ - if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { - tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]); - if (!tmp_action) { - err = -ENOMEM; - goto free_actions; - } - fs_dr_actions[fs_dr_num_actions++] = tmp_action; - actions[num_actions++] = tmp_action; - } - - if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) { - tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]); - if (!tmp_action) { - err = -ENOMEM; - goto free_actions; - } - fs_dr_actions[fs_dr_num_actions++] = tmp_action; - actions[num_actions++] = tmp_action; - } - if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { enum mlx5dr_action_reformat_type decap_type = DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2; @@ -354,6 +334,26 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, actions[num_actions++] = fte->action.modify_hdr->action.dr_action; + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) { + tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + if (delay_encap_set) actions[num_actions++] = fte->action.pkt_reformat->action.dr_action; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 88cdb9bb4c4a..bdafc85fd874 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -110,7 +110,7 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode)) break; - /* fall through */ + fallthrough; case MLX5_CAP_INLINE_MODE_L2: *min_inline_mode = MLX5_INLINE_MODE_L2; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index b01f8f2fab63..08d101138fbe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1177,14 +1177,15 @@ static void mlxsw_devlink_trap_fini(struct devlink *devlink, static int mlxsw_devlink_trap_action_set(struct devlink *devlink, const struct devlink_trap *trap, - enum devlink_trap_action action) + enum devlink_trap_action action, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver; if (!mlxsw_driver->trap_action_set) return -EOPNOTSUPP; - return mlxsw_driver->trap_action_set(mlxsw_core, trap, action); + return mlxsw_driver->trap_action_set(mlxsw_core, trap, action, extack); } static int @@ -1202,14 +1203,15 @@ mlxsw_devlink_trap_group_init(struct devlink *devlink, static int mlxsw_devlink_trap_group_set(struct devlink *devlink, const struct devlink_trap_group *group, - const struct devlink_trap_policer *policer) + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver; if (!mlxsw_driver->trap_group_set) return -EOPNOTSUPP; - return mlxsw_driver->trap_group_set(mlxsw_core, group, policer); + return mlxsw_driver->trap_group_set(mlxsw_core, group, policer, extack); } static int @@ -1815,7 +1817,7 @@ static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core, err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans, bulk_list, cb, cb_priv, tid); if (err) { - kfree(trans); + kfree_rcu(trans, rcu); return err; } return 0; @@ -2053,11 +2055,13 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, break; } } - rcu_read_unlock(); - if (!found) + if (!found) { + rcu_read_unlock(); goto drop; + } rxl->func(skb, local_port, rxl_item->priv); + rcu_read_unlock(); return; drop: diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index c1c1e039323a..11af3308f8cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -89,13 +89,15 @@ struct mlxsw_listener { }; #define __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ - _dis_action, _enabled_on_register, _dis_trap_group) \ + _dis_action, _enabled_on_register, _dis_trap_group, \ + _mirror_reason) \ { \ .trap_id = MLXSW_TRAP_ID_##_trap_id, \ .rx_listener = \ { \ .func = _func, \ .local_port = MLXSW_PORT_DONT_CARE, \ + .mirror_reason = _mirror_reason, \ .trap_id = MLXSW_TRAP_ID_##_trap_id, \ }, \ .en_action = MLXSW_REG_HPKT_ACTION_##_en_action, \ @@ -109,12 +111,17 @@ struct mlxsw_listener { #define MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _trap_group, \ _dis_action) \ __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _trap_group, \ - _dis_action, true, _trap_group) + _dis_action, true, _trap_group, 0) #define MLXSW_RXL_DIS(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ _dis_action, _dis_trap_group) \ __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ - _dis_action, false, _dis_trap_group) + _dis_action, false, _dis_trap_group, 0) + +#define MLXSW_RXL_MIRROR(_func, _session_id, _trap_group, _mirror_reason) \ + __MLXSW_RXL(_func, MIRROR_SESSION##_session_id, TRAP_TO_CPU, false, \ + _trap_group, TRAP_TO_CPU, true, _trap_group, \ + _mirror_reason) #define MLXSW_EVENTL(_func, _trap_id, _trap_group) \ { \ @@ -326,12 +333,14 @@ struct mlxsw_driver { const struct devlink_trap *trap, void *trap_ctx); int (*trap_action_set)(struct mlxsw_core *mlxsw_core, const struct devlink_trap *trap, - enum devlink_trap_action action); + enum devlink_trap_action action, + struct netlink_ext_ack *extack); int (*trap_group_init)(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group); int (*trap_group_set)(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group, - const struct devlink_trap_policer *policer); + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack); int (*trap_policer_init)(struct mlxsw_core *mlxsw_core, const struct devlink_trap_policer *policer); void (*trap_policer_fini)(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index a7d86df7123f..44fa02cbb683 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -11,7 +11,7 @@ #include "reg.h" static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, - bool *qsfp) + bool *qsfp, bool *cmis) { char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; @@ -25,15 +25,19 @@ static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, return err; mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); ident = eeprom_tmp[0]; + *cmis = false; switch (ident) { case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: *qsfp = false; break; case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */ case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ - case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: + *qsfp = true; + break; case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD: *qsfp = true; + *cmis = true; break; default: return -EINVAL; @@ -70,8 +74,9 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, if (qsfp) { /* When reading upper pages 1, 2 and 3 the offset * starts at 128. Please refer to "QSFP+ Memory Map" - * figure in SFF-8436 specification for graphical - * depiction. + * figure in SFF-8436 specification and to "CMIS Module + * Memory Map" figure in CMIS specification for + * graphical depiction. */ page = MLXSW_REG_MCIA_PAGE_GET(offset); offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page; @@ -116,7 +121,8 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, char mcia_pl[MLXSW_REG_MCIA_LEN] = {0}; char mtmp_pl[MLXSW_REG_MTMP_LEN]; unsigned int module_temp; - bool qsfp; + bool qsfp, cmis; + int page; int err; mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN + module, @@ -140,21 +146,28 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, */ /* Validate module identifier value. */ - err = mlxsw_env_validate_cable_ident(core, module, &qsfp); + err = mlxsw_env_validate_cable_ident(core, module, &qsfp, &cmis); if (err) return err; - if (qsfp) - mlxsw_reg_mcia_pack(mcia_pl, module, 0, - MLXSW_REG_MCIA_TH_PAGE_NUM, + if (qsfp) { + /* For QSFP/CMIS module-defined thresholds are located in page + * 02h, otherwise in page 03h. + */ + if (cmis) + page = MLXSW_REG_MCIA_TH_PAGE_CMIS_NUM; + else + page = MLXSW_REG_MCIA_TH_PAGE_NUM; + mlxsw_reg_mcia_pack(mcia_pl, module, 0, page, MLXSW_REG_MCIA_TH_PAGE_OFF + off, MLXSW_REG_MCIA_TH_ITEM_SIZE, MLXSW_REG_MCIA_I2C_ADDR_LOW); - else + } else { mlxsw_reg_mcia_pack(mcia_pl, module, 0, MLXSW_REG_MCIA_PAGE0_LO, off, MLXSW_REG_MCIA_TH_ITEM_SIZE, MLXSW_REG_MCIA_I2C_ADDR_HIGH); + } err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); if (err) @@ -221,6 +234,22 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, else modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN / 2; break; + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD: + /* Use SFF_8636 as base type. ethtool should recognize specific + * type through the identifier value. + */ + modinfo->type = ETH_MODULE_SFF_8636; + /* Verify if module EEPROM is a flat memory. In case of flat + * memory only page 00h (0-255 bytes) can be read. Otherwise + * upper pages 01h and 02h can also be read. Upper pages 10h + * and 11h are currently not supported by the driver. + */ + if (module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_TYPE_ID] & + MLXSW_REG_MCIA_EEPROM_CMIS_FLAT_MEMORY) + modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + else + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + break; default: return -EINVAL; } @@ -235,8 +264,8 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev, { int offset = ee->offset; unsigned int read_size; + bool qsfp, cmis; int i = 0; - bool qsfp; int err; if (!ee->len) @@ -244,7 +273,7 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev, memset(data, 0, ee->len); /* Validate module identifier value. */ - err = mlxsw_env_validate_cable_ident(mlxsw_core, module, &qsfp); + err = mlxsw_env_validate_cable_ident(mlxsw_core, module, &qsfp, &cmis); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 3c5b25495751..079b080de7f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5595,6 +5595,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST, MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY, MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP, + MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME, MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP, MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT, @@ -5613,6 +5614,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_EXCEPTIONS, MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_BUFFER_DISCARDS, __MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 @@ -8605,8 +8607,10 @@ MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16); #define MLXSW_REG_MCIA_PAGE0_LO_OFF 0xa0 #define MLXSW_REG_MCIA_TH_ITEM_SIZE 2 #define MLXSW_REG_MCIA_TH_PAGE_NUM 3 +#define MLXSW_REG_MCIA_TH_PAGE_CMIS_NUM 2 #define MLXSW_REG_MCIA_PAGE0_LO 0 #define MLXSW_REG_MCIA_TH_PAGE_OFF 0x80 +#define MLXSW_REG_MCIA_EEPROM_CMIS_FLAT_MEMORY BIT(7) enum mlxsw_reg_mcia_eeprom_module_info_rev_id { MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_UNSPC = 0x00, @@ -8625,6 +8629,7 @@ enum mlxsw_reg_mcia_eeprom_module_info_id { enum mlxsw_reg_mcia_eeprom_module_info { MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID, MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_TYPE_ID, MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 519eb44e4097..fdf9aa8314b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3055,6 +3055,7 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->ptp_ops = &mlxsw_sp1_ptp_ops; mlxsw_sp->span_ops = &mlxsw_sp1_span_ops; mlxsw_sp->policer_core_ops = &mlxsw_sp1_policer_core_ops; + mlxsw_sp->trap_ops = &mlxsw_sp1_trap_ops; mlxsw_sp->listeners = mlxsw_sp1_listener; mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp1_listener); mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1; @@ -3084,6 +3085,7 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops; mlxsw_sp->span_ops = &mlxsw_sp2_span_ops; mlxsw_sp->policer_core_ops = &mlxsw_sp2_policer_core_ops; + mlxsw_sp->trap_ops = &mlxsw_sp2_trap_ops; mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2; return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack); @@ -3111,6 +3113,7 @@ static int mlxsw_sp3_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops; mlxsw_sp->span_ops = &mlxsw_sp3_span_ops; mlxsw_sp->policer_core_ops = &mlxsw_sp2_policer_core_ops; + mlxsw_sp->trap_ops = &mlxsw_sp2_trap_ops; mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3; return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 6ab1b6d725af..f9ba59641b4d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -177,6 +177,7 @@ struct mlxsw_sp { const struct mlxsw_sp_ptp_ops *ptp_ops; const struct mlxsw_sp_span_ops *span_ops; const struct mlxsw_sp_policer_core_ops *policer_core_ops; + const struct mlxsw_sp_trap_ops *trap_ops; const struct mlxsw_listener *listeners; size_t listeners_count; u32 lowest_shaper_bs; @@ -983,6 +984,10 @@ struct mlxsw_sp_mall_mirror_entry { int span_id; }; +struct mlxsw_sp_mall_trap_entry { + int span_id; +}; + struct mlxsw_sp_mall_entry { struct list_head list; unsigned long cookie; @@ -991,6 +996,7 @@ struct mlxsw_sp_mall_entry { bool ingress; union { struct mlxsw_sp_mall_mirror_entry mirror; + struct mlxsw_sp_mall_trap_entry trap; struct mlxsw_sp_port_sample sample; }; struct rcu_head rcu; @@ -1177,12 +1183,14 @@ void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core, const struct devlink_trap *trap, void *trap_ctx); int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, const struct devlink_trap *trap, - enum devlink_trap_action action); + enum devlink_trap_action action, + struct netlink_ext_ack *extack); int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group); int mlxsw_sp_trap_group_set(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group, - const struct devlink_trap_policer *policer); + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack); int mlxsw_sp_trap_policer_init(struct mlxsw_core *mlxsw_core, const struct devlink_trap_policer *policer); @@ -1196,6 +1204,8 @@ int mlxsw_sp_trap_policer_counter_get(struct mlxsw_core *mlxsw_core, const struct devlink_trap_policer *policer, u64 *p_drops); +int mlxsw_sp_trap_group_policer_hw_id_get(struct mlxsw_sp *mlxsw_sp, u16 id, + bool *p_enabled, u16 *p_hw_id); static inline struct net *mlxsw_sp_net(struct mlxsw_sp *mlxsw_sp) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c index 7974982533b5..b65b93a2b9bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c @@ -121,7 +121,6 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) { unsigned int sub_pools_count = ARRAY_SIZE(mlxsw_sp_counter_sub_pools); struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); - struct mlxsw_sp_counter_sub_pool *sub_pool; struct mlxsw_sp_counter_pool *pool; unsigned int map_size; int err; @@ -131,9 +130,9 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) if (!pool) return -ENOMEM; mlxsw_sp->counter_pool = pool; - memcpy(pool->sub_pools, mlxsw_sp_counter_sub_pools, - sub_pools_count * sizeof(*sub_pool)); pool->sub_pools_count = sub_pools_count; + memcpy(pool->sub_pools, mlxsw_sp_counter_sub_pools, + flex_array_size(pool, sub_pools, pool->sub_pools_count)); spin_lock_init(&pool->counter_pool_lock); atomic_set(&pool->active_entries_count, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index a5ce1eec5418..964fd444bb10 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -1289,19 +1289,18 @@ struct mlxsw_sp_qevent_binding { static LIST_HEAD(mlxsw_sp_qevent_block_cb_list); -static int mlxsw_sp_qevent_mirror_configure(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_mall_entry *mall_entry, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding, + const struct mlxsw_sp_span_agent_parms *agent_parms, + int *p_span_id) { struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = {}; - struct mlxsw_sp_span_agent_parms agent_parms = { - .to_dev = mall_entry->mirror.to_dev, - }; int span_id; int err; - err = mlxsw_sp_span_agent_get(mlxsw_sp, &span_id, &agent_parms); + err = mlxsw_sp_span_agent_get(mlxsw_sp, &span_id, agent_parms); if (err) return err; @@ -1320,7 +1319,7 @@ static int mlxsw_sp_qevent_mirror_configure(struct mlxsw_sp *mlxsw_sp, if (err) goto err_trigger_enable; - mall_entry->mirror.span_id = span_id; + *p_span_id = span_id; return 0; err_trigger_enable: @@ -1333,13 +1332,13 @@ err_analyzed_port_get: return err; } -static void mlxsw_sp_qevent_mirror_deconfigure(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_mall_entry *mall_entry, - struct mlxsw_sp_qevent_binding *qevent_binding) +static void mlxsw_sp_qevent_span_deconfigure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_qevent_binding *qevent_binding, + int span_id) { struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = { - .span_id = mall_entry->mirror.span_id, + .span_id = span_id, }; mlxsw_sp_span_trigger_disable(mlxsw_sp_port, qevent_binding->span_trigger, @@ -1347,7 +1346,51 @@ static void mlxsw_sp_qevent_mirror_deconfigure(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, &trigger_parms); mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); - mlxsw_sp_span_agent_put(mlxsw_sp, mall_entry->mirror.span_id); + mlxsw_sp_span_agent_put(mlxsw_sp, span_id); +} + +static int mlxsw_sp_qevent_mirror_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + struct mlxsw_sp_span_agent_parms agent_parms = { + .to_dev = mall_entry->mirror.to_dev, + }; + + return mlxsw_sp_qevent_span_configure(mlxsw_sp, mall_entry, qevent_binding, + &agent_parms, &mall_entry->mirror.span_id); +} + +static void mlxsw_sp_qevent_mirror_deconfigure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + mlxsw_sp_qevent_span_deconfigure(mlxsw_sp, qevent_binding, mall_entry->mirror.span_id); +} + +static int mlxsw_sp_qevent_trap_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + struct mlxsw_sp_span_agent_parms agent_parms = {}; + int err; + + err = mlxsw_sp_trap_group_policer_hw_id_get(mlxsw_sp, + DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, + &agent_parms.policer_enable, + &agent_parms.policer_id); + if (err) + return err; + + return mlxsw_sp_qevent_span_configure(mlxsw_sp, mall_entry, qevent_binding, + &agent_parms, &mall_entry->trap.span_id); +} + +static void mlxsw_sp_qevent_trap_deconfigure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + mlxsw_sp_qevent_span_deconfigure(mlxsw_sp, qevent_binding, mall_entry->trap.span_id); } static int mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, @@ -1357,6 +1400,8 @@ static int mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, switch (mall_entry->type) { case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: return mlxsw_sp_qevent_mirror_configure(mlxsw_sp, mall_entry, qevent_binding); + case MLXSW_SP_MALL_ACTION_TYPE_TRAP: + return mlxsw_sp_qevent_trap_configure(mlxsw_sp, mall_entry, qevent_binding); default: /* This should have been validated away. */ WARN_ON(1); @@ -1371,6 +1416,8 @@ static void mlxsw_sp_qevent_entry_deconfigure(struct mlxsw_sp *mlxsw_sp, switch (mall_entry->type) { case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: return mlxsw_sp_qevent_mirror_deconfigure(mlxsw_sp, mall_entry, qevent_binding); + case MLXSW_SP_MALL_ACTION_TYPE_TRAP: + return mlxsw_sp_qevent_trap_deconfigure(mlxsw_sp, mall_entry, qevent_binding); default: WARN_ON(1); return; @@ -1490,6 +1537,8 @@ static int mlxsw_sp_qevent_mall_replace(struct mlxsw_sp *mlxsw_sp, if (act->id == FLOW_ACTION_MIRRED) { mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR; mall_entry->mirror.to_dev = act->dev; + } else if (act->id == FLOW_ACTION_TRAP) { + mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_TRAP; } else { NL_SET_ERR_MSG(f->common.extack, "Unsupported action"); err = -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 019ed503aadf..0521e9d48c45 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5001,15 +5001,6 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) { - /* Packets with link-local destination IP arriving to the router - * are trapped to the CPU, so no need to program specific routes - * for them. Only allow prefix routes (usually one fe80::/64) so - * that packets are trapped for the right reason. - */ - if ((ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL) && - (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))) - return true; - /* Multicast routes aren't supported, so ignore them. Neighbour * Discovery packets are specifically trapped. */ @@ -8078,16 +8069,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; - router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; - err = register_inetaddr_notifier(&router->inetaddr_nb); - if (err) - goto err_register_inetaddr_notifier; - - router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event; - err = register_inet6addr_notifier(&router->inet6addr_nb); - if (err) - goto err_register_inet6addr_notifier; - INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list); err = __mlxsw_sp_router_init(mlxsw_sp); if (err) @@ -8128,12 +8109,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_init; - mlxsw_sp->router->netevent_nb.notifier_call = - mlxsw_sp_router_netevent_event; - err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); - if (err) - goto err_register_netevent_notifier; - err = mlxsw_sp_mp_hash_init(mlxsw_sp); if (err) goto err_mp_hash_init; @@ -8142,6 +8117,22 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_dscp_init; + router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; + err = register_inetaddr_notifier(&router->inetaddr_nb); + if (err) + goto err_register_inetaddr_notifier; + + router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event; + err = register_inet6addr_notifier(&router->inet6addr_nb); + if (err) + goto err_register_inet6addr_notifier; + + mlxsw_sp->router->netevent_nb.notifier_call = + mlxsw_sp_router_netevent_event; + err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); + if (err) + goto err_register_netevent_notifier; + mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb, @@ -8152,10 +8143,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, return 0; err_register_fib_notifier: -err_dscp_init: -err_mp_hash_init: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: + unregister_inet6addr_notifier(&router->inet6addr_nb); +err_register_inet6addr_notifier: + unregister_inetaddr_notifier(&router->inetaddr_nb); +err_register_inetaddr_notifier: + mlxsw_core_flush_owq(); +err_dscp_init: +err_mp_hash_init: mlxsw_sp_neigh_fini(mlxsw_sp); err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); @@ -8174,10 +8170,6 @@ err_ipips_init: err_rifs_init: __mlxsw_sp_router_fini(mlxsw_sp); err_router_init: - unregister_inet6addr_notifier(&router->inet6addr_nb); -err_register_inet6addr_notifier: - unregister_inetaddr_notifier(&router->inetaddr_nb); -err_register_inetaddr_notifier: mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); return err; @@ -8188,6 +8180,9 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); + unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); + unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); + mlxsw_core_flush_owq(); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); @@ -8197,8 +8192,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_ipips_fini(mlxsw_sp); mlxsw_sp_rifs_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); - unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); - unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 323eaf979aea..5c959a995199 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -837,7 +837,8 @@ static int mlxsw_sp_span_policer_id_base_set(struct mlxsw_sp_span *span, static void mlxsw_sp_span_policer_id_base_unset(struct mlxsw_sp_span *span) { - refcount_dec(&span->policer_id_base_ref_count); + if (refcount_dec_and_test(&span->policer_id_base_ref_count)) + span->policer_id_base = 0; } static struct mlxsw_sp_span_entry * diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 157a42c63066..2e41c5519c1b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -21,6 +21,7 @@ struct mlxsw_sp_trap_group_item { struct devlink_trap_group group; u16 hw_group_id; u8 priority; + u8 fixed_policer:1; /* Whether policer binding can change */ }; #define MLXSW_SP_TRAP_LISTENERS_MAX 3 @@ -28,6 +29,7 @@ struct mlxsw_sp_trap_group_item { struct mlxsw_sp_trap_item { struct devlink_trap trap; struct mlxsw_listener listeners_arr[MLXSW_SP_TRAP_LISTENERS_MAX]; + u8 is_source:1; }; /* All driver-specific traps must be documented in @@ -46,6 +48,11 @@ enum { #define MLXSW_SP_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT +enum { + /* Packet was early dropped. */ + MLXSW_SP_MIRROR_REASON_INGRESS_WRED = 9, +}; + static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, u8 local_port, struct mlxsw_sp_port *mlxsw_sp_port) @@ -222,6 +229,11 @@ static void mlxsw_sp_rx_sample_listener(struct sk_buff *skb, u8 local_port, DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ MLXSW_SP_TRAP_METADATA | (_metadata)) +#define MLXSW_SP_TRAP_BUFFER_DROP(_id) \ + DEVLINK_TRAP_GENERIC(DROP, TRAP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, \ + MLXSW_SP_TRAP_METADATA) + #define MLXSW_SP_TRAP_DRIVER_DROP(_id, _group_id) \ DEVLINK_TRAP_DRIVER(DROP, DROP, DEVLINK_MLXSW_TRAP_ID_##_id, \ DEVLINK_MLXSW_TRAP_NAME_##_id, \ @@ -248,6 +260,10 @@ static void mlxsw_sp_rx_sample_listener(struct sk_buff *skb, u8 local_port, TRAP_EXCEPTION_TO_CPU, false, SP_##_en_group_id, \ SET_FW_DEFAULT, SP_##_dis_group_id) +#define MLXSW_SP_RXL_BUFFER_DISCARD(_mirror_reason) \ + MLXSW_RXL_MIRROR(mlxsw_sp_rx_drop_listener, 0, SP_BUFFER_DISCARDS, \ + MLXSW_SP_MIRROR_REASON_##_mirror_reason) + #define MLXSW_SP_RXL_EXCEPTION(_id, _group_id, _action) \ MLXSW_RXL(mlxsw_sp_rx_mark_listener, _id, \ _action, false, SP_##_group_id, SET_FW_DEFAULT) @@ -328,6 +344,12 @@ mlxsw_sp_trap_policer_items_arr[] = { { .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128), }, + { + .policer = MLXSW_SP_TRAP_POLICER(19, 1024, 512), + }, + { + .policer = MLXSW_SP_TRAP_POLICER(20, 10240, 4096), + }, }; static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { @@ -422,6 +444,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { .priority = 2, }, { + .group = DEVLINK_TRAP_GROUP_GENERIC(EXTERNAL_DELIVERY, 19), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, + .priority = 1, + }, + { .group = DEVLINK_TRAP_GROUP_GENERIC(IPV6, 15), .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6, .priority = 2, @@ -882,11 +909,11 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { }, }, { - .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, LOCAL_DELIVERY, + .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, EXTERNAL_DELIVERY, TRAP), .listeners_arr = { - MLXSW_SP_RXL_MARK(RTR_INGRESS0, IP2ME, TRAP_TO_CPU, - false), + MLXSW_SP_RXL_MARK(RTR_INGRESS0, EXTERNAL_ROUTE, + TRAP_TO_CPU, false), }, }, { @@ -1055,10 +1082,10 @@ static int mlxsw_sp_trap_dummy_group_init(struct mlxsw_sp *mlxsw_sp) static int mlxsw_sp_trap_policer_items_arr_init(struct mlxsw_sp *mlxsw_sp) { + size_t arr_size = ARRAY_SIZE(mlxsw_sp_trap_policer_items_arr); size_t elem_size = sizeof(struct mlxsw_sp_trap_policer_item); - u64 arr_size = ARRAY_SIZE(mlxsw_sp_trap_policer_items_arr); struct mlxsw_sp_trap *trap = mlxsw_sp->trap; - u64 free_policers = 0; + size_t free_policers = 0; u32 last_id; int i; @@ -1151,6 +1178,43 @@ static void mlxsw_sp_trap_policers_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_trap_policer_items_arr_fini(mlxsw_sp); } +static int mlxsw_sp_trap_group_items_arr_init(struct mlxsw_sp *mlxsw_sp) +{ + size_t common_groups_count = ARRAY_SIZE(mlxsw_sp_trap_group_items_arr); + const struct mlxsw_sp_trap_group_item *spec_group_items_arr; + size_t elem_size = sizeof(struct mlxsw_sp_trap_group_item); + struct mlxsw_sp_trap *trap = mlxsw_sp->trap; + size_t groups_count, spec_groups_count; + int err; + + err = mlxsw_sp->trap_ops->groups_init(mlxsw_sp, &spec_group_items_arr, + &spec_groups_count); + if (err) + return err; + + /* The group items array is created by concatenating the common trap + * group items and the ASIC-specific trap group items. + */ + groups_count = common_groups_count + spec_groups_count; + trap->group_items_arr = kcalloc(groups_count, elem_size, GFP_KERNEL); + if (!trap->group_items_arr) + return -ENOMEM; + + memcpy(trap->group_items_arr, mlxsw_sp_trap_group_items_arr, + elem_size * common_groups_count); + memcpy(trap->group_items_arr + common_groups_count, + spec_group_items_arr, elem_size * spec_groups_count); + + trap->groups_count = groups_count; + + return 0; +} + +static void mlxsw_sp_trap_group_items_arr_fini(struct mlxsw_sp *mlxsw_sp) +{ + kfree(mlxsw_sp->trap->group_items_arr); +} + static int mlxsw_sp_trap_groups_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); @@ -1158,13 +1222,9 @@ static int mlxsw_sp_trap_groups_init(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp_trap *trap = mlxsw_sp->trap; int err, i; - trap->group_items_arr = kmemdup(mlxsw_sp_trap_group_items_arr, - sizeof(mlxsw_sp_trap_group_items_arr), - GFP_KERNEL); - if (!trap->group_items_arr) - return -ENOMEM; - - trap->groups_count = ARRAY_SIZE(mlxsw_sp_trap_group_items_arr); + err = mlxsw_sp_trap_group_items_arr_init(mlxsw_sp); + if (err) + return err; for (i = 0; i < trap->groups_count; i++) { group_item = &trap->group_items_arr[i]; @@ -1181,7 +1241,7 @@ err_trap_group_register: group_item = &trap->group_items_arr[i]; devlink_trap_groups_unregister(devlink, &group_item->group, 1); } - kfree(trap->group_items_arr); + mlxsw_sp_trap_group_items_arr_fini(mlxsw_sp); return err; } @@ -1197,7 +1257,7 @@ static void mlxsw_sp_trap_groups_fini(struct mlxsw_sp *mlxsw_sp) group_item = &trap->group_items_arr[i]; devlink_trap_groups_unregister(devlink, &group_item->group, 1); } - kfree(trap->group_items_arr); + mlxsw_sp_trap_group_items_arr_fini(mlxsw_sp); } static bool @@ -1206,6 +1266,43 @@ mlxsw_sp_trap_listener_is_valid(const struct mlxsw_listener *listener) return listener->trap_id != 0; } +static int mlxsw_sp_trap_items_arr_init(struct mlxsw_sp *mlxsw_sp) +{ + size_t common_traps_count = ARRAY_SIZE(mlxsw_sp_trap_items_arr); + const struct mlxsw_sp_trap_item *spec_trap_items_arr; + size_t elem_size = sizeof(struct mlxsw_sp_trap_item); + struct mlxsw_sp_trap *trap = mlxsw_sp->trap; + size_t traps_count, spec_traps_count; + int err; + + err = mlxsw_sp->trap_ops->traps_init(mlxsw_sp, &spec_trap_items_arr, + &spec_traps_count); + if (err) + return err; + + /* The trap items array is created by concatenating the common trap + * items and the ASIC-specific trap items. + */ + traps_count = common_traps_count + spec_traps_count; + trap->trap_items_arr = kcalloc(traps_count, elem_size, GFP_KERNEL); + if (!trap->trap_items_arr) + return -ENOMEM; + + memcpy(trap->trap_items_arr, mlxsw_sp_trap_items_arr, + elem_size * common_traps_count); + memcpy(trap->trap_items_arr + common_traps_count, + spec_trap_items_arr, elem_size * spec_traps_count); + + trap->traps_count = traps_count; + + return 0; +} + +static void mlxsw_sp_trap_items_arr_fini(struct mlxsw_sp *mlxsw_sp) +{ + kfree(mlxsw_sp->trap->trap_items_arr); +} + static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); @@ -1213,13 +1310,9 @@ static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) const struct mlxsw_sp_trap_item *trap_item; int err, i; - trap->trap_items_arr = kmemdup(mlxsw_sp_trap_items_arr, - sizeof(mlxsw_sp_trap_items_arr), - GFP_KERNEL); - if (!trap->trap_items_arr) - return -ENOMEM; - - trap->traps_count = ARRAY_SIZE(mlxsw_sp_trap_items_arr); + err = mlxsw_sp_trap_items_arr_init(mlxsw_sp); + if (err) + return err; for (i = 0; i < trap->traps_count; i++) { trap_item = &trap->trap_items_arr[i]; @@ -1236,7 +1329,7 @@ err_trap_register: trap_item = &trap->trap_items_arr[i]; devlink_traps_unregister(devlink, &trap_item->trap, 1); } - kfree(trap->trap_items_arr); + mlxsw_sp_trap_items_arr_fini(mlxsw_sp); return err; } @@ -1252,7 +1345,7 @@ static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp) trap_item = &trap->trap_items_arr[i]; devlink_traps_unregister(devlink, &trap_item->trap, 1); } - kfree(trap->trap_items_arr); + mlxsw_sp_trap_items_arr_fini(mlxsw_sp); } int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp) @@ -1344,7 +1437,8 @@ void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core, int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, const struct devlink_trap *trap, - enum devlink_trap_action action) + enum devlink_trap_action action, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); const struct mlxsw_sp_trap_item *trap_item; @@ -1354,6 +1448,11 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, if (WARN_ON(!trap_item)) return -EINVAL; + if (trap_item->is_source) { + NL_SET_ERR_MSG_MOD(extack, "Changing the action of source traps is not supported"); + return -EOPNOTSUPP; + } + for (i = 0; i < MLXSW_SP_TRAP_LISTENERS_MAX; i++) { const struct mlxsw_listener *listener; bool enabled; @@ -1384,7 +1483,7 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, static int __mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group, - u32 policer_id) + u32 policer_id, struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); u16 hw_policer_id = MLXSW_REG_HTGT_INVALID_POLICER; @@ -1395,6 +1494,11 @@ __mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, if (WARN_ON(!group_item)) return -EINVAL; + if (group_item->fixed_policer && policer_id != group->init_policer_id) { + NL_SET_ERR_MSG_MOD(extack, "Changing the policer binding of this group is not supported"); + return -EOPNOTSUPP; + } + if (policer_id) { struct mlxsw_sp_trap_policer_item *policer_item; @@ -1414,16 +1518,18 @@ int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group) { return __mlxsw_sp_trap_group_init(mlxsw_core, group, - group->init_policer_id); + group->init_policer_id, NULL); } int mlxsw_sp_trap_group_set(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group, - const struct devlink_trap_policer *policer) + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack) { u32 policer_id = policer ? policer->id : 0; - return __mlxsw_sp_trap_group_init(mlxsw_core, group, policer_id); + return __mlxsw_sp_trap_group_init(mlxsw_core, group, policer_id, + extack); } static int @@ -1568,3 +1674,110 @@ mlxsw_sp_trap_policer_counter_get(struct mlxsw_core *mlxsw_core, return 0; } + +int mlxsw_sp_trap_group_policer_hw_id_get(struct mlxsw_sp *mlxsw_sp, u16 id, + bool *p_enabled, u16 *p_hw_id) +{ + struct mlxsw_sp_trap_policer_item *pol_item; + struct mlxsw_sp_trap_group_item *gr_item; + u32 pol_id; + + gr_item = mlxsw_sp_trap_group_item_lookup(mlxsw_sp, id); + if (!gr_item) + return -ENOENT; + + pol_id = gr_item->group.init_policer_id; + if (!pol_id) { + *p_enabled = false; + return 0; + } + + pol_item = mlxsw_sp_trap_policer_item_lookup(mlxsw_sp, pol_id); + if (WARN_ON(!pol_item)) + return -ENOENT; + + *p_enabled = true; + *p_hw_id = pol_item->hw_id; + return 0; +} + +static const struct mlxsw_sp_trap_group_item +mlxsw_sp1_trap_group_items_arr[] = { +}; + +static const struct mlxsw_sp_trap_item +mlxsw_sp1_trap_items_arr[] = { +}; + +static int +mlxsw_sp1_trap_groups_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_trap_group_item **arr, + size_t *p_groups_count) +{ + *arr = mlxsw_sp1_trap_group_items_arr; + *p_groups_count = ARRAY_SIZE(mlxsw_sp1_trap_group_items_arr); + + return 0; +} + +static int mlxsw_sp1_traps_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_trap_item **arr, + size_t *p_traps_count) +{ + *arr = mlxsw_sp1_trap_items_arr; + *p_traps_count = ARRAY_SIZE(mlxsw_sp1_trap_items_arr); + + return 0; +} + +const struct mlxsw_sp_trap_ops mlxsw_sp1_trap_ops = { + .groups_init = mlxsw_sp1_trap_groups_init, + .traps_init = mlxsw_sp1_traps_init, +}; + +static const struct mlxsw_sp_trap_group_item +mlxsw_sp2_trap_group_items_arr[] = { + { + .group = DEVLINK_TRAP_GROUP_GENERIC(BUFFER_DROPS, 20), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_BUFFER_DISCARDS, + .priority = 0, + .fixed_policer = true, + }, +}; + +static const struct mlxsw_sp_trap_item +mlxsw_sp2_trap_items_arr[] = { + { + .trap = MLXSW_SP_TRAP_BUFFER_DROP(EARLY_DROP), + .listeners_arr = { + MLXSW_SP_RXL_BUFFER_DISCARD(INGRESS_WRED), + }, + .is_source = true, + }, +}; + +static int +mlxsw_sp2_trap_groups_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_trap_group_item **arr, + size_t *p_groups_count) +{ + *arr = mlxsw_sp2_trap_group_items_arr; + *p_groups_count = ARRAY_SIZE(mlxsw_sp2_trap_group_items_arr); + + return 0; +} + +static int mlxsw_sp2_traps_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_trap_item **arr, + size_t *p_traps_count) +{ + *arr = mlxsw_sp2_trap_items_arr; + *p_traps_count = ARRAY_SIZE(mlxsw_sp2_trap_items_arr); + + return 0; +} + +const struct mlxsw_sp_trap_ops mlxsw_sp2_trap_ops = { + .groups_init = mlxsw_sp2_trap_groups_init, + .traps_init = mlxsw_sp2_traps_init, +}; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h index 13ac412f4d53..b8df684bedef 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h @@ -9,13 +9,13 @@ struct mlxsw_sp_trap { struct mlxsw_sp_trap_policer_item *policer_items_arr; - u64 policers_count; /* Number of registered policers */ + size_t policers_count; /* Number of registered policers */ struct mlxsw_sp_trap_group_item *group_items_arr; - u64 groups_count; /* Number of registered groups */ + size_t groups_count; /* Number of registered groups */ struct mlxsw_sp_trap_item *trap_items_arr; - u64 traps_count; /* Number of registered traps */ + size_t traps_count; /* Number of registered traps */ u16 thin_policer_hw_id; @@ -23,4 +23,16 @@ struct mlxsw_sp_trap { unsigned long policers_usage[]; /* Usage bitmap */ }; +struct mlxsw_sp_trap_ops { + int (*groups_init)(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_trap_group_item **arr, + size_t *p_groups_count); + int (*traps_init)(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_trap_item **arr, + size_t *p_traps_count); +}; + +extern const struct mlxsw_sp_trap_ops mlxsw_sp1_trap_ops; +extern const struct mlxsw_sp_trap_ops mlxsw_sp2_trap_ops; + #endif diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index f2d94b026d88..867c680f5917 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -497,21 +497,21 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) spin_unlock_irqrestore(&port->tx_skbs.lock, flags); - /* Next ts */ - ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); + /* Get the h/w timestamp */ + ocelot_get_hwtimestamp(ocelot, &ts); if (unlikely(!skb_match)) continue; - /* Get the h/w timestamp */ - ocelot_get_hwtimestamp(ocelot, &ts); - /* Set the timestamp into the skb */ memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); skb_tstamp_tx(skb_match, &shhwtstamps); dev_kfree_skb_any(skb_match); + + /* Next ts */ + ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); } } EXPORT_SYMBOL(ocelot_get_txtstamp); diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index d2708a57f2ff..4075f5e59955 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1299,19 +1299,21 @@ static int nixge_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT); err = nixge_of_get_resources(pdev); if (err) - return err; + goto free_netdev; __nixge_hw_set_mac_address(ndev); priv->tx_irq = platform_get_irq_byname(pdev, "tx"); if (priv->tx_irq < 0) { netdev_err(ndev, "could not find 'tx' irq"); - return priv->tx_irq; + err = priv->tx_irq; + goto free_netdev; } priv->rx_irq = platform_get_irq_byname(pdev, "rx"); if (priv->rx_irq < 0) { netdev_err(ndev, "could not find 'rx' irq"); - return priv->rx_irq; + err = priv->rx_irq; + goto free_netdev; } priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 095561924bdc..3c57c331729f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -403,8 +403,7 @@ static int ionic_get_coalesce(struct net_device *netdev, { struct ionic_lif *lif = netdev_priv(netdev); - /* Tx uses Rx interrupt */ - coalesce->tx_coalesce_usecs = lif->rx_coalesce_usecs; + coalesce->tx_coalesce_usecs = lif->tx_coalesce_usecs; coalesce->rx_coalesce_usecs = lif->rx_coalesce_usecs; return 0; @@ -417,7 +416,8 @@ static int ionic_set_coalesce(struct net_device *netdev, struct ionic_identity *ident; struct ionic_qcq *qcq; unsigned int i; - u32 coal; + u32 rx_coal; + u32 tx_coal; ident = &lif->ionic->ident; if (ident->dev.intr_coal_div == 0) { @@ -426,26 +426,31 @@ static int ionic_set_coalesce(struct net_device *netdev, return -EIO; } - /* Tx uses Rx interrupt, so only change Rx */ - if (coalesce->tx_coalesce_usecs != lif->rx_coalesce_usecs) { + /* Tx normally shares Rx interrupt, so only change Rx */ + if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state) && + coalesce->tx_coalesce_usecs != lif->rx_coalesce_usecs) { netdev_warn(netdev, "only the rx-usecs can be changed\n"); return -EINVAL; } - /* Convert the usec request to a HW useable value. If they asked + /* Convert the usec request to a HW usable value. If they asked * for non-zero and it resolved to zero, bump it up */ - coal = ionic_coal_usec_to_hw(lif->ionic, coalesce->rx_coalesce_usecs); - if (!coal && coalesce->rx_coalesce_usecs) - coal = 1; - - if (coal > IONIC_INTR_CTRL_COAL_MAX) + rx_coal = ionic_coal_usec_to_hw(lif->ionic, coalesce->rx_coalesce_usecs); + if (!rx_coal && coalesce->rx_coalesce_usecs) + rx_coal = 1; + tx_coal = ionic_coal_usec_to_hw(lif->ionic, coalesce->tx_coalesce_usecs); + if (!tx_coal && coalesce->tx_coalesce_usecs) + tx_coal = 1; + + if (rx_coal > IONIC_INTR_CTRL_COAL_MAX || + tx_coal > IONIC_INTR_CTRL_COAL_MAX) return -ERANGE; - /* Save the new value */ + /* Save the new values */ lif->rx_coalesce_usecs = coalesce->rx_coalesce_usecs; - if (coal != lif->rx_coalesce_hw) { - lif->rx_coalesce_hw = coal; + if (rx_coal != lif->rx_coalesce_hw) { + lif->rx_coalesce_hw = rx_coal; if (test_bit(IONIC_LIF_F_UP, lif->state)) { for (i = 0; i < lif->nxqs; i++) { @@ -457,6 +462,23 @@ static int ionic_set_coalesce(struct net_device *netdev, } } + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + lif->tx_coalesce_usecs = coalesce->tx_coalesce_usecs; + else + lif->tx_coalesce_usecs = coalesce->rx_coalesce_usecs; + if (tx_coal != lif->tx_coalesce_hw) { + lif->tx_coalesce_hw = tx_coal; + + if (test_bit(IONIC_LIF_F_UP, lif->state)) { + for (i = 0; i < lif->nxqs; i++) { + qcq = lif->txqcqs[i].qcq; + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + qcq->intr.index, + lif->tx_coalesce_hw); + } + } + } + return 0; } @@ -510,29 +532,63 @@ static void ionic_get_channels(struct net_device *netdev, /* report maximum channels */ ch->max_combined = lif->ionic->ntxqs_per_lif; + ch->max_rx = lif->ionic->ntxqs_per_lif / 2; + ch->max_tx = lif->ionic->ntxqs_per_lif / 2; /* report current channels */ - ch->combined_count = lif->nxqs; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { + ch->rx_count = lif->nxqs; + ch->tx_count = lif->nxqs; + } else { + ch->combined_count = lif->nxqs; + } } static void ionic_set_queuecount(struct ionic_lif *lif, void *arg) { struct ethtool_channels *ch = arg; - lif->nxqs = ch->combined_count; + if (ch->combined_count) { + lif->nxqs = ch->combined_count; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { + clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; + lif->tx_coalesce_hw = lif->rx_coalesce_hw; + netdev_info(lif->netdev, "Sharing queue interrupts\n"); + } + } else { + lif->nxqs = ch->rx_count; + if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { + set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + netdev_info(lif->netdev, "Splitting queue interrupts\n"); + } + } } static int ionic_set_channels(struct net_device *netdev, struct ethtool_channels *ch) { struct ionic_lif *lif = netdev_priv(netdev); + int new_cnt; - if (!ch->combined_count || ch->other_count || - ch->rx_count || ch->tx_count) + if (ch->rx_count != ch->tx_count) { + netdev_info(netdev, "The rx and tx count must be equal\n"); return -EINVAL; + } - if (ch->combined_count == lif->nxqs) - return 0; + if (ch->combined_count && ch->rx_count) { + netdev_info(netdev, "Use either combined_count or rx/tx_count, not both\n"); + return -EINVAL; + } + + if (ch->combined_count) + new_cnt = ch->combined_count; + else + new_cnt = ch->rx_count; + + if (lif->nxqs != new_cnt) + netdev_info(netdev, "Changing queue count from %d to %d\n", + lif->nxqs, new_cnt); return ionic_reset_queues(lif, ionic_set_queuecount, ch); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 728dd6429d80..1944bf5264db 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -616,7 +616,6 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) .index = cpu_to_le32(q->index), .flags = cpu_to_le16(IONIC_QINIT_F_IRQ | IONIC_QINIT_F_SG), - .intr_index = cpu_to_le16(lif->rxqcqs[q->index].qcq->intr.index), .pid = cpu_to_le16(q->pid), .ring_size = ilog2(q->num_descs), .ring_base = cpu_to_le64(q->base_pa), @@ -624,14 +623,22 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) .sg_ring_base = cpu_to_le64(q->sg_base_pa), }, }; + unsigned int intr_index; int err; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + intr_index = qcq->intr.index; + else + intr_index = lif->rxqcqs[q->index].qcq->intr.index; + ctx.cmd.q_init.intr_index = cpu_to_le16(intr_index); + dev_dbg(dev, "txq_init.pid %d\n", ctx.cmd.q_init.pid); dev_dbg(dev, "txq_init.index %d\n", ctx.cmd.q_init.index); dev_dbg(dev, "txq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); dev_dbg(dev, "txq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); dev_dbg(dev, "txq_init.flags 0x%x\n", ctx.cmd.q_init.flags); dev_dbg(dev, "txq_init.ver %d\n", ctx.cmd.q_init.ver); + dev_dbg(dev, "txq_init.intr_index %d\n", ctx.cmd.q_init.intr_index); q->tail = q->info; q->head = q->tail; @@ -648,6 +655,10 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + netif_napi_add(lif->netdev, &qcq->napi, ionic_tx_napi, + NAPI_POLL_WEIGHT); + qcq->flags |= IONIC_QCQ_F_INITED; return 0; @@ -684,6 +695,7 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); dev_dbg(dev, "rxq_init.flags 0x%x\n", ctx.cmd.q_init.flags); dev_dbg(dev, "rxq_init.ver %d\n", ctx.cmd.q_init.ver); + dev_dbg(dev, "rxq_init.intr_index %d\n", ctx.cmd.q_init.intr_index); q->tail = q->info; q->head = q->tail; @@ -700,8 +712,12 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); - netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi, - NAPI_POLL_WEIGHT); + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi, + NAPI_POLL_WEIGHT); + else + netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi, + NAPI_POLL_WEIGHT); qcq->flags |= IONIC_QCQ_F_INITED; @@ -1537,6 +1553,8 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) sg_desc_sz = sizeof(struct ionic_txq_sg_desc); flags = IONIC_QCQ_F_TX_STATS | IONIC_QCQ_F_SG; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + flags |= IONIC_QCQ_F_INTR; for (i = 0; i < lif->nxqs; i++) { err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, lif->ntxq_descs, @@ -1547,6 +1565,11 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) if (err) goto err_out; + if (flags & IONIC_QCQ_F_INTR) + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->txqcqs[i].qcq->intr.index, + lif->tx_coalesce_hw); + lif->txqcqs[i].qcq->stats = lif->txqcqs[i].stats; ionic_debugfs_add_qcq(lif, lif->txqcqs[i].qcq); } @@ -1562,13 +1585,15 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) if (err) goto err_out; - lif->rxqcqs[i].qcq->stats = lif->rxqcqs[i].stats; - ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, lif->rxqcqs[i].qcq->intr.index, lif->rx_coalesce_hw); - ionic_link_qcq_interrupts(lif->rxqcqs[i].qcq, - lif->txqcqs[i].qcq); + + if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + ionic_link_qcq_interrupts(lif->rxqcqs[i].qcq, + lif->txqcqs[i].qcq); + + lif->rxqcqs[i].qcq->stats = lif->rxqcqs[i].stats; ionic_debugfs_add_qcq(lif, lif->rxqcqs[i].qcq); } @@ -2002,7 +2027,7 @@ int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) netif_device_detach(lif->netdev); err = ionic_stop(lif->netdev); if (err) - return err; + goto reset_out; } if (cb) @@ -2012,6 +2037,8 @@ int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) err = ionic_open(lif->netdev); netif_device_attach(lif->netdev); } + +reset_out: mutex_unlock(&lif->queue_lock); return err; @@ -2063,11 +2090,14 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->index = index; lif->ntxq_descs = IONIC_DEF_TXRX_DESC; lif->nrxq_descs = IONIC_DEF_TXRX_DESC; + lif->tx_budget = IONIC_TX_BUDGET_DEFAULT; /* Convert the default coalesce value to actual hw resolution */ lif->rx_coalesce_usecs = IONIC_ITR_COAL_USEC_DEFAULT; lif->rx_coalesce_hw = ionic_coal_usec_to_hw(lif->ionic, lif->rx_coalesce_usecs); + lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; + lif->tx_coalesce_hw = lif->rx_coalesce_hw; snprintf(lif->name, sizeof(lif->name), "lif%u", index); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index edad17d7aeeb..1ee3b14c8d50 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -13,6 +13,7 @@ #define IONIC_MAX_NUM_NAPI_CNTR (NAPI_POLL_WEIGHT + 1) #define IONIC_MAX_NUM_SG_CNTR (IONIC_TX_MAX_SG_ELEMS + 1) #define IONIC_RX_COPYBREAK_DEFAULT 256 +#define IONIC_TX_BUDGET_DEFAULT 256 struct ionic_tx_stats { u64 dma_map_err; @@ -136,6 +137,7 @@ enum ionic_lif_state_flags { IONIC_LIF_F_UP, IONIC_LIF_F_LINK_CHECK_REQUESTED, IONIC_LIF_F_FW_RESET, + IONIC_LIF_F_SPLIT_INTR, /* leave this as last */ IONIC_LIF_F_STATE_SIZE @@ -176,6 +178,7 @@ struct ionic_lif { unsigned int ntxq_descs; unsigned int nrxq_descs; u32 rx_copybreak; + u32 tx_budget; unsigned int rx_mode; u64 hw_features; bool mc_overflow; @@ -203,6 +206,8 @@ struct ionic_lif { struct dentry *dentry; u32 rx_coalesce_usecs; /* what the user asked for */ u32 rx_coalesce_hw; /* what the hw is using */ + u32 tx_coalesce_usecs; /* what the user asked for */ + u32 tx_coalesce_hw; /* what the hw is using */ struct work_struct tx_timeout_work; }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 85eb8f276a37..8107d32c2767 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -15,6 +15,10 @@ static void ionic_rx_clean(struct ionic_queue *q, struct ionic_cq_info *cq_info, void *cb_arg); +static bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info); + +static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info); + static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell, ionic_desc_cb cb_func, void *cb_arg) { @@ -249,29 +253,13 @@ static bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) return true; } -static u32 ionic_rx_walk_cq(struct ionic_cq *rxcq, u32 limit) -{ - u32 work_done = 0; - - while (ionic_rx_service(rxcq, rxcq->tail)) { - if (rxcq->tail->last) - rxcq->done_color = !rxcq->done_color; - rxcq->tail = rxcq->tail->next; - DEBUG_STATS_CQE_CNT(rxcq); - - if (++work_done >= limit) - break; - } - - return work_done; -} - void ionic_rx_flush(struct ionic_cq *cq) { struct ionic_dev *idev = &cq->lif->ionic->idev; u32 work_done; - work_done = ionic_rx_walk_cq(cq, cq->num_descs); + work_done = ionic_cq_service(cq, cq->num_descs, + ionic_rx_service, NULL, NULL); if (work_done) ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, @@ -331,9 +319,6 @@ static void ionic_rx_page_free(struct ionic_queue *q, struct page *page, __free_page(page); } -#define IONIC_RX_RING_DOORBELL_STRIDE ((1 << 5) - 1) -#define IONIC_RX_RING_HEAD_BUF_SZ 2048 - void ionic_rx_fill(struct ionic_queue *q) { struct net_device *netdev = q->lif->netdev; @@ -345,7 +330,6 @@ void ionic_rx_fill(struct ionic_queue *q) unsigned int remain_len; unsigned int seg_len; unsigned int nfrags; - bool ring_doorbell; unsigned int i, j; unsigned int len; @@ -360,9 +344,7 @@ void ionic_rx_fill(struct ionic_queue *q) page_info = &desc_info->pages[0]; if (page_info->page) { /* recycle the buffer */ - ring_doorbell = ((q->head->index + 1) & - IONIC_RX_RING_DOORBELL_STRIDE) == 0; - ionic_rxq_post(q, ring_doorbell, ionic_rx_clean, NULL); + ionic_rxq_post(q, false, ionic_rx_clean, NULL); continue; } @@ -401,10 +383,11 @@ void ionic_rx_fill(struct ionic_queue *q) page_info++; } - ring_doorbell = ((q->head->index + 1) & - IONIC_RX_RING_DOORBELL_STRIDE) == 0; - ionic_rxq_post(q, ring_doorbell, ionic_rx_clean, NULL); + ionic_rxq_post(q, false, ionic_rx_clean, NULL); } + + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head->index); } static void ionic_rx_fill_cb(void *arg) @@ -436,40 +419,117 @@ void ionic_rx_empty(struct ionic_queue *q) } } +int ionic_tx_napi(struct napi_struct *napi, int budget) +{ + struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_cq *cq = napi_to_cq(napi); + struct ionic_dev *idev; + struct ionic_lif *lif; + u32 work_done = 0; + u32 flags = 0; + + lif = cq->bound_q->lif; + idev = &lif->ionic->idev; + + work_done = ionic_cq_service(cq, budget, + ionic_tx_service, NULL, NULL); + + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(cq->bound_intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(idev->intr_ctrl, + cq->bound_intr->index, + work_done, flags); + } + + DEBUG_STATS_NAPI_POLL(qcq, work_done); + + return work_done; +} + int ionic_rx_napi(struct napi_struct *napi, int budget) { struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_cq *cq = napi_to_cq(napi); + struct ionic_dev *idev; + struct ionic_lif *lif; + u32 work_done = 0; + u32 flags = 0; + + lif = cq->bound_q->lif; + idev = &lif->ionic->idev; + + work_done = ionic_cq_service(cq, budget, + ionic_rx_service, NULL, NULL); + + if (work_done) + ionic_rx_fill(cq->bound_q); + + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(cq->bound_intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(idev->intr_ctrl, + cq->bound_intr->index, + work_done, flags); + } + + DEBUG_STATS_NAPI_POLL(qcq, work_done); + + return work_done; +} + +int ionic_txrx_napi(struct napi_struct *napi, int budget) +{ + struct ionic_qcq *qcq = napi_to_qcq(napi); struct ionic_cq *rxcq = napi_to_cq(napi); unsigned int qi = rxcq->bound_q->index; struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; + u32 rx_work_done = 0; + u32 tx_work_done = 0; u32 work_done = 0; u32 flags = 0; + bool unmask; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; txcq = &lif->txqcqs[qi].qcq->cq; - ionic_tx_flush(txcq); + tx_work_done = ionic_cq_service(txcq, lif->tx_budget, + ionic_tx_service, NULL, NULL); - work_done = ionic_rx_walk_cq(rxcq, budget); - - if (work_done) + rx_work_done = ionic_cq_service(rxcq, budget, + ionic_rx_service, NULL, NULL); + if (rx_work_done) ionic_rx_fill_cb(rxcq->bound_q); - if (work_done < budget && napi_complete_done(napi, work_done)) { + unmask = (rx_work_done < budget) && (tx_work_done < lif->tx_budget); + + if (unmask && napi_complete_done(napi, rx_work_done)) { flags |= IONIC_INTR_CRED_UNMASK; DEBUG_STATS_INTR_REARM(rxcq->bound_intr); + work_done = rx_work_done; + } else { + work_done = budget; } if (work_done || flags) { flags |= IONIC_INTR_CRED_RESET_COALESCE; ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index, - work_done, flags); + tx_work_done + rx_work_done, flags); } - DEBUG_STATS_NAPI_POLL(qcq, work_done); + DEBUG_STATS_NAPI_POLL(qcq, rx_work_done); + DEBUG_STATS_NAPI_POLL(qcq, tx_work_done); return work_done; } @@ -557,43 +617,39 @@ static void ionic_tx_clean(struct ionic_queue *q, } } -void ionic_tx_flush(struct ionic_cq *cq) +static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) { - struct ionic_txq_comp *comp = cq->tail->cq_desc; - struct ionic_dev *idev = &cq->lif->ionic->idev; + struct ionic_txq_comp *comp = cq_info->cq_desc; struct ionic_queue *q = cq->bound_q; struct ionic_desc_info *desc_info; - unsigned int work_done = 0; - - /* walk the completed cq entries */ - while (work_done < cq->num_descs && - color_match(comp->color, cq->done_color)) { - - /* clean the related q entries, there could be - * several q entries completed for each cq completion - */ - do { - desc_info = q->tail; - q->tail = desc_info->next; - ionic_tx_clean(q, desc_info, cq->tail, - desc_info->cb_arg); - desc_info->cb = NULL; - desc_info->cb_arg = NULL; - } while (desc_info->index != le16_to_cpu(comp->comp_index)); - - if (cq->tail->last) - cq->done_color = !cq->done_color; - - cq->tail = cq->tail->next; - comp = cq->tail->cq_desc; - DEBUG_STATS_CQE_CNT(cq); - - work_done++; - } + if (!color_match(comp->color, cq->done_color)) + return false; + + /* clean the related q entries, there could be + * several q entries completed for each cq completion + */ + do { + desc_info = q->tail; + q->tail = desc_info->next; + ionic_tx_clean(q, desc_info, cq->tail, desc_info->cb_arg); + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + } while (desc_info->index != le16_to_cpu(comp->comp_index)); + + return true; +} + +void ionic_tx_flush(struct ionic_cq *cq) +{ + struct ionic_dev *idev = &cq->lif->ionic->idev; + u32 work_done; + + work_done = ionic_cq_service(cq, cq->num_descs, + ionic_tx_service, NULL, NULL); if (work_done) ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, - work_done, 0); + work_done, IONIC_INTR_CRED_RESET_COALESCE); } void ionic_tx_empty(struct ionic_queue *q) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h index 71973e3c35a6..a5883be0413f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h @@ -11,6 +11,8 @@ void ionic_rx_fill(struct ionic_queue *q); void ionic_rx_empty(struct ionic_queue *q); void ionic_tx_empty(struct ionic_queue *q); int ionic_rx_napi(struct napi_struct *napi, int budget); +int ionic_tx_napi(struct napi_struct *napi, int budget); +int ionic_txrx_napi(struct napi_struct *napi, int budget); netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev); #endif /* _IONIC_TXRX_H_ */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_chain.c b/drivers/net/ethernet/qlogic/qed/qed_chain.c index f8efd36d66e0..b83d17b14e85 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_chain.c +++ b/drivers/net/ethernet/qlogic/qed/qed_chain.c @@ -268,8 +268,10 @@ static int qed_chain_alloc_pbl(struct qed_dev *cdev, struct qed_chain *chain) chain->pbl.pp_addr_tbl = addr_tbl; - if (chain->b_external_pbl) + if (chain->b_external_pbl) { + pbl_virt = chain->pbl_sp.table_virt; goto alloc_pages; + } size = array_size(page_cnt, sizeof(*pbl_virt)); if (unlikely(size == SIZE_MAX)) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 988d84564849..5be08f83e0aa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2518,11 +2518,10 @@ int qed_mcp_fill_shmem_func_info(struct qed_hwfn *p_hwfn, } DP_VERBOSE(p_hwfn, (QED_MSG_SP | NETIF_MSG_IFUP), - "Read configuration from shmem: pause_on_host %02x protocol %02x BW [%02x - %02x] MAC %02x:%02x:%02x:%02x:%02x:%02x wwn port %llx node %llx ovlan %04x wol %02x\n", + "Read configuration from shmem: pause_on_host %02x protocol %02x BW [%02x - %02x] MAC %pM wwn port %llx node %llx ovlan %04x wol %02x\n", info->pause_on_host, info->protocol, info->bandwidth_min, info->bandwidth_max, - info->mac[0], info->mac[1], info->mac[2], - info->mac[3], info->mac[4], info->mac[5], + info->mac, info->wwn_port, info->wwn_node, info->ovlan, (u8)p_hwfn->hw_info.b_wol_support); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index aa215eeeb4df..f1f75b6d0421 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -3276,14 +3276,12 @@ static void qed_iov_vf_mbx_ucast_filter(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_IOV, - "VF[%d]: opcode 0x%02x type 0x%02x [%s %s] [vport 0x%02x] MAC %02x:%02x:%02x:%02x:%02x:%02x, vlan 0x%04x\n", + "VF[%d]: opcode 0x%02x type 0x%02x [%s %s] [vport 0x%02x] MAC %pM, vlan 0x%04x\n", vf->abs_vf_id, params.opcode, params.type, params.is_rx_filter ? "RX" : "", params.is_tx_filter ? "TX" : "", params.vport_to_add_to, - params.mac[0], params.mac[1], - params.mac[2], params.mac[3], - params.mac[4], params.mac[5], params.vlan); + params.mac, params.vlan); if (!vf->vport_instance) { DP_VERBOSE(p_hwfn, @@ -5040,8 +5038,7 @@ static void qed_update_mac_for_vf_trust_change(struct qed_hwfn *hwfn, int vf_id) for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) { if (ether_addr_equal(vf->shadow_config.macs[i], vf_info->mac)) { - memset(vf->shadow_config.macs[i], 0, - ETH_ALEN); + eth_zero_addr(vf->shadow_config.macs[i]); DP_VERBOSE(hwfn, QED_MSG_IOV, "Shadow MAC %pM removed for VF 0x%02x, VF trust mode is ON\n", vf_info->mac, vf_id); @@ -5050,7 +5047,7 @@ static void qed_update_mac_for_vf_trust_change(struct qed_hwfn *hwfn, int vf_id) } ether_addr_copy(vf_info->mac, force_mac); - memset(vf_info->forced_mac, 0, ETH_ALEN); + eth_zero_addr(vf_info->forced_mac); vf->bulletin.p_virt->valid_bitmap &= ~BIT(MAC_ADDR_FORCED); qed_schedule_iov(hwfn, QED_IOV_WQ_BULLETIN_UPDATE_FLAG); @@ -5061,7 +5058,7 @@ static void qed_update_mac_for_vf_trust_change(struct qed_hwfn *hwfn, int vf_id) if (!vf_info->is_trusted_configured) { u8 empty_mac[ETH_ALEN]; - memset(empty_mac, 0, ETH_ALEN); + eth_zero_addr(empty_mac); for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) { if (ether_addr_equal(vf->shadow_config.macs[i], empty_mac)) { diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 1aaae3203f5a..140a392a81bb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -144,9 +144,7 @@ static int qede_set_vf_mac(struct net_device *ndev, int vfidx, u8 *mac) { struct qede_dev *edev = netdev_priv(ndev); - DP_VERBOSE(edev, QED_MSG_IOV, - "Setting MAC %02x:%02x:%02x:%02x:%02x:%02x to VF [%d]\n", - mac[0], mac[1], mac[2], mac[3], mac[4], mac[5], vfidx); + DP_VERBOSE(edev, QED_MSG_IOV, "Setting MAC %pM to VF [%d]\n", mac, vfidx); if (!is_valid_ether_addr(mac)) { DP_VERBOSE(edev, QED_MSG_IOV, "MAC address isn't valid\n"); @@ -2676,8 +2674,8 @@ static void qede_get_generic_tlv_data(void *dev, struct qed_generic_tlvs *data) data->feat_flags |= QED_TLV_LSO; ether_addr_copy(data->mac[0], edev->ndev->dev_addr); - memset(data->mac[1], 0, ETH_ALEN); - memset(data->mac[2], 0, ETH_ALEN); + eth_zero_addr(data->mac[1]); + eth_zero_addr(data->mac[2]); /* Copy the first two UC macs */ netif_addr_lock_bh(edev->ndev); i = 1; diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig index 81b0f7d3a025..5e37c8313725 100644 --- a/drivers/net/ethernet/sfc/Kconfig +++ b/drivers/net/ethernet/sfc/Kconfig @@ -17,7 +17,7 @@ config NET_VENDOR_SOLARFLARE if NET_VENDOR_SOLARFLARE config SFC - tristate "Solarflare SFC9000/SFC9100-family support" + tristate "Solarflare SFC9000/SFC9100/EF100-family support" depends on PCI select MDIO select CRC32 @@ -26,6 +26,9 @@ config SFC This driver supports 10/40-gigabit Ethernet cards based on the Solarflare SFC9000-family and SFC9100-family controllers. + It also supports 10/25/40/100-gigabit Ethernet cards based + on the Solarflare EF100 networking IP in Xilinx FPGAs. + To compile this driver as a module, choose M here. The module will be called sfc. config SFC_MTD diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile index 87d093da22ca..8bd01c429f91 100644 --- a/drivers/net/ethernet/sfc/Makefile +++ b/drivers/net/ethernet/sfc/Makefile @@ -4,7 +4,9 @@ sfc-y += efx.o efx_common.o efx_channels.o nic.o \ tx.o tx_common.o tx_tso.o rx.o rx_common.o \ selftest.o ethtool.o ethtool_common.o ptp.o \ mcdi.o mcdi_port.o mcdi_port_common.o \ - mcdi_functions.o mcdi_filters.o mcdi_mon.o + mcdi_functions.o mcdi_filters.o mcdi_mon.o \ + ef100.o ef100_nic.o ef100_netdev.o \ + ef100_ethtool.o ef100_rx.o ef100_tx.o sfc-$(CONFIG_SFC_MTD) += mtd.o sfc-$(CONFIG_SFC_SRIOV) += sriov.o siena_sriov.o ef10_sriov.o diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index fa7229fff2ff..4b0b2cf026a5 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -6,6 +6,7 @@ #include "net_driver.h" #include "rx_common.h" +#include "tx_common.h" #include "ef10_regs.h" #include "io.h" #include "mcdi.h" @@ -3977,6 +3978,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .tx_remove = efx_mcdi_tx_remove, .tx_write = efx_ef10_tx_write, .tx_limit_len = efx_ef10_tx_limit_len, + .tx_enqueue = __efx_enqueue_skb, .rx_push_rss_config = efx_mcdi_vf_rx_push_rss_config, .rx_pull_rss_config = efx_mcdi_rx_pull_rss_config, .rx_probe = efx_mcdi_rx_probe, @@ -3984,6 +3986,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = efx_ef10_rx_write, .rx_defer_refill = efx_ef10_rx_defer_refill, + .rx_packet = __efx_rx_packet, .ev_probe = efx_mcdi_ev_probe, .ev_init = efx_ef10_ev_init, .ev_fini = efx_mcdi_ev_fini, @@ -4038,6 +4041,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .rx_hash_key_size = 40, .check_caps = ef10_check_caps, .print_additional_fwver = efx_ef10_print_additional_fwver, + .sensor_event = efx_mcdi_sensor_event, }; const struct efx_nic_type efx_hunt_a0_nic_type = { @@ -4087,6 +4091,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .tx_remove = efx_mcdi_tx_remove, .tx_write = efx_ef10_tx_write, .tx_limit_len = efx_ef10_tx_limit_len, + .tx_enqueue = __efx_enqueue_skb, .rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config, .rx_pull_rss_config = efx_mcdi_rx_pull_rss_config, .rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config, @@ -4097,6 +4102,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = efx_ef10_rx_write, .rx_defer_refill = efx_ef10_rx_defer_refill, + .rx_packet = __efx_rx_packet, .ev_probe = efx_mcdi_ev_probe, .ev_init = efx_ef10_ev_init, .ev_fini = efx_mcdi_ev_fini, @@ -4172,4 +4178,5 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .rx_hash_key_size = 40, .check_caps = ef10_check_caps, .print_additional_fwver = efx_ef10_print_additional_fwver, + .sensor_event = efx_mcdi_sensor_event, }; diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c new file mode 100644 index 000000000000..9729983f4840 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2005-2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#include "net_driver.h" +#include <linux/module.h> +#include <linux/aer.h> +#include "efx_common.h" +#include "efx_channels.h" +#include "io.h" +#include "ef100_nic.h" +#include "ef100_netdev.h" +#include "ef100_regs.h" +#include "ef100.h" + +#define EFX_EF100_PCI_DEFAULT_BAR 2 + +/* Number of bytes at start of vendor specified extended capability that indicate + * that the capability is vendor specified. i.e. offset from value returned by + * pci_find_next_ext_capability() to beginning of vendor specified capability + * header. + */ +#define PCI_EXT_CAP_HDR_LENGTH 4 + +/* Expected size of a Xilinx continuation address table entry. */ +#define ESE_GZ_CFGBAR_CONT_CAP_MIN_LENGTH 16 + +struct ef100_func_ctl_window { + bool valid; + unsigned int bar; + u64 offset; +}; + +static int ef100_pci_walk_xilinx_table(struct efx_nic *efx, u64 offset, + struct ef100_func_ctl_window *result); + +/* Number of bytes to offset when reading bit position x with dword accessors. */ +#define ROUND_DOWN_TO_DWORD(x) (((x) & (~31)) >> 3) + +#define EXTRACT_BITS(x, lbn, width) \ + (((x) >> ((lbn) & 31)) & ((1ull << (width)) - 1)) + +static u32 _ef100_pci_get_bar_bits_with_width(struct efx_nic *efx, + int structure_start, + int lbn, int width) +{ + efx_dword_t dword; + + efx_readd(efx, &dword, structure_start + ROUND_DOWN_TO_DWORD(lbn)); + + return EXTRACT_BITS(le32_to_cpu(dword.u32[0]), lbn, width); +} + +#define ef100_pci_get_bar_bits(efx, entry_location, bitdef) \ + _ef100_pci_get_bar_bits_with_width(efx, entry_location, \ + ESF_GZ_CFGBAR_ ## bitdef ## _LBN, \ + ESF_GZ_CFGBAR_ ## bitdef ## _WIDTH) + +static int ef100_pci_parse_ef100_entry(struct efx_nic *efx, int entry_location, + struct ef100_func_ctl_window *result) +{ + u64 offset = ef100_pci_get_bar_bits(efx, entry_location, EF100_FUNC_CTL_WIN_OFF) << + ESE_GZ_EF100_FUNC_CTL_WIN_OFF_SHIFT; + u32 bar = ef100_pci_get_bar_bits(efx, entry_location, EF100_BAR); + + netif_dbg(efx, probe, efx->net_dev, + "Found EF100 function control window bar=%d offset=0x%llx\n", + bar, offset); + + if (result->valid) { + netif_err(efx, probe, efx->net_dev, + "Duplicated EF100 table entry.\n"); + return -EINVAL; + } + + if (bar == ESE_GZ_CFGBAR_EF100_BAR_NUM_EXPANSION_ROM || + bar == ESE_GZ_CFGBAR_EF100_BAR_NUM_INVALID) { + netif_err(efx, probe, efx->net_dev, + "Bad BAR value of %d in Xilinx capabilities EF100 entry.\n", + bar); + return -EINVAL; + } + + result->bar = bar; + result->offset = offset; + result->valid = true; + return 0; +} + +static bool ef100_pci_does_bar_overflow(struct efx_nic *efx, int bar, + u64 next_entry) +{ + return next_entry + ESE_GZ_CFGBAR_ENTRY_HEADER_SIZE > + pci_resource_len(efx->pci_dev, bar); +} + +/* Parse a Xilinx capabilities table entry describing a continuation to a new + * sub-table. + */ +static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_location, + struct ef100_func_ctl_window *result) +{ + unsigned int previous_bar; + efx_oword_t entry; + u64 offset; + int rc = 0; + u32 bar; + + efx_reado(efx, &entry, entry_location); + + bar = EFX_OWORD_FIELD32(entry, ESF_GZ_CFGBAR_CONT_CAP_BAR); + + offset = EFX_OWORD_FIELD64(entry, ESF_GZ_CFGBAR_CONT_CAP_OFFSET) << + ESE_GZ_CONT_CAP_OFFSET_BYTES_SHIFT; + + previous_bar = efx->mem_bar; + + if (bar == ESE_GZ_VSEC_BAR_NUM_EXPANSION_ROM || + bar == ESE_GZ_VSEC_BAR_NUM_INVALID) { + netif_err(efx, probe, efx->net_dev, + "Bad BAR value of %d in Xilinx capabilities sub-table.\n", + bar); + return -EINVAL; + } + + if (bar != previous_bar) { + efx_fini_io(efx); + + if (ef100_pci_does_bar_overflow(efx, bar, offset)) { + netif_err(efx, probe, efx->net_dev, + "Xilinx table will overrun BAR[%d] offset=0x%llx\n", + bar, offset); + return -EINVAL; + } + + /* Temporarily map new BAR. */ + rc = efx_init_io(efx, bar, + DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + pci_resource_len(efx->pci_dev, bar)); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Mapping new BAR for Xilinx table failed, rc=%d\n", rc); + return rc; + } + } + + rc = ef100_pci_walk_xilinx_table(efx, offset, result); + if (rc) + return rc; + + if (bar != previous_bar) { + efx_fini_io(efx); + + /* Put old BAR back. */ + rc = efx_init_io(efx, previous_bar, + DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + pci_resource_len(efx->pci_dev, previous_bar)); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Putting old BAR back failed, rc=%d\n", rc); + return rc; + } + } + + return 0; +} + +/* Iterate over the Xilinx capabilities table in the currently mapped BAR and + * call ef100_pci_parse_ef100_entry() on any EF100 entries and + * ef100_pci_parse_continue_entry() on any table continuations. + */ +static int ef100_pci_walk_xilinx_table(struct efx_nic *efx, u64 offset, + struct ef100_func_ctl_window *result) +{ + u64 current_entry = offset; + int rc = 0; + + while (true) { + u32 id = ef100_pci_get_bar_bits(efx, current_entry, ENTRY_FORMAT); + u32 last = ef100_pci_get_bar_bits(efx, current_entry, ENTRY_LAST); + u32 rev = ef100_pci_get_bar_bits(efx, current_entry, ENTRY_REV); + u32 entry_size; + + if (id == ESE_GZ_CFGBAR_ENTRY_LAST) + return 0; + + entry_size = ef100_pci_get_bar_bits(efx, current_entry, ENTRY_SIZE); + + netif_dbg(efx, probe, efx->net_dev, + "Seen Xilinx table entry 0x%x size 0x%x at 0x%llx in BAR[%d]\n", + id, entry_size, current_entry, efx->mem_bar); + + if (entry_size < sizeof(u32) * 2) { + netif_err(efx, probe, efx->net_dev, + "Xilinx table entry too short len=0x%x\n", entry_size); + return -EINVAL; + } + + switch (id) { + case ESE_GZ_CFGBAR_ENTRY_EF100: + if (rev != ESE_GZ_CFGBAR_ENTRY_REV_EF100 || + entry_size < ESE_GZ_CFGBAR_ENTRY_SIZE_EF100) { + netif_err(efx, probe, efx->net_dev, + "Bad length or rev for EF100 entry in Xilinx capabilities table. entry_size=%d rev=%d.\n", + entry_size, rev); + return -EINVAL; + } + + rc = ef100_pci_parse_ef100_entry(efx, current_entry, + result); + if (rc) + return rc; + break; + case ESE_GZ_CFGBAR_ENTRY_CONT_CAP_ADDR: + if (rev != 0 || entry_size < ESE_GZ_CFGBAR_CONT_CAP_MIN_LENGTH) { + netif_err(efx, probe, efx->net_dev, + "Bad length or rev for continue entry in Xilinx capabilities table. entry_size=%d rev=%d.\n", + entry_size, rev); + return -EINVAL; + } + + rc = ef100_pci_parse_continue_entry(efx, current_entry, result); + if (rc) + return rc; + break; + default: + /* Ignore unknown table entries. */ + break; + } + + if (last) + return 0; + + current_entry += entry_size; + + if (ef100_pci_does_bar_overflow(efx, efx->mem_bar, current_entry)) { + netif_err(efx, probe, efx->net_dev, + "Xilinx table overrun at position=0x%llx.\n", + current_entry); + return -EINVAL; + } + } +} + +static int _ef100_pci_get_config_bits_with_width(struct efx_nic *efx, + int structure_start, int lbn, + int width, u32 *result) +{ + int rc, pos = structure_start + ROUND_DOWN_TO_DWORD(lbn); + u32 temp; + + rc = pci_read_config_dword(efx->pci_dev, pos, &temp); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read PCI config dword at %d\n", + pos); + return rc; + } + + *result = EXTRACT_BITS(temp, lbn, width); + + return 0; +} + +#define ef100_pci_get_config_bits(efx, entry_location, bitdef, result) \ + _ef100_pci_get_config_bits_with_width(efx, entry_location, \ + ESF_GZ_VSEC_ ## bitdef ## _LBN, \ + ESF_GZ_VSEC_ ## bitdef ## _WIDTH, result) + +/* Call ef100_pci_walk_xilinx_table() for the Xilinx capabilities table pointed + * to by this PCI_EXT_CAP_ID_VNDR. + */ +static int ef100_pci_parse_xilinx_cap(struct efx_nic *efx, int vndr_cap, + bool has_offset_hi, + struct ef100_func_ctl_window *result) +{ + u32 offset_high = 0; + u32 offset_lo = 0; + u64 offset = 0; + u32 bar = 0; + int rc = 0; + + rc = ef100_pci_get_config_bits(efx, vndr_cap, TBL_BAR, &bar); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read ESF_GZ_VSEC_TBL_BAR, rc=%d\n", + rc); + return rc; + } + + if (bar == ESE_GZ_CFGBAR_CONT_CAP_BAR_NUM_EXPANSION_ROM || + bar == ESE_GZ_CFGBAR_CONT_CAP_BAR_NUM_INVALID) { + netif_err(efx, probe, efx->net_dev, + "Bad BAR value of %d in Xilinx capabilities sub-table.\n", + bar); + return -EINVAL; + } + + rc = ef100_pci_get_config_bits(efx, vndr_cap, TBL_OFF_LO, &offset_lo); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read ESF_GZ_VSEC_TBL_OFF_LO, rc=%d\n", + rc); + return rc; + } + + /* Get optional extension to 64bit offset. */ + if (has_offset_hi) { + rc = ef100_pci_get_config_bits(efx, vndr_cap, TBL_OFF_HI, &offset_high); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read ESF_GZ_VSEC_TBL_OFF_HI, rc=%d\n", + rc); + return rc; + } + } + + offset = (((u64)offset_lo) << ESE_GZ_VSEC_TBL_OFF_LO_BYTES_SHIFT) | + (((u64)offset_high) << ESE_GZ_VSEC_TBL_OFF_HI_BYTES_SHIFT); + + if (offset > pci_resource_len(efx->pci_dev, bar) - sizeof(u32) * 2) { + netif_err(efx, probe, efx->net_dev, + "Xilinx table will overrun BAR[%d] offset=0x%llx\n", + bar, offset); + return -EINVAL; + } + + /* Temporarily map BAR. */ + rc = efx_init_io(efx, bar, + DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + pci_resource_len(efx->pci_dev, bar)); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "efx_init_io failed, rc=%d\n", rc); + return rc; + } + + rc = ef100_pci_walk_xilinx_table(efx, offset, result); + + /* Unmap temporarily mapped BAR. */ + efx_fini_io(efx); + return rc; +} + +/* Call ef100_pci_parse_ef100_entry() for each Xilinx PCI_EXT_CAP_ID_VNDR + * capability. + */ +static int ef100_pci_find_func_ctrl_window(struct efx_nic *efx, + struct ef100_func_ctl_window *result) +{ + int num_xilinx_caps = 0; + int cap = 0; + + result->valid = false; + + while ((cap = pci_find_next_ext_capability(efx->pci_dev, cap, PCI_EXT_CAP_ID_VNDR)) != 0) { + int vndr_cap = cap + PCI_EXT_CAP_HDR_LENGTH; + u32 vsec_ver = 0; + u32 vsec_len = 0; + u32 vsec_id = 0; + int rc = 0; + + num_xilinx_caps++; + + rc = ef100_pci_get_config_bits(efx, vndr_cap, ID, &vsec_id); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read ESF_GZ_VSEC_ID, rc=%d\n", + rc); + return rc; + } + + rc = ef100_pci_get_config_bits(efx, vndr_cap, VER, &vsec_ver); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read ESF_GZ_VSEC_VER, rc=%d\n", + rc); + return rc; + } + + /* Get length of whole capability - i.e. starting at cap */ + rc = ef100_pci_get_config_bits(efx, vndr_cap, LEN, &vsec_len); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to read ESF_GZ_VSEC_LEN, rc=%d\n", + rc); + return rc; + } + + if (vsec_id == ESE_GZ_XILINX_VSEC_ID && + vsec_ver == ESE_GZ_VSEC_VER_XIL_CFGBAR && + vsec_len >= ESE_GZ_VSEC_LEN_MIN) { + bool has_offset_hi = (vsec_len >= ESE_GZ_VSEC_LEN_HIGH_OFFT); + + rc = ef100_pci_parse_xilinx_cap(efx, vndr_cap, + has_offset_hi, result); + if (rc) + return rc; + } + } + + if (num_xilinx_caps && !result->valid) { + netif_err(efx, probe, efx->net_dev, + "Seen %d Xilinx tables, but no EF100 entry.\n", + num_xilinx_caps); + return -EINVAL; + } + + return 0; +} + +/* Final NIC shutdown + * This is called only at module unload (or hotplug removal). A PF can call + * this on its VFs to ensure they are unbound first. + */ +static void ef100_pci_remove(struct pci_dev *pci_dev) +{ + struct efx_nic *efx; + + efx = pci_get_drvdata(pci_dev); + if (!efx) + return; + + rtnl_lock(); + dev_close(efx->net_dev); + rtnl_unlock(); + + /* Unregistering our netdev notifier triggers unbinding of TC indirect + * blocks, so we have to do it before PCI removal. + */ + unregister_netdevice_notifier(&efx->netdev_notifier); + ef100_remove(efx); + efx_fini_io(efx); + netif_dbg(efx, drv, efx->net_dev, "shutdown successful\n"); + + pci_set_drvdata(pci_dev, NULL); + efx_fini_struct(efx); + free_netdev(efx->net_dev); + + pci_disable_pcie_error_reporting(pci_dev); +}; + +static int ef100_pci_probe(struct pci_dev *pci_dev, + const struct pci_device_id *entry) +{ + struct ef100_func_ctl_window fcw = { 0 }; + struct net_device *net_dev; + struct efx_nic *efx; + int rc; + + /* Allocate and initialise a struct net_device and struct efx_nic */ + net_dev = alloc_etherdev_mq(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES); + if (!net_dev) + return -ENOMEM; + efx = netdev_priv(net_dev); + efx->type = (const struct efx_nic_type *)entry->driver_data; + + pci_set_drvdata(pci_dev, efx); + SET_NETDEV_DEV(net_dev, &pci_dev->dev); + rc = efx_init_struct(efx, pci_dev, net_dev); + if (rc) + goto fail; + + efx->vi_stride = EF100_DEFAULT_VI_STRIDE; + netif_info(efx, probe, efx->net_dev, + "Solarflare EF100 NIC detected\n"); + + rc = ef100_pci_find_func_ctrl_window(efx, &fcw); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Error looking for ef100 function control window, rc=%d\n", + rc); + goto fail; + } + + if (!fcw.valid) { + /* Extended capability not found - use defaults. */ + fcw.bar = EFX_EF100_PCI_DEFAULT_BAR; + fcw.offset = 0; + fcw.valid = true; + } + + if (fcw.offset > pci_resource_len(efx->pci_dev, fcw.bar) - ESE_GZ_FCW_LEN) { + netif_err(efx, probe, efx->net_dev, + "Func control window overruns BAR\n"); + goto fail; + } + + /* Set up basic I/O (BAR mappings etc) */ + rc = efx_init_io(efx, fcw.bar, + DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + pci_resource_len(efx->pci_dev, fcw.bar)); + if (rc) + goto fail; + + efx->reg_base = fcw.offset; + + efx->netdev_notifier.notifier_call = ef100_netdev_event; + rc = register_netdevice_notifier(&efx->netdev_notifier); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Failed to register netdevice notifier, rc=%d\n", rc); + goto fail; + } + + rc = efx->type->probe(efx); + if (rc) + goto fail; + + netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n"); + + return 0; + +fail: + ef100_pci_remove(pci_dev); + return rc; +} + +/* PCI device ID table */ +static const struct pci_device_id ef100_pci_table[] = { + {PCI_DEVICE(PCI_VENDOR_ID_XILINX, 0x0100), /* Riverhead PF */ + .driver_data = (unsigned long) &ef100_pf_nic_type }, + {PCI_DEVICE(PCI_VENDOR_ID_XILINX, 0x1100), /* Riverhead VF */ + .driver_data = (unsigned long) &ef100_vf_nic_type }, + {0} /* end of list */ +}; + +struct pci_driver ef100_pci_driver = { + .name = "sfc_ef100", + .id_table = ef100_pci_table, + .probe = ef100_pci_probe, + .remove = ef100_pci_remove, + .err_handler = &efx_err_handlers, +}; + +MODULE_DEVICE_TABLE(pci, ef100_pci_table); diff --git a/drivers/net/ethernet/sfc/ef100.h b/drivers/net/ethernet/sfc/ef100.h new file mode 100644 index 000000000000..a63f0ff6641b --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +extern struct pci_driver ef100_pci_driver; diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c new file mode 100644 index 000000000000..729c425d0f78 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ +#include <linux/module.h> +#include <linux/netdevice.h> +#include "net_driver.h" +#include "efx.h" +#include "mcdi_port_common.h" +#include "ethtool_common.h" +#include "ef100_ethtool.h" +#include "mcdi_functions.h" + +/* Ethtool options available + */ +const struct ethtool_ops ef100_ethtool_ops = { + .get_drvinfo = efx_ethtool_get_drvinfo, +}; diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.h b/drivers/net/ethernet/sfc/ef100_ethtool.h new file mode 100644 index 000000000000..6efda72dfc6c --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_ethtool.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +extern const struct ethtool_ops ef100_ethtool_ops; diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c new file mode 100644 index 000000000000..63c311ba28b9 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ +#include "net_driver.h" +#include "mcdi_port_common.h" +#include "mcdi_functions.h" +#include "efx_common.h" +#include "efx_channels.h" +#include "tx_common.h" +#include "ef100_netdev.h" +#include "ef100_ethtool.h" +#include "nic_common.h" +#include "ef100_nic.h" +#include "ef100_tx.h" +#include "ef100_regs.h" +#include "mcdi_filters.h" +#include "rx_common.h" + +static void ef100_update_name(struct efx_nic *efx) +{ + strcpy(efx->name, efx->net_dev->name); +} + +static int ef100_alloc_vis(struct efx_nic *efx, unsigned int *allocated_vis) +{ + /* EF100 uses a single TXQ per channel, as all checksum offloading + * is configured in the TX descriptor, and there is no TX Pacer for + * HIGHPRI queues. + */ + unsigned int tx_vis = efx->n_tx_channels + efx->n_extra_tx_channels; + unsigned int rx_vis = efx->n_rx_channels; + unsigned int min_vis, max_vis; + + EFX_WARN_ON_PARANOID(efx->tx_queues_per_channel != 1); + + tx_vis += efx->n_xdp_channels * efx->xdp_tx_per_channel; + + max_vis = max(rx_vis, tx_vis); + /* Currently don't handle resource starvation and only accept + * our maximum needs and no less. + */ + min_vis = max_vis; + + return efx_mcdi_alloc_vis(efx, min_vis, max_vis, + NULL, allocated_vis); +} + +static int ef100_remap_bar(struct efx_nic *efx, int max_vis) +{ + unsigned int uc_mem_map_size; + void __iomem *membase; + + efx->max_vis = max_vis; + uc_mem_map_size = PAGE_ALIGN(max_vis * efx->vi_stride); + + /* Extend the original UC mapping of the memory BAR */ + membase = ioremap(efx->membase_phys, uc_mem_map_size); + if (!membase) { + netif_err(efx, probe, efx->net_dev, + "could not extend memory BAR to %x\n", + uc_mem_map_size); + return -ENOMEM; + } + iounmap(efx->membase); + efx->membase = membase; + return 0; +} + +/* Context: process, rtnl_lock() held. + * Note that the kernel will ignore our return code; this method + * should really be a void. + */ +static int ef100_net_stop(struct net_device *net_dev) +{ + struct efx_nic *efx = netdev_priv(net_dev); + + netif_dbg(efx, ifdown, efx->net_dev, "closing on CPU %d\n", + raw_smp_processor_id()); + + netif_stop_queue(net_dev); + efx_stop_all(efx); + efx_mcdi_mac_fini_stats(efx); + efx_disable_interrupts(efx); + efx_clear_interrupt_affinity(efx); + efx_nic_fini_interrupt(efx); + efx_remove_filters(efx); + efx_fini_napi(efx); + efx_remove_channels(efx); + efx_mcdi_free_vis(efx); + efx_remove_interrupts(efx); + + return 0; +} + +/* Context: process, rtnl_lock() held. */ +static int ef100_net_open(struct net_device *net_dev) +{ + struct efx_nic *efx = netdev_priv(net_dev); + unsigned int allocated_vis; + int rc; + + ef100_update_name(efx); + netif_dbg(efx, ifup, net_dev, "opening device on CPU %d\n", + raw_smp_processor_id()); + + rc = efx_check_disabled(efx); + if (rc) + goto fail; + + rc = efx_probe_interrupts(efx); + if (rc) + goto fail; + + rc = efx_set_channels(efx); + if (rc) + goto fail; + + rc = efx_mcdi_free_vis(efx); + if (rc) + goto fail; + + rc = ef100_alloc_vis(efx, &allocated_vis); + if (rc) + goto fail; + + rc = efx_probe_channels(efx); + if (rc) + return rc; + + rc = ef100_remap_bar(efx, allocated_vis); + if (rc) + goto fail; + + efx_init_napi(efx); + + rc = efx_probe_filters(efx); + if (rc) + goto fail; + + rc = efx_nic_init_interrupt(efx); + if (rc) + goto fail; + efx_set_interrupt_affinity(efx); + + rc = efx_enable_interrupts(efx); + if (rc) + goto fail; + + /* in case the MC rebooted while we were stopped, consume the change + * to the warm reboot count + */ + (void) efx_mcdi_poll_reboot(efx); + + rc = efx_mcdi_mac_init_stats(efx); + if (rc) + goto fail; + + efx_start_all(efx); + + /* Link state detection is normally event-driven; we have + * to poll now because we could have missed a change + */ + mutex_lock(&efx->mac_lock); + if (efx_mcdi_phy_poll(efx)) + efx_link_status_changed(efx); + mutex_unlock(&efx->mac_lock); + + return 0; + +fail: + ef100_net_stop(net_dev); + return rc; +} + +/* Initiate a packet transmission. We use one channel per CPU + * (sharing when we have more CPUs than channels). + * + * Context: non-blocking. + * Note that returning anything other than NETDEV_TX_OK will cause the + * OS to free the skb. + */ +static netdev_tx_t ef100_hard_start_xmit(struct sk_buff *skb, + struct net_device *net_dev) +{ + struct efx_nic *efx = netdev_priv(net_dev); + struct efx_tx_queue *tx_queue; + struct efx_channel *channel; + int rc; + + channel = efx_get_tx_channel(efx, skb_get_queue_mapping(skb)); + netif_vdbg(efx, tx_queued, efx->net_dev, + "%s len %d data %d channel %d\n", __func__, + skb->len, skb->data_len, channel->channel); + if (!efx->n_channels || !efx->n_tx_channels || !channel) { + netif_stop_queue(net_dev); + goto err; + } + + tx_queue = &channel->tx_queue[0]; + rc = ef100_enqueue_skb(tx_queue, skb); + if (rc == 0) + return NETDEV_TX_OK; + +err: + net_dev->stats.tx_dropped++; + return NETDEV_TX_OK; +} + +static const struct net_device_ops ef100_netdev_ops = { + .ndo_open = ef100_net_open, + .ndo_stop = ef100_net_stop, + .ndo_start_xmit = ef100_hard_start_xmit, + .ndo_get_stats64 = efx_net_stats, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_rx_mode = efx_set_rx_mode, /* Lookout */ + .ndo_get_phys_port_id = efx_get_phys_port_id, + .ndo_get_phys_port_name = efx_get_phys_port_name, +#ifdef CONFIG_RFS_ACCEL + .ndo_rx_flow_steer = efx_filter_rfs, +#endif +}; + +/* Netdev registration + */ +int ef100_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct efx_nic *efx = container_of(this, struct efx_nic, netdev_notifier); + struct net_device *net_dev = netdev_notifier_info_to_dev(ptr); + + if (netdev_priv(net_dev) == efx && event == NETDEV_CHANGENAME) + ef100_update_name(efx); + + return NOTIFY_DONE; +} + +int ef100_register_netdev(struct efx_nic *efx) +{ + struct net_device *net_dev = efx->net_dev; + int rc; + + net_dev->watchdog_timeo = 5 * HZ; + net_dev->irq = efx->pci_dev->irq; + net_dev->netdev_ops = &ef100_netdev_ops; + net_dev->min_mtu = EFX_MIN_MTU; + net_dev->max_mtu = EFX_MAX_MTU; + net_dev->ethtool_ops = &ef100_ethtool_ops; + + rtnl_lock(); + + rc = dev_alloc_name(net_dev, net_dev->name); + if (rc < 0) + goto fail_locked; + ef100_update_name(efx); + + rc = register_netdevice(net_dev); + if (rc) + goto fail_locked; + + /* Always start with carrier off; PHY events will detect the link */ + netif_carrier_off(net_dev); + + efx->state = STATE_READY; + rtnl_unlock(); + efx_init_mcdi_logging(efx); + + return 0; + +fail_locked: + rtnl_unlock(); + netif_err(efx, drv, efx->net_dev, "could not register net dev\n"); + return rc; +} + +void ef100_unregister_netdev(struct efx_nic *efx) +{ + if (efx_dev_registered(efx)) { + efx_fini_mcdi_logging(efx); + efx->state = STATE_UNINIT; + unregister_netdev(efx->net_dev); + } +} diff --git a/drivers/net/ethernet/sfc/ef100_netdev.h b/drivers/net/ethernet/sfc/ef100_netdev.h new file mode 100644 index 000000000000..d40abb7cc086 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_netdev.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#include <linux/netdevice.h> + +int ef100_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr); +int ef100_register_netdev(struct efx_nic *efx); +void ef100_unregister_netdev(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c new file mode 100644 index 000000000000..8a2126fec078 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -0,0 +1,1276 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#include "ef100_nic.h" +#include "efx_common.h" +#include "efx_channels.h" +#include "io.h" +#include "selftest.h" +#include "ef100_regs.h" +#include "mcdi.h" +#include "mcdi_pcol.h" +#include "mcdi_port_common.h" +#include "mcdi_functions.h" +#include "mcdi_filters.h" +#include "ef100_rx.h" +#include "ef100_tx.h" +#include "ef100_netdev.h" + +#define EF100_MAX_VIS 4096 +#define EF100_NUM_MCDI_BUFFERS 1 +#define MCDI_BUF_LEN (8 + MCDI_CTL_SDU_LEN_MAX) + +#define EF100_RESET_PORT ((ETH_RESET_MAC | ETH_RESET_PHY) << ETH_RESET_SHARED_SHIFT) + +/* MCDI + */ +static u8 *ef100_mcdi_buf(struct efx_nic *efx, u8 bufid, dma_addr_t *dma_addr) +{ + struct ef100_nic_data *nic_data = efx->nic_data; + + if (dma_addr) + *dma_addr = nic_data->mcdi_buf.dma_addr + + bufid * ALIGN(MCDI_BUF_LEN, 256); + return nic_data->mcdi_buf.addr + bufid * ALIGN(MCDI_BUF_LEN, 256); +} + +static int ef100_get_warm_boot_count(struct efx_nic *efx) +{ + efx_dword_t reg; + + efx_readd(efx, ®, efx_reg(efx, ER_GZ_MC_SFT_STATUS)); + + if (EFX_DWORD_FIELD(reg, EFX_DWORD_0) == 0xffffffff) { + netif_err(efx, hw, efx->net_dev, "Hardware unavailable\n"); + efx->state = STATE_DISABLED; + return -ENETDOWN; + } else { + return EFX_DWORD_FIELD(reg, EFX_WORD_1) == 0xb007 ? + EFX_DWORD_FIELD(reg, EFX_WORD_0) : -EIO; + } +} + +static void ef100_mcdi_request(struct efx_nic *efx, + const efx_dword_t *hdr, size_t hdr_len, + const efx_dword_t *sdu, size_t sdu_len) +{ + dma_addr_t dma_addr; + u8 *pdu = ef100_mcdi_buf(efx, 0, &dma_addr); + + memcpy(pdu, hdr, hdr_len); + memcpy(pdu + hdr_len, sdu, sdu_len); + wmb(); + + /* The hardware provides 'low' and 'high' (doorbell) registers + * for passing the 64-bit address of an MCDI request to + * firmware. However the dwords are swapped by firmware. The + * least significant bits of the doorbell are then 0 for all + * MCDI requests due to alignment. + */ + _efx_writed(efx, cpu_to_le32((u64)dma_addr >> 32), efx_reg(efx, ER_GZ_MC_DB_LWRD)); + _efx_writed(efx, cpu_to_le32((u32)dma_addr), efx_reg(efx, ER_GZ_MC_DB_HWRD)); +} + +static bool ef100_mcdi_poll_response(struct efx_nic *efx) +{ + const efx_dword_t hdr = + *(const efx_dword_t *)(ef100_mcdi_buf(efx, 0, NULL)); + + rmb(); + return EFX_DWORD_FIELD(hdr, MCDI_HEADER_RESPONSE); +} + +static void ef100_mcdi_read_response(struct efx_nic *efx, + efx_dword_t *outbuf, size_t offset, + size_t outlen) +{ + const u8 *pdu = ef100_mcdi_buf(efx, 0, NULL); + + memcpy(outbuf, pdu + offset, outlen); +} + +static int ef100_mcdi_poll_reboot(struct efx_nic *efx) +{ + struct ef100_nic_data *nic_data = efx->nic_data; + int rc; + + rc = ef100_get_warm_boot_count(efx); + if (rc < 0) { + /* The firmware is presumably in the process of + * rebooting. However, we are supposed to report each + * reboot just once, so we must only do that once we + * can read and store the updated warm boot count. + */ + return 0; + } + + if (rc == nic_data->warm_boot_count) + return 0; + + nic_data->warm_boot_count = rc; + + return -EIO; +} + +static void ef100_mcdi_reboot_detected(struct efx_nic *efx) +{ +} + +/* MCDI calls + */ +static int ef100_get_mac_address(struct efx_nic *efx, u8 *mac_address) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_MAC_ADDRESSES_OUT_LEN); + size_t outlen; + int rc; + + BUILD_BUG_ON(MC_CMD_GET_MAC_ADDRESSES_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_MAC_ADDRESSES, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + return rc; + if (outlen < MC_CMD_GET_MAC_ADDRESSES_OUT_LEN) + return -EIO; + + ether_addr_copy(mac_address, + MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE)); + return 0; +} + +static int efx_ef100_init_datapath_caps(struct efx_nic *efx) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V7_OUT_LEN); + struct ef100_nic_data *nic_data = efx->nic_data; + u8 vi_window_mode; + size_t outlen; + int rc; + + BUILD_BUG_ON(MC_CMD_GET_CAPABILITIES_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_CAPABILITIES, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + return rc; + if (outlen < MC_CMD_GET_CAPABILITIES_V4_OUT_LEN) { + netif_err(efx, drv, efx->net_dev, + "unable to read datapath firmware capabilities\n"); + return -EIO; + } + + nic_data->datapath_caps = MCDI_DWORD(outbuf, + GET_CAPABILITIES_OUT_FLAGS1); + nic_data->datapath_caps2 = MCDI_DWORD(outbuf, + GET_CAPABILITIES_V2_OUT_FLAGS2); + if (outlen < MC_CMD_GET_CAPABILITIES_V7_OUT_LEN) + nic_data->datapath_caps3 = 0; + else + nic_data->datapath_caps3 = MCDI_DWORD(outbuf, + GET_CAPABILITIES_V7_OUT_FLAGS3); + + vi_window_mode = MCDI_BYTE(outbuf, + GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE); + rc = efx_mcdi_window_mode_to_stride(efx, vi_window_mode); + if (rc) + return rc; + + if (efx_ef100_has_cap(nic_data->datapath_caps2, TX_TSO_V3)) + efx->net_dev->features |= NETIF_F_TSO | NETIF_F_TSO6; + efx->num_mac_stats = MCDI_WORD(outbuf, + GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS); + netif_dbg(efx, probe, efx->net_dev, + "firmware reports num_mac_stats = %u\n", + efx->num_mac_stats); + return 0; +} + +/* Event handling + */ +static int ef100_ev_probe(struct efx_channel *channel) +{ + /* Allocate an extra descriptor for the QMDA status completion entry */ + return efx_nic_alloc_buffer(channel->efx, &channel->eventq.buf, + (channel->eventq_mask + 2) * + sizeof(efx_qword_t), + GFP_KERNEL); +} + +static int ef100_ev_init(struct efx_channel *channel) +{ + struct ef100_nic_data *nic_data = channel->efx->nic_data; + + /* initial phase is 0 */ + clear_bit(channel->channel, nic_data->evq_phases); + + return efx_mcdi_ev_init(channel, false, false); +} + +static void ef100_ev_read_ack(struct efx_channel *channel) +{ + efx_dword_t evq_prime; + + EFX_POPULATE_DWORD_2(evq_prime, + ERF_GZ_EVQ_ID, channel->channel, + ERF_GZ_IDX, channel->eventq_read_ptr & + channel->eventq_mask); + + efx_writed(channel->efx, &evq_prime, + efx_reg(channel->efx, ER_GZ_EVQ_INT_PRIME)); +} + +static int ef100_ev_process(struct efx_channel *channel, int quota) +{ + struct efx_nic *efx = channel->efx; + struct ef100_nic_data *nic_data; + bool evq_phase, old_evq_phase; + unsigned int read_ptr; + efx_qword_t *p_event; + int spent = 0; + bool ev_phase; + int ev_type; + + if (unlikely(!channel->enabled)) + return 0; + + nic_data = efx->nic_data; + evq_phase = test_bit(channel->channel, nic_data->evq_phases); + old_evq_phase = evq_phase; + read_ptr = channel->eventq_read_ptr; + BUILD_BUG_ON(ESF_GZ_EV_RXPKTS_PHASE_LBN != ESF_GZ_EV_TXCMPL_PHASE_LBN); + + while (spent < quota) { + p_event = efx_event(channel, read_ptr); + + ev_phase = !!EFX_QWORD_FIELD(*p_event, ESF_GZ_EV_RXPKTS_PHASE); + if (ev_phase != evq_phase) + break; + + netif_vdbg(efx, drv, efx->net_dev, + "processing event on %d " EFX_QWORD_FMT "\n", + channel->channel, EFX_QWORD_VAL(*p_event)); + + ev_type = EFX_QWORD_FIELD(*p_event, ESF_GZ_E_TYPE); + + switch (ev_type) { + case ESE_GZ_EF100_EV_RX_PKTS: + efx_ef100_ev_rx(channel, p_event); + ++spent; + break; + case ESE_GZ_EF100_EV_MCDI: + efx_mcdi_process_event(channel, p_event); + break; + case ESE_GZ_EF100_EV_TX_COMPLETION: + ef100_ev_tx(channel, p_event); + break; + case ESE_GZ_EF100_EV_DRIVER: + netif_info(efx, drv, efx->net_dev, + "Driver initiated event " EFX_QWORD_FMT "\n", + EFX_QWORD_VAL(*p_event)); + break; + default: + netif_info(efx, drv, efx->net_dev, + "Unhandled event " EFX_QWORD_FMT "\n", + EFX_QWORD_VAL(*p_event)); + } + + ++read_ptr; + if ((read_ptr & channel->eventq_mask) == 0) + evq_phase = !evq_phase; + } + + channel->eventq_read_ptr = read_ptr; + if (evq_phase != old_evq_phase) + change_bit(channel->channel, nic_data->evq_phases); + + return spent; +} + +static irqreturn_t ef100_msi_interrupt(int irq, void *dev_id) +{ + struct efx_msi_context *context = dev_id; + struct efx_nic *efx = context->efx; + + netif_vdbg(efx, intr, efx->net_dev, + "IRQ %d on CPU %d\n", irq, raw_smp_processor_id()); + + if (likely(READ_ONCE(efx->irq_soft_enabled))) { + /* Note test interrupts */ + if (context->index == efx->irq_level) + efx->last_irq_cpu = raw_smp_processor_id(); + + /* Schedule processing of the channel */ + efx_schedule_channel_irq(efx->channel[context->index]); + } + + return IRQ_HANDLED; +} + +static int ef100_phy_probe(struct efx_nic *efx) +{ + struct efx_mcdi_phy_data *phy_data; + int rc; + + /* Probe for the PHY */ + efx->phy_data = kzalloc(sizeof(struct efx_mcdi_phy_data), GFP_KERNEL); + if (!efx->phy_data) + return -ENOMEM; + + rc = efx_mcdi_get_phy_cfg(efx, efx->phy_data); + if (rc) + return rc; + + /* Populate driver and ethtool settings */ + phy_data = efx->phy_data; + mcdi_to_ethtool_linkset(phy_data->media, phy_data->supported_cap, + efx->link_advertising); + efx->fec_config = mcdi_fec_caps_to_ethtool(phy_data->supported_cap, + false); + + /* Default to Autonegotiated flow control if the PHY supports it */ + efx->wanted_fc = EFX_FC_RX | EFX_FC_TX; + if (phy_data->supported_cap & (1 << MC_CMD_PHY_CAP_AN_LBN)) + efx->wanted_fc |= EFX_FC_AUTO; + efx_link_set_wanted_fc(efx, efx->wanted_fc); + + /* Push settings to the PHY. Failure is not fatal, the user can try to + * fix it using ethtool. + */ + rc = efx_mcdi_port_reconfigure(efx); + if (rc && rc != -EPERM) + netif_warn(efx, drv, efx->net_dev, + "could not initialise PHY settings\n"); + + return 0; +} + +static int ef100_filter_table_probe(struct efx_nic *efx) +{ + return efx_mcdi_filter_table_probe(efx, true); +} + +static int ef100_filter_table_up(struct efx_nic *efx) +{ + int rc; + + rc = efx_mcdi_filter_add_vlan(efx, EFX_FILTER_VID_UNSPEC); + if (rc) { + efx_mcdi_filter_table_down(efx); + return rc; + } + + rc = efx_mcdi_filter_add_vlan(efx, 0); + if (rc) { + efx_mcdi_filter_del_vlan(efx, EFX_FILTER_VID_UNSPEC); + efx_mcdi_filter_table_down(efx); + } + + return rc; +} + +static void ef100_filter_table_down(struct efx_nic *efx) +{ + efx_mcdi_filter_del_vlan(efx, 0); + efx_mcdi_filter_del_vlan(efx, EFX_FILTER_VID_UNSPEC); + efx_mcdi_filter_table_down(efx); +} + +/* Other + */ +static int ef100_reconfigure_mac(struct efx_nic *efx, bool mtu_only) +{ + WARN_ON(!mutex_is_locked(&efx->mac_lock)); + + efx_mcdi_filter_sync_rx_mode(efx); + + if (mtu_only && efx_has_cap(efx, SET_MAC_ENHANCED)) + return efx_mcdi_set_mtu(efx); + return efx_mcdi_set_mac(efx); +} + +static enum reset_type ef100_map_reset_reason(enum reset_type reason) +{ + if (reason == RESET_TYPE_TX_WATCHDOG) + return reason; + return RESET_TYPE_DISABLE; +} + +static int ef100_map_reset_flags(u32 *flags) +{ + /* Only perform a RESET_TYPE_ALL because we don't support MC_REBOOTs */ + if ((*flags & EF100_RESET_PORT)) { + *flags &= ~EF100_RESET_PORT; + return RESET_TYPE_ALL; + } + if (*flags & ETH_RESET_MGMT) { + *flags &= ~ETH_RESET_MGMT; + return RESET_TYPE_DISABLE; + } + + return -EINVAL; +} + +static int ef100_reset(struct efx_nic *efx, enum reset_type reset_type) +{ + int rc; + + dev_close(efx->net_dev); + + if (reset_type == RESET_TYPE_TX_WATCHDOG) { + netif_device_attach(efx->net_dev); + __clear_bit(reset_type, &efx->reset_pending); + rc = dev_open(efx->net_dev, NULL); + } else if (reset_type == RESET_TYPE_ALL) { + /* A RESET_TYPE_ALL will cause filters to be removed, so we remove filters + * and reprobe after reset to avoid removing filters twice + */ + down_read(&efx->filter_sem); + ef100_filter_table_down(efx); + up_read(&efx->filter_sem); + rc = efx_mcdi_reset(efx, reset_type); + if (rc) + return rc; + + netif_device_attach(efx->net_dev); + + down_read(&efx->filter_sem); + rc = ef100_filter_table_up(efx); + up_read(&efx->filter_sem); + if (rc) + return rc; + + rc = dev_open(efx->net_dev, NULL); + } else { + rc = 1; /* Leave the device closed */ + } + return rc; +} + +static void ef100_common_stat_mask(unsigned long *mask) +{ + __set_bit(EF100_STAT_port_rx_packets, mask); + __set_bit(EF100_STAT_port_tx_packets, mask); + __set_bit(EF100_STAT_port_rx_bytes, mask); + __set_bit(EF100_STAT_port_tx_bytes, mask); + __set_bit(EF100_STAT_port_rx_multicast, mask); + __set_bit(EF100_STAT_port_rx_bad, mask); + __set_bit(EF100_STAT_port_rx_align_error, mask); + __set_bit(EF100_STAT_port_rx_overflow, mask); +} + +static void ef100_ethtool_stat_mask(unsigned long *mask) +{ + __set_bit(EF100_STAT_port_tx_pause, mask); + __set_bit(EF100_STAT_port_tx_unicast, mask); + __set_bit(EF100_STAT_port_tx_multicast, mask); + __set_bit(EF100_STAT_port_tx_broadcast, mask); + __set_bit(EF100_STAT_port_tx_lt64, mask); + __set_bit(EF100_STAT_port_tx_64, mask); + __set_bit(EF100_STAT_port_tx_65_to_127, mask); + __set_bit(EF100_STAT_port_tx_128_to_255, mask); + __set_bit(EF100_STAT_port_tx_256_to_511, mask); + __set_bit(EF100_STAT_port_tx_512_to_1023, mask); + __set_bit(EF100_STAT_port_tx_1024_to_15xx, mask); + __set_bit(EF100_STAT_port_tx_15xx_to_jumbo, mask); + __set_bit(EF100_STAT_port_rx_good, mask); + __set_bit(EF100_STAT_port_rx_pause, mask); + __set_bit(EF100_STAT_port_rx_unicast, mask); + __set_bit(EF100_STAT_port_rx_broadcast, mask); + __set_bit(EF100_STAT_port_rx_lt64, mask); + __set_bit(EF100_STAT_port_rx_64, mask); + __set_bit(EF100_STAT_port_rx_65_to_127, mask); + __set_bit(EF100_STAT_port_rx_128_to_255, mask); + __set_bit(EF100_STAT_port_rx_256_to_511, mask); + __set_bit(EF100_STAT_port_rx_512_to_1023, mask); + __set_bit(EF100_STAT_port_rx_1024_to_15xx, mask); + __set_bit(EF100_STAT_port_rx_15xx_to_jumbo, mask); + __set_bit(EF100_STAT_port_rx_gtjumbo, mask); + __set_bit(EF100_STAT_port_rx_bad_gtjumbo, mask); + __set_bit(EF100_STAT_port_rx_length_error, mask); + __set_bit(EF100_STAT_port_rx_nodesc_drops, mask); + __set_bit(GENERIC_STAT_rx_nodesc_trunc, mask); + __set_bit(GENERIC_STAT_rx_noskb_drops, mask); +} + +#define EF100_DMA_STAT(ext_name, mcdi_name) \ + [EF100_STAT_ ## ext_name] = \ + { #ext_name, 64, 8 * MC_CMD_MAC_ ## mcdi_name } + +static const struct efx_hw_stat_desc ef100_stat_desc[EF100_STAT_COUNT] = { + EF100_DMA_STAT(port_tx_bytes, TX_BYTES), + EF100_DMA_STAT(port_tx_packets, TX_PKTS), + EF100_DMA_STAT(port_tx_pause, TX_PAUSE_PKTS), + EF100_DMA_STAT(port_tx_unicast, TX_UNICAST_PKTS), + EF100_DMA_STAT(port_tx_multicast, TX_MULTICAST_PKTS), + EF100_DMA_STAT(port_tx_broadcast, TX_BROADCAST_PKTS), + EF100_DMA_STAT(port_tx_lt64, TX_LT64_PKTS), + EF100_DMA_STAT(port_tx_64, TX_64_PKTS), + EF100_DMA_STAT(port_tx_65_to_127, TX_65_TO_127_PKTS), + EF100_DMA_STAT(port_tx_128_to_255, TX_128_TO_255_PKTS), + EF100_DMA_STAT(port_tx_256_to_511, TX_256_TO_511_PKTS), + EF100_DMA_STAT(port_tx_512_to_1023, TX_512_TO_1023_PKTS), + EF100_DMA_STAT(port_tx_1024_to_15xx, TX_1024_TO_15XX_PKTS), + EF100_DMA_STAT(port_tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS), + EF100_DMA_STAT(port_rx_bytes, RX_BYTES), + EF100_DMA_STAT(port_rx_packets, RX_PKTS), + EF100_DMA_STAT(port_rx_good, RX_GOOD_PKTS), + EF100_DMA_STAT(port_rx_bad, RX_BAD_FCS_PKTS), + EF100_DMA_STAT(port_rx_pause, RX_PAUSE_PKTS), + EF100_DMA_STAT(port_rx_unicast, RX_UNICAST_PKTS), + EF100_DMA_STAT(port_rx_multicast, RX_MULTICAST_PKTS), + EF100_DMA_STAT(port_rx_broadcast, RX_BROADCAST_PKTS), + EF100_DMA_STAT(port_rx_lt64, RX_UNDERSIZE_PKTS), + EF100_DMA_STAT(port_rx_64, RX_64_PKTS), + EF100_DMA_STAT(port_rx_65_to_127, RX_65_TO_127_PKTS), + EF100_DMA_STAT(port_rx_128_to_255, RX_128_TO_255_PKTS), + EF100_DMA_STAT(port_rx_256_to_511, RX_256_TO_511_PKTS), + EF100_DMA_STAT(port_rx_512_to_1023, RX_512_TO_1023_PKTS), + EF100_DMA_STAT(port_rx_1024_to_15xx, RX_1024_TO_15XX_PKTS), + EF100_DMA_STAT(port_rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS), + EF100_DMA_STAT(port_rx_gtjumbo, RX_GTJUMBO_PKTS), + EF100_DMA_STAT(port_rx_bad_gtjumbo, RX_JABBER_PKTS), + EF100_DMA_STAT(port_rx_align_error, RX_ALIGN_ERROR_PKTS), + EF100_DMA_STAT(port_rx_length_error, RX_LENGTH_ERROR_PKTS), + EF100_DMA_STAT(port_rx_overflow, RX_OVERFLOW_PKTS), + EF100_DMA_STAT(port_rx_nodesc_drops, RX_NODESC_DROPS), + EFX_GENERIC_SW_STAT(rx_nodesc_trunc), + EFX_GENERIC_SW_STAT(rx_noskb_drops), +}; + +static size_t ef100_describe_stats(struct efx_nic *efx, u8 *names) +{ + DECLARE_BITMAP(mask, EF100_STAT_COUNT) = {}; + + ef100_ethtool_stat_mask(mask); + return efx_nic_describe_stats(ef100_stat_desc, EF100_STAT_COUNT, + mask, names); +} + +static size_t ef100_update_stats_common(struct efx_nic *efx, u64 *full_stats, + struct rtnl_link_stats64 *core_stats) +{ + struct ef100_nic_data *nic_data = efx->nic_data; + DECLARE_BITMAP(mask, EF100_STAT_COUNT) = {}; + size_t stats_count = 0, index; + u64 *stats = nic_data->stats; + + ef100_ethtool_stat_mask(mask); + + if (full_stats) { + for_each_set_bit(index, mask, EF100_STAT_COUNT) { + if (ef100_stat_desc[index].name) { + *full_stats++ = stats[index]; + ++stats_count; + } + } + } + + if (!core_stats) + return stats_count; + + core_stats->rx_packets = stats[EF100_STAT_port_rx_packets]; + core_stats->tx_packets = stats[EF100_STAT_port_tx_packets]; + core_stats->rx_bytes = stats[EF100_STAT_port_rx_bytes]; + core_stats->tx_bytes = stats[EF100_STAT_port_tx_bytes]; + core_stats->rx_dropped = stats[EF100_STAT_port_rx_nodesc_drops] + + stats[GENERIC_STAT_rx_nodesc_trunc] + + stats[GENERIC_STAT_rx_noskb_drops]; + core_stats->multicast = stats[EF100_STAT_port_rx_multicast]; + core_stats->rx_length_errors = + stats[EF100_STAT_port_rx_gtjumbo] + + stats[EF100_STAT_port_rx_length_error]; + core_stats->rx_crc_errors = stats[EF100_STAT_port_rx_bad]; + core_stats->rx_frame_errors = + stats[EF100_STAT_port_rx_align_error]; + core_stats->rx_fifo_errors = stats[EF100_STAT_port_rx_overflow]; + core_stats->rx_errors = (core_stats->rx_length_errors + + core_stats->rx_crc_errors + + core_stats->rx_frame_errors); + + return stats_count; +} + +static size_t ef100_update_stats(struct efx_nic *efx, + u64 *full_stats, + struct rtnl_link_stats64 *core_stats) +{ + __le64 *mc_stats = kmalloc(array_size(efx->num_mac_stats, sizeof(__le64)), GFP_ATOMIC); + struct ef100_nic_data *nic_data = efx->nic_data; + DECLARE_BITMAP(mask, EF100_STAT_COUNT) = {}; + u64 *stats = nic_data->stats; + + ef100_common_stat_mask(mask); + ef100_ethtool_stat_mask(mask); + + efx_nic_copy_stats(efx, mc_stats); + efx_nic_update_stats(ef100_stat_desc, EF100_STAT_COUNT, mask, + stats, mc_stats, false); + + kfree(mc_stats); + + return ef100_update_stats_common(efx, full_stats, core_stats); +} + +static int efx_ef100_get_phys_port_id(struct efx_nic *efx, + struct netdev_phys_item_id *ppid) +{ + struct ef100_nic_data *nic_data = efx->nic_data; + + if (!is_valid_ether_addr(nic_data->port_id)) + return -EOPNOTSUPP; + + ppid->id_len = ETH_ALEN; + memcpy(ppid->id, nic_data->port_id, ppid->id_len); + + return 0; +} + +static int efx_ef100_irq_test_generate(struct efx_nic *efx) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_TRIGGER_INTERRUPT_IN_LEN); + + BUILD_BUG_ON(MC_CMD_TRIGGER_INTERRUPT_OUT_LEN != 0); + + MCDI_SET_DWORD(inbuf, TRIGGER_INTERRUPT_IN_INTR_LEVEL, efx->irq_level); + return efx_mcdi_rpc_quiet(efx, MC_CMD_TRIGGER_INTERRUPT, + inbuf, sizeof(inbuf), NULL, 0, NULL); +} + +#define EFX_EF100_TEST 1 + +static void efx_ef100_ev_test_generate(struct efx_channel *channel) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_DRIVER_EVENT_IN_LEN); + struct efx_nic *efx = channel->efx; + efx_qword_t event; + int rc; + + EFX_POPULATE_QWORD_2(event, + ESF_GZ_E_TYPE, ESE_GZ_EF100_EV_DRIVER, + ESF_GZ_DRIVER_DATA, EFX_EF100_TEST); + + MCDI_SET_DWORD(inbuf, DRIVER_EVENT_IN_EVQ, channel->channel); + + /* MCDI_SET_QWORD is not appropriate here since EFX_POPULATE_* has + * already swapped the data to little-endian order. + */ + memcpy(MCDI_PTR(inbuf, DRIVER_EVENT_IN_DATA), &event.u64[0], + sizeof(efx_qword_t)); + + rc = efx_mcdi_rpc(efx, MC_CMD_DRIVER_EVENT, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc && (rc != -ENETDOWN)) + goto fail; + + return; + +fail: + WARN_ON(true); + netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); +} + +static unsigned int ef100_check_caps(const struct efx_nic *efx, + u8 flag, u32 offset) +{ + const struct ef100_nic_data *nic_data = efx->nic_data; + + switch (offset) { + case MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS1_OFST: + return nic_data->datapath_caps & BIT_ULL(flag); + case MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS2_OFST: + return nic_data->datapath_caps2 & BIT_ULL(flag); + case MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS3_OFST: + return nic_data->datapath_caps3 & BIT_ULL(flag); + default: + return 0; + } +} + +/* NIC level access functions + */ +#define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \ + NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | \ + NETIF_F_RXHASH | NETIF_F_RXFCS | NETIF_F_TSO_ECN | NETIF_F_RXALL | \ + NETIF_F_TSO_MANGLEID | NETIF_F_HW_VLAN_CTAG_TX) + +const struct efx_nic_type ef100_pf_nic_type = { + .revision = EFX_REV_EF100, + .is_vf = false, + .probe = ef100_probe_pf, + .offload_features = EF100_OFFLOAD_FEATURES, + .mcdi_max_ver = 2, + .mcdi_request = ef100_mcdi_request, + .mcdi_poll_response = ef100_mcdi_poll_response, + .mcdi_read_response = ef100_mcdi_read_response, + .mcdi_poll_reboot = ef100_mcdi_poll_reboot, + .mcdi_reboot_detected = ef100_mcdi_reboot_detected, + .irq_enable_master = efx_port_dummy_op_void, + .irq_test_generate = efx_ef100_irq_test_generate, + .irq_disable_non_ev = efx_port_dummy_op_void, + .push_irq_moderation = efx_channel_dummy_op_void, + .min_interrupt_mode = EFX_INT_MODE_MSIX, + .map_reset_reason = ef100_map_reset_reason, + .map_reset_flags = ef100_map_reset_flags, + .reset = ef100_reset, + + .check_caps = ef100_check_caps, + + .ev_probe = ef100_ev_probe, + .ev_init = ef100_ev_init, + .ev_fini = efx_mcdi_ev_fini, + .ev_remove = efx_mcdi_ev_remove, + .irq_handle_msi = ef100_msi_interrupt, + .ev_process = ef100_ev_process, + .ev_read_ack = ef100_ev_read_ack, + .ev_test_generate = efx_ef100_ev_test_generate, + .tx_probe = ef100_tx_probe, + .tx_init = ef100_tx_init, + .tx_write = ef100_tx_write, + .tx_enqueue = ef100_enqueue_skb, + .rx_probe = efx_mcdi_rx_probe, + .rx_init = efx_mcdi_rx_init, + .rx_remove = efx_mcdi_rx_remove, + .rx_write = ef100_rx_write, + .rx_packet = __ef100_rx_packet, + .fini_dmaq = efx_fini_dmaq, + .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, + .filter_table_probe = ef100_filter_table_up, + .filter_table_restore = efx_mcdi_filter_table_restore, + .filter_table_remove = ef100_filter_table_down, + .filter_insert = efx_mcdi_filter_insert, + .filter_remove_safe = efx_mcdi_filter_remove_safe, + .filter_get_safe = efx_mcdi_filter_get_safe, + .filter_clear_rx = efx_mcdi_filter_clear_rx, + .filter_count_rx_used = efx_mcdi_filter_count_rx_used, + .filter_get_rx_id_limit = efx_mcdi_filter_get_rx_id_limit, + .filter_get_rx_ids = efx_mcdi_filter_get_rx_ids, +#ifdef CONFIG_RFS_ACCEL + .filter_rfs_expire_one = efx_mcdi_filter_rfs_expire_one, +#endif + + .get_phys_port_id = efx_ef100_get_phys_port_id, + + .rx_prefix_size = ESE_GZ_RX_PKT_PREFIX_LEN, + .rx_hash_offset = ESF_GZ_RX_PREFIX_RSS_HASH_LBN / 8, + .rx_ts_offset = ESF_GZ_RX_PREFIX_PARTIAL_TSTAMP_LBN / 8, + .rx_hash_key_size = 40, + .rx_pull_rss_config = efx_mcdi_rx_pull_rss_config, + .rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config, + .rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config, + .rx_pull_rss_context_config = efx_mcdi_rx_pull_rss_context_config, + .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, + + .reconfigure_mac = ef100_reconfigure_mac, + .test_nvram = efx_new_mcdi_nvram_test_all, + .describe_stats = ef100_describe_stats, + .start_stats = efx_mcdi_mac_start_stats, + .update_stats = ef100_update_stats, + .pull_stats = efx_mcdi_mac_pull_stats, + .stop_stats = efx_mcdi_mac_stop_stats, + + /* Per-type bar/size configuration not used on ef100. Location of + * registers is defined by extended capabilities. + */ + .mem_bar = NULL, + .mem_map_size = NULL, + +}; + +const struct efx_nic_type ef100_vf_nic_type = { + .revision = EFX_REV_EF100, + .is_vf = true, + .probe = ef100_probe_vf, + .offload_features = EF100_OFFLOAD_FEATURES, + .mcdi_max_ver = 2, + .mcdi_request = ef100_mcdi_request, + .mcdi_poll_response = ef100_mcdi_poll_response, + .mcdi_read_response = ef100_mcdi_read_response, + .mcdi_poll_reboot = ef100_mcdi_poll_reboot, + .mcdi_reboot_detected = ef100_mcdi_reboot_detected, + .irq_enable_master = efx_port_dummy_op_void, + .irq_test_generate = efx_ef100_irq_test_generate, + .irq_disable_non_ev = efx_port_dummy_op_void, + .push_irq_moderation = efx_channel_dummy_op_void, + .min_interrupt_mode = EFX_INT_MODE_MSIX, + .map_reset_reason = ef100_map_reset_reason, + .map_reset_flags = ef100_map_reset_flags, + .reset = ef100_reset, + .check_caps = ef100_check_caps, + .ev_probe = ef100_ev_probe, + .ev_init = ef100_ev_init, + .ev_fini = efx_mcdi_ev_fini, + .ev_remove = efx_mcdi_ev_remove, + .irq_handle_msi = ef100_msi_interrupt, + .ev_process = ef100_ev_process, + .ev_read_ack = ef100_ev_read_ack, + .ev_test_generate = efx_ef100_ev_test_generate, + .tx_probe = ef100_tx_probe, + .tx_init = ef100_tx_init, + .tx_write = ef100_tx_write, + .tx_enqueue = ef100_enqueue_skb, + .rx_probe = efx_mcdi_rx_probe, + .rx_init = efx_mcdi_rx_init, + .rx_remove = efx_mcdi_rx_remove, + .rx_write = ef100_rx_write, + .rx_packet = __ef100_rx_packet, + .fini_dmaq = efx_fini_dmaq, + .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, + .filter_table_probe = ef100_filter_table_up, + .filter_table_restore = efx_mcdi_filter_table_restore, + .filter_table_remove = ef100_filter_table_down, + .filter_insert = efx_mcdi_filter_insert, + .filter_remove_safe = efx_mcdi_filter_remove_safe, + .filter_get_safe = efx_mcdi_filter_get_safe, + .filter_clear_rx = efx_mcdi_filter_clear_rx, + .filter_count_rx_used = efx_mcdi_filter_count_rx_used, + .filter_get_rx_id_limit = efx_mcdi_filter_get_rx_id_limit, + .filter_get_rx_ids = efx_mcdi_filter_get_rx_ids, + .filter_rfs_expire_one = efx_mcdi_filter_rfs_expire_one, + + .rx_prefix_size = ESE_GZ_RX_PKT_PREFIX_LEN, + .rx_hash_offset = ESF_GZ_RX_PREFIX_RSS_HASH_LBN / 8, + .rx_ts_offset = ESF_GZ_RX_PREFIX_PARTIAL_TSTAMP_LBN / 8, + .rx_hash_key_size = 40, + .rx_pull_rss_config = efx_mcdi_rx_pull_rss_config, + .rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config, + .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, + + .reconfigure_mac = ef100_reconfigure_mac, + .test_nvram = efx_new_mcdi_nvram_test_all, + .describe_stats = ef100_describe_stats, + .start_stats = efx_mcdi_mac_start_stats, + .update_stats = ef100_update_stats, + .pull_stats = efx_mcdi_mac_pull_stats, + .stop_stats = efx_mcdi_mac_stop_stats, + + .mem_bar = NULL, + .mem_map_size = NULL, + +}; + +static int compare_versions(const char *a, const char *b) +{ + int a_major, a_minor, a_point, a_patch; + int b_major, b_minor, b_point, b_patch; + int a_matched, b_matched; + + a_matched = sscanf(a, "%d.%d.%d.%d", &a_major, &a_minor, &a_point, &a_patch); + b_matched = sscanf(b, "%d.%d.%d.%d", &b_major, &b_minor, &b_point, &b_patch); + + if (a_matched == 4 && b_matched != 4) + return +1; + + if (a_matched != 4 && b_matched == 4) + return -1; + + if (a_matched != 4 && b_matched != 4) + return 0; + + if (a_major != b_major) + return a_major - b_major; + + if (a_minor != b_minor) + return a_minor - b_minor; + + if (a_point != b_point) + return a_point - b_point; + + return a_patch - b_patch; +} + +enum ef100_tlv_state_machine { + EF100_TLV_TYPE, + EF100_TLV_TYPE_CONT, + EF100_TLV_LENGTH, + EF100_TLV_VALUE +}; + +struct ef100_tlv_state { + enum ef100_tlv_state_machine state; + u64 value; + u32 value_offset; + u16 type; + u8 len; +}; + +static int ef100_tlv_feed(struct ef100_tlv_state *state, u8 byte) +{ + switch (state->state) { + case EF100_TLV_TYPE: + state->type = byte & 0x7f; + state->state = (byte & 0x80) ? EF100_TLV_TYPE_CONT + : EF100_TLV_LENGTH; + /* Clear ready to read in a new entry */ + state->value = 0; + state->value_offset = 0; + return 0; + case EF100_TLV_TYPE_CONT: + state->type |= byte << 7; + state->state = EF100_TLV_LENGTH; + return 0; + case EF100_TLV_LENGTH: + state->len = byte; + /* We only handle TLVs that fit in a u64 */ + if (state->len > sizeof(state->value)) + return -EOPNOTSUPP; + /* len may be zero, implying a value of zero */ + state->state = state->len ? EF100_TLV_VALUE : EF100_TLV_TYPE; + return 0; + case EF100_TLV_VALUE: + state->value |= ((u64)byte) << (state->value_offset * 8); + state->value_offset++; + if (state->value_offset >= state->len) + state->state = EF100_TLV_TYPE; + return 0; + default: /* state machine error, can't happen */ + WARN_ON_ONCE(1); + return -EIO; + } +} + +static int ef100_process_design_param(struct efx_nic *efx, + const struct ef100_tlv_state *reader) +{ + struct ef100_nic_data *nic_data = efx->nic_data; + + switch (reader->type) { + case ESE_EF100_DP_GZ_PAD: /* padding, skip it */ + return 0; + case ESE_EF100_DP_GZ_PARTIAL_TSTAMP_SUB_NANO_BITS: + /* Driver doesn't support timestamping yet, so we don't care */ + return 0; + case ESE_EF100_DP_GZ_EVQ_UNSOL_CREDIT_SEQ_BITS: + /* Driver doesn't support unsolicited-event credits yet, so + * we don't care + */ + return 0; + case ESE_EF100_DP_GZ_NMMU_GROUP_SIZE: + /* Driver doesn't manage the NMMU (so we don't care) */ + return 0; + case ESE_EF100_DP_GZ_RX_L4_CSUM_PROTOCOLS: + /* Driver uses CHECKSUM_COMPLETE, so we don't care about + * protocol checksum validation + */ + return 0; + case ESE_EF100_DP_GZ_TSO_MAX_HDR_LEN: + nic_data->tso_max_hdr_len = min_t(u64, reader->value, 0xffff); + return 0; + case ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS: + /* We always put HDR_NUM_SEGS=1 in our TSO descriptors */ + if (!reader->value) { + netif_err(efx, probe, efx->net_dev, + "TSO_MAX_HDR_NUM_SEGS < 1\n"); + return -EOPNOTSUPP; + } + return 0; + case ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY: + case ESE_EF100_DP_GZ_TXQ_SIZE_GRANULARITY: + /* Our TXQ and RXQ sizes are always power-of-two and thus divisible by + * EFX_MIN_DMAQ_SIZE, so we just need to check that + * EFX_MIN_DMAQ_SIZE is divisible by GRANULARITY. + * This is very unlikely to fail. + */ + if (EFX_MIN_DMAQ_SIZE % reader->value) { + netif_err(efx, probe, efx->net_dev, + "%s size granularity is %llu, can't guarantee safety\n", + reader->type == ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY ? "RXQ" : "TXQ", + reader->value); + return -EOPNOTSUPP; + } + return 0; + case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN: + nic_data->tso_max_payload_len = min_t(u64, reader->value, GSO_MAX_SIZE); + efx->net_dev->gso_max_size = nic_data->tso_max_payload_len; + return 0; + case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS: + nic_data->tso_max_payload_num_segs = min_t(u64, reader->value, 0xffff); + efx->net_dev->gso_max_segs = nic_data->tso_max_payload_num_segs; + return 0; + case ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES: + nic_data->tso_max_frames = min_t(u64, reader->value, 0xffff); + return 0; + case ESE_EF100_DP_GZ_COMPAT: + if (reader->value) { + netif_err(efx, probe, efx->net_dev, + "DP_COMPAT has unknown bits %#llx, driver not compatible with this hw\n", + reader->value); + return -EOPNOTSUPP; + } + return 0; + case ESE_EF100_DP_GZ_MEM2MEM_MAX_LEN: + /* Driver doesn't use mem2mem transfers */ + return 0; + case ESE_EF100_DP_GZ_EVQ_TIMER_TICK_NANOS: + /* Driver doesn't currently use EVQ_TIMER */ + return 0; + case ESE_EF100_DP_GZ_NMMU_PAGE_SIZES: + /* Driver doesn't manage the NMMU (so we don't care) */ + return 0; + case ESE_EF100_DP_GZ_VI_STRIDES: + /* We never try to set the VI stride, and we don't rely on + * being able to find VIs past VI 0 until after we've learned + * the current stride from MC_CMD_GET_CAPABILITIES. + * So the value of this shouldn't matter. + */ + if (reader->value != ESE_EF100_DP_GZ_VI_STRIDES_DEFAULT) + netif_dbg(efx, probe, efx->net_dev, + "NIC has other than default VI_STRIDES (mask " + "%#llx), early probing might use wrong one\n", + reader->value); + return 0; + case ESE_EF100_DP_GZ_RX_MAX_RUNT: + /* Driver doesn't look at L2_STATUS:LEN_ERR bit, so we don't + * care whether it indicates runt or overlength for any given + * packet, so we don't care about this parameter. + */ + return 0; + default: + /* Host interface says "Drivers should ignore design parameters + * that they do not recognise." + */ + netif_dbg(efx, probe, efx->net_dev, + "Ignoring unrecognised design parameter %u\n", + reader->type); + return 0; + } +} + +static int ef100_check_design_params(struct efx_nic *efx) +{ + struct ef100_tlv_state reader = {}; + u32 total_len, offset = 0; + efx_dword_t reg; + int rc = 0, i; + u32 data; + + efx_readd(efx, ®, ER_GZ_PARAMS_TLV_LEN); + total_len = EFX_DWORD_FIELD(reg, EFX_DWORD_0); + netif_dbg(efx, probe, efx->net_dev, "%u bytes of design parameters\n", + total_len); + while (offset < total_len) { + efx_readd(efx, ®, ER_GZ_PARAMS_TLV + offset); + data = EFX_DWORD_FIELD(reg, EFX_DWORD_0); + for (i = 0; i < sizeof(data); i++) { + rc = ef100_tlv_feed(&reader, data); + /* Got a complete value? */ + if (!rc && reader.state == EF100_TLV_TYPE) + rc = ef100_process_design_param(efx, &reader); + if (rc) + goto out; + data >>= 8; + offset++; + } + } + /* Check we didn't end halfway through a TLV entry, which could either + * mean that the TLV stream is truncated or just that it's corrupted + * and our state machine is out of sync. + */ + if (reader.state != EF100_TLV_TYPE) { + if (reader.state == EF100_TLV_TYPE_CONT) + netif_err(efx, probe, efx->net_dev, + "truncated design parameter (incomplete type %u)\n", + reader.type); + else + netif_err(efx, probe, efx->net_dev, + "truncated design parameter %u\n", + reader.type); + rc = -EIO; + } +out: + return rc; +} + +/* NIC probe and remove + */ +static int ef100_probe_main(struct efx_nic *efx) +{ + unsigned int bar_size = resource_size(&efx->pci_dev->resource[efx->mem_bar]); + struct net_device *net_dev = efx->net_dev; + struct ef100_nic_data *nic_data; + char fw_version[32]; + int i, rc; + + if (WARN_ON(bar_size == 0)) + return -EIO; + + nic_data = kzalloc(sizeof(*nic_data), GFP_KERNEL); + if (!nic_data) + return -ENOMEM; + efx->nic_data = nic_data; + nic_data->efx = efx; + net_dev->features |= efx->type->offload_features; + net_dev->hw_features |= efx->type->offload_features; + + /* Populate design-parameter defaults */ + nic_data->tso_max_hdr_len = ESE_EF100_DP_GZ_TSO_MAX_HDR_LEN_DEFAULT; + nic_data->tso_max_frames = ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES_DEFAULT; + nic_data->tso_max_payload_num_segs = ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS_DEFAULT; + nic_data->tso_max_payload_len = ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN_DEFAULT; + net_dev->gso_max_segs = ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT; + /* Read design parameters */ + rc = ef100_check_design_params(efx); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "Unsupported design parameters\n"); + goto fail; + } + + /* we assume later that we can copy from this buffer in dwords */ + BUILD_BUG_ON(MCDI_CTL_SDU_LEN_MAX_V2 % 4); + + /* MCDI buffers must be 256 byte aligned. */ + rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf, MCDI_BUF_LEN, + GFP_KERNEL); + if (rc) + goto fail; + + /* Get the MC's warm boot count. In case it's rebooting right + * now, be prepared to retry. + */ + i = 0; + for (;;) { + rc = ef100_get_warm_boot_count(efx); + if (rc >= 0) + break; + if (++i == 5) + goto fail; + ssleep(1); + } + nic_data->warm_boot_count = rc; + + /* In case we're recovering from a crash (kexec), we want to + * cancel any outstanding request by the previous user of this + * function. We send a special message using the least + * significant bits of the 'high' (doorbell) register. + */ + _efx_writed(efx, cpu_to_le32(1), efx_reg(efx, ER_GZ_MC_DB_HWRD)); + + /* Post-IO section. */ + + rc = efx_mcdi_init(efx); + if (!rc && efx->mcdi->fn_flags & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_NO_ACTIVE_PORT)) { + netif_info(efx, probe, efx->net_dev, + "No network port on this PCI function"); + rc = -ENODEV; + } + if (rc) + goto fail; + /* Reset (most) configuration for this function */ + rc = efx_mcdi_reset(efx, RESET_TYPE_ALL); + if (rc) + goto fail; + + rc = efx_get_pf_index(efx, &nic_data->pf_index); + if (rc) + goto fail; + + rc = efx_ef100_init_datapath_caps(efx); + if (rc < 0) + goto fail; + + efx->max_vis = EF100_MAX_VIS; + + rc = efx_mcdi_port_get_number(efx); + if (rc < 0) + goto fail; + efx->port_num = rc; + + efx_mcdi_print_fwver(efx, fw_version, sizeof(fw_version)); + netif_dbg(efx, drv, efx->net_dev, "Firmware version %s\n", fw_version); + + if (compare_versions(fw_version, "1.1.0.1000") < 0) { + netif_info(efx, drv, efx->net_dev, "Firmware uses old event descriptors\n"); + rc = -EINVAL; + goto fail; + } + + if (efx_has_cap(efx, UNSOL_EV_CREDIT_SUPPORTED)) { + netif_info(efx, drv, efx->net_dev, "Firmware uses unsolicited-event credits\n"); + rc = -EINVAL; + goto fail; + } + + rc = ef100_phy_probe(efx); + if (rc) + goto fail; + + rc = efx_init_channels(efx); + if (rc) + goto fail; + + down_write(&efx->filter_sem); + rc = ef100_filter_table_probe(efx); + up_write(&efx->filter_sem); + if (rc) + goto fail; + + netdev_rss_key_fill(efx->rss_context.rx_hash_key, + sizeof(efx->rss_context.rx_hash_key)); + + /* Don't fail init if RSS setup doesn't work. */ + efx_mcdi_push_default_indir_table(efx, efx->n_rx_channels); + + rc = ef100_register_netdev(efx); + if (rc) + goto fail; + + return 0; +fail: + return rc; +} + +int ef100_probe_pf(struct efx_nic *efx) +{ + struct net_device *net_dev = efx->net_dev; + struct ef100_nic_data *nic_data; + int rc = ef100_probe_main(efx); + + if (rc) + goto fail; + + nic_data = efx->nic_data; + rc = ef100_get_mac_address(efx, net_dev->perm_addr); + if (rc) + goto fail; + /* Assign MAC address */ + memcpy(net_dev->dev_addr, net_dev->perm_addr, ETH_ALEN); + memcpy(nic_data->port_id, net_dev->perm_addr, ETH_ALEN); + + return 0; + +fail: + return rc; +} + +int ef100_probe_vf(struct efx_nic *efx) +{ + return ef100_probe_main(efx); +} + +void ef100_remove(struct efx_nic *efx) +{ + struct ef100_nic_data *nic_data = efx->nic_data; + + ef100_unregister_netdev(efx); + + down_write(&efx->filter_sem); + efx_mcdi_filter_table_remove(efx); + up_write(&efx->filter_sem); + efx_fini_channels(efx); + kfree(efx->phy_data); + efx->phy_data = NULL; + efx_mcdi_detach(efx); + efx_mcdi_fini(efx); + if (nic_data) + efx_nic_free_buffer(efx, &nic_data->mcdi_buf); + kfree(nic_data); + efx->nic_data = NULL; +} diff --git a/drivers/net/ethernet/sfc/ef100_nic.h b/drivers/net/ethernet/sfc/ef100_nic.h new file mode 100644 index 000000000000..e799688d5264 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_nic.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#include "net_driver.h" +#include "nic_common.h" + +extern const struct efx_nic_type ef100_pf_nic_type; +extern const struct efx_nic_type ef100_vf_nic_type; + +int ef100_probe_pf(struct efx_nic *efx); +int ef100_probe_vf(struct efx_nic *efx); +void ef100_remove(struct efx_nic *efx); + +enum { + EF100_STAT_port_tx_bytes = GENERIC_STAT_COUNT, + EF100_STAT_port_tx_packets, + EF100_STAT_port_tx_pause, + EF100_STAT_port_tx_unicast, + EF100_STAT_port_tx_multicast, + EF100_STAT_port_tx_broadcast, + EF100_STAT_port_tx_lt64, + EF100_STAT_port_tx_64, + EF100_STAT_port_tx_65_to_127, + EF100_STAT_port_tx_128_to_255, + EF100_STAT_port_tx_256_to_511, + EF100_STAT_port_tx_512_to_1023, + EF100_STAT_port_tx_1024_to_15xx, + EF100_STAT_port_tx_15xx_to_jumbo, + EF100_STAT_port_rx_bytes, + EF100_STAT_port_rx_packets, + EF100_STAT_port_rx_good, + EF100_STAT_port_rx_bad, + EF100_STAT_port_rx_pause, + EF100_STAT_port_rx_unicast, + EF100_STAT_port_rx_multicast, + EF100_STAT_port_rx_broadcast, + EF100_STAT_port_rx_lt64, + EF100_STAT_port_rx_64, + EF100_STAT_port_rx_65_to_127, + EF100_STAT_port_rx_128_to_255, + EF100_STAT_port_rx_256_to_511, + EF100_STAT_port_rx_512_to_1023, + EF100_STAT_port_rx_1024_to_15xx, + EF100_STAT_port_rx_15xx_to_jumbo, + EF100_STAT_port_rx_gtjumbo, + EF100_STAT_port_rx_bad_gtjumbo, + EF100_STAT_port_rx_align_error, + EF100_STAT_port_rx_length_error, + EF100_STAT_port_rx_overflow, + EF100_STAT_port_rx_nodesc_drops, + EF100_STAT_COUNT +}; + +struct ef100_nic_data { + struct efx_nic *efx; + struct efx_buffer mcdi_buf; + u32 datapath_caps; + u32 datapath_caps2; + u32 datapath_caps3; + unsigned int pf_index; + u16 warm_boot_count; + u8 port_id[ETH_ALEN]; + DECLARE_BITMAP(evq_phases, EFX_MAX_CHANNELS); + u64 stats[EF100_STAT_COUNT]; + u16 tso_max_hdr_len; + u16 tso_max_payload_num_segs; + u16 tso_max_frames; + unsigned int tso_max_payload_len; +}; + +#define efx_ef100_has_cap(caps, flag) \ + (!!((caps) & BIT_ULL(MC_CMD_GET_CAPABILITIES_V4_OUT_ ## flag ## _LBN))) diff --git a/drivers/net/ethernet/sfc/ef100_regs.h b/drivers/net/ethernet/sfc/ef100_regs.h new file mode 100644 index 000000000000..710bbdb19885 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_regs.h @@ -0,0 +1,693 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#ifndef EFX_EF100_REGS_H +#define EFX_EF100_REGS_H + +/* EF100 hardware architecture definitions have a name prefix following + * the format: + * + * E<type>_<min-rev><max-rev>_ + * + * The following <type> strings are used: + * + * MMIO register Host memory structure + * ------------------------------------------------------------- + * Address R + * Bitfield RF SF + * Enumerator FE SE + * + * <min-rev> is the first revision to which the definition applies: + * + * G: Riverhead + * + * If the definition has been changed or removed in later revisions + * then <max-rev> is the last revision to which the definition applies; + * otherwise it is "Z". + */ + +/************************************************************************** + * + * EF100 registers and descriptors + * + ************************************************************************** + */ + +/* HW_REV_ID_REG: Hardware revision info register */ +#define ER_GZ_HW_REV_ID 0x00000000 + +/* NIC_REV_ID: SoftNIC revision info register */ +#define ER_GZ_NIC_REV_ID 0x00000004 + +/* NIC_MAGIC: Signature register that should contain a well-known value */ +#define ER_GZ_NIC_MAGIC 0x00000008 +#define ERF_GZ_NIC_MAGIC_LBN 0 +#define ERF_GZ_NIC_MAGIC_WIDTH 32 +#define EFE_GZ_NIC_MAGIC_EXPECTED 0xEF100FCB + +/* MC_SFT_STATUS: MC soft status */ +#define ER_GZ_MC_SFT_STATUS 0x00000010 +#define ER_GZ_MC_SFT_STATUS_STEP 4 +#define ER_GZ_MC_SFT_STATUS_ROWS 2 + +/* MC_DB_LWRD_REG: MC doorbell register, low word */ +#define ER_GZ_MC_DB_LWRD 0x00000020 + +/* MC_DB_HWRD_REG: MC doorbell register, high word */ +#define ER_GZ_MC_DB_HWRD 0x00000024 + +/* EVQ_INT_PRIME: Prime EVQ */ +#define ER_GZ_EVQ_INT_PRIME 0x00000040 +#define ERF_GZ_IDX_LBN 16 +#define ERF_GZ_IDX_WIDTH 16 +#define ERF_GZ_EVQ_ID_LBN 0 +#define ERF_GZ_EVQ_ID_WIDTH 16 + +/* INT_AGG_RING_PRIME: Prime interrupt aggregation ring. */ +#define ER_GZ_INT_AGG_RING_PRIME 0x00000048 +/* defined as ERF_GZ_IDX_LBN 16; access=WO reset=0x0 */ +/* defined as ERF_GZ_IDX_WIDTH 16 */ +#define ERF_GZ_RING_ID_LBN 0 +#define ERF_GZ_RING_ID_WIDTH 16 + +/* EVQ_TMR: EVQ timer control */ +#define ER_GZ_EVQ_TMR 0x00000104 +#define ER_GZ_EVQ_TMR_STEP 65536 +#define ER_GZ_EVQ_TMR_ROWS 1024 + +/* EVQ_UNSOL_CREDIT_GRANT_SEQ: Grant credits for unsolicited events. */ +#define ER_GZ_EVQ_UNSOL_CREDIT_GRANT_SEQ 0x00000108 +#define ER_GZ_EVQ_UNSOL_CREDIT_GRANT_SEQ_STEP 65536 +#define ER_GZ_EVQ_UNSOL_CREDIT_GRANT_SEQ_ROWS 1024 + +/* EVQ_DESC_CREDIT_GRANT_SEQ: Grant credits for descriptor proxy events. */ +#define ER_GZ_EVQ_DESC_CREDIT_GRANT_SEQ 0x00000110 +#define ER_GZ_EVQ_DESC_CREDIT_GRANT_SEQ_STEP 65536 +#define ER_GZ_EVQ_DESC_CREDIT_GRANT_SEQ_ROWS 1024 + +/* RX_RING_DOORBELL: Ring Rx doorbell. */ +#define ER_GZ_RX_RING_DOORBELL 0x00000180 +#define ER_GZ_RX_RING_DOORBELL_STEP 65536 +#define ER_GZ_RX_RING_DOORBELL_ROWS 1024 +#define ERF_GZ_RX_RING_PIDX_LBN 16 +#define ERF_GZ_RX_RING_PIDX_WIDTH 16 + +/* TX_RING_DOORBELL: Ring Tx doorbell. */ +#define ER_GZ_TX_RING_DOORBELL 0x00000200 +#define ER_GZ_TX_RING_DOORBELL_STEP 65536 +#define ER_GZ_TX_RING_DOORBELL_ROWS 1024 +#define ERF_GZ_TX_RING_PIDX_LBN 16 +#define ERF_GZ_TX_RING_PIDX_WIDTH 16 + +/* TX_DESC_PUSH: Tx ring descriptor push. Reserved for future use. */ +#define ER_GZ_TX_DESC_PUSH 0x00000210 +#define ER_GZ_TX_DESC_PUSH_STEP 65536 +#define ER_GZ_TX_DESC_PUSH_ROWS 1024 + +/* THE_TIME: NIC hardware time */ +#define ER_GZ_THE_TIME 0x00000280 +#define ER_GZ_THE_TIME_STEP 65536 +#define ER_GZ_THE_TIME_ROWS 1024 +#define ERF_GZ_THE_TIME_SECS_LBN 32 +#define ERF_GZ_THE_TIME_SECS_WIDTH 32 +#define ERF_GZ_THE_TIME_NANOS_LBN 2 +#define ERF_GZ_THE_TIME_NANOS_WIDTH 30 +#define ERF_GZ_THE_TIME_CLOCK_IN_SYNC_LBN 1 +#define ERF_GZ_THE_TIME_CLOCK_IN_SYNC_WIDTH 1 +#define ERF_GZ_THE_TIME_CLOCK_IS_SET_LBN 0 +#define ERF_GZ_THE_TIME_CLOCK_IS_SET_WIDTH 1 + +/* PARAMS_TLV_LEN: Size of design parameters area in bytes */ +#define ER_GZ_PARAMS_TLV_LEN 0x00000c00 +#define ER_GZ_PARAMS_TLV_LEN_STEP 65536 +#define ER_GZ_PARAMS_TLV_LEN_ROWS 1024 + +/* PARAMS_TLV: Design parameters */ +#define ER_GZ_PARAMS_TLV 0x00000c04 +#define ER_GZ_PARAMS_TLV_STEP 65536 +#define ER_GZ_PARAMS_TLV_ROWS 1024 + +/* EW_EMBEDDED_EVENT */ +#define ESF_GZ_EV_256_EVENT_LBN 0 +#define ESF_GZ_EV_256_EVENT_WIDTH 64 +#define ESE_GZ_EW_EMBEDDED_EVENT_STRUCT_SIZE 64 + +/* NMMU_PAGESZ_2M_ADDR */ +#define ESF_GZ_NMMU_2M_PAGE_SIZE_ID_LBN 59 +#define ESF_GZ_NMMU_2M_PAGE_SIZE_ID_WIDTH 5 +#define ESE_GZ_NMMU_PAGE_SIZE_2M 9 +#define ESF_GZ_NMMU_2M_PAGE_ID_LBN 21 +#define ESF_GZ_NMMU_2M_PAGE_ID_WIDTH 38 +#define ESF_GZ_NMMU_2M_PAGE_OFFSET_LBN 0 +#define ESF_GZ_NMMU_2M_PAGE_OFFSET_WIDTH 21 +#define ESE_GZ_NMMU_PAGESZ_2M_ADDR_STRUCT_SIZE 64 + +/* PARAM_TLV */ +#define ESF_GZ_TLV_VALUE_LBN 16 +#define ESF_GZ_TLV_VALUE_WIDTH 8 +#define ESE_GZ_TLV_VALUE_LENMIN 8 +#define ESE_GZ_TLV_VALUE_LENMAX 2040 +#define ESF_GZ_TLV_LEN_LBN 8 +#define ESF_GZ_TLV_LEN_WIDTH 8 +#define ESF_GZ_TLV_TYPE_LBN 0 +#define ESF_GZ_TLV_TYPE_WIDTH 8 +#define ESE_GZ_DP_NMMU_GROUP_SIZE 5 +#define ESE_GZ_DP_EVQ_UNSOL_CREDIT_SEQ_BITS 4 +#define ESE_GZ_DP_TX_EV_NUM_DESCS_BITS 3 +#define ESE_GZ_DP_RX_EV_NUM_PACKETS_BITS 2 +#define ESE_GZ_DP_PARTIAL_TSTAMP_SUB_NANO_BITS 1 +#define ESE_GZ_DP_PAD 0 +#define ESE_GZ_PARAM_TLV_STRUCT_SIZE 24 + +/* PCI_EXPRESS_XCAP_HDR */ +#define ESF_GZ_PCI_EXPRESS_XCAP_NEXT_LBN 20 +#define ESF_GZ_PCI_EXPRESS_XCAP_NEXT_WIDTH 12 +#define ESF_GZ_PCI_EXPRESS_XCAP_VER_LBN 16 +#define ESF_GZ_PCI_EXPRESS_XCAP_VER_WIDTH 4 +#define ESE_GZ_PCI_EXPRESS_XCAP_VER_VSEC 1 +#define ESF_GZ_PCI_EXPRESS_XCAP_ID_LBN 0 +#define ESF_GZ_PCI_EXPRESS_XCAP_ID_WIDTH 16 +#define ESE_GZ_PCI_EXPRESS_XCAP_ID_VNDR 0xb +#define ESE_GZ_PCI_EXPRESS_XCAP_HDR_STRUCT_SIZE 32 + +/* RHEAD_BASE_EVENT */ +#define ESF_GZ_E_TYPE_LBN 60 +#define ESF_GZ_E_TYPE_WIDTH 4 +#define ESE_GZ_EF100_EV_DRIVER 5 +#define ESE_GZ_EF100_EV_MCDI 4 +#define ESE_GZ_EF100_EV_CONTROL 3 +#define ESE_GZ_EF100_EV_TX_TIMESTAMP 2 +#define ESE_GZ_EF100_EV_TX_COMPLETION 1 +#define ESE_GZ_EF100_EV_RX_PKTS 0 +#define ESF_GZ_EV_EVQ_PHASE_LBN 59 +#define ESF_GZ_EV_EVQ_PHASE_WIDTH 1 +#define ESE_GZ_RHEAD_BASE_EVENT_STRUCT_SIZE 64 + +/* RHEAD_EW_EVENT */ +#define ESF_GZ_EV_256_EV32_PHASE_LBN 255 +#define ESF_GZ_EV_256_EV32_PHASE_WIDTH 1 +#define ESF_GZ_EV_256_EV32_TYPE_LBN 251 +#define ESF_GZ_EV_256_EV32_TYPE_WIDTH 4 +#define ESE_GZ_EF100_EVEW_VIRTQ_DESC 2 +#define ESE_GZ_EF100_EVEW_TXQ_DESC 1 +#define ESE_GZ_EF100_EVEW_64BIT 0 +#define ESE_GZ_RHEAD_EW_EVENT_STRUCT_SIZE 256 + +/* RX_DESC */ +#define ESF_GZ_RX_BUF_ADDR_LBN 0 +#define ESF_GZ_RX_BUF_ADDR_WIDTH 64 +#define ESE_GZ_RX_DESC_STRUCT_SIZE 64 + +/* TXQ_DESC_PROXY_EVENT */ +#define ESF_GZ_EV_TXQ_DP_VI_ID_LBN 128 +#define ESF_GZ_EV_TXQ_DP_VI_ID_WIDTH 16 +#define ESF_GZ_EV_TXQ_DP_TXQ_DESC_LBN 0 +#define ESF_GZ_EV_TXQ_DP_TXQ_DESC_WIDTH 128 +#define ESE_GZ_TXQ_DESC_PROXY_EVENT_STRUCT_SIZE 144 + +/* TX_DESC_TYPE */ +#define ESF_GZ_TX_DESC_TYPE_LBN 124 +#define ESF_GZ_TX_DESC_TYPE_WIDTH 4 +#define ESE_GZ_TX_DESC_TYPE_DESC2CMPT 7 +#define ESE_GZ_TX_DESC_TYPE_MEM2MEM 4 +#define ESE_GZ_TX_DESC_TYPE_SEG 3 +#define ESE_GZ_TX_DESC_TYPE_TSO 2 +#define ESE_GZ_TX_DESC_TYPE_PREFIX 1 +#define ESE_GZ_TX_DESC_TYPE_SEND 0 +#define ESE_GZ_TX_DESC_TYPE_STRUCT_SIZE 128 + +/* VIRTQ_DESC_PROXY_EVENT */ +#define ESF_GZ_EV_VQ_DP_AVAIL_ENTRY_LBN 144 +#define ESF_GZ_EV_VQ_DP_AVAIL_ENTRY_WIDTH 16 +#define ESF_GZ_EV_VQ_DP_VI_ID_LBN 128 +#define ESF_GZ_EV_VQ_DP_VI_ID_WIDTH 16 +#define ESF_GZ_EV_VQ_DP_VIRTQ_DESC_LBN 0 +#define ESF_GZ_EV_VQ_DP_VIRTQ_DESC_WIDTH 128 +#define ESE_GZ_VIRTQ_DESC_PROXY_EVENT_STRUCT_SIZE 160 + +/* XIL_CFGBAR_TBL_ENTRY */ +#define ESF_GZ_CFGBAR_CONT_CAP_OFF_HI_LBN 96 +#define ESF_GZ_CFGBAR_CONT_CAP_OFF_HI_WIDTH 32 +#define ESF_GZ_CFGBAR_CONT_CAP_OFFSET_LBN 68 +#define ESF_GZ_CFGBAR_CONT_CAP_OFFSET_WIDTH 60 +#define ESE_GZ_CONT_CAP_OFFSET_BYTES_SHIFT 4 +#define ESF_GZ_CFGBAR_EF100_FUNC_CTL_WIN_OFF_LBN 67 +#define ESF_GZ_CFGBAR_EF100_FUNC_CTL_WIN_OFF_WIDTH 29 +#define ESE_GZ_EF100_FUNC_CTL_WIN_OFF_SHIFT 4 +#define ESF_GZ_CFGBAR_CONT_CAP_OFF_LO_LBN 68 +#define ESF_GZ_CFGBAR_CONT_CAP_OFF_LO_WIDTH 28 +#define ESF_GZ_CFGBAR_CONT_CAP_RSV_LBN 67 +#define ESF_GZ_CFGBAR_CONT_CAP_RSV_WIDTH 1 +#define ESF_GZ_CFGBAR_EF100_BAR_LBN 64 +#define ESF_GZ_CFGBAR_EF100_BAR_WIDTH 3 +#define ESE_GZ_CFGBAR_EF100_BAR_NUM_INVALID 7 +#define ESE_GZ_CFGBAR_EF100_BAR_NUM_EXPANSION_ROM 6 +#define ESF_GZ_CFGBAR_CONT_CAP_BAR_LBN 64 +#define ESF_GZ_CFGBAR_CONT_CAP_BAR_WIDTH 3 +#define ESE_GZ_CFGBAR_CONT_CAP_BAR_NUM_INVALID 7 +#define ESE_GZ_CFGBAR_CONT_CAP_BAR_NUM_EXPANSION_ROM 6 +#define ESF_GZ_CFGBAR_ENTRY_SIZE_LBN 32 +#define ESF_GZ_CFGBAR_ENTRY_SIZE_WIDTH 32 +#define ESE_GZ_CFGBAR_ENTRY_SIZE_EF100 12 +#define ESE_GZ_CFGBAR_ENTRY_HEADER_SIZE 8 +#define ESF_GZ_CFGBAR_ENTRY_LAST_LBN 28 +#define ESF_GZ_CFGBAR_ENTRY_LAST_WIDTH 1 +#define ESF_GZ_CFGBAR_ENTRY_REV_LBN 20 +#define ESF_GZ_CFGBAR_ENTRY_REV_WIDTH 8 +#define ESE_GZ_CFGBAR_ENTRY_REV_EF100 0 +#define ESF_GZ_CFGBAR_ENTRY_FORMAT_LBN 0 +#define ESF_GZ_CFGBAR_ENTRY_FORMAT_WIDTH 20 +#define ESE_GZ_CFGBAR_ENTRY_LAST 0xfffff +#define ESE_GZ_CFGBAR_ENTRY_CONT_CAP_ADDR 0xffffe +#define ESE_GZ_CFGBAR_ENTRY_EF100 0xef100 +#define ESE_GZ_XIL_CFGBAR_TBL_ENTRY_STRUCT_SIZE 128 + +/* XIL_CFGBAR_VSEC */ +#define ESF_GZ_VSEC_TBL_OFF_HI_LBN 64 +#define ESF_GZ_VSEC_TBL_OFF_HI_WIDTH 32 +#define ESE_GZ_VSEC_TBL_OFF_HI_BYTES_SHIFT 32 +#define ESF_GZ_VSEC_TBL_OFF_LO_LBN 36 +#define ESF_GZ_VSEC_TBL_OFF_LO_WIDTH 28 +#define ESE_GZ_VSEC_TBL_OFF_LO_BYTES_SHIFT 4 +#define ESF_GZ_VSEC_TBL_BAR_LBN 32 +#define ESF_GZ_VSEC_TBL_BAR_WIDTH 4 +#define ESE_GZ_VSEC_BAR_NUM_INVALID 7 +#define ESE_GZ_VSEC_BAR_NUM_EXPANSION_ROM 6 +#define ESF_GZ_VSEC_LEN_LBN 20 +#define ESF_GZ_VSEC_LEN_WIDTH 12 +#define ESE_GZ_VSEC_LEN_HIGH_OFFT 16 +#define ESE_GZ_VSEC_LEN_MIN 12 +#define ESF_GZ_VSEC_VER_LBN 16 +#define ESF_GZ_VSEC_VER_WIDTH 4 +#define ESE_GZ_VSEC_VER_XIL_CFGBAR 0 +#define ESF_GZ_VSEC_ID_LBN 0 +#define ESF_GZ_VSEC_ID_WIDTH 16 +#define ESE_GZ_XILINX_VSEC_ID 0x20 +#define ESE_GZ_XIL_CFGBAR_VSEC_STRUCT_SIZE 96 + +/* rh_egres_hclass */ +#define ESF_GZ_RX_PREFIX_HCLASS_TUN_OUTER_L4_CSUM_LBN 15 +#define ESF_GZ_RX_PREFIX_HCLASS_TUN_OUTER_L4_CSUM_WIDTH 1 +#define ESF_GZ_RX_PREFIX_HCLASS_TUN_OUTER_L3_CLASS_LBN 13 +#define ESF_GZ_RX_PREFIX_HCLASS_TUN_OUTER_L3_CLASS_WIDTH 2 +#define ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L4_CSUM_LBN 12 +#define ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L4_CSUM_WIDTH 1 +#define ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L4_CLASS_LBN 10 +#define ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L4_CLASS_WIDTH 2 +#define ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_LBN 8 +#define ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_WIDTH 2 +#define ESF_GZ_RX_PREFIX_HCLASS_TUNNEL_CLASS_LBN 5 +#define ESF_GZ_RX_PREFIX_HCLASS_TUNNEL_CLASS_WIDTH 3 +#define ESF_GZ_RX_PREFIX_HCLASS_L2_N_VLAN_LBN 3 +#define ESF_GZ_RX_PREFIX_HCLASS_L2_N_VLAN_WIDTH 2 +#define ESF_GZ_RX_PREFIX_HCLASS_L2_CLASS_LBN 2 +#define ESF_GZ_RX_PREFIX_HCLASS_L2_CLASS_WIDTH 1 +#define ESF_GZ_RX_PREFIX_HCLASS_L2_STATUS_LBN 0 +#define ESF_GZ_RX_PREFIX_HCLASS_L2_STATUS_WIDTH 2 +#define ESE_GZ_RH_EGRES_HCLASS_STRUCT_SIZE 16 + +/* sf_driver */ +#define ESF_GZ_DRIVER_E_TYPE_LBN 60 +#define ESF_GZ_DRIVER_E_TYPE_WIDTH 4 +#define ESF_GZ_DRIVER_PHASE_LBN 59 +#define ESF_GZ_DRIVER_PHASE_WIDTH 1 +#define ESF_GZ_DRIVER_DATA_LBN 0 +#define ESF_GZ_DRIVER_DATA_WIDTH 59 +#define ESE_GZ_SF_DRIVER_STRUCT_SIZE 64 + +/* sf_ev_rsvd */ +#define ESF_GZ_EV_RSVD_TBD_NEXT_LBN 34 +#define ESF_GZ_EV_RSVD_TBD_NEXT_WIDTH 3 +#define ESF_GZ_EV_RSVD_EVENT_GEN_FLAGS_LBN 30 +#define ESF_GZ_EV_RSVD_EVENT_GEN_FLAGS_WIDTH 4 +#define ESF_GZ_EV_RSVD_SRC_QID_LBN 18 +#define ESF_GZ_EV_RSVD_SRC_QID_WIDTH 12 +#define ESF_GZ_EV_RSVD_SEQ_NUM_LBN 2 +#define ESF_GZ_EV_RSVD_SEQ_NUM_WIDTH 16 +#define ESF_GZ_EV_RSVD_TBD_LBN 0 +#define ESF_GZ_EV_RSVD_TBD_WIDTH 2 +#define ESE_GZ_SF_EV_RSVD_STRUCT_SIZE 37 + +/* sf_flush_evnt */ +#define ESF_GZ_EV_FLSH_E_TYPE_LBN 60 +#define ESF_GZ_EV_FLSH_E_TYPE_WIDTH 4 +#define ESF_GZ_EV_FLSH_PHASE_LBN 59 +#define ESF_GZ_EV_FLSH_PHASE_WIDTH 1 +#define ESF_GZ_EV_FLSH_SUB_TYPE_LBN 53 +#define ESF_GZ_EV_FLSH_SUB_TYPE_WIDTH 6 +#define ESF_GZ_EV_FLSH_RSVD_LBN 10 +#define ESF_GZ_EV_FLSH_RSVD_WIDTH 43 +#define ESF_GZ_EV_FLSH_LABEL_LBN 4 +#define ESF_GZ_EV_FLSH_LABEL_WIDTH 6 +#define ESF_GZ_EV_FLSH_FLUSH_TYPE_LBN 0 +#define ESF_GZ_EV_FLSH_FLUSH_TYPE_WIDTH 4 +#define ESE_GZ_SF_FLUSH_EVNT_STRUCT_SIZE 64 + +/* sf_rx_pkts */ +#define ESF_GZ_EV_RXPKTS_E_TYPE_LBN 60 +#define ESF_GZ_EV_RXPKTS_E_TYPE_WIDTH 4 +#define ESF_GZ_EV_RXPKTS_PHASE_LBN 59 +#define ESF_GZ_EV_RXPKTS_PHASE_WIDTH 1 +#define ESF_GZ_EV_RXPKTS_RSVD_LBN 22 +#define ESF_GZ_EV_RXPKTS_RSVD_WIDTH 37 +#define ESF_GZ_EV_RXPKTS_Q_LABEL_LBN 16 +#define ESF_GZ_EV_RXPKTS_Q_LABEL_WIDTH 6 +#define ESF_GZ_EV_RXPKTS_NUM_PKT_LBN 0 +#define ESF_GZ_EV_RXPKTS_NUM_PKT_WIDTH 16 +#define ESE_GZ_SF_RX_PKTS_STRUCT_SIZE 64 + +/* sf_rx_prefix */ +#define ESF_GZ_RX_PREFIX_VLAN_STRIP_TCI_LBN 160 +#define ESF_GZ_RX_PREFIX_VLAN_STRIP_TCI_WIDTH 16 +#define ESF_GZ_RX_PREFIX_CSUM_FRAME_LBN 144 +#define ESF_GZ_RX_PREFIX_CSUM_FRAME_WIDTH 16 +#define ESF_GZ_RX_PREFIX_INGRESS_VPORT_LBN 128 +#define ESF_GZ_RX_PREFIX_INGRESS_VPORT_WIDTH 16 +#define ESF_GZ_RX_PREFIX_USER_MARK_LBN 96 +#define ESF_GZ_RX_PREFIX_USER_MARK_WIDTH 32 +#define ESF_GZ_RX_PREFIX_RSS_HASH_LBN 64 +#define ESF_GZ_RX_PREFIX_RSS_HASH_WIDTH 32 +#define ESF_GZ_RX_PREFIX_PARTIAL_TSTAMP_LBN 32 +#define ESF_GZ_RX_PREFIX_PARTIAL_TSTAMP_WIDTH 32 +#define ESF_GZ_RX_PREFIX_CLASS_LBN 16 +#define ESF_GZ_RX_PREFIX_CLASS_WIDTH 16 +#define ESF_GZ_RX_PREFIX_USER_FLAG_LBN 15 +#define ESF_GZ_RX_PREFIX_USER_FLAG_WIDTH 1 +#define ESF_GZ_RX_PREFIX_RSS_HASH_VALID_LBN 14 +#define ESF_GZ_RX_PREFIX_RSS_HASH_VALID_WIDTH 1 +#define ESF_GZ_RX_PREFIX_LENGTH_LBN 0 +#define ESF_GZ_RX_PREFIX_LENGTH_WIDTH 14 +#define ESE_GZ_SF_RX_PREFIX_STRUCT_SIZE 176 + +/* sf_rxtx_generic */ +#define ESF_GZ_EV_BARRIER_LBN 167 +#define ESF_GZ_EV_BARRIER_WIDTH 1 +#define ESF_GZ_EV_RSVD_LBN 130 +#define ESF_GZ_EV_RSVD_WIDTH 37 +#define ESF_GZ_EV_DPRXY_LBN 129 +#define ESF_GZ_EV_DPRXY_WIDTH 1 +#define ESF_GZ_EV_VIRTIO_LBN 128 +#define ESF_GZ_EV_VIRTIO_WIDTH 1 +#define ESF_GZ_EV_COUNT_LBN 0 +#define ESF_GZ_EV_COUNT_WIDTH 128 +#define ESE_GZ_SF_RXTX_GENERIC_STRUCT_SIZE 168 + +/* sf_ts_stamp */ +#define ESF_GZ_EV_TS_E_TYPE_LBN 60 +#define ESF_GZ_EV_TS_E_TYPE_WIDTH 4 +#define ESF_GZ_EV_TS_PHASE_LBN 59 +#define ESF_GZ_EV_TS_PHASE_WIDTH 1 +#define ESF_GZ_EV_TS_RSVD_LBN 56 +#define ESF_GZ_EV_TS_RSVD_WIDTH 3 +#define ESF_GZ_EV_TS_STATUS_LBN 54 +#define ESF_GZ_EV_TS_STATUS_WIDTH 2 +#define ESF_GZ_EV_TS_Q_LABEL_LBN 48 +#define ESF_GZ_EV_TS_Q_LABEL_WIDTH 6 +#define ESF_GZ_EV_TS_DESC_ID_LBN 32 +#define ESF_GZ_EV_TS_DESC_ID_WIDTH 16 +#define ESF_GZ_EV_TS_PARTIAL_STAMP_LBN 0 +#define ESF_GZ_EV_TS_PARTIAL_STAMP_WIDTH 32 +#define ESE_GZ_SF_TS_STAMP_STRUCT_SIZE 64 + +/* sf_tx_cmplt */ +#define ESF_GZ_EV_TXCMPL_E_TYPE_LBN 60 +#define ESF_GZ_EV_TXCMPL_E_TYPE_WIDTH 4 +#define ESF_GZ_EV_TXCMPL_PHASE_LBN 59 +#define ESF_GZ_EV_TXCMPL_PHASE_WIDTH 1 +#define ESF_GZ_EV_TXCMPL_RSVD_LBN 22 +#define ESF_GZ_EV_TXCMPL_RSVD_WIDTH 37 +#define ESF_GZ_EV_TXCMPL_Q_LABEL_LBN 16 +#define ESF_GZ_EV_TXCMPL_Q_LABEL_WIDTH 6 +#define ESF_GZ_EV_TXCMPL_NUM_DESC_LBN 0 +#define ESF_GZ_EV_TXCMPL_NUM_DESC_WIDTH 16 +#define ESE_GZ_SF_TX_CMPLT_STRUCT_SIZE 64 + +/* sf_tx_desc2cmpt_dsc_fmt */ +#define ESF_GZ_D2C_TGT_VI_ID_LBN 108 +#define ESF_GZ_D2C_TGT_VI_ID_WIDTH 16 +#define ESF_GZ_D2C_CMPT2_LBN 107 +#define ESF_GZ_D2C_CMPT2_WIDTH 1 +#define ESF_GZ_D2C_ABS_VI_ID_LBN 106 +#define ESF_GZ_D2C_ABS_VI_ID_WIDTH 1 +#define ESF_GZ_D2C_ORDERED_LBN 105 +#define ESF_GZ_D2C_ORDERED_WIDTH 1 +#define ESF_GZ_D2C_SKIP_N_LBN 97 +#define ESF_GZ_D2C_SKIP_N_WIDTH 8 +#define ESF_GZ_D2C_RSVD_LBN 64 +#define ESF_GZ_D2C_RSVD_WIDTH 33 +#define ESF_GZ_D2C_COMPLETION_LBN 0 +#define ESF_GZ_D2C_COMPLETION_WIDTH 64 +#define ESE_GZ_SF_TX_DESC2CMPT_DSC_FMT_STRUCT_SIZE 124 + +/* sf_tx_mem2mem_dsc_fmt */ +#define ESF_GZ_M2M_ADDR_SPC_EN_LBN 123 +#define ESF_GZ_M2M_ADDR_SPC_EN_WIDTH 1 +#define ESF_GZ_M2M_TRANSLATE_ADDR_LBN 122 +#define ESF_GZ_M2M_TRANSLATE_ADDR_WIDTH 1 +#define ESF_GZ_M2M_RSVD_LBN 120 +#define ESF_GZ_M2M_RSVD_WIDTH 2 +#define ESF_GZ_M2M_ADDR_SPC_LBN 108 +#define ESF_GZ_M2M_ADDR_SPC_WIDTH 12 +#define ESF_GZ_M2M_ADDR_SPC_PASID_LBN 86 +#define ESF_GZ_M2M_ADDR_SPC_PASID_WIDTH 22 +#define ESF_GZ_M2M_ADDR_SPC_MODE_LBN 84 +#define ESF_GZ_M2M_ADDR_SPC_MODE_WIDTH 2 +#define ESF_GZ_M2M_LEN_MINUS_1_LBN 64 +#define ESF_GZ_M2M_LEN_MINUS_1_WIDTH 20 +#define ESF_GZ_M2M_ADDR_LBN 0 +#define ESF_GZ_M2M_ADDR_WIDTH 64 +#define ESE_GZ_SF_TX_MEM2MEM_DSC_FMT_STRUCT_SIZE 124 + +/* sf_tx_ovr_dsc_fmt */ +#define ESF_GZ_TX_PREFIX_MARK_EN_LBN 123 +#define ESF_GZ_TX_PREFIX_MARK_EN_WIDTH 1 +#define ESF_GZ_TX_PREFIX_INGRESS_MPORT_EN_LBN 122 +#define ESF_GZ_TX_PREFIX_INGRESS_MPORT_EN_WIDTH 1 +#define ESF_GZ_TX_PREFIX_INLINE_CAPSULE_META_LBN 121 +#define ESF_GZ_TX_PREFIX_INLINE_CAPSULE_META_WIDTH 1 +#define ESF_GZ_TX_PREFIX_EGRESS_MPORT_EN_LBN 120 +#define ESF_GZ_TX_PREFIX_EGRESS_MPORT_EN_WIDTH 1 +#define ESF_GZ_TX_PREFIX_RSRVD_LBN 64 +#define ESF_GZ_TX_PREFIX_RSRVD_WIDTH 56 +#define ESF_GZ_TX_PREFIX_EGRESS_MPORT_LBN 48 +#define ESF_GZ_TX_PREFIX_EGRESS_MPORT_WIDTH 16 +#define ESF_GZ_TX_PREFIX_INGRESS_MPORT_LBN 32 +#define ESF_GZ_TX_PREFIX_INGRESS_MPORT_WIDTH 16 +#define ESF_GZ_TX_PREFIX_MARK_LBN 0 +#define ESF_GZ_TX_PREFIX_MARK_WIDTH 32 +#define ESE_GZ_SF_TX_OVR_DSC_FMT_STRUCT_SIZE 124 + +/* sf_tx_seg_dsc_fmt */ +#define ESF_GZ_TX_SEG_ADDR_SPC_EN_LBN 123 +#define ESF_GZ_TX_SEG_ADDR_SPC_EN_WIDTH 1 +#define ESF_GZ_TX_SEG_TRANSLATE_ADDR_LBN 122 +#define ESF_GZ_TX_SEG_TRANSLATE_ADDR_WIDTH 1 +#define ESF_GZ_TX_SEG_RSVD2_LBN 120 +#define ESF_GZ_TX_SEG_RSVD2_WIDTH 2 +#define ESF_GZ_TX_SEG_ADDR_SPC_LBN 108 +#define ESF_GZ_TX_SEG_ADDR_SPC_WIDTH 12 +#define ESF_GZ_TX_SEG_ADDR_SPC_PASID_LBN 86 +#define ESF_GZ_TX_SEG_ADDR_SPC_PASID_WIDTH 22 +#define ESF_GZ_TX_SEG_ADDR_SPC_MODE_LBN 84 +#define ESF_GZ_TX_SEG_ADDR_SPC_MODE_WIDTH 2 +#define ESF_GZ_TX_SEG_RSVD_LBN 80 +#define ESF_GZ_TX_SEG_RSVD_WIDTH 4 +#define ESF_GZ_TX_SEG_LEN_LBN 64 +#define ESF_GZ_TX_SEG_LEN_WIDTH 16 +#define ESF_GZ_TX_SEG_ADDR_LBN 0 +#define ESF_GZ_TX_SEG_ADDR_WIDTH 64 +#define ESE_GZ_SF_TX_SEG_DSC_FMT_STRUCT_SIZE 124 + +/* sf_tx_std_dsc_fmt */ +#define ESF_GZ_TX_SEND_VLAN_INSERT_TCI_LBN 108 +#define ESF_GZ_TX_SEND_VLAN_INSERT_TCI_WIDTH 16 +#define ESF_GZ_TX_SEND_VLAN_INSERT_EN_LBN 107 +#define ESF_GZ_TX_SEND_VLAN_INSERT_EN_WIDTH 1 +#define ESF_GZ_TX_SEND_TSTAMP_REQ_LBN 106 +#define ESF_GZ_TX_SEND_TSTAMP_REQ_WIDTH 1 +#define ESF_GZ_TX_SEND_CSO_OUTER_L4_LBN 105 +#define ESF_GZ_TX_SEND_CSO_OUTER_L4_WIDTH 1 +#define ESF_GZ_TX_SEND_CSO_OUTER_L3_LBN 104 +#define ESF_GZ_TX_SEND_CSO_OUTER_L3_WIDTH 1 +#define ESF_GZ_TX_SEND_CSO_INNER_L3_LBN 101 +#define ESF_GZ_TX_SEND_CSO_INNER_L3_WIDTH 3 +#define ESF_GZ_TX_SEND_RSVD_LBN 99 +#define ESF_GZ_TX_SEND_RSVD_WIDTH 2 +#define ESF_GZ_TX_SEND_CSO_PARTIAL_EN_LBN 97 +#define ESF_GZ_TX_SEND_CSO_PARTIAL_EN_WIDTH 2 +#define ESF_GZ_TX_SEND_CSO_PARTIAL_CSUM_W_LBN 92 +#define ESF_GZ_TX_SEND_CSO_PARTIAL_CSUM_W_WIDTH 5 +#define ESF_GZ_TX_SEND_CSO_PARTIAL_START_W_LBN 83 +#define ESF_GZ_TX_SEND_CSO_PARTIAL_START_W_WIDTH 9 +#define ESF_GZ_TX_SEND_NUM_SEGS_LBN 78 +#define ESF_GZ_TX_SEND_NUM_SEGS_WIDTH 5 +#define ESF_GZ_TX_SEND_LEN_LBN 64 +#define ESF_GZ_TX_SEND_LEN_WIDTH 14 +#define ESF_GZ_TX_SEND_ADDR_LBN 0 +#define ESF_GZ_TX_SEND_ADDR_WIDTH 64 +#define ESE_GZ_SF_TX_STD_DSC_FMT_STRUCT_SIZE 124 + +/* sf_tx_tso_dsc_fmt */ +#define ESF_GZ_TX_TSO_VLAN_INSERT_TCI_LBN 108 +#define ESF_GZ_TX_TSO_VLAN_INSERT_TCI_WIDTH 16 +#define ESF_GZ_TX_TSO_VLAN_INSERT_EN_LBN 107 +#define ESF_GZ_TX_TSO_VLAN_INSERT_EN_WIDTH 1 +#define ESF_GZ_TX_TSO_TSTAMP_REQ_LBN 106 +#define ESF_GZ_TX_TSO_TSTAMP_REQ_WIDTH 1 +#define ESF_GZ_TX_TSO_CSO_OUTER_L4_LBN 105 +#define ESF_GZ_TX_TSO_CSO_OUTER_L4_WIDTH 1 +#define ESF_GZ_TX_TSO_CSO_OUTER_L3_LBN 104 +#define ESF_GZ_TX_TSO_CSO_OUTER_L3_WIDTH 1 +#define ESF_GZ_TX_TSO_CSO_INNER_L3_LBN 101 +#define ESF_GZ_TX_TSO_CSO_INNER_L3_WIDTH 3 +#define ESF_GZ_TX_TSO_RSVD_LBN 94 +#define ESF_GZ_TX_TSO_RSVD_WIDTH 7 +#define ESF_GZ_TX_TSO_CSO_INNER_L4_LBN 93 +#define ESF_GZ_TX_TSO_CSO_INNER_L4_WIDTH 1 +#define ESF_GZ_TX_TSO_INNER_L4_OFF_W_LBN 85 +#define ESF_GZ_TX_TSO_INNER_L4_OFF_W_WIDTH 8 +#define ESF_GZ_TX_TSO_INNER_L3_OFF_W_LBN 77 +#define ESF_GZ_TX_TSO_INNER_L3_OFF_W_WIDTH 8 +#define ESF_GZ_TX_TSO_OUTER_L4_OFF_W_LBN 69 +#define ESF_GZ_TX_TSO_OUTER_L4_OFF_W_WIDTH 8 +#define ESF_GZ_TX_TSO_OUTER_L3_OFF_W_LBN 64 +#define ESF_GZ_TX_TSO_OUTER_L3_OFF_W_WIDTH 5 +#define ESF_GZ_TX_TSO_PAYLOAD_LEN_LBN 42 +#define ESF_GZ_TX_TSO_PAYLOAD_LEN_WIDTH 22 +#define ESF_GZ_TX_TSO_HDR_LEN_W_LBN 34 +#define ESF_GZ_TX_TSO_HDR_LEN_W_WIDTH 8 +#define ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN_LBN 33 +#define ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN_WIDTH 1 +#define ESF_GZ_TX_TSO_ED_INNER_IP_LEN_LBN 32 +#define ESF_GZ_TX_TSO_ED_INNER_IP_LEN_WIDTH 1 +#define ESF_GZ_TX_TSO_ED_OUTER_IP_LEN_LBN 31 +#define ESF_GZ_TX_TSO_ED_OUTER_IP_LEN_WIDTH 1 +#define ESF_GZ_TX_TSO_ED_INNER_IP4_ID_LBN 29 +#define ESF_GZ_TX_TSO_ED_INNER_IP4_ID_WIDTH 2 +#define ESF_GZ_TX_TSO_ED_OUTER_IP4_ID_LBN 27 +#define ESF_GZ_TX_TSO_ED_OUTER_IP4_ID_WIDTH 2 +#define ESF_GZ_TX_TSO_PAYLOAD_NUM_SEGS_LBN 17 +#define ESF_GZ_TX_TSO_PAYLOAD_NUM_SEGS_WIDTH 10 +#define ESF_GZ_TX_TSO_HDR_NUM_SEGS_LBN 14 +#define ESF_GZ_TX_TSO_HDR_NUM_SEGS_WIDTH 3 +#define ESF_GZ_TX_TSO_MSS_LBN 0 +#define ESF_GZ_TX_TSO_MSS_WIDTH 14 +#define ESE_GZ_SF_TX_TSO_DSC_FMT_STRUCT_SIZE 124 + + +/* Enum DESIGN_PARAMS */ +#define ESE_EF100_DP_GZ_RX_MAX_RUNT 17 +#define ESE_EF100_DP_GZ_VI_STRIDES 16 +#define ESE_EF100_DP_GZ_NMMU_PAGE_SIZES 15 +#define ESE_EF100_DP_GZ_EVQ_TIMER_TICK_NANOS 14 +#define ESE_EF100_DP_GZ_MEM2MEM_MAX_LEN 13 +#define ESE_EF100_DP_GZ_COMPAT 12 +#define ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES 11 +#define ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS 10 +#define ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN 9 +#define ESE_EF100_DP_GZ_TXQ_SIZE_GRANULARITY 8 +#define ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY 7 +#define ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS 6 +#define ESE_EF100_DP_GZ_TSO_MAX_HDR_LEN 5 +#define ESE_EF100_DP_GZ_RX_L4_CSUM_PROTOCOLS 4 +#define ESE_EF100_DP_GZ_NMMU_GROUP_SIZE 3 +#define ESE_EF100_DP_GZ_EVQ_UNSOL_CREDIT_SEQ_BITS 2 +#define ESE_EF100_DP_GZ_PARTIAL_TSTAMP_SUB_NANO_BITS 1 +#define ESE_EF100_DP_GZ_PAD 0 + +/* Enum DESIGN_PARAM_DEFAULTS */ +#define ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN_DEFAULT 0x3fffff +#define ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES_DEFAULT 8192 +#define ESE_EF100_DP_GZ_MEM2MEM_MAX_LEN_DEFAULT 8192 +#define ESE_EF100_DP_GZ_RX_L4_CSUM_PROTOCOLS_DEFAULT 0x1106 +#define ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS_DEFAULT 0x3ff +#define ESE_EF100_DP_GZ_RX_MAX_RUNT_DEFAULT 640 +#define ESE_EF100_DP_GZ_EVQ_TIMER_TICK_NANOS_DEFAULT 512 +#define ESE_EF100_DP_GZ_NMMU_PAGE_SIZES_DEFAULT 512 +#define ESE_EF100_DP_GZ_TSO_MAX_HDR_LEN_DEFAULT 192 +#define ESE_EF100_DP_GZ_RXQ_SIZE_GRANULARITY_DEFAULT 64 +#define ESE_EF100_DP_GZ_TXQ_SIZE_GRANULARITY_DEFAULT 64 +#define ESE_EF100_DP_GZ_NMMU_GROUP_SIZE_DEFAULT 32 +#define ESE_EF100_DP_GZ_VI_STRIDES_DEFAULT 16 +#define ESE_EF100_DP_GZ_EVQ_UNSOL_CREDIT_SEQ_BITS_DEFAULT 7 +#define ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT 4 +#define ESE_EF100_DP_GZ_PARTIAL_TSTAMP_SUB_NANO_BITS_DEFAULT 2 +#define ESE_EF100_DP_GZ_COMPAT_DEFAULT 0 + +/* Enum HOST_IF_CONSTANTS */ +#define ESE_GZ_FCW_LEN 0x4C +#define ESE_GZ_RX_PKT_PREFIX_LEN 22 + +/* Enum PCI_CONSTANTS */ +#define ESE_GZ_PCI_BASE_CONFIG_SPACE_SIZE 256 +#define ESE_GZ_PCI_EXPRESS_XCAP_HDR_SIZE 4 + +/* Enum RH_HCLASS_L2_CLASS */ +#define ESE_GZ_RH_HCLASS_L2_CLASS_E2_0123VLAN 1 +#define ESE_GZ_RH_HCLASS_L2_CLASS_OTHER 0 + +/* Enum RH_HCLASS_L2_STATUS */ +#define ESE_GZ_RH_HCLASS_L2_STATUS_RESERVED 3 +#define ESE_GZ_RH_HCLASS_L2_STATUS_FCS_ERR 2 +#define ESE_GZ_RH_HCLASS_L2_STATUS_LEN_ERR 1 +#define ESE_GZ_RH_HCLASS_L2_STATUS_OK 0 + +/* Enum RH_HCLASS_L3_CLASS */ +#define ESE_GZ_RH_HCLASS_L3_CLASS_OTHER 3 +#define ESE_GZ_RH_HCLASS_L3_CLASS_IP6 2 +#define ESE_GZ_RH_HCLASS_L3_CLASS_IP4BAD 1 +#define ESE_GZ_RH_HCLASS_L3_CLASS_IP4GOOD 0 + +/* Enum RH_HCLASS_L4_CLASS */ +#define ESE_GZ_RH_HCLASS_L4_CLASS_OTHER 3 +#define ESE_GZ_RH_HCLASS_L4_CLASS_FRAG 2 +#define ESE_GZ_RH_HCLASS_L4_CLASS_UDP 1 +#define ESE_GZ_RH_HCLASS_L4_CLASS_TCP 0 + +/* Enum RH_HCLASS_L4_CSUM */ +#define ESE_GZ_RH_HCLASS_L4_CSUM_GOOD 1 +#define ESE_GZ_RH_HCLASS_L4_CSUM_BAD_OR_UNKNOWN 0 + +/* Enum RH_HCLASS_TUNNEL_CLASS */ +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_RESERVED_7 7 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_RESERVED_6 6 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_RESERVED_5 5 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_RESERVED_4 4 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_GENEVE 3 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_NVGRE 2 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_VXLAN 1 +#define ESE_GZ_RH_HCLASS_TUNNEL_CLASS_NONE 0 + +/* Enum TX_DESC_CSO_PARTIAL_EN */ +#define ESE_GZ_TX_DESC_CSO_PARTIAL_EN_TCP 2 +#define ESE_GZ_TX_DESC_CSO_PARTIAL_EN_UDP 1 +#define ESE_GZ_TX_DESC_CSO_PARTIAL_EN_OFF 0 + +/* Enum TX_DESC_CS_INNER_L3 */ +#define ESE_GZ_TX_DESC_CS_INNER_L3_GENEVE 3 +#define ESE_GZ_TX_DESC_CS_INNER_L3_NVGRE 2 +#define ESE_GZ_TX_DESC_CS_INNER_L3_VXLAN 1 +#define ESE_GZ_TX_DESC_CS_INNER_L3_OFF 0 + +/* Enum TX_DESC_IP4_ID */ +#define ESE_GZ_TX_DESC_IP4_ID_INC_MOD16 2 +#define ESE_GZ_TX_DESC_IP4_ID_INC_MOD15 1 +#define ESE_GZ_TX_DESC_IP4_ID_NO_OP 0 +/**************************************************************************/ + +#define ESF_GZ_EV_DEBUG_EVENT_GEN_FLAGS_LBN 44 +#define ESF_GZ_EV_DEBUG_EVENT_GEN_FLAGS_WIDTH 4 +#define ESF_GZ_EV_DEBUG_SRC_QID_LBN 32 +#define ESF_GZ_EV_DEBUG_SRC_QID_WIDTH 12 +#define ESF_GZ_EV_DEBUG_SEQ_NUM_LBN 16 +#define ESF_GZ_EV_DEBUG_SEQ_NUM_WIDTH 16 + +#endif /* EFX_EF100_REGS_H */ diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c new file mode 100644 index 000000000000..13ba1a4f66fc --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_rx.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2005-2019 Solarflare Communications Inc. + * + * 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, incorporated herein by reference. + */ + +#include "net_driver.h" +#include "ef100_rx.h" +#include "rx_common.h" +#include "efx.h" +#include "nic_common.h" +#include "mcdi_functions.h" +#include "ef100_regs.h" +#include "ef100_nic.h" +#include "io.h" + +/* Get the value of a field in the RX prefix */ +#define PREFIX_OFFSET_W(_f) (ESF_GZ_RX_PREFIX_ ## _f ## _LBN / 32) +#define PREFIX_OFFSET_B(_f) (ESF_GZ_RX_PREFIX_ ## _f ## _LBN % 32) +#define PREFIX_WIDTH_MASK(_f) ((1UL << ESF_GZ_RX_PREFIX_ ## _f ## _WIDTH) - 1) +#define PREFIX_WORD(_p, _f) le32_to_cpu((__force __le32)(_p)[PREFIX_OFFSET_W(_f)]) +#define PREFIX_FIELD(_p, _f) ((PREFIX_WORD(_p, _f) >> PREFIX_OFFSET_B(_f)) & \ + PREFIX_WIDTH_MASK(_f)) + +#define ESF_GZ_RX_PREFIX_NT_OR_INNER_L3_CLASS_LBN \ + (ESF_GZ_RX_PREFIX_CLASS_LBN + ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_LBN) +#define ESF_GZ_RX_PREFIX_NT_OR_INNER_L3_CLASS_WIDTH \ + ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_WIDTH + +static bool check_fcs(struct efx_channel *channel, u32 *prefix) +{ + u16 rxclass; + u8 l2status; + + rxclass = le16_to_cpu((__force __le16)PREFIX_FIELD(prefix, CLASS)); + l2status = PREFIX_FIELD(&rxclass, HCLASS_L2_STATUS); + + if (likely(l2status == ESE_GZ_RH_HCLASS_L2_STATUS_OK)) + /* Everything is ok */ + return 0; + + if (l2status == ESE_GZ_RH_HCLASS_L2_STATUS_FCS_ERR) + channel->n_rx_eth_crc_err++; + return 1; +} + +void __ef100_rx_packet(struct efx_channel *channel) +{ + struct efx_rx_buffer *rx_buf = efx_rx_buffer(&channel->rx_queue, channel->rx_pkt_index); + struct efx_nic *efx = channel->efx; + u8 *eh = efx_rx_buf_va(rx_buf); + __wsum csum = 0; + u32 *prefix; + + prefix = (u32 *)(eh - ESE_GZ_RX_PKT_PREFIX_LEN); + + if (check_fcs(channel, prefix) && + unlikely(!(efx->net_dev->features & NETIF_F_RXALL))) + goto out; + + rx_buf->len = le16_to_cpu((__force __le16)PREFIX_FIELD(prefix, LENGTH)); + if (rx_buf->len <= sizeof(struct ethhdr)) { + if (net_ratelimit()) + netif_err(channel->efx, rx_err, channel->efx->net_dev, + "RX packet too small (%d)\n", rx_buf->len); + ++channel->n_rx_frm_trunc; + goto out; + } + + if (likely(efx->net_dev->features & NETIF_F_RXCSUM)) { + if (PREFIX_FIELD(prefix, NT_OR_INNER_L3_CLASS) == 1) { + ++channel->n_rx_ip_hdr_chksum_err; + } else { + u16 sum = be16_to_cpu((__force __be16)PREFIX_FIELD(prefix, CSUM_FRAME)); + + csum = (__force __wsum) sum; + } + } + + if (channel->type->receive_skb) { + struct efx_rx_queue *rx_queue = + efx_channel_get_rx_queue(channel); + + /* no support for special channels yet, so just discard */ + WARN_ON_ONCE(1); + efx_free_rx_buffers(rx_queue, rx_buf, 1); + goto out; + } + + efx_rx_packet_gro(channel, rx_buf, channel->rx_pkt_n_frags, eh, csum); + +out: + channel->rx_pkt_n_frags = 0; +} + +static void ef100_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index) +{ + struct efx_rx_buffer *rx_buf = efx_rx_buffer(rx_queue, index); + struct efx_channel *channel = efx_rx_queue_channel(rx_queue); + struct efx_nic *efx = rx_queue->efx; + + ++rx_queue->rx_packets; + + netif_vdbg(efx, rx_status, efx->net_dev, + "RX queue %d received id %x\n", + efx_rx_queue_index(rx_queue), index); + + efx_sync_rx_buffer(efx, rx_buf, efx->rx_dma_len); + + prefetch(efx_rx_buf_va(rx_buf)); + + rx_buf->page_offset += efx->rx_prefix_size; + + efx_recycle_rx_pages(channel, rx_buf, 1); + + efx_rx_flush_packet(channel); + channel->rx_pkt_n_frags = 1; + channel->rx_pkt_index = index; +} + +void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event) +{ + struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel); + unsigned int n_packets = + EFX_QWORD_FIELD(*p_event, ESF_GZ_EV_RXPKTS_NUM_PKT); + int i; + + WARN_ON_ONCE(!n_packets); + if (n_packets > 1) + ++channel->n_rx_merge_events; + + channel->irq_mod_score += 2 * n_packets; + + for (i = 0; i < n_packets; ++i) { + ef100_rx_packet(rx_queue, + rx_queue->removed_count & rx_queue->ptr_mask); + ++rx_queue->removed_count; + } +} + +void ef100_rx_write(struct efx_rx_queue *rx_queue) +{ + struct efx_rx_buffer *rx_buf; + unsigned int idx; + efx_qword_t *rxd; + efx_dword_t rxdb; + + while (rx_queue->notified_count != rx_queue->added_count) { + idx = rx_queue->notified_count & rx_queue->ptr_mask; + rx_buf = efx_rx_buffer(rx_queue, idx); + rxd = efx_rx_desc(rx_queue, idx); + + EFX_POPULATE_QWORD_1(*rxd, ESF_GZ_RX_BUF_ADDR, rx_buf->dma_addr); + + ++rx_queue->notified_count; + } + + wmb(); + EFX_POPULATE_DWORD_1(rxdb, ERF_GZ_RX_RING_PIDX, + rx_queue->added_count & rx_queue->ptr_mask); + efx_writed_page(rx_queue->efx, &rxdb, + ER_GZ_RX_RING_DOORBELL, efx_rx_queue_index(rx_queue)); +} diff --git a/drivers/net/ethernet/sfc/ef100_rx.h b/drivers/net/ethernet/sfc/ef100_rx.h new file mode 100644 index 000000000000..f2f266863966 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_rx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2019 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#ifndef EFX_EF100_RX_H +#define EFX_EF100_RX_H + +#include "net_driver.h" + +void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event); +void ef100_rx_write(struct efx_rx_queue *rx_queue); +void __ef100_rx_packet(struct efx_channel *channel); + +#endif diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c new file mode 100644 index 000000000000..a09546e43408 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0-only +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2018 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#include <net/ip6_checksum.h> + +#include "net_driver.h" +#include "tx_common.h" +#include "nic_common.h" +#include "mcdi_functions.h" +#include "ef100_regs.h" +#include "io.h" +#include "ef100_tx.h" +#include "ef100_nic.h" + +int ef100_tx_probe(struct efx_tx_queue *tx_queue) +{ + /* Allocate an extra descriptor for the QMDA status completion entry */ + return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd.buf, + (tx_queue->ptr_mask + 2) * + sizeof(efx_oword_t), + GFP_KERNEL); + return 0; +} + +void ef100_tx_init(struct efx_tx_queue *tx_queue) +{ + /* must be the inverse of lookup in efx_get_tx_channel */ + tx_queue->core_txq = + netdev_get_tx_queue(tx_queue->efx->net_dev, + tx_queue->channel->channel - + tx_queue->efx->tx_channel_offset); + + if (efx_mcdi_tx_init(tx_queue, false)) + netdev_WARN(tx_queue->efx->net_dev, + "failed to initialise TXQ %d\n", tx_queue->queue); +} + +static bool ef100_tx_can_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +{ + struct efx_nic *efx = tx_queue->efx; + struct ef100_nic_data *nic_data; + struct efx_tx_buffer *buffer; + struct tcphdr *tcphdr; + struct iphdr *iphdr; + size_t header_len; + u32 mss; + + nic_data = efx->nic_data; + + if (!skb_is_gso_tcp(skb)) + return false; + if (!(efx->net_dev->features & NETIF_F_TSO)) + return false; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(mss < 4)) { + WARN_ONCE(1, "MSS of %u is too small for TSO\n", mss); + return false; + } + + header_len = efx_tx_tso_header_length(skb); + if (header_len > nic_data->tso_max_hdr_len) + return false; + + if (skb_shinfo(skb)->gso_segs > nic_data->tso_max_payload_num_segs) { + /* net_dev->gso_max_segs should've caught this */ + WARN_ON_ONCE(1); + return false; + } + + if (skb->data_len / mss > nic_data->tso_max_frames) + return false; + + /* net_dev->gso_max_size should've caught this */ + if (WARN_ON_ONCE(skb->data_len > nic_data->tso_max_payload_len)) + return false; + + /* Reserve an empty buffer for the TSO V3 descriptor. + * Convey the length of the header since we already know it. + */ + buffer = efx_tx_queue_get_insert_buffer(tx_queue); + buffer->flags = EFX_TX_BUF_TSO_V3 | EFX_TX_BUF_CONT; + buffer->len = header_len; + buffer->unmap_len = 0; + buffer->skb = skb; + ++tx_queue->insert_count; + + /* Adjust the TCP checksum to exclude the total length, since we set + * ED_INNER_IP_LEN in the descriptor. + */ + tcphdr = tcp_hdr(skb); + if (skb_is_gso_v6(skb)) { + tcphdr->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } else { + iphdr = ip_hdr(skb); + tcphdr->check = ~csum_tcpudp_magic(iphdr->saddr, iphdr->daddr, + 0, IPPROTO_TCP, 0); + } + return true; +} + +static efx_oword_t *ef100_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index) +{ + if (likely(tx_queue->txd.buf.addr)) + return ((efx_oword_t *)tx_queue->txd.buf.addr) + index; + else + return NULL; +} + +void ef100_notify_tx_desc(struct efx_tx_queue *tx_queue) +{ + unsigned int write_ptr; + efx_dword_t reg; + + if (unlikely(tx_queue->notify_count == tx_queue->write_count)) + return; + + write_ptr = tx_queue->write_count & tx_queue->ptr_mask; + /* The write pointer goes into the high word */ + EFX_POPULATE_DWORD_1(reg, ERF_GZ_TX_RING_PIDX, write_ptr); + efx_writed_page(tx_queue->efx, ®, + ER_GZ_TX_RING_DOORBELL, tx_queue->queue); + tx_queue->notify_count = tx_queue->write_count; + tx_queue->xmit_more_available = false; +} + +static void ef100_tx_push_buffers(struct efx_tx_queue *tx_queue) +{ + ef100_notify_tx_desc(tx_queue); + ++tx_queue->pushes; +} + +static void ef100_set_tx_csum_partial(const struct sk_buff *skb, + struct efx_tx_buffer *buffer, efx_oword_t *txd) +{ + efx_oword_t csum; + int csum_start; + + if (!skb || skb->ip_summed != CHECKSUM_PARTIAL) + return; + + /* skb->csum_start has the offset from head, but we need the offset + * from data. + */ + csum_start = skb_checksum_start_offset(skb); + EFX_POPULATE_OWORD_3(csum, + ESF_GZ_TX_SEND_CSO_PARTIAL_EN, 1, + ESF_GZ_TX_SEND_CSO_PARTIAL_START_W, + csum_start >> 1, + ESF_GZ_TX_SEND_CSO_PARTIAL_CSUM_W, + skb->csum_offset >> 1); + EFX_OR_OWORD(*txd, *txd, csum); +} + +static void ef100_set_tx_hw_vlan(const struct sk_buff *skb, efx_oword_t *txd) +{ + u16 vlan_tci = skb_vlan_tag_get(skb); + efx_oword_t vlan; + + EFX_POPULATE_OWORD_2(vlan, + ESF_GZ_TX_SEND_VLAN_INSERT_EN, 1, + ESF_GZ_TX_SEND_VLAN_INSERT_TCI, vlan_tci); + EFX_OR_OWORD(*txd, *txd, vlan); +} + +static void ef100_make_send_desc(struct efx_nic *efx, + const struct sk_buff *skb, + struct efx_tx_buffer *buffer, efx_oword_t *txd, + unsigned int segment_count) +{ + /* TX send descriptor */ + EFX_POPULATE_OWORD_3(*txd, + ESF_GZ_TX_SEND_NUM_SEGS, segment_count, + ESF_GZ_TX_SEND_LEN, buffer->len, + ESF_GZ_TX_SEND_ADDR, buffer->dma_addr); + + if (likely(efx->net_dev->features & NETIF_F_HW_CSUM)) + ef100_set_tx_csum_partial(skb, buffer, txd); + if (efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX && + skb && skb_vlan_tag_present(skb)) + ef100_set_tx_hw_vlan(skb, txd); +} + +static void ef100_make_tso_desc(struct efx_nic *efx, + const struct sk_buff *skb, + struct efx_tx_buffer *buffer, efx_oword_t *txd, + unsigned int segment_count) +{ + u32 mangleid = (efx->net_dev->features & NETIF_F_TSO_MANGLEID) || + skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID ? + ESE_GZ_TX_DESC_IP4_ID_NO_OP : + ESE_GZ_TX_DESC_IP4_ID_INC_MOD16; + u16 vlan_enable = efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX ? + skb_vlan_tag_present(skb) : 0; + unsigned int len, ip_offset, tcp_offset, payload_segs; + u16 vlan_tci = skb_vlan_tag_get(skb); + u32 mss = skb_shinfo(skb)->gso_size; + + len = skb->len - buffer->len; + /* We use 1 for the TSO descriptor and 1 for the header */ + payload_segs = segment_count - 2; + ip_offset = skb_network_offset(skb); + tcp_offset = skb_transport_offset(skb); + + EFX_POPULATE_OWORD_13(*txd, + ESF_GZ_TX_DESC_TYPE, ESE_GZ_TX_DESC_TYPE_TSO, + ESF_GZ_TX_TSO_MSS, mss, + ESF_GZ_TX_TSO_HDR_NUM_SEGS, 1, + ESF_GZ_TX_TSO_PAYLOAD_NUM_SEGS, payload_segs, + ESF_GZ_TX_TSO_HDR_LEN_W, buffer->len >> 1, + ESF_GZ_TX_TSO_PAYLOAD_LEN, len, + ESF_GZ_TX_TSO_CSO_INNER_L4, 1, + ESF_GZ_TX_TSO_INNER_L3_OFF_W, ip_offset >> 1, + ESF_GZ_TX_TSO_INNER_L4_OFF_W, tcp_offset >> 1, + ESF_GZ_TX_TSO_ED_INNER_IP4_ID, mangleid, + ESF_GZ_TX_TSO_ED_INNER_IP_LEN, 1, + ESF_GZ_TX_TSO_VLAN_INSERT_EN, vlan_enable, + ESF_GZ_TX_TSO_VLAN_INSERT_TCI, vlan_tci + ); +} + +static void ef100_tx_make_descriptors(struct efx_tx_queue *tx_queue, + const struct sk_buff *skb, + unsigned int segment_count) +{ + unsigned int old_write_count = tx_queue->write_count; + unsigned int new_write_count = old_write_count; + struct efx_tx_buffer *buffer; + unsigned int next_desc_type; + unsigned int write_ptr; + efx_oword_t *txd; + unsigned int nr_descs = tx_queue->insert_count - old_write_count; + + if (unlikely(nr_descs == 0)) + return; + + if (segment_count) + next_desc_type = ESE_GZ_TX_DESC_TYPE_TSO; + else + next_desc_type = ESE_GZ_TX_DESC_TYPE_SEND; + + /* if it's a raw write (such as XDP) then always SEND single frames */ + if (!skb) + nr_descs = 1; + + do { + write_ptr = new_write_count & tx_queue->ptr_mask; + buffer = &tx_queue->buffer[write_ptr]; + txd = ef100_tx_desc(tx_queue, write_ptr); + ++new_write_count; + + /* Create TX descriptor ring entry */ + tx_queue->packet_write_count = new_write_count; + + switch (next_desc_type) { + case ESE_GZ_TX_DESC_TYPE_SEND: + ef100_make_send_desc(tx_queue->efx, skb, + buffer, txd, nr_descs); + break; + case ESE_GZ_TX_DESC_TYPE_TSO: + /* TX TSO descriptor */ + WARN_ON_ONCE(!(buffer->flags & EFX_TX_BUF_TSO_V3)); + ef100_make_tso_desc(tx_queue->efx, skb, + buffer, txd, nr_descs); + break; + default: + /* TX segment descriptor */ + EFX_POPULATE_OWORD_3(*txd, + ESF_GZ_TX_DESC_TYPE, ESE_GZ_TX_DESC_TYPE_SEG, + ESF_GZ_TX_SEG_LEN, buffer->len, + ESF_GZ_TX_SEG_ADDR, buffer->dma_addr); + } + /* if it's a raw write (such as XDP) then always SEND */ + next_desc_type = skb ? ESE_GZ_TX_DESC_TYPE_SEG : + ESE_GZ_TX_DESC_TYPE_SEND; + + } while (new_write_count != tx_queue->insert_count); + + wmb(); /* Ensure descriptors are written before they are fetched */ + + tx_queue->write_count = new_write_count; + + /* The write_count above must be updated before reading + * channel->holdoff_doorbell to avoid a race with the + * completion path, so ensure these operations are not + * re-ordered. This also flushes the update of write_count + * back into the cache. + */ + smp_mb(); +} + +void ef100_tx_write(struct efx_tx_queue *tx_queue) +{ + ef100_tx_make_descriptors(tx_queue, NULL, 0); + ef100_tx_push_buffers(tx_queue); +} + +void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event) +{ + unsigned int tx_done = + EFX_QWORD_FIELD(*p_event, ESF_GZ_EV_TXCMPL_NUM_DESC); + unsigned int qlabel = + EFX_QWORD_FIELD(*p_event, ESF_GZ_EV_TXCMPL_Q_LABEL); + struct efx_tx_queue *tx_queue = + efx_channel_get_tx_queue(channel, qlabel); + unsigned int tx_index = (tx_queue->read_count + tx_done - 1) & + tx_queue->ptr_mask; + + efx_xmit_done(tx_queue, tx_index); +} + +/* Add a socket buffer to a TX queue + * + * You must hold netif_tx_lock() to call this function. + * + * Returns 0 on success, error code otherwise. In case of an error this + * function will free the SKB. + */ +int ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +{ + unsigned int old_insert_count = tx_queue->insert_count; + struct efx_nic *efx = tx_queue->efx; + bool xmit_more = netdev_xmit_more(); + unsigned int fill_level; + unsigned int segments; + int rc; + + if (!tx_queue->buffer || !tx_queue->ptr_mask) { + netif_stop_queue(efx->net_dev); + dev_kfree_skb_any(skb); + return -ENODEV; + } + + segments = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 0; + if (segments == 1) + segments = 0; /* Don't use TSO/GSO for a single segment. */ + if (segments && !ef100_tx_can_tso(tx_queue, skb)) { + rc = efx_tx_tso_fallback(tx_queue, skb); + tx_queue->tso_fallbacks++; + if (rc) + goto err; + else + return 0; + } + + /* Map for DMA and create descriptors */ + rc = efx_tx_map_data(tx_queue, skb, segments); + if (rc) + goto err; + ef100_tx_make_descriptors(tx_queue, skb, segments); + + fill_level = efx_channel_tx_fill_level(tx_queue->channel); + if (fill_level > efx->txq_stop_thresh) { + netif_tx_stop_queue(tx_queue->core_txq); + /* Re-read after a memory barrier in case we've raced with + * the completion path. Otherwise there's a danger we'll never + * restart the queue if all completions have just happened. + */ + smp_mb(); + fill_level = efx_channel_tx_fill_level(tx_queue->channel); + if (fill_level < efx->txq_stop_thresh) + netif_tx_start_queue(tx_queue->core_txq); + } + + if (__netdev_tx_sent_queue(tx_queue->core_txq, skb->len, xmit_more)) + tx_queue->xmit_more_available = false; /* push doorbell */ + else if (tx_queue->write_count - tx_queue->notify_count > 255) + /* Ensure we never push more than 256 packets at once */ + tx_queue->xmit_more_available = false; /* push */ + else + tx_queue->xmit_more_available = true; /* don't push yet */ + + if (!tx_queue->xmit_more_available) + ef100_tx_push_buffers(tx_queue); + + if (segments) { + tx_queue->tso_bursts++; + tx_queue->tso_packets += segments; + tx_queue->tx_packets += segments; + } else { + tx_queue->tx_packets++; + } + return 0; + +err: + efx_enqueue_unwind(tx_queue, old_insert_count); + if (!IS_ERR_OR_NULL(skb)) + dev_kfree_skb_any(skb); + + /* If we're not expecting another transmit and we had something to push + * on this queue then we need to push here to get the previous packets + * out. We only enter this branch from before the 'Update BQL' section + * above, so xmit_more_available still refers to the old state. + */ + if (tx_queue->xmit_more_available && !xmit_more) + ef100_tx_push_buffers(tx_queue); + return rc; +} diff --git a/drivers/net/ethernet/sfc/ef100_tx.h b/drivers/net/ethernet/sfc/ef100_tx.h new file mode 100644 index 000000000000..fa23e430bdd7 --- /dev/null +++ b/drivers/net/ethernet/sfc/ef100_tx.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/**************************************************************************** + * Driver for Solarflare network controllers and boards + * Copyright 2019 Solarflare Communications Inc. + * Copyright 2019-2020 Xilinx Inc. + * + * 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, incorporated herein by reference. + */ + +#ifndef EFX_EF100_TX_H +#define EFX_EF100_TX_H + +#include "net_driver.h" + +int ef100_tx_probe(struct efx_tx_queue *tx_queue); +void ef100_tx_init(struct efx_tx_queue *tx_queue); +void ef100_tx_write(struct efx_tx_queue *tx_queue); +void ef100_notify_tx_desc(struct efx_tx_queue *tx_queue); +unsigned int ef100_tx_max_skb_descs(struct efx_nic *efx); + +void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event); + +netdev_tx_t ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); +#endif diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index d60acaa3879d..e06fa89f2d72 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -25,6 +25,7 @@ #include "efx.h" #include "efx_common.h" #include "efx_channels.h" +#include "ef100.h" #include "rx_common.h" #include "tx_common.h" #include "nic.h" @@ -1355,8 +1356,14 @@ static int __init efx_init_module(void) if (rc < 0) goto err_pci; + rc = pci_register_driver(&ef100_pci_driver); + if (rc < 0) + goto err_pci_ef100; + return 0; + err_pci_ef100: + pci_unregister_driver(&efx_pci_driver); err_pci: efx_destroy_reset_workqueue(); err_reset: @@ -1373,6 +1380,7 @@ static void __exit efx_exit_module(void) { printk(KERN_INFO "Solarflare NET driver unloading\n"); + pci_unregister_driver(&ef100_pci_driver); pci_unregister_driver(&efx_pci_driver); efx_destroy_reset_workqueue(); #ifdef CONFIG_SFC_SRIOV diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index e7e7d8d1a07b..a9808e86068d 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -8,7 +8,10 @@ #ifndef EFX_EFX_H #define EFX_EFX_H +#include <linux/indirect_call_wrapper.h> #include "net_driver.h" +#include "ef100_rx.h" +#include "ef100_tx.h" #include "filter.h" int efx_net_open(struct net_device *net_dev); @@ -18,13 +21,18 @@ int efx_net_stop(struct net_device *net_dev); void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue); netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); -netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); +netdev_tx_t __efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); +static inline netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +{ + return INDIRECT_CALL_2(tx_queue->efx->type->tx_enqueue, + ef100_enqueue_skb, __efx_enqueue_skb, + tx_queue, skb); +} void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); void efx_xmit_done_single(struct efx_tx_queue *tx_queue); int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type, void *type_data); extern unsigned int efx_piobuf_size; -extern bool efx_separate_tx_channels; /* RX */ void __efx_rx_packet(struct efx_channel *channel); @@ -33,7 +41,9 @@ void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index, static inline void efx_rx_flush_packet(struct efx_channel *channel) { if (channel->rx_pkt_n_frags) - __efx_rx_packet(channel); + INDIRECT_CALL_2(channel->efx->type->rx_packet, + __ef100_rx_packet, __efx_rx_packet, + channel); } /* Maximum number of TCP segments we support for soft-TSO */ diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index 5667694c6514..26b05ec4e712 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -814,14 +814,18 @@ fail: */ int efx_reset(struct efx_nic *efx, enum reset_type method) { + int rc, rc2 = 0; bool disabled; - int rc, rc2; netif_info(efx, drv, efx->net_dev, "resetting (%s)\n", RESET_TYPE(method)); efx_device_detach_sync(efx); - efx_reset_down(efx, method); + /* efx_reset_down() grabs locks that prevent recovery on EF100. + * EF100 reset is handled in the efx_nic_type callback below. + */ + if (efx_nic_rev(efx) != EFX_REV_EF100) + efx_reset_down(efx, method); rc = efx->type->reset(efx, method); if (rc) { @@ -849,7 +853,8 @@ out: disabled = rc || method == RESET_TYPE_DISABLE || method == RESET_TYPE_RECOVER_OR_DISABLE; - rc2 = efx_reset_up(efx, method, !disabled); + if (efx_nic_rev(efx) != EFX_REV_EF100) + rc2 = efx_reset_up(efx, method, !disabled); if (rc2) { disabled = true; if (!rc) diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 9828516bd82d..4ffda7782f68 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -221,8 +221,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev, return 0; } -const char *efx_driver_name = KBUILD_MODNAME; - const struct ethtool_ops efx_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USECS_IRQ | @@ -232,7 +230,6 @@ const struct ethtool_ops efx_ethtool_ops = { .get_regs = efx_ethtool_get_regs, .get_msglevel = efx_ethtool_get_msglevel, .set_msglevel = efx_ethtool_set_msglevel, - .nway_reset = efx_ethtool_nway_reset, .get_link = ethtool_op_get_link, .get_coalesce = efx_ethtool_get_coalesce, .set_coalesce = efx_ethtool_set_coalesce, diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index e9a5a66529bf..05ac87807929 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -104,7 +104,7 @@ void efx_ethtool_get_drvinfo(struct net_device *net_dev, { struct efx_nic *efx = netdev_priv(net_dev); - strlcpy(info->driver, efx_driver_name, sizeof(info->driver)); + strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); strlcpy(info->version, EFX_DRIVER_VERSION, sizeof(info->version)); efx_mcdi_print_fwver(efx, info->fw_version, sizeof(info->fw_version)); @@ -173,14 +173,6 @@ fail: test->flags |= ETH_TEST_FL_FAILED; } -/* Restart autonegotiation */ -int efx_ethtool_nway_reset(struct net_device *net_dev) -{ - struct efx_nic *efx = netdev_priv(net_dev); - - return mdio45_nway_restart(&efx->mdio); -} - void efx_ethtool_get_pauseparam(struct net_device *net_dev, struct ethtool_pauseparam *pause) { diff --git a/drivers/net/ethernet/sfc/ethtool_common.h b/drivers/net/ethernet/sfc/ethtool_common.h index 3f3aaa92fbb5..659491932101 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.h +++ b/drivers/net/ethernet/sfc/ethtool_common.h @@ -11,15 +11,12 @@ #ifndef EFX_ETHTOOL_COMMON_H #define EFX_ETHTOOL_COMMON_H -extern const char *efx_driver_name; - void efx_ethtool_get_drvinfo(struct net_device *net_dev, struct ethtool_drvinfo *info); u32 efx_ethtool_get_msglevel(struct net_device *net_dev); void efx_ethtool_set_msglevel(struct net_device *net_dev, u32 msg_enable); void efx_ethtool_self_test(struct net_device *net_dev, struct ethtool_test *test, u64 *data); -int efx_ethtool_nway_reset(struct net_device *net_dev); void efx_ethtool_get_pauseparam(struct net_device *net_dev, struct ethtool_pauseparam *pause); int efx_ethtool_set_pauseparam(struct net_device *net_dev, diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h index c3c011bc6a68..30439cc83a89 100644 --- a/drivers/net/ethernet/sfc/io.h +++ b/drivers/net/ethernet/sfc/io.h @@ -75,6 +75,11 @@ #endif #endif +static inline u32 efx_reg(struct efx_nic *efx, unsigned int reg) +{ + return efx->reg_base + reg; +} + #ifdef EFX_USE_QWORD_IO static inline void _efx_writeq(struct efx_nic *efx, __le64 value, unsigned int reg) @@ -217,8 +222,11 @@ static inline void efx_reado_table(struct efx_nic *efx, efx_oword_t *value, efx_reado(efx, value, reg + index * sizeof(efx_oword_t)); } -/* default VI stride (step between per-VI registers) is 8K */ -#define EFX_DEFAULT_VI_STRIDE 0x2000 +/* default VI stride (step between per-VI registers) is 8K on EF10 and + * 64K on EF100 + */ +#define EFX_DEFAULT_VI_STRIDE 0x2000 +#define EF100_DEFAULT_VI_STRIDE 0x10000 /* Calculate offset to page-mapped register */ static inline unsigned int efx_paged_reg(struct efx_nic *efx, unsigned int page, @@ -265,7 +273,9 @@ _efx_writed_page(struct efx_nic *efx, const efx_dword_t *value, #define efx_writed_page(efx, value, reg, page) \ _efx_writed_page(efx, value, \ reg + \ - BUILD_BUG_ON_ZERO((reg) != 0x400 && \ + BUILD_BUG_ON_ZERO((reg) != 0x180 && \ + (reg) != 0x200 && \ + (reg) != 0x400 && \ (reg) != 0x420 && \ (reg) != 0x830 && \ (reg) != 0x83c && \ diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 6c49740a178e..5467819aef6e 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1337,7 +1337,7 @@ void efx_mcdi_process_event(struct efx_channel *channel, efx_mcdi_process_link_change(efx, event); break; case MCDI_EVENT_CODE_SENSOREVT: - efx_mcdi_sensor_event(efx, event); + efx_sensor_event(efx, event); break; case MCDI_EVENT_CODE_SCHEDERR: netif_dbg(efx, hw, efx->net_dev, diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index e053adfe82b0..658cf345420d 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -327,10 +327,10 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field) #define MCDI_CAPABILITY(field) \ - MC_CMD_GET_CAPABILITIES_V4_OUT_ ## field ## _LBN + MC_CMD_GET_CAPABILITIES_V8_OUT_ ## field ## _LBN #define MCDI_CAPABILITY_OFST(field) \ - MC_CMD_GET_CAPABILITIES_V4_OUT_ ## field ## _OFST + MC_CMD_GET_CAPABILITIES_V8_OUT_ ## field ## _OFST #define efx_has_cap(efx, field) \ efx->type->check_caps(efx, \ diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 786fda559976..7bb7ecb480ae 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -173,6 +173,7 @@ struct efx_tx_buffer { #define EFX_TX_BUF_MAP_SINGLE 8 /* buffer was mapped with dma_map_single() */ #define EFX_TX_BUF_OPTION 0x10 /* empty buffer for option descriptor */ #define EFX_TX_BUF_XDP 0x20 /* buffer was sent with XDP */ +#define EFX_TX_BUF_TSO_V3 0x40 /* empty buffer for a TSO_V3 descriptor */ /** * struct efx_tx_queue - An Efx TX queue @@ -245,6 +246,7 @@ struct efx_tx_buffer { * @pio_packets: Number of times the TX PIO feature has been used * @xmit_more_available: Are any packets waiting to be pushed to the NIC * @cb_packets: Number of times the TX copybreak feature has been used + * @notify_count: Count of notified descriptors to the NIC * @empty_read_count: If the completion path has seen the queue as empty * and the transmission path has not yet checked this, the value of * @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0. @@ -292,6 +294,7 @@ struct efx_tx_queue { unsigned int pio_packets; bool xmit_more_available; unsigned int cb_packets; + unsigned int notify_count; /* Statistics to supplement MAC stats */ unsigned long tx_packets; @@ -963,7 +966,9 @@ struct efx_async_filter_insertion { * @vpd_sn: Serial number read from VPD * @xdp_rxq_info_failed: Have any of the rx queues failed to initialise their * xdp_rxq_info structures? + * @netdev_notifier: Netdevice notifier. * @mem_bar: The BAR that is mapped into membase. + * @reg_base: Offset from the start of the bar to the function control window. * @monitor_work: Hardware monitor workitem * @biu_lock: BIU (bus interface unit) lock * @last_irq_cpu: Last CPU to handle a possible test interrupt. This @@ -1141,7 +1146,10 @@ struct efx_nic { char *vpd_sn; bool xdp_rxq_info_failed; + struct notifier_block netdev_notifier; + unsigned int mem_bar; + u32 reg_base; /* The following fields may be written more often */ @@ -1244,6 +1252,7 @@ struct efx_udp_tunnel { * @tx_init: Initialise TX queue on the NIC * @tx_remove: Free resources for TX queue * @tx_write: Write TX descriptors and doorbell + * @tx_enqueue: Add an SKB to TX queue * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC * @rx_pull_rss_config: Read RSS hash key and indirection table back from the NIC * @rx_push_rss_context_config: Write RSS hash key and indirection table for @@ -1255,6 +1264,7 @@ struct efx_udp_tunnel { * @rx_remove: Free resources for RX queue * @rx_write: Write RX descriptors and doorbell * @rx_defer_refill: Generate a refill reminder event + * @rx_packet: Receive the queued RX buffer on a channel * @ev_probe: Allocate resources for event queue * @ev_init: Initialise event queue on the NIC * @ev_fini: Deinitialise event queue on the NIC @@ -1299,6 +1309,7 @@ struct efx_udp_tunnel { * @udp_tnl_push_ports: Push the list of UDP tunnel ports to the NIC if required. * @udp_tnl_has_port: Check if a port has been added as UDP tunnel * @print_additional_fwver: Dump NIC-specific additional FW version info + * @sensor_event: Handle a sensor event from MCDI * @revision: Hardware architecture revision * @txd_ptr_tbl_base: TX descriptor ring base address * @rxd_ptr_tbl_base: RX descriptor ring base address @@ -1379,6 +1390,7 @@ struct efx_nic_type { void (*tx_init)(struct efx_tx_queue *tx_queue); void (*tx_remove)(struct efx_tx_queue *tx_queue); void (*tx_write)(struct efx_tx_queue *tx_queue); + netdev_tx_t (*tx_enqueue)(struct efx_tx_queue *tx_queue, struct sk_buff *skb); unsigned int (*tx_limit_len)(struct efx_tx_queue *tx_queue, dma_addr_t dma_addr, unsigned int len); int (*rx_push_rss_config)(struct efx_nic *efx, bool user, @@ -1396,6 +1408,7 @@ struct efx_nic_type { void (*rx_remove)(struct efx_rx_queue *rx_queue); void (*rx_write)(struct efx_rx_queue *rx_queue); void (*rx_defer_refill)(struct efx_rx_queue *rx_queue); + void (*rx_packet)(struct efx_channel *channel); int (*ev_probe)(struct efx_channel *channel); int (*ev_init)(struct efx_channel *channel); void (*ev_fini)(struct efx_channel *channel); @@ -1470,6 +1483,7 @@ struct efx_nic_type { bool (*udp_tnl_has_port)(struct efx_nic *efx, __be16 port); size_t (*print_additional_fwver)(struct efx_nic *efx, char *buf, size_t len); + void (*sensor_event)(struct efx_nic *efx, efx_qword_t *ev); int revision; unsigned int txd_ptr_tbl_base; @@ -1521,6 +1535,13 @@ efx_get_channel(struct efx_nic *efx, unsigned index) _channel = _channel->channel ? \ (_efx)->channel[_channel->channel - 1] : NULL) +static inline struct efx_channel * +efx_get_tx_channel(struct efx_nic *efx, unsigned int index) +{ + EFX_WARN_ON_ONCE_PARANOID(index >= efx->n_tx_channels); + return efx->channel[efx->tx_channel_offset + index]; +} + static inline struct efx_tx_queue * efx_get_tx_queue(struct efx_nic *efx, unsigned index, unsigned type) { @@ -1651,6 +1672,24 @@ static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb) skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; } +/* Get the max fill level of the TX queues on this channel */ +static inline unsigned int +efx_channel_tx_fill_level(struct efx_channel *channel) +{ + struct efx_tx_queue *tx_queue; + unsigned int fill_level = 0; + + /* This function is currently only used by EF100, which maybe + * could do something simpler and just compute the fill level + * of the single TXQ that's really in use. + */ + efx_for_each_channel_tx_queue(tx_queue, channel) + fill_level = max(fill_level, + tx_queue->insert_count - tx_queue->read_count); + + return fill_level; +} + /* Get all supported features. * If a feature is not fixed, it is present in hw_features. * If a feature is fixed, it does not present in hw_features, but diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h index e04b6817cde3..974107354087 100644 --- a/drivers/net/ethernet/sfc/nic_common.h +++ b/drivers/net/ethernet/sfc/nic_common.h @@ -225,6 +225,12 @@ void efx_nic_event_test_start(struct efx_channel *channel); bool efx_nic_event_present(struct efx_channel *channel); +static inline void efx_sensor_event(struct efx_nic *efx, efx_qword_t *ev) +{ + if (efx->type->sensor_event) + efx->type->sensor_event(efx, ev); +} + /* Some statistics are computed as A - B where A and B each increase * linearly with some hardware counter(s) and the counters are read * asynchronously. If the counters contributing to B are always read diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 393b7cbac8b2..bea4725a4499 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1154,17 +1154,15 @@ static void efx_ptp_drop_time_expired_events(struct efx_nic *efx) /* Drop time-expired events */ spin_lock_bh(&ptp->evt_lock); - if (!list_empty(&ptp->evt_list)) { - list_for_each_safe(cursor, next, &ptp->evt_list) { - struct efx_ptp_event_rx *evt; - - evt = list_entry(cursor, struct efx_ptp_event_rx, - link); - if (time_after(jiffies, evt->expiry)) { - list_move(&evt->link, &ptp->evt_free_list); - netif_warn(efx, hw, efx->net_dev, - "PTP rx event dropped\n"); - } + list_for_each_safe(cursor, next, &ptp->evt_list) { + struct efx_ptp_event_rx *evt; + + evt = list_entry(cursor, struct efx_ptp_event_rx, + link); + if (time_after(jiffies, evt->expiry)) { + list_move(&evt->link, &ptp->evt_free_list); + netif_warn(efx, hw, efx->net_dev, + "PTP rx event dropped\n"); } } spin_unlock_bh(&ptp->evt_lock); diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index 219fb3a0c9d0..a7ea630bb5e6 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -1018,6 +1018,7 @@ const struct efx_nic_type siena_a0_nic_type = { .tx_remove = efx_farch_tx_remove, .tx_write = efx_farch_tx_write, .tx_limit_len = efx_farch_tx_limit_len, + .tx_enqueue = __efx_enqueue_skb, .rx_push_rss_config = siena_rx_push_rss_config, .rx_pull_rss_config = siena_rx_pull_rss_config, .rx_probe = efx_farch_rx_probe, @@ -1025,6 +1026,7 @@ const struct efx_nic_type siena_a0_nic_type = { .rx_remove = efx_farch_rx_remove, .rx_write = efx_farch_rx_write, .rx_defer_refill = efx_farch_rx_defer_refill, + .rx_packet = __efx_rx_packet, .ev_probe = efx_farch_ev_probe, .ev_init = efx_farch_ev_init, .ev_fini = efx_farch_ev_fini, @@ -1096,4 +1098,5 @@ const struct efx_nic_type siena_a0_nic_type = { 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT), .rx_hash_key_size = 16, .check_caps = siena_check_caps, + .sensor_event = efx_mcdi_sensor_event, }; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 1bcf50ab95d9..727201d5eb24 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -284,7 +284,7 @@ static int efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, * Returns NETDEV_TX_OK. * You must hold netif_tx_lock() to call this function. */ -netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +netdev_tx_t __efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) { unsigned int old_insert_count = tx_queue->insert_count; bool xmit_more = netdev_xmit_more(); @@ -503,7 +503,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, } tx_queue = efx_get_tx_queue(efx, index, type); - return efx_enqueue_skb(tx_queue, skb); + return __efx_enqueue_skb(tx_queue, skb); } void efx_xmit_done_single(struct efx_tx_queue *tx_queue) diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index 11b64c609550..793e234819a8 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -71,6 +71,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) "initialising TX queue %d\n", tx_queue->queue); tx_queue->insert_count = 0; + tx_queue->notify_count = 0; tx_queue->write_count = 0; tx_queue->packet_write_count = 0; tx_queue->old_write_count = 0; diff --git a/drivers/net/ethernet/sfc/tx_common.h b/drivers/net/ethernet/sfc/tx_common.h index cbe995b024a6..bbab7f248250 100644 --- a/drivers/net/ethernet/sfc/tx_common.h +++ b/drivers/net/ethernet/sfc/tx_common.h @@ -40,4 +40,6 @@ int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb, unsigned int efx_tx_max_skb_descs(struct efx_nic *efx); int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue, struct sk_buff *skb); + +extern bool efx_separate_tx_channels; #endif diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 6646eba9f57f..6eef0f45b133 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -951,7 +951,7 @@ out_stop: dma_free_coherent(ip->dma_dev, RX_RING_SIZE, ip->rxr, ip->rxr_dma); if (ip->tx_ring) - dma_free_coherent(ip->dma_dev, TX_RING_SIZE, ip->tx_ring, + dma_free_coherent(ip->dma_dev, TX_RING_SIZE + SZ_16K - 1, ip->tx_ring, ip->txr_dma); out_free: free_netdev(dev); @@ -964,7 +964,7 @@ static int ioc3eth_remove(struct platform_device *pdev) struct ioc3_private *ip = netdev_priv(dev); dma_free_coherent(ip->dma_dev, RX_RING_SIZE, ip->rxr, ip->rxr_dma); - dma_free_coherent(ip->dma_dev, TX_RING_SIZE, ip->tx_ring, ip->txr_dma); + dma_free_coherent(ip->dma_dev, TX_RING_SIZE + SZ_16K - 1, ip->tx_ring, ip->txr_dma); unregister_netdev(dev); del_timer_sync(&ip->ioc3_timer); diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index cb043eb1bdc1..f94078f8ebe5 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -1499,15 +1499,13 @@ static void sc92031_remove(struct pci_dev *pdev) pci_disable_device(pdev); } -static int sc92031_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused sc92031_suspend(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(dev_d); struct sc92031_priv *priv = netdev_priv(dev); - pci_save_state(pdev); - if (!netif_running(dev)) - goto out; + return 0; netif_device_detach(dev); @@ -1521,22 +1519,16 @@ static int sc92031_suspend(struct pci_dev *pdev, pm_message_t state) spin_unlock_bh(&priv->lock); -out: - pci_set_power_state(pdev, pci_choose_state(pdev, state)); - return 0; } -static int sc92031_resume(struct pci_dev *pdev) +static int __maybe_unused sc92031_resume(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(dev_d); struct sc92031_priv *priv = netdev_priv(dev); - pci_restore_state(pdev); - pci_set_power_state(pdev, PCI_D0); - if (!netif_running(dev)) - goto out; + return 0; /* Interrupts already disabled by sc92031_suspend */ spin_lock_bh(&priv->lock); @@ -1553,7 +1545,6 @@ static int sc92031_resume(struct pci_dev *pdev) else netif_tx_disable(dev); -out: return 0; } @@ -1565,13 +1556,14 @@ static const struct pci_device_id sc92031_pci_device_id_table[] = { }; MODULE_DEVICE_TABLE(pci, sc92031_pci_device_id_table); +static SIMPLE_DEV_PM_OPS(sc92031_pm_ops, sc92031_suspend, sc92031_resume); + static struct pci_driver sc92031_pci_driver = { .name = SC92031_NAME, .id_table = sc92031_pci_device_id_table, .probe = sc92031_probe, .remove = sc92031_remove, - .suspend = sc92031_suspend, - .resume = sc92031_resume, + .driver.pm = &sc92031_pm_ops, }; module_pci_driver(sc92031_pci_driver); diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 82e020add19f..336105f77313 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -2502,11 +2502,9 @@ static void sis900_remove(struct pci_dev *pci_dev) pci_release_regions(pci_dev); } -#ifdef CONFIG_PM - -static int sis900_suspend(struct pci_dev *pci_dev, pm_message_t state) +static int __maybe_unused sis900_suspend(struct device *dev) { - struct net_device *net_dev = pci_get_drvdata(pci_dev); + struct net_device *net_dev = dev_get_drvdata(dev); struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; @@ -2519,22 +2517,17 @@ static int sis900_suspend(struct pci_dev *pci_dev, pm_message_t state) /* Stop the chip's Tx and Rx Status Machine */ sw32(cr, RxDIS | TxDIS | sr32(cr)); - pci_set_power_state(pci_dev, PCI_D3hot); - pci_save_state(pci_dev); - return 0; } -static int sis900_resume(struct pci_dev *pci_dev) +static int __maybe_unused sis900_resume(struct device *dev) { - struct net_device *net_dev = pci_get_drvdata(pci_dev); + struct net_device *net_dev = dev_get_drvdata(dev); struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; if(!netif_running(net_dev)) return 0; - pci_restore_state(pci_dev); - pci_set_power_state(pci_dev, PCI_D0); sis900_init_rxfilter(net_dev); @@ -2558,17 +2551,15 @@ static int sis900_resume(struct pci_dev *pci_dev) return 0; } -#endif /* CONFIG_PM */ + +static SIMPLE_DEV_PM_OPS(sis900_pm_ops, sis900_suspend, sis900_resume); static struct pci_driver sis900_pci_driver = { .name = SIS900_MODULE_NAME, .id_table = sis900_pci_tbl, .probe = sis900_probe, .remove = sis900_remove, -#ifdef CONFIG_PM - .suspend = sis900_suspend, - .resume = sis900_resume, -#endif /* CONFIG_PM */ + .driver.pm = &sis900_pm_ops, }; static int __init sis900_init_module(void) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index eae11c585025..ac5e8cc5fb9f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -600,9 +600,14 @@ static void stmmac_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct stmmac_priv *priv = netdev_priv(dev); + if (!priv->plat->pmt) + return phylink_ethtool_get_wol(priv->phylink, wol); + mutex_lock(&priv->lock); if (device_can_wakeup(priv->device)) { wol->supported = WAKE_MAGIC | WAKE_UCAST; + if (priv->hw_cap_support && !priv->dma_cap.pmt_magic_frame) + wol->supported &= ~WAKE_MAGIC; wol->wolopts = priv->wolopts; } mutex_unlock(&priv->lock); @@ -613,15 +618,23 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct stmmac_priv *priv = netdev_priv(dev); u32 support = WAKE_MAGIC | WAKE_UCAST; + if (!device_can_wakeup(priv->device)) + return -EOPNOTSUPP; + + if (!priv->plat->pmt) { + int ret = phylink_ethtool_set_wol(priv->phylink, wol); + + if (!ret) + device_set_wakeup_enable(priv->device, !!wol->wolopts); + return ret; + } + /* By default almost all GMAC devices support the WoL via * magic frame but we can disable it if the HW capability * register shows no support for pmt_magic_frame. */ if ((priv->hw_cap_support) && (!priv->dma_cap.pmt_magic_frame)) wol->wolopts &= ~WAKE_MAGIC; - if (!device_can_wakeup(priv->device)) - return -EINVAL; - if (wol->wolopts & ~support) return -EINVAL; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 73677c3b33b6..89b2b3472852 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1075,6 +1075,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) */ static int stmmac_init_phy(struct net_device *dev) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct stmmac_priv *priv = netdev_priv(dev); struct device_node *node; int ret; @@ -1100,6 +1101,9 @@ static int stmmac_init_phy(struct net_device *dev) ret = phylink_connect_phy(priv->phylink, phydev); } + phylink_ethtool_get_wol(priv->phylink, &wol); + device_set_wakeup_capable(priv->device, !!wol.supported); + return ret; } @@ -2819,6 +2823,8 @@ static int stmmac_open(struct net_device *dev) stmmac_init_coalesce(priv); phylink_start(priv->phylink); + /* We may have called phylink_speed_down before */ + phylink_speed_up(priv->phylink); /* Request the IRQ lines */ ret = request_irq(dev->irq, stmmac_interrupt, @@ -2892,6 +2898,8 @@ static int stmmac_release(struct net_device *dev) if (priv->eee_enabled) del_timer_sync(&priv->eee_ctrl_timer); + if (device_may_wakeup(priv->device)) + phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ phylink_stop(priv->phylink); phylink_disconnect_phy(priv->phylink); @@ -5085,12 +5093,14 @@ int stmmac_suspend(struct device *dev) priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv); /* Enable Power down mode by programming the PMT regs */ - if (device_may_wakeup(priv->device)) { + if (device_may_wakeup(priv->device) && priv->plat->pmt) { stmmac_pmt(priv, priv->hw, priv->wolopts); priv->irq_wake = 1; } else { mutex_unlock(&priv->lock); rtnl_lock(); + if (device_may_wakeup(priv->device)) + phylink_speed_down(priv->phylink, false); phylink_stop(priv->phylink); rtnl_unlock(); mutex_lock(&priv->lock); @@ -5157,7 +5167,7 @@ int stmmac_resume(struct device *dev) * this bit because it can generate problems while resuming * from another devices (e.g. serial console). */ - if (device_may_wakeup(priv->device)) { + if (device_may_wakeup(priv->device) && priv->plat->pmt) { mutex_lock(&priv->lock); stmmac_pmt(priv, priv->hw, 0); mutex_unlock(&priv->lock); @@ -5200,9 +5210,11 @@ int stmmac_resume(struct device *dev) mutex_unlock(&priv->lock); - if (!device_may_wakeup(priv->device)) { + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { rtnl_lock(); phylink_start(priv->phylink); + /* We may have called phylink_speed_down before */ + phylink_speed_up(priv->phylink); rtnl_unlock(); } diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 583cd2ef7662..58623e974a0c 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -345,33 +345,21 @@ static void tlan_stop(struct net_device *dev) } } -#ifdef CONFIG_PM - -static int tlan_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused tlan_suspend(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(dev_d); if (netif_running(dev)) tlan_stop(dev); netif_device_detach(dev); - pci_save_state(pdev); - pci_disable_device(pdev); - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); return 0; } -static int tlan_resume(struct pci_dev *pdev) +static int __maybe_unused tlan_resume(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); - int rc = pci_enable_device(pdev); - - if (rc) - return rc; - pci_restore_state(pdev); - pci_enable_wake(pdev, PCI_D0, 0); + struct net_device *dev = dev_get_drvdata(dev_d); netif_device_attach(dev); if (netif_running(dev)) @@ -380,21 +368,14 @@ static int tlan_resume(struct pci_dev *pdev) return 0; } -#else /* CONFIG_PM */ - -#define tlan_suspend NULL -#define tlan_resume NULL - -#endif /* CONFIG_PM */ - +static SIMPLE_DEV_PM_OPS(tlan_pm_ops, tlan_suspend, tlan_resume); static struct pci_driver tlan_driver = { .name = "tlan", .id_table = tlan_pci_tbl, .probe = tlan_init_one, .remove = tlan_remove_one, - .suspend = tlan_suspend, - .resume = tlan_resume, + .driver.pm = &tlan_pm_ops, }; static int __init tlan_probe(void) diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 3902b3aeb0c2..07389702a540 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -283,8 +283,8 @@ spider_net_free_chain(struct spider_net_card *card, descr = descr->next; } while (descr != chain->ring); - dma_free_coherent(&card->pdev->dev, chain->num_desc, - chain->hwring, chain->dma_addr); + dma_free_coherent(&card->pdev->dev, chain->num_desc * sizeof(struct spider_net_hw_descr), + chain->hwring, chain->dma_addr); } /** @@ -314,8 +314,6 @@ spider_net_init_chain(struct spider_net_card *card, if (!chain->hwring) return -ENOMEM; - memset(chain->ring, 0, chain->num_desc * sizeof(struct spider_net_descr)); - /* Set up the hardware pointers in each descriptor */ descr = chain->ring; hwdescr = chain->hwring; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 929244064abd..9a15f14daa47 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1407,10 +1407,8 @@ static int temac_probe(struct platform_device *pdev) } /* map device registers */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - lp->regs = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); - if (!lp->regs) { + lp->regs = devm_platform_ioremap_resource_byname(pdev, 0); + if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map TEMAC registers\n"); return -ENOMEM; } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index ce719c830a77..32f339fedb21 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -810,7 +810,8 @@ static int nsim_dev_devlink_trap_init(struct devlink *devlink, static int nsim_dev_devlink_trap_action_set(struct devlink *devlink, const struct devlink_trap *trap, - enum devlink_trap_action action) + enum devlink_trap_action action, + struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); struct nsim_trap_item *nsim_trap_item; @@ -829,7 +830,8 @@ nsim_dev_devlink_trap_action_set(struct devlink *devlink, static int nsim_dev_devlink_trap_group_set(struct devlink *devlink, const struct devlink_trap_group *group, - const struct devlink_trap_policer *policer) + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index dd20c2c27c2f..726e4b240e7e 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -194,6 +194,7 @@ config MDIO_MSCC_MIIM config MDIO_MVUSB tristate "Marvell USB to MDIO Adapter" depends on USB + select MDIO_DEVRES help A USB to MDIO converter present on development boards for Marvell's Link Street family of Ethernet switches. diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 46b33701ad4b..0af20faad69d 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -554,8 +554,10 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) bus->reset_gpiod = gpiod; gpiod_set_value_cansleep(gpiod, 1); - udelay(bus->reset_delay_us); + fsleep(bus->reset_delay_us); gpiod_set_value_cansleep(gpiod, 0); + if (bus->reset_post_delay_us > 0) + fsleep(bus->reset_post_delay_us); } if (bus->reset) { diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 0f625a1b1644..0837319a52d7 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -132,7 +132,7 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value) d = value ? mdiodev->reset_assert_delay : mdiodev->reset_deassert_delay; if (d) - usleep_range(d, d + max_t(unsigned int, d / 10, 100)); + fsleep(d); } EXPORT_SYMBOL(mdio_device_reset); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 061bebe25cb1..3c11a77f5709 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2968,7 +2968,7 @@ unlock: return ret; } -static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog **prog_p, +static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, void __user *data) { struct bpf_prog *prog; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 5f123a8cf68e..d2fdb5430d27 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2261,12 +2261,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, minor = get_free_serial_index(); if (minor < 0) - goto exit; + goto exit2; /* register our minor number */ serial->parent->dev = tty_port_register_device_attr(&serial->port, tty_drv, minor, &serial->parent->interface->dev, serial->parent, hso_serial_dev_groups); + if (IS_ERR(serial->parent->dev)) + goto exit2; /* fill in specific data for later use */ serial->minor = minor; @@ -2311,6 +2313,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, return 0; exit: hso_serial_tty_unregister(serial); +exit2: hso_serial_common_free(serial); return -1; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index eccbf4cd7149..442507f25aad 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -377,10 +377,6 @@ struct lan78xx_net { struct tasklet_struct bh; struct delayed_work wq; - struct usb_host_endpoint *ep_blkin; - struct usb_host_endpoint *ep_blkout; - struct usb_host_endpoint *ep_intr; - int msg_enable; struct urb *urb_intr; @@ -2860,78 +2856,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) return NETDEV_TX_OK; } -static int -lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf) -{ - int tmp; - struct usb_host_interface *alt = NULL; - struct usb_host_endpoint *in = NULL, *out = NULL; - struct usb_host_endpoint *status = NULL; - - for (tmp = 0; tmp < intf->num_altsetting; tmp++) { - unsigned ep; - - in = NULL; - out = NULL; - status = NULL; - alt = intf->altsetting + tmp; - - for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) { - struct usb_host_endpoint *e; - int intr = 0; - - e = alt->endpoint + ep; - switch (e->desc.bmAttributes) { - case USB_ENDPOINT_XFER_INT: - if (!usb_endpoint_dir_in(&e->desc)) - continue; - intr = 1; - /* FALLTHROUGH */ - case USB_ENDPOINT_XFER_BULK: - break; - default: - continue; - } - if (usb_endpoint_dir_in(&e->desc)) { - if (!intr && !in) - in = e; - else if (intr && !status) - status = e; - } else { - if (!out) - out = e; - } - } - if (in && out) - break; - } - if (!alt || !in || !out) - return -EINVAL; - - dev->pipe_in = usb_rcvbulkpipe(dev->udev, - in->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->pipe_out = usb_sndbulkpipe(dev->udev, - out->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->ep_intr = status; - - return 0; -} - static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = NULL; int ret; int i; - ret = lan78xx_get_endpoints(dev, intf); - if (ret) { - netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n", - ret); - return ret; - } - dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); pdata = (struct lan78xx_priv *)(dev->data[0]); @@ -3700,6 +3630,7 @@ static void lan78xx_stat_monitor(struct timer_list *t) static int lan78xx_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr; struct lan78xx_net *dev; struct net_device *netdev; struct usb_device *udev; @@ -3748,6 +3679,34 @@ static int lan78xx_probe(struct usb_interface *intf, mutex_init(&dev->stats.access_lock); + if (intf->cur_altsetting->desc.bNumEndpoints < 3) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); + ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in); + if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); + ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out); + if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) { + ret = -ENODEV; + goto out2; + } + + ep_intr = &intf->cur_altsetting->endpoint[2]; + if (!usb_endpoint_is_int_in(&ep_intr->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_intr = usb_rcvintpipe(dev->udev, + usb_endpoint_num(&ep_intr->desc)); + ret = lan78xx_bind(dev, intf); if (ret < 0) goto out2; @@ -3759,18 +3718,7 @@ static int lan78xx_probe(struct usb_interface *intf, netdev->max_mtu = MAX_SINGLE_PACKET_SIZE; netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER); - dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0; - dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1; - dev->ep_intr = (intf->cur_altsetting)->endpoint + 2; - - dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); - dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); - - dev->pipe_intr = usb_rcvintpipe(dev->udev, - dev->ep_intr->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - period = dev->ep_intr->desc.bInterval; - + period = ep_intr->desc.bInterval; maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0); buf = kmalloc(maxp, GFP_KERNEL); if (buf) { @@ -3783,6 +3731,7 @@ static int lan78xx_probe(struct usb_interface *intf, usb_fill_int_urb(dev->urb_intr, dev->udev, dev->pipe_intr, buf, maxp, intr_complete, dev, period); + dev->urb_intr->transfer_flags |= URB_FREE_BUFFER; } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index a43c97b13924..77658425db8a 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1376,6 +1376,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; + rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; @@ -1387,8 +1388,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip_nh: *idx += 1; continue; @@ -1403,12 +1406,15 @@ skip_nh: cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip: *idx += 1; } } + rcu_read_unlock(); } out: return err; @@ -3070,8 +3076,10 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP))) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ - if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f, true, true); + if (is_zero_ether_addr(f->eth_addr) && + f->vni == vxlan->cfg.vni) + continue; + vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 0196b7fd130d..fe4650260bc6 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -2636,12 +2636,10 @@ fst_remove_one(struct pci_dev *pdev) } static struct pci_driver fst_driver = { - .name = FST_NAME, - .id_table = fst_pci_dev_id, - .probe = fst_add_one, - .remove = fst_remove_one, - .suspend = NULL, - .resume = NULL, + .name = FST_NAME, + .id_table = fst_pci_dev_id, + .probe = fst_add_one, + .remove = fst_remove_one, }; static int __init diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 919d15584d4a..3c0c33a9f30c 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -568,11 +568,7 @@ chan_to_phymode(const struct cfg80211_chan_def *chandef) case NL80211_CHAN_WIDTH_40: phymode = MODE_11NG_HT40; break; - case NL80211_CHAN_WIDTH_5: - case NL80211_CHAN_WIDTH_10: - case NL80211_CHAN_WIDTH_80: - case NL80211_CHAN_WIDTH_80P80: - case NL80211_CHAN_WIDTH_160: + default: phymode = MODE_UNKNOWN; break; } @@ -597,8 +593,7 @@ chan_to_phymode(const struct cfg80211_chan_def *chandef) case NL80211_CHAN_WIDTH_80P80: phymode = MODE_11AC_VHT80_80; break; - case NL80211_CHAN_WIDTH_5: - case NL80211_CHAN_WIDTH_10: + default: phymode = MODE_UNKNOWN; break; } diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 07d3e031c75a..94ae2b9ea663 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2072,7 +2072,7 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, ret = ath11k_wmi_send_obss_color_collision_cfg_cmd( ar, arvif->vdev_id, info->he_bss_color.color, ATH11K_BSS_COLOR_COLLISION_DETECTION_AP_PERIOD_MS, - !info->he_bss_color.disabled); + info->he_bss_color.enabled); if (ret) ath11k_warn(ar->ab, "failed to set bss color collision on vdev %i: %d\n", arvif->vdev_id, ret); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 1356e8cbe617..9dd9d73f4484 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4334,7 +4334,7 @@ static int __init init_mac80211_hwsim(void) break; case HWSIM_REGTEST_STRICT_ALL: param.reg_strict = true; - /* fall through */ + fallthrough; case HWSIM_REGTEST_DRIVER_REG_ALL: param.reg_alpha2 = hwsim_alpha2s[0]; break; diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h index 71cd8629b28e..8b476b007c5e 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.h +++ b/drivers/net/wireless/marvell/mwifiex/sdio.h @@ -36,9 +36,9 @@ #define SD8897_DEFAULT_FW_NAME "mrvl/sd8897_uapsta.bin" #define SD8887_DEFAULT_FW_NAME "mrvl/sd8887_uapsta.bin" #define SD8801_DEFAULT_FW_NAME "mrvl/sd8801_uapsta.bin" -#define SD8977_DEFAULT_FW_NAME "mrvl/sd8977_uapsta.bin" +#define SD8977_DEFAULT_FW_NAME "mrvl/sdsd8977_combo_v2.bin" #define SD8987_DEFAULT_FW_NAME "mrvl/sd8987_uapsta.bin" -#define SD8997_DEFAULT_FW_NAME "mrvl/sd8997_uapsta.bin" +#define SD8997_DEFAULT_FW_NAME "mrvl/sdsd8997_combo_v4.bin" #define BLOCK_MODE 1 #define BYTE_MODE 0 diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index add040168e67..4ee2330c603e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1102,6 +1102,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, int pos; int len; + if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST) + return 0; + c.identify.opcode = nvme_admin_identify; c.identify.nsid = cpu_to_le32(nsid); c.identify.cns = NVME_ID_CNS_NS_DESC_LIST; @@ -1115,18 +1118,6 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, if (status) { dev_warn(ctrl->device, "Identify Descriptors failed (%d)\n", status); - /* - * Don't treat non-retryable errors as fatal, as we potentially - * already have a NGUID or EUI-64. If we failed with DNR set, - * we want to silently ignore the error as we can still - * identify the device, but if the status has DNR set, we want - * to propagate the error back specifically for the disk - * revalidation flow to make sure we don't abandon the - * device just because of a temporal retry-able error (such - * as path of transport errors). - */ - if (status > 0 && (status & NVME_SC_DNR)) - status = 0; goto free_data; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1de3f9b827aa..09ffc3246f60 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -129,6 +129,13 @@ enum nvme_quirks { * Don't change the value of the temperature threshold feature */ NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14), + + /* + * The controller doesn't handle the Identify Namespace + * Identification Descriptor list subcommand despite claiming + * NVMe 1.3 compliance. + */ + NVME_QUIRK_NO_NS_DESC_LIST = (1 << 15), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b1d18f0633c7..d4b1ff747123 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3099,6 +3099,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ + .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */ @@ -3122,6 +3124,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1c5c, 0x1504), /* SK Hynix PC400 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), .driver_data = NVME_QUIRK_SINGLE_VECTOR }, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 79ef2b8e2b3c..f3a91818167b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1382,6 +1382,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (nctrl->opts->tos >= 0) ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos); + /* Set 10 seconds timeout for icresp recvmsg */ + queue->sock->sk->sk_rcvtimeo = 10 * HZ; + queue->sock->sk->sk_allocation = GFP_ATOMIC; nvme_tcp_set_queue_io_cpu(queue); queue->request = NULL; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index eb84507de28a..cb32d7ef4938 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -268,6 +268,8 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) /* Get bus level PHY reset GPIO details */ mdio->reset_delay_us = DEFAULT_GPIO_RESET_DELAY; of_property_read_u32(np, "reset-delay-us", &mdio->reset_delay_us); + mdio->reset_post_delay_us = 0; + of_property_read_u32(np, "reset-post-delay-us", &mdio->reset_post_delay_us); /* Register the MDIO bus */ rc = mdiobus_register(mdio); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 812bfc32ecb8..2ea61abd5830 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2330,6 +2330,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); +static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) +{ + pci_info(dev, "Disabling ASPM L0s/L1\n"); + pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); +} + +/* + * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the + * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected; + * disable both L0s and L1 for now to be safe. + */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); + /* * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain * Link bit cleared after starting the link retrain process to allow this diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index ff1ee159dca2..f8ff30cdafa6 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -7,6 +7,8 @@ config PINCTRL_MSM select PINCONF select GENERIC_PINCONF select GPIOLIB_IRQCHIP + select IRQ_DOMAIN_HIERARCHY + select IRQ_FASTEOI_HIERARCHY_HANDLERS config PINCTRL_APQ8064 tristate "Qualcomm APQ8064 pin controller driver" diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 83b7d64bc4c1..c322f30a2064 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -832,6 +832,52 @@ static void msm_gpio_irq_unmask(struct irq_data *d) msm_gpio_irq_clear_unmask(d, false); } +/** + * msm_gpio_update_dual_edge_parent() - Prime next edge for IRQs handled by parent. + * @d: The irq dta. + * + * This is much like msm_gpio_update_dual_edge_pos() but for IRQs that are + * normally handled by the parent irqchip. The logic here is slightly + * different due to what's easy to do with our parent, but in principle it's + * the same. + */ +static void msm_gpio_update_dual_edge_parent(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq]; + int loop_limit = 100; + unsigned int val; + unsigned int type; + + /* Read the value and make a guess about what edge we need to catch */ + val = msm_readl_io(pctrl, g) & BIT(g->in_bit); + type = val ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING; + + do { + /* Set the parent to catch the next edge */ + irq_chip_set_type_parent(d, type); + + /* + * Possibly the line changed between when we last read "val" + * (and decided what edge we needed) and when set the edge. + * If the value didn't change (or changed and then changed + * back) then we're done. + */ + val = msm_readl_io(pctrl, g) & BIT(g->in_bit); + if (type == IRQ_TYPE_EDGE_RISING) { + if (!val) + return; + type = IRQ_TYPE_EDGE_FALLING; + } else if (type == IRQ_TYPE_EDGE_FALLING) { + if (val) + return; + type = IRQ_TYPE_EDGE_RISING; + } + } while (loop_limit-- > 0); + dev_warn_once(pctrl->dev, "dual-edge irq failed to stabilize\n"); +} + static void msm_gpio_irq_ack(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -840,8 +886,11 @@ static void msm_gpio_irq_ack(struct irq_data *d) unsigned long flags; u32 val; - if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { + if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) + msm_gpio_update_dual_edge_parent(d); return; + } g = &pctrl->soc->groups[d->hwirq]; @@ -860,6 +909,17 @@ static void msm_gpio_irq_ack(struct irq_data *d) raw_spin_unlock_irqrestore(&pctrl->lock, flags); } +static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d, + unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + return type == IRQ_TYPE_EDGE_BOTH && + pctrl->soc->wakeirq_dual_edge_errata && d->parent_data && + test_bit(d->hwirq, pctrl->skip_wake_irqs); +} + static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -868,11 +928,21 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) unsigned long flags; u32 val; + if (msm_gpio_needs_dual_edge_parent_workaround(d, type)) { + set_bit(d->hwirq, pctrl->dual_edge_irqs); + irq_set_handler_locked(d, handle_fasteoi_ack_irq); + msm_gpio_update_dual_edge_parent(d); + return 0; + } + if (d->parent_data) irq_chip_set_type_parent(d, type); - if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { + clear_bit(d->hwirq, pctrl->dual_edge_irqs); + irq_set_handler_locked(d, handle_fasteoi_irq); return 0; + } g = &pctrl->soc->groups[d->hwirq]; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 9452da18a78b..7486fe08eb9b 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -113,6 +113,9 @@ struct msm_gpio_wakeirq_map { * @pull_no_keeper: The SoC does not support keeper bias. * @wakeirq_map: The map of wakeup capable GPIOs and the pin at PDC/MPM * @nwakeirq_map: The number of entries in @wakeirq_map + * @wakeirq_dual_edge_errata: If true then GPIOs using the wakeirq_map need + * to be aware that their parent can't handle dual + * edge interrupts. */ struct msm_pinctrl_soc_data { const struct pinctrl_pin_desc *pins; @@ -128,6 +131,7 @@ struct msm_pinctrl_soc_data { const int *reserved_gpios; const struct msm_gpio_wakeirq_map *wakeirq_map; unsigned int nwakeirq_map; + bool wakeirq_dual_edge_errata; }; extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops; diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c index 1b6465a882f2..1d9acad3c1ce 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7180.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c @@ -1147,6 +1147,7 @@ static const struct msm_pinctrl_soc_data sc7180_pinctrl = { .ntiles = ARRAY_SIZE(sc7180_tiles), .wakeirq_map = sc7180_pdc_map, .nwakeirq_map = ARRAY_SIZE(sc7180_pdc_map), + .wakeirq_dual_edge_errata = true, }; static int sc7180_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/ptp/idt8a340_reg.h b/drivers/ptp/idt8a340_reg.h index 69eedda9f731..b297c4aba2ba 100644 --- a/drivers/ptp/idt8a340_reg.h +++ b/drivers/ptp/idt8a340_reg.h @@ -20,6 +20,10 @@ #define HW_DPLL_1 (0x8b00) #define HW_DPLL_2 (0x8c00) #define HW_DPLL_3 (0x8d00) +#define HW_DPLL_4 (0x8e00) +#define HW_DPLL_5 (0x8f00) +#define HW_DPLL_6 (0x9000) +#define HW_DPLL_7 (0x9100) #define HW_DPLL_TOD_SW_TRIG_ADDR__0 (0x080) #define HW_DPLL_TOD_CTRL_1 (0x089) @@ -57,6 +61,43 @@ #define SYNCTRL1_Q1_DIV_SYNC_TRIG BIT(1) #define SYNCTRL1_Q0_DIV_SYNC_TRIG BIT(0) +#define HW_Q8_CTRL_SPARE (0xa7d4) +#define HW_Q11_CTRL_SPARE (0xa7ec) + +/** + * Select FOD5 as sync_trigger for Q8 divider. + * Transition from logic zero to one + * sets trigger to sync Q8 divider. + * + * Unused when FOD4 is driving Q8 divider (normal operation). + */ +#define Q9_TO_Q8_SYNC_TRIG BIT(1) + +/** + * Enable FOD5 as driver for clock and sync for Q8 divider. + * Enable fanout buffer for FOD5. + * + * Unused when FOD4 is driving Q8 divider (normal operation). + */ +#define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) + +/** + * Select FOD6 as sync_trigger for Q11 divider. + * Transition from logic zero to one + * sets trigger to sync Q11 divider. + * + * Unused when FOD7 is driving Q11 divider (normal operation). + */ +#define Q10_TO_Q11_SYNC_TRIG BIT(1) + +/** + * Enable FOD6 as driver for clock and sync for Q11 divider. + * Enable fanout buffer for FOD6. + * + * Unused when FOD7 is driving Q11 divider (normal operation). + */ +#define Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) + #define RESET_CTRL 0xc000 #define SM_RESET 0x0012 #define SM_RESET_CMD 0x5A @@ -191,6 +232,7 @@ #define DPLL_CTRL_0 0xc600 #define DPLL_CTRL_DPLL_MANU_REF_CFG 0x0001 +#define DPLL_CTRL_COMBO_MASTER_CFG 0x003a #define DPLL_CTRL_1 0xc63c @@ -646,6 +688,9 @@ /* Bit definitions for the TOD_WRITE_CMD register */ #define TOD_WRITE_SELECTION_SHIFT (0) #define TOD_WRITE_SELECTION_MASK (0xf) +/* 4.8.7 */ +#define TOD_WRITE_TYPE_SHIFT (4) +#define TOD_WRITE_TYPE_MASK (0x3) /* Bit definitions for the TOD_READ_PRIMARY_SEL_CFG_0 register */ #define RD_PWM_DECODER_INDEX_SHIFT (4) @@ -658,4 +703,7 @@ #define TOD_READ_TRIGGER_SHIFT (0) #define TOD_READ_TRIGGER_MASK (0xf) +/* Bit definitions for the DPLL_CTRL_COMBO_MASTER_CFG register */ +#define COMBO_MASTER_HOLD BIT(0) + #endif diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index ceb6bc58f3b4..73aaae5574ed 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -13,6 +13,7 @@ #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/timekeeping.h> +#include <linux/string.h> #include "ptp_private.h" #include "ptp_clockmatrix.h" @@ -23,6 +24,13 @@ MODULE_AUTHOR("IDT support-1588 <IDT-support-1588@lm.renesas.com>"); MODULE_VERSION("1.0"); MODULE_LICENSE("GPL"); +/* + * The name of the firmware file to be loaded + * over-rides any automatic selection + */ +static char *firmware; +module_param(firmware, charp, 0); + #define SETTIME_CORRECTION (0) static long set_write_phase_ready(struct ptp_clock_info *ptp) @@ -95,6 +103,45 @@ static int timespec_to_char_array(struct timespec64 const *ts, return 0; } +static int idtcm_strverscmp(const char *ver1, const char *ver2) +{ + u8 num1; + u8 num2; + int result = 0; + + /* loop through each level of the version string */ + while (result == 0) { + /* extract leading version numbers */ + if (kstrtou8(ver1, 10, &num1) < 0) + return -1; + + if (kstrtou8(ver2, 10, &num2) < 0) + return -1; + + /* if numbers differ, then set the result */ + if (num1 < num2) + result = -1; + else if (num1 > num2) + result = 1; + else { + /* if numbers are the same, go to next level */ + ver1 = strchr(ver1, '.'); + ver2 = strchr(ver2, '.'); + if (!ver1 && !ver2) + break; + else if (!ver1) + result = -1; + else if (!ver2) + result = 1; + else { + ver1++; + ver2++; + } + } + } + return result; +} + static int idtcm_xfer(struct idtcm *idtcm, u8 regaddr, u8 *buf, @@ -104,6 +151,7 @@ static int idtcm_xfer(struct idtcm *idtcm, struct i2c_client *client = idtcm->client; struct i2c_msg msg[2]; int cnt; + char *fmt = "i2c_transfer failed at %d in %s for %s, at addr: %04X!\n"; msg[0].addr = client->addr; msg[0].flags = 0; @@ -118,7 +166,12 @@ static int idtcm_xfer(struct idtcm *idtcm, cnt = i2c_transfer(client->adapter, msg, 2); if (cnt < 0) { - dev_err(&client->dev, "i2c_transfer returned %d\n", cnt); + dev_err(&client->dev, + fmt, + __LINE__, + __func__, + write ? "write" : "read", + regaddr); return cnt; } else if (cnt != 2) { dev_err(&client->dev, @@ -144,10 +197,12 @@ static int idtcm_page_offset(struct idtcm *idtcm, u8 val) err = idtcm_xfer(idtcm, PAGE_ADDR, buf, sizeof(buf), 1); - if (err) + if (err) { + idtcm->page_offset = 0xff; dev_err(&idtcm->client->dev, "failed to set page offset\n"); - else + } else { idtcm->page_offset = val; + } return err; } @@ -198,6 +253,7 @@ static int _idtcm_gettime(struct idtcm_channel *channel, { struct idtcm *idtcm = channel->idtcm; u8 buf[TOD_BYTE_COUNT]; + u8 timeout = 10; u8 trigger; int err; @@ -208,16 +264,29 @@ static int _idtcm_gettime(struct idtcm_channel *channel, trigger &= ~(TOD_READ_TRIGGER_MASK << TOD_READ_TRIGGER_SHIFT); trigger |= (1 << TOD_READ_TRIGGER_SHIFT); - trigger |= TOD_READ_TRIGGER_MODE; + trigger &= ~TOD_READ_TRIGGER_MODE; /* single shot */ err = idtcm_write(idtcm, channel->tod_read_primary, TOD_READ_PRIMARY_CMD, &trigger, sizeof(trigger)); - if (err) return err; - if (idtcm->calculate_overhead_flag) - idtcm->start_time = ktime_get_raw(); + /* wait trigger to be 0 */ + while (trigger & TOD_READ_TRIGGER_MASK) { + + if (idtcm->calculate_overhead_flag) + idtcm->start_time = ktime_get_raw(); + + err = idtcm_read(idtcm, channel->tod_read_primary, + TOD_READ_PRIMARY_CMD, &trigger, + sizeof(trigger)); + + if (err) + return err; + + if (--timeout == 0) + return -EIO; + } err = idtcm_read(idtcm, channel->tod_read_primary, TOD_READ_PRIMARY, buf, sizeof(buf)); @@ -240,6 +309,7 @@ static int _sync_pll_output(struct idtcm *idtcm, u8 val; u16 sync_ctrl0; u16 sync_ctrl1; + u8 temp; if ((qn == 0) && (qn_plus_1 == 0)) return 0; @@ -305,6 +375,50 @@ static int _sync_pll_output(struct idtcm *idtcm, if (err) return err; + /* PLL5 can have OUT8 as second additional output. */ + if ((pll == 5) && (qn_plus_1 != 0)) { + err = idtcm_read(idtcm, 0, HW_Q8_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + + temp &= ~(Q9_TO_Q8_SYNC_TRIG); + + err = idtcm_write(idtcm, 0, HW_Q8_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + + temp |= Q9_TO_Q8_SYNC_TRIG; + + err = idtcm_write(idtcm, 0, HW_Q8_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + } + + /* PLL6 can have OUT11 as second additional output. */ + if ((pll == 6) && (qn_plus_1 != 0)) { + err = idtcm_read(idtcm, 0, HW_Q11_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + + temp &= ~(Q10_TO_Q11_SYNC_TRIG); + + err = idtcm_write(idtcm, 0, HW_Q11_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + + temp |= Q10_TO_Q11_SYNC_TRIG; + + err = idtcm_write(idtcm, 0, HW_Q11_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + } + /* Place master sync out of reset */ val &= ~(SYNCTRL1_MASTER_SYNC_RST); err = idtcm_write(idtcm, 0, sync_ctrl1, &val, sizeof(val)); @@ -312,6 +426,30 @@ static int _sync_pll_output(struct idtcm *idtcm, return err; } +static int sync_source_dpll_tod_pps(u16 tod_addr, u8 *sync_src) +{ + int err = 0; + + switch (tod_addr) { + case TOD_0: + *sync_src = SYNC_SOURCE_DPLL0_TOD_PPS; + break; + case TOD_1: + *sync_src = SYNC_SOURCE_DPLL1_TOD_PPS; + break; + case TOD_2: + *sync_src = SYNC_SOURCE_DPLL2_TOD_PPS; + break; + case TOD_3: + *sync_src = SYNC_SOURCE_DPLL3_TOD_PPS; + break; + default: + err = -EINVAL; + } + + return err; +} + static int idtcm_sync_pps_output(struct idtcm_channel *channel) { struct idtcm *idtcm = channel->idtcm; @@ -321,37 +459,68 @@ static int idtcm_sync_pps_output(struct idtcm_channel *channel) u8 qn; u8 qn_plus_1; int err = 0; + u8 out8_mux = 0; + u8 out11_mux = 0; + u8 temp; u16 output_mask = channel->output_mask; - switch (channel->dpll_n) { - case DPLL_0: - sync_src = SYNC_SOURCE_DPLL0_TOD_PPS; - break; - case DPLL_1: - sync_src = SYNC_SOURCE_DPLL1_TOD_PPS; - break; - case DPLL_2: - sync_src = SYNC_SOURCE_DPLL2_TOD_PPS; - break; - case DPLL_3: - sync_src = SYNC_SOURCE_DPLL3_TOD_PPS; - break; - default: - return -EINVAL; - } + err = sync_source_dpll_tod_pps(channel->tod_n, &sync_src); + if (err) + return err; - for (pll = 0; pll < 8; pll++) { + err = idtcm_read(idtcm, 0, HW_Q8_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; - qn = output_mask & 0x1; - output_mask = output_mask >> 1; + if ((temp & Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) == + Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) + out8_mux = 1; + + err = idtcm_read(idtcm, 0, HW_Q11_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + + if ((temp & Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) == + Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) + out11_mux = 1; + + for (pll = 0; pll < 8; pll++) { + qn = 0; + qn_plus_1 = 0; if (pll < 4) { /* First 4 pll has 2 outputs */ + qn = output_mask & 0x1; + output_mask = output_mask >> 1; qn_plus_1 = output_mask & 0x1; output_mask = output_mask >> 1; - } else { - qn_plus_1 = 0; + } else if (pll == 4) { + if (out8_mux == 0) { + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + } + } else if (pll == 5) { + if (out8_mux) { + qn_plus_1 = output_mask & 0x1; + output_mask = output_mask >> 1; + } + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + } else if (pll == 6) { + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + if (out11_mux) { + qn_plus_1 = output_mask & 0x1; + output_mask = output_mask >> 1; + } + } else if (pll == 7) { + if (out11_mux == 0) { + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + } } if ((qn != 0) || (qn_plus_1 != 0)) @@ -365,7 +534,7 @@ static int idtcm_sync_pps_output(struct idtcm_channel *channel) return err; } -static int _idtcm_set_dpll_tod(struct idtcm_channel *channel, +static int _idtcm_set_dpll_hw_tod(struct idtcm_channel *channel, struct timespec64 const *ts, enum hw_tod_write_trig_sel wr_trig) { @@ -439,17 +608,78 @@ static int _idtcm_set_dpll_tod(struct idtcm_channel *channel, return err; } +static int _idtcm_set_dpll_scsr_tod(struct idtcm_channel *channel, + struct timespec64 const *ts, + enum scsr_tod_write_trig_sel wr_trig, + enum scsr_tod_write_type_sel wr_type) +{ + struct idtcm *idtcm = channel->idtcm; + unsigned char buf[TOD_BYTE_COUNT], cmd; + struct timespec64 local_ts = *ts; + int err, count = 0; + + timespec64_add_ns(&local_ts, SETTIME_CORRECTION); + + err = timespec_to_char_array(&local_ts, buf, sizeof(buf)); + + if (err) + return err; + + err = idtcm_write(idtcm, channel->tod_write, TOD_WRITE, + buf, sizeof(buf)); + if (err) + return err; + + /* Trigger the write operation. */ + err = idtcm_read(idtcm, channel->tod_write, TOD_WRITE_CMD, + &cmd, sizeof(cmd)); + if (err) + return err; + + cmd &= ~(TOD_WRITE_SELECTION_MASK << TOD_WRITE_SELECTION_SHIFT); + cmd &= ~(TOD_WRITE_TYPE_MASK << TOD_WRITE_TYPE_SHIFT); + cmd |= (wr_trig << TOD_WRITE_SELECTION_SHIFT); + cmd |= (wr_type << TOD_WRITE_TYPE_SHIFT); + + err = idtcm_write(idtcm, channel->tod_write, TOD_WRITE_CMD, + &cmd, sizeof(cmd)); + if (err) + return err; + + /* Wait for the operation to complete. */ + while (1) { + /* pps trigger takes up to 1 sec to complete */ + if (wr_trig == SCSR_TOD_WR_TRIG_SEL_TODPPS) + msleep(50); + + err = idtcm_read(idtcm, channel->tod_write, TOD_WRITE_CMD, + &cmd, sizeof(cmd)); + if (err) + return err; + + if (cmd == 0) + break; + + if (++count > 20) { + dev_err(&idtcm->client->dev, + "Timed out waiting for the write counter\n"); + return -EIO; + } + } + + return 0; +} + static int _idtcm_settime(struct idtcm_channel *channel, struct timespec64 const *ts, enum hw_tod_write_trig_sel wr_trig) { struct idtcm *idtcm = channel->idtcm; - s32 retval; int err; int i; u8 trig_sel; - err = _idtcm_set_dpll_tod(channel, ts, wr_trig); + err = _idtcm_set_dpll_hw_tod(channel, ts, wr_trig); if (err) return err; @@ -469,12 +699,24 @@ static int _idtcm_settime(struct idtcm_channel *channel, err = 1; } - if (err) + if (err) { + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); return err; + } - retval = idtcm_sync_pps_output(channel); + return idtcm_sync_pps_output(channel); +} - return retval; +static int _idtcm_settime_v487(struct idtcm_channel *channel, + struct timespec64 const *ts, + enum scsr_tod_write_type_sel wr_type) +{ + return _idtcm_set_dpll_scsr_tod(channel, ts, + SCSR_TOD_WR_TRIG_SEL_IMMEDIATE, + wr_type); } static int idtcm_set_phase_pull_in_offset(struct idtcm_channel *channel, @@ -565,6 +807,50 @@ static int idtcm_do_phase_pull_in(struct idtcm_channel *channel, return err; } +static int set_tod_write_overhead(struct idtcm_channel *channel) +{ + struct idtcm *idtcm = channel->idtcm; + s64 current_ns = 0; + s64 lowest_ns = 0; + int err; + u8 i; + + ktime_t start; + ktime_t stop; + + char buf[TOD_BYTE_COUNT] = {0}; + + /* Set page offset */ + idtcm_write(idtcm, channel->hw_dpll_n, HW_DPLL_TOD_OVR__0, + buf, sizeof(buf)); + + for (i = 0; i < TOD_WRITE_OVERHEAD_COUNT_MAX; i++) { + + start = ktime_get_raw(); + + err = idtcm_write(idtcm, channel->hw_dpll_n, + HW_DPLL_TOD_OVR__0, buf, sizeof(buf)); + + if (err) + return err; + + stop = ktime_get_raw(); + + current_ns = ktime_to_ns(stop - start); + + if (i == 0) { + lowest_ns = current_ns; + } else { + if (current_ns < lowest_ns) + lowest_ns = current_ns; + } + } + + idtcm->tod_write_overhead_ns = lowest_ns; + + return err; +} + static int _idtcm_adjtime(struct idtcm_channel *channel, s64 delta) { int err; @@ -577,6 +863,11 @@ static int _idtcm_adjtime(struct idtcm_channel *channel, s64 delta) } else { idtcm->calculate_overhead_flag = 1; + err = set_tod_write_overhead(channel); + + if (err) + return err; + err = _idtcm_gettime(channel, &ts); if (err) @@ -656,93 +947,118 @@ static int idtcm_read_otp_scsr_config_select(struct idtcm *idtcm, config_select, sizeof(u8)); } -static int process_pll_mask(struct idtcm *idtcm, u32 addr, u8 val, u8 *mask) -{ - int err = 0; - - if (addr == PLL_MASK_ADDR) { - if ((val & 0xf0) || !(val & 0xf)) { - dev_err(&idtcm->client->dev, - "Invalid PLL mask 0x%hhx\n", val); - err = -EINVAL; - } - *mask = val; - } - - return err; -} - static int set_pll_output_mask(struct idtcm *idtcm, u16 addr, u8 val) { int err = 0; switch (addr) { - case OUTPUT_MASK_PLL0_ADDR: + case TOD0_OUT_ALIGN_MASK_ADDR: SET_U16_LSB(idtcm->channel[0].output_mask, val); break; - case OUTPUT_MASK_PLL0_ADDR + 1: + case TOD0_OUT_ALIGN_MASK_ADDR + 1: SET_U16_MSB(idtcm->channel[0].output_mask, val); break; - case OUTPUT_MASK_PLL1_ADDR: + case TOD1_OUT_ALIGN_MASK_ADDR: SET_U16_LSB(idtcm->channel[1].output_mask, val); break; - case OUTPUT_MASK_PLL1_ADDR + 1: + case TOD1_OUT_ALIGN_MASK_ADDR + 1: SET_U16_MSB(idtcm->channel[1].output_mask, val); break; - case OUTPUT_MASK_PLL2_ADDR: + case TOD2_OUT_ALIGN_MASK_ADDR: SET_U16_LSB(idtcm->channel[2].output_mask, val); break; - case OUTPUT_MASK_PLL2_ADDR + 1: + case TOD2_OUT_ALIGN_MASK_ADDR + 1: SET_U16_MSB(idtcm->channel[2].output_mask, val); break; - case OUTPUT_MASK_PLL3_ADDR: + case TOD3_OUT_ALIGN_MASK_ADDR: SET_U16_LSB(idtcm->channel[3].output_mask, val); break; - case OUTPUT_MASK_PLL3_ADDR + 1: + case TOD3_OUT_ALIGN_MASK_ADDR + 1: SET_U16_MSB(idtcm->channel[3].output_mask, val); break; default: - err = -EINVAL; + err = -EFAULT; /* Bad address */; break; } return err; } +static int set_tod_ptp_pll(struct idtcm *idtcm, u8 index, u8 pll) +{ + if (index >= MAX_TOD) { + dev_err(&idtcm->client->dev, "ToD%d not supported\n", index); + return -EINVAL; + } + + if (pll >= MAX_PLL) { + dev_err(&idtcm->client->dev, "Pll%d not supported\n", pll); + return -EINVAL; + } + + idtcm->channel[index].pll = pll; + + return 0; +} + static int check_and_set_masks(struct idtcm *idtcm, u16 regaddr, u8 val) { int err = 0; - if (set_pll_output_mask(idtcm, regaddr, val)) { - /* Not an output mask, check for pll mask */ - err = process_pll_mask(idtcm, regaddr, val, &idtcm->pll_mask); + switch (regaddr) { + case TOD_MASK_ADDR: + if ((val & 0xf0) || !(val & 0x0f)) { + dev_err(&idtcm->client->dev, + "Invalid TOD mask 0x%hhx\n", val); + err = -EINVAL; + } else { + idtcm->tod_mask = val; + } + break; + case TOD0_PTP_PLL_ADDR: + err = set_tod_ptp_pll(idtcm, 0, val); + break; + case TOD1_PTP_PLL_ADDR: + err = set_tod_ptp_pll(idtcm, 1, val); + break; + case TOD2_PTP_PLL_ADDR: + err = set_tod_ptp_pll(idtcm, 2, val); + break; + case TOD3_PTP_PLL_ADDR: + err = set_tod_ptp_pll(idtcm, 3, val); + break; + default: + err = set_pll_output_mask(idtcm, regaddr, val); + break; } return err; } -static void display_pll_and_output_masks(struct idtcm *idtcm) +static void display_pll_and_masks(struct idtcm *idtcm) { u8 i; u8 mask; - dev_dbg(&idtcm->client->dev, "pllmask = 0x%02x\n", idtcm->pll_mask); + dev_dbg(&idtcm->client->dev, "tod_mask = 0x%02x\n", idtcm->tod_mask); - for (i = 0; i < MAX_PHC_PLL; i++) { + for (i = 0; i < MAX_TOD; i++) { mask = 1 << i; - if (mask & idtcm->pll_mask) + if (mask & idtcm->tod_mask) dev_dbg(&idtcm->client->dev, - "PLL%d output_mask = 0x%04x\n", - i, idtcm->channel[i].output_mask); + "TOD%d pll = %d output_mask = 0x%04x\n", + i, idtcm->channel[i].pll, + idtcm->channel[i].output_mask); } } static int idtcm_load_firmware(struct idtcm *idtcm, struct device *dev) { + char fname[128] = FW_FILENAME; const struct firmware *fw; struct idtcm_fwrc *rec; u32 regaddr; @@ -751,12 +1067,20 @@ static int idtcm_load_firmware(struct idtcm *idtcm, u8 val; u8 loaddr; - dev_dbg(&idtcm->client->dev, "requesting firmware '%s'\n", FW_FILENAME); + if (firmware) /* module parameter */ + snprintf(fname, sizeof(fname), "%s", firmware); - err = request_firmware(&fw, FW_FILENAME, dev); + dev_dbg(&idtcm->client->dev, "requesting firmware '%s'\n", fname); - if (err) + err = request_firmware(&fw, fname, dev); + + if (err) { + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); return err; + } dev_dbg(&idtcm->client->dev, "firmware size %zu bytes\n", fw->size); @@ -783,7 +1107,9 @@ static int idtcm_load_firmware(struct idtcm *idtcm, err = check_and_set_masks(idtcm, regaddr, val); } - if (err == 0) { + if (err != -EINVAL) { + err = 0; + /* Top (status registers) and bottom are read-only */ if ((regaddr < GPIO_USER_CONTROL) || (regaddr >= SCRATCH)) @@ -801,42 +1127,22 @@ static int idtcm_load_firmware(struct idtcm *idtcm, goto out; } - display_pll_and_output_masks(idtcm); + display_pll_and_masks(idtcm); out: release_firmware(fw); return err; } -static int idtcm_pps_enable(struct idtcm_channel *channel, bool enable) +static int idtcm_output_enable(struct idtcm_channel *channel, + bool enable, unsigned int outn) { struct idtcm *idtcm = channel->idtcm; - u32 module; - u8 val; int err; + u8 val; - /* - * This assumes that the 1-PPS is on the second of the two - * output. But is this always true? - */ - switch (channel->dpll_n) { - case DPLL_0: - module = OUTPUT_1; - break; - case DPLL_1: - module = OUTPUT_3; - break; - case DPLL_2: - module = OUTPUT_5; - break; - case DPLL_3: - module = OUTPUT_7; - break; - default: - return -EINVAL; - } - - err = idtcm_read(idtcm, module, OUT_CTRL_1, &val, sizeof(val)); + err = idtcm_read(idtcm, OUTPUT_MODULE_FROM_INDEX(outn), + OUT_CTRL_1, &val, sizeof(val)); if (err) return err; @@ -846,14 +1152,50 @@ static int idtcm_pps_enable(struct idtcm_channel *channel, bool enable) else val &= ~SQUELCH_DISABLE; - err = idtcm_write(idtcm, module, OUT_CTRL_1, &val, sizeof(val)); + return idtcm_write(idtcm, OUTPUT_MODULE_FROM_INDEX(outn), + OUT_CTRL_1, &val, sizeof(val)); +} - if (err) - return err; +static int idtcm_output_mask_enable(struct idtcm_channel *channel, + bool enable) +{ + u16 mask; + int err; + u8 outn; + + mask = channel->output_mask; + outn = 0; + + while (mask) { + + if (mask & 0x1) { + + err = idtcm_output_enable(channel, enable, outn); + + if (err) + return err; + } + + mask >>= 0x1; + outn++; + } return 0; } +static int idtcm_perout_enable(struct idtcm_channel *channel, + bool enable, + struct ptp_perout_request *perout) +{ + unsigned int flags = perout->flags; + + if (flags == PEROUT_ENABLE_OUTPUT_MASK) + return idtcm_output_mask_enable(channel, enable); + + /* Enable/disable individual output instead */ + return idtcm_output_enable(channel, enable, perout->index); +} + static int idtcm_set_pll_mode(struct idtcm_channel *channel, enum pll_mode pll_mode) { @@ -940,10 +1282,8 @@ static int _idtcm_adjphase(struct idtcm_channel *channel, s32 delta_ns) return err; } -static int idtcm_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int _idtcm_adjfine(struct idtcm_channel *channel, long scaled_ppm) { - struct idtcm_channel *channel = - container_of(ptp, struct idtcm_channel, caps); struct idtcm *idtcm = channel->idtcm; u8 i; bool neg_adj = 0; @@ -970,15 +1310,15 @@ static int idtcm_adjfreq(struct ptp_clock_info *ptp, s32 ppb) * FCW = ------------- * 111 * 2^4 */ - if (ppb < 0) { + if (scaled_ppm < 0) { neg_adj = 1; - ppb = -ppb; + scaled_ppm = -scaled_ppm; } /* 2 ^ -53 = 1.1102230246251565404236316680908e-16 */ - fcw = ppb * 1000000000000ULL; + fcw = scaled_ppm * 244140625ULL; - fcw = div_u64(fcw, 111022); + fcw = div_u64(fcw, 1776); if (neg_adj) fcw = -fcw; @@ -988,12 +1328,9 @@ static int idtcm_adjfreq(struct ptp_clock_info *ptp, s32 ppb) fcw >>= 8; } - mutex_lock(&idtcm->reg_lock); - err = idtcm_write(idtcm, channel->dpll_freq, DPLL_WR_FREQ, buf, sizeof(buf)); - mutex_unlock(&idtcm->reg_lock); return err; } @@ -1008,6 +1345,12 @@ static int idtcm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) err = _idtcm_gettime(channel, ts); + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + mutex_unlock(&idtcm->reg_lock); return err; @@ -1025,6 +1368,35 @@ static int idtcm_settime(struct ptp_clock_info *ptp, err = _idtcm_settime(channel, ts, HW_TOD_WR_TRIG_SEL_MSB); + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + + mutex_unlock(&idtcm->reg_lock); + + return err; +} + +static int idtcm_settime_v487(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct idtcm_channel *channel = + container_of(ptp, struct idtcm_channel, caps); + struct idtcm *idtcm = channel->idtcm; + int err; + + mutex_lock(&idtcm->reg_lock); + + err = _idtcm_settime_v487(channel, ts, SCSR_TOD_WR_TYPE_SEL_ABSOLUTE); + + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + mutex_unlock(&idtcm->reg_lock); return err; @@ -1041,6 +1413,54 @@ static int idtcm_adjtime(struct ptp_clock_info *ptp, s64 delta) err = _idtcm_adjtime(channel, delta); + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + + mutex_unlock(&idtcm->reg_lock); + + return err; +} + +static int idtcm_adjtime_v487(struct ptp_clock_info *ptp, s64 delta) +{ + struct idtcm_channel *channel = + container_of(ptp, struct idtcm_channel, caps); + struct idtcm *idtcm = channel->idtcm; + struct timespec64 ts; + enum scsr_tod_write_type_sel type; + int err; + + if (abs(delta) < PHASE_PULL_IN_THRESHOLD_NS_V487) { + err = idtcm_do_phase_pull_in(channel, delta, 0); + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + return err; + } + + if (delta >= 0) { + ts = ns_to_timespec64(delta); + type = SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS; + } else { + ts = ns_to_timespec64(-delta); + type = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS; + } + + mutex_lock(&idtcm->reg_lock); + + err = _idtcm_settime_v487(channel, &ts, type); + + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + mutex_unlock(&idtcm->reg_lock); return err; @@ -1059,6 +1479,36 @@ static int idtcm_adjphase(struct ptp_clock_info *ptp, s32 delta) err = _idtcm_adjphase(channel, delta); + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + + mutex_unlock(&idtcm->reg_lock); + + return err; +} + +static int idtcm_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct idtcm_channel *channel = + container_of(ptp, struct idtcm_channel, caps); + + struct idtcm *idtcm = channel->idtcm; + + int err; + + mutex_lock(&idtcm->reg_lock); + + err = _idtcm_adjfine(channel, scaled_ppm); + + if (err) + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + mutex_unlock(&idtcm->reg_lock); return err; @@ -1067,20 +1517,35 @@ static int idtcm_adjphase(struct ptp_clock_info *ptp, s32 delta) static int idtcm_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { + int err; + struct idtcm_channel *channel = container_of(ptp, struct idtcm_channel, caps); switch (rq->type) { case PTP_CLK_REQ_PEROUT: - if (!on) - return idtcm_pps_enable(channel, false); + if (!on) { + err = idtcm_perout_enable(channel, false, &rq->perout); + if (err) + dev_err(&channel->idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + return err; + } /* Only accept a 1-PPS aligned to the second. */ if (rq->perout.start.nsec || rq->perout.period.sec != 1 || rq->perout.period.nsec) return -ERANGE; - return idtcm_pps_enable(channel, true); + err = idtcm_perout_enable(channel, true, &rq->perout); + if (err) + dev_err(&channel->idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + return err; default: break; } @@ -1088,17 +1553,237 @@ static int idtcm_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } -static int idtcm_enable_tod(struct idtcm_channel *channel) +static int _enable_pll_tod_sync(struct idtcm *idtcm, + u8 pll, + u8 sync_src, + u8 qn, + u8 qn_plus_1) +{ + int err; + u8 val; + u16 dpll; + u16 out0 = 0, out1 = 0; + + if ((qn == 0) && (qn_plus_1 == 0)) + return 0; + + switch (pll) { + case 0: + dpll = DPLL_0; + if (qn) + out0 = OUTPUT_0; + if (qn_plus_1) + out1 = OUTPUT_1; + break; + case 1: + dpll = DPLL_1; + if (qn) + out0 = OUTPUT_2; + if (qn_plus_1) + out1 = OUTPUT_3; + break; + case 2: + dpll = DPLL_2; + if (qn) + out0 = OUTPUT_4; + if (qn_plus_1) + out1 = OUTPUT_5; + break; + case 3: + dpll = DPLL_3; + if (qn) + out0 = OUTPUT_6; + if (qn_plus_1) + out1 = OUTPUT_7; + break; + case 4: + dpll = DPLL_4; + if (qn) + out0 = OUTPUT_8; + break; + case 5: + dpll = DPLL_5; + if (qn) + out0 = OUTPUT_9; + if (qn_plus_1) + out1 = OUTPUT_8; + break; + case 6: + dpll = DPLL_6; + if (qn) + out0 = OUTPUT_10; + if (qn_plus_1) + out1 = OUTPUT_11; + break; + case 7: + dpll = DPLL_7; + if (qn) + out0 = OUTPUT_11; + break; + default: + return -EINVAL; + } + + /* + * Enable OUTPUT OUT_SYNC. + */ + if (out0) { + err = idtcm_read(idtcm, out0, OUT_CTRL_1, &val, sizeof(val)); + + if (err) + return err; + + val &= ~OUT_SYNC_DISABLE; + + err = idtcm_write(idtcm, out0, OUT_CTRL_1, &val, sizeof(val)); + + if (err) + return err; + } + + if (out1) { + err = idtcm_read(idtcm, out1, OUT_CTRL_1, &val, sizeof(val)); + + if (err) + return err; + + val &= ~OUT_SYNC_DISABLE; + + err = idtcm_write(idtcm, out1, OUT_CTRL_1, &val, sizeof(val)); + + if (err) + return err; + } + + /* enable dpll sync tod pps, must be set before dpll_mode */ + err = idtcm_read(idtcm, dpll, DPLL_TOD_SYNC_CFG, &val, sizeof(val)); + if (err) + return err; + + val &= ~(TOD_SYNC_SOURCE_MASK << TOD_SYNC_SOURCE_SHIFT); + val |= (sync_src << TOD_SYNC_SOURCE_SHIFT); + val |= TOD_SYNC_EN; + + return idtcm_write(idtcm, dpll, DPLL_TOD_SYNC_CFG, &val, sizeof(val)); +} + +static int idtcm_enable_tod_sync(struct idtcm_channel *channel) { struct idtcm *idtcm = channel->idtcm; - struct timespec64 ts = {0, 0}; + + u8 pll; + u8 sync_src; + u8 qn; + u8 qn_plus_1; u8 cfg; - int err; + int err = 0; + u16 output_mask = channel->output_mask; + u8 out8_mux = 0; + u8 out11_mux = 0; + u8 temp; + + /* + * set tod_out_sync_enable to 0. + */ + err = idtcm_read(idtcm, channel->tod_n, TOD_CFG, &cfg, sizeof(cfg)); + if (err) + return err; + + cfg &= ~TOD_OUT_SYNC_ENABLE; + + err = idtcm_write(idtcm, channel->tod_n, TOD_CFG, &cfg, sizeof(cfg)); + if (err) + return err; + + switch (channel->tod_n) { + case TOD_0: + sync_src = 0; + break; + case TOD_1: + sync_src = 1; + break; + case TOD_2: + sync_src = 2; + break; + case TOD_3: + sync_src = 3; + break; + default: + return -EINVAL; + } - err = idtcm_pps_enable(channel, false); + err = idtcm_read(idtcm, 0, HW_Q8_CTRL_SPARE, + &temp, sizeof(temp)); if (err) return err; + if ((temp & Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) == + Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) + out8_mux = 1; + + err = idtcm_read(idtcm, 0, HW_Q11_CTRL_SPARE, + &temp, sizeof(temp)); + if (err) + return err; + + if ((temp & Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) == + Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) + out11_mux = 1; + + for (pll = 0; pll < 8; pll++) { + qn = 0; + qn_plus_1 = 0; + + if (pll < 4) { + /* First 4 pll has 2 outputs */ + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + qn_plus_1 = output_mask & 0x1; + output_mask = output_mask >> 1; + } else if (pll == 4) { + if (out8_mux == 0) { + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + } + } else if (pll == 5) { + if (out8_mux) { + qn_plus_1 = output_mask & 0x1; + output_mask = output_mask >> 1; + } + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + } else if (pll == 6) { + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + if (out11_mux) { + qn_plus_1 = output_mask & 0x1; + output_mask = output_mask >> 1; + } + } else if (pll == 7) { + if (out11_mux == 0) { + qn = output_mask & 0x1; + output_mask = output_mask >> 1; + } + } + + if ((qn != 0) || (qn_plus_1 != 0)) + err = _enable_pll_tod_sync(idtcm, pll, sync_src, qn, + qn_plus_1); + + if (err) + return err; + } + + return err; +} + +static int idtcm_enable_tod(struct idtcm_channel *channel) +{ + struct idtcm *idtcm = channel->idtcm; + struct timespec64 ts = {0, 0}; + u8 cfg; + int err; + /* * Start the TOD clock ticking. */ @@ -1134,16 +1819,32 @@ static void idtcm_display_version_info(struct idtcm *idtcm) idtcm_read_otp_scsr_config_select(idtcm, &config_select); + snprintf(idtcm->version, sizeof(idtcm->version), "%u.%u.%u", + major, minor, hotfix); + dev_info(&idtcm->client->dev, fmt, major, minor, hotfix, product_id, hw_rev_id, config_select); } +static const struct ptp_clock_info idtcm_caps_v487 = { + .owner = THIS_MODULE, + .max_adj = 244000, + .n_per_out = 12, + .adjphase = &idtcm_adjphase, + .adjfine = &idtcm_adjfine, + .adjtime = &idtcm_adjtime_v487, + .gettime64 = &idtcm_gettime, + .settime64 = &idtcm_settime_v487, + .enable = &idtcm_enable, + .do_aux_work = &set_write_phase_ready, +}; + static const struct ptp_clock_info idtcm_caps = { .owner = THIS_MODULE, .max_adj = 244000, - .n_per_out = 1, + .n_per_out = 12, .adjphase = &idtcm_adjphase, - .adjfreq = &idtcm_adjfreq, + .adjfine = &idtcm_adjfine, .adjtime = &idtcm_adjtime, .gettime64 = &idtcm_gettime, .settime64 = &idtcm_settime, @@ -1151,24 +1852,14 @@ static const struct ptp_clock_info idtcm_caps = { .do_aux_work = &set_write_phase_ready, }; - -static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) +static int configure_channel_pll(struct idtcm_channel *channel) { - struct idtcm_channel *channel; - int err; - - if (!(index < MAX_PHC_PLL)) - return -EINVAL; - - channel = &idtcm->channel[index]; + int err = 0; - switch (index) { + switch (channel->pll) { case 0: channel->dpll_freq = DPLL_FREQ_0; channel->dpll_n = DPLL_0; - channel->tod_read_primary = TOD_READ_PRIMARY_0; - channel->tod_write = TOD_WRITE_0; - channel->tod_n = TOD_0; channel->hw_dpll_n = HW_DPLL_0; channel->dpll_phase = DPLL_PHASE_0; channel->dpll_ctrl_n = DPLL_CTRL_0; @@ -1177,9 +1868,6 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) case 1: channel->dpll_freq = DPLL_FREQ_1; channel->dpll_n = DPLL_1; - channel->tod_read_primary = TOD_READ_PRIMARY_1; - channel->tod_write = TOD_WRITE_1; - channel->tod_n = TOD_1; channel->hw_dpll_n = HW_DPLL_1; channel->dpll_phase = DPLL_PHASE_1; channel->dpll_ctrl_n = DPLL_CTRL_1; @@ -1188,9 +1876,6 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) case 2: channel->dpll_freq = DPLL_FREQ_2; channel->dpll_n = DPLL_2; - channel->tod_read_primary = TOD_READ_PRIMARY_2; - channel->tod_write = TOD_WRITE_2; - channel->tod_n = TOD_2; channel->hw_dpll_n = HW_DPLL_2; channel->dpll_phase = DPLL_PHASE_2; channel->dpll_ctrl_n = DPLL_CTRL_2; @@ -1199,31 +1884,129 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) case 3: channel->dpll_freq = DPLL_FREQ_3; channel->dpll_n = DPLL_3; - channel->tod_read_primary = TOD_READ_PRIMARY_3; - channel->tod_write = TOD_WRITE_3; - channel->tod_n = TOD_3; channel->hw_dpll_n = HW_DPLL_3; channel->dpll_phase = DPLL_PHASE_3; channel->dpll_ctrl_n = DPLL_CTRL_3; channel->dpll_phase_pull_in = DPLL_PHASE_PULL_IN_3; break; + case 4: + channel->dpll_freq = DPLL_FREQ_4; + channel->dpll_n = DPLL_4; + channel->hw_dpll_n = HW_DPLL_4; + channel->dpll_phase = DPLL_PHASE_4; + channel->dpll_ctrl_n = DPLL_CTRL_4; + channel->dpll_phase_pull_in = DPLL_PHASE_PULL_IN_4; + break; + case 5: + channel->dpll_freq = DPLL_FREQ_5; + channel->dpll_n = DPLL_5; + channel->hw_dpll_n = HW_DPLL_5; + channel->dpll_phase = DPLL_PHASE_5; + channel->dpll_ctrl_n = DPLL_CTRL_5; + channel->dpll_phase_pull_in = DPLL_PHASE_PULL_IN_5; + break; + case 6: + channel->dpll_freq = DPLL_FREQ_6; + channel->dpll_n = DPLL_6; + channel->hw_dpll_n = HW_DPLL_6; + channel->dpll_phase = DPLL_PHASE_6; + channel->dpll_ctrl_n = DPLL_CTRL_6; + channel->dpll_phase_pull_in = DPLL_PHASE_PULL_IN_6; + break; + case 7: + channel->dpll_freq = DPLL_FREQ_7; + channel->dpll_n = DPLL_7; + channel->hw_dpll_n = HW_DPLL_7; + channel->dpll_phase = DPLL_PHASE_7; + channel->dpll_ctrl_n = DPLL_CTRL_7; + channel->dpll_phase_pull_in = DPLL_PHASE_PULL_IN_7; + break; + default: + err = -EINVAL; + } + + return err; +} + +static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) +{ + struct idtcm_channel *channel; + int err; + + if (!(index < MAX_TOD)) + return -EINVAL; + + channel = &idtcm->channel[index]; + + /* Set pll addresses */ + err = configure_channel_pll(channel); + if (err) + return err; + + /* Set tod addresses */ + switch (index) { + case 0: + channel->tod_read_primary = TOD_READ_PRIMARY_0; + channel->tod_write = TOD_WRITE_0; + channel->tod_n = TOD_0; + break; + case 1: + channel->tod_read_primary = TOD_READ_PRIMARY_1; + channel->tod_write = TOD_WRITE_1; + channel->tod_n = TOD_1; + break; + case 2: + channel->tod_read_primary = TOD_READ_PRIMARY_2; + channel->tod_write = TOD_WRITE_2; + channel->tod_n = TOD_2; + break; + case 3: + channel->tod_read_primary = TOD_READ_PRIMARY_3; + channel->tod_write = TOD_WRITE_3; + channel->tod_n = TOD_3; + break; default: return -EINVAL; } channel->idtcm = idtcm; - channel->caps = idtcm_caps; + if (idtcm_strverscmp(idtcm->version, "4.8.7") >= 0) + channel->caps = idtcm_caps_v487; + else + channel->caps = idtcm_caps; + snprintf(channel->caps.name, sizeof(channel->caps.name), - "IDT CM PLL%u", index); + "IDT CM TOD%u", index); + + if (idtcm_strverscmp(idtcm->version, "4.8.7") >= 0) { + err = idtcm_enable_tod_sync(channel); + if (err) { + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); + return err; + } + } err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_FREQUENCY); - if (err) + if (err) { + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); return err; + } err = idtcm_enable_tod(channel); - if (err) + if (err) { + dev_err(&idtcm->client->dev, + "Failed at line %d in func %s!\n", + __LINE__, + __func__); return err; + } channel->ptp_clock = ptp_clock_register(&channel->caps, NULL); @@ -1249,7 +2032,7 @@ static void ptp_clock_unregister_all(struct idtcm *idtcm) u8 i; struct idtcm_channel *channel; - for (i = 0; i < MAX_PHC_PLL; i++) { + for (i = 0; i < MAX_TOD; i++) { channel = &idtcm->channel[i]; @@ -1260,7 +2043,12 @@ static void ptp_clock_unregister_all(struct idtcm *idtcm) static void set_default_masks(struct idtcm *idtcm) { - idtcm->pll_mask = DEFAULT_PLL_MASK; + idtcm->tod_mask = DEFAULT_TOD_MASK; + + idtcm->channel[0].pll = DEFAULT_TOD0_PTP_PLL; + idtcm->channel[1].pll = DEFAULT_TOD1_PTP_PLL; + idtcm->channel[2].pll = DEFAULT_TOD2_PTP_PLL; + idtcm->channel[3].pll = DEFAULT_TOD3_PTP_PLL; idtcm->channel[0].output_mask = DEFAULT_OUTPUT_MASK_PLL0; idtcm->channel[1].output_mask = DEFAULT_OUTPUT_MASK_PLL1; @@ -1268,51 +2056,13 @@ static void set_default_masks(struct idtcm *idtcm) idtcm->channel[3].output_mask = DEFAULT_OUTPUT_MASK_PLL3; } -static int set_tod_write_overhead(struct idtcm *idtcm) -{ - int err; - u8 i; - - s64 total_ns = 0; - - ktime_t start; - ktime_t stop; - - char buf[TOD_BYTE_COUNT]; - - struct idtcm_channel *channel = &idtcm->channel[2]; - - /* Set page offset */ - idtcm_write(idtcm, channel->hw_dpll_n, HW_DPLL_TOD_OVR__0, - buf, sizeof(buf)); - - for (i = 0; i < TOD_WRITE_OVERHEAD_COUNT_MAX; i++) { - - start = ktime_get_raw(); - - err = idtcm_write(idtcm, channel->hw_dpll_n, - HW_DPLL_TOD_OVR__0, buf, sizeof(buf)); - - if (err) - return err; - - stop = ktime_get_raw(); - - total_ns += ktime_to_ns(stop - start); - } - - idtcm->tod_write_overhead_ns = div_s64(total_ns, - TOD_WRITE_OVERHEAD_COUNT_MAX); - - return err; -} - static int idtcm_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct idtcm *idtcm; int err; u8 i; + char *fmt = "Failed at %d in line %s with channel output %d!\n"; /* Unused for now */ (void)id; @@ -1333,25 +2083,24 @@ static int idtcm_probe(struct i2c_client *client, idtcm_display_version_info(idtcm); - err = set_tod_write_overhead(idtcm); - - if (err) { - mutex_unlock(&idtcm->reg_lock); - return err; - } - err = idtcm_load_firmware(idtcm, &client->dev); if (err) dev_warn(&idtcm->client->dev, "loading firmware failed with %d\n", err); - if (idtcm->pll_mask) { - for (i = 0; i < MAX_PHC_PLL; i++) { - if (idtcm->pll_mask & (1 << i)) { + if (idtcm->tod_mask) { + for (i = 0; i < MAX_TOD; i++) { + if (idtcm->tod_mask & (1 << i)) { err = idtcm_enable_channel(idtcm, i); - if (err) + if (err) { + dev_err(&idtcm->client->dev, + fmt, + __LINE__, + __func__, + i); break; + } } } } else { diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h index 3de0eb72889c..ffae56c5d97f 100644 --- a/drivers/ptp/ptp_clockmatrix.h +++ b/drivers/ptp/ptp_clockmatrix.h @@ -13,32 +13,48 @@ #include "idt8a340_reg.h" #define FW_FILENAME "idtcm.bin" -#define MAX_PHC_PLL 4 +#define MAX_TOD (4) +#define MAX_PLL (8) #define MAX_ABS_WRITE_PHASE_PICOSECONDS (107374182350LL) -#define PLL_MASK_ADDR (0xFFA5) -#define DEFAULT_PLL_MASK (0x04) +#define TOD_MASK_ADDR (0xFFA5) +#define DEFAULT_TOD_MASK (0x04) #define SET_U16_LSB(orig, val8) (orig = (0xff00 & (orig)) | (val8)) #define SET_U16_MSB(orig, val8) (orig = (0x00ff & (orig)) | (val8 << 8)) -#define OUTPUT_MASK_PLL0_ADDR (0xFFB0) -#define OUTPUT_MASK_PLL1_ADDR (0xFFB2) -#define OUTPUT_MASK_PLL2_ADDR (0xFFB4) -#define OUTPUT_MASK_PLL3_ADDR (0xFFB6) +#define TOD0_PTP_PLL_ADDR (0xFFA8) +#define TOD1_PTP_PLL_ADDR (0xFFA9) +#define TOD2_PTP_PLL_ADDR (0xFFAA) +#define TOD3_PTP_PLL_ADDR (0xFFAB) + +#define TOD0_OUT_ALIGN_MASK_ADDR (0xFFB0) +#define TOD1_OUT_ALIGN_MASK_ADDR (0xFFB2) +#define TOD2_OUT_ALIGN_MASK_ADDR (0xFFB4) +#define TOD3_OUT_ALIGN_MASK_ADDR (0xFFB6) #define DEFAULT_OUTPUT_MASK_PLL0 (0x003) #define DEFAULT_OUTPUT_MASK_PLL1 (0x00c) #define DEFAULT_OUTPUT_MASK_PLL2 (0x030) #define DEFAULT_OUTPUT_MASK_PLL3 (0x0c0) +#define DEFAULT_TOD0_PTP_PLL (0) +#define DEFAULT_TOD1_PTP_PLL (1) +#define DEFAULT_TOD2_PTP_PLL (2) +#define DEFAULT_TOD3_PTP_PLL (3) + #define POST_SM_RESET_DELAY_MS (3000) #define PHASE_PULL_IN_THRESHOLD_NS (150000) -#define TOD_WRITE_OVERHEAD_COUNT_MAX (5) +#define PHASE_PULL_IN_THRESHOLD_NS_V487 (15000) +#define TOD_WRITE_OVERHEAD_COUNT_MAX (2) #define TOD_BYTE_COUNT (11) #define WR_PHASE_SETUP_MS (5000) +#define OUTPUT_MODULE_FROM_INDEX(index) (OUTPUT_0 + (index) * 0x10) + +#define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef) + /* Values of DPLL_N.DPLL_MODE.PLL_MODE */ enum pll_mode { PLL_MODE_MIN = 0, @@ -48,7 +64,8 @@ enum pll_mode { PLL_MODE_GPIO_INC_DEC = 3, PLL_MODE_SYNTHESIS = 4, PLL_MODE_PHASE_MEASUREMENT = 5, - PLL_MODE_MAX = PLL_MODE_PHASE_MEASUREMENT, + PLL_MODE_DISABLED = 6, + PLL_MODE_MAX = PLL_MODE_DISABLED, }; enum hw_tod_write_trig_sel { @@ -63,6 +80,26 @@ enum hw_tod_write_trig_sel { WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_FOD_SYNC, }; +/* 4.8.7 only */ +enum scsr_tod_write_trig_sel { + SCSR_TOD_WR_TRIG_SEL_DISABLE = 0, + SCSR_TOD_WR_TRIG_SEL_IMMEDIATE = 1, + SCSR_TOD_WR_TRIG_SEL_REFCLK = 2, + SCSR_TOD_WR_TRIG_SEL_PWMPPS = 3, + SCSR_TOD_WR_TRIG_SEL_TODPPS = 4, + SCSR_TOD_WR_TRIG_SEL_SYNCFOD = 5, + SCSR_TOD_WR_TRIG_SEL_GPIO = 6, + SCSR_TOD_WR_TRIG_SEL_MAX = SCSR_TOD_WR_TRIG_SEL_GPIO, +}; + +/* 4.8.7 only */ +enum scsr_tod_write_type_sel { + SCSR_TOD_WR_TYPE_SEL_ABSOLUTE = 0, + SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS = 1, + SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS = 2, + SCSR_TOD_WR_TYPE_SEL_MAX = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS, +}; + struct idtcm; struct idtcm_channel { @@ -79,15 +116,17 @@ struct idtcm_channel { u16 tod_n; u16 hw_dpll_n; enum pll_mode pll_mode; + u8 pll; u16 output_mask; int write_phase_ready; }; struct idtcm { - struct idtcm_channel channel[MAX_PHC_PLL]; + struct idtcm_channel channel[MAX_TOD]; struct i2c_client *client; u8 page_offset; - u8 pll_mask; + u8 tod_mask; + char version[16]; /* Overhead calculation for adjtime */ u8 calculate_overhead_flag; diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index c7fade836d83..5fbe9eae84d1 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -231,7 +231,7 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct smcd_dmb *dmb) bit = find_next_zero_bit(ism->sba_bitmap, ISM_NR_DMBS, ISM_DMB_BIT_OFFSET); if (bit == ISM_NR_DMBS) - return -ENOMEM; + return -ENOSPC; dmb->sba_idx = bit; } diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 3d54c8bbfa86..ecfd6d152e86 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -764,6 +764,7 @@ struct qeth_rx { u8 buf_element; int e_offset; int qdio_err; + u8 bufs_refill; }; struct carrier_info { @@ -833,7 +834,6 @@ struct qeth_card { struct napi_struct napi; struct qeth_rx rx; struct delayed_work buffer_reclaim_work; - int reclaim_index; struct work_struct close_dev_work; }; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8a76022fceda..bba1b54b8aa3 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -204,12 +204,17 @@ EXPORT_SYMBOL_GPL(qeth_threads_running); void qeth_clear_working_pool_list(struct qeth_card *card) { struct qeth_buffer_pool_entry *pool_entry, *tmp; + struct qeth_qdio_q *queue = card->qdio.in_q; + unsigned int i; QETH_CARD_TEXT(card, 5, "clwrklst"); list_for_each_entry_safe(pool_entry, tmp, &card->qdio.in_buf_pool.entry_list, list){ list_del(&pool_entry->list); } + + for (i = 0; i < ARRAY_SIZE(queue->bufs); i++) + queue->bufs[i].pool_entry = NULL; } EXPORT_SYMBOL_GPL(qeth_clear_working_pool_list); @@ -2965,7 +2970,7 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( static int qeth_init_input_buffer(struct qeth_card *card, struct qeth_qdio_buffer *buf) { - struct qeth_buffer_pool_entry *pool_entry; + struct qeth_buffer_pool_entry *pool_entry = buf->pool_entry; int i; if ((card->options.cq == QETH_CQ_ENABLED) && (!buf->rx_skb)) { @@ -2976,9 +2981,13 @@ static int qeth_init_input_buffer(struct qeth_card *card, return -ENOMEM; } - pool_entry = qeth_find_free_buffer_pool_entry(card); - if (!pool_entry) - return -ENOBUFS; + if (!pool_entry) { + pool_entry = qeth_find_free_buffer_pool_entry(card); + if (!pool_entry) + return -ENOBUFS; + + buf->pool_entry = pool_entry; + } /* * since the buffer is accessed only from the input_tasklet @@ -2986,8 +2995,6 @@ static int qeth_init_input_buffer(struct qeth_card *card, * the QETH_IN_BUF_REQUEUE_THRESHOLD we should never run out off * buffers */ - - buf->pool_entry = pool_entry; for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { buf->buffer->element[i].length = PAGE_SIZE; buf->buffer->element[i].addr = @@ -3015,6 +3022,7 @@ static unsigned int qeth_tx_select_bulk_max(struct qeth_card *card, static int qeth_init_qdio_queues(struct qeth_card *card) { + unsigned int rx_bufs = card->qdio.in_buf_pool.buf_count; unsigned int i; int rc; @@ -3026,16 +3034,14 @@ static int qeth_init_qdio_queues(struct qeth_card *card) qeth_initialize_working_pool_list(card); /*give only as many buffers to hardware as we have buffer pool entries*/ - for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; i++) { + for (i = 0; i < rx_bufs; i++) { rc = qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]); if (rc) return rc; } - card->qdio.in_q->next_buf_to_init = - card->qdio.in_buf_pool.buf_count - 1; - rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, - card->qdio.in_buf_pool.buf_count - 1); + card->qdio.in_q->next_buf_to_init = QDIO_BUFNR(rx_bufs); + rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, rx_bufs); if (rc) { QETH_CARD_TEXT_(card, 2, "1err%d", rc); return rc; @@ -3485,20 +3491,15 @@ static int qeth_check_qdio_errors(struct qeth_card *card, return 0; } -static void qeth_queue_input_buffer(struct qeth_card *card, int index) +static unsigned int qeth_rx_refill_queue(struct qeth_card *card, + unsigned int count) { struct qeth_qdio_q *queue = card->qdio.in_q; struct list_head *lh; - int count; int i; int rc; int newcount = 0; - count = (index < queue->next_buf_to_init)? - card->qdio.in_buf_pool.buf_count - - (queue->next_buf_to_init - index) : - card->qdio.in_buf_pool.buf_count - - (queue->next_buf_to_init + QDIO_MAX_BUFFERS_PER_Q - index); /* only requeue at a certain threshold to avoid SIGAs */ if (count >= QETH_IN_BUF_REQUEUE_THRESHOLD(card)) { for (i = queue->next_buf_to_init; @@ -3526,21 +3527,13 @@ static void qeth_queue_input_buffer(struct qeth_card *card, int index) i++; if (i == card->qdio.in_buf_pool.buf_count) { QETH_CARD_TEXT(card, 2, "qsarbw"); - card->reclaim_index = index; schedule_delayed_work( &card->buffer_reclaim_work, QETH_RECLAIM_WORK_TIME); } - return; + return 0; } - /* - * according to old code it should be avoided to requeue all - * 128 buffers in order to benefit from PCI avoidance. - * this function keeps at least one buffer (the buffer at - * 'index') un-requeued -> this buffer is the first buffer that - * will be requeued the next time - */ rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, queue->next_buf_to_init, count); if (rc) { @@ -3548,7 +3541,10 @@ static void qeth_queue_input_buffer(struct qeth_card *card, int index) } queue->next_buf_to_init = QDIO_BUFNR(queue->next_buf_to_init + count); + return count; } + + return 0; } static void qeth_buffer_reclaim_work(struct work_struct *work) @@ -3556,8 +3552,10 @@ static void qeth_buffer_reclaim_work(struct work_struct *work) struct qeth_card *card = container_of(work, struct qeth_card, buffer_reclaim_work.work); - QETH_CARD_TEXT_(card, 2, "brw:%x", card->reclaim_index); - qeth_queue_input_buffer(card, card->reclaim_index); + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } static void qeth_handle_send_error(struct qeth_card *card, @@ -5736,6 +5734,7 @@ static unsigned int qeth_extract_skbs(struct qeth_card *card, int budget, static unsigned int qeth_rx_poll(struct qeth_card *card, int budget) { + struct qeth_rx *ctx = &card->rx; unsigned int work_done = 0; while (budget > 0) { @@ -5771,8 +5770,11 @@ static unsigned int qeth_rx_poll(struct qeth_card *card, int budget) if (done) { QETH_CARD_STAT_INC(card, rx_bufs); qeth_put_buffer_pool_entry(card, buffer->pool_entry); - qeth_queue_input_buffer(card, card->rx.b_index); + buffer->pool_entry = NULL; card->rx.b_count--; + ctx->bufs_refill++; + ctx->bufs_refill -= qeth_rx_refill_queue(card, + ctx->bufs_refill); /* Step forward to next buffer: */ card->rx.b_index = QDIO_BUFNR(card->rx.b_index + 1); @@ -5812,9 +5814,16 @@ int qeth_poll(struct napi_struct *napi, int budget) if (card->options.cq == QETH_CQ_ENABLED) qeth_cq_poll(card); - /* Exhausted the RX budget. Keep IRQ disabled, we get called again. */ - if (budget && work_done >= budget) - return work_done; + if (budget) { + struct qeth_rx *ctx = &card->rx; + + /* Process any substantial refill backlog: */ + ctx->bufs_refill -= qeth_rx_refill_queue(card, ctx->bufs_refill); + + /* Exhausted the RX budget. Keep IRQ disabled, we get called again. */ + if (work_done >= budget) + return work_done; + } if (napi_complete_done(napi, work_done) && qdio_start_irq(CARD_DDEV(card))) @@ -7001,6 +7010,7 @@ int qeth_stop(struct net_device *dev) } napi_disable(&card->napi); + cancel_delayed_work_sync(&card->buffer_reclaim_work); qdio_stop_irq(CARD_DDEV(card)); return 0; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index ef7a2db7a724..8b342a88ff5c 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -285,7 +285,6 @@ static void qeth_l2_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_clear_ipacmd_list(card); qeth_drain_output_queues(card); - cancel_delayed_work_sync(&card->buffer_reclaim_work); card->state = CARD_STATE_DOWN; } @@ -1141,6 +1140,10 @@ static void qeth_bridge_state_change(struct qeth_card *card, int extrasize; QETH_CARD_TEXT(card, 2, "brstchng"); + if (qports->num_entries == 0) { + QETH_CARD_TEXT(card, 2, "BPempty"); + return; + } if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) { QETH_CARD_TEXT_(card, 2, "BPsz%04x", qports->entry_length); return; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 15a12487ff7a..fe44b0249e34 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1169,7 +1169,6 @@ static void qeth_l3_stop_card(struct qeth_card *card) qeth_l3_clear_ip_htable(card, 1); qeth_clear_ipacmd_list(card); qeth_drain_output_queues(card); - cancel_delayed_work_sync(&card->buffer_reclaim_work); card->state = CARD_STATE_DOWN; } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0ba7a65e7c8d..06056e9ec333 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -547,6 +547,15 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) scsi_uninit_cmd(cmd); } +static void scsi_run_queue_async(struct scsi_device *sdev) +{ + if (scsi_target(sdev)->single_lun || + !list_empty(&sdev->host->starved_list)) + kblockd_schedule_work(&sdev->requeue_work); + else + blk_mq_run_hw_queues(sdev->request_queue, true); +} + /* Returns false when no more bytes to process, true if there are more */ static bool scsi_end_request(struct request *req, blk_status_t error, unsigned int bytes) @@ -591,11 +600,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, __blk_mq_end_request(req, error); - if (scsi_target(sdev)->single_lun || - !list_empty(&sdev->host->starved_list)) - kblockd_schedule_work(&sdev->requeue_work); - else - blk_mq_run_hw_queues(q, true); + scsi_run_queue_async(sdev); percpu_ref_put(&q->q_usage_counter); return false; @@ -1702,6 +1707,7 @@ out_put_budget: */ if (req->rq_flags & RQF_DONTPREP) scsi_mq_uninit_cmd(cmd); + scsi_run_queue_async(sdev); break; } return ret; diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c index 560649be9d13..e035c9f757a1 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1032.c +++ b/drivers/staging/comedi/drivers/addi_apci_1032.c @@ -106,14 +106,22 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1032_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -136,8 +144,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA | @@ -154,8 +162,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c index 689acd69a1b9..816dd25b9d0e 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1500.c +++ b/drivers/staging/comedi/drivers/addi_apci_1500.c @@ -452,13 +452,14 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, struct apci1500_private *devpriv = dev->private; unsigned int trig = data[1]; unsigned int shift = data[3]; - unsigned int hi_mask = data[4] << shift; - unsigned int lo_mask = data[5] << shift; - unsigned int chan_mask = hi_mask | lo_mask; - unsigned int old_mask = (1 << shift) - 1; + unsigned int hi_mask; + unsigned int lo_mask; + unsigned int chan_mask; + unsigned int old_mask; unsigned int pm; unsigned int pt; unsigned int pp; + unsigned int invalid_chan; if (trig > 1) { dev_dbg(dev->class_dev, @@ -466,7 +467,20 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, return -EINVAL; } - if (chan_mask > 0xffff) { + if (shift <= 16) { + hi_mask = data[4] << shift; + lo_mask = data[5] << shift; + old_mask = (1U << shift) - 1; + invalid_chan = (data[4] | data[5]) >> (16 - shift); + } else { + hi_mask = 0; + lo_mask = 0; + old_mask = 0xffff; + invalid_chan = data[4] | data[5]; + } + chan_mask = hi_mask | lo_mask; + + if (invalid_chan) { dev_dbg(dev->class_dev, "invalid digital trigger channel\n"); return -EINVAL; } diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c index 10501fe6bb25..1268ba34be5f 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1564.c +++ b/drivers/staging/comedi/drivers/addi_apci_1564.c @@ -331,14 +331,22 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1564_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -362,8 +370,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA | @@ -380,8 +388,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c index 4d1eccb5041d..4518c2680b7c 100644 --- a/drivers/staging/comedi/drivers/ni_6527.c +++ b/drivers/staging/comedi/drivers/ni_6527.c @@ -332,7 +332,7 @@ static int ni6527_intr_insn_config(struct comedi_device *dev, case COMEDI_DIGITAL_TRIG_ENABLE_EDGES: /* check shift amount */ shift = data[3]; - if (shift >= s->n_chan) { + if (shift >= 32) { mask = 0; rising = 0; falling = 0; diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c index 4689b2170e4f..456603fd26c0 100644 --- a/drivers/staging/wlan-ng/prism2usb.c +++ b/drivers/staging/wlan-ng/prism2usb.c @@ -61,11 +61,25 @@ static int prism2sta_probe_usb(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *dev; - + const struct usb_endpoint_descriptor *epd; + const struct usb_host_interface *iface_desc = interface->cur_altsetting; struct wlandevice *wlandev = NULL; struct hfa384x *hw = NULL; int result = 0; + if (iface_desc->desc.bNumEndpoints != 2) { + result = -ENODEV; + goto failed; + } + + result = -EINVAL; + epd = &iface_desc->endpoint[1].desc; + if (!usb_endpoint_is_bulk_in(epd)) + goto failed; + epd = &iface_desc->endpoint[2].desc; + if (!usb_endpoint_is_bulk_out(epd)) + goto failed; + dev = interface_to_usbdev(interface); wlandev = create_wlan(); if (!wlandev) { diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index fc118f649887..cae61d1ebec5 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -524,6 +524,7 @@ static void __init serial8250_isa_init_ports(void) */ up->mcr_mask = ~ALPHA_KLUDGE_MCR; up->mcr_force = ALPHA_KLUDGE_MCR; + serial8250_set_defaults(up); } /* chain base port ops to support Remote Supervisor Adapter */ @@ -547,7 +548,6 @@ static void __init serial8250_isa_init_ports(void) port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; - serial8250_set_defaults(up); port->irqflags |= irqflag; if (serial8250_isa_config != NULL) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index ddb6aeb76dc5..04b9af7ed941 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -326,7 +326,17 @@ static void setup_gpio(struct pci_dev *pcidev, u8 __iomem *p) * devices will export them as GPIOs, so we pre-configure them safely * as inputs. */ - u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00; + + u8 dir = 0x00; + + if ((pcidev->vendor == PCI_VENDOR_ID_EXAR) && + (pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) { + // Configure GPIO as inputs for Commtech adapters + dir = 0xff; + } else { + // Configure GPIO as outputs for SeaLevel adapters + dir = 0x00; + } writeb(0x00, p + UART_EXAR_MPIOINT_7_0); writeb(0x00, p + UART_EXAR_MPIOLVL_7_0); diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f839380c2f4c..98b8a3e30733 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -306,8 +306,21 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, } #endif + /* + * Store the requested baud rate before calling the generic 8250 + * set_termios method. Standard 8250 port expects bauds to be + * no higher than (uartclk / 16) so the baud will be clamped if it + * gets out of that bound. Mediatek 8250 port supports speed + * higher than that, therefore we'll get original baud rate back + * after calling the generic set_termios method and recalculate + * the speed later in this method. + */ + baud = tty_termios_baud_rate(termios); + serial8250_do_set_termios(port, termios, old); + tty_termios_encode_baud_rate(termios, baud, baud); + /* * Mediatek UARTs use an extra highspeed register (MTK_UART_HIGHS) * @@ -339,6 +352,11 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, */ spin_lock_irqsave(&port->lock, flags); + /* + * Update the per-port timeout. + */ + uart_update_timeout(port, termios->c_cflag, baud); + /* set DLAB we have cval saved in up->lcr from the call to the core */ serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB); serial_dl_write(up, quot); diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 8de8bac9c6c7..04d1b0807e66 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -635,7 +635,7 @@ static void tegra_uart_handle_tx_pio(struct tegra_uart_port *tup) } static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup, - struct tty_port *tty) + struct tty_port *port) { do { char flag = TTY_NORMAL; @@ -653,16 +653,18 @@ static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup, ch = (unsigned char) tegra_uart_read(tup, UART_RX); tup->uport.icount.rx++; - if (!uart_handle_sysrq_char(&tup->uport, ch) && tty) - tty_insert_flip_char(tty, ch, flag); + if (uart_handle_sysrq_char(&tup->uport, ch)) + continue; if (tup->uport.ignore_status_mask & UART_LSR_DR) continue; + + tty_insert_flip_char(port, ch, flag); } while (1); } static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, - struct tty_port *tty, + struct tty_port *port, unsigned int count) { int copied; @@ -672,17 +674,13 @@ static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, return; tup->uport.icount.rx += count; - if (!tty) { - dev_err(tup->uport.dev, "No tty port\n"); - return; - } if (tup->uport.ignore_status_mask & UART_LSR_DR) return; dma_sync_single_for_cpu(tup->uport.dev, tup->rx_dma_buf_phys, count, DMA_FROM_DEVICE); - copied = tty_insert_flip_string(tty, + copied = tty_insert_flip_string(port, ((unsigned char *)(tup->rx_dma_buf_virt)), count); if (copied != count) { WARN_ON(1); diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 672cfa075e28..2833f1418d6d 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1580,8 +1580,10 @@ static int cdns_uart_probe(struct platform_device *pdev) * If register_console() don't assign value, then console_port pointer * is cleanup. */ - if (!console_port) + if (!console_port) { + cdns_uart_console.index = id; console_port = port; + } #endif rc = uart_add_one_port(&cdns_uart_uart_driver, port); @@ -1594,8 +1596,10 @@ static int cdns_uart_probe(struct platform_device *pdev) #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE /* This is not port which is used for console that's why clean it up */ if (console_port == port && - !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) + !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) { console_port = NULL; + cdns_uart_console.index = -1; + } #endif cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node, diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 48a8199f7845..42d8c67a481f 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1092,10 +1092,19 @@ static const struct tty_port_operations vc_port_ops = { .destruct = vc_port_destruct, }; +/* + * Change # of rows and columns (0 means unchanged/the size of fg_console) + * [this is to be used together with some user program + * like resize that changes the hardware videomode] + */ +#define VC_MAXCOL (32767) +#define VC_MAXROW (32767) + int vc_allocate(unsigned int currcons) /* return 0 on success */ { struct vt_notifier_param param; struct vc_data *vc; + int err; WARN_CONSOLE_UNLOCKED(); @@ -1125,6 +1134,11 @@ int vc_allocate(unsigned int currcons) /* return 0 on success */ if (!*vc->vc_uni_pagedir_loc) con_set_default_unimap(vc); + err = -EINVAL; + if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW || + vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size) + goto err_free; + err = -ENOMEM; vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL); if (!vc->vc_screenbuf) goto err_free; @@ -1143,7 +1157,7 @@ err_free: visual_deinit(vc); kfree(vc); vc_cons[currcons].d = NULL; - return -ENOMEM; + return err; } static inline int resize_screen(struct vc_data *vc, int width, int height, @@ -1158,14 +1172,6 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, return err; } -/* - * Change # of rows and columns (0 means unchanged/the size of fg_console) - * [this is to be used together with some user program - * like resize that changes the hardware videomode] - */ -#define VC_RESIZE_MAXCOL (32767) -#define VC_RESIZE_MAXROW (32767) - /** * vc_do_resize - resizing method for the tty * @tty: tty being resized @@ -1201,7 +1207,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, user = vc->vc_resize_user; vc->vc_resize_user = 0; - if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW) + if (cols > VC_MAXCOL || lines > VC_MAXROW) return -EINVAL; new_cols = (cols ? cols : vc->vc_cols); @@ -1212,7 +1218,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, if (new_cols == vc->vc_cols && new_rows == vc->vc_rows) return 0; - if (new_screen_size > KMALLOC_MAX_SIZE) + if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size) return -EINVAL; newscreen = kzalloc(new_screen_size, GFP_USER); if (!newscreen) @@ -3393,6 +3399,7 @@ static int __init con_init(void) INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK); tty_port_init(&vc->port); visual_init(vc, currcons, 1); + /* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */ vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT); vc_init(vc, vc->vc_rows, vc->vc_cols, currcons || !vc->vc_sw->con_save_screen); diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index fea555570ad4..45c54d56ecbd 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -557,6 +557,10 @@ static bool need_bw_sch(struct usb_host_endpoint *ep, if (is_fs_or_ls(speed) && !has_tt) return false; + /* skip endpoint with zero maxpkt */ + if (usb_endpoint_maxp(&ep->desc) == 0) + return false; + return true; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ef513c2fb843..9234c82e70e4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -265,6 +265,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1142) xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && + pdev->device == 0x2142) + xhci->quirks |= XHCI_NO_64BIT_SUPPORT; if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 2eaf5c0af80c..ee6bf01775bb 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -856,7 +856,7 @@ static int tegra_xusb_init_context(struct tegra_xusb *tegra) if (!tegra->context.ipfs) return -ENOMEM; - tegra->context.fpci = devm_kcalloc(tegra->dev, soc->ipfs.num_offsets, + tegra->context.fpci = devm_kcalloc(tegra->dev, soc->fpci.num_offsets, sizeof(u32), GFP_KERNEL); if (!tegra->context.fpci) return -ENOMEM; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 6fb4d7ecfa19..b22adf03f584 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1215,7 +1215,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) continue; } - switch (v_req.type) { + switch (vhost32_to_cpu(vq, v_req.type)) { case VIRTIO_SCSI_T_TMF: vc.req = &v_req.tmf; vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req); diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index ca935c09a261..35ebeeccde4d 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -216,7 +216,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = info->var.xoffset + rs; region.dy = 0; region.width = rw; @@ -224,7 +224,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset + bs; region.width = rs; diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index dfa9a8aa4509..78f3a5621478 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -201,7 +201,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset; region.height = rw; @@ -209,7 +209,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset + bs; region.dy = 0; region.height = info->var.yres_virtual; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index ce08251bfd38..fd098ff17574 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -184,7 +184,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset + rs; region.height = rw; @@ -192,7 +192,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset; region.height = info->var.yres; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 1936afc78fec..e165a3fad29a 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -231,7 +231,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dy = 0; region.dx = info->var.xoffset; region.width = rw; @@ -239,7 +239,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dy = info->var.yoffset; region.dx = info->var.xoffset; region.height = bh; diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 5809e5f5b157..5c92e4a50882 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -85,7 +85,7 @@ config VIRTIO_MEM depends on VIRTIO depends on MEMORY_HOTPLUG_SPARSE depends on MEMORY_HOTREMOVE - select CONTIG_ALLOC + depends on CONTIG_ALLOC help This driver provides access to virtio-mem paravirtualized memory devices, allowing to hotplug and hotunplug memory. diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 1f157d2f4952..8be02f333b7a 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -578,10 +578,14 @@ static int init_vqs(struct virtio_balloon *vb) static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) { if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, - &vb->config_read_bitmap)) + &vb->config_read_bitmap)) { virtio_cread(vb->vdev, struct virtio_balloon_config, free_page_hint_cmd_id, &vb->cmd_id_received_cache); + /* Legacy balloon config space is LE, unlike all other devices. */ + if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) + vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache); + } return vb->cmd_id_received_cache; } @@ -974,6 +978,11 @@ static int virtballoon_probe(struct virtio_device *vdev) /* * Let the hypervisor know that we are expecting a * specific value to be written back in balloon pages. + * + * If the PAGE_POISON value was larger than a byte we would + * need to byte swap poison_val here to guarantee it is + * little-endian. However for now it is a single byte so we + * can pass it as-is. */ if (!want_init_on_free()) memset(&poison_val, PAGE_POISON, sizeof(poison_val)); diff --git a/fs/io_uring.c b/fs/io_uring.c index 32b0064f806e..493e5047e67c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4199,10 +4199,9 @@ static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt) hash_del(&req->hash_node); io_poll_complete(req, req->result, 0); - req->flags |= REQ_F_COMP_LOCKED; - io_put_req_find_next(req, nxt); spin_unlock_irq(&ctx->completion_lock); + io_put_req_find_next(req, nxt); io_cqring_ev_posted(ctx); } @@ -4658,6 +4657,10 @@ static int io_poll_add(struct io_kiocb *req) struct io_poll_table ipt; __poll_t mask; + /* ->work is in union with hash_node and others */ + io_req_work_drop_env(req); + req->flags &= ~REQ_F_WORK_INITIALIZED; + INIT_HLIST_NODE(&req->hash_node); INIT_LIST_HEAD(&req->list); ipt.pt._qproc = io_poll_queue_proc; diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 8b1e020e9a03..30a3aab312e6 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -456,7 +456,7 @@ static inline void writesq(volatile void __iomem *addr, const void *buffer, #if !defined(inb) && !defined(_inb) #define _inb _inb -static inline u16 _inb(unsigned long addr) +static inline u8 _inb(unsigned long addr) { u8 val; @@ -482,7 +482,7 @@ static inline u16 _inw(unsigned long addr) #if !defined(inl) && !defined(_inl) #define _inl _inl -static inline u16 _inl(unsigned long addr) +static inline u32 _inl(unsigned long addr) { u32 val; diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 6c3ef49b46b3..e73dea5c7333 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -866,6 +866,18 @@ struct drm_mode_config { bool prefer_shadow_fbdev; /** + * @fbdev_use_iomem: + * + * Set to true if framebuffer reside in iomem. + * When set to true memcpy_toio() is used when copying the framebuffer in + * drm_fb_helper.drm_fb_helper_dirty_blit_real(). + * + * FIXME: This should be replaced with a per-mapping is_iomem + * flag (like ttm does), and then used everywhere in fbdev code. + */ + bool fbdev_use_iomem; + + /** * @quirk_addfb_prefer_xbgr_30bpp: * * Special hack for legacy ADDFB to keep nouveau userspace happy. Should diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h new file mode 100644 index 000000000000..5a3470bcc8a7 --- /dev/null +++ b/include/linux/dsa/loop.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef DSA_LOOP_H +#define DSA_LOOP_H + +#include <linux/types.h> +#include <linux/ethtool.h> +#include <net/dsa.h> + +struct dsa_loop_vlan { + u16 members; + u16 untagged; +}; + +struct dsa_loop_mib_entry { + char name[ETH_GSTRING_LEN]; + unsigned long val; +}; + +enum dsa_loop_mib_counters { + DSA_LOOP_PHY_READ_OK, + DSA_LOOP_PHY_READ_ERR, + DSA_LOOP_PHY_WRITE_OK, + DSA_LOOP_PHY_WRITE_ERR, + __DSA_LOOP_CNT_MAX, +}; + +struct dsa_loop_port { + struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX]; + u16 pvid; + int mtu; +}; + +struct dsa_loop_priv { + struct mii_bus *bus; + unsigned int port_base; + struct dsa_loop_vlan vlans[VLAN_N_VID]; + struct net_device *netdev; + struct dsa_loop_port ports[DSA_MAX_PORTS]; +}; + +#endif /* DSA_LOOP_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index ee328cf80bd9..4e7714c88f95 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1001,7 +1001,7 @@ static inline u32 i2c_acpi_find_bus_speed(struct device *dev) static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) { diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9f732499ea88..c47f43e65a2f 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2561,6 +2561,8 @@ enum ieee80211_statuscode { /* 802.11ai */ WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, + WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, + WLAN_STATUS_SAE_PK = 127, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6a97ad601991..a0fcc4d13e93 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -541,7 +541,7 @@ struct mlx5_priv { /* pages stuff */ struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; - struct rb_root page_root; + struct xarray page_root_xa; int fw_pages; atomic_t reg_pages; struct list_head free_list; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9e64710bc54f..35e4dc66b326 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4388,6 +4388,7 @@ struct mlx5_ifc_query_vport_state_out_bits { enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_UPLINK = 0x2, }; struct mlx5_ifc_arm_monitor_counter_in_bits { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1046763cd0dc..88d40b9abaa1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2063,6 +2063,8 @@ struct net_device { struct timer_list watchdog_timer; int watchdog_timeo; + u32 proto_down_reason; + struct list_head todo_list; int __percpu *pcpu_refcnt; @@ -3818,6 +3820,8 @@ int dev_get_port_parent_id(struct net_device *dev, bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); +void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, + u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0403eb799913..3a09d2bf69ea 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -293,6 +293,8 @@ struct mii_bus { /* GPIO reset pulse width in microseconds */ int reset_delay_us; + /* GPIO reset deassert delay in microseconds */ + int reset_post_delay_us; /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h new file mode 100644 index 000000000000..0fc831338226 --- /dev/null +++ b/include/linux/pldmfw.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#ifndef _PLDMFW_H_ +#define _PLDMFW_H_ + +#include <linux/list.h> +#include <linux/firmware.h> + +#define PLDM_DEVICE_UPDATE_CONTINUE_AFTER_FAIL BIT(0) + +#define PLDM_STRING_TYPE_UNKNOWN 0 +#define PLDM_STRING_TYPE_ASCII 1 +#define PLDM_STRING_TYPE_UTF8 2 +#define PLDM_STRING_TYPE_UTF16 3 +#define PLDM_STRING_TYPE_UTF16LE 4 +#define PLDM_STRING_TYPE_UTF16BE 5 + +struct pldmfw_record { + struct list_head entry; + + /* List of descriptor TLVs */ + struct list_head descs; + + /* Component Set version string*/ + const u8 *version_string; + u8 version_type; + u8 version_len; + + /* Package Data length */ + u16 package_data_len; + + /* Bitfield of Device Update Flags */ + u32 device_update_flags; + + /* Package Data block */ + const u8 *package_data; + + /* Bitmap of components applicable to this record */ + unsigned long *component_bitmap; + u16 component_bitmap_len; +}; + +/* Standard descriptor TLV identifiers */ +#define PLDM_DESC_ID_PCI_VENDOR_ID 0x0000 +#define PLDM_DESC_ID_IANA_ENTERPRISE_ID 0x0001 +#define PLDM_DESC_ID_UUID 0x0002 +#define PLDM_DESC_ID_PNP_VENDOR_ID 0x0003 +#define PLDM_DESC_ID_ACPI_VENDOR_ID 0x0004 +#define PLDM_DESC_ID_PCI_DEVICE_ID 0x0100 +#define PLDM_DESC_ID_PCI_SUBVENDOR_ID 0x0101 +#define PLDM_DESC_ID_PCI_SUBDEV_ID 0x0102 +#define PLDM_DESC_ID_PCI_REVISION_ID 0x0103 +#define PLDM_DESC_ID_PNP_PRODUCT_ID 0x0104 +#define PLDM_DESC_ID_ACPI_PRODUCT_ID 0x0105 +#define PLDM_DESC_ID_VENDOR_DEFINED 0xFFFF + +struct pldmfw_desc_tlv { + struct list_head entry; + + const u8 *data; + u16 type; + u16 size; +}; + +#define PLDM_CLASSIFICATION_UNKNOWN 0x0000 +#define PLDM_CLASSIFICATION_OTHER 0x0001 +#define PLDM_CLASSIFICATION_DRIVER 0x0002 +#define PLDM_CLASSIFICATION_CONFIG_SW 0x0003 +#define PLDM_CLASSIFICATION_APP_SW 0x0004 +#define PLDM_CLASSIFICATION_INSTRUMENTATION 0x0005 +#define PLDM_CLASSIFICATION_BIOS 0x0006 +#define PLDM_CLASSIFICATION_DIAGNOSTIC_SW 0x0007 +#define PLDM_CLASSIFICATION_OS 0x0008 +#define PLDM_CLASSIFICATION_MIDDLEWARE 0x0009 +#define PLDM_CLASSIFICATION_FIRMWARE 0x000A +#define PLDM_CLASSIFICATION_CODE 0x000B +#define PLDM_CLASSIFICATION_SERVICE_PACK 0x000C +#define PLDM_CLASSIFICATION_SOFTWARE_BUNDLE 0x000D + +#define PLDM_ACTIVATION_METHOD_AUTO BIT(0) +#define PLDM_ACTIVATION_METHOD_SELF_CONTAINED BIT(1) +#define PLDM_ACTIVATION_METHOD_MEDIUM_SPECIFIC BIT(2) +#define PLDM_ACTIVATION_METHOD_REBOOT BIT(3) +#define PLDM_ACTIVATION_METHOD_DC_CYCLE BIT(4) +#define PLDM_ACTIVATION_METHOD_AC_CYCLE BIT(5) + +#define PLDMFW_COMPONENT_OPTION_FORCE_UPDATE BIT(0) +#define PLDMFW_COMPONENT_OPTION_USE_COMPARISON_STAMP BIT(1) + +struct pldmfw_component { + struct list_head entry; + + /* component identifier */ + u16 classification; + u16 identifier; + + u16 options; + u16 activation_method; + + u32 comparison_stamp; + + u32 component_size; + const u8 *component_data; + + /* Component version string */ + const u8 *version_string; + u8 version_type; + u8 version_len; + + /* component index */ + u8 index; + +}; + +/* Transfer flag used for sending components to the firmware */ +#define PLDM_TRANSFER_FLAG_START BIT(0) +#define PLDM_TRANSFER_FLAG_MIDDLE BIT(1) +#define PLDM_TRANSFER_FLAG_END BIT(2) + +struct pldmfw_ops; + +/* Main entry point to the PLDM firmware update engine. Device drivers + * should embed this in a private structure and use container_of to obtain + * a pointer to their own data, used to implement the device specific + * operations. + */ +struct pldmfw { + const struct pldmfw_ops *ops; + struct device *dev; +}; + +bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record); + +/* Operations invoked by the generic PLDM firmware update engine. Used to + * implement device specific logic. + * + * @match_record: check if the device matches the given record. For + * convenience, a standard implementation is provided for PCI devices. + * + * @send_package_data: send the package data associated with the matching + * record to firmware. + * + * @send_component_table: send the component data associated with a given + * component to firmware. Called once for each applicable component. + * + * @flash_component: Flash the data for a given component to the device. + * Called once for each applicable component, after all component tables have + * been sent. + * + * @finalize_update: (optional) Finish the update. Called after all components + * have been flashed. + */ +struct pldmfw_ops { + bool (*match_record)(struct pldmfw *context, struct pldmfw_record *record); + int (*send_package_data)(struct pldmfw *context, const u8 *data, u16 length); + int (*send_component_table)(struct pldmfw *context, struct pldmfw_component *component, + u8 transfer_flag); + int (*flash_component)(struct pldmfw *context, struct pldmfw_component *component); + int (*finalize_update)(struct pldmfw *context); +}; + +int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw); + +#endif diff --git a/include/linux/random.h b/include/linux/random.h index 45e1f8fa742b..9ab7443bd91b 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/once.h> +#include <asm/percpu.h> #include <uapi/linux/random.h> @@ -119,6 +120,8 @@ struct rnd_state { __u32 s1, s2, s3, s4; }; +DECLARE_PER_CPU(struct rnd_state, net_rand_state); + u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d3432ee65de7..68dab3e08aad 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -84,7 +84,7 @@ struct bucket_table { struct lockdep_map dep_map; - struct rhash_lock_head *buckets[] ____cacheline_aligned_in_smp; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* @@ -261,13 +261,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -284,21 +283,21 @@ struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -static inline struct rhash_lock_head *const *rht_bucket( +static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_var( +static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_insert( +static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : @@ -325,7 +324,7 @@ static inline struct rhash_lock_head **rht_bucket_insert( */ static inline void rht_lock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { local_bh_disable(); bit_spin_lock(0, (unsigned long *)bkt); @@ -333,7 +332,7 @@ static inline void rht_lock(struct bucket_table *tbl, } static inline void rht_lock_nested(struct bucket_table *tbl, - struct rhash_lock_head **bucket, + struct rhash_lock_head __rcu **bucket, unsigned int subclass) { local_bh_disable(); @@ -342,18 +341,18 @@ static inline void rht_lock_nested(struct bucket_table *tbl, } static inline void rht_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); local_bh_enable(); } -static inline struct rhash_head __rcu *__rht_ptr( - struct rhash_lock_head *const *bkt) +static inline struct rhash_head *__rht_ptr( + struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) { - return (struct rhash_head __rcu *) - ((unsigned long)*bkt & ~BIT(0) ?: + return (struct rhash_head *) + ((unsigned long)p & ~BIT(0) ?: (unsigned long)RHT_NULLS_MARKER(bkt)); } @@ -365,47 +364,41 @@ static inline struct rhash_head __rcu *__rht_ptr( * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head __rcu *const *bkt) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - return rcu_dereference(p); + return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( - struct rhash_lock_head *const *bkt, + struct rhash_lock_head __rcu *const *bkt, struct bucket_table *tbl, unsigned int hash) { - return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash); + return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head __rcu *const *bkt) { - return rcu_dereference_protected(__rht_ptr(bkt), 1); + return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } -static inline void rht_assign_locked(struct rhash_lock_head **bkt, +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; - rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0))); + rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; lock_map_release(&tbl->dep_map); - rcu_assign_pointer(*p, obj); + rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); local_bh_enable(); @@ -593,7 +586,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - struct rhash_lock_head *const *bkt; + struct rhash_lock_head __rcu *const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -709,7 +702,7 @@ static inline void *__rhashtable_insert_fast( .ht = ht, .key = key, }; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; @@ -995,7 +988,7 @@ static inline int __rhashtable_remove_fast_one( struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; @@ -1147,7 +1140,7 @@ static inline int __rhashtable_replace_fast( struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fa817a105517..3ad65d4ce085 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -283,6 +283,7 @@ struct nf_bridge_info { */ struct tc_skb_ext { __u32 chain; + __u16 mru; }; #endif diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 7d5cdb2b30b5..96840def9d69 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -27,14 +27,6 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p }; } - -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) -{ - if ((unsigned long)p >= TASK_SIZE) - return -EFAULT; - sp->user = p; - return 0; -} #else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { @@ -53,33 +45,44 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } +#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p, + size_t size) { - sp->user = p; - sp->is_kernel = false; + if (!access_ok(p, size)) + return -EFAULT; + *sp = (sockptr_t) { .user = p }; return 0; } -#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ static inline bool sockptr_is_null(sockptr_t sockptr) { - return !sockptr.user && !sockptr.kernel; + if (sockptr_is_kernel(sockptr)) + return !sockptr.kernel; + return !sockptr.user; } -static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, + size_t offset, size_t size) { if (!sockptr_is_kernel(src)) - return copy_from_user(dst, src.user, size); - memcpy(dst, src.kernel, size); + return copy_from_user(dst, src.user + offset, size); + memcpy(dst, src.kernel + offset, size); return 0; } -static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +{ + return copy_from_sockptr_offset(dst, src, 0, size); +} + +static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, + const void *src, size_t size) { if (!sockptr_is_kernel(dst)) - return copy_to_user(dst.user, src, size); - memcpy(dst.kernel, src, size); + return copy_to_user(dst.user + offset, src, size); + memcpy(dst.kernel + offset, src, size); return 0; } @@ -110,14 +113,6 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) return p; } -static inline void sockptr_advance(sockptr_t sockptr, size_t len) -{ - if (sockptr_is_kernel(sockptr)) - sockptr.kernel += len; - else - sockptr.user += len; -} - static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 527d668a5275..14b62d7df942 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -484,7 +484,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } -struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk); +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, + const struct sk_buff *orig_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { diff --git a/include/net/addrconf.h b/include/net/addrconf.h index fdb07105384c..8418b7d38468 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -274,6 +274,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); +void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 18190055374c..9125effbf448 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -41,6 +41,8 @@ #define BLUETOOTH_VER_1_1 1 #define BLUETOOTH_VER_1_2 2 #define BLUETOOTH_VER_2_0 3 +#define BLUETOOTH_VER_2_1 4 +#define BLUETOOTH_VER_4_0 6 /* Reserv for core and drivers use */ #define BT_SKB_RESERVE 8 @@ -147,6 +149,10 @@ struct bt_voice { #define BT_MODE_LE_FLOWCTL 0x03 #define BT_MODE_EXT_FLOWCTL 0x04 +#define BT_PKT_STATUS 16 + +#define BT_SCM_PKT_STATUS 0x03 + __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) @@ -286,6 +292,7 @@ struct bt_sock { struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); + void (*skb_put_cmsg)(struct sk_buff *, struct msghdr *, struct sock *); }; enum { @@ -335,6 +342,10 @@ struct l2cap_ctrl { struct l2cap_chan *chan; }; +struct sco_ctrl { + u8 pkt_status; +}; + struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); @@ -361,6 +372,7 @@ struct bt_skb_cb { u8 incoming:1; union { struct l2cap_ctrl l2cap; + struct sco_ctrl sco; struct hci_ctrl hci; }; }; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 16ab6ce87883..c8e67042a3b1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -227,6 +227,17 @@ enum { * supported. */ HCI_QUIRK_VALID_LE_STATES, + + /* When this quirk is set, then erroneous data reporting + * is ignored. This is mainly due to the fact that the HCI + * Read Default Erroneous Data Reporting command is advertised, + * but not supported; these controllers often reply with unknown + * command and tend to lock up randomly. Needing a hard reset. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, }; /* HCI device flags */ @@ -307,6 +318,7 @@ enum { HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, + HCI_ENABLE_LL_PRIVACY, HCI_CMD_PENDING, HCI_FORCE_NO_MITM, @@ -1637,6 +1649,8 @@ struct hci_rp_le_read_resolv_list_size { #define HCI_OP_LE_SET_ADDR_RESOLV_ENABLE 0x202d +#define HCI_OP_LE_SET_RPA_TIMEOUT 0x202e + #define HCI_OP_LE_READ_MAX_DATA_LEN 0x202f struct hci_rp_le_read_max_data_len { __u8 status; @@ -2268,8 +2282,10 @@ struct hci_ev_le_conn_complete { #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 +#define ADDR_LE_DEV_PUBLIC 0x00 +#define ADDR_LE_DEV_RANDOM 0x01 +#define ADDR_LE_DEV_PUBLIC_RESOLVED 0x02 +#define ADDR_LE_DEV_RANDOM_RESOLVED 0x03 #define HCI_EV_LE_ADVERTISING_REPORT 0x02 struct hci_ev_le_advertising_info { @@ -2516,4 +2532,12 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb) #define hci_iso_data_len(h) ((h) & 0x3fff) #define hci_iso_data_flags(h) ((h) >> 14) +/* le24 support */ +static inline void hci_cpu_to_le24(__u32 val, __u8 dst[3]) +{ + dst[0] = val & 0xff; + dst[1] = (val & 0xff00) >> 8; + dst[2] = (val & 0xff0000) >> 16; +} + #endif /* __HCI_H */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index cdd4f1db8670..8caac20556b4 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -25,6 +25,7 @@ #ifndef __HCI_CORE_H #define __HCI_CORE_H +#include <linux/idr.h> #include <linux/leds.h> #include <linux/rculist.h> @@ -136,6 +137,23 @@ struct bdaddr_list_with_irk { u8 local_irk[16]; }; +struct bdaddr_list_with_flags { + struct list_head list; + bdaddr_t bdaddr; + u8 bdaddr_type; + u32 current_flags; +}; + +enum hci_conn_flags { + HCI_CONN_FLAG_REMOTE_WAKEUP, + HCI_CONN_FLAG_MAX +}; + +#define hci_conn_test_flag(nr, flags) ((flags) & (1U << nr)) + +/* Make sure number of flags doesn't exceed sizeof(current_flags) */ +static_assert(HCI_CONN_FLAG_MAX < 32); + struct bt_uuid { struct list_head list; u8 uuid[16]; @@ -220,6 +238,24 @@ struct adv_info { #define HCI_MAX_ADV_INSTANCES 5 #define HCI_DEFAULT_ADV_DURATION 2 +struct adv_pattern { + struct list_head list; + __u8 ad_type; + __u8 offset; + __u8 length; + __u8 value[HCI_MAX_AD_LENGTH]; +}; + +struct adv_monitor { + struct list_head patterns; + bool active; + __u16 handle; +}; + +#define HCI_MIN_ADV_MONITOR_HANDLE 1 +#define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32 +#define HCI_MAX_ADV_MONITOR_NUM_PATTERNS 16 + #define HCI_MAX_SHORT_NAME_LENGTH 10 /* Min encryption key size to match with SMP */ @@ -295,6 +331,14 @@ struct hci_dev { __u8 le_scan_type; __u16 le_scan_interval; __u16 le_scan_window; + __u16 le_scan_int_suspend; + __u16 le_scan_window_suspend; + __u16 le_scan_int_discovery; + __u16 le_scan_window_discovery; + __u16 le_scan_int_adv_monitor; + __u16 le_scan_window_adv_monitor; + __u16 le_scan_int_connect; + __u16 le_scan_window_connect; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_latency; @@ -323,6 +367,17 @@ struct hci_dev { __u16 devid_product; __u16 devid_version; + __u8 def_page_scan_type; + __u16 def_page_scan_int; + __u16 def_page_scan_window; + __u8 def_inq_scan_type; + __u16 def_inq_scan_int; + __u16 def_inq_scan_window; + __u16 def_br_lsto; + __u16 def_page_timeout; + __u16 def_multi_adv_rotation_duration; + __u16 def_le_autoconnect_timeout; + __u16 pkt_type; __u16 esco_type; __u16 link_policy; @@ -438,7 +493,6 @@ struct hci_dev { struct list_head mgmt_pending; struct list_head blacklist; struct list_head whitelist; - struct list_head wakeable; struct list_head uuids; struct list_head link_keys; struct list_head long_term_keys; @@ -477,6 +531,9 @@ struct hci_dev { __u16 adv_instance_timeout; struct delayed_work adv_instance_expire; + struct idr adv_monitors_idr; + unsigned int adv_monitors_cnt; + __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; @@ -508,6 +565,12 @@ struct hci_dev { #define HCI_PHY_HANDLE(handle) (handle & 0xff) +enum conn_reasons { + CONN_REASON_PAIR_DEVICE, + CONN_REASON_L2CAP_CHAN, + CONN_REASON_SCO_CONNECT, +}; + struct hci_conn { struct list_head list; @@ -559,6 +622,8 @@ struct hci_conn { __s8 max_tx_power; unsigned long flags; + enum conn_reasons conn_reason; + __u32 clock; __u16 clock_accuracy; @@ -626,7 +691,7 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; - bool wakeable; + u32 current_flags; }; extern struct list_head hci_dev_list; @@ -984,12 +1049,14 @@ struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle); struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, - u16 conn_timeout); + u16 conn_timeout, + enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, u8 role, bdaddr_t *direct_rpa); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, - u8 sec_level, u8 auth_type); + u8 sec_level, u8 auth_type, + enum conn_reasons conn_reason); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting); int hci_conn_check_link_mode(struct hci_conn *conn); @@ -1151,12 +1218,19 @@ struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *list, struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *list, bdaddr_t *bdaddr, u8 type); +struct bdaddr_list_with_flags * +hci_bdaddr_list_lookup_with_flags(struct list_head *list, bdaddr_t *bdaddr, + u8 type); int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, - u8 type, u8 *peer_irk, u8 *local_irk); + u8 type, u8 *peer_irk, u8 *local_irk); +int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, + u8 type, u32 flags); int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, - u8 type); + u8 type); +int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, + u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, @@ -1217,6 +1291,12 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, 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_adv_monitors_clear(struct hci_dev *hdev); +void hci_free_adv_monitor(struct adv_monitor *monitor); +int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); +int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle); +bool hci_is_adv_monitoring(struct hci_dev *hdev); + void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); void hci_init_sysfs(struct hci_dev *hdev); @@ -1279,6 +1359,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #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 LL Privacy based address resolution if supported */ +#define use_ll_privacy(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) + /* 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)) @@ -1387,7 +1470,7 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) __u8 encrypt; if (conn->state == BT_CONFIG) { - if (status) + if (!status) conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); @@ -1402,11 +1485,13 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) else encrypt = 0x01; - if (conn->sec_level == BT_SECURITY_SDP) - conn->sec_level = BT_SECURITY_LOW; + if (!status) { + if (conn->sec_level == BT_SECURITY_SDP) + conn->sec_level = BT_SECURITY_LOW; - if (conn->pending_sec_level > conn->sec_level) - conn->sec_level = conn->pending_sec_level; + if (conn->pending_sec_level > conn->sec_level) + conn->sec_level = conn->pending_sec_level; + } mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 9352bb1bf34c..9949870f7d78 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -31,8 +31,8 @@ #define HCI_TIME_STAMP 3 /* CMSG flags */ -#define HCI_CMSG_DIR 0x0001 -#define HCI_CMSG_TSTAMP 0x0002 +#define HCI_CMSG_DIR 0x01 +#define HCI_CMSG_TSTAMP 0x02 struct sockaddr_hci { sa_family_t hci_family; diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 16e0d87bd8fa..beae5c3980f0 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -52,6 +52,12 @@ struct mgmt_hdr { __le16 len; } __packed; +struct mgmt_tlv { + __le16 type; + __u8 length; + __u8 value[]; +} __packed; + struct mgmt_addr_info { bdaddr_t bdaddr; __u8 type; @@ -702,6 +708,78 @@ struct mgmt_rp_set_exp_feature { __le32 flags; } __packed; +#define MGMT_OP_READ_DEF_SYSTEM_CONFIG 0x004b +#define MGMT_READ_DEF_SYSTEM_CONFIG_SIZE 0 + +#define MGMT_OP_SET_DEF_SYSTEM_CONFIG 0x004c +#define MGMT_SET_DEF_SYSTEM_CONFIG_SIZE 0 + +#define MGMT_OP_READ_DEF_RUNTIME_CONFIG 0x004d +#define MGMT_READ_DEF_RUNTIME_CONFIG_SIZE 0 + +#define MGMT_OP_SET_DEF_RUNTIME_CONFIG 0x004e +#define MGMT_SET_DEF_RUNTIME_CONFIG_SIZE 0 + +#define MGMT_OP_GET_DEVICE_FLAGS 0x004F +#define MGMT_GET_DEVICE_FLAGS_SIZE 7 +struct mgmt_cp_get_device_flags { + struct mgmt_addr_info addr; +} __packed; +struct mgmt_rp_get_device_flags { + struct mgmt_addr_info addr; + __le32 supported_flags; + __le32 current_flags; +} __packed; + +#define MGMT_OP_SET_DEVICE_FLAGS 0x0050 +#define MGMT_SET_DEVICE_FLAGS_SIZE 11 +struct mgmt_cp_set_device_flags { + struct mgmt_addr_info addr; + __le32 current_flags; +} __packed; +struct mgmt_rp_set_device_flags { + struct mgmt_addr_info addr; +} __packed; + +#define MGMT_ADV_MONITOR_FEATURE_MASK_OR_PATTERNS BIT(0) + +#define MGMT_OP_READ_ADV_MONITOR_FEATURES 0x0051 +#define MGMT_READ_ADV_MONITOR_FEATURES_SIZE 0 +struct mgmt_rp_read_adv_monitor_features { + __le32 supported_features; + __le32 enabled_features; + __le16 max_num_handles; + __u8 max_num_patterns; + __le16 num_handles; + __le16 handles[]; +} __packed; + +struct mgmt_adv_pattern { + __u8 ad_type; + __u8 offset; + __u8 length; + __u8 value[31]; +} __packed; + +#define MGMT_OP_ADD_ADV_PATTERNS_MONITOR 0x0052 +struct mgmt_cp_add_adv_patterns_monitor { + __u8 pattern_count; + struct mgmt_adv_pattern patterns[]; +} __packed; +#define MGMT_ADD_ADV_PATTERNS_MONITOR_SIZE 1 +struct mgmt_rp_add_adv_patterns_monitor { + __le16 monitor_handle; +} __packed; + +#define MGMT_OP_REMOVE_ADV_MONITOR 0x0053 +struct mgmt_cp_remove_adv_monitor { + __le16 monitor_handle; +} __packed; +#define MGMT_REMOVE_ADV_MONITOR_SIZE 2 +struct mgmt_rp_remove_adv_monitor { + __le16 monitor_handle; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -933,3 +1011,20 @@ struct mgmt_ev_exp_feature_changed { __u8 uuid[16]; __le32 flags; } __packed; + +#define MGMT_EV_DEVICE_FLAGS_CHANGED 0x002a +struct mgmt_ev_device_flags_changed { + struct mgmt_addr_info addr; + __le32 supported_flags; + __le32 current_flags; +} __packed; + +#define MGMT_EV_ADV_MONITOR_ADDED 0x002b +struct mgmt_ev_adv_monitor_added { + __le16 monitor_handle; +} __packed; + +#define MGMT_EV_ADV_MONITOR_REMOVED 0x002c +struct mgmt_ev_adv_monitor_removed { + __le16 monitor_handle; +} __packed; diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h index f40ddb4264fc..1aa2e14b6c94 100644 --- a/include/net/bluetooth/sco.h +++ b/include/net/bluetooth/sco.h @@ -46,4 +46,6 @@ struct sco_conninfo { __u8 dev_class[3]; }; +#define SCO_CMSG_PKT_STATUS 0x01 + #endif /* __SCO_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index fc7e8807838d..d9e6b9fbd95b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -267,12 +267,12 @@ struct ieee80211_he_obss_pd { * struct cfg80211_he_bss_color - AP settings for BSS coloring * * @color: the current color. - * @disabled: is the feature disabled. + * @enabled: HE BSS color is used * @partial: define the AID equation. */ struct cfg80211_he_bss_color { u8 color; - bool disabled; + bool enabled; bool partial; }; @@ -418,12 +418,28 @@ struct ieee80211_edmg { }; /** + * struct ieee80211_sta_s1g_cap - STA's S1G capabilities + * + * This structure describes most essential parameters needed + * to describe 802.11ah S1G capabilities for a STA. + * + * @s1g_supported: is STA an S1G STA + * @cap: S1G capabilities information + * @nss_mcs: Supported NSS MCS set + */ +struct ieee80211_sta_s1g_cap { + bool s1g; + u8 cap[10]; /* use S1G_CAPAB_ */ + u8 nss_mcs[5]; +}; + +/** * struct ieee80211_supported_band - frequency band definition * * This structure describes a frequency band a wiphy * is able to operate in. * - * @channels: Array of channels the hardware can operate in + * @channels: Array of channels the hardware can operate with * in this band. * @band: the band this structure represents * @n_channels: Number of channels in @channels @@ -448,6 +464,7 @@ struct ieee80211_supported_band { int n_bitrates; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; + struct ieee80211_sta_s1g_cap s1g_cap; struct ieee80211_edmg edmg_cap; u16 n_iftype_data; const struct ieee80211_sband_iftype_data *iftype_data; @@ -1581,6 +1598,7 @@ struct cfg80211_tid_stats { * an FCS error. This counter should be incremented only when TA of the * received packet with an FCS error matches the peer MAC address. * @airtime_link_metric: mesh airtime link metric. + * @connected_to_as: true if mesh STA has a path to authentication server */ struct station_info { u64 filled; @@ -1638,6 +1656,8 @@ struct station_info { u32 fcs_err_count; u32 airtime_link_metric; + + u8 connected_to_as; }; #if IS_ENABLED(CONFIG_CFG80211) @@ -1853,6 +1873,11 @@ struct bss_parameters { * connected to a mesh gate in mesh formation info. If false, the * value in mesh formation is determined by the presence of root paths * in the mesh path table + * @dot11MeshNolearn: Try to avoid multi-hop path discovery (e.g. PREQ/PREP + * for HWMP) if the destination is a direct neighbor. Note that this might + * not be the optimal decision as a multi-hop route might be better. So + * if using this setting you will likely also want to disable + * dot11MeshForwarding and use another mesh routing protocol on top. */ struct mesh_config { u16 dot11MeshRetryTimeout; @@ -1873,6 +1898,7 @@ struct mesh_config { u16 dot11MeshHWMPnetDiameterTraversalTime; u8 dot11MeshHWMPRootMode; bool dot11MeshConnectedToMeshGate; + bool dot11MeshConnectedToAuthServer; u16 dot11MeshHWMPRannInterval; bool dot11MeshGateAnnouncementProtocol; bool dot11MeshForwarding; @@ -1884,6 +1910,7 @@ struct mesh_config { enum nl80211_mesh_power_mode power_mode; u16 dot11MeshAwakeWindowDuration; u32 plink_timeout; + bool dot11MeshNolearn; }; /** @@ -5510,7 +5537,7 @@ static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, * * @skb: The input A-MSDU frame without any headers. * @list: The output list of 802.3 frames. It must be allocated and - * initialized by by the caller. + * initialized by the caller. * @addr: The device MAC address. * @iftype: The device interface type. * @extra_headroom: The hardware extra headroom for SKBs in the @list. @@ -7882,4 +7909,10 @@ void cfg80211_update_owe_info_event(struct net_device *netdev, struct cfg80211_update_owe_info *owe_info, gfp_t gfp); +/** + * cfg80211_bss_flush - resets all the scan entries + * @wiphy: the wiphy + */ +void cfg80211_bss_flush(struct wiphy *wiphy); + #endif /* __NET_CFG80211_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 19d990c8edcc..8f3c8a443238 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -703,6 +703,7 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_PTP_GENERAL, DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE, DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP, + DEVLINK_TRAP_GENERIC_ID_EARLY_DROP, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -732,6 +733,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_PIM, DEVLINK_TRAP_GROUP_GENERIC_ID_UC_LB, DEVLINK_TRAP_GROUP_GENERIC_ID_LOCAL_DELIVERY, + DEVLINK_TRAP_GROUP_GENERIC_ID_EXTERNAL_DELIVERY, DEVLINK_TRAP_GROUP_GENERIC_ID_IPV6, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_EVENT, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, @@ -890,6 +892,8 @@ enum devlink_trap_group_generic_id { "flow_action_sample" #define DEVLINK_TRAP_GENERIC_NAME_FLOW_ACTION_TRAP \ "flow_action_trap" +#define DEVLINK_TRAP_GENERIC_NAME_EARLY_DROP \ + "early_drop" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -929,6 +933,8 @@ enum devlink_trap_group_generic_id { "uc_loopback" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_LOCAL_DELIVERY \ "local_delivery" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EXTERNAL_DELIVERY \ + "external_delivery" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_IPV6 \ "ipv6" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_EVENT \ @@ -1071,7 +1077,8 @@ struct devlink_ops { */ int (*trap_action_set)(struct devlink *devlink, const struct devlink_trap *trap, - enum devlink_trap_action action); + enum devlink_trap_action action, + struct netlink_ext_ack *extack); /** * @trap_group_init: Trap group initialization function. * @@ -1088,7 +1095,8 @@ struct devlink_ops { */ int (*trap_group_set)(struct devlink *devlink, const struct devlink_trap_group *group, - const struct devlink_trap_policer *policer); + const struct devlink_trap_policer *policer, + struct netlink_ext_ack *extack); /** * @trap_policer_init: Trap policer initialization function. * diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index a259050f84af..4b10676c69d1 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -10,6 +10,7 @@ #include <net/flow.h> #include <net/rtnetlink.h> #include <net/fib_notifier.h> +#include <linux/indirect_call_wrapper.h> struct fib_kuid_range { kuid_t start; @@ -203,4 +204,21 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); + +INDIRECT_CALLABLE_DECLARE(int fib6_rule_match(struct fib_rule *rule, + struct flowi *fl, int flags)); +INDIRECT_CALLABLE_DECLARE(int fib4_rule_match(struct fib_rule *rule, + struct flowi *fl, int flags)); + +INDIRECT_CALLABLE_DECLARE(int fib6_rule_action(struct fib_rule *rule, + struct flowi *flp, int flags, + struct fib_lookup_arg *arg)); +INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule, + struct flowi *flp, int flags, + struct fib_lookup_arg *arg)); + +INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule, + struct fib_lookup_arg *arg)); +INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule, + struct fib_lookup_arg *arg)); #endif diff --git a/include/net/fq.h b/include/net/fq.h index 2ad85e683041..e39f3f8d5f8a 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -69,7 +69,6 @@ struct fq { struct list_head backlogs; spinlock_t lock; u32 flows_cnt; - siphash_key_t perturbation; u32 limit; u32 memory_limit; u32 memory_usage; diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 38a9a3d1222b..e73d74d2fabf 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -108,7 +108,7 @@ begin: static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) { - u32 hash = skb_get_hash_perturb(skb, &fq->perturbation); + u32 hash = skb_get_hash(skb); return reciprocal_scale(hash, fq->flows_cnt); } @@ -308,7 +308,6 @@ static int fq_init(struct fq *fq, int flows_cnt) INIT_LIST_HEAD(&fq->backlogs); spin_lock_init(&fq->lock); fq->flows_cnt = max_t(u32, flows_cnt, 1); - get_random_bytes(&fq->perturbation, sizeof(fq->perturbation)); fq->quantum = 300; fq->limit = 8192; fq->memory_limit = 16 << 20; /* 16 MBytes */ diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 459d355f6506..19c00d100096 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -117,6 +117,7 @@ enum ieee80211_radiotap_tx_flags { IEEE80211_RADIOTAP_F_TX_CTS = 0x0002, IEEE80211_RADIOTAP_F_TX_RTS = 0x0004, IEEE80211_RADIOTAP_F_TX_NOACK = 0x0008, + IEEE80211_RADIOTAP_F_TX_NOSEQNO = 0x0010, }; /* for IEEE80211_RADIOTAP_MCS "have" flags */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 011f407b76fe..9a59a33787cb 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -14,6 +14,7 @@ #include <linux/spinlock.h> /* for struct rwlock_t */ #include <linux/atomic.h> /* for struct atomic_t */ #include <linux/refcount.h> /* for struct refcount_t */ +#include <linux/workqueue.h> #include <linux/compiler.h> #include <linux/timer.h> @@ -886,6 +887,8 @@ struct netns_ipvs { atomic_t conn_out_counter; #ifdef CONFIG_SYSCTL + /* delayed work for expiring no dest connections */ + struct delayed_work expire_nodest_conn_work; /* 1/rate drop and drop-entry variables */ struct delayed_work defense_work; /* Work handler */ int drop_rate; @@ -1051,6 +1054,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return ipvs->sysctl_conn_reuse_mode; } +static inline int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_expire_nodest_conn; +} + static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) { return ipvs->sysctl_schedule_icmp; @@ -1138,6 +1146,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) +{ + return 0; +} + static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) { return 0; @@ -1507,6 +1520,22 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs) static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } #endif +#ifdef CONFIG_SYSCTL +/* Enqueue delayed work for expiring no dest connections + * Only run when sysctl_expire_nodest=1 + */ +static inline void ip_vs_enqueue_expire_nodest_conns(struct netns_ipvs *ipvs) +{ + if (sysctl_expire_nodest_conn(ipvs)) + queue_delayed_work(system_long_wq, + &ipvs->expire_nodest_conn_work, 1); +} + +void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs); +#else +static inline void ip_vs_enqueue_expire_nodest_conns(struct netns_ipvs *ipvs) {} +#endif + #define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \ IP_VS_CONN_F_FWD_MASK) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 11d5610d2ad5..66e2bfd165e8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -825,6 +825,8 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup * @IEEE80211_TX_CTRL_HW_80211_ENCAP: This frame uses hardware encapsulation * (header conversion) + * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that + * has already been assigned to this frame. * * These flags are used in tx_info->control.flags. */ @@ -836,6 +838,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), IEEE80211_TX_CTRL_HW_80211_ENCAP = BIT(6), + IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), }; /* @@ -2727,7 +2730,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * for devices that support offload of data packets (e.g. ARP responses). * * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag - * when they are able to replace in-use PTK keys according to to following + * when they are able to replace in-use PTK keys according to the following * requirements: * 1) They do not hand over frames decrypted with the old key to mac80211 once the call to set_key() with command %DISABLE_KEY has been @@ -4358,6 +4361,31 @@ void ieee80211_free_hw(struct ieee80211_hw *hw); void ieee80211_restart_hw(struct ieee80211_hw *hw); /** + * ieee80211_rx_list - receive frame and store processed skbs in a list + * + * Use this function to hand received frames to mac80211. The receive + * buffer in @skb must start with an IEEE 802.11 header. In case of a + * paged @skb is used, the driver is recommended to put the ieee80211 + * header of the frame on the linear part of the @skb to avoid memory + * allocation and/or memcpy by the stack. + * + * This function may not be called in IRQ context. Calls to this function + * for a single hardware must be synchronized against each other. Calls to + * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be + * mixed for a single hardware. Must not run concurrently with + * ieee80211_tx_status() or ieee80211_tx_status_ni(). + * + * This function must be called with BHs disabled and RCU read lock + * + * @hw: the hardware this frame came in on + * @sta: the station the frame was received from, or %NULL + * @skb: the buffer to receive, owned by mac80211 after this call + * @list: the destination list + */ +void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *sta, + struct sk_buff *skb, struct list_head *list); + +/** * ieee80211_rx_napi - receive frame from NAPI context * * Use this function to hand received frames to mac80211. The receive @@ -4709,7 +4737,7 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, * * Call this function for all transmitted data frames after their transmit * completion. This callback should only be called for data frames which - * are are using driver's (or hardware's) offload capability of encap/decap + * are using driver's (or hardware's) offload capability of encap/decap * 802.11 frames. * * This function may not be called in IRQ context. Calls to this function @@ -6236,6 +6264,14 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, int band, struct ieee80211_sta **sta); /** + * Sanity-check and parse the radiotap header of injected frames + * @skb: packet injected by userspace + * @dev: the &struct device of this 802.11 device + */ +bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, + struct net_device *dev); + +/** * struct ieee80211_noa_data - holds temporary data for tracking P2P NoA state * * @next_tsf: TSF timestamp of the next absent state change @@ -6344,7 +6380,7 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * * Note that this must be called in an rcu_read_lock() critical section, * which can only be released after the SKB was handled. Some pointers in - * skb->cb, e.g. the key pointer, are protected by by RCU and thus the + * skb->cb, e.g. the key pointer, are protected by RCU and thus the * critical section must persist not just for the duration of this call * but for the duration of the frame handling. * However, also note that while in the wake_tx_queue() method, diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 02158c257bd4..3525d2822abe 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -58,6 +58,7 @@ struct mptcp_out_options { }; #ifdef CONFIG_MPTCP +extern struct request_sock_ops mptcp_subflow_request_sock_ops; void mptcp_init(void); @@ -130,6 +131,9 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, } void mptcp_seq_show(struct seq_file *seq); +int mptcp_subflow_init_cookie_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb); #else static inline void mptcp_init(void) @@ -199,6 +203,13 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { } static inline void mptcp_seq_show(struct seq_file *seq) { } + +static inline int mptcp_subflow_init_cookie_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + return 0; /* TCP fallback */ +} #endif /* CONFIG_MPTCP */ #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 09a3099886e5..47f06f6f5a67 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -44,7 +44,7 @@ enum environment_cap { * and potentially inform users of which devices specifically * cased the conflicts. * @initiator: indicates who sent this request, could be any of - * of those set in nl80211_reg_initiator (%NL80211_REGDOM_SET_BY_*) + * those set in nl80211_reg_initiator (%NL80211_REGDOM_SET_BY_*) * @alpha2: the ISO / IEC 3166 alpha2 country code of the requested * regulatory domain. We have a few special codes: * 00 - World regulatory domain diff --git a/include/net/request_sock.h b/include/net/request_sock.h index cf8b33213bbc..b2eb8b4ba697 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -54,7 +54,7 @@ struct request_sock { struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ - u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ + u8 syncookie:1; /* syncookie: encode tcpopts in timestamp */ u8 num_timeout:7; /* number of timeouts */ u32 ts_recent; struct timer_list rsk_timer; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c510b03b9751..d60e7c39d60c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -384,6 +384,7 @@ struct qdisc_skb_cb { }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; + u16 mru; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); @@ -463,7 +464,7 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; - BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz); + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb)); BUILD_BUG_ON(sizeof(qcb->data) < sz); } diff --git a/include/net/tcp.h b/include/net/tcp.h index e0c35d56091f..dbf5c791a6eb 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -469,6 +469,8 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); +struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index dd20ce99740c..94bb7a882250 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -193,6 +193,11 @@ enum udp_tunnel_nic_info_flags { UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), + /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. + * This port must not be counted towards n_entries of any table. + * Driver will not receive any callback associated with port 4789. + */ + UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; /** diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 5e81868b574a..2737d24ec244 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -374,7 +374,8 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family); struct xfrm_input_afinfo { - unsigned int family; + u8 family; + bool is_ipip; int (*callback)(struct sk_buff *skb, u8 protocol, int err); }; @@ -943,7 +944,7 @@ struct xfrm_dst { static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; @@ -955,7 +956,7 @@ static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } @@ -1417,6 +1418,7 @@ struct xfrm6_protocol { /* XFRM tunnel handlers. */ struct xfrm_tunnel { int (*handler)(struct sk_buff *skb); + int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm_tunnel __rcu *next; @@ -1425,6 +1427,7 @@ struct xfrm_tunnel { struct xfrm6_tunnel { int (*handler)(struct sk_buff *skb); + int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_tunnel __rcu *next; @@ -1633,13 +1636,16 @@ 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, u32 if_id, - u8 type, int dir, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, + const struct xfrm_mark *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, u32 if_id, u8, - int dir, u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, + const struct xfrm_mark *mark, u32 if_id, + u8 type, 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); diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index c4369a6c2951..2f1fc23602cb 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -305,6 +305,25 @@ struct rvt_rq { spinlock_t lock ____cacheline_aligned_in_smp; }; +/** + * rvt_get_rq_count - count numbers of request work queue entries + * in circular buffer + * @rq: data structure for request queue entry + * @head: head indices of the circular buffer + * @tail: tail indices of the circular buffer + * + * Return - total number of entries in the Receive Queue + */ + +static inline u32 rvt_get_rq_count(struct rvt_rq *rq, u32 head, u32 tail) +{ + u32 count = head - tail; + + if ((s32)count < 0) + count += rq->size; + return count; +} + /* * This structure holds the information that the send tasklet needs * to send a RDMA read response or atomic operation. diff --git a/include/uapi/linux/hsr_netlink.h b/include/uapi/linux/hsr_netlink.h index c218ef9c35dd..d540ea9bbef4 100644 --- a/include/uapi/linux/hsr_netlink.h +++ b/include/uapi/linux/hsr_netlink.h @@ -17,7 +17,7 @@ /* Generic Netlink HSR family definition */ -/* attributes */ +/* attributes for HSR or PRP node */ enum { HSR_A_UNSPEC, HSR_A_NODE_ADDR, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index af8f31987526..7fba4de511de 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -170,12 +170,22 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -907,7 +917,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -917,6 +934,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; diff --git a/include/uapi/linux/netfilter/xt_connmark.h b/include/uapi/linux/netfilter/xt_connmark.h index 1aa5c955ee1e..f01c19b83a2b 100644 --- a/include/uapi/linux/netfilter/xt_connmark.h +++ b/include/uapi/linux/netfilter/xt_connmark.h @@ -4,7 +4,7 @@ #include <linux/types.h> -/* Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> +/* Copyright (C) 2002,2004 MARA Systems AB <https://www.marasystems.com> * by Henrik Nordstrom <hno@marasystems.com> * * This program is free software; you can redistribute it and/or modify diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 4e6339ab1fce..631f3a997b3c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -183,18 +183,27 @@ * * By setting @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK flag drivers * can indicate they support offloading EAPOL handshakes for WPA/WPA2 - * preshared key authentication. In %NL80211_CMD_CONNECT the preshared - * key should be specified using %NL80211_ATTR_PMK. Drivers supporting - * this offload may reject the %NL80211_CMD_CONNECT when no preshared - * key material is provided, for example when that driver does not - * support setting the temporal keys through %CMD_NEW_KEY. + * preshared key authentication in station mode. In %NL80211_CMD_CONNECT + * the preshared key should be specified using %NL80211_ATTR_PMK. Drivers + * supporting this offload may reject the %NL80211_CMD_CONNECT when no + * preshared key material is provided, for example when that driver does + * not support setting the temporal keys through %NL80211_CMD_NEW_KEY. * * Similarly @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X flag can be * set by drivers indicating offload support of the PTK/GTK EAPOL - * handshakes during 802.1X authentication. In order to use the offload - * the %NL80211_CMD_CONNECT should have %NL80211_ATTR_WANT_1X_4WAY_HS - * attribute flag. Drivers supporting this offload may reject the - * %NL80211_CMD_CONNECT when the attribute flag is not present. + * handshakes during 802.1X authentication in station mode. In order to + * use the offload the %NL80211_CMD_CONNECT should have + * %NL80211_ATTR_WANT_1X_4WAY_HS attribute flag. Drivers supporting this + * offload may reject the %NL80211_CMD_CONNECT when the attribute flag is + * not present. + * + * By setting @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK flag drivers + * can indicate they support offloading EAPOL handshakes for WPA/WPA2 + * preshared key authentication in AP mode. In %NL80211_CMD_START_AP + * the preshared key should be specified using %NL80211_ATTR_PMK. Drivers + * supporting this offload may reject the %NL80211_CMD_START_AP when no + * preshared key material is provided, for example when that driver does + * not support setting the temporal keys through %NL80211_CMD_NEW_KEY. * * For 802.1X the PMK or PMK-R0 are set by providing %NL80211_ATTR_PMK * using %NL80211_CMD_SET_PMK. For offloaded FT support also @@ -363,7 +372,7 @@ * @NL80211_CMD_SET_STATION: Set station attributes for station identified by * %NL80211_ATTR_MAC on the interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_NEW_STATION: Add a station with given attributes to the - * the interface identified by %NL80211_ATTR_IFINDEX. + * interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_DEL_STATION: Remove a station identified by %NL80211_ATTR_MAC * or, if no MAC address given, all stations, on the interface identified * by %NL80211_ATTR_IFINDEX. %NL80211_ATTR_MGMT_SUBTYPE and @@ -383,7 +392,7 @@ * @NL80211_CMD_DEL_MPATH: Delete a mesh path to the destination given by * %NL80211_ATTR_MAC. * @NL80211_CMD_NEW_PATH: Add a mesh path with given attributes to the - * the interface identified by %NL80211_ATTR_IFINDEX. + * interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_DEL_PATH: Remove a mesh path identified by %NL80211_ATTR_MAC * or, if no MAC address given, all mesh paths, on the interface identified * by %NL80211_ATTR_IFINDEX. @@ -934,7 +943,7 @@ * @NL80211_CMD_SET_COALESCE: Configure coalesce rules or clear existing rules. * * @NL80211_CMD_CHANNEL_SWITCH: Perform a channel switch by announcing the - * the new channel information (Channel Switch Announcement - CSA) + * new channel information (Channel Switch Announcement - CSA) * in the beacon for some time (as defined in the * %NL80211_ATTR_CH_SWITCH_COUNT parameter) and then change to the * new channel. Userspace provides the new channel information (using @@ -1113,7 +1122,7 @@ * randomization may be enabled and configured by specifying the * %NL80211_ATTR_MAC and %NL80211_ATTR_MAC_MASK attributes. * If a timeout is requested, use the %NL80211_ATTR_TIMEOUT attribute. - * A u64 cookie for further %NL80211_ATTR_COOKIE use is is returned in + * A u64 cookie for further %NL80211_ATTR_COOKIE use is returned in * the netlink extended ack message. * * To cancel a measurement, close the socket that requested it. @@ -1511,7 +1520,7 @@ enum nl80211_commands { * rates as defined by IEEE 802.11 7.3.2.2 but without the length * restriction (at most %NL80211_MAX_SUPP_RATES). * @NL80211_ATTR_STA_VLAN: interface index of VLAN interface to move station - * to, or the AP interface the station was originally added to to. + * to, or the AP interface the station was originally added to. * @NL80211_ATTR_STA_INFO: information about a station, part of station info * given for %NL80211_CMD_GET_STATION, nested attribute containing * info as possible, see &enum nl80211_sta_info. @@ -2084,7 +2093,7 @@ enum nl80211_commands { * @NL80211_ATTR_STA_SUPPORTED_CHANNELS: array of supported channels. * * @NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES: array of supported - * supported operating classes. + * operating classes. * * @NL80211_ATTR_HANDLE_DFS: A flag indicating whether user space * controls DFS operation in IBSS mode. If the flag is included in @@ -2362,10 +2371,11 @@ enum nl80211_commands { * * @NL80211_ATTR_PMK: attribute for passing PMK key material. Used with * %NL80211_CMD_SET_PMKSA for the PMKSA identified by %NL80211_ATTR_PMKID. - * For %NL80211_CMD_CONNECT it is used to provide PSK for offloading 4-way - * handshake for WPA/WPA2-PSK networks. For 802.1X authentication it is - * used with %NL80211_CMD_SET_PMK. For offloaded FT support this attribute - * specifies the PMK-R0 if NL80211_ATTR_PMKR0_NAME is included as well. + * For %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP it is used to provide + * PSK for offloading 4-way handshake for WPA/WPA2-PSK networks. For 802.1X + * authentication it is used with %NL80211_CMD_SET_PMK. For offloaded FT + * support this attribute specifies the PMK-R0 if NL80211_ATTR_PMKR0_NAME + * is included as well. * * @NL80211_ATTR_SCHED_SCAN_MULTI: flag attribute which user-space shall use to * indicate that it supports multiple active scheduled scan requests. @@ -2395,7 +2405,7 @@ enum nl80211_commands { * nl80211_txq_stats) * @NL80211_ATTR_TXQ_LIMIT: Total packet limit for the TXQ queues for this phy. * The smaller of this and the memory limit is enforced. - * @NL80211_ATTR_TXQ_MEMORY_LIMIT: Total memory memory limit (in bytes) for the + * @NL80211_ATTR_TXQ_MEMORY_LIMIT: Total memory limit (in bytes) for the * TXQ queues for this phy. The smaller of this and the packet limit is * enforced. * @NL80211_ATTR_TXQ_QUANTUM: TXQ scheduler quantum (bytes). Number of bytes @@ -3370,6 +3380,8 @@ enum nl80211_sta_bss_param { * @NL80211_STA_INFO_AIRTIME_LINK_METRIC: airtime link metric for mesh station * @NL80211_STA_INFO_ASSOC_AT_BOOTTIME: Timestamp (CLOCK_BOOTTIME, nanoseconds) * of STA's association + * @NL80211_STA_INFO_CONNECTED_TO_AS: set to true if STA has a path to a + * authentication server (u8, 0 or 1) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -3417,6 +3429,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_AIRTIME_WEIGHT, NL80211_STA_INFO_AIRTIME_LINK_METRIC, NL80211_STA_INFO_ASSOC_AT_BOOTTIME, + NL80211_STA_INFO_CONNECTED_TO_AS, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, @@ -4236,6 +4249,16 @@ enum nl80211_mesh_power_mode { * field. If left unset then the mesh formation field will only * advertise such if there is an active root mesh path. * + * @NL80211_MESHCONF_NOLEARN: Try to avoid multi-hop path discovery (e.g. + * PREQ/PREP for HWMP) if the destination is a direct neighbor. Note that + * this might not be the optimal decision as a multi-hop route might be + * better. So if using this setting you will likely also want to disable + * dot11MeshForwarding and use another mesh routing protocol on top. + * + * @NL80211_MESHCONF_CONNECTED_TO_AS: If set to true then this mesh STA + * will advertise that it is connected to a authentication server + * in the mesh formation field. + * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ enum nl80211_meshconf_params { @@ -4269,6 +4292,8 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_AWAKE_WINDOW, NL80211_MESHCONF_PLINK_TIMEOUT, NL80211_MESHCONF_CONNECTED_TO_GATE, + NL80211_MESHCONF_NOLEARN, + NL80211_MESHCONF_CONNECTED_TO_AS, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, @@ -4437,6 +4462,11 @@ enum nl80211_key_mode { * attribute must be provided as well * @NL80211_CHAN_WIDTH_5: 5 MHz OFDM channel * @NL80211_CHAN_WIDTH_10: 10 MHz OFDM channel + * @NL80211_CHAN_WIDTH_1: 1 MHz OFDM channel + * @NL80211_CHAN_WIDTH_2: 2 MHz OFDM channel + * @NL80211_CHAN_WIDTH_4: 4 MHz OFDM channel + * @NL80211_CHAN_WIDTH_8: 8 MHz OFDM channel + * @NL80211_CHAN_WIDTH_16: 16 MHz OFDM channel */ enum nl80211_chan_width { NL80211_CHAN_WIDTH_20_NOHT, @@ -4447,6 +4477,11 @@ enum nl80211_chan_width { NL80211_CHAN_WIDTH_160, NL80211_CHAN_WIDTH_5, NL80211_CHAN_WIDTH_10, + NL80211_CHAN_WIDTH_1, + NL80211_CHAN_WIDTH_2, + NL80211_CHAN_WIDTH_4, + NL80211_CHAN_WIDTH_8, + NL80211_CHAN_WIDTH_16, }; /** @@ -4457,11 +4492,15 @@ enum nl80211_chan_width { * @NL80211_BSS_CHAN_WIDTH_20: control channel is 20 MHz wide or compatible * @NL80211_BSS_CHAN_WIDTH_10: control channel is 10 MHz wide * @NL80211_BSS_CHAN_WIDTH_5: control channel is 5 MHz wide + * @NL80211_BSS_CHAN_WIDTH_1: control channel is 1 MHz wide + * @NL80211_BSS_CHAN_WIDTH_2: control channel is 2 MHz wide */ enum nl80211_bss_scan_width { NL80211_BSS_CHAN_WIDTH_20, NL80211_BSS_CHAN_WIDTH_10, NL80211_BSS_CHAN_WIDTH_5, + NL80211_BSS_CHAN_WIDTH_1, + NL80211_BSS_CHAN_WIDTH_2, }; /** @@ -4740,6 +4779,7 @@ enum nl80211_txrate_gi { * @NL80211_BAND_5GHZ: around 5 GHz band (4.9 - 5.7 GHz) * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 69.12 GHz) * @NL80211_BAND_6GHZ: around 6 GHz band (5.9 - 7.2 GHz) + * @NL80211_BAND_S1GHZ: around 900MHz, supported by S1G PHYs * @NUM_NL80211_BANDS: number of bands, avoid using this in userspace * since newer kernel versions may support more bands */ @@ -4748,6 +4788,7 @@ enum nl80211_band { NL80211_BAND_5GHZ, NL80211_BAND_60GHZ, NL80211_BAND_6GHZ, + NL80211_BAND_S1GHZ, NUM_NL80211_BANDS, }; @@ -5636,7 +5677,7 @@ enum nl80211_feature_flags { * enum nl80211_ext_feature_index - bit index of extended features. * @NL80211_EXT_FEATURE_VHT_IBSS: This driver supports IBSS with VHT datarates. * @NL80211_EXT_FEATURE_RRM: This driver supports RRM. When featured, user can - * can request to use RRM (see %NL80211_ATTR_USE_RRM) with + * request to use RRM (see %NL80211_ATTR_USE_RRM) with * %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set * the ASSOC_REQ_USE_RRM flag in the association request even if * NL80211_FEATURE_QUIET is not advertized. @@ -5773,6 +5814,13 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS: The driver * can report tx status for control port over nl80211 tx operations. * + * @NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION: Driver supports Operating + * Channel Validation (OCV) when using driver's SME for RSNA handshakes. + * + * @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK: Device wants to do 4-way + * handshake with PSK in AP mode (PSK is passed as part of the start AP + * command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5828,6 +5876,8 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT, NL80211_EXT_FEATURE_SCAN_FREQ_KHZ, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, + NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -6045,7 +6095,7 @@ enum nl80211_dfs_state { }; /** - * enum enum nl80211_protocol_features - nl80211 protocol features + * enum nl80211_protocol_features - nl80211 protocol features * @NL80211_PROTOCOL_FEATURE_SPLIT_WIPHY_DUMP: nl80211 supports splitting * wiphy dumps (if requested by the application with the attribute * %NL80211_ATTR_SPLIT_WIPHY_DUMP. Also supported is filtering the diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 9b14519e74d9..8300cc29dec8 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -86,6 +86,7 @@ enum ovs_datapath_attr { OVS_DP_ATTR_MEGAFLOW_STATS, /* struct ovs_dp_megaflow_stats */ OVS_DP_ATTR_USER_FEATURES, /* OVS_DP_F_* */ OVS_DP_ATTR_PAD, + OVS_DP_ATTR_MASKS_CACHE_SIZE, __OVS_DP_ATTR_MAX }; @@ -102,8 +103,8 @@ struct ovs_dp_megaflow_stats { __u64 n_mask_hit; /* Number of masks used for flow lookups. */ __u32 n_masks; /* Number of masks for the datapath. */ __u32 pad0; /* Pad for future expension. */ + __u64 n_cache_hit; /* Number of cache matches for flow lookups. */ __u64 pad1; /* Pad for future expension. */ - __u64 pad2; /* Pad for future expension. */ }; struct ovs_vport_stats { diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index 09fb608a35ec..eb815e0d0ac3 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -37,25 +37,4 @@ enum { SEG6_IPTUN_MODE_L2ENCAP, }; -#ifdef __KERNEL__ - -static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) -{ - int head = 0; - - switch (tuninfo->mode) { - case SEG6_IPTUN_MODE_INLINE: - break; - case SEG6_IPTUN_MODE_ENCAP: - head = sizeof(struct ipv6hdr); - break; - case SEG6_IPTUN_MODE_L2ENCAP: - return 0; - } - - return ((tuninfo->srh->hdrlen + 1) << 3) + head; -} - -#endif - #endif diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index f2acb2566333..cfcb10b75483 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -313,6 +313,7 @@ enum { TCP_NLA_SRTT, /* smoothed RTT in usecs */ TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ + TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ }; /* for TCP_MD5SIG socket option */ diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index 24f3371ad826..08967b3f19c8 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -914,7 +914,7 @@ union iwreq_data { struct iw_param sens; /* signal level threshold */ struct iw_param bitrate; /* default bit rate */ struct iw_param txpower; /* default transmit power */ - struct iw_param rts; /* RTS threshold threshold */ + struct iw_param rts; /* RTS threshold */ struct iw_param frag; /* Fragmentation threshold */ __u32 mode; /* Operation mode */ struct iw_param retry; /* Retry limits & lifetime */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index ff7cfdc6cb44..ffc6a5391bb7 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -387,6 +387,7 @@ struct xfrm_usersa_info { }; #define XFRM_SA_XFLAG_DONT_ENCAP_DSCP 1 +#define XFRM_SA_XFLAG_OSEQ_MAY_WRAP 2 struct xfrm_usersa_id { xfrm_address_t daddr; diff --git a/kernel/audit.c b/kernel/audit.c index 8c201f414226..b2301bdc9773 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1851,7 +1851,6 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, } audit_get_stamp(ab->ctx, &t, &serial); - audit_clear_dummy(ab->ctx); audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); diff --git a/kernel/audit.h b/kernel/audit.h index f0233dc40b17..ddc22878433d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -290,13 +290,6 @@ extern int audit_signal_info_syscall(struct task_struct *t); extern void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx); extern struct list_head *audit_killed_trees(void); - -static inline void audit_clear_dummy(struct audit_context *ctx) -{ - if (ctx) - ctx->dummy = 0; -} - #else /* CONFIG_AUDITSYSCALL */ #define auditsc_get_stamp(c, t, s) 0 #define audit_put_watch(w) {} @@ -330,7 +323,6 @@ static inline int audit_signal_info_syscall(struct task_struct *t) } #define audit_filter_inodes(t, c) AUDIT_DISABLED -#define audit_clear_dummy(c) {} #endif /* CONFIG_AUDITSYSCALL */ extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 468a23390457..fd840c40abf7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1417,6 +1417,9 @@ static void audit_log_proctitle(void) struct audit_context *context = audit_context(); struct audit_buffer *ab; + if (!context || context->dummy) + return; + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE); if (!ab) return; /* audit_panic or being filtered */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0fd6bb62be3a..91afdd4c82e3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4095,7 +4095,7 @@ int btf_resolve_helper_id(struct bpf_verifier_log *log, { int id; - if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID) + if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID || !btf_vmlinux) return -EINVAL; id = fn->btf_id[arg]; if (!id || id > btf_vmlinux->nr_types) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 024276787055..78dfff6a501b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -779,15 +779,20 @@ static void htab_elem_free_rcu(struct rcu_head *head) htab_elem_free(htab, l); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -839,6 +844,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/kernel/signal.c b/kernel/signal.c index ee22ec78fd6d..6f16f7c5d375 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -719,7 +719,7 @@ static int dequeue_synchronous_signal(kernel_siginfo_t *info) * Return the first synchronous signal in the queue. */ list_for_each_entry(q, &pending->list, list) { - /* Synchronous signals have a postive si_code */ + /* Synchronous signals have a positive si_code */ if ((q->info.si_code > SI_USER) && (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { sync = q; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index df1ff803acc4..026ac01af9da 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -1742,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** diff --git a/lib/Kconfig b/lib/Kconfig index df3f3da95990..3ffbca6998e5 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -676,3 +676,7 @@ config GENERIC_LIB_CMPDI2 config GENERIC_LIB_UCMPDI2 bool + +config PLDMFW + bool + default n diff --git a/lib/Makefile b/lib/Makefile index b1c42c10073b..281888ff713b 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -315,6 +315,9 @@ obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o obj-$(CONFIG_OBJAGG) += objagg.o +# pldmfw library +obj-$(CONFIG_PLDMFW) += pldmfw/ + # KUnit tests obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o diff --git a/lib/pldmfw/Makefile b/lib/pldmfw/Makefile new file mode 100644 index 000000000000..99ad10711abe --- /dev/null +++ b/lib/pldmfw/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_PLDMFW) += pldmfw.o diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c new file mode 100644 index 000000000000..e5d4b3b2af81 --- /dev/null +++ b/lib/pldmfw/pldmfw.c @@ -0,0 +1,879 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#include <asm/unaligned.h> +#include <linux/crc32.h> +#include <linux/device.h> +#include <linux/firmware.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/pldmfw.h> +#include <linux/slab.h> +#include <linux/uuid.h> + +#include "pldmfw_private.h" + +/* Internal structure used to store details about the PLDM image file as it is + * being validated and processed. + */ +struct pldmfw_priv { + struct pldmfw *context; + const struct firmware *fw; + + /* current offset of firmware image */ + size_t offset; + + struct list_head records; + struct list_head components; + + /* PLDM Firmware Package Header */ + const struct __pldm_header *header; + u16 total_header_size; + + /* length of the component bitmap */ + u16 component_bitmap_len; + u16 bitmap_size; + + /* Start of the component image information */ + u16 component_count; + const u8 *component_start; + + /* Start pf the firmware device id records */ + const u8 *record_start; + u8 record_count; + + /* The CRC at the end of the package header */ + u32 header_crc; + + struct pldmfw_record *matching_record; +}; + +/** + * pldm_check_fw_space - Verify that the firmware image has space left + * @data: pointer to private data + * @offset: offset to start from + * @length: length to check for + * + * Verify that the firmware data can hold a chunk of bytes with the specified + * offset and length. + * + * Returns: zero on success, or -EFAULT if the image does not have enough + * space left to fit the expected length. + */ +static int +pldm_check_fw_space(struct pldmfw_priv *data, size_t offset, size_t length) +{ + size_t expected_size = offset + length; + struct device *dev = data->context->dev; + + if (data->fw->size < expected_size) { + dev_dbg(dev, "Firmware file size smaller than expected. Got %zu bytes, needed %zu bytes\n", + data->fw->size, expected_size); + return -EFAULT; + } + + return 0; +} + +/** + * pldm_move_fw_offset - Move the current firmware offset forward + * @data: pointer to private data + * @bytes_to_move: number of bytes to move the offset forward by + * + * Check that there is enough space past the current offset, and then move the + * offset forward by this ammount. + * + * Returns: zero on success, or -EFAULT if the image is too small to fit the + * expected length. + */ +static int +pldm_move_fw_offset(struct pldmfw_priv *data, size_t bytes_to_move) +{ + int err; + + err = pldm_check_fw_space(data, data->offset, bytes_to_move); + if (err) + return err; + + data->offset += bytes_to_move; + + return 0; +} + +/** + * pldm_parse_header - Validate and extract details about the PLDM header + * @data: pointer to private data + * + * Performs initial basic verification of the PLDM image, up to the first + * firmware record. + * + * This includes the following checks and extractions + * + * * Verify that the UUID at the start of the header matches the expected + * value as defined in the DSP0267 PLDM specification + * * Check that the revision is 0x01 + * * Extract the total header_size and verify that the image is large enough + * to contain at least the length of this header + * * Extract the size of the component bitmap length + * * Extract a pointer to the start of the record area + * + * Returns: zero on success, or a negative error code on failure. + */ +static int pldm_parse_header(struct pldmfw_priv *data) +{ + const struct __pldmfw_record_area *record_area; + struct device *dev = data->context->dev; + const struct __pldm_header *header; + size_t header_size; + int err; + + err = pldm_move_fw_offset(data, sizeof(*header)); + if (err) + return err; + + header = (const struct __pldm_header *)data->fw->data; + data->header = header; + + if (!uuid_equal(&header->id, &pldm_firmware_header_id)) { + dev_dbg(dev, "Invalid package header identifier. Expected UUID %pUB, but got %pUB\n", + &pldm_firmware_header_id, &header->id); + return -EINVAL; + } + + if (header->revision != PACKAGE_HEADER_FORMAT_REVISION) { + dev_dbg(dev, "Invalid package header revision. Expected revision %u but got %u\n", + PACKAGE_HEADER_FORMAT_REVISION, header->revision); + return -EOPNOTSUPP; + } + + data->total_header_size = get_unaligned_le16(&header->size); + header_size = data->total_header_size - sizeof(*header); + + err = pldm_check_fw_space(data, data->offset, header_size); + if (err) + return err; + + data->component_bitmap_len = + get_unaligned_le16(&header->component_bitmap_len); + + if (data->component_bitmap_len % 8 != 0) { + dev_dbg(dev, "Invalid component bitmap length. The length is %u, which is not a multiple of 8\n", + data->component_bitmap_len); + return -EINVAL; + } + + data->bitmap_size = data->component_bitmap_len / 8; + + err = pldm_move_fw_offset(data, header->version_len); + if (err) + return err; + + /* extract a pointer to the record area, which just follows the main + * PLDM header data. + */ + record_area = (const struct __pldmfw_record_area *)(data->fw->data + + data->offset); + + err = pldm_move_fw_offset(data, sizeof(*record_area)); + if (err) + return err; + + data->record_count = record_area->record_count; + data->record_start = record_area->records; + + return 0; +} + +/** + * pldm_check_desc_tlv_len - Check that the length matches expectation + * @data: pointer to image details + * @type: the descriptor type + * @size: the length from the descriptor header + * + * If the descriptor type is one of the documented descriptor types according + * to the standard, verify that the provided length matches. + * + * If the type is not recognized or is VENDOR_DEFINED, return zero. + * + * Returns: zero on success, or -EINVAL if the specified size of a standard + * TLV does not match the expected value defined for that TLV. + */ +static int +pldm_check_desc_tlv_len(struct pldmfw_priv *data, u16 type, u16 size) +{ + struct device *dev = data->context->dev; + u16 expected_size; + + switch (type) { + case PLDM_DESC_ID_PCI_VENDOR_ID: + case PLDM_DESC_ID_PCI_DEVICE_ID: + case PLDM_DESC_ID_PCI_SUBVENDOR_ID: + case PLDM_DESC_ID_PCI_SUBDEV_ID: + expected_size = 2; + break; + case PLDM_DESC_ID_PCI_REVISION_ID: + expected_size = 1; + break; + case PLDM_DESC_ID_PNP_VENDOR_ID: + expected_size = 3; + break; + case PLDM_DESC_ID_IANA_ENTERPRISE_ID: + case PLDM_DESC_ID_ACPI_VENDOR_ID: + case PLDM_DESC_ID_PNP_PRODUCT_ID: + case PLDM_DESC_ID_ACPI_PRODUCT_ID: + expected_size = 4; + break; + case PLDM_DESC_ID_UUID: + expected_size = 16; + break; + case PLDM_DESC_ID_VENDOR_DEFINED: + return 0; + default: + /* Do not report an error on an unexpected TLV */ + dev_dbg(dev, "Found unrecognized TLV type 0x%04x\n", type); + return 0; + } + + if (size != expected_size) { + dev_dbg(dev, "Found TLV type 0x%04x with unexpected length. Got %u bytes, but expected %u bytes\n", + type, size, expected_size); + return -EINVAL; + } + + return 0; +} + +/** + * pldm_parse_desc_tlvs - Check and skip past a number of TLVs + * @data: pointer to private data + * @record: pointer to the record this TLV belongs too + * @desc_count: descriptor count + * + * From the current offset, read and extract the descriptor TLVs, updating the + * current offset each time. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +pldm_parse_desc_tlvs(struct pldmfw_priv *data, struct pldmfw_record *record, u8 desc_count) +{ + const struct __pldmfw_desc_tlv *__desc; + const u8 *desc_start; + u8 i; + + desc_start = data->fw->data + data->offset; + + pldm_for_each_desc_tlv(i, __desc, desc_start, desc_count) { + struct pldmfw_desc_tlv *desc; + int err; + u16 type, size; + + err = pldm_move_fw_offset(data, sizeof(*__desc)); + if (err) + return err; + + type = get_unaligned_le16(&__desc->type); + + /* According to DSP0267, this only includes the data field */ + size = get_unaligned_le16(&__desc->size); + + err = pldm_check_desc_tlv_len(data, type, size); + if (err) + return err; + + /* check that we have space and move the offset forward */ + err = pldm_move_fw_offset(data, size); + if (err) + return err; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + desc->type = type; + desc->size = size; + desc->data = __desc->data; + + list_add_tail(&desc->entry, &record->descs); + } + + return 0; +} + +/** + * pldm_parse_one_record - Verify size of one PLDM record + * @data: pointer to image details + * @__record: pointer to the record to check + * + * This function checks that the record size does not exceed either the size + * of the firmware file or the total length specified in the header section. + * + * It also verifies that the recorded length of the start of the record + * matches the size calculated by adding the static structure length, the + * component bitmap length, the version string length, the length of all + * descriptor TLVs, and the length of the package data. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +pldm_parse_one_record(struct pldmfw_priv *data, + const struct __pldmfw_record_info *__record) +{ + struct pldmfw_record *record; + size_t measured_length; + int err; + const u8 *bitmap_ptr; + u16 record_len; + int i; + + /* Make a copy and insert it into the record list */ + record = kzalloc(sizeof(*record), GFP_KERNEL); + if (!record) + return -ENOMEM; + + INIT_LIST_HEAD(&record->descs); + list_add_tail(&record->entry, &data->records); + + /* Then check that we have space and move the offset */ + err = pldm_move_fw_offset(data, sizeof(*__record)); + if (err) + return err; + + record_len = get_unaligned_le16(&__record->record_len); + record->package_data_len = get_unaligned_le16(&__record->package_data_len); + record->version_len = __record->version_len; + record->version_type = __record->version_type; + + bitmap_ptr = data->fw->data + data->offset; + + /* check that we have space for the component bitmap length */ + err = pldm_move_fw_offset(data, data->bitmap_size); + if (err) + return err; + + record->component_bitmap_len = data->component_bitmap_len; + record->component_bitmap = bitmap_zalloc(record->component_bitmap_len, + GFP_KERNEL); + if (!record->component_bitmap) + return -ENOMEM; + + for (i = 0; i < data->bitmap_size; i++) + bitmap_set_value8(record->component_bitmap, bitmap_ptr[i], i * 8); + + record->version_string = data->fw->data + data->offset; + + err = pldm_move_fw_offset(data, record->version_len); + if (err) + return err; + + /* Scan through the descriptor TLVs and find the end */ + err = pldm_parse_desc_tlvs(data, record, __record->descriptor_count); + if (err) + return err; + + record->package_data = data->fw->data + data->offset; + + err = pldm_move_fw_offset(data, record->package_data_len); + if (err) + return err; + + measured_length = data->offset - ((const u8 *)__record - data->fw->data); + if (measured_length != record_len) { + dev_dbg(data->context->dev, "Unexpected record length. Measured record length is %zu bytes, expected length is %u bytes\n", + measured_length, record_len); + return -EFAULT; + } + + return 0; +} + +/** + * pldm_parse_records - Locate the start of the component area + * @data: pointer to private data + * + * Extract the record count, and loop through each record, searching for the + * component area. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int pldm_parse_records(struct pldmfw_priv *data) +{ + const struct __pldmfw_component_area *component_area; + const struct __pldmfw_record_info *record; + int err; + u8 i; + + pldm_for_each_record(i, record, data->record_start, data->record_count) { + err = pldm_parse_one_record(data, record); + if (err) + return err; + } + + /* Extract a pointer to the component area, which just follows the + * PLDM device record data. + */ + component_area = (const struct __pldmfw_component_area *)(data->fw->data + data->offset); + + err = pldm_move_fw_offset(data, sizeof(*component_area)); + if (err) + return err; + + data->component_count = + get_unaligned_le16(&component_area->component_image_count); + data->component_start = component_area->components; + + return 0; +} + +/** + * pldm_parse_components - Locate the CRC header checksum + * @data: pointer to private data + * + * Extract the component count, and find the pointer to the component area. + * Scan through each component searching for the end, which should point to + * the package header checksum. + * + * Extract the package header CRC and save it for verification. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int pldm_parse_components(struct pldmfw_priv *data) +{ + const struct __pldmfw_component_info *__component; + struct device *dev = data->context->dev; + const u8 *header_crc_ptr; + int err; + u8 i; + + pldm_for_each_component(i, __component, data->component_start, data->component_count) { + struct pldmfw_component *component; + u32 offset, size; + + err = pldm_move_fw_offset(data, sizeof(*__component)); + if (err) + return err; + + err = pldm_move_fw_offset(data, __component->version_len); + if (err) + return err; + + offset = get_unaligned_le32(&__component->location_offset); + size = get_unaligned_le32(&__component->size); + + err = pldm_check_fw_space(data, offset, size); + if (err) + return err; + + component = kzalloc(sizeof(*component), GFP_KERNEL); + if (!component) + return -ENOMEM; + + component->index = i; + component->classification = get_unaligned_le16(&__component->classification); + component->identifier = get_unaligned_le16(&__component->identifier); + component->comparison_stamp = get_unaligned_le32(&__component->comparison_stamp); + component->options = get_unaligned_le16(&__component->options); + component->activation_method = get_unaligned_le16(&__component->activation_method); + component->version_type = __component->version_type; + component->version_len = __component->version_len; + component->version_string = __component->version_string; + component->component_data = data->fw->data + offset; + component->component_size = size; + + list_add_tail(&component->entry, &data->components); + } + + header_crc_ptr = data->fw->data + data->offset; + + err = pldm_move_fw_offset(data, sizeof(data->header_crc)); + if (err) + return err; + + /* Make sure that we reached the expected offset */ + if (data->offset != data->total_header_size) { + dev_dbg(dev, "Invalid firmware header size. Expected %u but got %zu\n", + data->total_header_size, data->offset); + return -EFAULT; + } + + data->header_crc = get_unaligned_le32(header_crc_ptr); + + return 0; +} + +/** + * pldm_verify_header_crc - Verify that the CRC in the header matches + * @data: pointer to private data + * + * Calculates the 32-bit CRC using the standard IEEE 802.3 CRC polynomial and + * compares it to the value stored in the header. + * + * Returns: zero on success if the CRC matches, or -EBADMSG on an invalid CRC. + */ +static int pldm_verify_header_crc(struct pldmfw_priv *data) +{ + struct device *dev = data->context->dev; + u32 calculated_crc; + size_t length; + + /* Calculate the 32-bit CRC of the header header contents up to but + * not including the checksum. Note that the Linux crc32_le function + * does not perform an expected final XOR. + */ + length = data->offset - sizeof(data->header_crc); + calculated_crc = crc32_le(~0, data->fw->data, length) ^ ~0; + + if (calculated_crc != data->header_crc) { + dev_dbg(dev, "Invalid CRC in firmware header. Got 0x%08x but expected 0x%08x\n", + calculated_crc, data->header_crc); + return -EBADMSG; + } + + return 0; +} + +/** + * pldmfw_free_priv - Free memory allocated while parsing the PLDM image + * @data: pointer to the PLDM data structure + * + * Loops through and clears all allocated memory associated with each + * allocated descriptor, record, and component. + */ +static void pldmfw_free_priv(struct pldmfw_priv *data) +{ + struct pldmfw_component *component, *c_safe; + struct pldmfw_record *record, *r_safe; + struct pldmfw_desc_tlv *desc, *d_safe; + + list_for_each_entry_safe(component, c_safe, &data->components, entry) { + list_del(&component->entry); + kfree(component); + } + + list_for_each_entry_safe(record, r_safe, &data->records, entry) { + list_for_each_entry_safe(desc, d_safe, &record->descs, entry) { + list_del(&desc->entry); + kfree(desc); + } + + if (record->component_bitmap) { + bitmap_free(record->component_bitmap); + record->component_bitmap = NULL; + } + + list_del(&record->entry); + kfree(record); + } +} + +/** + * pldm_parse_image - parse and extract details from PLDM image + * @data: pointer to private data + * + * Verify that the firmware file contains valid data for a PLDM firmware + * file. Extract useful pointers and data from the firmware file and store + * them in the data structure. + * + * The PLDM firmware file format is defined in DMTF DSP0267 1.0.0. Care + * should be taken to use get_unaligned_le* when accessing data from the + * pointers in data. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int pldm_parse_image(struct pldmfw_priv *data) +{ + int err; + + if (WARN_ON(!(data->context->dev && data->fw->data && data->fw->size))) + return -EINVAL; + + err = pldm_parse_header(data); + if (err) + return err; + + err = pldm_parse_records(data); + if (err) + return err; + + err = pldm_parse_components(data); + if (err) + return err; + + return pldm_verify_header_crc(data); +} + +/* these are u32 so that we can store PCI_ANY_ID */ +struct pldm_pci_record_id { + int vendor; + int device; + int subsystem_vendor; + int subsystem_device; +}; + +/** + * pldmfw_op_pci_match_record - Check if a PCI device matches the record + * @context: PLDM fw update structure + * @record: list of records extracted from the PLDM image + * + * Determine of the PCI device associated with this device matches the record + * data provided. + * + * Searches the descriptor TLVs and extracts the relevant descriptor data into + * a pldm_pci_record_id. This is then compared against the PCI device ID + * information. + * + * Returns: true if the device matches the record, false otherwise. + */ +bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record) +{ + struct pci_dev *pdev = to_pci_dev(context->dev); + struct pldm_pci_record_id id = { + .vendor = PCI_ANY_ID, + .device = PCI_ANY_ID, + .subsystem_vendor = PCI_ANY_ID, + .subsystem_device = PCI_ANY_ID, + }; + struct pldmfw_desc_tlv *desc; + + list_for_each_entry(desc, &record->descs, entry) { + u16 value; + int *ptr; + + switch (desc->type) { + case PLDM_DESC_ID_PCI_VENDOR_ID: + ptr = &id.vendor; + break; + case PLDM_DESC_ID_PCI_DEVICE_ID: + ptr = &id.device; + break; + case PLDM_DESC_ID_PCI_SUBVENDOR_ID: + ptr = &id.subsystem_vendor; + break; + case PLDM_DESC_ID_PCI_SUBDEV_ID: + ptr = &id.subsystem_device; + break; + default: + /* Skip unrelated TLVs */ + continue; + } + + value = get_unaligned_le16(desc->data); + /* A value of zero for one of the descriptors is sometimes + * used when the record should ignore this field when matching + * device. For example if the record applies to any subsystem + * device or vendor. + */ + if (value) + *ptr = (int)value; + else + *ptr = PCI_ANY_ID; + } + + if ((id.vendor == PCI_ANY_ID || id.vendor == pdev->vendor) && + (id.device == PCI_ANY_ID || id.device == pdev->device) && + (id.subsystem_vendor == PCI_ANY_ID || id.subsystem_vendor == pdev->subsystem_vendor) && + (id.subsystem_device == PCI_ANY_ID || id.subsystem_device == pdev->subsystem_device)) + return true; + else + return false; +} +EXPORT_SYMBOL(pldmfw_op_pci_match_record); + +/** + * pldm_find_matching_record - Find the first matching PLDM record + * @data: pointer to private data + * + * Search through PLDM records and find the first matching entry. It is + * expected that only one entry matches. + * + * Store a pointer to the matching record, if found. + * + * Returns: zero on success, or -ENOENT if no matching record is found. + */ +static int pldm_find_matching_record(struct pldmfw_priv *data) +{ + struct pldmfw_record *record; + + list_for_each_entry(record, &data->records, entry) { + if (data->context->ops->match_record(data->context, record)) { + data->matching_record = record; + return 0; + } + } + + return -ENOENT; +} + +/** + * pldm_send_package_data - Send firmware the package data for the record + * @data: pointer to private data + * + * Send the package data associated with the matching record to the firmware, + * using the send_pkg_data operation. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +pldm_send_package_data(struct pldmfw_priv *data) +{ + struct pldmfw_record *record = data->matching_record; + const struct pldmfw_ops *ops = data->context->ops; + + return ops->send_package_data(data->context, record->package_data, + record->package_data_len); +} + +/** + * pldm_send_component_tables - Send component table information to firmware + * @data: pointer to private data + * + * Loop over each component, sending the applicable components to the firmware + * via the send_component_table operation. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +pldm_send_component_tables(struct pldmfw_priv *data) +{ + unsigned long *bitmap = data->matching_record->component_bitmap; + struct pldmfw_component *component; + int err; + + list_for_each_entry(component, &data->components, entry) { + u8 index = component->index, transfer_flag = 0; + + /* Skip components which are not intended for this device */ + if (!test_bit(index, bitmap)) + continue; + + /* determine whether this is the start, middle, end, or both + * the start and end of the component tables + */ + if (index == find_first_bit(bitmap, data->component_bitmap_len)) + transfer_flag |= PLDM_TRANSFER_FLAG_START; + if (index == find_last_bit(bitmap, data->component_bitmap_len)) + transfer_flag |= PLDM_TRANSFER_FLAG_END; + if (!transfer_flag) + transfer_flag = PLDM_TRANSFER_FLAG_MIDDLE; + + err = data->context->ops->send_component_table(data->context, + component, + transfer_flag); + if (err) + return err; + } + + return 0; +} + +/** + * pldm_flash_components - Program each component to device flash + * @data: pointer to private data + * + * Loop through each component that is active for the matching device record, + * and send it to the device driver for flashing. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int pldm_flash_components(struct pldmfw_priv *data) +{ + unsigned long *bitmap = data->matching_record->component_bitmap; + struct pldmfw_component *component; + int err; + + list_for_each_entry(component, &data->components, entry) { + u8 index = component->index; + + /* Skip components which are not intended for this device */ + if (!test_bit(index, bitmap)) + continue; + + err = data->context->ops->flash_component(data->context, component); + if (err) + return err; + } + + return 0; +} + +/** + * pldm_finalize_update - Finalize the device flash update + * @data: pointer to private data + * + * Tell the device driver to perform any remaining logic to complete the + * device update. + * + * Returns: zero on success, or a PLFM_FWU error indicating the reason for + * failure. + */ +static int pldm_finalize_update(struct pldmfw_priv *data) +{ + if (data->context->ops->finalize_update) + return data->context->ops->finalize_update(data->context); + + return 0; +} + +/** + * pldmfw_flash_image - Write a PLDM-formatted firmware image to the device + * @context: ops and data for firmware update + * @fw: firmware object pointing to the relevant firmware file to program + * + * Parse the data for a given firmware file, verifying that it is a valid PLDM + * formatted image that matches this device. + * + * Extract the device record Package Data and Component Tables and send them + * to the device firmware. Extract and write the flash data for each of the + * components indicated in the firmware file. + * + * Returns: zero on success, or a negative error code on failure. + */ +int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw) +{ + struct pldmfw_priv *data; + int err; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + INIT_LIST_HEAD(&data->records); + INIT_LIST_HEAD(&data->components); + + data->fw = fw; + data->context = context; + + err = pldm_parse_image(data); + if (err) + goto out_release_data; + + err = pldm_find_matching_record(data); + if (err) + goto out_release_data; + + err = pldm_send_package_data(data); + if (err) + goto out_release_data; + + err = pldm_send_component_tables(data); + if (err) + goto out_release_data; + + err = pldm_flash_components(data); + if (err) + goto out_release_data; + + err = pldm_finalize_update(data); + +out_release_data: + pldmfw_free_priv(data); + kfree(data); + + return err; +} +EXPORT_SYMBOL(pldmfw_flash_image); + +MODULE_AUTHOR("Jacob Keller <jacob.e.keller@intel.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("PLDM firmware flash update library"); diff --git a/lib/pldmfw/pldmfw_private.h b/lib/pldmfw/pldmfw_private.h new file mode 100644 index 000000000000..687ef2200692 --- /dev/null +++ b/lib/pldmfw/pldmfw_private.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#ifndef _PLDMFW_PRIVATE_H_ +#define _PLDMFW_PRIVATE_H_ + +/* The following data structures define the layout of a firmware binary + * following the "PLDM For Firmware Update Specification", DMTF standard + * #DSP0267. + * + * pldmfw.c uses these structures to implement a simple engine that will parse + * a fw binary file in this format and perform a firmware update for a given + * device. + * + * Due to the variable sized data layout, alignment of fields within these + * structures is not guaranteed when reading. For this reason, all multi-byte + * field accesses should be done using the unaligned access macros. + * Additionally, the standard specifies that multi-byte fields are in + * LittleEndian format. + * + * The structure definitions are not made public, in order to keep direct + * accesses within code that is prepared to deal with the limitation of + * unaligned access. + */ + +/* UUID for PLDM firmware packages: f018878c-cb7d-4943-9800-a02f059aca02 */ +static const uuid_t pldm_firmware_header_id = + UUID_INIT(0xf018878c, 0xcb7d, 0x4943, + 0x98, 0x00, 0xa0, 0x2f, 0x05, 0x9a, 0xca, 0x02); + +/* Revision number of the PLDM header format this code supports */ +#define PACKAGE_HEADER_FORMAT_REVISION 0x01 + +/* timestamp104 structure defined in PLDM Base specification */ +#define PLDM_TIMESTAMP_SIZE 13 +struct __pldm_timestamp { + u8 b[PLDM_TIMESTAMP_SIZE]; +} __packed __aligned(1); + +/* Package Header Information */ +struct __pldm_header { + uuid_t id; /* PackageHeaderIdentifier */ + u8 revision; /* PackageHeaderFormatRevision */ + __le16 size; /* PackageHeaderSize */ + struct __pldm_timestamp release_date; /* PackageReleaseDateTime */ + __le16 component_bitmap_len; /* ComponentBitmapBitLength */ + u8 version_type; /* PackageVersionStringType */ + u8 version_len; /* PackageVersionStringLength */ + + /* + * DSP0267 also includes the following variable length fields at the + * end of this structure: + * + * PackageVersionString, length is version_len. + * + * The total size of this section is + * sizeof(pldm_header) + version_len; + */ + u8 version_string[]; /* PackageVersionString */ +} __packed __aligned(1); + +/* Firmware Device ID Record */ +struct __pldmfw_record_info { + __le16 record_len; /* RecordLength */ + u8 descriptor_count; /* DescriptorCount */ + __le32 device_update_flags; /* DeviceUpdateOptionFlags */ + u8 version_type; /* ComponentImageSetVersionType */ + u8 version_len; /* ComponentImageSetVersionLength */ + __le16 package_data_len; /* FirmwareDevicePackageDataLength */ + + /* + * DSP0267 also includes the following variable length fields at the + * end of this structure: + * + * ApplicableComponents, length is component_bitmap_len from header + * ComponentImageSetVersionString, length is version_len + * RecordDescriptors, a series of TLVs with 16bit type and length + * FirmwareDevicePackageData, length is package_data_len + * + * The total size of each record is + * sizeof(pldmfw_record_info) + + * component_bitmap_len (converted to bytes!) + + * version_len + + * <length of RecordDescriptors> + + * package_data_len + */ + u8 variable_record_data[]; +} __packed __aligned(1); + +/* Firmware Descriptor Definition */ +struct __pldmfw_desc_tlv { + __le16 type; /* DescriptorType */ + __le16 size; /* DescriptorSize */ + u8 data[]; /* DescriptorData */ +} __aligned(1); + +/* Firmware Device Identification Area */ +struct __pldmfw_record_area { + u8 record_count; /* DeviceIDRecordCount */ + /* This is not a struct type because the size of each record varies */ + u8 records[]; +} __aligned(1); + +/* Individual Component Image Information */ +struct __pldmfw_component_info { + __le16 classification; /* ComponentClassfication */ + __le16 identifier; /* ComponentIdentifier */ + __le32 comparison_stamp; /* ComponentComparisonStamp */ + __le16 options; /* componentOptions */ + __le16 activation_method; /* RequestedComponentActivationMethod */ + __le32 location_offset; /* ComponentLocationOffset */ + __le32 size; /* ComponentSize */ + u8 version_type; /* ComponentVersionStringType */ + u8 version_len; /* ComponentVersionStringLength */ + + /* + * DSP0267 also includes the following variable length fields at the + * end of this structure: + * + * ComponentVersionString, length is version_len + * + * The total size of this section is + * sizeof(pldmfw_component_info) + version_len; + */ + u8 version_string[]; /* ComponentVersionString */ +} __packed __aligned(1); + +/* Component Image Information Area */ +struct __pldmfw_component_area { + __le16 component_image_count; + /* This is not a struct type because the component size varies */ + u8 components[]; +} __aligned(1); + +/** + * pldm_first_desc_tlv + * @start: byte offset of the start of the descriptor TLVs + * + * Converts the starting offset of the descriptor TLVs into a pointer to the + * first descriptor. + */ +#define pldm_first_desc_tlv(start) \ + ((const struct __pldmfw_desc_tlv *)(start)) + +/** + * pldm_next_desc_tlv + * @desc: pointer to a descriptor TLV + * + * Finds the pointer to the next descriptor following a given descriptor + */ +#define pldm_next_desc_tlv(desc) \ + ((const struct __pldmfw_desc_tlv *)((desc)->data + \ + get_unaligned_le16(&(desc)->size))) + +/** + * pldm_for_each_desc_tlv + * @i: variable to store descriptor index + * @desc: variable to store descriptor pointer + * @start: byte offset of the start of the descriptors + * @count: the number of descriptors + * + * for loop macro to iterate over all of the descriptors of a given PLDM + * record. + */ +#define pldm_for_each_desc_tlv(i, desc, start, count) \ + for ((i) = 0, (desc) = pldm_first_desc_tlv(start); \ + (i) < (count); \ + (i)++, (desc) = pldm_next_desc_tlv(desc)) + +/** + * pldm_first_record + * @start: byte offset of the start of the PLDM records + * + * Converts a starting offset of the PLDM records into a pointer to the first + * record. + */ +#define pldm_first_record(start) \ + ((const struct __pldmfw_record_info *)(start)) + +/** + * pldm_next_record + * @record: pointer to a PLDM record + * + * Finds a pointer to the next record following a given record + */ +#define pldm_next_record(record) \ + ((const struct __pldmfw_record_info *) \ + ((const u8 *)(record) + get_unaligned_le16(&(record)->record_len))) + +/** + * pldm_for_each_record + * @i: variable to store record index + * @record: variable to store record pointer + * @start: byte offset of the start of the records + * @count: the number of records + * + * for loop macro to iterate over all of the records of a PLDM file. + */ +#define pldm_for_each_record(i, record, start, count) \ + for ((i) = 0, (record) = pldm_first_record(start); \ + (i) < (count); \ + (i)++, (record) = pldm_next_record(record)) + +/** + * pldm_first_component + * @start: byte offset of the start of the PLDM components + * + * Convert a starting offset of the PLDM components into a pointer to the + * first component + */ +#define pldm_first_component(start) \ + ((const struct __pldmfw_component_info *)(start)) + +/** + * pldm_next_component + * @component: pointer to a PLDM component + * + * Finds a pointer to the next component following a given component + */ +#define pldm_next_component(component) \ + ((const struct __pldmfw_component_info *)((component)->version_string + \ + (component)->version_len)) + +/** + * pldm_for_each_component + * @i: variable to store component index + * @component: variable to store component pointer + * @start: byte offset to the start of the first component + * @count: the number of components + * + * for loop macro to iterate over all of the components of a PLDM file. + */ +#define pldm_for_each_component(i, component, start, count) \ + for ((i) = 0, (component) = pldm_first_component(start); \ + (i) < (count); \ + (i)++, (component) = pldm_next_component(component)) + +#endif diff --git a/lib/random32.c b/lib/random32.c index 763b920a6206..3d749abb9e80 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void) } #endif -static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DEFINE_PER_CPU(struct rnd_state, net_rand_state); /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9f6890aedd1a..c949c1e3b87c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -31,7 +31,7 @@ union nested_table { union nested_table __rcu *table; - struct rhash_lock_head *bucket; + struct rhash_lock_head __rcu *bucket; }; static u32 head_hashfn(struct rhashtable *ht, @@ -222,7 +222,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, } static int rhashtable_rehash_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); @@ -275,7 +275,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash); + struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); int err; if (!bkt) @@ -485,7 +485,7 @@ fail: } static void *rhashtable_lookup_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, const void *key, struct rhash_head *obj) { @@ -535,12 +535,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, return ERR_PTR(-ENOENT); } -static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, - struct bucket_table *tbl, - unsigned int hash, - struct rhash_head *obj, - void *data) +static struct bucket_table *rhashtable_insert_one( + struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, + struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj, + void *data) { struct bucket_table *new_tbl; struct rhash_head *head; @@ -591,7 +589,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, { struct bucket_table *new_tbl; struct bucket_table *tbl; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; unsigned int hash; void *data; @@ -1173,8 +1171,8 @@ void rhashtable_destroy(struct rhashtable *ht) } EXPORT_SYMBOL_GPL(rhashtable_destroy); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); @@ -1202,10 +1200,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(__rht_bucket_nested); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash) { - static struct rhash_lock_head *rhnull; + static struct rhash_lock_head __rcu *rhnull; if (!rhnull) INIT_RHT_NULLS_HEAD(rhnull); @@ -1213,9 +1211,8 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(rht_bucket_nested); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 13cd683a658a..12ecacf0c55f 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -362,6 +362,10 @@ static void p9_read_work(struct work_struct *work) if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); + } else if (m->rreq->status == REQ_STATUS_FLSHD) { + /* Ignore replies associated with a cancelled request. */ + p9_debug(P9_DEBUG_TRANS, + "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->client->lock); p9_debug(P9_DEBUG_ERROR, @@ -703,11 +707,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + spin_lock(&client->lock); + /* Ignore cancelled request if message has been received + * before lock. + */ + if (req->status == REQ_STATUS_RCVD) { + spin_unlock(&client->lock); + return 0; + } + /* we haven't received a response for oldreq, * remove it from the list. */ - spin_lock(&client->lock); list_del(&req->req_list); + req->status = REQ_STATUS_FLSHD; spin_unlock(&client->lock); p9_req_put(req); @@ -803,20 +816,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) return -ENOMEM; ts->rd = fget(rfd); + if (!ts->rd) + goto out_free_ts; + if (!(ts->rd->f_mode & FMODE_READ)) + goto out_put_rd; ts->wr = fget(wfd); - if (!ts->rd || !ts->wr) { - if (ts->rd) - fput(ts->rd); - if (ts->wr) - fput(ts->wr); - kfree(ts); - return -EIO; - } + if (!ts->wr) + goto out_put_rd; + if (!(ts->wr->f_mode & FMODE_WRITE)) + goto out_put_wr; client->trans = ts; client->status = Connected; return 0; + +out_put_wr: + fput(ts->wr); +out_put_rd: + fput(ts->rd); +out_free_ts: + kfree(ts); + return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index 550c6ca007cc..9c1241292d1d 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -229,6 +229,8 @@ int __init atalk_proc_init(void) sizeof(struct aarp_iter_state), NULL)) goto out; + return 0; + out: remove_proc_subtree("atalk", init_net.proc_net); return -ENOMEM; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index bb55d92691b0..cff4944d5b66 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -50,6 +50,7 @@ static bool enable_6lowpan; /* We are listening incoming connections via this channel */ static struct l2cap_chan *listen_chan; +static DEFINE_MUTEX(set_lock); struct lowpan_peer { struct list_head list; @@ -1078,12 +1079,14 @@ static void do_enable_set(struct work_struct *work) enable_6lowpan = set_enable->flag; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); } listen_chan = bt_6lowpan_listen(); + mutex_unlock(&set_lock); kfree(set_enable); } @@ -1135,11 +1138,13 @@ static ssize_t lowpan_control_write(struct file *fp, if (ret == -EINVAL) return ret; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); listen_chan = NULL; } + mutex_unlock(&set_lock); if (conn) { struct lowpan_peer *peer; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 1d6d243cdde9..e2497d764e97 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -21,7 +21,7 @@ menuconfig BT It was designed as a replacement for cables and other short-range technologies like IrDA. Bluetooth operates in personal area range that typically extends up to 10 meters. More information about - Bluetooth can be found at <http://www.bluetooth.com/>. + Bluetooth can be found at <https://www.bluetooth.com/>. Linux Bluetooth subsystem consist of several layers: Bluetooth Core diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 41dd541a44a5..1c645fba8c49 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -14,7 +14,7 @@ bluetooth_6lowpan-y := 6lowpan.o bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o lib.o \ - ecdh_helper.o hci_request.o mgmt_util.o + ecdh_helper.o hci_request.o mgmt_util.o mgmt_config.o bluetooth-$(CONFIG_BT_BREDR) += sco.o bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 3fd124927d4d..4ef6a54403aa 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -286,6 +286,9 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (msg->msg_name && bt_sk(sk)->skb_msg_name) bt_sk(sk)->skb_msg_name(skb, msg->msg_name, &msg->msg_namelen); + + if (bt_sk(sk)->skb_put_cmsg) + bt_sk(sk)->skb_put_cmsg(skb, msg, sk); } skb_free_datagram(sk, skb); @@ -453,8 +456,6 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask = 0; - BT_DBG("sock %p, sk %p", sock, sk); - poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == BT_LISTEN) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 307800fd18e6..9832f8445d43 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -789,11 +789,8 @@ static void set_ext_conn_params(struct hci_conn *conn, 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->scan_interval = cpu_to_le16(hdev->le_scan_int_connect); + p->scan_window = cpu_to_le16(hdev->le_scan_window_connect); 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); @@ -875,11 +872,8 @@ static void hci_req_add_le_create_conn(struct hci_request *req, 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; + cp.scan_interval = cpu_to_le16(hdev->le_scan_int_connect); + cp.scan_window = cpu_to_le16(hdev->le_scan_window_connect); bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; @@ -937,7 +931,7 @@ static void hci_req_directed_advertising(struct hci_request *req, * So it is required to remove adv set for handle 0x00. since we use * instance 0 for directed adv. */ - hci_req_add(req, HCI_OP_LE_REMOVE_ADV_SET, sizeof(cp.handle), &cp.handle); + __hci_req_remove_ext_adv_instance(req, cp.handle); hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); @@ -1009,6 +1003,11 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, struct hci_request req; int err; + /* This ensures that during disable le_scan address resolution + * will not be disabled if it is followed by le_create_conn + */ + bool rpa_le_conn = true; + /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) @@ -1109,7 +1108,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, * state. */ if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) { - hci_req_add_le_scan_disable(&req); + hci_req_add_le_scan_disable(&req, rpa_le_conn); hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED); } @@ -1180,7 +1179,8 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, /* This function requires the caller holds hdev->lock */ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, - u16 conn_timeout) + u16 conn_timeout, + enum conn_reasons conn_reason) { struct hci_conn *conn; @@ -1225,6 +1225,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, conn->sec_level = BT_SECURITY_LOW; conn->pending_sec_level = sec_level; conn->conn_timeout = conn_timeout; + conn->conn_reason = conn_reason; hci_update_background_scan(hdev); @@ -1234,7 +1235,8 @@ done: } struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, - u8 sec_level, u8 auth_type) + u8 sec_level, u8 auth_type, + enum conn_reasons conn_reason) { struct hci_conn *acl; @@ -1254,6 +1256,7 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, hci_conn_hold(acl); + acl->conn_reason = conn_reason; if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { acl->sec_level = BT_SECURITY_LOW; acl->pending_sec_level = sec_level; @@ -1270,7 +1273,8 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, struct hci_conn *acl; struct hci_conn *sco; - acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING); + acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING, + CONN_REASON_SCO_CONNECT); if (IS_ERR(acl)) return acl; @@ -1323,6 +1327,23 @@ int hci_conn_check_link_mode(struct hci_conn *conn) return 0; } + /* AES encryption is required for Level 4: + * + * BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 3, Part C + * page 1319: + * + * 128-bit equivalent strength for link and encryption keys + * required using FIPS approved algorithms (E0 not allowed, + * SAFER+ not allowed, and P-192 not allowed; encryption key + * not shortened) + */ + if (conn->sec_level == BT_SECURITY_FIPS && + !test_bit(HCI_CONN_AES_CCM, &conn->flags)) { + bt_dev_err(conn->hdev, + "Invalid security: Missing AES-CCM usage"); + return 0; + } + if (hci_conn_ssp_enabled(conn) && !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index dbe2d79f233f..68bfe57b6625 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -26,7 +26,6 @@ /* Bluetooth HCI core. */ #include <linux/export.h> -#include <linux/idr.h> #include <linux/rfkill.h> #include <linux/debugfs.h> #include <linux/crypto.h> @@ -606,7 +605,8 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[8] & 0x01) hci_req_add(req, HCI_OP_READ_PAGE_SCAN_ACTIVITY, 0, NULL); - if (hdev->commands[18] & 0x04) + if (hdev->commands[18] & 0x04 && + !test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) hci_req_add(req, HCI_OP_READ_DEF_ERR_DATA_REPORTING, 0, NULL); /* Some older Broadcom based Bluetooth 1.2 controllers do not @@ -763,6 +763,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_CLEAR_RESOLV_LIST, 0, NULL); } + if (hdev->commands[35] & 0x40) { + __le16 rpa_timeout = cpu_to_le16(hdev->rpa_timeout); + + /* Set RPA timeout */ + hci_req_add(req, HCI_OP_LE_SET_RPA_TIMEOUT, 2, + &rpa_timeout); + } + 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); @@ -851,7 +859,8 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) /* Set erroneous data reporting if supported to the wideband speech * setting value */ - if (hdev->commands[18] & 0x08) { + if (hdev->commands[18] & 0x08 && + !test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) { bool enabled = hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED); @@ -2982,7 +2991,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, adv_instance->remaining_time = timeout; if (duration == 0) - adv_instance->duration = HCI_DEFAULT_ADV_DURATION; + adv_instance->duration = hdev->def_multi_adv_rotation_duration; else adv_instance->duration = duration; @@ -2996,6 +3005,94 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, return 0; } +/* This function requires the caller holds hdev->lock */ +void hci_adv_monitors_clear(struct hci_dev *hdev) +{ + struct adv_monitor *monitor; + int handle; + + idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) + hci_free_adv_monitor(monitor); + + idr_destroy(&hdev->adv_monitors_idr); +} + +void hci_free_adv_monitor(struct adv_monitor *monitor) +{ + struct adv_pattern *pattern; + struct adv_pattern *tmp; + + if (!monitor) + return; + + list_for_each_entry_safe(pattern, tmp, &monitor->patterns, list) + kfree(pattern); + + kfree(monitor); +} + +/* This function requires the caller holds hdev->lock */ +int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) +{ + int min, max, handle; + + if (!monitor) + return -EINVAL; + + min = HCI_MIN_ADV_MONITOR_HANDLE; + max = HCI_MIN_ADV_MONITOR_HANDLE + HCI_MAX_ADV_MONITOR_NUM_HANDLES; + handle = idr_alloc(&hdev->adv_monitors_idr, monitor, min, max, + GFP_KERNEL); + if (handle < 0) + return handle; + + hdev->adv_monitors_cnt++; + monitor->handle = handle; + + hci_update_background_scan(hdev); + + return 0; +} + +static int free_adv_monitor(int id, void *ptr, void *data) +{ + struct hci_dev *hdev = data; + struct adv_monitor *monitor = ptr; + + idr_remove(&hdev->adv_monitors_idr, monitor->handle); + hci_free_adv_monitor(monitor); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle) +{ + struct adv_monitor *monitor; + + if (handle) { + monitor = idr_find(&hdev->adv_monitors_idr, handle); + if (!monitor) + return -ENOENT; + + idr_remove(&hdev->adv_monitors_idr, monitor->handle); + hci_free_adv_monitor(monitor); + } else { + /* Remove all monitors if handle is 0. */ + idr_for_each(&hdev->adv_monitors_idr, &free_adv_monitor, hdev); + } + + hci_update_background_scan(hdev); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +bool hci_is_adv_monitoring(struct hci_dev *hdev) +{ + return !idr_is_empty(&hdev->adv_monitors_idr); +} + struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { @@ -3023,6 +3120,20 @@ struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( return NULL; } +struct bdaddr_list_with_flags * +hci_bdaddr_list_lookup_with_flags(struct list_head *bdaddr_list, + bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list_with_flags *b; + + list_for_each_entry(b, bdaddr_list, list) { + if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) + return b; + } + + return NULL; +} + void hci_bdaddr_list_clear(struct list_head *bdaddr_list) { struct bdaddr_list *b, *n; @@ -3084,6 +3195,30 @@ int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, return 0; } +int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, + u8 type, u32 flags) +{ + struct bdaddr_list_with_flags *entry; + + if (!bacmp(bdaddr, BDADDR_ANY)) + return -EBADF; + + if (hci_bdaddr_list_lookup(list, bdaddr, type)) + return -EEXIST; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + bacpy(&entry->bdaddr, bdaddr); + entry->bdaddr_type = type; + entry->current_flags = flags; + + list_add(&entry->list, list); + + return 0; +} + int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; @@ -3123,6 +3258,26 @@ int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, return 0; } +int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, + u8 type) +{ + struct bdaddr_list_with_flags *entry; + + if (!bacmp(bdaddr, BDADDR_ANY)) { + hci_bdaddr_list_clear(list); + return 0; + } + + entry = hci_bdaddr_list_lookup_with_flags(list, bdaddr, type); + if (!entry) + return -ENOENT; + + list_del(&entry->list); + kfree(entry); + + return 0; +} + /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) @@ -3145,6 +3300,15 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, { struct hci_conn_params *param; + switch (addr_type) { + case ADDR_LE_DEV_PUBLIC_RESOLVED: + addr_type = ADDR_LE_DEV_PUBLIC; + break; + case ADDR_LE_DEV_RANDOM_RESOLVED: + addr_type = ADDR_LE_DEV_RANDOM; + break; + } + list_for_each_entry(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && param->addr_type == addr_type) @@ -3289,10 +3453,10 @@ static int hci_suspend_wait_event(struct hci_dev *hdev) WAKE_COND, SUSPEND_NOTIFIER_TIMEOUT); if (ret == 0) { - bt_dev_dbg(hdev, "Timed out waiting for suspend"); + bt_dev_err(hdev, "Timed out waiting for suspend events"); for (i = 0; i < __SUSPEND_NUM_TASKS; ++i) { if (test_bit(i, hdev->suspend_tasks)) - bt_dev_dbg(hdev, "Bit %d is set", i); + bt_dev_err(hdev, "Suspend timeout bit: %d", i); clear_bit(i, hdev->suspend_tasks); } @@ -3360,12 +3524,15 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, ret = hci_change_suspend_state(hdev, BT_RUNNING); } - /* If suspend failed, restore it to running */ - if (ret && action == PM_SUSPEND_PREPARE) - hci_change_suspend_state(hdev, BT_RUNNING); - done: - return ret ? notifier_from_errno(-EBUSY) : NOTIFY_STOP; + /* We always allow suspend even if suspend preparation failed and + * attempt to recover in resume. + */ + if (ret) + bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", + action, ret); + + return NOTIFY_DONE; } /* Alloc HCI device */ @@ -3397,6 +3564,12 @@ struct hci_dev *hci_alloc_dev(void) hdev->le_adv_max_interval = 0x0800; hdev->le_scan_interval = 0x0060; hdev->le_scan_window = 0x0030; + hdev->le_scan_int_suspend = 0x0400; + hdev->le_scan_window_suspend = 0x0012; + hdev->le_scan_int_discovery = DISCOV_LE_SCAN_INT; + hdev->le_scan_window_discovery = DISCOV_LE_SCAN_WIN; + hdev->le_scan_int_connect = 0x0060; + hdev->le_scan_window_connect = 0x0060; hdev->le_conn_min_interval = 0x0018; hdev->le_conn_max_interval = 0x0028; hdev->le_conn_latency = 0x0000; @@ -3412,6 +3585,8 @@ struct hci_dev *hci_alloc_dev(void) hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_num_of_adv_sets = HCI_MAX_ADV_INSTANCES; + hdev->def_multi_adv_rotation_duration = HCI_DEFAULT_ADV_DURATION; + hdev->def_le_autoconnect_timeout = HCI_LE_AUTOCONN_TIMEOUT; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; @@ -3420,13 +3595,17 @@ struct hci_dev *hci_alloc_dev(void) hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE; + /* default 1.28 sec page scan */ + hdev->def_page_scan_type = PAGE_SCAN_TYPE_STANDARD; + hdev->def_page_scan_int = 0x0800; + hdev->def_page_scan_window = 0x0012; + mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->blacklist); INIT_LIST_HEAD(&hdev->whitelist); - INIT_LIST_HEAD(&hdev->wakeable); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); @@ -3574,6 +3753,8 @@ int hci_register_dev(struct hci_dev *hdev) queue_work(hdev->req_workqueue, &hdev->power_on); + idr_init(&hdev->adv_monitors_idr); + return id; err_wqueue: @@ -3603,9 +3784,10 @@ void hci_unregister_dev(struct hci_dev *hdev) cancel_work_sync(&hdev->power_on); - hci_dev_do_close(hdev); - unregister_pm_notifier(&hdev->suspend_notifier); + cancel_work_sync(&hdev->suspend_prepare); + + hci_dev_do_close(hdev); if (!test_bit(HCI_INIT, &hdev->flags) && !hci_dev_test_flag(hdev, HCI_SETUP) && @@ -3644,6 +3826,7 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); + hci_adv_monitors_clear(hdev); hci_bdaddr_list_clear(&hdev->le_white_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); @@ -4551,6 +4734,7 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { /* Send to upper protocol */ + bt_cb(skb)->sco.pkt_status = flags & 0x03; sco_recv_scodata(conn, skb); return; } else { diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index cfeaee347db3..4b7fc430793c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1338,6 +1338,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; + if (len > HCI_MAX_AD_LENGTH) + return; + bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; @@ -2296,6 +2299,22 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, if (!conn) return; + /* When using controller based address resolution, then the new + * address types 0x02 and 0x03 are used. These types need to be + * converted back into either public address or random address type + */ + if (use_ll_privacy(hdev) && + hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) { + switch (own_address_type) { + case ADDR_LE_DEV_PUBLIC_RESOLVED: + own_address_type = ADDR_LE_DEV_PUBLIC; + break; + case ADDR_LE_DEV_RANDOM_RESOLVED: + own_address_type = ADDR_LE_DEV_RANDOM; + break; + } + } + /* Store the initiator and responder address information which * is needed for SMP. These values will not change during the * lifetime of the connection. @@ -2517,7 +2536,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -2697,10 +2716,10 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) */ if (hci_dev_test_flag(hdev, HCI_MGMT) && !hci_dev_test_flag(hdev, HCI_CONNECTABLE) && - !hci_bdaddr_list_lookup(&hdev->whitelist, &ev->bdaddr, - BDADDR_BREDR)) { - hci_reject_conn(hdev, &ev->bdaddr); - return; + !hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, &ev->bdaddr, + BDADDR_BREDR)) { + hci_reject_conn(hdev, &ev->bdaddr); + return; } /* Connection accepted */ @@ -2825,7 +2844,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) case HCI_AUTO_CONN_LINK_LOSS: if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT) break; - /* Fall through */ + fallthrough; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: @@ -3065,27 +3084,23 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + /* Check link security requirements are met */ + if (!hci_conn_check_link_mode(conn)) + ev->status = HCI_ERROR_AUTH_FAILURE; + if (ev->status && conn->state == BT_CONNECTED) { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); + /* Notify upper layers so they can cleanup before + * disconnecting. + */ + hci_encrypt_cfm(conn, ev->status); hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } - /* In Secure Connections Only mode, do not allow any connections - * that are not encrypted with AES-CCM using a P-256 authenticated - * combination key. - */ - if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && - (!test_bit(HCI_CONN_AES_CCM, &conn->flags) || - conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) { - hci_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE); - hci_conn_drop(conn); - goto unlock; - } - /* Try reading the encryption key size for encrypted ACL links */ if (!ev->status && ev->encrypt && conn->type == ACL_LINK) { struct hci_cp_read_enc_key_size cp; @@ -4163,6 +4178,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, struct inquiry_info_with_rssi_and_pscan_mode *info; info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4184,6 +4202,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } else { struct inquiry_info_with_rssi *info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4204,6 +4225,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } } +unlock: hci_dev_unlock(hdev); } @@ -4324,7 +4346,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, if (hci_setup_sync(conn, conn->link->handle)) goto unlock; } - /* fall through */ + fallthrough; default: conn->state = BT_CLOSED; @@ -4379,7 +4401,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -5209,6 +5231,11 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); + + if (use_ll_privacy(hdev) && + hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && + hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) + hci_req_disable_address_resolution(hdev); } static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -5319,7 +5346,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, } conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, - HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER, + hdev->def_le_autoconnect_timeout, HCI_ROLE_MASTER, direct_rpa); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned @@ -5355,7 +5382,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len) + u8 direct_addr_type, s8 rssi, u8 *data, u8 len, + bool ext_adv) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -5377,6 +5405,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } + if (!ext_adv && len > HCI_MAX_AD_LENGTH) { + bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + return; + } + /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * @@ -5437,7 +5470,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type, direct_addr); - if (conn && type == LE_ADV_IND) { + if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -5447,14 +5480,15 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* Passive scanning shouldn't trigger any device found events, * except for devices marked as CONN_REPORT for which we do send - * device found events. + * device found events, or advertisement monitoring requested. */ if (hdev->le_scan_type == LE_SCAN_PASSIVE) { if (type == LE_ADV_DIRECT_IND) return; if (!hci_pend_le_action_lookup(&hdev->pend_le_reports, - bdaddr, bdaddr_type)) + bdaddr, bdaddr_type) && + idr_is_empty(&hdev->adv_monitors_idr)) return; if (type == LE_ADV_NONCONN_IND || type == LE_ADV_SCAN_IND) @@ -5491,7 +5525,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * event or send an immediate device found event if the data * should not be stored for later. */ - if (!has_pending_adv_report(hdev)) { + if (!ext_adv && !has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ @@ -5526,7 +5560,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* If the new report will trigger a SCAN_REQ store it for * later merging. */ - if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { + if (!ext_adv && (type == LE_ADV_IND || + type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; @@ -5566,7 +5601,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) rssi = ev->data[ev->length]; process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, rssi, - ev->data, ev->length); + ev->data, ev->length, false); } else { bt_dev_err(hdev, "Dropping invalid advertising data"); } @@ -5638,7 +5673,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) 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); + ev->data, ev->length, + !(evt_type & LE_EXT_ADV_LEGACY_PDU)); } ptr += sizeof(*ev) + ev->length; @@ -5836,7 +5872,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, &ev->direct_addr, - ev->direct_addr_type, ev->rssi, NULL, 0); + ev->direct_addr_type, ev->rssi, NULL, 0, + false); ptr += sizeof(*ev); } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 1fc55685da62..e0269192f2e5 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -34,9 +34,6 @@ #define HCI_REQ_PEND 1 #define HCI_REQ_CANCELED 2 -#define LE_SUSPEND_SCAN_WINDOW 0x0012 -#define LE_SUSPEND_SCAN_INTERVAL 0x0400 - void hci_req_init(struct hci_request *req, struct hci_dev *hdev) { skb_queue_head_init(&req->cmd_q); @@ -366,13 +363,11 @@ void __hci_req_write_fast_connectable(struct hci_request *req, bool enable) /* 160 msec page scan interval */ acp.interval = cpu_to_le16(0x0100); } else { - type = PAGE_SCAN_TYPE_STANDARD; /* default */ - - /* default 1.28 sec page scan */ - acp.interval = cpu_to_le16(0x0800); + type = hdev->def_page_scan_type; + acp.interval = cpu_to_le16(hdev->def_page_scan_int); } - acp.window = cpu_to_le16(0x0012); + acp.window = cpu_to_le16(hdev->def_page_scan_window); if (__cpu_to_le16(hdev->page_scan_interval) != acp.interval || __cpu_to_le16(hdev->page_scan_window) != acp.window) @@ -418,18 +413,22 @@ static void __hci_update_background_scan(struct hci_request *req) */ hci_discovery_filter_clear(hdev); + BT_DBG("%s ADV monitoring is %s", hdev->name, + hci_is_adv_monitoring(hdev) ? "on" : "off"); + if (list_empty(&hdev->pend_le_conns) && - list_empty(&hdev->pend_le_reports)) { + list_empty(&hdev->pend_le_reports) && + !hci_is_adv_monitoring(hdev)) { /* If there is no pending LE connections or devices - * to be scanned for, we should stop the background - * scanning. + * to be scanned for or no ADV monitors, we should stop the + * background scanning. */ /* If controller is not scanning we are done. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) return; - hci_req_add_le_scan_disable(req); + hci_req_add_le_scan_disable(req, false); BT_DBG("%s stopping background scanning", hdev->name); } else { @@ -448,7 +447,7 @@ static void __hci_update_background_scan(struct hci_request *req) * don't miss any advertising (due to duplicates filter). */ if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) - hci_req_add_le_scan_disable(req); + hci_req_add_le_scan_disable(req, false); hci_req_add_le_passive_scan(req); @@ -653,7 +652,7 @@ void __hci_req_update_eir(struct hci_request *req) hci_req_add(req, HCI_OP_WRITE_EIR, sizeof(cp), &cp); } -void hci_req_add_le_scan_disable(struct hci_request *req) +void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn) { struct hci_dev *hdev = req->hdev; @@ -676,6 +675,15 @@ void hci_req_add_le_scan_disable(struct hci_request *req) cp.enable = LE_SCAN_DISABLE; hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); } + + /* Disable address resolution */ + if (use_ll_privacy(hdev) && + hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && + hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION) && !rpa_le_conn) { + __u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE, 1, &enable); + } } static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr, @@ -689,6 +697,21 @@ static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr, bt_dev_dbg(req->hdev, "Remove %pMR (0x%x) from whitelist", &cp.bdaddr, cp.bdaddr_type); hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, sizeof(cp), &cp); + + if (use_ll_privacy(req->hdev)) { + struct smp_irk *irk; + + irk = hci_find_irk_by_addr(req->hdev, bdaddr, bdaddr_type); + if (irk) { + struct hci_cp_le_del_from_resolv_list cp; + + cp.bdaddr_type = bdaddr_type; + bacpy(&cp.bdaddr, bdaddr); + + hci_req_add(req, HCI_OP_LE_DEL_FROM_RESOLV_LIST, + sizeof(cp), &cp); + } + } } /* Adds connection to white list if needed. On error, returns -1. */ @@ -709,13 +732,14 @@ static int add_to_white_list(struct hci_request *req, return -1; /* White list can not be used with RPAs */ - if (!allow_rpa && + if (!allow_rpa && !use_ll_privacy(hdev) && hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) { return -1; } /* During suspend, only wakeable devices can be in whitelist */ - if (hdev->suspended && !params->wakeable) + if (hdev->suspended && !hci_conn_test_flag(HCI_CONN_FLAG_REMOTE_WAKEUP, + params->current_flags)) return 0; *num_entries += 1; @@ -726,6 +750,28 @@ static int add_to_white_list(struct hci_request *req, cp.bdaddr_type); hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp); + if (use_ll_privacy(hdev)) { + struct smp_irk *irk; + + irk = hci_find_irk_by_addr(hdev, ¶ms->addr, + params->addr_type); + if (irk) { + struct hci_cp_le_add_to_resolv_list cp; + + cp.bdaddr_type = params->addr_type; + bacpy(&cp.bdaddr, ¶ms->addr); + memcpy(cp.peer_irk, irk->val, 16); + + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) + memcpy(cp.local_irk, hdev->irk, 16); + else + memset(cp.local_irk, 0, 16); + + hci_req_add(req, HCI_OP_LE_ADD_TO_RESOLV_LIST, + sizeof(cp), &cp); + } + } + return 0; } @@ -766,7 +812,7 @@ static u8 update_white_list(struct hci_request *req) } /* White list can not be used with RPAs */ - if (!allow_rpa && + if (!allow_rpa && !use_ll_privacy(hdev) && hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { return 0x00; } @@ -798,6 +844,14 @@ static u8 update_white_list(struct hci_request *req) return 0x00; } + /* Once the controller offloading of advertisement monitor is in place, + * the if condition should include the support of MSFT extension + * support. If suspend is ongoing, whitelist should be the default to + * prevent waking by random advertisements. + */ + if (!idr_is_empty(&hdev->adv_monitors_idr) && !hdev->suspended) + return 0x00; + /* Select filter policy to use white list */ return 0x01; } @@ -808,10 +862,24 @@ static bool scan_use_rpa(struct hci_dev *hdev) } static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, - u16 window, u8 own_addr_type, u8 filter_policy) + u16 window, u8 own_addr_type, u8 filter_policy, + bool addr_resolv) { struct hci_dev *hdev = req->hdev; + if (hdev->scanning_paused) { + bt_dev_dbg(hdev, "Scanning is paused for suspend"); + return; + } + + if (use_ll_privacy(hdev) && + hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && + addr_resolv) { + u8 enable = 0x01; + + hci_req_add(req, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE, 1, &enable); + } + /* Use ext scanning if set ext scan param and ext scan enable is * supported */ @@ -885,12 +953,39 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, } } +/* Returns true if an le connection is in the scanning state */ +static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type == LE_LINK && c->state == BT_CONNECT && + test_bit(HCI_CONN_SCANNING, &c->flags)) { + rcu_read_unlock(); + return true; + } + } + + rcu_read_unlock(); + + return false; +} + +/* Ensure to call hci_req_add_le_scan_disable() first to disable the + * controller based address resolution to be able to reconfigure + * resolving list. + */ void hci_req_add_le_passive_scan(struct hci_request *req) { struct hci_dev *hdev = req->hdev; u8 own_addr_type; u8 filter_policy; u16 window, interval; + /* Background scanning should run with address resolution */ + bool addr_resolv = true; if (hdev->scanning_paused) { bt_dev_dbg(hdev, "Scanning is paused for suspend"); @@ -927,8 +1022,11 @@ void hci_req_add_le_passive_scan(struct hci_request *req) filter_policy |= 0x02; if (hdev->suspended) { - window = LE_SUSPEND_SCAN_WINDOW; - interval = LE_SUSPEND_SCAN_INTERVAL; + window = hdev->le_scan_window_suspend; + interval = hdev->le_scan_int_suspend; + } else if (hci_is_le_conn_scanning(hdev)) { + window = hdev->le_scan_window_connect; + interval = hdev->le_scan_int_connect; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; @@ -936,7 +1034,7 @@ void hci_req_add_le_passive_scan(struct hci_request *req) bt_dev_dbg(hdev, "LE passive scan with whitelist = %d", filter_policy); hci_req_start_scan(req, LE_SCAN_PASSIVE, interval, window, - own_addr_type, filter_policy); + own_addr_type, filter_policy, addr_resolv); } static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance) @@ -973,15 +1071,19 @@ static void hci_req_clear_event_filter(struct hci_request *req) static void hci_req_set_event_filter(struct hci_request *req) { - struct bdaddr_list *b; + struct bdaddr_list_with_flags *b; struct hci_cp_set_event_filter f; struct hci_dev *hdev = req->hdev; - u8 scan; + u8 scan = SCAN_DISABLED; /* Always clear event filter when starting */ hci_req_clear_event_filter(req); - list_for_each_entry(b, &hdev->wakeable, list) { + list_for_each_entry(b, &hdev->whitelist, list) { + if (!hci_conn_test_flag(HCI_CONN_FLAG_REMOTE_WAKEUP, + b->current_flags)) + continue; + memset(&f, 0, sizeof(f)); bacpy(&f.addr_conn_flt.bdaddr, &b->bdaddr); f.flt_type = HCI_FLT_CONN_SETUP; @@ -990,16 +1092,17 @@ static void hci_req_set_event_filter(struct hci_request *req) bt_dev_dbg(hdev, "Adding event filters for %pMR", &b->bdaddr); hci_req_add(req, HCI_OP_SET_EVENT_FLT, sizeof(f), &f); + scan = SCAN_PAGE; } - scan = !list_empty(&hdev->wakeable) ? SCAN_PAGE : SCAN_DISABLED; hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } static void hci_req_config_le_suspend_scan(struct hci_request *req) { - /* Can't change params without disabling first */ - hci_req_add_le_scan_disable(req); + /* Before changing params disable scan if enabled */ + if (hci_dev_test_flag(req->hdev, HCI_LE_SCAN)) + hci_req_add_le_scan_disable(req, false); /* Configure params and enable scanning */ hci_req_add_le_passive_scan(req); @@ -1065,8 +1168,9 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) page_scan = SCAN_DISABLED; hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &page_scan); - /* Disable LE passive scan */ - hci_req_add_le_scan_disable(&req); + /* Disable LE passive scan if enabled */ + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) + hci_req_add_le_scan_disable(&req, false); /* Mark task needing completion */ set_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks); @@ -1160,13 +1264,8 @@ static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) void __hci_req_disable_advertising(struct hci_request *req) { if (ext_adv_capable(req->hdev)) { - struct hci_cp_le_set_ext_adv_enable cp; - - cp.enable = 0x00; - /* Disable all sets since we only support one set at the moment */ - cp.num_of_sets = 0x00; + __hci_req_disable_ext_adv_instance(req, 0x00); - hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, sizeof(cp), &cp); } else { u8 enable = 0x00; @@ -1627,6 +1726,28 @@ int hci_req_update_adv_data(struct hci_dev *hdev, u8 instance) return hci_req_run(&req, NULL); } +static void enable_addr_resolution_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + BT_DBG("%s status %u", hdev->name, status); +} + +void hci_req_disable_address_resolution(struct hci_dev *hdev) +{ + struct hci_request req; + __u8 enable = 0x00; + + if (!use_ll_privacy(hdev) && + !hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) + return; + + hci_req_init(&req, hdev); + + hci_req_add(&req, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE, 1, &enable); + + hci_req_run(&req, enable_addr_resolution_complete); +} + static void adv_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) { BT_DBG("%s status %u", hdev->name, status); @@ -1786,8 +1907,6 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) 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); @@ -1820,8 +1939,9 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) 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)); + /* In ext adv set param interval is 3 octets */ + hci_cpu_to_le24(hdev->le_adv_min_interval, cp.min_interval); + hci_cpu_to_le24(hdev->le_adv_max_interval, cp.max_interval); secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK); @@ -1932,13 +2052,59 @@ int __hci_req_enable_ext_advertising(struct hci_request *req, u8 instance) return 0; } +int __hci_req_disable_ext_adv_instance(struct hci_request *req, u8 instance) +{ + struct hci_dev *hdev = req->hdev; + 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]; + u8 req_size; + + /* If request specifies an instance that doesn't exist, fail */ + if (instance > 0 && !hci_find_adv_instance(hdev, instance)) + return -EINVAL; + + memset(data, 0, sizeof(data)); + + cp = (void *)data; + adv_set = (void *)cp->data; + + /* Instance 0x00 indicates all advertising instances will be disabled */ + cp->num_of_sets = !!instance; + cp->enable = 0x00; + + adv_set->handle = instance; + + req_size = sizeof(*cp) + sizeof(*adv_set) * cp->num_of_sets; + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, req_size, data); + + return 0; +} + +int __hci_req_remove_ext_adv_instance(struct hci_request *req, u8 instance) +{ + struct hci_dev *hdev = req->hdev; + + /* If request specifies an instance that doesn't exist, fail */ + if (instance > 0 && !hci_find_adv_instance(hdev, instance)) + return -EINVAL; + + hci_req_add(req, HCI_OP_LE_REMOVE_ADV_SET, sizeof(instance), &instance); + + return 0; +} + int __hci_req_start_ext_adv(struct hci_request *req, u8 instance) { struct hci_dev *hdev = req->hdev; + struct adv_info *adv_instance = hci_find_adv_instance(hdev, instance); int err; - if (hci_dev_test_flag(hdev, HCI_LE_ADV)) - __hci_req_disable_advertising(req); + /* If instance isn't pending, the chip knows about it, and it's safe to + * disable + */ + if (adv_instance && !adv_instance->pending) + __hci_req_disable_ext_adv_instance(req, instance); err = __hci_req_setup_ext_adv_instance(req, instance); if (err < 0) @@ -2086,7 +2252,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, hci_dev_test_flag(hdev, HCI_ADVERTISING)) return; - if (next_instance) + if (next_instance && !ext_adv_capable(hdev)) __hci_req_schedule_adv_instance(req, next_instance->instance, false); } @@ -2128,7 +2294,13 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, if (use_rpa) { int to; - *own_addr_type = ADDR_LE_DEV_RANDOM; + /* If Controller supports LL Privacy use own address type is + * 0x03 + */ + if (use_ll_privacy(hdev)) + *own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED; + else + *own_addr_type = ADDR_LE_DEV_RANDOM; if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) && !bacmp(&hdev->random_addr, &hdev->rpa)) @@ -2547,7 +2719,7 @@ static void bg_scan_update(struct work_struct *work) static int le_scan_disable(struct hci_request *req, unsigned long opt) { - hci_req_add_le_scan_disable(req); + hci_req_add_le_scan_disable(req, false); return 0; } @@ -2645,7 +2817,12 @@ static int le_scan_restart(struct hci_request *req, unsigned long opt) if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) return 0; - hci_req_add_le_scan_disable(req); + if (hdev->scanning_paused) { + bt_dev_dbg(hdev, "Scanning is paused for suspend"); + return 0; + } + + hci_req_add_le_scan_disable(req, false); if (use_ext_scan(hdev)) { struct hci_cp_le_set_ext_scan_enable ext_enable_cp; @@ -2725,6 +2902,8 @@ static int active_scan(struct hci_request *req, unsigned long opt) u8 own_addr_type; /* White list is not used for discovery */ u8 filter_policy = 0x00; + /* Discovery doesn't require controller address resolution */ + bool addr_resolv = false; int err; BT_DBG("%s", hdev->name); @@ -2734,7 +2913,7 @@ static int active_scan(struct hci_request *req, unsigned long opt) * discovery scanning parameters. */ if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) - hci_req_add_le_scan_disable(req); + hci_req_add_le_scan_disable(req, false); /* All active scans will be done with either a resolvable private * address (when privacy feature has been enabled) or non-resolvable @@ -2745,8 +2924,9 @@ static int active_scan(struct hci_request *req, unsigned long opt) if (err < 0) own_addr_type = ADDR_LE_DEV_PUBLIC; - hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, DISCOV_LE_SCAN_WIN, - own_addr_type, filter_policy); + hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, + hdev->le_scan_window_discovery, own_addr_type, + filter_policy, addr_resolv); return 0; } @@ -2793,18 +2973,18 @@ static void start_discovery(struct hci_dev *hdev, u8 *status) * to do BR/EDR inquiry. */ hci_req_sync(hdev, interleaved_discov, - DISCOV_LE_SCAN_INT * 2, HCI_CMD_TIMEOUT, + hdev->le_scan_int_discovery * 2, HCI_CMD_TIMEOUT, status); break; } timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout); - hci_req_sync(hdev, active_scan, DISCOV_LE_SCAN_INT, + hci_req_sync(hdev, active_scan, hdev->le_scan_int_discovery, HCI_CMD_TIMEOUT, status); break; case DISCOV_TYPE_LE: timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT); - hci_req_sync(hdev, active_scan, DISCOV_LE_SCAN_INT, + hci_req_sync(hdev, active_scan, hdev->le_scan_int_discovery, HCI_CMD_TIMEOUT, status); break; default: @@ -2848,14 +3028,14 @@ bool hci_req_stop_discovery(struct hci_request *req) if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) { cancel_delayed_work(&hdev->le_scan_disable); - hci_req_add_le_scan_disable(req); + hci_req_add_le_scan_disable(req, false); } ret = true; } else { /* Passive scanning */ if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) { - hci_req_add_le_scan_disable(req); + hci_req_add_le_scan_disable(req, false); ret = true; } } diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 0e81614d235e..6a12e84c66c4 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -65,11 +65,12 @@ void __hci_req_write_fast_connectable(struct hci_request *req, bool enable); void __hci_req_update_name(struct hci_request *req); void __hci_req_update_eir(struct hci_request *req); -void hci_req_add_le_scan_disable(struct hci_request *req); +void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn); void hci_req_add_le_passive_scan(struct hci_request *req); void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next); +void hci_req_disable_address_resolution(struct hci_dev *hdev); void hci_req_reenable_advertising(struct hci_dev *hdev); void __hci_req_enable_advertising(struct hci_request *req); void __hci_req_disable_advertising(struct hci_request *req); @@ -86,6 +87,8 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, 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); int __hci_req_enable_ext_advertising(struct hci_request *req, u8 instance); +int __hci_req_disable_ext_adv_instance(struct hci_request *req, u8 instance); +int __hci_req_remove_ext_adv_instance(struct hci_request *req, u8 instance); 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, diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index d5eff27d5b1e..251b9128f530 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -52,7 +52,7 @@ struct hci_pinfo { struct bt_sock bt; struct hci_dev *hdev; struct hci_filter filter; - __u32 cmsg_mask; + __u8 cmsg_mask; unsigned short channel; unsigned long flags; __u32 cookie; @@ -443,8 +443,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) case HCI_DEV_SETUP: if (hdev->manufacturer == 0xffff) return NULL; - - /* fall through */ + fallthrough; case HCI_DEV_UP: skb = bt_skb_alloc(HCI_MON_INDEX_INFO_SIZE, GFP_ATOMIC); @@ -1399,7 +1398,7 @@ done: static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { - __u32 mask = hci_pi(sk)->cmsg_mask; + __u8 mask = hci_pi(sk)->cmsg_mask; if (mask & HCI_CMSG_DIR) { int incoming = bt_cb(skb)->incoming; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index fe913a5c754a..ade83e224567 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -666,8 +666,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) l2cap_seq_list_free(&chan->srej_list); l2cap_seq_list_free(&chan->retrans_list); - - /* fall through */ + fallthrough; case L2CAP_MODE_STREAMING: skb_queue_purge(&chan->tx_q); @@ -872,7 +871,8 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) else return HCI_AT_NO_BONDING; } - /* fall through */ + fallthrough; + default: switch (chan->sec_level) { case BT_SECURITY_HIGH: @@ -2983,8 +2983,7 @@ static void l2cap_tx_state_wait_f(struct l2cap_chan *chan, break; case L2CAP_EV_RECV_REQSEQ_AND_FBIT: l2cap_process_reqseq(chan, control->reqseq); - - /* Fall through */ + fallthrough; case L2CAP_EV_RECV_FBIT: if (control && control->final) { @@ -3311,7 +3310,7 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask) case L2CAP_MODE_ERTM: if (l2cap_mode_supported(mode, remote_feat_mask)) return mode; - /* fall through */ + fallthrough; default: return L2CAP_MODE_BASIC; } @@ -3447,7 +3446,7 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data, size_t data if (__l2cap_efs_supported(chan->conn)) set_bit(FLAG_EFS_ENABLE, &chan->flags); - /* fall through */ + fallthrough; default: chan->mode = l2cap_select_mode(rfc.mode, chan->conn->feat_mask); break; @@ -4539,7 +4538,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, goto done; break; } - /* fall through */ + fallthrough; default: l2cap_chan_set_err(chan, ECONNRESET); @@ -7719,7 +7718,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) conn->mtu = hcon->hdev->le_mtu; break; } - /* fall through */ + fallthrough; default: conn->mtu = hcon->hdev->acl_mtu; break; @@ -7841,7 +7840,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, case L2CAP_MODE_STREAMING: if (!disable_ertm) break; - /* fall through */ + fallthrough; default: err = -EOPNOTSUPP; goto done; @@ -7893,11 +7892,13 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, else hcon = hci_connect_le_scan(hdev, dst, dst_type, chan->sec_level, - HCI_LE_CONN_TIMEOUT); + HCI_LE_CONN_TIMEOUT, + CONN_REASON_L2CAP_CHAN); } else { u8 auth_type = l2cap_get_auth_type(chan); - hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type); + hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type, + CONN_REASON_L2CAP_CHAN); } if (IS_ERR(hcon)) { diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a3d104123f38..e1a3e66b1754 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -284,7 +284,7 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) case L2CAP_MODE_STREAMING: if (!disable_ertm) break; - /* fall through */ + fallthrough; default: err = -EOPNOTSUPP; goto done; @@ -760,7 +760,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, case L2CAP_MODE_STREAMING: if (!disable_ertm) break; - /* fall through */ + fallthrough; default: err = -EINVAL; break; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 9e8a3cccc6ca..5bbe71002fb9 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -36,9 +36,11 @@ #include "hci_request.h" #include "smp.h" #include "mgmt_util.h" +#include "mgmt_config.h" +#include "msft.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 17 +#define MGMT_REVISION 18 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -111,6 +113,15 @@ static const u16 mgmt_commands[] = { MGMT_OP_READ_SECURITY_INFO, MGMT_OP_READ_EXP_FEATURES_INFO, MGMT_OP_SET_EXP_FEATURE, + MGMT_OP_READ_DEF_SYSTEM_CONFIG, + MGMT_OP_SET_DEF_SYSTEM_CONFIG, + MGMT_OP_READ_DEF_RUNTIME_CONFIG, + MGMT_OP_SET_DEF_RUNTIME_CONFIG, + MGMT_OP_GET_DEVICE_FLAGS, + MGMT_OP_SET_DEVICE_FLAGS, + MGMT_OP_READ_ADV_MONITOR_FEATURES, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_OP_REMOVE_ADV_MONITOR, }; static const u16 mgmt_events[] = { @@ -151,6 +162,7 @@ static const u16 mgmt_events[] = { MGMT_EV_EXT_INFO_CHANGED, MGMT_EV_PHY_CONFIGURATION_CHANGED, MGMT_EV_EXP_FEATURE_CHANGED, + MGMT_EV_DEVICE_FLAGS_CHANGED, }; static const u16 mgmt_untrusted_commands[] = { @@ -162,6 +174,8 @@ static const u16 mgmt_untrusted_commands[] = { MGMT_OP_READ_EXT_INFO, MGMT_OP_READ_SECURITY_INFO, MGMT_OP_READ_EXP_FEATURES_INFO, + MGMT_OP_READ_DEF_SYSTEM_CONFIG, + MGMT_OP_READ_DEF_RUNTIME_CONFIG, }; static const u16 mgmt_untrusted_events[] = { @@ -177,6 +191,8 @@ static const u16 mgmt_untrusted_events[] = { MGMT_EV_EXT_INDEX_REMOVED, MGMT_EV_EXT_INFO_CHANGED, MGMT_EV_EXP_FEATURE_CHANGED, + MGMT_EV_ADV_MONITOR_ADDED, + MGMT_EV_ADV_MONITOR_REMOVED, }; #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) @@ -779,10 +795,15 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_le_capable(hdev)) { settings |= MGMT_SETTING_LE; - settings |= MGMT_SETTING_ADVERTISING; settings |= MGMT_SETTING_SECURE_CONN; settings |= MGMT_SETTING_PRIVACY; settings |= MGMT_SETTING_STATIC_ADDRESS; + + /* When the experimental feature for LL Privacy support is + * enabled, then advertising is no longer supported. + */ + if (!hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) + settings |= MGMT_SETTING_ADVERTISING; } if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || @@ -2915,7 +2936,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->addr.type == BDADDR_BREDR) { conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level, - auth_type); + auth_type, CONN_REASON_PAIR_DEVICE); } else { u8 addr_type = le_addr_type(cp->addr.type); struct hci_conn_params *p; @@ -2934,9 +2955,9 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; - conn = hci_connect_le_scan(hdev, &cp->addr.bdaddr, - addr_type, sec_level, - HCI_LE_CONN_TIMEOUT); + conn = hci_connect_le_scan(hdev, &cp->addr.bdaddr, addr_type, + sec_level, HCI_LE_CONN_TIMEOUT, + CONN_REASON_PAIR_DEVICE); } if (IS_ERR(conn)) { @@ -3037,6 +3058,20 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, 0, addr, sizeof(*addr)); + + /* Since user doesn't want to proceed with the connection, abort any + * ongoing pairing and then terminate the link if it was created + * because of the pair device action. + */ + if (addr->type == BDADDR_BREDR) + hci_remove_link_key(hdev, &addr->bdaddr); + else + smp_cancel_and_remove_pairing(hdev, &addr->bdaddr, + le_addr_type(addr->type)); + + if (conn->conn_reason == CONN_REASON_PAIR_DEVICE) + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + unlock: hci_dev_unlock(hdev); return err; @@ -3723,12 +3758,25 @@ static const u8 debug_uuid[16] = { }; #endif +/* 671b10b5-42c0-4696-9227-eb28d1b049d6 */ +static const u8 simult_central_periph_uuid[16] = { + 0xd6, 0x49, 0xb0, 0xd1, 0x28, 0xeb, 0x27, 0x92, + 0x96, 0x46, 0xc0, 0x42, 0xb5, 0x10, 0x1b, 0x67, +}; + +/* 15c0a148-c273-11ea-b3de-0242ac130004 */ +static const u8 rpa_resolution_uuid[16] = { + 0x04, 0x00, 0x13, 0xac, 0x42, 0x02, 0xde, 0xb3, + 0xea, 0x11, 0x73, 0xc2, 0x48, 0xa1, 0xc0, 0x15, +}; + static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { - char buf[42]; + char buf[62]; /* Enough space for 3 features */ struct mgmt_rp_read_exp_features_info *rp = (void *)buf; u16 idx = 0; + u32 flags; bt_dev_dbg(hdev, "sock %p", sk); @@ -3736,7 +3784,7 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, #ifdef CONFIG_BT_FEATURE_DEBUG if (!hdev) { - u32 flags = bt_dbg_get() ? BIT(0) : 0; + flags = bt_dbg_get() ? BIT(0) : 0; memcpy(rp->features[idx].uuid, debug_uuid, 16); rp->features[idx].flags = cpu_to_le32(flags); @@ -3744,6 +3792,31 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, } #endif + if (hdev) { + if (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && + (hdev->le_states[4] & 0x08) && /* Central */ + (hdev->le_states[4] & 0x40) && /* Peripheral */ + (hdev->le_states[3] & 0x10)) /* Simultaneous */ + flags = BIT(0); + else + flags = 0; + + memcpy(rp->features[idx].uuid, simult_central_periph_uuid, 16); + rp->features[idx].flags = cpu_to_le32(flags); + idx++; + } + + if (hdev && use_ll_privacy(hdev)) { + if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) + flags = BIT(0) | BIT(1); + else + flags = BIT(1); + + memcpy(rp->features[idx].uuid, rpa_resolution_uuid, 16); + rp->features[idx].flags = cpu_to_le32(flags); + idx++; + } + rp->feature_count = cpu_to_le16(idx); /* After reading the experimental features information, enable @@ -3756,6 +3829,21 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, 0, rp, sizeof(*rp) + (20 * idx)); } +static int exp_ll_privacy_feature_changed(bool enabled, struct hci_dev *hdev, + struct sock *skip) +{ + struct mgmt_ev_exp_feature_changed ev; + + memset(&ev, 0, sizeof(ev)); + memcpy(ev.uuid, rpa_resolution_uuid, 16); + ev.flags = cpu_to_le32((enabled ? BIT(0) : 0) | BIT(1)); + + return mgmt_limited_event(MGMT_EV_EXP_FEATURE_CHANGED, hdev, + &ev, sizeof(ev), + HCI_MGMT_EXP_FEATURE_EVENTS, skip); + +} + #ifdef CONFIG_BT_FEATURE_DEBUG static int exp_debug_feature_changed(bool enabled, struct sock *skip) { @@ -3794,6 +3882,16 @@ static int set_exp_feature(struct sock *sk, struct hci_dev *hdev, } #endif + if (hdev && use_ll_privacy(hdev) && !hdev_is_powered(hdev)) { + bool changed = hci_dev_test_flag(hdev, + HCI_ENABLE_LL_PRIVACY); + + hci_dev_clear_flag(hdev, HCI_ENABLE_LL_PRIVACY); + + if (changed) + exp_ll_privacy_feature_changed(false, hdev, sk); + } + hci_sock_set_flag(sk, HCI_MGMT_EXP_FEATURE_EVENTS); return mgmt_cmd_complete(sk, hdev ? hdev->id : MGMT_INDEX_NONE, @@ -3844,11 +3942,401 @@ static int set_exp_feature(struct sock *sk, struct hci_dev *hdev, } #endif + if (!memcmp(cp->uuid, rpa_resolution_uuid, 16)) { + bool val, changed; + int err; + u32 flags; + + /* Command requires to use the controller index */ + if (!hdev) + return mgmt_cmd_status(sk, MGMT_INDEX_NONE, + MGMT_OP_SET_EXP_FEATURE, + MGMT_STATUS_INVALID_INDEX); + + /* Changes can only be made when controller is powered down */ + if (hdev_is_powered(hdev)) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_EXP_FEATURE, + MGMT_STATUS_NOT_POWERED); + + /* Parameters are limited to a single octet */ + if (data_len != MGMT_SET_EXP_FEATURE_SIZE + 1) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_EXP_FEATURE, + MGMT_STATUS_INVALID_PARAMS); + + /* Only boolean on/off is supported */ + if (cp->param[0] != 0x00 && cp->param[0] != 0x01) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_EXP_FEATURE, + MGMT_STATUS_INVALID_PARAMS); + + val = !!cp->param[0]; + + if (val) { + changed = !hci_dev_test_flag(hdev, + HCI_ENABLE_LL_PRIVACY); + hci_dev_set_flag(hdev, HCI_ENABLE_LL_PRIVACY); + hci_dev_clear_flag(hdev, HCI_ADVERTISING); + + /* Enable LL privacy + supported settings changed */ + flags = BIT(0) | BIT(1); + } else { + changed = hci_dev_test_flag(hdev, + HCI_ENABLE_LL_PRIVACY); + hci_dev_clear_flag(hdev, HCI_ENABLE_LL_PRIVACY); + + /* Disable LL privacy + supported settings changed */ + flags = BIT(1); + } + + memcpy(rp.uuid, rpa_resolution_uuid, 16); + rp.flags = cpu_to_le32(flags); + + hci_sock_set_flag(sk, HCI_MGMT_EXP_FEATURE_EVENTS); + + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_SET_EXP_FEATURE, 0, + &rp, sizeof(rp)); + + if (changed) + exp_ll_privacy_feature_changed(val, hdev, sk); + + return err; + } + return mgmt_cmd_status(sk, hdev ? hdev->id : MGMT_INDEX_NONE, MGMT_OP_SET_EXP_FEATURE, MGMT_STATUS_NOT_SUPPORTED); } +#define SUPPORTED_DEVICE_FLAGS() ((1U << HCI_CONN_FLAG_MAX) - 1) + +static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len) +{ + struct mgmt_cp_get_device_flags *cp = data; + struct mgmt_rp_get_device_flags rp; + struct bdaddr_list_with_flags *br_params; + struct hci_conn_params *params; + u32 supported_flags = SUPPORTED_DEVICE_FLAGS(); + u32 current_flags = 0; + u8 status = MGMT_STATUS_INVALID_PARAMS; + + bt_dev_dbg(hdev, "Get device flags %pMR (type 0x%x)\n", + &cp->addr.bdaddr, cp->addr.type); + + hci_dev_lock(hdev); + + if (cp->addr.type == BDADDR_BREDR) { + br_params = hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + &cp->addr.bdaddr, + cp->addr.type); + if (!br_params) + goto done; + + current_flags = br_params->current_flags; + } else { + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + + if (!params) + goto done; + + current_flags = params->current_flags; + } + + bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr); + rp.addr.type = cp->addr.type; + rp.supported_flags = cpu_to_le32(supported_flags); + rp.current_flags = cpu_to_le32(current_flags); + + status = MGMT_STATUS_SUCCESS; + +done: + hci_dev_unlock(hdev); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_DEVICE_FLAGS, status, + &rp, sizeof(rp)); +} + +static void device_flags_changed(struct sock *sk, struct hci_dev *hdev, + bdaddr_t *bdaddr, u8 bdaddr_type, + u32 supported_flags, u32 current_flags) +{ + struct mgmt_ev_device_flags_changed ev; + + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = bdaddr_type; + ev.supported_flags = cpu_to_le32(supported_flags); + ev.current_flags = cpu_to_le32(current_flags); + + mgmt_event(MGMT_EV_DEVICE_FLAGS_CHANGED, hdev, &ev, sizeof(ev), sk); +} + +static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, + u16 len) +{ + struct mgmt_cp_set_device_flags *cp = data; + struct bdaddr_list_with_flags *br_params; + struct hci_conn_params *params; + u8 status = MGMT_STATUS_INVALID_PARAMS; + u32 supported_flags = SUPPORTED_DEVICE_FLAGS(); + u32 current_flags = __le32_to_cpu(cp->current_flags); + + bt_dev_dbg(hdev, "Set device flags %pMR (type 0x%x) = 0x%x", + &cp->addr.bdaddr, cp->addr.type, + __le32_to_cpu(current_flags)); + + if ((supported_flags | current_flags) != supported_flags) { + bt_dev_warn(hdev, "Bad flag given (0x%x) vs supported (0x%0x)", + current_flags, supported_flags); + goto done; + } + + hci_dev_lock(hdev); + + if (cp->addr.type == BDADDR_BREDR) { + br_params = hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + &cp->addr.bdaddr, + cp->addr.type); + + if (br_params) { + br_params->current_flags = current_flags; + status = MGMT_STATUS_SUCCESS; + } else { + bt_dev_warn(hdev, "No such BR/EDR device %pMR (0x%x)", + &cp->addr.bdaddr, cp->addr.type); + } + } else { + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + if (params) { + params->current_flags = current_flags; + status = MGMT_STATUS_SUCCESS; + } else { + bt_dev_warn(hdev, "No such LE device %pMR (0x%x)", + &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + } + } + +done: + hci_dev_unlock(hdev); + + if (status == MGMT_STATUS_SUCCESS) + device_flags_changed(sk, hdev, &cp->addr.bdaddr, cp->addr.type, + supported_flags, current_flags); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEVICE_FLAGS, status, + &cp->addr, sizeof(cp->addr)); +} + +static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev, + u16 handle) +{ + struct mgmt_ev_adv_monitor_added ev; + + ev.monitor_handle = cpu_to_le16(handle); + + mgmt_event(MGMT_EV_ADV_MONITOR_ADDED, hdev, &ev, sizeof(ev), sk); +} + +static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev, + u16 handle) +{ + struct mgmt_ev_adv_monitor_added ev; + + ev.monitor_handle = cpu_to_le16(handle); + + mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk); +} + +static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct adv_monitor *monitor = NULL; + struct mgmt_rp_read_adv_monitor_features *rp = NULL; + int handle; + size_t rp_size = 0; + __u32 supported = 0; + __u16 num_handles = 0; + __u16 handles[HCI_MAX_ADV_MONITOR_NUM_HANDLES]; + + BT_DBG("request for %s", hdev->name); + + hci_dev_lock(hdev); + + if (msft_get_features(hdev) & MSFT_FEATURE_MASK_LE_ADV_MONITOR) + supported |= MGMT_ADV_MONITOR_FEATURE_MASK_OR_PATTERNS; + + idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) { + handles[num_handles++] = monitor->handle; + } + + hci_dev_unlock(hdev); + + rp_size = sizeof(*rp) + (num_handles * sizeof(u16)); + rp = kmalloc(rp_size, GFP_KERNEL); + if (!rp) + return -ENOMEM; + + /* Once controller-based monitoring is in place, the enabled_features + * should reflect the use. + */ + rp->supported_features = cpu_to_le32(supported); + rp->enabled_features = 0; + rp->max_num_handles = cpu_to_le16(HCI_MAX_ADV_MONITOR_NUM_HANDLES); + rp->max_num_patterns = HCI_MAX_ADV_MONITOR_NUM_PATTERNS; + rp->num_handles = cpu_to_le16(num_handles); + if (num_handles) + memcpy(&rp->handles, &handles, (num_handles * sizeof(u16))); + + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_READ_ADV_MONITOR_FEATURES, + MGMT_STATUS_SUCCESS, rp, rp_size); +} + +static int add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_add_adv_patterns_monitor *cp = data; + struct mgmt_rp_add_adv_patterns_monitor rp; + struct adv_monitor *m = NULL; + struct adv_pattern *p = NULL; + unsigned int mp_cnt = 0, prev_adv_monitors_cnt; + __u8 cp_ofst = 0, cp_len = 0; + int err, i; + + BT_DBG("request for %s", hdev->name); + + if (len <= sizeof(*cp) || cp->pattern_count == 0) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_STATUS_INVALID_PARAMS); + goto failed; + } + + m = kmalloc(sizeof(*m), GFP_KERNEL); + if (!m) { + err = -ENOMEM; + goto failed; + } + + INIT_LIST_HEAD(&m->patterns); + m->active = false; + + for (i = 0; i < cp->pattern_count; i++) { + if (++mp_cnt > HCI_MAX_ADV_MONITOR_NUM_PATTERNS) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_STATUS_INVALID_PARAMS); + goto failed; + } + + cp_ofst = cp->patterns[i].offset; + cp_len = cp->patterns[i].length; + if (cp_ofst >= HCI_MAX_AD_LENGTH || + cp_len > HCI_MAX_AD_LENGTH || + (cp_ofst + cp_len) > HCI_MAX_AD_LENGTH) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_STATUS_INVALID_PARAMS); + goto failed; + } + + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto failed; + } + + p->ad_type = cp->patterns[i].ad_type; + p->offset = cp->patterns[i].offset; + p->length = cp->patterns[i].length; + memcpy(p->value, cp->patterns[i].value, p->length); + + INIT_LIST_HEAD(&p->list); + list_add(&p->list, &m->patterns); + } + + if (mp_cnt != cp->pattern_count) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_STATUS_INVALID_PARAMS); + goto failed; + } + + hci_dev_lock(hdev); + + prev_adv_monitors_cnt = hdev->adv_monitors_cnt; + + err = hci_add_adv_monitor(hdev, m); + if (err) { + if (err == -ENOSPC) { + mgmt_cmd_status(sk, hdev->id, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_STATUS_NO_RESOURCES); + } + goto unlock; + } + + if (hdev->adv_monitors_cnt > prev_adv_monitors_cnt) + mgmt_adv_monitor_added(sk, hdev, m->handle); + + hci_dev_unlock(hdev); + + rp.monitor_handle = cpu_to_le16(m->handle); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_ADV_PATTERNS_MONITOR, + MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + +unlock: + hci_dev_unlock(hdev); + +failed: + hci_free_adv_monitor(m); + return err; +} + +static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_remove_adv_monitor *cp = data; + struct mgmt_rp_remove_adv_monitor rp; + unsigned int prev_adv_monitors_cnt; + u16 handle; + int err; + + BT_DBG("request for %s", hdev->name); + + hci_dev_lock(hdev); + + handle = __le16_to_cpu(cp->monitor_handle); + prev_adv_monitors_cnt = hdev->adv_monitors_cnt; + + err = hci_remove_adv_monitor(hdev, handle); + if (err == -ENOENT) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADV_MONITOR, + MGMT_STATUS_INVALID_INDEX); + goto unlock; + } + + if (hdev->adv_monitors_cnt < prev_adv_monitors_cnt) + mgmt_adv_monitor_removed(sk, hdev, handle); + + hci_dev_unlock(hdev); + + rp.monitor_handle = cp->monitor_handle; + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_ADV_MONITOR, + MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + +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) { @@ -4147,7 +4635,7 @@ static bool discovery_type_is_valid(struct hci_dev *hdev, uint8_t type, *mgmt_status = mgmt_le_support(hdev); if (*mgmt_status) return false; - /* Intentional fall-through */ + fallthrough; case DISCOV_TYPE_BREDR: *mgmt_status = mgmt_bredr_support(hdev); if (*mgmt_status) @@ -4662,6 +5150,13 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, status); + /* Enabling the experimental LL Privay support disables support for + * advertising. + */ + if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + MGMT_STATUS_NOT_SUPPORTED); + if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); @@ -4848,7 +5343,7 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); - hci_req_add_le_scan_disable(&req); + hci_req_add_le_scan_disable(&req, false); hci_req_add_le_passive_scan(&req); hci_req_run(&req, NULL); @@ -5523,7 +6018,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, case MGMT_LTK_P256_DEBUG: authenticated = 0x00; type = SMP_LTK_P256_DEBUG; - /* fall through */ + fallthrough; default: continue; } @@ -5966,7 +6461,9 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, { struct mgmt_cp_add_device *cp = data; u8 auto_conn, addr_type; + struct hci_conn_params *params; int err; + u32 current_flags = 0; bt_dev_dbg(hdev, "sock %p", sk); @@ -5993,8 +6490,9 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_bdaddr_list_add(&hdev->whitelist, &cp->addr.bdaddr, - cp->addr.type); + err = hci_bdaddr_list_add_with_flags(&hdev->whitelist, + &cp->addr.bdaddr, + cp->addr.type, 0); if (err) goto unlock; @@ -6033,12 +6531,19 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, MGMT_STATUS_FAILED, &cp->addr, sizeof(cp->addr)); goto unlock; + } else { + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, + addr_type); + if (params) + current_flags = params->current_flags; } hci_update_background_scan(hdev); added: device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); + device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, + SUPPORTED_DEVICE_FLAGS(), current_flags); err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, MGMT_STATUS_SUCCESS, &cp->addr, @@ -6724,6 +7229,13 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_ADV_FEATURES, MGMT_STATUS_REJECTED); + /* Enabling the experimental LL Privay support disables support for + * advertising. + */ + if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + MGMT_STATUS_NOT_SUPPORTED); + hci_dev_lock(hdev); rp_len = sizeof(*rp) + hdev->adv_instance_cnt; @@ -6927,6 +7439,13 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, status); + /* Enabling the experimental LL Privay support disables support for + * advertising. + */ + if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + MGMT_STATUS_NOT_SUPPORTED); + if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); @@ -7091,6 +7610,13 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, bt_dev_dbg(hdev, "sock %p", sk); + /* Enabling the experimental LL Privay support disables support for + * advertising. + */ + if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + MGMT_STATUS_NOT_SUPPORTED); + hci_dev_lock(hdev); if (cp->instance && !hci_find_adv_instance(hdev, cp->instance)) { @@ -7116,6 +7642,12 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); + /* If we use extended advertising, instance is disabled and removed */ + if (ext_adv_capable(hdev)) { + __hci_req_disable_ext_adv_instance(&req, cp->instance); + __hci_req_remove_ext_adv_instance(&req, cp->instance); + } + hci_req_clear_adv_instance(hdev, sk, &req, cp->instance, true); if (list_empty(&hdev->adv_instances)) @@ -7297,6 +7829,20 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { set_exp_feature, MGMT_SET_EXP_FEATURE_SIZE, HCI_MGMT_VAR_LEN | HCI_MGMT_HDEV_OPTIONAL }, + { read_def_system_config, MGMT_READ_DEF_SYSTEM_CONFIG_SIZE, + HCI_MGMT_UNTRUSTED }, + { set_def_system_config, MGMT_SET_DEF_SYSTEM_CONFIG_SIZE, + HCI_MGMT_VAR_LEN }, + { read_def_runtime_config, MGMT_READ_DEF_RUNTIME_CONFIG_SIZE, + HCI_MGMT_UNTRUSTED }, + { set_def_runtime_config, MGMT_SET_DEF_RUNTIME_CONFIG_SIZE, + HCI_MGMT_VAR_LEN }, + { get_device_flags, MGMT_GET_DEVICE_FLAGS_SIZE }, + { set_device_flags, MGMT_SET_DEVICE_FLAGS_SIZE }, + { read_adv_mon_features, MGMT_READ_ADV_MONITOR_FEATURES_SIZE }, + { add_adv_patterns_monitor,MGMT_ADD_ADV_PATTERNS_MONITOR_SIZE, + HCI_MGMT_VAR_LEN }, + { remove_adv_monitor, MGMT_REMOVE_ADV_MONITOR_SIZE }, }; void mgmt_index_added(struct hci_dev *hdev) @@ -8216,8 +8762,11 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, if (!hci_discovery_active(hdev)) { if (link_type == ACL_LINK) return; - if (link_type == LE_LINK && list_empty(&hdev->pend_le_reports)) + if (link_type == LE_LINK && + list_empty(&hdev->pend_le_reports) && + !hci_is_adv_monitoring(hdev)) { return; + } } if (hdev->discovery.result_filtering) { diff --git a/net/bluetooth/mgmt_config.c b/net/bluetooth/mgmt_config.c new file mode 100644 index 000000000000..b30b571f8caf --- /dev/null +++ b/net/bluetooth/mgmt_config.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright (C) 2020 Google Corporation + */ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> +#include <net/bluetooth/mgmt.h> + +#include "mgmt_util.h" +#include "mgmt_config.h" + +#define HDEV_PARAM_U16(_param_code_, _param_name_) \ +{ \ + { cpu_to_le16(_param_code_), sizeof(__u16) }, \ + { cpu_to_le16(hdev->_param_name_) } \ +} + +#define HDEV_PARAM_U16_JIFFIES_TO_MSECS(_param_code_, _param_name_) \ +{ \ + { cpu_to_le16(_param_code_), sizeof(__u16) }, \ + { cpu_to_le16(jiffies_to_msecs(hdev->_param_name_)) } \ +} + +int read_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len) +{ + struct { + struct mgmt_tlv entry; + union { + /* This is a simplification for now since all values + * are 16 bits. In the future, this code may need + * refactoring to account for variable length values + * and properly calculate the required buffer size. + */ + __le16 value; + }; + } __packed params[] = { + /* Please see mgmt-api.txt for documentation of these values */ + HDEV_PARAM_U16(0x0000, def_page_scan_type), + HDEV_PARAM_U16(0x0001, def_page_scan_int), + HDEV_PARAM_U16(0x0002, def_page_scan_window), + HDEV_PARAM_U16(0x0003, def_inq_scan_type), + HDEV_PARAM_U16(0x0004, def_inq_scan_int), + HDEV_PARAM_U16(0x0005, def_inq_scan_window), + HDEV_PARAM_U16(0x0006, def_br_lsto), + HDEV_PARAM_U16(0x0007, def_page_timeout), + HDEV_PARAM_U16(0x0008, sniff_min_interval), + HDEV_PARAM_U16(0x0009, sniff_max_interval), + HDEV_PARAM_U16(0x000a, le_adv_min_interval), + HDEV_PARAM_U16(0x000b, le_adv_max_interval), + HDEV_PARAM_U16(0x000c, def_multi_adv_rotation_duration), + HDEV_PARAM_U16(0x000d, le_scan_interval), + HDEV_PARAM_U16(0x000e, le_scan_window), + HDEV_PARAM_U16(0x000f, le_scan_int_suspend), + HDEV_PARAM_U16(0x0010, le_scan_window_suspend), + HDEV_PARAM_U16(0x0011, le_scan_int_discovery), + HDEV_PARAM_U16(0x0012, le_scan_window_discovery), + HDEV_PARAM_U16(0x0013, le_scan_int_adv_monitor), + HDEV_PARAM_U16(0x0014, le_scan_window_adv_monitor), + HDEV_PARAM_U16(0x0015, le_scan_int_connect), + HDEV_PARAM_U16(0x0016, le_scan_window_connect), + HDEV_PARAM_U16(0x0017, le_conn_min_interval), + HDEV_PARAM_U16(0x0018, le_conn_max_interval), + HDEV_PARAM_U16(0x0019, le_conn_latency), + HDEV_PARAM_U16(0x001a, le_supv_timeout), + HDEV_PARAM_U16_JIFFIES_TO_MSECS(0x001b, + def_le_autoconnect_timeout), + }; + struct mgmt_rp_read_def_system_config *rp = (void *)params; + + bt_dev_dbg(hdev, "sock %p", sk); + + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_READ_DEF_SYSTEM_CONFIG, + 0, rp, sizeof(params)); +} + +#define TO_TLV(x) ((struct mgmt_tlv *)(x)) +#define TLV_GET_LE16(tlv) le16_to_cpu(*((__le16 *)(TO_TLV(tlv)->value))) + +int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len) +{ + u16 buffer_left = data_len; + u8 *buffer = data; + + if (buffer_left < sizeof(struct mgmt_tlv)) { + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_DEF_SYSTEM_CONFIG, + MGMT_STATUS_INVALID_PARAMS); + } + + /* First pass to validate the tlv */ + while (buffer_left >= sizeof(struct mgmt_tlv)) { + const u8 len = TO_TLV(buffer)->length; + const u16 exp_len = sizeof(struct mgmt_tlv) + + len; + const u16 type = le16_to_cpu(TO_TLV(buffer)->type); + + if (buffer_left < exp_len) { + bt_dev_warn(hdev, "invalid len left %d, exp >= %d", + buffer_left, exp_len); + + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_DEF_SYSTEM_CONFIG, + MGMT_STATUS_INVALID_PARAMS); + } + + /* Please see mgmt-api.txt for documentation of these values */ + switch (type) { + case 0x0000: + case 0x0001: + case 0x0002: + case 0x0003: + case 0x0004: + case 0x0005: + case 0x0006: + case 0x0007: + case 0x0008: + case 0x0009: + case 0x000a: + case 0x000b: + case 0x000c: + case 0x000d: + case 0x000e: + case 0x000f: + case 0x0010: + case 0x0011: + case 0x0012: + case 0x0013: + case 0x0014: + case 0x0015: + case 0x0016: + case 0x0017: + case 0x0018: + case 0x0019: + case 0x001a: + case 0x001b: + if (len != sizeof(u16)) { + bt_dev_warn(hdev, "invalid length %d, exp %zu for type %d", + len, sizeof(u16), type); + + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_DEF_SYSTEM_CONFIG, + MGMT_STATUS_INVALID_PARAMS); + } + break; + default: + bt_dev_warn(hdev, "unsupported parameter %u", type); + break; + } + + buffer_left -= exp_len; + buffer += exp_len; + } + + buffer_left = data_len; + buffer = data; + while (buffer_left >= sizeof(struct mgmt_tlv)) { + const u8 len = TO_TLV(buffer)->length; + const u16 exp_len = sizeof(struct mgmt_tlv) + + len; + const u16 type = le16_to_cpu(TO_TLV(buffer)->type); + + switch (type) { + case 0x0000: + hdev->def_page_scan_type = TLV_GET_LE16(buffer); + break; + case 0x0001: + hdev->def_page_scan_int = TLV_GET_LE16(buffer); + break; + case 0x0002: + hdev->def_page_scan_window = TLV_GET_LE16(buffer); + break; + case 0x0003: + hdev->def_inq_scan_type = TLV_GET_LE16(buffer); + break; + case 0x0004: + hdev->def_inq_scan_int = TLV_GET_LE16(buffer); + break; + case 0x0005: + hdev->def_inq_scan_window = TLV_GET_LE16(buffer); + break; + case 0x0006: + hdev->def_br_lsto = TLV_GET_LE16(buffer); + break; + case 0x0007: + hdev->def_page_timeout = TLV_GET_LE16(buffer); + break; + case 0x0008: + hdev->sniff_min_interval = TLV_GET_LE16(buffer); + break; + case 0x0009: + hdev->sniff_max_interval = TLV_GET_LE16(buffer); + break; + case 0x000a: + hdev->le_adv_min_interval = TLV_GET_LE16(buffer); + break; + case 0x000b: + hdev->le_adv_max_interval = TLV_GET_LE16(buffer); + break; + case 0x000c: + hdev->def_multi_adv_rotation_duration = + TLV_GET_LE16(buffer); + break; + case 0x000d: + hdev->le_scan_interval = TLV_GET_LE16(buffer); + break; + case 0x000e: + hdev->le_scan_window = TLV_GET_LE16(buffer); + break; + case 0x000f: + hdev->le_scan_int_suspend = TLV_GET_LE16(buffer); + break; + case 0x0010: + hdev->le_scan_window_suspend = TLV_GET_LE16(buffer); + break; + case 0x0011: + hdev->le_scan_int_discovery = TLV_GET_LE16(buffer); + break; + case 0x00012: + hdev->le_scan_window_discovery = TLV_GET_LE16(buffer); + break; + case 0x00013: + hdev->le_scan_int_adv_monitor = TLV_GET_LE16(buffer); + break; + case 0x00014: + hdev->le_scan_window_adv_monitor = TLV_GET_LE16(buffer); + break; + case 0x00015: + hdev->le_scan_int_connect = TLV_GET_LE16(buffer); + break; + case 0x00016: + hdev->le_scan_window_connect = TLV_GET_LE16(buffer); + break; + case 0x00017: + hdev->le_conn_min_interval = TLV_GET_LE16(buffer); + break; + case 0x00018: + hdev->le_conn_max_interval = TLV_GET_LE16(buffer); + break; + case 0x00019: + hdev->le_conn_latency = TLV_GET_LE16(buffer); + break; + case 0x0001a: + hdev->le_supv_timeout = TLV_GET_LE16(buffer); + break; + case 0x0001b: + hdev->def_le_autoconnect_timeout = + msecs_to_jiffies(TLV_GET_LE16(buffer)); + break; + default: + bt_dev_warn(hdev, "unsupported parameter %u", type); + break; + } + + buffer_left -= exp_len; + buffer += exp_len; + } + + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_SET_DEF_SYSTEM_CONFIG, 0, NULL, 0); +} + +int read_def_runtime_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len) +{ + bt_dev_dbg(hdev, "sock %p", sk); + + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_READ_DEF_RUNTIME_CONFIG, 0, NULL, 0); +} + +int set_def_runtime_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len) +{ + bt_dev_dbg(hdev, "sock %p", sk); + + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEF_SYSTEM_CONFIG, + MGMT_STATUS_INVALID_PARAMS); +} diff --git a/net/bluetooth/mgmt_config.h b/net/bluetooth/mgmt_config.h new file mode 100644 index 000000000000..a4965f107891 --- /dev/null +++ b/net/bluetooth/mgmt_config.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright (C) 2020 Google Corporation + */ + +int read_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len); + +int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len); + +int read_def_runtime_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len); + +int set_def_runtime_config(struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len); diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index d6c4e6b5ae77..8579bfeb2836 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -139,3 +139,10 @@ void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb) bt_dev_dbg(hdev, "MSFT vendor event %u", event); } + +__u64 msft_get_features(struct hci_dev *hdev) +{ + struct msft_data *msft = hdev->msft_data; + + return msft ? msft->features : 0; +} diff --git a/net/bluetooth/msft.h b/net/bluetooth/msft.h index 5aa9130e1f8a..e9c478e890b8 100644 --- a/net/bluetooth/msft.h +++ b/net/bluetooth/msft.h @@ -3,16 +3,25 @@ * Copyright (C) 2020 Google Corporation */ +#define MSFT_FEATURE_MASK_BREDR_RSSI_MONITOR BIT(0) +#define MSFT_FEATURE_MASK_LE_CONN_RSSI_MONITOR BIT(1) +#define MSFT_FEATURE_MASK_LE_ADV_RSSI_MONITOR BIT(2) +#define MSFT_FEATURE_MASK_LE_ADV_MONITOR BIT(3) +#define MSFT_FEATURE_MASK_CURVE_VALIDITY BIT(4) +#define MSFT_FEATURE_MASK_CONCURRENT_ADV_MONITOR BIT(5) + #if IS_ENABLED(CONFIG_BT_MSFTEXT) void msft_do_open(struct hci_dev *hdev); void msft_do_close(struct hci_dev *hdev); void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb); +__u64 msft_get_features(struct hci_dev *hdev); #else static inline void msft_do_open(struct hci_dev *hdev) {} static inline void msft_do_close(struct hci_dev *hdev) {} static inline void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb) {} +static inline __u64 msft_get_features(struct hci_dev *hdev) { return 0; } #endif diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 2e20af317cea..f2bacb464ccf 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -479,7 +479,7 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) /* if closing a dlc in a session that hasn't been started, * just close and unlink the dlc */ - /* fall through */ + fallthrough; default: rfcomm_dlc_clear_timer(d); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index dba4ea0e1b0d..ae6f80730561 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -218,7 +218,7 @@ static void __rfcomm_sock_close(struct sock *sk) case BT_CONFIG: case BT_CONNECTED: rfcomm_dlc_close(d, 0); - /* fall through */ + fallthrough; default: sock_set_flag(sk, SOCK_ZAPPED); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 37260baf7150..dcf7f96ff417 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -66,6 +66,7 @@ struct sco_pinfo { bdaddr_t dst; __u32 flags; __u16 setting; + __u8 cmsg_mask; struct sco_conn *conn; }; @@ -449,6 +450,15 @@ static void sco_sock_close(struct sock *sk) sco_sock_kill(sk); } +static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg, + struct sock *sk) +{ + if (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS) + put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS, + sizeof(bt_cb(skb)->sco.pkt_status), + &bt_cb(skb)->sco.pkt_status); +} + static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); @@ -457,6 +467,8 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); + } else { + bt_sk(sk)->skb_put_cmsg = sco_skb_put_cmsg; } } @@ -846,6 +858,18 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sco_pi(sk)->setting = voice.setting; break; + case BT_PKT_STATUS: + if (copy_from_sockptr(&opt, optval, sizeof(u32))) { + err = -EFAULT; + break; + } + + if (opt) + sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; + else + sco_pi(sk)->cmsg_mask &= SCO_CMSG_PKT_STATUS; + break; + default: err = -ENOPROTOOPT; break; @@ -923,6 +947,7 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, int len, err = 0; struct bt_voice voice; u32 phys; + int pkt_status; BT_DBG("sk %p", sk); @@ -969,6 +994,13 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, err = -EFAULT; break; + case BT_PKT_STATUS: + pkt_status = (sco_pi(sk)->cmsg_mask & SCO_CMSG_PKT_STATUS); + + if (put_user(pkt_status, (int __user *)optval)) + err = -EFAULT; + break; + default: err = -ENOPROTOOPT; break; diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c index 03e3c89c3046..f71c6fa65fb3 100644 --- a/net/bluetooth/selftest.c +++ b/net/bluetooth/selftest.c @@ -205,7 +205,7 @@ static int __init test_ecdh(void) calltime = ktime_get(); - tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + tfm = crypto_alloc_kpp("ecdh", 0, 0); if (IS_ERR(tfm)) { BT_ERR("Unable to create ECDH crypto context"); err = PTR_ERR(tfm); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index c2c5ab05fa7e..433227f96c73 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1387,7 +1387,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) goto zfree_smp; } - smp->tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + smp->tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0); if (IS_ERR(smp->tfm_ecdh)) { BT_ERR("Unable to create ECDH crypto context"); goto free_shash; @@ -1654,7 +1654,7 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) memset(smp->tk, 0, sizeof(smp->tk)); BT_DBG("PassKey: %d", value); put_unaligned_le32(value, smp->tk); - /* Fall Through */ + fallthrough; case MGMT_OP_USER_CONFIRM_REPLY: set_bit(SMP_FLAG_TK_VALID, &smp->flags); break; @@ -3282,7 +3282,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_cmac); } - tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0); if (IS_ERR(tfm_ecdh)) { BT_ERR("Unable to create ECDH crypto context"); crypto_free_shash(tfm_cmac); @@ -3847,7 +3847,7 @@ int __init bt_selftest_smp(void) return PTR_ERR(tfm_cmac); } - tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0); if (IS_ERR(tfm_ecdh)) { BT_ERR("Unable to create ECDH crypto context"); crypto_free_shash(tfm_cmac); diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index f580c3344cb3..51a941b56ec3 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -34,7 +34,7 @@ static void __stop_umh(void) static int bpfilter_send_req(struct mbox_request *req) { struct mbox_reply reply; - loff_t pos; + loff_t pos = 0; ssize_t n; if (!bpfilter_ops.info.tgid) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 8c7b78f8bc23..9a2fb4aa1a10 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -36,6 +36,8 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const unsigned char *dest; u16 vid = 0; + memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); + rcu_read_lock(); nf_ops = rcu_dereference(nf_br_ops); if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index d35173e803d3..fe66932f5abb 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1852,7 +1852,7 @@ static int compat_mtw_from_user(const struct compat_ebt_entry_mwt *mwt, size_kern = match_size; module_put(match->me); break; - case EBT_COMPAT_WATCHER: /* fallthrough */ + case EBT_COMPAT_WATCHER: case EBT_COMPAT_TARGET: wt = xt_request_find_target(NFPROTO_BRIDGE, name, mwt->u.revision); diff --git a/net/compat.c b/net/compat.c index 091875bd6210..93ea07e93ae5 100644 --- a/net/compat.c +++ b/net/compat.c @@ -202,7 +202,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, /* Advance. */ kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp); - ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); + ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, cmsg.cmsg_len); } /* diff --git a/net/core/dev.c b/net/core/dev.c index c8b911b10187..7df6c9617321 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3454,10 +3454,9 @@ static netdev_features_t net_mpls_features(struct sk_buff *skb, static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { - int tmp; __be16 type; - type = skb_network_protocol(skb, &tmp); + type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && @@ -8712,6 +8711,31 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down_generic); +/** + * dev_change_proto_down_reason - proto down reason + * + * @dev: device + * @mask: proto down mask + * @value: proto down value + */ +void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, + u32 value) +{ + int b; + + if (!mask) { + dev->proto_down_reason = value; + } else { + for_each_set_bit(b, &mask, 32) { + if (value & (1 << b)) + dev->proto_down_reason |= BIT(b); + else + dev->proto_down_reason &= ~BIT(b); + } + } +} +EXPORT_SYMBOL(dev_change_proto_down_reason); + struct bpf_xdp_link { struct bpf_link link; struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 0ca89196a367..e674f0f46dc2 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1206,7 +1206,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -1415,7 +1417,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -1656,7 +1660,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -3470,7 +3476,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -3740,7 +3748,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -4697,7 +4707,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); mutex_unlock(&devlink->lock); - if (err && err != -EOPNOTSUPP) + if (err == -EOPNOTSUPP) + err = 0; + else if (err) break; idx++; } @@ -6411,7 +6423,7 @@ static int __devlink_trap_action_set(struct devlink *devlink, } err = devlink->ops->trap_action_set(devlink, trap_item->trap, - trap_action); + trap_action, extack); if (err) return err; @@ -6701,7 +6713,8 @@ static int devlink_trap_group_set(struct devlink *devlink, } policer = policer_item ? policer_item->policer : NULL; - err = devlink->ops->trap_group_set(devlink, group_item->group, policer); + err = devlink->ops->trap_group_set(devlink, group_item->group, policer, + extack); if (err) return err; @@ -8789,6 +8802,7 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(PTP_GENERAL, CONTROL), DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL), DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL), + DEVLINK_TRAP(EARLY_DROP, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -8817,6 +8831,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(PIM), DEVLINK_TRAP_GROUP(UC_LB), DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), + DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), DEVLINK_TRAP_GROUP(IPV6), DEVLINK_TRAP_GROUP(PTP_EVENT), DEVLINK_TRAP_GROUP(PTP_GENERAL), @@ -9037,7 +9052,8 @@ static void devlink_trap_disable(struct devlink *devlink, if (WARN_ON_ONCE(!trap_item)) return; - devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP); + devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP, + NULL); trap_item->action = DEVLINK_TRAP_ACTION_DROP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bd7eba9066f8..51678a528f85 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -14,6 +14,20 @@ #include <net/sock.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> +#include <linux/indirect_call_wrapper.h> + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +#ifdef CONFIG_IP_MULTIPLE_TABLES +#define INDIRECT_CALL_MT(f, f2, f1, ...) \ + INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) +#endif +#elif defined(CONFIG_IP_MULTIPLE_TABLES) +#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__) +#endif static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(0), @@ -267,7 +281,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, uid_gt(fl->flowi_uid, rule->uid_range.end)) goto out; - ret = ops->match(rule, fl, flags); + ret = INDIRECT_CALL_MT(ops->match, + fib6_rule_match, + fib4_rule_match, + rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; } @@ -298,9 +315,15 @@ jumped: } else if (rule->action == FR_ACT_NOP) continue; else - err = ops->action(rule, fl, flags, arg); - - if (!err && ops->suppress && ops->suppress(rule, arg)) + err = INDIRECT_CALL_MT(ops->action, + fib6_rule_action, + fib4_rule_action, + rule, fl, flags, arg); + + if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, + fib6_rule_suppress, + fib4_rule_suppress, + rule, arg)) continue; if (err != -EAGAIN) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 58c484a28395..68e0682450c6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1000,6 +1000,16 @@ static size_t rtnl_prop_list_size(const struct net_device *dev) return size; } +static size_t rtnl_proto_down_size(const struct net_device *dev) +{ + size_t size = nla_total_size(1); + + if (dev->proto_down_reason) + size += nla_total_size(0) + nla_total_size(4); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1041,7 +1051,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_EVENT */ + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(4) /* IFLA_NEW_IFINDEX */ - + nla_total_size(1) /* IFLA_PROTO_DOWN */ + + rtnl_proto_down_size(dev) /* proto down */ + nla_total_size(4) /* IFLA_TARGET_NETNSID */ + nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */ + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ @@ -1657,6 +1667,35 @@ nest_cancel: return ret; } +static int rtnl_fill_proto_down(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *pr; + u32 preason; + + if (nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) + goto nla_put_failure; + + preason = dev->proto_down_reason; + if (!preason) + return 0; + + pr = nla_nest_start(skb, IFLA_PROTO_DOWN_REASON); + if (!pr) + return -EMSGSIZE; + + if (nla_put_u32(skb, IFLA_PROTO_DOWN_REASON_VALUE, preason)) { + nla_nest_cancel(skb, pr); + goto nla_put_failure; + } + + nla_nest_end(skb, pr); + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, @@ -1707,13 +1746,15 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_up_count) + atomic_read(&dev->carrier_down_count)) || - nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down) || nla_put_u32(skb, IFLA_CARRIER_UP_COUNT, atomic_read(&dev->carrier_up_count)) || nla_put_u32(skb, IFLA_CARRIER_DOWN_COUNT, atomic_read(&dev->carrier_down_count))) goto nla_put_failure; + if (rtnl_fill_proto_down(skb, dev)) + goto nla_put_failure; + if (event != IFLA_EVENT_NONE) { if (nla_put_u32(skb, IFLA_EVENT, event)) goto nla_put_failure; @@ -1833,6 +1874,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_ALT_IFNAME] = { .type = NLA_STRING, .len = ALTIFNAMSIZ - 1 }, [IFLA_PERM_ADDRESS] = { .type = NLA_REJECT }, + [IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2482,6 +2524,67 @@ static int do_set_master(struct net_device *dev, int ifindex, return 0; } +static const struct nla_policy ifla_proto_down_reason_policy[IFLA_PROTO_DOWN_REASON_VALUE + 1] = { + [IFLA_PROTO_DOWN_REASON_MASK] = { .type = NLA_U32 }, + [IFLA_PROTO_DOWN_REASON_VALUE] = { .type = NLA_U32 }, +}; + +static int do_set_proto_down(struct net_device *dev, + struct nlattr *nl_proto_down, + struct nlattr *nl_proto_down_reason, + struct netlink_ext_ack *extack) +{ + struct nlattr *pdreason[IFLA_PROTO_DOWN_REASON_MAX + 1]; + const struct net_device_ops *ops = dev->netdev_ops; + unsigned long mask = 0; + u32 value; + bool proto_down; + int err; + + if (!ops->ndo_change_proto_down) { + NL_SET_ERR_MSG(extack, "Protodown not supported by device"); + return -EOPNOTSUPP; + } + + if (nl_proto_down_reason) { + err = nla_parse_nested_deprecated(pdreason, + IFLA_PROTO_DOWN_REASON_MAX, + nl_proto_down_reason, + ifla_proto_down_reason_policy, + NULL); + if (err < 0) + return err; + + if (!pdreason[IFLA_PROTO_DOWN_REASON_VALUE]) { + NL_SET_ERR_MSG(extack, "Invalid protodown reason value"); + return -EINVAL; + } + + value = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_VALUE]); + + if (pdreason[IFLA_PROTO_DOWN_REASON_MASK]) + mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]); + + dev_change_proto_down_reason(dev, mask, value); + } + + if (nl_proto_down) { + proto_down = nla_get_u8(nl_proto_down); + + /* Dont turn off protodown if there are active reasons */ + if (!proto_down && dev->proto_down_reason) { + NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons"); + return -EBUSY; + } + err = dev_change_proto_down(dev, + proto_down); + if (err) + return err; + } + + return 0; +} + #define DO_SETLINK_MODIFIED 0x01 /* notify flag means notify + modified. */ #define DO_SETLINK_NOTIFY 0x03 @@ -2770,9 +2873,9 @@ static int do_setlink(const struct sk_buff *skb, } err = 0; - if (tb[IFLA_PROTO_DOWN]) { - err = dev_change_proto_down(dev, - nla_get_u8(tb[IFLA_PROTO_DOWN])); + if (tb[IFLA_PROTO_DOWN] || tb[IFLA_PROTO_DOWN_REASON]) { + err = do_set_proto_down(dev, tb[IFLA_PROTO_DOWN], + tb[IFLA_PROTO_DOWN_REASON], extack); if (err) goto errout; status |= DO_SETLINK_NOTIFY; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b8afefe6f6b6..2828f6d5ba89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3758,7 +3758,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int err = -ENOMEM; int i = 0; int pos; - int dummy; if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) && (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) { @@ -3780,7 +3779,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, } __skb_push(head_skb, doffset); - proto = skb_network_protocol(head_skb, &dummy); + proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL); @@ -4413,7 +4412,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) * at the moment even if they are anonymous). */ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && - __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL) + !__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM; /* Easy case. Most of packets will go this way. */ @@ -4692,7 +4691,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { - skb = tcp_get_timestamping_opt_stats(sk); + skb = tcp_get_timestamping_opt_stats(sk, orig_skb); opt_stats = true; } else #endif diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 2e9e8449698f..d148ab1530e5 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -426,9 +426,8 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service, return -ENOMEM; sl->dccpsl_nr = optlen / sizeof(u32) - 1; - sockptr_advance(optval, sizeof(service)); - if (copy_from_sockptr(sl->dccpsl_list, optval, - optlen - sizeof(service)) || + if (copy_from_sockptr_offset(sl->dccpsl_list, optval, + sizeof(service), optlen - sizeof(service)) || dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) { kfree(sl); return -EFAULT; diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index dc705769acc9..26a9193df783 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -6,7 +6,7 @@ * * DECnet Routing Message Grabulator * - * (C) 2000 ChyGwyn Limited - http://www.chygwyn.com/ + * (C) 2000 ChyGwyn Limited - https://www.chygwyn.com/ * * Author: Steven Whitehouse <steve@chygwyn.com> */ diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 317a93129551..7044a2853886 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -421,8 +421,7 @@ int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) ret = __ethtool_get_link_ksettings(dev, &ksettings); if (ret < 0) { - if (info) - GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); + GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out_ops; } diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index 6b89255f1231..84f23289475b 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -2,6 +2,7 @@ #include <linux/ethtool_netlink.h> #include <net/udp_tunnel.h> +#include <net/vxlan.h> #include "bitset.h" #include "common.h" @@ -18,6 +19,20 @@ static_assert(ETHTOOL_UDP_TUNNEL_TYPE_GENEVE == ilog2(UDP_TUNNEL_TYPE_GENEVE)); static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE == ilog2(UDP_TUNNEL_TYPE_VXLAN_GPE)); +static ssize_t ethnl_udp_table_reply_size(unsigned int types, bool compact) +{ + ssize_t size; + + size = ethnl_bitset32_size(&types, NULL, __ETHTOOL_UDP_TUNNEL_TYPE_CNT, + udp_tunnel_type_names, compact); + if (size < 0) + return size; + + return size + + nla_total_size(0) + /* _UDP_TABLE */ + nla_total_size(sizeof(u32)); /* _UDP_TABLE_SIZE */ +} + static ssize_t ethnl_tunnel_info_reply_size(const struct ethnl_req_info *req_base, struct netlink_ext_ack *extack) @@ -25,8 +40,8 @@ ethnl_tunnel_info_reply_size(const struct ethnl_req_info *req_base, bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct udp_tunnel_nic_info *info; unsigned int i; + ssize_t ret; size_t size; - int ret; info = req_base->dev->udp_tunnel_nic_info; if (!info) { @@ -39,13 +54,10 @@ ethnl_tunnel_info_reply_size(const struct ethnl_req_info *req_base, for (i = 0; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) - return size; + break; - size += nla_total_size(0); /* _UDP_TABLE */ - size += nla_total_size(sizeof(u32)); /* _UDP_TABLE_SIZE */ - ret = ethnl_bitset32_size(&info->tables[i].tunnel_types, NULL, - __ETHTOOL_UDP_TUNNEL_TYPE_CNT, - udp_tunnel_type_names, compact); + ret = ethnl_udp_table_reply_size(info->tables[i].tunnel_types, + compact); if (ret < 0) return ret; size += ret; @@ -53,6 +65,17 @@ ethnl_tunnel_info_reply_size(const struct ethnl_req_info *req_base, size += udp_tunnel_nic_dump_size(req_base->dev, i); } + if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN) { + ret = ethnl_udp_table_reply_size(0, compact); + if (ret < 0) + return ret; + size += ret; + + size += nla_total_size(0) + /* _TABLE_ENTRY */ + nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ + nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ + } + return size; } @@ -62,7 +85,7 @@ ethnl_tunnel_info_fill_reply(const struct ethnl_req_info *req_base, { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct udp_tunnel_nic_info *info; - struct nlattr *ports, *table; + struct nlattr *ports, *table, *entry; unsigned int i; info = req_base->dev->udp_tunnel_nic_info; @@ -97,10 +120,40 @@ ethnl_tunnel_info_fill_reply(const struct ethnl_req_info *req_base, nla_nest_end(skb, table); } + if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN) { + u32 zero = 0; + + table = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE); + if (!table) + goto err_cancel_ports; + + if (nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE, 1)) + goto err_cancel_table; + + if (ethnl_put_bitset32(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES, + &zero, NULL, + __ETHTOOL_UDP_TUNNEL_TYPE_CNT, + udp_tunnel_type_names, compact)) + goto err_cancel_table; + + entry = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); + + if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, + htons(IANA_VXLAN_UDP_PORT)) || + nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, + ilog2(UDP_TUNNEL_TYPE_VXLAN))) + goto err_cancel_entry; + + nla_nest_end(skb, entry); + nla_nest_end(skb, table); + } + nla_nest_end(skb, ports); return 0; +err_cancel_entry: + nla_nest_cancel(skb, entry); err_cancel_table: nla_nest_cancel(skb, table); err_cancel_ports: diff --git a/net/hsr/Kconfig b/net/hsr/Kconfig index 8095b034e76e..1b048c17b6c8 100644 --- a/net/hsr/Kconfig +++ b/net/hsr/Kconfig @@ -4,24 +4,35 @@ # config HSR - tristate "High-availability Seamless Redundancy (HSR)" + tristate "High-availability Seamless Redundancy (HSR & PRP)" help + This enables IEC 62439 defined High-availability Seamless + Redundancy (HSR) and Parallel Redundancy Protocol (PRP). + If you say Y here, then your Linux box will be able to act as a - DANH ("Doubly attached node implementing HSR"). For this to work, - your Linux box needs (at least) two physical Ethernet interfaces, - and it must be connected as a node in a ring network together with - other HSR capable nodes. + DANH ("Doubly attached node implementing HSR") or DANP ("Doubly + attached node implementing PRP"). For this to work, your Linux box + needs (at least) two physical Ethernet interfaces. + + For DANH, it must be connected as a node in a ring network together + with other HSR capable nodes. All Ethernet frames sent over the HSR + device will be sent in both directions on the ring (over both slave + ports), giving a redundant, instant fail-over network. Each HSR node + in the ring acts like a bridge for HSR frames, but filters frames + that have been forwarded earlier. - All Ethernet frames sent over the hsr device will be sent in both - directions on the ring (over both slave ports), giving a redundant, - instant fail-over network. Each HSR node in the ring acts like a - bridge for HSR frames, but filters frames that have been forwarded - earlier. + For DANP, it must be connected as a node connecting to two + separate networks over the two slave interfaces. Like HSR, Ethernet + frames sent over the PRP device will be sent to both networks giving + a redundant, instant fail-over network. Unlike HSR, PRP networks + can have Singly Attached Nodes (SAN) such as PC, printer, bridges + etc and will be able to communicate with DANP nodes. This code is a "best effort" to comply with the HSR standard as described in IEC 62439-3:2010 (HSRv0) and IEC 62439-3:2012 (HSRv1), - but no compliancy tests have been made. Use iproute2 to select - the version you desire. + and PRP standard described in IEC 62439-4:2012 (PRP), but no + compliancy tests have been made. Use iproute2 to select the protocol + you would like to use. You need to perform any and all necessary tests yourself before relying on this code in a safety critical system! diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 9787ef11ca71..7e11a6c35bc3 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -1,5 +1,5 @@ /* - * hsr_debugfs code + * debugfs code for HSR & PRP * Copyright (C) 2019 Texas Instruments Incorporated * * Author(s): @@ -22,12 +22,6 @@ static struct dentry *hsr_debugfs_root_dir; -static void print_mac_address(struct seq_file *sfp, unsigned char *mac) -{ - seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:", - mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]); -} - /* hsr_node_table_show - Formats and prints node_table entries */ static int hsr_node_table_show(struct seq_file *sfp, void *data) @@ -35,20 +29,32 @@ hsr_node_table_show(struct seq_file *sfp, void *data) struct hsr_priv *priv = (struct hsr_priv *)sfp->private; struct hsr_node *node; - seq_puts(sfp, "Node Table entries\n"); - seq_puts(sfp, "MAC-Address-A, MAC-Address-B, time_in[A], "); - seq_puts(sfp, "time_in[B], Address-B port\n"); + seq_printf(sfp, "Node Table entries for (%s) device\n", + (priv->prot_version == PRP_V1 ? "PRP" : "HSR")); + seq_puts(sfp, "MAC-Address-A, MAC-Address-B, time_in[A], "); + seq_puts(sfp, "time_in[B], Address-B port, "); + if (priv->prot_version == PRP_V1) + seq_puts(sfp, "SAN-A, SAN-B, DAN-P\n"); + else + seq_puts(sfp, "DAN-H\n"); + rcu_read_lock(); list_for_each_entry_rcu(node, &priv->node_db, mac_list) { /* skip self node */ if (hsr_addr_is_self(priv, node->macaddress_A)) continue; - print_mac_address(sfp, &node->macaddress_A[0]); - seq_puts(sfp, " "); - print_mac_address(sfp, &node->macaddress_B[0]); - seq_printf(sfp, "0x%lx, ", node->time_in[HSR_PT_SLAVE_A]); - seq_printf(sfp, "0x%lx ", node->time_in[HSR_PT_SLAVE_B]); - seq_printf(sfp, "0x%x\n", node->addr_B_port); + seq_printf(sfp, "%pM ", &node->macaddress_A[0]); + seq_printf(sfp, "%pM ", &node->macaddress_B[0]); + seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_A]); + seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_B]); + seq_printf(sfp, "%14x, ", node->addr_B_port); + + if (priv->prot_version == PRP_V1) + seq_printf(sfp, "%5x, %5x, %5x\n", + node->san_a, node->san_b, + (node->san_a == 0 && node->san_b == 0)); + else + seq_printf(sfp, "%5x\n", 1); } rcu_read_unlock(); return 0; @@ -57,7 +63,8 @@ hsr_node_table_show(struct seq_file *sfp, void *data) /* hsr_node_table_open - Open the node_table file * * Description: - * This routine opens a debugfs file node_table of specific hsr device + * This routine opens a debugfs file node_table of specific hsr + * or prp device */ static int hsr_node_table_open(struct inode *inode, struct file *filp) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 8a927b647829..ab953a1a0d6c 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -3,9 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se - * * This file contains device methods for creating, using and destroying - * virtual HSR devices. + * virtual HSR or PRP devices. */ #include <linux/netdevice.h> @@ -231,66 +230,103 @@ static const struct header_ops hsr_header_ops = { .parse = eth_header_parse, }; -static void send_hsr_supervision_frame(struct hsr_port *master, - u8 type, u8 hsr_ver) +static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) { + struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; - struct hsr_tag *hsr_tag; - struct hsr_sup_tag *hsr_stag; - struct hsr_sup_payload *hsr_sp; - unsigned long irqflags; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; + /* skb size is same for PRP/HSR frames, only difference + * being, for PRP it is a trailer and for HSR it is a + * header + */ skb = dev_alloc_skb(sizeof(struct hsr_tag) + sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) - return; + return skb; skb_reserve(skb, hlen); - skb->dev = master->dev; - skb->protocol = htons(hsr_ver ? ETH_P_HSR : ETH_P_PRP); + skb->protocol = htons(proto); skb->priority = TC_PRIO_CONTROL; - if (dev_hard_header(skb, skb->dev, (hsr_ver ? ETH_P_HSR : ETH_P_PRP), - master->hsr->sup_multicast_addr, + if (dev_hard_header(skb, skb->dev, proto, + hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; + skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); - if (hsr_ver > 0) { + return skb; +out: + kfree_skb(skb); + + return NULL; +} + +static void send_hsr_supervision_frame(struct hsr_port *master, + unsigned long *interval) +{ + struct hsr_priv *hsr = master->hsr; + __u8 type = HSR_TLV_LIFE_CHECK; + struct hsr_tag *hsr_tag = NULL; + struct hsr_sup_payload *hsr_sp; + struct hsr_sup_tag *hsr_stag; + unsigned long irqflags; + struct sk_buff *skb; + u16 proto; + + *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); + if (hsr->announce_count < 3 && hsr->prot_version == 0) { + type = HSR_TLV_ANNOUNCE; + *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); + hsr->announce_count++; + } + + if (!hsr->prot_version) + proto = ETH_P_PRP; + else + proto = ETH_P_HSR; + + skb = hsr_init_skb(master, proto); + if (!skb) { + WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + return; + } + + if (hsr->prot_version > 0) { hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); hsr_tag->encap_proto = htons(ETH_P_PRP); set_hsr_tag_LSDU_size(hsr_tag, HSR_V1_SUP_LSDUSIZE); } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); - set_hsr_stag_path(hsr_stag, (hsr_ver ? 0x0 : 0xf)); - set_hsr_stag_HSR_ver(hsr_stag, hsr_ver); + set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); + set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags); - if (hsr_ver > 0) { - hsr_stag->sequence_nr = htons(master->hsr->sup_sequence_nr); - hsr_tag->sequence_nr = htons(master->hsr->sequence_nr); - master->hsr->sup_sequence_nr++; - master->hsr->sequence_nr++; + if (hsr->prot_version > 0) { + hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); + hsr->sup_sequence_nr++; + hsr_tag->sequence_nr = htons(hsr->sequence_nr); + hsr->sequence_nr++; } else { - hsr_stag->sequence_nr = htons(master->hsr->sequence_nr); - master->hsr->sequence_nr++; + hsr_stag->sequence_nr = htons(hsr->sequence_nr); + hsr->sequence_nr++; } spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); hsr_stag->HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ - hsr_stag->HSR_TLV_length = - hsr_ver ? sizeof(struct hsr_sup_payload) : 12; + hsr_stag->HSR_TLV_length = hsr->prot_version ? + sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); @@ -300,11 +336,57 @@ static void send_hsr_supervision_frame(struct hsr_port *master, return; hsr_forward_skb(skb, master); + return; +} -out: - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); - kfree_skb(skb); +static void send_prp_supervision_frame(struct hsr_port *master, + unsigned long *interval) +{ + struct hsr_priv *hsr = master->hsr; + struct hsr_sup_payload *hsr_sp; + struct hsr_sup_tag *hsr_stag; + unsigned long irqflags; + struct sk_buff *skb; + struct prp_rct *rct; + u8 *tail; + + skb = hsr_init_skb(master, ETH_P_PRP); + if (!skb) { + WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + return; + } + + *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); + hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); + set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); + set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); + + /* From HSRv1 on we have separate supervision sequence numbers. */ + spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags); + hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); + hsr->sup_sequence_nr++; + hsr_stag->HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; + hsr_stag->HSR_TLV_length = sizeof(struct hsr_sup_payload); + + /* Payload: MacAddressA */ + hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); + ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); + + if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) { + spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); + return; + } + + tail = skb_tail_pointer(skb) - HSR_HLEN; + rct = (struct prp_rct *)tail; + rct->PRP_suffix = htons(ETH_P_PRP); + set_prp_LSDU_size(rct, HSR_V1_SUP_LSDUSIZE); + rct->sequence_nr = htons(hsr->sequence_nr); + hsr->sequence_nr++; + spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); + + hsr_forward_skb(skb, master); } /* Announce (supervision frame) timer function @@ -319,19 +401,7 @@ static void hsr_announce(struct timer_list *t) rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - - if (hsr->announce_count < 3 && hsr->prot_version == 0) { - send_hsr_supervision_frame(master, HSR_TLV_ANNOUNCE, - hsr->prot_version); - hsr->announce_count++; - - interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); - } else { - send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK, - hsr->prot_version); - - interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); - } + hsr->proto_ops->send_sv_frame(master, &interval); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); @@ -368,6 +438,24 @@ static struct device_type hsr_type = { .name = "hsr", }; +static struct hsr_proto_ops hsr_ops = { + .send_sv_frame = send_hsr_supervision_frame, + .create_tagged_frame = hsr_create_tagged_frame, + .get_untagged_frame = hsr_get_untagged_frame, + .fill_frame_info = hsr_fill_frame_info, + .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, +}; + +static struct hsr_proto_ops prp_ops = { + .send_sv_frame = send_prp_supervision_frame, + .create_tagged_frame = prp_create_tagged_frame, + .get_untagged_frame = prp_get_untagged_frame, + .drop_frame = prp_drop_frame, + .fill_frame_info = prp_fill_frame_info, + .handle_san_frame = prp_handle_san_frame, + .update_san_info = prp_update_san_info, +}; + void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); @@ -427,6 +515,17 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr); + /* initialize protocol specific functions */ + if (protocol_version == PRP_V1) { + /* For PRP, lan_id has most significant 3 bits holding + * the net_id of PRP_LAN_ID + */ + hsr->net_id = PRP_LAN_ID << 1; + hsr->proto_ops = &prp_ops; + } else { + hsr->proto_ops = &hsr_ops; + } + /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index b8f9262ed101..868373822ee4 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * include file for HSR and PRP. */ #ifndef __HSR_DEVICE_H diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index ab8dca0c0b65..cadfccd7876e 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * Frame router for HSR and PRP. */ #include "hsr_forward.h" @@ -15,18 +17,6 @@ struct hsr_node; -struct hsr_frame_info { - struct sk_buff *skb_std; - struct sk_buff *skb_hsr; - struct hsr_port *port_rcv; - struct hsr_node *node_src; - u16 sequence_nr; - bool is_supervision; - bool is_vlan; - bool is_local_dest; - bool is_local_exclusive; -}; - /* The uses I can see for these HSR supervision frames are: * 1) Use the frames that are sent after node initialization ("HSR_TLV.Type = * 22") to reset any sequence_nr counters belonging to that node. Useful if @@ -74,7 +64,9 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) } if (hsr_sup_tag->HSR_TLV_type != HSR_TLV_ANNOUNCE && - hsr_sup_tag->HSR_TLV_type != HSR_TLV_LIFE_CHECK) + hsr_sup_tag->HSR_TLV_type != HSR_TLV_LIFE_CHECK && + hsr_sup_tag->HSR_TLV_type != PRP_TLV_LIFE_CHECK_DD && + hsr_sup_tag->HSR_TLV_type != PRP_TLV_LIFE_CHECK_DA) return false; if (hsr_sup_tag->HSR_TLV_length != 12 && hsr_sup_tag->HSR_TLV_length != sizeof(struct hsr_sup_payload)) @@ -83,8 +75,8 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) return true; } -static struct sk_buff *create_stripped_skb(struct sk_buff *skb_in, - struct hsr_frame_info *frame) +static struct sk_buff *create_stripped_skb_hsr(struct sk_buff *skb_in, + struct hsr_frame_info *frame) { struct sk_buff *skb; int copylen; @@ -112,38 +104,123 @@ static struct sk_buff *create_stripped_skb(struct sk_buff *skb_in, return skb; } -static struct sk_buff *frame_get_stripped_skb(struct hsr_frame_info *frame, - struct hsr_port *port) +struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port) { - if (!frame->skb_std) - frame->skb_std = create_stripped_skb(frame->skb_hsr, frame); + if (!frame->skb_std) { + if (frame->skb_hsr) { + frame->skb_std = + create_stripped_skb_hsr(frame->skb_hsr, frame); + } else { + /* Unexpected */ + WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", + __FILE__, __LINE__, port->dev->name); + return NULL; + } + } + return skb_clone(frame->skb_std, GFP_ATOMIC); } +struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port) +{ + if (!frame->skb_std) { + if (frame->skb_prp) { + /* trim the skb by len - HSR_HLEN to exclude RCT */ + skb_trim(frame->skb_prp, + frame->skb_prp->len - HSR_HLEN); + frame->skb_std = + __pskb_copy(frame->skb_prp, + skb_headroom(frame->skb_prp), + GFP_ATOMIC); + } else { + /* Unexpected */ + WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", + __FILE__, __LINE__, port->dev->name); + return NULL; + } + } + + return skb_clone(frame->skb_std, GFP_ATOMIC); +} + +static void prp_set_lan_id(struct prp_rct *trailer, + struct hsr_port *port) +{ + int lane_id; + + if (port->type == HSR_PT_SLAVE_A) + lane_id = 0; + else + lane_id = 1; + + /* Add net_id in the upper 3 bits of lane_id */ + lane_id |= port->hsr->net_id; + set_prp_lan_id(trailer, lane_id); +} + +/* Tailroom for PRP rct should have been created before calling this */ +static struct sk_buff *prp_fill_rct(struct sk_buff *skb, + struct hsr_frame_info *frame, + struct hsr_port *port) +{ + struct prp_rct *trailer; + int min_size = ETH_ZLEN; + int lsdu_size; + + if (!skb) + return skb; + + if (frame->is_vlan) + min_size = VLAN_ETH_ZLEN; + + if (skb_put_padto(skb, min_size)) + return NULL; + + trailer = (struct prp_rct *)skb_put(skb, HSR_HLEN); + lsdu_size = skb->len - 14; + if (frame->is_vlan) + lsdu_size -= 4; + prp_set_lan_id(trailer, port); + set_prp_LSDU_size(trailer, lsdu_size); + trailer->sequence_nr = htons(frame->sequence_nr); + trailer->PRP_suffix = htons(ETH_P_PRP); + + return skb; +} + +static void hsr_set_path_id(struct hsr_ethhdr *hsr_ethhdr, + struct hsr_port *port) +{ + int path_id; + + if (port->type == HSR_PT_SLAVE_A) + path_id = 0; + else + path_id = 1; + + set_hsr_tag_path(&hsr_ethhdr->hsr_tag, path_id); +} + static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame, struct hsr_port *port, u8 proto_version) { struct hsr_ethhdr *hsr_ethhdr; - int lane_id; int lsdu_size; /* pad to minimum packet size which is 60 + 6 (HSR tag) */ if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) return NULL; - if (port->type == HSR_PT_SLAVE_A) - lane_id = 0; - else - lane_id = 1; - lsdu_size = skb->len - 14; if (frame->is_vlan) lsdu_size -= 4; hsr_ethhdr = (struct hsr_ethhdr *)skb_mac_header(skb); - set_hsr_tag_path(&hsr_ethhdr->hsr_tag, lane_id); + hsr_set_path_id(hsr_ethhdr, port); set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, lsdu_size); hsr_ethhdr->hsr_tag.sequence_nr = htons(frame->sequence_nr); hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; @@ -153,16 +230,28 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, return skb; } -static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, - struct hsr_frame_info *frame, - struct hsr_port *port) +/* If the original frame was an HSR tagged frame, just clone it to be sent + * unchanged. Otherwise, create a private frame especially tagged for 'port'. + */ +struct sk_buff *hsr_create_tagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port) { - int movelen; unsigned char *dst, *src; struct sk_buff *skb; + int movelen; + + if (frame->skb_hsr) { + struct hsr_ethhdr *hsr_ethhdr = + (struct hsr_ethhdr *)skb_mac_header(frame->skb_hsr); + + /* set the lane id properly */ + hsr_set_path_id(hsr_ethhdr, port); + return skb_clone(frame->skb_hsr, GFP_ATOMIC); + } /* Create the new skb with enough headroom to fit the HSR tag */ - skb = __pskb_copy(skb_o, skb_headroom(skb_o) + HSR_HLEN, GFP_ATOMIC); + skb = __pskb_copy(frame->skb_std, + skb_headroom(frame->skb_std) + HSR_HLEN, GFP_ATOMIC); if (!skb) return NULL; skb_reset_mac_header(skb); @@ -185,21 +274,29 @@ static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, return hsr_fill_tag(skb, frame, port, port->hsr->prot_version); } -/* If the original frame was an HSR tagged frame, just clone it to be sent - * unchanged. Otherwise, create a private frame especially tagged for 'port'. - */ -static struct sk_buff *frame_get_tagged_skb(struct hsr_frame_info *frame, - struct hsr_port *port) +struct sk_buff *prp_create_tagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port) { - if (frame->skb_hsr) - return skb_clone(frame->skb_hsr, GFP_ATOMIC); + struct sk_buff *skb; - if (port->type != HSR_PT_SLAVE_A && port->type != HSR_PT_SLAVE_B) { - WARN_ONCE(1, "HSR: Bug: trying to create a tagged frame for a non-ring port"); - return NULL; + if (frame->skb_prp) { + struct prp_rct *trailer = skb_get_PRP_rct(frame->skb_prp); + + if (trailer) { + prp_set_lan_id(trailer, port); + } else { + WARN_ONCE(!trailer, "errored PRP skb"); + return NULL; + } + return skb_clone(frame->skb_prp, GFP_ATOMIC); } - return create_tagged_skb(frame->skb_std, frame, port); + skb = skb_copy_expand(frame->skb_std, 0, + skb_tailroom(frame->skb_std) + HSR_HLEN, + GFP_ATOMIC); + prp_fill_rct(skb, frame, port); + + return skb; } static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev, @@ -236,9 +333,18 @@ static int hsr_xmit(struct sk_buff *skb, struct hsr_port *port, return dev_queue_xmit(skb); } +bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) +{ + return ((frame->port_rcv->type == HSR_PT_SLAVE_A && + port->type == HSR_PT_SLAVE_B) || + (frame->port_rcv->type == HSR_PT_SLAVE_B && + port->type == HSR_PT_SLAVE_A)); +} + /* Forward the frame through all devices except: * - Back through the receiving device * - If it's a HSR frame: through a device where it has passed before + * - if it's a PRP frame: through another PRP slave device (no bridge) * - To the local HSR master only if the frame is directly addressed to it, or * a non-supervision multicast or broadcast frame. * @@ -253,6 +359,7 @@ static void hsr_forward_do(struct hsr_frame_info *frame) struct sk_buff *skb; hsr_for_each_port(frame->port_rcv->hsr, port) { + struct hsr_priv *hsr = port->hsr; /* Don't send frame back the way it came */ if (port == frame->port_rcv) continue; @@ -265,24 +372,33 @@ static void hsr_forward_do(struct hsr_frame_info *frame) if (port->type != HSR_PT_MASTER && frame->is_local_exclusive) continue; - /* Don't send frame over port where it has been sent before */ - if (hsr_register_frame_out(port, frame->node_src, + /* Don't send frame over port where it has been sent before. + * Also fro SAN, this shouldn't be done. + */ + if (!frame->is_from_san && + hsr_register_frame_out(port, frame->node_src, frame->sequence_nr)) continue; if (frame->is_supervision && port->type == HSR_PT_MASTER) { - hsr_handle_sup_frame(frame->skb_hsr, - frame->node_src, - frame->port_rcv); + hsr_handle_sup_frame(frame); continue; } + /* Check if frame is to be dropped. Eg. for PRP no forward + * between ports. + */ + if (hsr->proto_ops->drop_frame && + hsr->proto_ops->drop_frame(frame, port)) + continue; + if (port->type != HSR_PT_MASTER) - skb = frame_get_tagged_skb(frame, port); + skb = hsr->proto_ops->create_tagged_frame(frame, port); else - skb = frame_get_stripped_skb(frame, port); + skb = hsr->proto_ops->get_untagged_frame(frame, port); + if (!skb) { - /* FIXME: Record the dropped frame? */ + frame->port_rcv->dev->stats.rx_dropped++; continue; } @@ -313,40 +429,95 @@ static void check_local_dest(struct hsr_priv *hsr, struct sk_buff *skb, } } -static int hsr_fill_frame_info(struct hsr_frame_info *frame, - struct sk_buff *skb, struct hsr_port *port) +static void handle_std_frame(struct sk_buff *skb, + struct hsr_frame_info *frame) { - struct ethhdr *ethhdr; + struct hsr_port *port = frame->port_rcv; + struct hsr_priv *hsr = port->hsr; unsigned long irqflags; + frame->skb_hsr = NULL; + frame->skb_prp = NULL; + frame->skb_std = skb; + + if (port->type != HSR_PT_MASTER) { + frame->is_from_san = true; + } else { + /* Sequence nr for the master node */ + spin_lock_irqsave(&hsr->seqnr_lock, irqflags); + frame->sequence_nr = hsr->sequence_nr; + hsr->sequence_nr++; + spin_unlock_irqrestore(&hsr->seqnr_lock, irqflags); + } +} + +void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) +{ + if (proto == htons(ETH_P_PRP) || + proto == htons(ETH_P_HSR)) { + /* HSR tagged frame :- Data or Supervision */ + frame->skb_std = NULL; + frame->skb_prp = NULL; + frame->skb_hsr = skb; + frame->sequence_nr = hsr_get_skb_sequence_nr(skb); + return; + } + + /* Standard frame or PRP from master port */ + handle_std_frame(skb, frame); +} + +void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame) +{ + /* Supervision frame */ + struct prp_rct *rct = skb_get_PRP_rct(skb); + + if (rct && + prp_check_lsdu_size(skb, rct, frame->is_supervision)) { + frame->skb_hsr = NULL; + frame->skb_std = NULL; + frame->skb_prp = skb; + frame->sequence_nr = prp_get_skb_sequence_nr(rct); + return; + } + handle_std_frame(skb, frame); +} + +static int fill_frame_info(struct hsr_frame_info *frame, + struct sk_buff *skb, struct hsr_port *port) +{ + struct hsr_priv *hsr = port->hsr; + struct hsr_vlan_ethhdr *vlan_hdr; + struct ethhdr *ethhdr; + __be16 proto; + + memset(frame, 0, sizeof(*frame)); frame->is_supervision = is_supervision_frame(port->hsr, skb); - frame->node_src = hsr_get_node(port, skb, frame->is_supervision); + frame->node_src = hsr_get_node(port, &hsr->node_db, skb, + frame->is_supervision, + port->type); if (!frame->node_src) return -1; /* Unknown node and !is_supervision, or no mem */ ethhdr = (struct ethhdr *)skb_mac_header(skb); frame->is_vlan = false; - if (ethhdr->h_proto == htons(ETH_P_8021Q)) { + proto = ethhdr->h_proto; + + if (proto == htons(ETH_P_8021Q)) frame->is_vlan = true; + + if (frame->is_vlan) { + vlan_hdr = (struct hsr_vlan_ethhdr *)ethhdr; + proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto; /* FIXME: */ netdev_warn_once(skb->dev, "VLAN not yet supported"); } - if (ethhdr->h_proto == htons(ETH_P_PRP) || - ethhdr->h_proto == htons(ETH_P_HSR)) { - frame->skb_std = NULL; - frame->skb_hsr = skb; - frame->sequence_nr = hsr_get_skb_sequence_nr(skb); - } else { - frame->skb_std = skb; - frame->skb_hsr = NULL; - /* Sequence nr for the master node */ - spin_lock_irqsave(&port->hsr->seqnr_lock, irqflags); - frame->sequence_nr = port->hsr->sequence_nr; - port->hsr->sequence_nr++; - spin_unlock_irqrestore(&port->hsr->seqnr_lock, irqflags); - } + frame->is_from_san = false; frame->port_rcv = port; + hsr->proto_ops->fill_frame_info(proto, skb, frame); check_local_dest(port->hsr, skb, frame); return 0; @@ -363,8 +534,9 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) goto out_drop; } - if (hsr_fill_frame_info(&frame, skb, port) < 0) + if (fill_frame_info(&frame, skb, port) < 0) goto out_drop; + hsr_register_frame_in(frame.node_src, port, frame.sequence_nr); hsr_forward_do(&frame); /* Gets called for ingress frames as well as egress from master port. @@ -376,6 +548,7 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) } kfree_skb(frame.skb_hsr); + kfree_skb(frame.skb_prp); kfree_skb(frame.skb_std); return; diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h index 51a69295566c..618140d484ad 100644 --- a/net/hsr/hsr_forward.h +++ b/net/hsr/hsr_forward.h @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * include file for HSR and PRP. */ #ifndef __HSR_FORWARD_H @@ -12,5 +14,17 @@ #include "hsr_main.h" void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port); - +struct sk_buff *prp_create_tagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port); +struct sk_buff *hsr_create_tagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port); +struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port); +struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, + struct hsr_port *port); +bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); +void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); +void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); #endif /* __HSR_FORWARD_H */ diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 530de24b1fb5..5c97de459905 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -8,6 +8,7 @@ * interface. A frame is identified by its source MAC address and its HSR * sequence number. This code keeps track of senders and their sequence numbers * to allow filtering of duplicate frames, and to detect HSR ring errors. + * Same code handles filtering of duplicates for PRP as well. */ #include <linux/if_ether.h> @@ -126,6 +127,19 @@ void hsr_del_nodes(struct list_head *node_db) kfree(node); } +void prp_handle_san_frame(bool san, enum hsr_port_type port, + struct hsr_node *node) +{ + /* Mark if the SAN node is over LAN_A or LAN_B */ + if (port == HSR_PT_SLAVE_A) { + node->san_a = true; + return; + } + + if (port == HSR_PT_SLAVE_B) + node->san_b = true; +} + /* Allocate an hsr_node and add it to node_db. 'addr' is the node's address_A; * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. @@ -133,7 +147,8 @@ void hsr_del_nodes(struct list_head *node_db) static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, struct list_head *node_db, unsigned char addr[], - u16 seq_out) + u16 seq_out, bool san, + enum hsr_port_type rx_port) { struct hsr_node *new_node, *node; unsigned long now; @@ -154,6 +169,9 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, for (i = 0; i < HSR_PT_PORTS; i++) new_node->seq_out[i] = seq_out; + if (san && hsr->proto_ops->handle_san_frame) + hsr->proto_ops->handle_san_frame(san, rx_port, new_node); + spin_lock_bh(&hsr->list_lock); list_for_each_entry_rcu(node, node_db, mac_list, lockdep_is_held(&hsr->list_lock)) { @@ -171,15 +189,26 @@ out: return node; } +void prp_update_san_info(struct hsr_node *node, bool is_sup) +{ + if (!is_sup) + return; + + node->san_a = false; + node->san_b = false; +} + /* Get the hsr_node from which 'skb' was sent. */ -struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, - bool is_sup) +struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, + struct sk_buff *skb, bool is_sup, + enum hsr_port_type rx_port) { - struct list_head *node_db = &port->hsr->node_db; struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; + struct prp_rct *rct; + bool san = false; u16 seq_out; if (!skb_mac_header_was_set(skb)) @@ -188,14 +217,21 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, ethhdr = (struct ethhdr *)skb_mac_header(skb); list_for_each_entry_rcu(node, node_db, mac_list) { - if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) + if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { + if (hsr->proto_ops->update_san_info) + hsr->proto_ops->update_san_info(node, is_sup); return node; - if (ether_addr_equal(node->macaddress_B, ethhdr->h_source)) + } + if (ether_addr_equal(node->macaddress_B, ethhdr->h_source)) { + if (hsr->proto_ops->update_san_info) + hsr->proto_ops->update_san_info(node, is_sup); return node; + } } - /* Everyone may create a node entry, connected node to a HSR device. */ - + /* Everyone may create a node entry, connected node to a HSR/PRP + * device. + */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { /* Use the existing sequence_nr from the tag as starting point @@ -203,31 +239,47 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, */ seq_out = hsr_get_skb_sequence_nr(skb) - 1; } else { - /* this is called also for frames from master port and - * so warn only for non master ports - */ - if (port->type != HSR_PT_MASTER) - WARN_ONCE(1, "%s: Non-HSR frame\n", __func__); - seq_out = HSR_SEQNR_START; + rct = skb_get_PRP_rct(skb); + if (rct && prp_check_lsdu_size(skb, rct, is_sup)) { + seq_out = prp_get_skb_sequence_nr(rct); + } else { + if (rx_port != HSR_PT_MASTER) + san = true; + seq_out = HSR_SEQNR_START; + } } - return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out); + return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out, + san, rx_port); } /* Use the Supervision frame's info about an eventual macaddress_B for merging * nodes that has previously had their macaddress_B registered as a separate * node. */ -void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, - struct hsr_port *port_rcv) +void hsr_handle_sup_frame(struct hsr_frame_info *frame) { + struct hsr_node *node_curr = frame->node_src; + struct hsr_port *port_rcv = frame->port_rcv; struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_node *node_real; + struct sk_buff *skb = NULL; struct list_head *node_db; struct ethhdr *ethhdr; int i; + /* Here either frame->skb_hsr or frame->skb_prp should be + * valid as supervision frame always will have protocol + * header info. + */ + if (frame->skb_hsr) + skb = frame->skb_hsr; + else if (frame->skb_prp) + skb = frame->skb_prp; + if (!skb) + return; + ethhdr = (struct ethhdr *)skb_mac_header(skb); /* Leave the ethernet header. */ @@ -248,7 +300,8 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, if (!node_real) /* No frame received from AddrA of this node yet */ node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, - HSR_SEQNR_START - 1); + HSR_SEQNR_START - 1, true, + port_rcv->type); if (!node_real) goto done; /* No mem */ if (node_real == node_curr) @@ -274,7 +327,11 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, kfree_rcu(node_curr, rcu_head); done: - skb_push(skb, sizeof(struct hsrv1_ethhdr_sp)); + /* PRP uses v0 header */ + if (ethhdr->h_proto == htons(ETH_P_HSR)) + skb_push(skb, sizeof(struct hsrv1_ethhdr_sp)); + else + skb_push(skb, sizeof(struct hsrv0_ethhdr_sp)); } /* 'skb' is a frame meant for this host, that is to be passed to upper layers. diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 0f0fa12b4329..86b43f539f2c 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * include file for HSR and PRP. */ #ifndef __HSR_FRAMEREG_H @@ -12,12 +14,26 @@ struct hsr_node; +struct hsr_frame_info { + struct sk_buff *skb_std; + struct sk_buff *skb_hsr; + struct sk_buff *skb_prp; + struct hsr_port *port_rcv; + struct hsr_node *node_src; + u16 sequence_nr; + bool is_supervision; + bool is_vlan; + bool is_local_dest; + bool is_local_exclusive; + bool is_from_san; +}; + void hsr_del_self_node(struct hsr_priv *hsr); void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, - bool is_sup); -void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, - struct hsr_port *port); +struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, + struct sk_buff *skb, bool is_sup, + enum hsr_port_type rx_port); +void hsr_handle_sup_frame(struct hsr_frame_info *frame); bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr); void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb); @@ -47,6 +63,10 @@ int hsr_get_node_data(struct hsr_priv *hsr, int *if2_age, u16 *if2_seq); +void prp_handle_san_frame(bool san, enum hsr_port_type port, + struct hsr_node *node); +void prp_update_san_info(struct hsr_node *node, bool is_sup); + struct hsr_node { struct list_head mac_list; unsigned char macaddress_A[ETH_ALEN]; @@ -55,6 +75,9 @@ struct hsr_node { enum hsr_port_type addr_B_port; unsigned long time_in[HSR_PT_PORTS]; bool time_in_stale[HSR_PT_PORTS]; + /* if the node is a SAN */ + bool san_a; + bool san_b; u16 seq_out[HSR_PT_PORTS]; struct rcu_head rcu_head; }; diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 144da15f0a81..2fd1976e5b1c 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * Event handling for HSR and PRP devices. */ #include <linux/netdevice.h> diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index f74193465bf5..7dc92ce5a134 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * include file for HSR and PRP. */ #ifndef __HSR_PRIVATE_H @@ -10,6 +12,7 @@ #include <linux/netdevice.h> #include <linux/list.h> +#include <linux/if_vlan.h> /* Time constants as specified in the HSR specification (IEC-62439-3 2010) * Table 8. @@ -33,6 +36,10 @@ #define HSR_TLV_ANNOUNCE 22 #define HSR_TLV_LIFE_CHECK 23 +/* PRP V1 life check for Duplicate discard */ +#define PRP_TLV_LIFE_CHECK_DD 20 +/* PRP V1 life check for Duplicate Accept */ +#define PRP_TLV_LIFE_CHECK_DA 21 /* HSR Tag. * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, @@ -80,7 +87,12 @@ struct hsr_ethhdr { struct hsr_tag hsr_tag; } __packed; -/* HSR Supervision Frame data types. +struct hsr_vlan_ethhdr { + struct vlan_ethhdr vlanhdr; + struct hsr_tag hsr_tag; +} __packed; + +/* HSR/PRP Supervision Frame data types. * Field names as defined in the IEC:2010 standard for HSR. */ struct hsr_sup_tag { @@ -124,6 +136,34 @@ enum hsr_port_type { HSR_PT_PORTS, /* This must be the last item in the enum */ }; +/* PRP Redunancy Control Trailor (RCT). + * As defined in IEC-62439-4:2012, the PRP RCT is really { sequence Nr, + * Lan indentifier (LanId), LSDU_size and PRP_suffix = 0x88FB }. + * + * Field names as defined in the IEC:2012 standard for PRP. + */ +struct prp_rct { + __be16 sequence_nr; + __be16 lan_id_and_LSDU_size; + __be16 PRP_suffix; +} __packed; + +static inline u16 get_prp_LSDU_size(struct prp_rct *rct) +{ + return ntohs(rct->lan_id_and_LSDU_size) & 0x0FFF; +} + +static inline void set_prp_lan_id(struct prp_rct *rct, u16 lan_id) +{ + rct->lan_id_and_LSDU_size = htons((ntohs(rct->lan_id_and_LSDU_size) & + 0x0FFF) | (lan_id << 12)); +} +static inline void set_prp_LSDU_size(struct prp_rct *rct, u16 LSDU_size) +{ + rct->lan_id_and_LSDU_size = htons((ntohs(rct->lan_id_and_LSDU_size) & + 0xF000) | (LSDU_size & 0x0FFF)); +} + struct hsr_port { struct list_head port_list; struct net_device *dev; @@ -131,6 +171,32 @@ struct hsr_port { enum hsr_port_type type; }; +/* used by driver internally to differentiate various protocols */ +enum hsr_version { + HSR_V0 = 0, + HSR_V1, + PRP_V1, +}; + +struct hsr_frame_info; +struct hsr_node; + +struct hsr_proto_ops { + /* format and send supervision frame */ + void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval); + void (*handle_san_frame)(bool san, enum hsr_port_type port, + struct hsr_node *node); + bool (*drop_frame)(struct hsr_frame_info *frame, struct hsr_port *port); + struct sk_buff * (*get_untagged_frame)(struct hsr_frame_info *frame, + struct hsr_port *port); + struct sk_buff * (*create_tagged_frame)(struct hsr_frame_info *frame, + struct hsr_port *port); + void (*fill_frame_info)(__be16 proto, struct sk_buff *skb, + struct hsr_frame_info *frame); + bool (*invalid_dan_ingress_frame)(__be16 protocol); + void (*update_san_info)(struct hsr_node *node, bool is_sup); +}; + struct hsr_priv { struct rcu_head rcu_head; struct list_head ports; @@ -141,9 +207,16 @@ struct hsr_priv { int announce_count; u16 sequence_nr; u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ - u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ + enum hsr_version prot_version; /* Indicate if HSRv0, HSRv1 or PRPv1 */ spinlock_t seqnr_lock; /* locking for sequence_nr */ spinlock_t list_lock; /* locking for node list */ + struct hsr_proto_ops *proto_ops; +#define PRP_LAN_ID 0x5 /* 0x1010 for A and 0x1011 for B. Bit 0 is set + * based on SLAVE_A or SLAVE_B + */ + u8 net_id; /* for PRP, it occupies most significant 3 bits + * of lan_id + */ unsigned char sup_multicast_addr[ETH_ALEN]; #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; @@ -164,6 +237,49 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb) return ntohs(hsr_ethhdr->hsr_tag.sequence_nr); } +static inline struct prp_rct *skb_get_PRP_rct(struct sk_buff *skb) +{ + unsigned char *tail = skb_tail_pointer(skb) - HSR_HLEN; + + struct prp_rct *rct = (struct prp_rct *)tail; + + if (rct->PRP_suffix == htons(ETH_P_PRP)) + return rct; + + return NULL; +} + +/* Assume caller has confirmed this skb is PRP suffixed */ +static inline u16 prp_get_skb_sequence_nr(struct prp_rct *rct) +{ + return ntohs(rct->sequence_nr); +} + +static inline u16 get_prp_lan_id(struct prp_rct *rct) +{ + return ntohs(rct->lan_id_and_LSDU_size) >> 12; +} + +/* assume there is a valid rct */ +static inline bool prp_check_lsdu_size(struct sk_buff *skb, + struct prp_rct *rct, + bool is_sup) +{ + struct ethhdr *ethhdr; + int expected_lsdu_size; + + if (is_sup) { + expected_lsdu_size = HSR_V1_SUP_LSDUSIZE; + } else { + ethhdr = (struct ethhdr *)skb_mac_header(skb); + expected_lsdu_size = skb->len - 14; + if (ethhdr->h_proto == htons(ETH_P_8021Q)) + expected_lsdu_size -= 4; + } + + return (expected_lsdu_size == get_prp_LSDU_size(rct)); +} + #if IS_ENABLED(CONFIG_DEBUG_FS) void hsr_debugfs_rename(struct net_device *dev); void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 6e14b7d22639..06c3cd988760 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -4,7 +4,7 @@ * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * - * Routines for handling Netlink messages for HSR. + * Routines for handling Netlink messages for HSR and PRP. */ #include "hsr_netlink.h" @@ -22,6 +22,7 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { [IFLA_HSR_VERSION] = { .type = NLA_U8 }, [IFLA_HSR_SUPERVISION_ADDR] = { .len = ETH_ALEN }, [IFLA_HSR_SEQ_NR] = { .type = NLA_U16 }, + [IFLA_HSR_PROTOCOL] = { .type = NLA_U8 }, }; /* Here, it seems a netdevice has already been allocated for us, and the @@ -31,8 +32,10 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + enum hsr_version proto_version; + unsigned char multicast_spec; + u8 proto = HSR_PROTOCOL_HSR; struct net_device *link[2]; - unsigned char multicast_spec, hsr_version; if (!data) { NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); @@ -69,18 +72,34 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, else multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]); + if (data[IFLA_HSR_PROTOCOL]) + proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]); + + if (proto >= HSR_PROTOCOL_MAX) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol\n"); + return -EINVAL; + } + if (!data[IFLA_HSR_VERSION]) { - hsr_version = 0; + proto_version = HSR_V0; } else { - hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]); - if (hsr_version > 1) { + if (proto == HSR_PROTOCOL_PRP) { + NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported\n"); + return -EINVAL; + } + + proto_version = nla_get_u8(data[IFLA_HSR_VERSION]); + if (proto_version > HSR_V1) { NL_SET_ERR_MSG_MOD(extack, - "Only versions 0..1 are supported"); + "Only HSR version 0/1 supported\n"); return -EINVAL; } } - return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack); + if (proto == HSR_PROTOCOL_PRP) + proto_version = PRP_V1; + + return hsr_dev_finalize(dev, link, multicast_spec, proto_version, extack); } static void hsr_dellink(struct net_device *dev, struct list_head *head) @@ -102,6 +121,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); + u8 proto = HSR_PROTOCOL_HSR; struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); @@ -120,6 +140,10 @@ static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) hsr->sup_multicast_addr) || nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr)) goto nla_put_failure; + if (hsr->prot_version == PRP_V1) + proto = HSR_PROTOCOL_PRP; + if (nla_put_u8(skb, IFLA_HSR_PROTOCOL, proto)) + goto nla_put_failure; return 0; diff --git a/net/hsr/hsr_netlink.h b/net/hsr/hsr_netlink.h index 1121bb192a18..501552d9753b 100644 --- a/net/hsr/hsr_netlink.h +++ b/net/hsr/hsr_netlink.h @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * include file for HSR and PRP. */ #ifndef __HSR_NETLINK_H diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 25b6ffba26cd..36d5fcf09c61 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -3,6 +3,8 @@ * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * Frame handler other utility functions for HSR and PRP. */ #include "hsr_slave.h" @@ -14,12 +16,22 @@ #include "hsr_forward.h" #include "hsr_framereg.h" +bool hsr_invalid_dan_ingress_frame(__be16 protocol) +{ + return (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)); +} + static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; + struct hsr_priv *hsr; __be16 protocol; + /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ + if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) + return RX_HANDLER_PASS; + if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); return RX_HANDLER_PASS; @@ -28,6 +40,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; + hsr = port->hsr; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ @@ -35,12 +48,23 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) goto finish_consume; } + /* For HSR, only tagged frames are expected, but for PRP + * there could be non tagged frames as well from Single + * attached nodes (SANs). + */ protocol = eth_hdr(skb)->h_proto; - if (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)) + if (hsr->proto_ops->invalid_dan_ingress_frame && + hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; skb_push(skb, ETH_HLEN); + if (skb_mac_header(skb) != skb->data) { + WARN_ONCE(1, "%s:%d: Malformed frame at source port %s)\n", + __func__, __LINE__, port->dev->name); + goto finish_consume; + } + hsr_forward_skb(skb, port); finish_consume: diff --git a/net/hsr/hsr_slave.h b/net/hsr/hsr_slave.h index 8953ea279ce9..edc4612bb009 100644 --- a/net/hsr/hsr_slave.h +++ b/net/hsr/hsr_slave.h @@ -2,6 +2,8 @@ /* Copyright 2011-2014 Autronica Fire and Security AS * * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + * + * include file for HSR and PRP. */ #ifndef __HSR_SLAVE_H @@ -30,4 +32,6 @@ static inline struct hsr_port *hsr_port_get_rcu(const struct net_device *dev) rcu_dereference(dev->rx_handler_data) : NULL; } +bool hsr_invalid_dan_ingress_frame(__be16 protocol); + #endif /* __HSR_SLAVE_H */ diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c index 94f18d2352d0..545b2640f019 100644 --- a/net/ipv4/bpfilter/sockopt.c +++ b/net/ipv4/bpfilter/sockopt.c @@ -65,7 +65,7 @@ int bpfilter_ip_get_sockopt(struct sock *sk, int optname, if (get_user(len, optlen)) return -EFAULT; - err = init_user_sockptr(&optval, user_optval); + err = init_user_sockptr(&optval, user_optval, len); if (err) return err; return bpfilter_mbox_request(sk, optname, optval, len, false); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f99e3bac5cab..ce54a30c2ef1 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -29,6 +29,7 @@ #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/fib_rules.h> +#include <linux/indirect_call_wrapper.h> struct fib4_rule { struct fib_rule common; @@ -103,8 +104,9 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, } EXPORT_SYMBOL_GPL(__fib_lookup); -static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, - int flags, struct fib_lookup_arg *arg) +INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule, + struct flowi *flp, int flags, + struct fib_lookup_arg *arg) { int err = -EAGAIN; struct fib_table *tbl; @@ -138,7 +140,8 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, return err; } -static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule, + struct fib_lookup_arg *arg) { struct fib_result *result = (struct fib_result *) arg->result; struct net_device *dev = NULL; @@ -169,7 +172,8 @@ suppress_route: return true; } -static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, + struct flowi *fl, int flags) { struct fib4_rule *r = (struct fib4_rule *) rule; struct flowi4 *fl4 = &fl->u.ip4; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index dcb0802a47d5..c89b46fec153 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1864,7 +1864,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; - hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 2e6d1b7a7bc9..e0a246575887 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + bool need_csum, need_recompute_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; - bool need_csum, gso_partial; if (!skb->encapsulation) goto out; @@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); + need_recompute_csum = skb->csum_not_inet; skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; @@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } *(pcsum + 1) = 0; - *pcsum = gso_make_checksum(skb, 0); + if (need_recompute_csum && !skb_is_gso(skb)) { + __wsum csum; + + csum = skb_checksum(skb, gre_offset, + skb->len - gre_offset, 0); + *pcsum = csum_fold(csum); + } else { + *pcsum = gso_make_checksum(skb, 0); + } } while ((skb = skb->next)); out: return segs; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 460ca1099e8a..49daaed89764 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -91,32 +91,6 @@ static int vti_rcv_proto(struct sk_buff *skb) return vti_rcv(skb, 0, false); } -static int vti_rcv_tunnel(struct sk_buff *skb) -{ - struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id); - const struct iphdr *iph = ip_hdr(skb); - struct ip_tunnel *tunnel; - - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->saddr, iph->daddr, 0); - if (tunnel) { - struct tnl_ptk_info tpi = { - .proto = htons(ETH_P_IP), - }; - - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) - goto drop; - if (iptunnel_pull_header(skb, 0, tpi.proto, false)) - goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false); - } - - return -EINVAL; -drop: - kfree_skb(skb); - return 0; -} - static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; @@ -244,12 +218,15 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, } dst_hold(dst); - dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0); + dst = xfrm_lookup_route(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } + if (dst->flags & DST_XFRM_QUEUE) + goto queued; + if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; dst_release(dst); @@ -281,6 +258,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } +queued: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; @@ -496,11 +474,29 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .priority = 100, }; -static struct xfrm_tunnel ipip_handler __read_mostly = { +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) +static int vti_rcv_tunnel(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr, 0, false); +} + +static struct xfrm_tunnel vti_ipip_handler __read_mostly = { + .handler = vti_rcv_tunnel, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 0, +}; + +static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .handler = vti_rcv_tunnel, + .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; +#endif static int __net_init vti_init_net(struct net *net) { @@ -670,10 +666,17 @@ static int __init vti_init(void) if (err < 0) goto xfrm_proto_comp_failed; +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) msg = "ipip tunnel"; - err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + err = xfrm4_tunnel_register(&vti_ipip_handler, AF_INET); + if (err < 0) + goto xfrm_tunnel_ipip_failed; +#if IS_ENABLED(CONFIG_IPV6) + err = xfrm4_tunnel_register(&vti_ipip6_handler, AF_INET6); if (err < 0) - goto xfrm_tunnel_failed; + goto xfrm_tunnel_ipip6_failed; +#endif +#endif msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); @@ -683,8 +686,14 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_tunnel_deregister(&ipip_handler, AF_INET); -xfrm_tunnel_failed: +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) +#if IS_ENABLED(CONFIG_IPV6) + xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); +xfrm_tunnel_ipip6_failed: +#endif + xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); +xfrm_tunnel_ipip_failed: +#endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); @@ -700,7 +709,12 @@ pernet_dev_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); - xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) +#if IS_ENABLED(CONFIG_IPV6) + xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); +#endif + xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); +#endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 59bfa3825810..b42683212c65 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -72,6 +72,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t->props.flags = x->props.flags; t->props.extra_flags = x->props.extra_flags; memcpy(&t->mark, &x->mark, sizeof(t->mark)); + t->if_id = x->if_id; if (xfrm_init_state(t)) goto error; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index cdf3a40f9ff5..876fd6ff1ff9 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1441,7 +1441,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, ret = -EINVAL; break; } - if (copy_from_sockptr(&val, optval, sizeof(val))) { + if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) { ret = -EFAULT; break; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index f5b26ef17820..d1e04d2b5170 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1,4 +1,4 @@ - +// SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code for ARP packets. * @@ -971,8 +971,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - sockptr_advance(arg, sizeof(tmp)); - if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } @@ -1267,8 +1267,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - sockptr_advance(arg, sizeof(tmp)); - if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f2a9680303d8..f15bc21d7301 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1126,8 +1126,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - sockptr_advance(arg, sizeof(tmp)); - if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } @@ -1508,8 +1508,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - sockptr_advance(arg, sizeof(tmp)); - if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 9a4f6b16c9bc..f0794f0232ba 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -212,6 +212,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); + + if (rsk_drop_req(req)) { + refcount_set(&req->rsk_refcnt, 2); + return child; + } + if (inet_csk_reqsk_queue_add(sk, req, child)) return child; @@ -276,6 +282,40 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, } EXPORT_SYMBOL(cookie_ecn_ok); +struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk, + struct sk_buff *skb) +{ + struct request_sock *req; + +#ifdef CONFIG_MPTCP + struct tcp_request_sock *treq; + + if (sk_is_mptcp(sk)) + ops = &mptcp_subflow_request_sock_ops; +#endif + + req = inet_reqsk_alloc(ops, sk, false); + if (!req) + return NULL; + +#if IS_ENABLED(CONFIG_MPTCP) + treq = tcp_rsk(req); + treq->is_mptcp = sk_is_mptcp(sk); + if (treq->is_mptcp) { + int err = mptcp_subflow_init_cookie_req(req, sk, skb); + + if (err) { + reqsk_free(req); + return NULL; + } + } +#endif + + return req; +} +EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc); + /* On input, sk is a listener. * Output is listener if incoming packet would not create a child * NULL if memory could not be allocated. @@ -326,7 +366,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */ + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); if (!req) goto out; @@ -350,9 +390,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->snt_synack = 0; treq->tfo_listener = false; - if (IS_ENABLED(CONFIG_MPTCP)) - treq->is_mptcp = 0; - if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 27de9380ed14..c06d2bfd2ec4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2801,12 +2801,13 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, { struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; + size_t offset = 0; while (len >= sizeof(opt)) { - if (copy_from_sockptr(&opt, optbuf, sizeof(opt))) + if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt))) return -EFAULT; - sockptr_advance(optbuf, sizeof(opt)); + offset += sizeof(opt); len -= sizeof(opt); switch (opt.opt_code) { @@ -3500,10 +3501,12 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ 0; } -struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, + const struct sk_buff *orig_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; @@ -3557,6 +3560,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); + nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, + TCP_NLA_PAD); return stats; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a018bafd7bdf..184ea556f50e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2950,6 +2950,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); ca_rtt_us = seq_rtt_us; } @@ -6519,7 +6521,6 @@ static void tcp_openreq_init(struct request_sock *req, struct inet_request_sock *ireq = inet_rsk(req); req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tcp_rsk(req)->snt_synack = 0; @@ -6674,6 +6675,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!req) goto drop; + req->syncookie = want_cookie; tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; #if IS_ENABLED(CONFIG_MPTCP) @@ -6701,9 +6703,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->init_req(req, sk, skb); - if (IS_ENABLED(CONFIG_MPTCP) && want_cookie) - tcp_rsk(req)->is_mptcp = 0; - if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; @@ -6739,7 +6738,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (want_cookie) { isn = cookie_init_sequence(af_ops, sk, skb, &req->mss); - req->cookie_ts = tmp_opt.tstamp_ok; if (!tmp_opt.tstamp_ok) inet_rsk(req)->ecn_ok = 0; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d8f16f6a9b02..85ff417bda7f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3393,7 +3393,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES - if (unlikely(req->cookie_ts)) + if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb->skb_mstamp_ns = cookie_init_timestamp(req, now); else #endif diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index c4b2ccbeba04..e44aaf41a138 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -110,6 +110,33 @@ drop: return 0; } +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) +static int tunnel4_rcv_cb(struct sk_buff *skb, u8 proto, int err) +{ + struct xfrm_tunnel __rcu *head; + struct xfrm_tunnel *handler; + int ret; + + head = (proto == IPPROTO_IPIP) ? tunnel4_handlers : tunnel64_handlers; + + for_each_tunnel_rcu(head, handler) { + if (handler->cb_handler) { + ret = handler->cb_handler(skb, err); + if (ret <= 0) + return ret; + } + } + + return 0; +} + +static const struct xfrm_input_afinfo tunnel4_input_afinfo = { + .family = AF_INET, + .is_ipip = true, + .callback = tunnel4_rcv_cb, +}; +#endif + #if IS_ENABLED(CONFIG_IPV6) static int tunnel64_rcv(struct sk_buff *skb) { @@ -231,6 +258,18 @@ static int __init tunnel4_init(void) goto err; } #endif +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) + if (xfrm_input_register_afinfo(&tunnel4_input_afinfo)) { + inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP); +#if IS_ENABLED(CONFIG_IPV6) + inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6); +#endif +#if IS_ENABLED(CONFIG_MPLS) + inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS); +#endif + goto err; + } +#endif return 0; err: @@ -240,6 +279,10 @@ err: static void __exit tunnel4_fini(void) { +#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) + if (xfrm_input_unregister_afinfo(&tunnel4_input_afinfo)) + pr_err("tunnel4 close: can't remove input afinfo\n"); +#endif #if IS_ENABLED(CONFIG_MPLS) if (inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS)) pr_err("tunnelmpls4 close: can't remove protocol\n"); diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index f0dbd9905a53..69962165c0e8 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -7,6 +7,7 @@ #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> +#include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), @@ -504,6 +505,12 @@ __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; + if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && + ti->port == htons(IANA_VXLAN_UDP_PORT)) { + if (ti->type != UDP_TUNNEL_TYPE_VXLAN) + netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); + return; + } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 840bfdb3d7bd..0acf6a9796ca 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -163,7 +163,7 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); static void addrconf_type_change(struct net_device *dev, unsigned long event); -static int addrconf_ifdown(struct net_device *dev, int how); +static int addrconf_ifdown(struct net_device *dev, bool unregister); static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, @@ -3630,7 +3630,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, * an L3 master device (e.g., VRF) */ if (info->upper_dev && netif_is_l3_master(info->upper_dev)) - addrconf_ifdown(dev, 0); + addrconf_ifdown(dev, false); } return NOTIFY_OK; @@ -3663,9 +3663,9 @@ static bool addr_is_local(const struct in6_addr *addr) (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } -static int addrconf_ifdown(struct net_device *dev, int how) +static int addrconf_ifdown(struct net_device *dev, bool unregister) { - unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN; + unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN; struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; @@ -3684,7 +3684,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) * Step 1: remove reference to ipv6 device from parent device. * Do not dev_put! */ - if (how) { + if (unregister) { idev->dead = 1; /* protected by rtnl_lock */ @@ -3698,7 +3698,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - if (!how && !idev->cnf.disable_ipv6) { + if (!unregister && !idev->cnf.disable_ipv6) { /* aggregate the system setting and interface setting */ int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; @@ -3736,7 +3736,7 @@ restart: addrconf_del_rs_timer(idev); /* Step 2: clear flags for stateless addrconf */ - if (!how) + if (!unregister) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); /* Step 3: clear tempaddr list */ @@ -3806,7 +3806,7 @@ restart: write_unlock_bh(&idev->lock); /* Step 5: Discard anycast and multicast list */ - if (how) { + if (unregister) { ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); } else { @@ -3816,7 +3816,7 @@ restart: idev->tstamp = jiffies; /* Last: Shot the device (if unregistered) */ - if (how) { + if (unregister) { addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); neigh_ifdown(&nd_tbl, dev); @@ -4038,7 +4038,7 @@ static void addrconf_dad_work(struct work_struct *w) in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 1); if (disable_ipv6) - addrconf_ifdown(idev->dev, 0); + addrconf_ifdown(idev->dev, false); goto out; } @@ -7187,9 +7187,9 @@ void addrconf_cleanup(void) for_each_netdev(&init_net, dev) { if (__in6_dev_get(dev) == NULL) continue; - addrconf_ifdown(dev, 1); + addrconf_ifdown(dev, true); } - addrconf_ifdown(init_net.loopback_dev, 2); + addrconf_ifdown(init_net.loopback_dev, true); /* * Check hash table. diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 893261230ffc..dacdea7fcb62 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c43592771126..52c2f063529f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -805,10 +805,17 @@ int esp6_input_done2(struct sk_buff *skb, int err) if (x->encap) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int offset = skb_network_offset(skb) + sizeof(*ip6h); struct xfrm_encap_tmpl *encap = x->encap; - struct udphdr *uh = (void *)(skb_network_header(skb) + hdr_len); - struct tcphdr *th = (void *)(skb_network_header(skb) + hdr_len); - __be16 source; + u8 nexthdr = ip6h->nexthdr; + __be16 frag_off, source; + struct udphdr *uh; + struct tcphdr *th; + + offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); + uh = (void *)(skb->data + offset); + th = (void *)(skb->data + offset); + hdr_len += offset; switch (x->encap->encap_type) { case TCP_ENCAP_ESPINTCP: diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 6053ef851555..8f9a83314de7 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -13,6 +13,7 @@ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/export.h> +#include <linux/indirect_call_wrapper.h> #include <net/fib_rules.h> #include <net/ipv6.h> @@ -255,8 +256,9 @@ out: return err; } -static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, - int flags, struct fib_lookup_arg *arg) +INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule, + struct flowi *flp, int flags, + struct fib_lookup_arg *arg) { if (arg->lookup_ptr == fib6_table_lookup) return fib6_rule_action_alt(rule, flp, flags, arg); @@ -264,7 +266,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, return __fib6_rule_action(rule, flp, flags, arg); } -static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, + struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct rt6_info *rt = res->rt6; @@ -296,7 +299,8 @@ suppress_route: return true; } -static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, + struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; struct flowi6 *fl6 = &fl->u.ip6; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 215b6f5e733e..2d655260dedc 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -401,8 +401,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, memset(fl->opt, 0, sizeof(*fl->opt)); fl->opt->tot_len = sizeof(*fl->opt) + olen; err = -EFAULT; - sockptr_advance(optval, CMSG_ALIGN(sizeof(*freq))); - if (copy_from_sockptr(fl->opt + 1, optval, olen)) + if (copy_from_sockptr_offset(fl->opt + 1, optval, + CMSG_ALIGN(sizeof(*freq)), olen)) goto done; msg.msg_controllen = olen; @@ -703,9 +703,10 @@ release: goto recheck; if (!freq->flr_label) { - sockptr_advance(optval, - offsetof(struct in6_flowlabel_req, flr_label)); - if (copy_to_sockptr(optval, &fl->label, sizeof(fl->label))) { + size_t offset = offsetof(struct in6_flowlabel_req, flr_label); + + if (copy_to_sockptr_offset(optval, offset, &fl->label, + sizeof(fl->label))) { /* Intentionally ignore fault. */ } } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0d964160a9dd..fac01b80a104 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -491,13 +491,16 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } dst_hold(dst); - dst = xfrm_lookup(t->net, dst, fl, NULL, 0); + dst = xfrm_lookup_route(t->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } + if (dst->flags & DST_XFRM_QUEUE) + goto queued; + x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; @@ -533,6 +536,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } +queued: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; @@ -1219,6 +1223,33 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .priority = 100, }; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) +static int vti6_rcv_tunnel(struct sk_buff *skb) +{ + const xfrm_address_t *saddr; + __be32 spi; + + saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; + spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); + + return vti6_input_proto(skb, IPPROTO_IPV6, spi, 0); +} + +static struct xfrm6_tunnel vti_ipv6_handler __read_mostly = { + .handler = vti6_rcv_tunnel, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 0, +}; + +static struct xfrm6_tunnel vti_ip6ip_handler __read_mostly = { + .handler = vti6_rcv_tunnel, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 0, +}; +#endif + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -1244,6 +1275,15 @@ static int __init vti6_tunnel_init(void) err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + msg = "ipv6 tunnel"; + err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET6); + if (err < 0) + goto vti_tunnel_ipv6_failed; + err = xfrm6_tunnel_register(&vti_ip6ip_handler, AF_INET); + if (err < 0) + goto vti_tunnel_ip6ip_failed; +#endif msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); @@ -1253,6 +1293,12 @@ static int __init vti6_tunnel_init(void) return 0; rtnl_link_failed: +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + err = xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); +vti_tunnel_ip6ip_failed: + err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); +vti_tunnel_ipv6_failed: +#endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); @@ -1271,6 +1317,10 @@ pernet_dev_failed: static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); + xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); +#endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 99668bfebd85..daef890460b7 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -91,6 +91,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) t->props.mode = x->props.mode; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); memcpy(&t->mark, &x->mark, sizeof(t->mark)); + t->if_id = x->if_id; if (xfrm_init_state(t)) goto error; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 20c740976334..43a894bf9a1b 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -458,6 +458,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 1d52957a413f..2e2119bfcf13 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1143,8 +1143,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - sockptr_advance(arg, sizeof(tmp)); - if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } @@ -1517,8 +1517,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; loc_cpu_entry = newinfo->entries; - sockptr_advance(arg, sizeof(tmp)); - if (copy_from_sockptr(loc_cpu_entry, arg, tmp.size) != 0) { + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 4e15a14435e4..70da2f2ce064 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -74,8 +74,7 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) ahinfo->hdrres, ah->reserved, !(ahinfo->hdrres && ah->reserved)); - return (ah != NULL) && - spi_match(ahinfo->spis[0], ahinfo->spis[1], + return spi_match(ahinfo->spis[0], ahinfo->spis[1], ntohl(ah->spi), !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && (!ahinfo->hdrlen || diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index fb91eeee4a1e..3aad6439386b 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -85,8 +85,7 @@ frag_mt6(const struct sk_buff *skb, struct xt_action_param *par) !((fraginfo->flags & IP6T_FRAG_NMF) && (ntohs(fh->frag_off) & IP6_MF))); - return (fh != NULL) && - id_match(fraginfo->ids[0], fraginfo->ids[1], + return id_match(fraginfo->ids[0], fraginfo->ids[1], ntohl(fh->identification), !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && !((fraginfo->flags & IP6T_FRAG_RES) && diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 467b2a86031b..e7a3fb9355ee 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -86,8 +86,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) ((optinfo->hdrlen == hdrlen) ^ !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); - ret = (oh != NULL) && - (!(optinfo->flags & IP6T_OPTS_LEN) || + ret = (!(optinfo->flags & IP6T_OPTS_LEN) || ((optinfo->hdrlen == hdrlen) ^ !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index f633dc84ca3f..733c83d38b30 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -89,8 +89,7 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) !((rtinfo->flags & IP6T_RT_RES) && (((const struct rt0_hdr *)rh)->reserved))); - ret = (rh != NULL) && - (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], + ret = (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], rh->segments_left, !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && (!(rtinfo->flags & IP6T_RT_LEN) || diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8bfc57b0802a..5e7e25e2523a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3686,14 +3686,14 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { - if (!nexthop_get(nh)) { - NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); - goto out; - } if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out; } + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + goto out; + } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index e0e9f48ab14f..897fa59c47de 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -27,6 +27,23 @@ #include <net/seg6_hmac.h> #endif +static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) +{ + int head = 0; + + switch (tuninfo->mode) { + case SEG6_IPTUN_MODE_INLINE: + break; + case SEG6_IPTUN_MODE_ENCAP: + head = sizeof(struct ipv6hdr); + break; + case SEG6_IPTUN_MODE_L2ENCAP: + return 0; + } + + return ((tuninfo->srh->hdrlen + 1) << 3) + head; +} + struct seg6_lwt { struct dst_cache cache; struct seg6_iptunnel_encap tuninfo[]; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 13235a012388..e796a64be308 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk, false); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); if (!req) goto out; @@ -178,9 +178,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) treq = tcp_rsk(req); treq->tfo_listener = false; - if (IS_ENABLED(CONFIG_MPTCP)) - treq->is_mptcp = 0; - if (security_inet_conn_request(sk, skb, req)) goto out_free; diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 06c02ebe6b9b..00e8d8b1c9a7 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -155,6 +155,33 @@ drop: return 0; } +#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) +static int tunnel6_rcv_cb(struct sk_buff *skb, u8 proto, int err) +{ + struct xfrm6_tunnel __rcu *head; + struct xfrm6_tunnel *handler; + int ret; + + head = (proto == IPPROTO_IPV6) ? tunnel6_handlers : tunnel46_handlers; + + for_each_tunnel_rcu(head, handler) { + if (handler->cb_handler) { + ret = handler->cb_handler(skb, err); + if (ret <= 0) + return ret; + } + } + + return 0; +} + +static const struct xfrm_input_afinfo tunnel6_input_afinfo = { + .family = AF_INET6, + .is_ipip = true, + .callback = tunnel6_rcv_cb, +}; +#endif + static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; @@ -245,11 +272,25 @@ static int __init tunnel6_init(void) inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); return -EAGAIN; } +#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) + if (xfrm_input_register_afinfo(&tunnel6_input_afinfo)) { + pr_err("%s: can't add input afinfo\n", __func__); + inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); + inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); + if (xfrm6_tunnel_mpls_supported()) + inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS); + return -EAGAIN; + } +#endif return 0; } static void __exit tunnel6_fini(void) { +#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) + if (xfrm_input_unregister_afinfo(&tunnel6_input_afinfo)) + pr_err("%s: can't remove input afinfo\n", __func__); +#endif if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) pr_err("%s: can't remove protocol\n", __func__); if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) diff --git a/net/key/af_key.c b/net/key/af_key.c index f13626c1a985..c12dbc51ef5f 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1849,6 +1849,13 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + if ((xfilter->sadb_x_filter_splen >= + (sizeof(xfrm_address_t) << 3)) || + (xfilter->sadb_x_filter_dplen >= + (sizeof(xfrm_address_t) << 3))) { + mutex_unlock(&pfk->dump_lock); + return -EINVAL; + } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); @@ -2400,7 +2407,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, 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); @@ -2651,7 +2658,7 @@ 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, 0, 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 e723828e458b..701fc72ad9f4 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -149,12 +149,51 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } -void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) +static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } -EXPORT_SYMBOL(l2tp_tunnel_free); + +static void l2tp_session_free(struct l2tp_session *session) +{ + struct l2tp_tunnel *tunnel = session->tunnel; + + if (tunnel) { + if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) + goto out; + l2tp_tunnel_dec_refcount(tunnel); + } + +out: + kfree(session); +} + +void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) +{ + refcount_inc(&tunnel->ref_count); +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); + +void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) +{ + if (refcount_dec_and_test(&tunnel->ref_count)) + l2tp_tunnel_free(tunnel); +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); + +void l2tp_session_inc_refcount(struct l2tp_session *session) +{ + refcount_inc(&session->ref_count); +} +EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); + +void l2tp_session_dec_refcount(struct l2tp_session *session) +{ + if (refcount_dec_and_test(&session->ref_count)) + l2tp_session_free(session); +} +EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) @@ -769,7 +808,7 @@ discard: atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } -EXPORT_SYMBOL(l2tp_recv_common); +EXPORT_SYMBOL_GPL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ @@ -1077,7 +1116,10 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len } /* Setup L2TP header */ - session->build_header(session, __skb_push(skb, hdr_len)); + if (tunnel->version == L2TP_HDR_VER_2) + l2tp_build_l2tpv2_header(session, __skb_push(skb, hdr_len)); + else + l2tp_build_l2tpv3_header(session, __skb_push(skb, hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1180,6 +1222,30 @@ end: return; } +/* Remove an l2tp session from l2tp_core's hash lists. */ +static void l2tp_session_unhash(struct l2tp_session *session) +{ + struct l2tp_tunnel *tunnel = session->tunnel; + + /* Remove the session from core hashes */ + if (tunnel) { + /* Remove from the per-tunnel hash */ + write_lock_bh(&tunnel->hlist_lock); + hlist_del_init(&session->hlist); + write_unlock_bh(&tunnel->hlist_lock); + + /* For L2TPv3 we have a per-net hash: remove from there, too */ + if (tunnel->version != L2TP_HDR_VER_2) { + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + + spin_lock_bh(&pn->l2tp_session_hlist_lock); + hlist_del_init_rcu(&session->global_hlist); + spin_unlock_bh(&pn->l2tp_session_hlist_lock); + synchronize_rcu(); + } + } +} + /* When the tunnel is closed, all the attached sessions need to go too. */ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) @@ -1209,7 +1275,7 @@ again: write_unlock_bh(&tunnel->hlist_lock); - __l2tp_session_unhash(session); + l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) @@ -1557,68 +1623,17 @@ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); -/* Really kill the session. - */ -void l2tp_session_free(struct l2tp_session *session) -{ - struct l2tp_tunnel *tunnel = session->tunnel; - - if (tunnel) { - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - goto out; - l2tp_tunnel_dec_refcount(tunnel); - } - -out: - kfree(session); -} -EXPORT_SYMBOL_GPL(l2tp_session_free); - -/* Remove an l2tp session from l2tp_core's hash lists. - * Provides a tidyup interface for pseudowire code which can't just route all - * shutdown via. l2tp_session_delete and a pseudowire-specific session_close - * callback. - */ -void __l2tp_session_unhash(struct l2tp_session *session) -{ - struct l2tp_tunnel *tunnel = session->tunnel; - - /* Remove the session from core hashes */ - if (tunnel) { - /* Remove from the per-tunnel hash */ - write_lock_bh(&tunnel->hlist_lock); - hlist_del_init(&session->hlist); - write_unlock_bh(&tunnel->hlist_lock); - - /* For L2TPv3 we have a per-net hash: remove from there, too */ - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); - synchronize_rcu(); - } - } -} -EXPORT_SYMBOL_GPL(__l2tp_session_unhash); - -/* This function is used by the netlink SESSION_DELETE command and by - * pseudowire modules. - */ -int l2tp_session_delete(struct l2tp_session *session) +void l2tp_session_delete(struct l2tp_session *session) { if (test_and_set_bit(0, &session->dead)) - return 0; + return; - __l2tp_session_unhash(session); + l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); l2tp_session_dec_refcount(session); - - return 0; } EXPORT_SYMBOL_GPL(l2tp_session_delete); @@ -1688,11 +1703,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } - if (tunnel->version == L2TP_HDR_VER_2) - session->build_header = l2tp_build_l2tpv2_header; - else - session->build_header = l2tp_build_l2tpv3_header; - l2tp_session_set_header_len(session, tunnel->version); refcount_set(&session->ref_count, 1); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 2d2dd219a176..3468d6b177a0 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -15,15 +15,15 @@ #include <net/xfrm.h> #endif -/* Just some random numbers */ +/* Random numbers used for internal consistency checks of tunnel and session structures */ #define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D -/* Per tunnel, session hash table size */ +/* Per tunnel session hash table size */ #define L2TP_HASH_BITS 4 #define L2TP_HASH_SIZE BIT(L2TP_HASH_BITS) -/* System-wide, session hash table size */ +/* System-wide session hash table size */ #define L2TP_HASH_BITS_2 8 #define L2TP_HASH_SIZE_2 BIT(L2TP_HASH_BITS_2) @@ -43,9 +43,7 @@ struct l2tp_stats { struct l2tp_tunnel; -/* Describes a session. Contains information to determine incoming - * packets and transmit outgoing ones. - */ +/* L2TP session configuration */ struct l2tp_session_cfg { enum l2tp_pwtype pw_type; unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */ @@ -63,6 +61,11 @@ struct l2tp_session_cfg { char *ifname; }; +/* Represents a session (pseudowire) instance. + * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics. + * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into + * an additional per-net ("global") hashlist. + */ struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; @@ -101,16 +104,32 @@ struct l2tp_session { struct l2tp_stats stats; struct hlist_node global_hlist; /* global hash list node */ - int (*build_header)(struct l2tp_session *session, void *buf); + /* Session receive handler for data packets. + * Each pseudowire implementation should implement this callback in order to + * handle incoming packets. Packets are passed to the pseudowire handler after + * reordering, if data sequence numbers are enabled for the session. + */ void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len); + + /* Session close handler. + * Each pseudowire implementation may implement this callback in order to carry + * out pseudowire-specific shutdown actions. + * The callback is called by core after unhashing the session and purging its + * reorder queue. + */ void (*session_close)(struct l2tp_session *session); + + /* Session show handler. + * Pseudowire-specific implementation of debugfs session rendering. + * The callback is called by l2tp_debugfs.c after rendering core session + * information. + */ void (*show)(struct seq_file *m, void *priv); + u8 priv[]; /* private data */ }; -/* Describes the tunnel. It contains info to track all the associated - * sessions so incoming packets can be sorted out - */ +/* L2TP tunnel configuration */ struct l2tp_tunnel_cfg { int debug; /* bitmask of debug message categories */ enum l2tp_encap_type encap; @@ -129,6 +148,12 @@ struct l2tp_tunnel_cfg { udp6_zero_rx_checksums:1; }; +/* Represents a tunnel instance. + * Tracks runtime state including IO statistics. + * Holds the tunnel socket (either passed from userspace or directly created by the kernel). + * Maintains a hashlist of sessions belonging to the tunnel instance. + * Is linked into a per-net list of tunnels. + */ struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ @@ -163,11 +188,24 @@ struct l2tp_tunnel { struct work_struct del_work; }; +/* Pseudowire ops callbacks for use with the l2tp genetlink interface */ struct l2tp_nl_cmd_ops { + /* The pseudowire session create callback is responsible for creating a session + * instance for a specific pseudowire type. + * It must call l2tp_session_create and l2tp_session_register to register the + * session instance, as well as carry out any pseudowire-specific initialisation. + * It must return >= 0 on success, or an appropriate negative errno value on failure. + */ int (*session_create)(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); - int (*session_delete)(struct l2tp_session *session); + + /* The pseudowire session delete callback is responsible for initiating the deletion + * of a session instance. + * It must call l2tp_session_delete, as well as carry out any pseudowire-specific + * teardown actions. + */ + void (*session_delete)(struct l2tp_session *session); }; static inline void *l2tp_session_priv(struct l2tp_session *session) @@ -175,73 +213,68 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) return &session->priv[0]; } +/* Tunnel and session refcounts */ +void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel); +void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel); +void l2tp_session_inc_refcount(struct l2tp_session *session); +void l2tp_session_dec_refcount(struct l2tp_session *session); + +/* Tunnel and session lookup. + * These functions take a reference on the instances they return, so + * the caller must ensure that the reference is dropped appropriately. + */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, u32 session_id); -void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); - struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); +/* Tunnel and session lifetime management. + * Creation of a new instance is a two-step process: create, then register. + * Destruction is triggered using the *_delete functions, and completes asynchronously. + */ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg); - void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); + struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel); +void l2tp_session_delete(struct l2tp_session *session); -void __l2tp_session_unhash(struct l2tp_session *session); -int l2tp_session_delete(struct l2tp_session *session); -void l2tp_session_free(struct l2tp_session *session); +/* Receive path helpers. If data sequencing is enabled for the session these + * functions handle queuing and reordering prior to passing packets to the + * pseudowire code to be passed to userspace. + */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, 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); +/* Transmit path helpers for sending packets over the tunnel socket. */ +void l2tp_session_set_header_len(struct l2tp_session *session, int version); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len); -int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, - const struct l2tp_nl_cmd_ops *ops); -void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); -int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); - -static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) -{ - refcount_inc(&tunnel->ref_count); -} - -static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) -{ - if (refcount_dec_and_test(&tunnel->ref_count)) - l2tp_tunnel_free(tunnel); -} - -/* Session reference counts. Incremented when code obtains a reference - * to a session. +/* Pseudowire management. + * Pseudowires should register with l2tp core on module init, and unregister + * on module exit. */ -static inline void l2tp_session_inc_refcount(struct l2tp_session *session) -{ - refcount_inc(&session->ref_count); -} +int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops); +void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); -static inline void l2tp_session_dec_refcount(struct l2tp_session *session) -{ - if (refcount_dec_and_test(&session->ref_count)) - l2tp_session_free(session); -} +/* IOCTL helper for IP encap modules. */ +int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index a159cb2bf0f4..df2a35b5714a 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -597,7 +597,7 @@ int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) return put_user(amount, (int __user *)arg); } -EXPORT_SYMBOL(l2tp_ioctl); +EXPORT_SYMBOL_GPL(l2tp_ioctl); static struct proto l2tp_ip_prot = { .name = "L2TP/IP", diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 35716a6e1e2c..def78eebca4c 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -670,7 +670,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf pw_type = session->pwtype; if (pw_type < __L2TP_PWTYPE_MAX) if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete) - ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session); + l2tp_nl_cmd_ops[pw_type]->session_delete(session); l2tp_session_dec_refcount(session); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 7f245e9f114c..313ba97acae3 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -477,7 +477,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len) { u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; - struct ieee802_11_elems elems = { 0 }; + struct ieee802_11_elems elems = { }; u8 dialog_token; int ies_len; diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 9fc2968856c0..366f76c9003d 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -551,7 +551,7 @@ EXPORT_SYMBOL_GPL(ieee80211_calc_tx_airtime); u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *pubsta, - int len) + int len, bool ampdu) { struct ieee80211_supported_band *sband; struct ieee80211_chanctx_conf *conf; @@ -572,10 +572,26 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, if (pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - - return ieee80211_calc_tx_airtime_rate(hw, - &sta->tx_stats.last_rate, - band, len); + struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate; + u32 airtime; + + if (!(rate->flags & (IEEE80211_TX_RC_VHT_MCS | + IEEE80211_TX_RC_MCS))) + ampdu = false; + + /* + * Assume that HT/VHT transmission on any AC except VO will + * use aggregation. Since we don't have reliable reporting + * of aggregation length, assume an average of 16. + * This will not be very accurate, but much better than simply + * assuming un-aggregated tx. + */ + airtime = ieee80211_calc_tx_airtime_rate(hw, rate, band, + ampdu ? len * 16 : len); + if (ampdu) + airtime /= 16; + + return airtime; } if (!conf) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 9b360544ad6f..87fddd84c621 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -608,12 +608,12 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, case WLAN_CIPHER_SUITE_BIP_CMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_cmac)); - /* fall through */ + fallthrough; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_gmac)); - /* fall through */ + fallthrough; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != @@ -991,9 +991,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | - BSS_CHANGED_TWT | - BSS_CHANGED_HE_OBSS_PD | - BSS_CHANGED_HE_BSS_COLOR; + BSS_CHANGED_TWT; int i, err; int prev_beacon_int; @@ -1019,6 +1017,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.frame_time_rts_th = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); + changed |= BSS_CHANGED_HE_OBSS_PD; + + if (params->he_bss_color.enabled) + changed |= BSS_CHANGED_HE_BSS_COLOR; } mutex_lock(&local->mtx); @@ -2126,6 +2128,11 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_GATE, mask)) conf->dot11MeshConnectedToMeshGate = nconf->dot11MeshConnectedToMeshGate; + if (_chg_mesh_attr(NL80211_MESHCONF_NOLEARN, mask)) + conf->dot11MeshNolearn = nconf->dot11MeshNolearn; + if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_AS, mask)) + conf->dot11MeshConnectedToAuthServer = + nconf->dot11MeshConnectedToAuthServer; ieee80211_mbss_info_change_notify(sdata, BSS_CHANGED_BEACON); return 0; } @@ -2166,6 +2173,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; @@ -2336,7 +2344,7 @@ static int ieee80211_scan(struct wiphy *wiphy, * for now fall through to allow scanning only when * beaconing hasn't been configured yet */ - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: /* * If the scan has been forced (and the driver supports @@ -3583,7 +3591,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, } local_bh_disable(); - ieee80211_xmit(sdata, sta, skb, 0); + ieee80211_xmit(sdata, sta, skb); local_bh_enable(); ret = 0; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index e6e192f53e4e..bdc0f29dc6cd 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -313,9 +313,14 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, lockdep_assert_held(&local->chanctx_mtx); - /* don't optimize 5MHz, 10MHz, and radar_enabled confs */ + /* don't optimize non-20MHz based and radar_enabled confs */ if (ctx->conf.def.width == NL80211_CHAN_WIDTH_5 || ctx->conf.def.width == NL80211_CHAN_WIDTH_10 || + ctx->conf.def.width == NL80211_CHAN_WIDTH_1 || + ctx->conf.def.width == NL80211_CHAN_WIDTH_2 || + ctx->conf.def.width == NL80211_CHAN_WIDTH_4 || + ctx->conf.def.width == NL80211_CHAN_WIDTH_8 || + ctx->conf.def.width == NL80211_CHAN_WIDTH_16 || ctx->conf.radar_enabled) { ctx->conf.min_def = ctx->conf.def; return; @@ -743,7 +748,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, default: WARN_ONCE(1, "Invalid SMPS mode %d\n", sdata->smps_mode); - /* fall through */ + fallthrough; case IEEE80211_SMPS_OFF: needed_static = sdata->needed_rx_chains; needed_dynamic = sdata->needed_rx_chains; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index d7e955127d5c..fe8a7a87e513 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -638,6 +638,9 @@ IEEE80211_IF_FILE(dot11MeshAwakeWindowDuration, u.mesh.mshcfg.dot11MeshAwakeWindowDuration, DEC); IEEE80211_IF_FILE(dot11MeshConnectedToMeshGate, u.mesh.mshcfg.dot11MeshConnectedToMeshGate, DEC); +IEEE80211_IF_FILE(dot11MeshNolearn, u.mesh.mshcfg.dot11MeshNolearn, DEC); +IEEE80211_IF_FILE(dot11MeshConnectedToAuthServer, + u.mesh.mshcfg.dot11MeshConnectedToAuthServer, DEC); #endif #define DEBUGFS_ADD_MODE(name, mode) \ @@ -762,6 +765,8 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata) MESHPARAMS_ADD(power_mode); MESHPARAMS_ADD(dot11MeshAwakeWindowDuration); MESHPARAMS_ADD(dot11MeshConnectedToMeshGate); + MESHPARAMS_ADD(dot11MeshNolearn); + MESHPARAMS_ADD(dot11MeshConnectedToAuthServer); #undef MESHPARAMS_ADD } #endif diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index de69fc9c4f07..41d495d73d3a 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -12,12 +12,11 @@ #include "ieee80211_i.h" #include "trace.h" -static inline bool check_sdata_in_driver(struct ieee80211_sub_if_data *sdata) -{ - return !WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER), - "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", - sdata->dev ? sdata->dev->name : sdata->name, sdata->flags); -} +#define check_sdata_in_driver(sdata) ({ \ + !WARN_ONCE(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER), \ + "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", \ + sdata->dev ? sdata->dev->name : sdata->name, sdata->flags); \ +}) static inline struct ieee80211_sub_if_data * get_bss_sdata(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index e32906202575..3d62a80b5790 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -250,7 +250,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.bss_conf.chandef.width) { default: WARN_ON_ONCE(1); - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: bw = IEEE80211_STA_RX_BW_20; @@ -517,7 +517,7 @@ int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, case IEEE80211_SMPS_AUTOMATIC: case IEEE80211_SMPS_NUM_MODES: WARN_ON(1); - /* fall through */ + fallthrough; case IEEE80211_SMPS_OFF: action_frame->u.action.u.ht_smps.smps_control = WLAN_HT_SMPS_CONTROL_DISABLED; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 81d26fef41e9..53632c2f5217 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -791,7 +791,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_20_NOHT: sta_flags |= IEEE80211_STA_DISABLE_HT; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_20: sta_flags |= IEEE80211_STA_DISABLE_40MHZ; break; @@ -1401,7 +1401,7 @@ ieee80211_ibss_setup_scan_channels(struct wiphy *wiphy, break; case NL80211_CHAN_WIDTH_80P80: cf2 = chandef->center_freq2; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_80: width = 80; break; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ec1a71ac65f2..0b1eaec6649f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -164,7 +164,6 @@ typedef unsigned __bitwise ieee80211_tx_result; #define TX_DROP ((__force ieee80211_tx_result) 1u) #define TX_QUEUED ((__force ieee80211_tx_result) 2u) -#define IEEE80211_TX_NO_SEQNO BIT(0) #define IEEE80211_TX_UNICAST BIT(1) #define IEEE80211_TX_PS_BUFFERED BIT(2) @@ -218,7 +217,7 @@ enum ieee80211_rx_flags { }; struct ieee80211_rx_data { - struct napi_struct *napi; + struct list_head *list; struct sk_buff *skb; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; @@ -1967,12 +1966,11 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, bool bss_notify, bool enable_qos); void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, struct sk_buff *skb, - u32 txdata_flags); + struct sta_info *sta, struct sk_buff *skb); void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, - enum nl80211_band band, u32 txdata_flags); + enum nl80211_band band); /* sta_out needs to be checked for ERR_PTR() before using */ int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, @@ -1982,10 +1980,10 @@ int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, static inline void ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, - enum nl80211_band band, u32 txdata_flags) + enum nl80211_band band) { rcu_read_lock(); - __ieee80211_tx_skb_tid_band(sdata, skb, tid, band, txdata_flags); + __ieee80211_tx_skb_tid_band(sdata, skb, tid, band); rcu_read_unlock(); } @@ -2003,7 +2001,7 @@ static inline void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, } __ieee80211_tx_skb_tid_band(sdata, skb, tid, - chanctx_conf->def.chan->band, 0); + chanctx_conf->def.chan->band); rcu_read_unlock(); } @@ -2290,7 +2288,7 @@ extern const struct ethtool_ops ieee80211_ethtool_ops; u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *pubsta, - int len); + int len, bool ampdu); #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline #else diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f900c84fb40f..9740ae8fa697 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -978,7 +978,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_P2P_DEVICE: /* relies on synchronize_rcu() below */ RCU_INIT_POINTER(local->p2p_sdata, NULL); - /* fall through */ + fallthrough; default: cancel_work_sync(&sdata->work); /* @@ -1048,7 +1048,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) break; - /* fall through */ + fallthrough; default: if (going_down) drv_remove_interface(local, sdata); @@ -1183,17 +1183,24 @@ static u16 ieee80211_monitor_select_queue(struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr; - struct ieee80211_radiotap_header *rtap = (void *)skb->data; + int len_rthdr; if (local->hw.queues < IEEE80211_NUM_ACS) return 0; - if (skb->len < 4 || - skb->len < le16_to_cpu(rtap->it_len) + 2 /* frame control */) + /* reset flags and info before parsing radiotap header */ + memset(info, 0, sizeof(*info)); + + if (!ieee80211_parse_tx_radiotap(skb, dev)) return 0; /* doesn't matter, frame will be dropped */ - hdr = (void *)((u8 *)skb->data + le16_to_cpu(rtap->it_len)); + len_rthdr = ieee80211_get_radiotap_len(skb->data); + hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); + if (skb->len < len_rthdr + 2 || + skb->len < len_rthdr + ieee80211_hdrlen(hdr->frame_control)) + return 0; /* doesn't matter, frame will be dropped */ return ieee80211_select_queue_80211(sdata, skb, hdr); } @@ -1497,7 +1504,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, type = NL80211_IFTYPE_AP; sdata->vif.type = type; sdata->vif.p2p = true; - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: skb_queue_head_init(&sdata->u.ap.ps.bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); @@ -1507,7 +1514,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, type = NL80211_IFTYPE_STATION; sdata->vif.type = type; sdata->vif.p2p = true; - /* fall through */ + fallthrough; case NL80211_IFTYPE_STATION: sdata->vif.bss_conf.bssid = sdata->u.mgd.bssid; ieee80211_sta_setup_sdata(sdata); @@ -1703,7 +1710,7 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, goto out_unlock; } } - /* fall through */ + fallthrough; default: /* assign a new address if possible -- try n_addresses first */ for (i = 0; i < local->hw.wiphy->n_addresses; i++) { diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 8f403c1bb908..9c2888004878 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -225,7 +225,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) */ if (sdata->hw_80211_encap) return -EINVAL; - /* Fall through */ + fallthrough; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5f1ca25b6c97..7ecd801a943b 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -260,6 +260,7 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, bool is_connected_to_gate = ifmsh->num_gates > 0 || ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol || ifmsh->mshcfg.dot11MeshConnectedToMeshGate; + bool is_connected_to_as = ifmsh->mshcfg.dot11MeshConnectedToAuthServer; if (skb_tailroom(skb) < 2 + meshconf_len) return -ENOMEM; @@ -284,7 +285,9 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, /* Mesh Formation Info - number of neighbors */ neighbors = atomic_read(&ifmsh->estab_plinks); neighbors = min_t(int, neighbors, IEEE80211_MAX_MESH_PEERINGS); - *pos++ = (neighbors << 1) | is_connected_to_gate; + *pos++ = (is_connected_to_as << 7) | + (neighbors << 1) | + is_connected_to_gate; /* Mesh capability */ *pos = 0x00; *pos |= ifmsh->mshcfg.dot11MeshForwarding ? @@ -617,6 +620,19 @@ int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { + struct ieee80211_supported_band *sband; + const struct ieee80211_sband_iftype_data *iftd; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + iftd = ieee80211_get_sband_iftype_data(sband, + NL80211_IFTYPE_MESH_POINT); + /* The device doesn't support HE in mesh mode or at all */ + if (!iftd) + return 0; + ieee80211_ie_build_he_6ghz_cap(sdata, skb); return 0; } @@ -1094,10 +1110,10 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.bss_conf.chandef.width) { case NL80211_CHAN_WIDTH_20_NOHT: sta_flags |= IEEE80211_STA_DISABLE_HT; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_20: sta_flags |= IEEE80211_STA_DISABLE_40MHZ; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_40: sta_flags |= IEEE80211_STA_DISABLE_VHT; break; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 02cde0fd08fe..bec23d2eee7a 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1173,6 +1173,40 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, } /** + * mesh_nexthop_lookup_nolearn - try to set next hop without path discovery + * @skb: 802.11 frame to be sent + * @sdata: network subif the frame will be sent through + * + * Check if the meshDA (addr3) of a unicast frame is a direct neighbor. + * And if so, set the RA (addr1) to it to transmit to this node directly, + * avoiding PREQ/PREP path discovery. + * + * Returns: 0 if the next hop was found and -ENOENT otherwise. + */ +static int mesh_nexthop_lookup_nolearn(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct sta_info *sta; + + if (is_multicast_ether_addr(hdr->addr1)) + return -ENOENT; + + rcu_read_lock(); + sta = sta_info_get(sdata, hdr->addr3); + + if (!sta || sta->mesh->plink_state != NL80211_PLINK_ESTAB) { + rcu_read_unlock(); + return -ENOENT; + } + rcu_read_unlock(); + + memcpy(hdr->addr1, hdr->addr3, ETH_ALEN); + memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); + return 0; +} + +/** * mesh_nexthop_lookup - put the appropriate next hop on a mesh frame. Calling * this function is considered "using" the associated mpath, so preempt a path * refresh if this mpath expires soon. @@ -1185,11 +1219,16 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, int mesh_nexthop_lookup(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_path *mpath; struct sta_info *next_hop; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; u8 *target_addr = hdr->addr3; + if (ifmsh->mshcfg.dot11MeshNolearn && + !mesh_nexthop_lookup_nolearn(sdata, skb)) + return 0; + mpath = mesh_path_lookup(sdata, target_addr); if (!mpath || !(mpath->flags & MESH_PATH_ACTIVE)) return -ENOENT; @@ -1266,7 +1305,7 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) break; case IEEE80211_PROACTIVE_PREQ_WITH_PREP: flags |= IEEE80211_PREQ_PROACTIVE_PREP_FLAG; - /* fall through */ + fallthrough; case IEEE80211_PROACTIVE_PREQ_NO_PREP: interval = ifmsh->mshcfg.dot11MeshHWMPactivePathToRootTimeout; target_flags |= IEEE80211_PREQ_TO_FLAG | diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index fe4e853c61f4..48f31ac9233c 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -519,6 +519,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, del_timer_sync(&mpath->timer); atomic_dec(&sdata->u.mesh.mpaths); atomic_dec(&tbl->entries); + mesh_path_flush_pending(mpath); kfree_rcu(mpath, rcu); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 798e4b6b383f..15f2fc658f70 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -699,7 +699,7 @@ void mesh_plink_timer(struct timer_list *t) break; } reason = WLAN_REASON_MESH_MAX_RETRIES; - /* fall through */ + fallthrough; case NL80211_PLINK_CNF_RCVD: /* confirm timer */ if (!reason) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index b2a9d47cf86d..ac870309b911 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -533,7 +533,7 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, case IEEE80211_SMPS_AUTOMATIC: case IEEE80211_SMPS_NUM_MODES: WARN_ON(1); - /* fall through */ + fallthrough; case IEEE80211_SMPS_OFF: cap |= WLAN_HT_CAP_SM_PS_DISABLED << IEEE80211_HT_CAP_SM_PS_SHIFT; @@ -1529,7 +1529,7 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata, switch (channel->band) { default: WARN_ON_ONCE(1); - /* fall through */ + fallthrough; case NL80211_BAND_2GHZ: case NL80211_BAND_60GHZ: chan_increment = 1; @@ -2988,7 +2988,10 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); if (auth_alg == WLAN_AUTH_SAE && - status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED) + (status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED || + (auth_transaction == 1 && + (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT || + status_code == WLAN_STATUS_SAE_PK)))) return; sdata_info(sdata, "%pM denied authentication (status %d)\n", @@ -3460,10 +3463,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, bss_conf->he_bss_color.partial = le32_get_bits(elems->he_operation->he_oper_params, IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR); - bss_conf->he_bss_color.disabled = - le32_get_bits(elems->he_operation->he_oper_params, - IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); - changed |= BSS_CHANGED_HE_BSS_COLOR; + bss_conf->he_bss_color.enabled = + !le32_get_bits(elems->he_operation->he_oper_params, + IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); + + if (bss_conf->he_bss_color.enabled) + changed |= BSS_CHANGED_HE_BSS_COLOR; bss_conf->htc_trig_based_pkt_ext = le32_get_bits(elems->he_operation->he_oper_params, @@ -4558,6 +4563,9 @@ static void ieee80211_sta_bcn_mon_timer(struct timer_list *t) if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn) return; + if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER) + return; + sdata->u.mgd.connection_loss = false; ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.beacon_connection_loss_work); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index db3b8bf75656..f470d1a7ce9b 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -264,7 +264,7 @@ static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, if (roc->mgmt_tx_cookie) { if (!WARN_ON(!roc->frame)) { ieee80211_tx_skb_tid_band(roc->sdata, roc->frame, 7, - roc->chan->band, 0); + roc->chan->band); roc->frame = NULL; } } else { @@ -808,13 +808,13 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, if (!sdata->vif.bss_conf.ibss_joined) need_offchan = true; #ifdef CONFIG_MAC80211_MESH - /* fall through */ + fallthrough; case NL80211_IFTYPE_MESH_POINT: if (ieee80211_vif_is_mesh(&sdata->vif) && !sdata->u.mesh.mesh_id_len) need_offchan = true; #endif - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_P2P_GO: diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5c5af4b5fc08..836cde516a18 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2578,8 +2578,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, memset(skb->cb, 0, sizeof(skb->cb)); /* deliver to local stack */ - if (rx->napi) - napi_gro_receive(rx->napi, skb); + if (rx->list) + list_add_tail(&skb->list, rx->list); else netif_receive_skb(skb); } @@ -3591,7 +3591,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) } __ieee80211_tx_skb_tid_band(rx->sdata, nskb, 7, - status->band, 0); + status->band); } dev_kfree_skb(rx->skb); return RX_QUEUED; @@ -3736,7 +3736,7 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx, I802_DEBUG_INC(rx->sdata->local->rx_handlers_drop); if (rx->sta) rx->sta->rx_stats.dropped++; - /* fall through */ + fallthrough; case RX_CONTINUE: { struct ieee80211_rate *rate = NULL; struct ieee80211_supported_band *sband; @@ -3869,7 +3869,6 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .napi = NULL, /* must be NULL to not have races */ }; struct tid_ampdu_rx *tid_agg_rx; @@ -4479,8 +4478,8 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, /* deliver to local stack */ skb->protocol = eth_type_trans(skb, fast_rx->dev); memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->napi) - napi_gro_receive(rx->napi, skb); + if (rx->list) + list_add_tail(&skb->list, rx->list); else netif_receive_skb(skb); @@ -4547,7 +4546,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct sk_buff *skb, - struct napi_struct *napi) + struct list_head *list) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; @@ -4562,7 +4561,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, memset(&rx, 0, sizeof(rx)); rx.skb = skb; rx.local = local; - rx.napi = napi; + rx.list = list; if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) I802_DEBUG_INC(local->dot11ReceivedFragmentCount); @@ -4670,8 +4669,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, * This is the receive path handler. It is called by a low level driver when an * 802.11 MPDU is received from the hardware. */ -void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, - struct sk_buff *skb, struct napi_struct *napi) +void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, + struct sk_buff *skb, struct list_head *list) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_rate *rate = NULL; @@ -4752,7 +4751,7 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, break; default: WARN_ON_ONCE(1); - /* fall through */ + fallthrough; case RX_ENC_LEGACY: if (WARN_ON(status->rate_idx >= sband->n_bitrates)) goto drop; @@ -4763,36 +4762,53 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, status->rx_flags = 0; /* - * key references and virtual interfaces are protected using RCU - * and this requires that we are in a read-side RCU section during - * receive processing - */ - rcu_read_lock(); - - /* * Frames with failed FCS/PLCP checksum are not returned, * all other frames are returned without radiotap header * if it was previously present. * Also, frames with less than 16 bytes are dropped. */ skb = ieee80211_rx_monitor(local, skb, rate); - if (!skb) { - rcu_read_unlock(); + if (!skb) return; - } ieee80211_tpt_led_trig_rx(local, ((struct ieee80211_hdr *)skb->data)->frame_control, skb->len); - __ieee80211_rx_handle_packet(hw, pubsta, skb, napi); - - rcu_read_unlock(); + __ieee80211_rx_handle_packet(hw, pubsta, skb, list); return; drop: kfree_skb(skb); } +EXPORT_SYMBOL(ieee80211_rx_list); + +void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, + struct sk_buff *skb, struct napi_struct *napi) +{ + struct sk_buff *tmp; + LIST_HEAD(list); + + + /* + * key references and virtual interfaces are protected using RCU + * and this requires that we are in a read-side RCU section during + * receive processing + */ + rcu_read_lock(); + ieee80211_rx_list(hw, pubsta, skb, &list); + rcu_read_unlock(); + + if (!napi) { + netif_receive_skb_list(&list); + return; + } + + list_for_each_entry_safe(skb, tmp, &list, list) { + skb_list_del_init(skb); + napi_gro_receive(napi, skb); + } +} EXPORT_SYMBOL(ieee80211_rx_napi); /* This is a version of the rx handler that can be called from hard irq diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index ad90bbe57457..5ac2785cdc7b 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -591,7 +591,6 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel) { struct sk_buff *skb; - u32 txdata_flags = 0; skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel, ssid, ssid_len, @@ -600,15 +599,15 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, if (skb) { if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { struct ieee80211_hdr *hdr = (void *)skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u16 sn = get_random_u32(); - txdata_flags |= IEEE80211_TX_NO_SEQNO; + info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; hdr->seq_ctrl = cpu_to_le16(IEEE80211_SN_TO_SEQ(sn)); } IEEE80211_SKB_CB(skb)->flags |= tx_flags; - ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band, - txdata_flags); + ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); } } @@ -913,6 +912,7 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, case NL80211_BSS_CHAN_WIDTH_10: local->scan_chandef.width = NL80211_CHAN_WIDTH_10; break; + default: case NL80211_BSS_CHAN_WIDTH_20: /* If scanning on oper channel, use whatever channel-type * is currently in use. diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index cd8487bc6fc2..f2840d1d95cf 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1050,7 +1050,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) might_sleep(); lockdep_assert_held(&local->sta_mtx); - while (sta->sta_state == IEEE80211_STA_AUTHORIZED) { + if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); WARN_ON_ONCE(ret); } @@ -1455,7 +1455,7 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, } info->band = chanctx_conf->def.chan->band; - ieee80211_xmit(sdata, sta, skb, 0); + ieee80211_xmit(sdata, sta, skb); rcu_read_unlock(); } @@ -1923,9 +1923,7 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, if (sta) { tx_pending = atomic_sub_return(tx_airtime, &sta->airtime[ac].aql_tx_pending); - if (WARN_ONCE(tx_pending < 0, - "STA %pM AC %d txq pending airtime underflow: %u, %u", - sta->addr, ac, tx_pending, tx_airtime)) + if (tx_pending < 0) atomic_cmpxchg(&sta->airtime[ac].aql_tx_pending, tx_pending, 0); } @@ -2426,7 +2424,8 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, BIT_ULL(NL80211_STA_INFO_LOCAL_PM) | BIT_ULL(NL80211_STA_INFO_PEER_PM) | BIT_ULL(NL80211_STA_INFO_NONPEER_PM) | - BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_GATE); + BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_GATE) | + BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_AS); sinfo->llid = sta->mesh->llid; sinfo->plid = sta->mesh->plid; @@ -2439,6 +2438,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->peer_pm = sta->mesh->peer_pm; sinfo->nonpeer_pm = sta->mesh->nonpeer_pm; sinfo->connected_to_gate = sta->mesh->connected_to_gate; + sinfo->connected_to_as = sta->mesh->connected_to_as; #endif } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 49728047dfad..9d398c9daa4c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -385,6 +385,7 @@ DECLARE_EWMA(mesh_tx_rate_avg, 8, 16) * @processed_beacon: set to true after peer rates and capabilities are * processed * @connected_to_gate: true if mesh STA has a path to a mesh gate + * @connected_to_as: true if mesh STA has a path to a authentication server * @fail_avg: moving percentage of failed MSDUs * @tx_rate_avg: moving average of tx bitrate */ @@ -404,6 +405,7 @@ struct mesh_sta { bool processed_beacon; bool connected_to_gate; + bool connected_to_as; enum nl80211_plink_state plink_state; u32 plink_timeout; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index cbc40b358ba2..adb1d30ce06e 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -799,7 +799,6 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, int *retry_count) { - int rates_idx = -1; int count = -1; int i; @@ -821,13 +820,12 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw, count += info->status.rates[i].count; } - rates_idx = i - 1; if (count < 0) count = 0; *retry_count = count; - return rates_idx; + return i - 1; } void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 4b0cff4a07bd..e01e4daeb8cd 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -239,7 +239,7 @@ static enum ieee80211_ac_numbers ieee80211_ac_from_wmm(int ac) switch (ac) { default: WARN_ON_ONCE(1); - /* fall through */ + fallthrough; case 0: return IEEE80211_AC_BE; case 1: @@ -952,7 +952,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, set_sta_flag(sta, WLAN_STA_TDLS_INITIATOR); sta->sta.tdls_initiator = false; } - /* fall-through */ + fallthrough; case WLAN_TDLS_SETUP_CONFIRM: case WLAN_TDLS_DISCOVERY_REQUEST: initiator = true; @@ -967,7 +967,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, clear_sta_flag(sta, WLAN_STA_TDLS_INITIATOR); sta->sta.tdls_initiator = true; } - /* fall-through */ + fallthrough; case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: initiator = false; break; @@ -1222,7 +1222,7 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, * by the AP. */ drv_mgd_protect_tdls_discover(sdata->local, sdata); - /* fall-through */ + fallthrough; case WLAN_TDLS_SETUP_CONFIRM: case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: /* no special handling */ diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 1b4709694d2a..50ab5b9d8eab 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -22,7 +22,8 @@ #define LOCAL_PR_ARG __entry->wiphy_name #define STA_ENTRY __array(char, sta_addr, ETH_ALEN) -#define STA_ASSIGN (sta ? memcpy(__entry->sta_addr, sta->addr, ETH_ALEN) : memset(__entry->sta_addr, 0, ETH_ALEN)) +#define STA_ASSIGN (sta ? memcpy(__entry->sta_addr, sta->addr, ETH_ALEN) : \ + eth_zero_addr(__entry->sta_addr)) #define STA_NAMED_ASSIGN(s) memcpy(__entry->sta_addr, (s)->addr, ETH_ALEN) #define STA_PR_FMT " sta:%pM" #define STA_PR_ARG __entry->sta_addr diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a2941e5244f..dca01d7e6e3e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -166,6 +166,7 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, if (r->flags & IEEE80211_RATE_MANDATORY_A) mrate = r->bitrate; break; + case NL80211_BAND_S1GHZ: case NL80211_BAND_60GHZ: /* TODO, for now fall through */ case NUM_NL80211_BANDS: @@ -824,6 +825,9 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) if (ieee80211_is_qos_nullfunc(hdr->frame_control)) return TX_CONTINUE; + if (info->control.flags & IEEE80211_TX_CTRL_NO_SEQNO) + return TX_CONTINUE; + /* * Anything but QoS data that has a sequence number field * (is long enough) gets a sequence number from the global @@ -832,8 +836,6 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) */ if (!ieee80211_is_data_qos(hdr->frame_control) || is_multicast_ether_addr(hdr->addr1)) { - if (tx->flags & IEEE80211_TX_NO_SEQNO) - return TX_CONTINUE; /* driver should assign sequence number */ info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; /* for pure STA mode without beacons, we can do it */ @@ -1739,7 +1741,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, case NL80211_IFTYPE_AP_VLAN: sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); - /* fall through */ + fallthrough; default: vif = &sdata->vif; break; @@ -1890,7 +1892,7 @@ EXPORT_SYMBOL(ieee80211_tx_prepare_skb); */ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct sk_buff *skb, - bool txpending, u32 txdata_flags) + bool txpending) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_data tx; @@ -1908,8 +1910,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, led_len = skb->len; res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb); - tx.flags |= txdata_flags; - if (unlikely(res_prepare == TX_DROP)) { ieee80211_free_txskb(&local->hw, skb); return true; @@ -1977,8 +1977,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, } void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, struct sk_buff *skb, - u32 txdata_flags) + struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -2013,12 +2012,13 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, } ieee80211_set_qos_hdr(sdata, skb); - ieee80211_tx(sdata, sta, skb, false, txdata_flags); + ieee80211_tx(sdata, sta, skb, false); } -static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, - struct sk_buff *skb) +bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, + struct net_device *dev) { + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_radiotap_iterator iterator; struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; @@ -2037,6 +2037,18 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, u8 vht_mcs = 0, vht_nss = 0; int i; + /* check for not even having the fixed radiotap header part */ + if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) + return false; /* too short to be possibly valid */ + + /* is it a header version we can trust to find length from? */ + if (unlikely(rthdr->it_version)) + return false; /* only version 0 is supported */ + + /* does the skb contain enough to deliver on the alleged length? */ + if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) + return false; /* skb too short for claimed rt header extent */ + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -2084,6 +2096,8 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, txflags = get_unaligned_le16(iterator.this_arg); if (txflags & IEEE80211_RADIOTAP_F_TX_NOACK) info->flags |= IEEE80211_TX_CTL_NO_ACK; + if (txflags & IEEE80211_RADIOTAP_F_TX_NOSEQNO) + info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; break; case IEEE80211_RADIOTAP_RATE: @@ -2188,13 +2202,6 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, local->hw.max_rate_tries); } - /* - * remove the radiotap header - * iterator->_max_length was sanity-checked against - * skb->len by iterator init - */ - skb_pull(skb, iterator._max_length); - return true; } @@ -2203,8 +2210,6 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_radiotap_header *prthdr = - (struct ieee80211_radiotap_header *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr; struct ieee80211_sub_if_data *tmp_sdata, *sdata; @@ -2212,21 +2217,17 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, u16 len_rthdr; int hdrlen; - /* check for not even having the fixed radiotap header part */ - if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) - goto fail; /* too short to be possibly valid */ + memset(info, 0, sizeof(*info)); + info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | + IEEE80211_TX_CTL_INJECTED; - /* is it a header version we can trust to find length from? */ - if (unlikely(prthdr->it_version)) - goto fail; /* only version 0 is supported */ + /* Sanity-check and process the injection radiotap header */ + if (!ieee80211_parse_tx_radiotap(skb, dev)) + goto fail; - /* then there must be a radiotap header with a length we can use */ + /* we now know there is a radiotap header with a length we can use */ len_rthdr = ieee80211_get_radiotap_len(skb->data); - /* does the skb contain enough to deliver on the alleged length? */ - if (unlikely(skb->len < len_rthdr)) - goto fail; /* skb too short for claimed rt header extent */ - /* * fix up the pointers accounting for the radiotap * header still being in there. We are being given @@ -2272,11 +2273,6 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; } - memset(info, 0, sizeof(*info)); - - info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | - IEEE80211_TX_CTL_INJECTED; - rcu_read_lock(); /* @@ -2342,11 +2338,10 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, info->band = chandef->chan->band; - /* process and remove the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(local, skb)) - goto fail_rcu; + /* remove the injection radiotap header */ + skb_pull(skb, len_rthdr); - ieee80211_xmit(sdata, NULL, skb, 0); + ieee80211_xmit(sdata, NULL, skb); rcu_read_unlock(); return NETDEV_TX_OK; @@ -2382,7 +2377,7 @@ int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, } else if (sdata->wdev.use_4addr) { return -ENOLINK; } - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_ADHOC: @@ -2552,7 +2547,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, band = chanctx_conf->def.chan->band; if (sdata->wdev.use_4addr) break; - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: if (sdata->vif.type == NL80211_IFTYPE_AP) chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); @@ -2999,7 +2994,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) build.hdr_len = 30; break; } - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); /* DA BSSID SA */ @@ -3618,7 +3613,7 @@ begin: tx.skb = skb; tx.sdata = vif_to_sdata(info->control.vif); - if (txq->sta) { + if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) { tx.sta = container_of(txq->sta, struct sta_info, sta); /* * Drop unicast frames to unauthorised stations unless they are @@ -3710,7 +3705,7 @@ begin: case NL80211_IFTYPE_AP_VLAN: tx.sdata = container_of(tx.sdata->bss, struct ieee80211_sub_if_data, u.ap); - /* fall through */ + fallthrough; default: vif = &tx.sdata->vif; break; @@ -3721,10 +3716,11 @@ encap_out: if (vif && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { + bool ampdu = txq->ac != IEEE80211_AC_VO; u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, - skb->len); + skb->len, ampdu); if (airtime) { airtime = ieee80211_info_set_tx_time_est(info, airtime); ieee80211_sta_update_pending_airtime(local, tx.sta, @@ -3950,6 +3946,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (local->ops->wake_tx_queue) { u16 queue = __ieee80211_select_queue(sdata, sta, skb); skb_set_queue_mapping(skb, queue); + skb_get_hash(skb); } if (sta) { @@ -4008,7 +4005,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, ieee80211_tx_stats(dev, skb->len); - ieee80211_xmit(sdata, sta, skb, 0); + ieee80211_xmit(sdata, sta, skb); } goto out; out_free: @@ -4049,7 +4046,7 @@ static bool ieee80211_multicast_to_unicast(struct sk_buff *skb, return false; if (sdata->wdev.use_4addr) return false; - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: /* check runtime toggle for this bss */ if (!sdata->bss->multicast_to_unicast) @@ -4230,11 +4227,12 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) goto out_free; + memset(info, 0, sizeof(*info)); + if (unlikely(!multicast && skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) - ieee80211_store_ack_skb(local, skb, &info->flags, NULL); - - memset(info, 0, sizeof(*info)); + info->ack_frame_id = ieee80211_store_ack_skb(local, skb, + &info->flags, NULL); if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) { if (sdata->control_port_no_encrypt) @@ -4374,7 +4372,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, return true; } info->band = chanctx_conf->def.chan->band; - result = ieee80211_tx(sdata, NULL, skb, true, 0); + result = ieee80211_tx(sdata, NULL, skb, true); } else if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) { if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { dev_kfree_skb(skb); @@ -5333,7 +5331,7 @@ EXPORT_SYMBOL(ieee80211_unreserve_tid); void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, - enum nl80211_band band, u32 txdata_flags) + enum nl80211_band band) { int ac = ieee80211_ac_from_tid(tid); @@ -5350,7 +5348,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, */ local_bh_disable(); IEEE80211_SKB_CB(skb)->band = band; - ieee80211_xmit(sdata, NULL, skb, txdata_flags); + ieee80211_xmit(sdata, NULL, skb); local_bh_enable(); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 21c94094a699..c8504ffc71a1 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2347,10 +2347,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_ADHOC: if (sdata->vif.bss_conf.ibss_joined) WARN_ON(drv_join_ibss(local, sdata)); - /* fall through */ + fallthrough; default: ieee80211_reconfig_stations(sdata); - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: /* AP stations are handled later */ for (i = 0; i < IEEE80211_NUM_ACS; i++) drv_conf_tx(local, sdata, i, @@ -2399,7 +2399,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) break; case NL80211_IFTYPE_ADHOC: changed |= BSS_CHANGED_IBSS; - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: changed |= BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS; @@ -2414,8 +2414,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (rcu_access_pointer(sdata->u.ap.beacon)) drv_start_ap(local, sdata); } - - /* fall through */ + fallthrough; case NL80211_IFTYPE_MESH_POINT: if (sdata->vif.bss_conf.enable_beacon) { changed |= BSS_CHANGED_BEACON | @@ -2878,6 +2877,10 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!iftd)) return; + /* Check for device HE 6 GHz capability before adding element */ + if (!iftd->he_6ghz_capa.capa) + return; + cap = le16_to_cpu(iftd->he_6ghz_capa.capa); cap &= ~IEEE80211_HE_6GHZ_CAP_SM_PS; @@ -2885,7 +2888,7 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, case IEEE80211_SMPS_AUTOMATIC: case IEEE80211_SMPS_NUM_MODES: WARN_ON(1); - /* fall through */ + fallthrough; case IEEE80211_SMPS_OFF: cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_DISABLED, IEEE80211_HE_6GHZ_CAP_SM_PS); @@ -3196,7 +3199,7 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info, break; case 0x01: support_80_80 = false; - /* fall through */ + fallthrough; case 0x02: case 0x03: ccf1 = ccfs2; @@ -3566,7 +3569,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, break; default: WARN_ON(1); - /* fall through */ + fallthrough; case RX_ENC_LEGACY: { struct ieee80211_supported_band *sband; int shift = 0; @@ -3730,6 +3733,11 @@ u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c) c->width = NL80211_CHAN_WIDTH_20_NOHT; ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; break; + case NL80211_CHAN_WIDTH_1: + case NL80211_CHAN_WIDTH_2: + case NL80211_CHAN_WIDTH_4: + case NL80211_CHAN_WIDTH_8: + case NL80211_CHAN_WIDTH_16: case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: WARN_ON_ONCE(1); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 72920d82928c..2fb99325135a 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -198,7 +198,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, sta = rcu_dereference(sdata->u.vlan.sta); if (sta) break; - /* fall through */ + fallthrough; case NL80211_IFTYPE_AP: ra = skb->data; break; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index fd30ea61336e..6fdd0c9f865a 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1584,21 +1584,10 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, unsigned int flags; if (event == NETDEV_REGISTER) { + mdev = mpls_add_dev(dev); + if (IS_ERR(mdev)) + return notifier_from_errno(PTR_ERR(mdev)); - /* For now just support Ethernet, IPGRE, IP6GRE, SIT and - * IPIP devices - */ - if (dev->type == ARPHRD_ETHER || - dev->type == ARPHRD_LOOPBACK || - dev->type == ARPHRD_IPGRE || - dev->type == ARPHRD_IP6GRE || - dev->type == ARPHRD_SIT || - dev->type == ARPHRD_TUNNEL || - dev->type == ARPHRD_TUNNEL6) { - mdev = mpls_add_dev(dev); - if (IS_ERR(mdev)) - return notifier_from_errno(PTR_ERR(mdev)); - } return NOTIFY_OK; } diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index 2360cbd27d59..a611968be4d7 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ mib.o pm_netlink.o +obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o mptcp_crypto_test-objs := crypto_test.o diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 8e39585d37f3..54b888f94009 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -112,6 +112,7 @@ static struct pernet_operations mptcp_pernet_ops = { void __init mptcp_init(void) { + mptcp_join_cookie_init(); mptcp_proto_init(); if (register_pernet_subsys(&mptcp_pernet_ops) < 0) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 3bc56eb608d8..7fa822b55c34 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -451,6 +451,8 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_ext *ext) { + u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq); + if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values * if DATA_FIN is set but no data payload is mapped @@ -458,10 +460,13 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, ext->data_fin = 1; ext->use_map = 1; ext->dsn64 = 1; - ext->data_seq = subflow->data_fin_tx_seq; + /* The write_seq value has already been incremented, so + * the actual sequence number for the DATA_FIN is one less. + */ + ext->data_seq = data_fin_tx_seq - 1; ext->subflow_seq = 0; ext->data_len = 1; - } else if (ext->data_seq + ext->data_len == subflow->data_fin_tx_seq) { + } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { /* If there's an existing DSS mapping and it is the * final mapping, DATA_FIN consumes 1 additional byte of * mapping space. @@ -477,22 +482,17 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int dss_size = 0; + u64 snd_data_fin_enable; struct mptcp_ext *mpext; - struct mptcp_sock *msk; unsigned int ack_size; bool ret = false; - u8 tcp_fin; - if (skb) { - mpext = mptcp_get_ext(skb); - tcp_fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - } else { - mpext = NULL; - tcp_fin = 0; - } + mpext = skb ? mptcp_get_ext(skb) : NULL; + snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable); - if (!skb || (mpext && mpext->use_map) || tcp_fin) { + if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size; map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; @@ -502,7 +502,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (mpext) opts->ext_copy = *mpext; - if (skb && tcp_fin && subflow->data_fin_tx_enable) + if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; } @@ -511,7 +511,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, * if the first subflow may have the already the remote key handy */ opts->ext_copy.use_ack = 0; - msk = mptcp_sk(subflow->conn); if (!READ_ONCE(msk->can_ack)) { *size = ALIGN(dss_size, 4); return ret; @@ -783,6 +782,22 @@ static void update_una(struct mptcp_sock *msk, } } +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq) +{ + /* Skip if DATA_FIN was already received. + * If updating simultaneously with the recvmsg loop, values + * should match. If they mismatch, the peer is misbehaving and + * we will prefer the most recent information. + */ + if (READ_ONCE(msk->rcv_data_fin) || !READ_ONCE(msk->first)) + return false; + + WRITE_ONCE(msk->rcv_data_fin_seq, data_fin_seq); + WRITE_ONCE(msk->rcv_data_fin, 1); + + return true; +} + static bool add_addr_hmac_valid(struct mptcp_sock *msk, struct mptcp_options_received *mp_opt) { @@ -853,6 +868,20 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, if (mp_opt.use_ack) update_una(msk, &mp_opt); + /* Zero-data-length packets are dropped by the caller and not + * propagated to the MPTCP layer, so the skb extension does not + * need to be allocated or populated. DATA_FIN information, if + * present, needs to be updated here before the skb is freed. + */ + if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { + if (mp_opt.data_fin && mp_opt.data_len == 1 && + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq) && + schedule_work(&msk->work)) + sock_hold(subflow->conn); + + return; + } + mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) return; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2891ae8a1028..8c1d1a595701 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -16,6 +16,7 @@ #include <net/inet_hashtables.h> #include <net/protocol.h> #include <net/tcp.h> +#include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> #endif @@ -142,6 +143,14 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, MPTCP_SKB_CB(skb)->offset = offset; } +static void mptcp_stop_timer(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + mptcp_sk(sk)->timer_ival = 0; +} + /* both sockets must be locked */ static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk, struct sock *ssk) @@ -163,6 +172,139 @@ static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk, return mptcp_subflow_data_available(ssk); } +static void mptcp_check_data_fin_ack(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (__mptcp_check_fallback(msk)) + return; + + /* Look for an acknowledged DATA_FIN */ + if (((1 << sk->sk_state) & + (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && + msk->write_seq == atomic64_read(&msk->snd_una)) { + mptcp_stop_timer(sk); + + WRITE_ONCE(msk->snd_data_fin_enable, 0); + + switch (sk->sk_state) { + case TCP_FIN_WAIT1: + inet_sk_state_store(sk, TCP_FIN_WAIT2); + sk->sk_state_change(sk); + break; + case TCP_CLOSING: + fallthrough; + case TCP_LAST_ACK: + inet_sk_state_store(sk, TCP_CLOSE); + sk->sk_state_change(sk); + break; + } + + if (sk->sk_shutdown == SHUTDOWN_MASK || + sk->sk_state == TCP_CLOSE) + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + else + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + } +} + +static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (READ_ONCE(msk->rcv_data_fin) && + ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) { + u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq); + + if (msk->ack_seq == rcv_data_fin_seq) { + if (seq) + *seq = rcv_data_fin_seq; + + return true; + } + } + + return false; +} + +static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) +{ + long tout = ssk && inet_csk(ssk)->icsk_pending ? + inet_csk(ssk)->icsk_timeout - jiffies : 0; + + if (tout <= 0) + tout = mptcp_sk(sk)->timer_ival; + mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; +} + +static void mptcp_check_data_fin(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + u64 rcv_data_fin_seq; + + if (__mptcp_check_fallback(msk) || !msk->first) + return; + + /* Need to ack a DATA_FIN received from a peer while this side + * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. + * msk->rcv_data_fin was set when parsing the incoming options + * at the subflow level and the msk lock was not held, so this + * is the first opportunity to act on the DATA_FIN and change + * the msk state. + * + * If we are caught up to the sequence number of the incoming + * DATA_FIN, send the DATA_ACK now and do state transition. If + * not caught up, do nothing and let the recv code send DATA_ACK + * when catching up. + */ + + if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { + struct mptcp_subflow_context *subflow; + + msk->ack_seq++; + WRITE_ONCE(msk->rcv_data_fin, 0); + + sk->sk_shutdown |= RCV_SHUTDOWN; + smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ + set_bit(MPTCP_DATA_READY, &msk->flags); + + switch (sk->sk_state) { + case TCP_ESTABLISHED: + inet_sk_state_store(sk, TCP_CLOSE_WAIT); + break; + case TCP_FIN_WAIT1: + inet_sk_state_store(sk, TCP_CLOSING); + break; + case TCP_FIN_WAIT2: + inet_sk_state_store(sk, TCP_CLOSE); + // @@ Close subflows now? + break; + default: + /* Other states not expected */ + WARN_ON_ONCE(1); + break; + } + + mptcp_set_timeout(sk, NULL); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + lock_sock(ssk); + tcp_send_ack(ssk); + release_sock(ssk); + } + + sk->sk_state_change(sk); + + if (sk->sk_shutdown == SHUTDOWN_MASK || + sk->sk_state == TCP_CLOSE) + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + else + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + } +} + static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sock *ssk, unsigned int *bytes) @@ -239,6 +381,15 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, *bytes = moved; + /* If the moves have caught up with the DATA_FIN sequence number + * it's time to ack the DATA_FIN and change socket state, but + * this is not a good place to change state. Let the workqueue + * do it. + */ + if (mptcp_pending_data_fin(sk, NULL) && + schedule_work(&msk->work)) + sock_hold(sk); + return done; } @@ -303,16 +454,6 @@ static void __mptcp_flush_join_list(struct mptcp_sock *msk) spin_unlock_bh(&msk->join_list_lock); } -static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) -{ - long tout = ssk && inet_csk(ssk)->icsk_pending ? - inet_csk(ssk)->icsk_timeout - jiffies : 0; - - if (tout <= 0) - tout = mptcp_sk(sk)->timer_ival; - mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; -} - static bool mptcp_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); @@ -334,7 +475,8 @@ void mptcp_data_acked(struct sock *sk) { mptcp_reset_timer(sk); - if (!sk_stream_is_writeable(sk) && + if ((!sk_stream_is_writeable(sk) || + (inet_sk_state_load(sk) != TCP_ESTABLISHED)) && schedule_work(&mptcp_sk(sk)->work)) sock_hold(sk); } @@ -369,14 +511,6 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) } } -static void mptcp_stop_timer(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); - mptcp_sk(sk)->timer_ival = 0; -} - static bool mptcp_ext_cache_refill(struct mptcp_sock *msk) { const struct sock *sk = (const struct sock *)msk; @@ -659,7 +793,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, out: if (!retransmission) pfrag->offset += frag_truesize; - *write_seq += ret; + WRITE_ONCE(*write_seq, *write_seq + ret); mptcp_subflow_ctx(ssk)->rel_write_seq += ret; return ret; @@ -748,6 +882,11 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) restart: mptcp_clean_una(sk); + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) { + ret = -EPIPE; + goto out; + } + wait_for_sndbuf: __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); @@ -845,7 +984,6 @@ wait_for_sndbuf: mptcp_set_timeout(sk, ssk); if (copied) { - ret = copied; tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle, size_goal); @@ -858,7 +996,7 @@ wait_for_sndbuf: release_sock(ssk); out: release_sock(sk); - return ret; + return copied ? : ret; } static void mptcp_wait_data(struct sock *sk, long *timeo) @@ -1130,7 +1268,7 @@ static void mptcp_retransmit_handler(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - if (atomic64_read(&msk->snd_una) == msk->write_seq) { + if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->write_seq)) { mptcp_stop_timer(sk); } else { set_bit(MPTCP_WORK_RTX, &msk->flags); @@ -1255,6 +1393,7 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); mptcp_clean_una(sk); + mptcp_check_data_fin_ack(sk); __mptcp_flush_join_list(msk); __mptcp_move_skbs(msk); @@ -1264,6 +1403,8 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) mptcp_check_for_eof(msk); + mptcp_check_data_fin(sk); + if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) goto unlock; @@ -1386,8 +1527,7 @@ static void mptcp_cancel_work(struct sock *sk) sock_put(sk); } -static void mptcp_subflow_shutdown(struct sock *ssk, int how, - bool data_fin_tx_enable, u64 data_fin_tx_seq) +static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) { lock_sock(ssk); @@ -1400,34 +1540,84 @@ static void mptcp_subflow_shutdown(struct sock *ssk, int how, tcp_disconnect(ssk, O_NONBLOCK); break; default: - if (data_fin_tx_enable) { - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->data_fin_tx_seq = data_fin_tx_seq; - subflow->data_fin_tx_enable = 1; + if (__mptcp_check_fallback(mptcp_sk(sk))) { + pr_debug("Fallback"); + ssk->sk_shutdown |= how; + tcp_shutdown(ssk, how); + } else { + pr_debug("Sending DATA_FIN on subflow %p", ssk); + mptcp_set_timeout(sk, ssk); + tcp_send_ack(ssk); } - - ssk->sk_shutdown |= how; - tcp_shutdown(ssk, how); break; } release_sock(ssk); } -/* Called with msk lock held, releases such lock before returning */ +static const unsigned char new_state[16] = { + /* current state: new state: action: */ + [0 /* (Invalid) */] = TCP_CLOSE, + [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_SYN_SENT] = TCP_CLOSE, + [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, + [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, + [TCP_TIME_WAIT] = TCP_CLOSE, /* should not happen ! */ + [TCP_CLOSE] = TCP_CLOSE, + [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, + [TCP_LAST_ACK] = TCP_LAST_ACK, + [TCP_LISTEN] = TCP_CLOSE, + [TCP_CLOSING] = TCP_CLOSING, + [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ +}; + +static int mptcp_close_state(struct sock *sk) +{ + int next = (int)new_state[sk->sk_state]; + int ns = next & TCP_STATE_MASK; + + inet_sk_state_store(sk, ns); + + return next & TCP_ACTION_FIN; +} + static void mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); LIST_HEAD(conn_list); - u64 data_fin_tx_seq; lock_sock(sk); + sk->sk_shutdown = SHUTDOWN_MASK; + + if (sk->sk_state == TCP_LISTEN) { + inet_sk_state_store(sk, TCP_CLOSE); + goto cleanup; + } else if (sk->sk_state == TCP_CLOSE) { + goto cleanup; + } + + if (__mptcp_check_fallback(msk)) { + goto update_state; + } else if (mptcp_close_state(sk)) { + pr_debug("Sending DATA_FIN sk=%p", sk); + WRITE_ONCE(msk->write_seq, msk->write_seq + 1); + WRITE_ONCE(msk->snd_data_fin_enable, 1); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK); + } + } + + sk_stream_wait_close(sk, timeout); + +update_state: inet_sk_state_store(sk, TCP_CLOSE); +cleanup: /* be sure to always acquire the join list lock, to sync vs * mptcp_finish_join(). */ @@ -1436,17 +1626,12 @@ static void mptcp_close(struct sock *sk, long timeout) spin_unlock_bh(&msk->join_list_lock); list_splice_init(&msk->conn_list, &conn_list); - data_fin_tx_seq = msk->write_seq; - __mptcp_clear_xmit(sk); release_sock(sk); list_for_each_entry_safe(subflow, tmp, &conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - - subflow->data_fin_tx_seq = data_fin_tx_seq; - subflow->data_fin_tx_enable = 1; __mptcp_close_ssk(sk, ssk, subflow, timeout); } @@ -1994,7 +2179,7 @@ do_connect: /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ - if (!err || err == EINPROGRESS) + if (!err || err == -EINPROGRESS) mptcp_copy_inaddrs(sock->sk, ssock->sk); else inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); @@ -2063,7 +2248,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, * This is needed so NOSPACE flag can be set from tcp stack. */ __mptcp_flush_join_list(msk); - list_for_each_entry(subflow, &msk->conn_list, node) { + mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!ssk->sk_socket) @@ -2123,11 +2308,8 @@ static int mptcp_shutdown(struct socket *sock, int how) pr_debug("sk=%p, how=%d", msk, how); lock_sock(sock->sk); - if (how == SHUT_WR || how == SHUT_RDWR) - inet_sk_state_store(sock->sk, TCP_FIN_WAIT1); how++; - if ((how & ~SHUTDOWN_MASK) || !how) { ret = -EINVAL; goto out_unlock; @@ -2141,11 +2323,31 @@ static int mptcp_shutdown(struct socket *sock, int how) sock->state = SS_CONNECTED; } - __mptcp_flush_join_list(msk); - mptcp_for_each_subflow(msk, subflow) { - struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + /* If we've already sent a FIN, or it's a closed state, skip this. */ + if (__mptcp_check_fallback(msk)) { + if (how == SHUT_WR || how == SHUT_RDWR) + inet_sk_state_store(sock->sk, TCP_FIN_WAIT1); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + + mptcp_subflow_shutdown(sock->sk, tcp_sk, how); + } + } else if ((how & SEND_SHUTDOWN) && + ((1 << sock->sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | + TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) && + mptcp_close_state(sock->sk)) { + __mptcp_flush_join_list(msk); + + WRITE_ONCE(msk->write_seq, msk->write_seq + 1); + WRITE_ONCE(msk->snd_data_fin_enable, 1); - mptcp_subflow_shutdown(tcp_sk, how, 1, msk->write_seq); + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + + mptcp_subflow_shutdown(sock->sk, tcp_sk, how); + } } /* Wake up anyone sleeping in poll. */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67634b595466..60b27d44c184 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -193,12 +193,15 @@ struct mptcp_sock { u64 remote_key; u64 write_seq; u64 ack_seq; + u64 rcv_data_fin_seq; atomic64_t snd_una; unsigned long timer_ival; u32 token; unsigned long flags; bool can_ack; bool fully_established; + bool rcv_data_fin; + bool snd_data_fin_enable; spinlock_t join_list_lock; struct work_struct work; struct list_head conn_list; @@ -291,10 +294,8 @@ struct mptcp_subflow_context { backup : 1, data_avail : 1, rx_eof : 1, - data_fin_tx_enable : 1, use_64bit_ack : 1, /* Set when we received a 64-bit DSN */ can_ack : 1; /* only after processing the remote a key */ - u64 data_fin_tx_seq; u32 remote_nonce; u64 thmac; u32 local_nonce; @@ -386,6 +387,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); void mptcp_data_acked(struct sock *sk); void mptcp_subflow_eof(struct sock *sk); +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq); void __init mptcp_token_init(void); static inline void mptcp_token_init_request(struct request_sock *req) @@ -398,6 +400,7 @@ void mptcp_token_destroy_request(struct request_sock *req); int mptcp_token_new_connect(struct sock *sk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); +bool mptcp_token_exists(u32 token); struct mptcp_sock *mptcp_token_get_sock(u32 token); struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num); @@ -503,4 +506,24 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) !subflow->conn_finished; } +#ifdef CONFIG_SYN_COOKIES +void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb); +bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb); +void __init mptcp_join_cookie_init(void); +#else +static inline void +subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) {} +static inline bool +mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) +{ + return false; +} + +static inline void mptcp_join_cookie_init(void) {} +#endif + #endif /* __MPTCP_PROTOCOL_H */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e645483d1200..a4cc4591bd4e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -91,17 +91,9 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, return msk; } -static void subflow_init_req(struct request_sock *req, - const struct sock *sk_listener, - struct sk_buff *skb) +static int __subflow_init_req(struct request_sock *req, const struct sock *sk_listener) { - struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - struct mptcp_options_received mp_opt; - - pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); - - mptcp_get_options(skb, &mp_opt); subflow_req->mp_capable = 0; subflow_req->mp_join = 0; @@ -113,9 +105,29 @@ static void subflow_init_req(struct request_sock *req, * TCP option space. */ if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) - return; + return -EINVAL; #endif + return 0; +} + +static void subflow_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_options_received mp_opt; + int ret; + + pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); + + ret = __subflow_init_req(req, sk_listener); + if (ret) + return; + + mptcp_get_options(skb, &mp_opt); + if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -126,13 +138,33 @@ static void subflow_init_req(struct request_sock *req, } if (mp_opt.mp_capable && listener->request_mptcp) { - int err; + int err, retries = 4; + + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; +again: + do { + get_random_bytes(&subflow_req->local_key, sizeof(subflow_req->local_key)); + } while (subflow_req->local_key == 0); + + if (unlikely(req->syncookie)) { + mptcp_crypto_key_sha(subflow_req->local_key, + &subflow_req->token, + &subflow_req->idsn); + if (mptcp_token_exists(subflow_req->token)) { + if (retries-- > 0) + goto again; + } else { + subflow_req->mp_capable = 1; + } + return; + } err = mptcp_token_new_request(req); if (err == 0) subflow_req->mp_capable = 1; + else if (retries-- > 0) + goto again; - subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; } else if (mp_opt.mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; @@ -141,11 +173,60 @@ static void subflow_init_req(struct request_sock *req, subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; subflow_req->msk = subflow_token_join_request(req, skb); + + if (unlikely(req->syncookie) && subflow_req->msk) { + if (mptcp_can_accept_new_subflow(subflow_req->msk)) + subflow_init_req_cookie_join_save(subflow_req, skb); + } + pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, subflow_req->remote_nonce, subflow_req->msk); } } +int mptcp_subflow_init_cookie_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_options_received mp_opt; + int err; + + err = __subflow_init_req(req, sk_listener); + if (err) + return err; + + mptcp_get_options(skb, &mp_opt); + + if (mp_opt.mp_capable && mp_opt.mp_join) + return -EINVAL; + + if (mp_opt.mp_capable && listener->request_mptcp) { + if (mp_opt.sndr_key == 0) + return -EINVAL; + + subflow_req->local_key = mp_opt.rcvr_key; + err = mptcp_token_new_request(req); + if (err) + return err; + + subflow_req->mp_capable = 1; + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; + } else if (mp_opt.mp_join && listener->request_mptcp) { + if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) + return -EINVAL; + + if (mptcp_can_accept_new_subflow(subflow_req->msk)) + subflow_req->mp_join = 1; + + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req); + static void subflow_v4_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) @@ -265,7 +346,8 @@ do_reset: tcp_done(sk); } -static struct request_sock_ops subflow_request_sock_ops; +struct request_sock_ops mptcp_subflow_request_sock_ops; +EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops); static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -278,7 +360,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; - return tcp_conn_request(&subflow_request_sock_ops, + return tcp_conn_request(&mptcp_subflow_request_sock_ops, &subflow_request_sock_ipv4_ops, sk, skb); drop: @@ -303,7 +385,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; - return tcp_conn_request(&subflow_request_sock_ops, + return tcp_conn_request(&mptcp_subflow_request_sock_ops, &subflow_request_sock_ipv6_ops, sk, skb); drop: @@ -598,7 +680,8 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) return true; } -static enum mapping_status get_mapping_status(struct sock *ssk) +static enum mapping_status get_mapping_status(struct sock *ssk, + struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_ext *mpext; @@ -648,7 +731,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk) if (mpext->data_fin == 1) { if (data_len == 1) { - pr_debug("DATA_FIN with no payload"); + mptcp_update_rcv_data_fin(msk, mpext->data_seq); + pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS * option before the previous mapping @@ -660,6 +744,9 @@ static enum mapping_status get_mapping_status(struct sock *ssk) } else { return MAPPING_DATA_FIN; } + } else { + mptcp_update_rcv_data_fin(msk, mpext->data_seq + data_len); + pr_debug("DATA_FIN with mapping seq=%llu", mpext->data_seq + data_len); } /* Adjust for DATA_FIN using 1 byte of sequence space */ @@ -748,7 +835,7 @@ static bool subflow_check_data_avail(struct sock *ssk) u64 ack_seq; u64 old_ack; - status = get_mapping_status(ssk); + status = get_mapping_status(ssk, msk); pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status); if (status == MAPPING_INVALID) { ssk->sk_err = EBADMSG; @@ -1154,7 +1241,8 @@ static void subflow_state_change(struct sock *sk) if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); - if (!(parent->sk_shutdown & RCV_SHUTDOWN) && + if (__mptcp_check_fallback(mptcp_sk(parent)) && + !(parent->sk_shutdown & RCV_SHUTDOWN) && !subflow->rx_eof && subflow_is_done(sk)) { subflow->rx_eof = 1; mptcp_subflow_eof(parent); @@ -1286,8 +1374,8 @@ static int subflow_ops_init(struct request_sock_ops *subflow_ops) void __init mptcp_subflow_init(void) { - subflow_request_sock_ops = tcp_request_sock_ops; - if (subflow_ops_init(&subflow_request_sock_ops) != 0) + mptcp_subflow_request_sock_ops = tcp_request_sock_ops; + if (subflow_ops_init(&mptcp_subflow_request_sock_ops) != 0) panic("MPTCP: failed to init subflow request sock ops\n"); subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops; diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c new file mode 100644 index 000000000000..abe0fd099746 --- /dev/null +++ b/net/mptcp/syncookies.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/skbuff.h> + +#include "protocol.h" + +/* Syncookies do not work for JOIN requests. + * + * Unlike MP_CAPABLE, where the ACK cookie contains the needed MPTCP + * options to reconstruct the initial syn state, MP_JOIN does not contain + * the token to obtain the mptcp socket nor the server-generated nonce + * that was used in the cookie SYN/ACK response. + * + * Keep a small best effort state table to store the syn/synack data, + * indexed by skb hash. + * + * A MP_JOIN SYN packet handled by syn cookies is only stored if the 32bit + * token matches a known mptcp connection that can still accept more subflows. + * + * There is no timeout handling -- state is only re-constructed + * when the TCP ACK passed the cookie validation check. + */ + +struct join_entry { + u32 token; + u32 remote_nonce; + u32 local_nonce; + u8 join_id; + u8 local_id; + u8 backup; + u8 valid; +}; + +#define COOKIE_JOIN_SLOTS 1024 + +static struct join_entry join_entries[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp; +static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp; + +static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net) +{ + u32 i = skb_get_hash(skb) ^ net_hash_mix(net); + + return i % ARRAY_SIZE(join_entries); +} + +static void mptcp_join_store_state(struct join_entry *entry, + const struct mptcp_subflow_request_sock *subflow_req) +{ + entry->token = subflow_req->token; + entry->remote_nonce = subflow_req->remote_nonce; + entry->local_nonce = subflow_req->local_nonce; + entry->backup = subflow_req->backup; + entry->join_id = subflow_req->remote_id; + entry->local_id = subflow_req->local_id; + entry->valid = 1; +} + +void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) +{ + struct net *net = read_pnet(&subflow_req->sk.req.ireq_net); + u32 i = mptcp_join_entry_hash(skb, net); + + /* No use in waiting if other cpu is already using this slot -- + * would overwrite the data that got stored. + */ + spin_lock_bh(&join_entry_locks[i]); + mptcp_join_store_state(&join_entries[i], subflow_req); + spin_unlock_bh(&join_entry_locks[i]); +} + +/* Called for a cookie-ack with MP_JOIN option present. + * Look up the saved state based on skb hash & check token matches msk + * in same netns. + * + * Caller will check msk can still accept another subflow. The hmac + * present in the cookie ACK mptcp option space will be checked later. + */ +bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req, + struct sk_buff *skb) +{ + struct net *net = read_pnet(&subflow_req->sk.req.ireq_net); + u32 i = mptcp_join_entry_hash(skb, net); + struct mptcp_sock *msk; + struct join_entry *e; + + e = &join_entries[i]; + + spin_lock_bh(&join_entry_locks[i]); + + if (e->valid == 0) { + spin_unlock_bh(&join_entry_locks[i]); + return false; + } + + e->valid = 0; + + msk = mptcp_token_get_sock(e->token); + if (!msk) { + spin_unlock_bh(&join_entry_locks[i]); + return false; + } + + /* If this fails, the token got re-used in the mean time by another + * mptcp socket in a different netns, i.e. entry is outdated. + */ + if (!net_eq(sock_net((struct sock *)msk), net)) + goto err_put; + + subflow_req->remote_nonce = e->remote_nonce; + subflow_req->local_nonce = e->local_nonce; + subflow_req->backup = e->backup; + subflow_req->remote_id = e->join_id; + subflow_req->token = e->token; + subflow_req->msk = msk; + spin_unlock_bh(&join_entry_locks[i]); + return true; + +err_put: + spin_unlock_bh(&join_entry_locks[i]); + sock_put((struct sock *)msk); + return false; +} + +void __init mptcp_join_cookie_init(void) +{ + int i; + + for (i = 0; i < COOKIE_JOIN_SLOTS; i++) + spin_lock_init(&join_entry_locks[i]); +} diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 97cfc45bcc4f..8b47c4bb1c6b 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -109,14 +109,12 @@ static void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn) int mptcp_token_new_request(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - int retries = TOKEN_MAX_RETRIES; struct token_bucket *bucket; u32 token; -again: - mptcp_crypto_key_gen_sha(&subflow_req->local_key, - &subflow_req->token, - &subflow_req->idsn); + mptcp_crypto_key_sha(subflow_req->local_key, + &subflow_req->token, + &subflow_req->idsn); pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n", req, subflow_req->local_key, subflow_req->token, subflow_req->idsn); @@ -126,9 +124,7 @@ again: spin_lock_bh(&bucket->lock); if (__token_bucket_busy(bucket, token)) { spin_unlock_bh(&bucket->lock); - if (!--retries) - return -EBUSY; - goto again; + return -EBUSY; } hlist_nulls_add_head_rcu(&subflow_req->token_node, &bucket->req_chain); @@ -208,6 +204,32 @@ void mptcp_token_accept(struct mptcp_subflow_request_sock *req, spin_unlock_bh(&bucket->lock); } +bool mptcp_token_exists(u32 token) +{ + struct hlist_nulls_node *pos; + struct token_bucket *bucket; + struct mptcp_sock *msk; + struct sock *sk; + + rcu_read_lock(); + bucket = token_bucket(token); + +again: + sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { + msk = mptcp_sk(sk); + if (READ_ONCE(msk->token) == token) + goto found; + } + if (get_nulls_value(pos) != (token & token_mask)) + goto again; + + rcu_read_unlock(); + return false; +found: + rcu_read_unlock(); + return true; +} + /** * mptcp_token_get_sock - retrieve mptcp connection sock using its token * @token: token of the mptcp connection to retrieve diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0ffe2b8723c4..25313c29d799 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -447,7 +447,7 @@ config NF_TABLES replace the existing {ip,ip6,arp,eb}_tables infrastructure. It provides a pseudo-state machine with an extensible instruction-set (also known as expressions) that the userspace 'nft' utility - (http://www.netfilter.org/projects/nftables) uses to build the + (https://www.netfilter.org/projects/nftables) uses to build the rule-set. It also comes with the generic set infrastructure that allows you to construct mappings between matchings and actions for performance lookups. diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 56621d6bfd29..920b7c4331f0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1644,7 +1644,7 @@ dump_last: goto next_set; if (set->variant->uref) set->variant->uref(set, cb, true); - /* fall through */ + fallthrough; default: ret = set->variant->list(set, skb, cb); if (!cb->args[IPSET_CB_ARG0]) diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index b3921ae92740..a90b8eac16ac 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1389,6 +1389,45 @@ flush_again: goto flush_again; } } + +#ifdef CONFIG_SYSCTL +void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs) +{ + int idx; + struct ip_vs_conn *cp, *cp_c; + struct ip_vs_dest *dest; + + rcu_read_lock(); + for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { + if (cp->ipvs != ipvs) + continue; + + dest = cp->dest; + if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE)) + continue; + + if (atomic_read(&cp->n_control)) + continue; + + cp_c = cp->control; + IP_VS_DBG(4, "del connection\n"); + ip_vs_conn_del(cp); + if (cp_c && !atomic_read(&cp_c->n_control)) { + IP_VS_DBG(4, "del controlling connection\n"); + ip_vs_conn_del(cp_c); + } + } + cond_resched_rcu(); + + /* netns clean up started, abort delayed work */ + if (!ipvs->enable) + break; + } + rcu_read_unlock(); +} +#endif + /* * per netns init and exit */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b4a6b7662f3f..e3668a6e54e4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -694,16 +694,10 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) return ipvs->sysctl_nat_icmp_send; } -static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) -{ - return ipvs->sysctl_expire_nodest_conn; -} - #else static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } -static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; } #endif @@ -2097,36 +2091,35 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int } } - if (unlikely(!cp)) { - int v; - - if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) - return v; - } - - IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); - /* Check the server status */ - if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ + if (sysctl_expire_nodest_conn(ipvs)) { + bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - __u32 flags = cp->flags; - - /* when timer already started, silently drop the packet.*/ - if (timer_pending(&cp->timer)) - __ip_vs_conn_put(cp); - else - ip_vs_conn_put(cp); + if (!old_ct) + cp->flags &= ~IP_VS_CONN_F_NFCT; - if (sysctl_expire_nodest_conn(ipvs) && - !(flags & IP_VS_CONN_F_ONE_PACKET)) { - /* try to expire the connection immediately */ ip_vs_conn_expire_now(cp); + __ip_vs_conn_put(cp); + if (old_ct) + return NF_DROP; + cp = NULL; + } else { + __ip_vs_conn_put(cp); + return NF_DROP; } + } - return NF_DROP; + if (unlikely(!cp)) { + int v; + + if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) + return v; } + IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); + ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index bcac316addab..678c5b14841c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -210,6 +210,17 @@ static void update_defense_level(struct netns_ipvs *ipvs) local_bh_enable(); } +/* Handler for delayed work for expiring no + * destination connections + */ +static void expire_nodest_conn_handler(struct work_struct *work) +{ + struct netns_ipvs *ipvs; + + ipvs = container_of(work, struct netns_ipvs, + expire_nodest_conn_work.work); + ip_vs_expire_nodest_conn_flush(ipvs); +} /* * Timer for checking the defense @@ -1164,6 +1175,12 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, list_add(&dest->t_list, &ipvs->dest_trash); dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); + + /* Queue up delayed work to expire all no destination connections. + * No-op when CONFIG_SYSCTL is disabled. + */ + if (!cleanup) + ip_vs_enqueue_expire_nodest_conns(ipvs); } @@ -4086,6 +4103,10 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) queue_delayed_work(system_long_wq, &ipvs->defense_work, DEFENSE_TIMER_PERIOD); + /* Init delayed work for expiring no dest conn */ + INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work, + expire_nodest_conn_handler); + return 0; } @@ -4093,6 +4114,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { struct net *net = ipvs->net; + cancel_delayed_work_sync(&ipvs->expire_nodest_conn_work); cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 573cb4481481..e697a824b001 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -257,15 +257,15 @@ static unsigned int get_uint(struct bitstr *bs, int b) case 4: v |= *bs->cur++; v <<= 8; - /* fall through */ + fallthrough; case 3: v |= *bs->cur++; v <<= 8; - /* fall through */ + fallthrough; case 2: v |= *bs->cur++; v <<= 8; - /* fall through */ + fallthrough; case 1: v |= *bs->cur++; break; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index a0560d175a7f..95f79980348c 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -610,7 +610,7 @@ void nf_ct_netns_put(struct net *net, uint8_t nfproto) switch (nfproto) { case NFPROTO_BRIDGE: nf_ct_netns_do_put(net, NFPROTO_BRIDGE); - /* fall through */ + fallthrough; case NFPROTO_INET: nf_ct_netns_do_put(net, NFPROTO_IPV4); nf_ct_netns_do_put(net, NFPROTO_IPV6); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1926fd56df56..6892e497781c 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -900,7 +900,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, return -NF_REPEAT; return NF_DROP; } - /* Fall through */ + fallthrough; case TCP_CONNTRACK_IGNORE: /* Ignored packets: * diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 6a26299cb064..a604f43e3e6b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -60,7 +60,7 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, ntohs(tuple->src.u.tcp.port), ntohs(tuple->dst.u.tcp.port)); break; - case IPPROTO_UDPLITE: /* fallthrough */ + case IPPROTO_UDPLITE: case IPPROTO_UDP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.udp.port), diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index bfc555fcbc72..ea923f8cf9c4 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -408,7 +408,7 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, static const unsigned int max_attempts = 128; switch (tuple->dst.protonum) { - case IPPROTO_ICMP: /* fallthrough */ + case IPPROTO_ICMP: case IPPROTO_ICMPV6: /* id is same for either direction... */ keyptr = &tuple->src.u.icmp.id; @@ -442,11 +442,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, } goto find_free_id; #endif - case IPPROTO_UDP: /* fallthrough */ - case IPPROTO_UDPLITE: /* fallthrough */ - case IPPROTO_TCP: /* fallthrough */ - case IPPROTO_SCTP: /* fallthrough */ - case IPPROTO_DCCP: /* fallthrough */ + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + case IPPROTO_TCP: + case IPPROTO_SCTP: + case IPPROTO_DCCP: if (maniptype == NF_NAT_MANIP_SRC) keyptr = &tuple->src.u.all; else diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index ebcdc8e54476..9cca35d22927 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -704,8 +704,7 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb, nf_ct_seqadj_init(ct, ctinfo, 0); synproxy->tsoff = 0; this_cpu_inc(snet->stats->conn_reopened); - - /* fall through */ + fallthrough; case TCP_CONNTRACK_SYN_SENT: if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; @@ -1128,8 +1127,7 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb, nf_ct_seqadj_init(ct, ctinfo, 0); synproxy->tsoff = 0; this_cpu_inc(snet->stats->conn_reopened); - - /* fall through */ + fallthrough; case TCP_CONNTRACK_SYN_SENT: if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index de70a7c4e769..dc0e4f5cb975 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2084,7 +2084,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nla[NFTA_CHAIN_HOOK]) { if (!nft_is_base_chain(chain)) - return -EBUSY; + return -EEXIST; err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family, false); @@ -2094,21 +2094,21 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, basechain = nft_base_chain(chain); if (basechain->type != hook.type) { nft_chain_release_hook(&hook); - return -EBUSY; + return -EEXIST; } if (ctx->family == NFPROTO_NETDEV) { if (!nft_hook_list_equal(&basechain->hook_list, &hook.list)) { nft_chain_release_hook(&hook); - return -EBUSY; + return -EEXIST; } } else { ops = &basechain->ops; if (ops->hooknum != hook.num || ops->priority != hook.priority) { nft_chain_release_hook(&hook); - return -EBUSY; + return -EEXIST; } } nft_chain_release_hook(&hook); @@ -2496,6 +2496,7 @@ nla_put_failure: struct nft_expr_info { const struct nft_expr_ops *ops; + const struct nlattr *attr; struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; }; @@ -2543,7 +2544,9 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, } else ops = type->ops; + info->attr = nla; info->ops = ops; + return 0; err1: @@ -3201,8 +3204,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, expr = nft_expr_first(rule); for (i = 0; i < n; i++) { err = nf_tables_newexpr(&ctx, &info[i], expr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, info[i].attr); goto err2; + } if (info[i].ops->validate) nft_validate_state_update(net, NFT_VALIDATE_NEED); @@ -4362,7 +4367,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: set->use--; - /* fall through */ + fallthrough; default: nf_tables_unbind_set(ctx, set, binding, phase == NFT_TRANS_COMMIT); @@ -5244,10 +5249,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ - nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) { - err = -EBUSY; + nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) goto err_element_clash; - } if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && memcmp(nft_set_ext_data(ext), @@ -5255,7 +5258,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) && *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2))) - err = -EBUSY; + goto err_element_clash; else if (!(nlmsg_flags & NLM_F_EXCL)) err = 0; } else if (err == -ENOTEMPTY) { @@ -6243,7 +6246,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: flowtable->use--; - /* fall through */ + fallthrough; default: return; } @@ -6405,7 +6408,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, list_for_each_entry(hook2, &ft->hook_list, list) { if (hook->ops.dev == hook2->ops.dev && hook->ops.pf == hook2->ops.pf) { - err = -EBUSY; + err = -EEXIST; goto err_unregister_net_hooks; } } @@ -7249,7 +7252,7 @@ static int nf_tables_validate(struct net *net) break; case NFT_VALIDATE_NEED: nft_validate_state_update(net, NFT_VALIDATE_DO); - /* fall through */ + fallthrough; case NFT_VALIDATE_DO: list_for_each_entry(table, &net->nft.tables, list) { if (nft_table_validate(net, table) < 0) @@ -8323,7 +8326,7 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, default: return -EINVAL; } - /* fall through */ + fallthrough; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 96c74c4c7176..587897a2498b 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -213,7 +213,7 @@ next_rule: jumpstack[stackptr].chain = chain; jumpstack[stackptr].rules = rules + 1; stackptr++; - /* fall through */ + fallthrough; case NFT_GOTO: nft_trace_packet(&info, chain, rule, NFT_TRACETYPE_RULE); diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 5827117f2635..5bfec829c12f 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org> - * (C) 2011 Intra2net AG <http://www.intra2net.com> + * (C) 2011 Intra2net AG <https://www.intra2net.com> */ #include <linux/init.h> #include <linux/module.h> diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index da915c224a82..89a381f7f945 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -451,7 +451,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, case IPPROTO_TCP: timeouts = nf_tcp_pernet(net)->timeouts; break; - case IPPROTO_UDP: /* fallthrough */ + case IPPROTO_UDP: case IPPROTO_UDPLITE: timeouts = nf_udp_pernet(net)->timeouts; break; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 8a28c127effc..16f4d84599ac 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -43,7 +43,7 @@ void nft_cmp_eval(const struct nft_expr *expr, case NFT_CMP_LT: if (d == 0) goto mismatch; - /* fall through */ + fallthrough; case NFT_CMP_LTE: if (d > 0) goto mismatch; @@ -51,7 +51,7 @@ void nft_cmp_eval(const struct nft_expr *expr, case NFT_CMP_GT: if (d == 0) goto mismatch; - /* fall through */ + fallthrough; case NFT_CMP_GTE: if (d < 0) goto mismatch; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 77258af1fce0..322bd674963e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -129,7 +129,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; } #endif - case NFT_CT_BYTES: /* fallthrough */ + case NFT_CT_BYTES: case NFT_CT_PKTS: { const struct nf_conn_acct *acct = nf_conn_acct_find(ct); u64 count = 0; @@ -1013,8 +1013,8 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx, help6 = nf_conntrack_helper_try_module_get(name, family, priv->l4proto); break; - case NFPROTO_NETDEV: /* fallthrough */ - case NFPROTO_BRIDGE: /* same */ + case NFPROTO_NETDEV: + case NFPROTO_BRIDGE: case NFPROTO_INET: help4 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV4, priv->l4proto); diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index cfac0964f48d..4dfdaeaf09a5 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -32,7 +32,7 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, unsigned int hooks; switch (priv->result) { - case NFT_FIB_RESULT_OIF: /* fallthrough */ + case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: hooks = (1 << NF_INET_PRE_ROUTING); break; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 9e556638bb32..c63eb3b17178 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -103,9 +103,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, { const struct nft_immediate_expr *priv = nft_expr_priv(expr); const struct nft_data *data = &priv->data; + struct nft_rule *rule, *n; struct nft_ctx chain_ctx; struct nft_chain *chain; - struct nft_rule *rule; if (priv->dreg != NFT_REG_VERDICT) return; @@ -121,7 +121,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, chain_ctx = *ctx; chain_ctx.chain = chain; - list_for_each_entry(rule, &chain->rules, list) + list_for_each_entry_safe(rule, n, &chain->rules, list) nf_tables_rule_release(&chain_ctx, rule); nf_tables_chain_destroy(&chain_ctx); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index a7de3a58f553..ed7cb9f747f6 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -467,7 +467,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, case IPPROTO_UDP: if (!nft_payload_udp_checksum(skb, pkt->xt.thoff)) return -1; - /* Fall through. */ + fallthrough; case IPPROTO_UDPLITE: *l4csum_offset = offsetof(struct udphdr, check); break; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index cc6082a5f7ad..9944523f5c2c 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -312,7 +312,7 @@ * Jay Ligatti, Josh Kuhn, and Chris Gage. * Proceedings of the IEEE International Conference on Computer * Communication Networks (ICCCN), August 2010. - * http://www.cse.usf.edu/~ligatti/papers/grouper-conf.pdf + * https://www.cse.usf.edu/~ligatti/papers/grouper-conf.pdf * * [Rottenstreich 2010] * Worst-Case TCAM Rule Expansion @@ -325,7 +325,7 @@ * Kirill Kogan, Sergey Nikolenko, Ori Rottenstreich, William Culhane, * and Patrick Eugster. * Proceedings of the 2014 ACM conference on SIGCOMM, August 2014. - * http://www.sigcomm.org/sites/default/files/ccr/papers/2014/August/2619239-2626294.pdf + * https://www.sigcomm.org/sites/default/files/ccr/papers/2014/August/2619239-2626294.pdf */ #include <linux/kernel.h> diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index 51b454d8fa9c..cedf47ab3c6f 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -25,7 +25,7 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, skb->ip_summed = CHECKSUM_UNNECESSARY; break; } - /* fall through */ + fallthrough; case CHECKSUM_NONE: if (protocol != IPPROTO_TCP && protocol != IPPROTO_UDP) skb->csum = 0; @@ -51,7 +51,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, case CHECKSUM_COMPLETE: if (len == skb->len - dataoff) return nf_ip_checksum(skb, hook, dataoff, protocol); - /* fall through */ + fallthrough; case CHECKSUM_NONE: skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol, skb->len - dataoff, 0); @@ -79,7 +79,7 @@ __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, skb->ip_summed = CHECKSUM_UNNECESSARY; break; } - /* fall through */ + fallthrough; case CHECKSUM_NONE: skb->csum = ~csum_unfold( csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, @@ -106,7 +106,7 @@ static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, case CHECKSUM_COMPLETE: if (len == skb->len - dataoff) return nf_ip6_checksum(skb, hook, dataoff, protocol); - /* fall through */ + fallthrough; case CHECKSUM_NONE: hsum = skb_checksum(skb, 0, dataoff, 0); skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index b97eb4b538fd..73d343abd115 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1050,6 +1050,7 @@ EXPORT_SYMBOL_GPL(xt_check_target); void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info) { + size_t offset; void *mem; u64 size; @@ -1067,7 +1068,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len, memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; - sockptr_advance(arg, sizeof(compat_tmp)); + offset = sizeof(compat_tmp); } else #endif { @@ -1078,7 +1079,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len, if (copy_from_sockptr(info, arg, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); - sockptr_advance(arg, sizeof(*info)); + offset = sizeof(*info); } info->name[sizeof(info->name) - 1] = '\0'; @@ -1092,7 +1093,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len, if (!mem) return ERR_PTR(-ENOMEM); - if (copy_from_sockptr(mem, arg, len) == 0) + if (copy_from_sockptr_offset(mem, arg, offset, len) == 0) return mem; vfree(mem); @@ -1570,7 +1571,7 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, trav->curr = trav->curr->next; if (trav->curr != trav->head) break; - /* fall through */ + fallthrough; default: return NULL; } diff --git a/net/netfilter/xt_CONNSECMARK.c b/net/netfilter/xt_CONNSECMARK.c index a5c8b653476a..76acecf3e757 100644 --- a/net/netfilter/xt_CONNSECMARK.c +++ b/net/netfilter/xt_CONNSECMARK.c @@ -6,7 +6,7 @@ * with the SECMARK target and state match. * * Based somewhat on CONNMARK: - * Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> + * Copyright (C) 2002,2004 MARA Systems AB <https://www.marasystems.com> * by Henrik Nordstrom <hno@marasystems.com> * * (C) 2006,2008 Red Hat, Inc., James Morris <jmorris@redhat.com> diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index eec2f3a88d73..e5ebc0810675 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -2,7 +2,7 @@ /* * xt_connmark - Netfilter module to operate on connection marks * - * Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> + * Copyright (C) 2002,2004 MARA Systems AB <https://www.marasystems.com> * by Henrik Nordstrom <hno@marasystems.com> * Copyright © CC Computer Consultants GmbH, 2007 - 2008 * Jan Engelhardt <jengelh@medozas.de> diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 5aab6df74e0f..a97c2259bbc8 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org> - * (C) 2011 Intra2net AG <http://www.intra2net.com> + * (C) 2011 Intra2net AG <https://www.intra2net.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index 67cb98489415..6aa12d0f54e2 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -5,7 +5,7 @@ * based on ipt_time by Fabrice MARIE <fabrice@netfilter.org> * This is a module which is used for time matching * It is using some modified code from dietlibc (localtime() function) - * that you can find at http://www.fefe.de/dietlibc/ + * that you can find at https://www.fefe.de/dietlibc/ * This file is distributed under the terms of the GNU General Public * License (GPL). Copies of the GPL can be obtained from gnu.org/gpl. */ diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 4340f25fe390..98d393e70de3 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) ovs_ct_update_key(skb, NULL, key, false, false); } -#define IN6_ADDR_INITIALIZER(ADDR) \ - { (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \ - (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] } - int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { @@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey, if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { - struct ovs_key_ct_tuple_ipv4 orig = { - output->ipv4.ct_orig.src, - output->ipv4.ct_orig.dst, - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv4 orig; + + memset(&orig, 0, sizeof(orig)); + orig.ipv4_src = output->ipv4.ct_orig.src; + orig.ipv4_dst = output->ipv4.ct_orig.dst; + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv4_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - struct ovs_key_ct_tuple_ipv6 orig = { - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src), - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst), - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv6 orig; + + memset(&orig, 0, sizeof(orig)); + memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, + sizeof(orig.ipv6_src)); + memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, + sizeof(orig.ipv6_dst)); + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv6_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6b6822f82f70..42f8cc70bb2c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -225,13 +225,14 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_stats_percpu *stats; u64 *stats_counter; u32 n_mask_hit; + u32 n_cache_hit; int error; stats = this_cpu_ptr(dp->stats_percpu); /* Look up flow. */ flow = ovs_flow_tbl_lookup_stats(&dp->table, key, skb_get_hash(skb), - &n_mask_hit); + &n_mask_hit, &n_cache_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; @@ -262,6 +263,7 @@ out: u64_stats_update_begin(&stats->syncp); (*stats_counter)++; stats->n_mask_hit += n_mask_hit; + stats->n_cache_hit += n_cache_hit; u64_stats_update_end(&stats->syncp); } @@ -699,6 +701,7 @@ static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats, stats->n_missed += local_stats.n_missed; stats->n_lost += local_stats.n_lost; mega_stats->n_mask_hit += local_stats.n_mask_hit; + mega_stats->n_cache_hit += local_stats.n_cache_hit; } } @@ -1495,6 +1498,7 @@ static size_t ovs_dp_cmd_msg_size(void) msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_stats)); msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_megaflow_stats)); msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */ + msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_MASKS_CACHE_SIZE */ return msgsize; } @@ -1532,6 +1536,10 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features)) goto nla_put_failure; + if (nla_put_u32(skb, OVS_DP_ATTR_MASKS_CACHE_SIZE, + ovs_flow_tbl_masks_cache_size(&dp->table))) + goto nla_put_failure; + genlmsg_end(skb, ovs_header); return 0; @@ -1596,6 +1604,16 @@ static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) #endif } + if (a[OVS_DP_ATTR_MASKS_CACHE_SIZE]) { + int err; + u32 cache_size; + + cache_size = nla_get_u32(a[OVS_DP_ATTR_MASKS_CACHE_SIZE]); + err = ovs_flow_tbl_masks_cache_resize(&dp->table, cache_size); + if (err) + return err; + } + dp->user_features = user_features; if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) @@ -1884,6 +1902,8 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, + [OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0, + PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), }; static const struct genl_ops dp_datapath_genl_ops[] = { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 24fcec22fde2..38f7d3e66ca6 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -38,12 +38,15 @@ * @n_mask_hit: Number of masks looked up for flow match. * @n_mask_hit / (@n_hit + @n_missed) will be the average masks looked * up per packet. + * @n_cache_hit: The number of received packets that had their mask found using + * the mask cache. */ struct dp_stats_percpu { u64 n_hit; u64 n_missed; u64 n_lost; u64 n_mask_hit; + u64 n_cache_hit; struct u64_stats_sync syncp; }; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 9d375e74b607..03942c30d83e 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -890,6 +890,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, if (static_branch_unlikely(&tc_recirc_sharing_support)) { tc_ext = skb_ext_find(skb, TC_SKB_EXT); key->recirc_id = tc_ext ? tc_ext->chain : 0; + OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; } else { key->recirc_id = 0; } diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index af22c9ee28dd..6527d84c3ea6 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -38,8 +38,8 @@ #define MASK_ARRAY_SIZE_MIN 16 #define REHASH_INTERVAL (10 * 60 * HZ) +#define MC_DEFAULT_HASH_ENTRIES 256 #define MC_HASH_SHIFT 8 -#define MC_HASH_ENTRIES (1u << MC_HASH_SHIFT) #define MC_HASH_SEGS ((sizeof(uint32_t) * 8) / MC_HASH_SHIFT) static struct kmem_cache *flow_cache; @@ -341,15 +341,79 @@ static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask) } } +static void __mask_cache_destroy(struct mask_cache *mc) +{ + free_percpu(mc->mask_cache); + kfree(mc); +} + +static void mask_cache_rcu_cb(struct rcu_head *rcu) +{ + struct mask_cache *mc = container_of(rcu, struct mask_cache, rcu); + + __mask_cache_destroy(mc); +} + +static struct mask_cache *tbl_mask_cache_alloc(u32 size) +{ + struct mask_cache_entry __percpu *cache = NULL; + struct mask_cache *new; + + /* Only allow size to be 0, or a power of 2, and does not exceed + * percpu allocation size. + */ + if ((!is_power_of_2(size) && size != 0) || + (size * sizeof(struct mask_cache_entry)) > PCPU_MIN_UNIT_SIZE) + return NULL; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + new->cache_size = size; + if (new->cache_size > 0) { + cache = __alloc_percpu(array_size(sizeof(struct mask_cache_entry), + new->cache_size), + __alignof__(struct mask_cache_entry)); + if (!cache) { + kfree(new); + return NULL; + } + } + + new->mask_cache = cache; + return new; +} +int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size) +{ + struct mask_cache *mc = rcu_dereference(table->mask_cache); + struct mask_cache *new; + + if (size == mc->cache_size) + return 0; + + if ((!is_power_of_2(size) && size != 0) || + (size * sizeof(struct mask_cache_entry)) > PCPU_MIN_UNIT_SIZE) + return -EINVAL; + + new = tbl_mask_cache_alloc(size); + if (!new) + return -ENOMEM; + + rcu_assign_pointer(table->mask_cache, new); + call_rcu(&mc->rcu, mask_cache_rcu_cb); + + return 0; +} + int ovs_flow_tbl_init(struct flow_table *table) { struct table_instance *ti, *ufid_ti; + struct mask_cache *mc; struct mask_array *ma; - table->mask_cache = __alloc_percpu(sizeof(struct mask_cache_entry) * - MC_HASH_ENTRIES, - __alignof__(struct mask_cache_entry)); - if (!table->mask_cache) + mc = tbl_mask_cache_alloc(MC_DEFAULT_HASH_ENTRIES); + if (!mc) return -ENOMEM; ma = tbl_mask_array_alloc(MASK_ARRAY_SIZE_MIN); @@ -367,6 +431,7 @@ int ovs_flow_tbl_init(struct flow_table *table) rcu_assign_pointer(table->ti, ti); rcu_assign_pointer(table->ufid_ti, ufid_ti); rcu_assign_pointer(table->mask_array, ma); + rcu_assign_pointer(table->mask_cache, mc); table->last_rehash = jiffies; table->count = 0; table->ufid_count = 0; @@ -377,7 +442,7 @@ free_ti: free_mask_array: __mask_array_destroy(ma); free_mask_cache: - free_percpu(table->mask_cache); + __mask_cache_destroy(mc); return -ENOMEM; } @@ -453,9 +518,11 @@ void ovs_flow_tbl_destroy(struct flow_table *table) { struct table_instance *ti = rcu_dereference_raw(table->ti); struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti); + struct mask_cache *mc = rcu_dereference(table->mask_cache); + struct mask_array *ma = rcu_dereference_ovsl(table->mask_array); - free_percpu(table->mask_cache); - call_rcu(&table->mask_array->rcu, mask_array_rcu_cb); + call_rcu(&mc->rcu, mask_cache_rcu_cb); + call_rcu(&ma->rcu, mask_array_rcu_cb); table_instance_destroy(table, ti, ufid_ti, false); } @@ -667,6 +734,7 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl, struct mask_array *ma, const struct sw_flow_key *key, u32 *n_mask_hit, + u32 *n_cache_hit, u32 *index) { u64 *usage_counters = this_cpu_ptr(ma->masks_usage_cntr); @@ -682,6 +750,7 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl, u64_stats_update_begin(&ma->syncp); usage_counters[*index]++; u64_stats_update_end(&ma->syncp); + (*n_cache_hit)++; return flow; } } @@ -719,8 +788,10 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl, struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl, const struct sw_flow_key *key, u32 skb_hash, - u32 *n_mask_hit) + u32 *n_mask_hit, + u32 *n_cache_hit) { + struct mask_cache *mc = rcu_dereference(tbl->mask_cache); struct mask_array *ma = rcu_dereference(tbl->mask_array); struct table_instance *ti = rcu_dereference(tbl->ti); struct mask_cache_entry *entries, *ce; @@ -729,10 +800,13 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl, int seg; *n_mask_hit = 0; - if (unlikely(!skb_hash)) { + *n_cache_hit = 0; + if (unlikely(!skb_hash || mc->cache_size == 0)) { u32 mask_index = 0; + u32 cache = 0; - return flow_lookup(tbl, ti, ma, key, n_mask_hit, &mask_index); + return flow_lookup(tbl, ti, ma, key, n_mask_hit, &cache, + &mask_index); } /* Pre and post recirulation flows usually have the same skb_hash @@ -743,17 +817,17 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl, ce = NULL; hash = skb_hash; - entries = this_cpu_ptr(tbl->mask_cache); + entries = this_cpu_ptr(mc->mask_cache); /* Find the cache entry 'ce' to operate on. */ for (seg = 0; seg < MC_HASH_SEGS; seg++) { - int index = hash & (MC_HASH_ENTRIES - 1); + int index = hash & (mc->cache_size - 1); struct mask_cache_entry *e; e = &entries[index]; if (e->skb_hash == skb_hash) { flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, - &e->mask_index); + n_cache_hit, &e->mask_index); if (!flow) e->skb_hash = 0; return flow; @@ -766,10 +840,12 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl, } /* Cache miss, do full lookup. */ - flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, &ce->mask_index); + flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, n_cache_hit, + &ce->mask_index); if (flow) ce->skb_hash = skb_hash; + *n_cache_hit = 0; return flow; } @@ -779,9 +855,10 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl, struct table_instance *ti = rcu_dereference_ovsl(tbl->ti); struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array); u32 __always_unused n_mask_hit; + u32 __always_unused n_cache_hit; u32 index = 0; - return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &index); + return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index); } struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl, @@ -858,6 +935,13 @@ int ovs_flow_tbl_num_masks(const struct flow_table *table) return READ_ONCE(ma->count); } +u32 ovs_flow_tbl_masks_cache_size(const struct flow_table *table) +{ + struct mask_cache *mc = rcu_dereference(table->mask_cache); + + return READ_ONCE(mc->cache_size); +} + static struct table_instance *table_instance_expand(struct table_instance *ti, bool ufid) { @@ -1086,8 +1170,8 @@ void ovs_flow_masks_rebalance(struct flow_table *table) for (i = 0; i < masks_entries; i++) { int index = masks_and_count[i].index; - new->masks[new->count++] = - rcu_dereference_ovsl(ma->masks[index]); + if (ovsl_dereference(ma->masks[index])) + new->masks[new->count++] = ma->masks[index]; } rcu_assign_pointer(table->mask_array, new); diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 1f664b050e3b..74ce48fecba9 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -27,6 +27,12 @@ struct mask_cache_entry { u32 mask_index; }; +struct mask_cache { + struct rcu_head rcu; + u32 cache_size; /* Must be ^2 value. */ + struct mask_cache_entry __percpu *mask_cache; +}; + struct mask_count { int index; u64 counter; @@ -53,7 +59,7 @@ struct table_instance { struct flow_table { struct table_instance __rcu *ti; struct table_instance __rcu *ufid_ti; - struct mask_cache_entry __percpu *mask_cache; + struct mask_cache __rcu *mask_cache; struct mask_array __rcu *mask_array; unsigned long last_rehash; unsigned int count; @@ -77,12 +83,15 @@ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, const struct sw_flow_mask *mask); void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow); int ovs_flow_tbl_num_masks(const struct flow_table *table); +u32 ovs_flow_tbl_masks_cache_size(const struct flow_table *table); +int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size); struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table, u32 *bucket, u32 *idx); struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *, const struct sw_flow_key *, u32 skb_hash, - u32 *n_mask_hit); + u32 *n_mask_hit, + u32 *n_cache_hit); struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *, const struct sw_flow_key *); struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl, diff --git a/net/rds/recv.c b/net/rds/recv.c index c8404971d5ab..aba4afe4dfed 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ + struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; + memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f07970207b54..38a46167523f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -288,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) - goto error; + goto error_attached_to_socket; trace_rxrpc_call(call->debug_id, rxrpc_call_connected, atomic_read(&call->usage), here, NULL); @@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - ret = -EEXIST; - -error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); + RX_CALL_DEAD, -EEXIST); trace_rxrpc_call(call->debug_id, rxrpc_call_error, - atomic_read(&call->usage), here, ERR_PTR(ret)); + atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = -EEXIST"); + return ERR_PTR(-EEXIST); + + /* We got an error, but the call is attached to the socket and is in + * need of release. However, we might now race with recvmsg() when + * completing the call queues it. Return 0 from sys_sendmsg() and + * leave the error to recvmsg() to deal with. + */ +error_attached_to_socket: + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + _leave(" = c=%08x [err]", call->debug_id); + return call; } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 19e141eeed17..8cbe0bf20ed5 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; - spin_lock_bh(&conn->params.peer->lock); - hlist_del_rcu(&call->error_link); - spin_unlock_bh(&conn->params.peer->lock); + if (!hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_del_rcu(&call->error_link); + spin_unlock_bh(&call->peer->lock); + } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 490b1927215c..efecc5a8f67d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -620,7 +620,7 @@ try_again: goto error_unlock_call; } - if (msg->msg_name) { + if (msg->msg_name && call->peer) { struct sockaddr_rxrpc *srx = msg->msg_name; size_t len = sizeof(call->peer->srx); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 03a30d014bb6..f3f6da6e4ad2 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -681,6 +681,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + ret = 0; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + goto out_put_unlock; } else { switch (READ_ONCE(call->state)) { case RXRPC_CALL_UNINITIALISED: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f2f663e88610..e6ad42b11835 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -706,8 +706,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, if (err && err != -EINPROGRESS) goto out_free; - if (!err) + if (!err) { *defrag = true; + cb.mru = IPCB(skb)->frag_max_size; + } } else { /* NFPROTO_IPV6 */ #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; @@ -717,8 +719,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, if (err && err != -EINPROGRESS) goto out_free; - if (!err) + if (!err) { *defrag = true; + cb.mru = IP6CB(skb)->frag_max_size; + } #else err = -EOPNOTSUPP; goto out_free; @@ -1543,10 +1547,10 @@ static int __init ct_init_module(void) return 0; -err_tbl_init: - destroy_workqueue(act_ct_wq); err_register: tcf_ct_flow_tables_uninit(); +err_tbl_init: + destroy_workqueue(act_ct_wq); return err; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 66986db062ed..c158bfed86d5 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -436,8 +436,7 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, return -ENOBUFS; spin_lock_bh(&p->tcf_lock); - memcpy(opt->keys, p->tcfp_keys, - p->tcfp_nkeys * sizeof(struct tc_pedit_key)); + memcpy(opt->keys, p->tcfp_keys, flex_array_size(opt, keys, p->tcfp_nkeys)); opt->index = p->tcf_index; opt->nkeys = p->tcfp_nkeys; opt->flags = p->tcfp_flags; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0b8623b3b24f..41a55c6cbeb8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb, if (WARN_ON_ONCE(!ext)) return TC_ACT_SHOT; ext->chain = last_executed_chain; + ext->mru = qdisc_skb_cb(skb)->mru; } return ret; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 771b068f8254..7b69ab1993ba 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -852,9 +852,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, u32 htid, flags = 0; size_t sel_size; int err; -#ifdef CONFIG_CLS_U32_PERF - size_t size; -#endif if (!opt) { if (handle) { @@ -1022,15 +1019,15 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, goto erridr; } - n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL); + n = kzalloc(struct_size(n, sel.keys, s->nkeys), GFP_KERNEL); if (n == NULL) { err = -ENOBUFS; goto erridr; } #ifdef CONFIG_CLS_U32_PERF - size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); - n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); + n->pf = __alloc_percpu(struct_size(n->pf, kcnts, s->nkeys), + __alignof__(struct tc_u32_pcnt)); if (!n->pf) { err = -ENOBUFS; goto errfree; @@ -1294,8 +1291,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, int cpu; #endif - if (nla_put(skb, TCA_U32_SEL, - sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), + if (nla_put(skb, TCA_U32_SEL, struct_size(&n->sel, keys, n->sel.nkeys), &n->sel)) goto nla_put_failure; @@ -1345,9 +1341,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, goto nla_put_failure; } #ifdef CONFIG_CLS_U32_PERF - gpf = kzalloc(sizeof(struct tc_u32_pcnt) + - n->sel.nkeys * sizeof(u64), - GFP_KERNEL); + gpf = kzalloc(struct_size(gpf, kcnts, n->sel.nkeys), GFP_KERNEL); if (!gpf) goto nla_put_failure; @@ -1361,9 +1355,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, gpf->kcnts[i] += pf->kcnts[i]; } - if (nla_put_64bit(skb, TCA_U32_PCNT, - sizeof(struct tc_u32_pcnt) + - n->sel.nkeys * sizeof(u64), + if (nla_put_64bit(skb, TCA_U32_PCNT, struct_size(gpf, kcnts, n->sel.nkeys), gpf, TCA_U32_PAD)) { kfree(gpf); goto nla_put_failure; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 4cc0ad0b1189..deac82f3ad7b 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -333,6 +333,10 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, struct nlattr *tb[TCA_RED_MAX + 1]; int err; + q->qdisc = &noop_qdisc; + q->sch = sch; + timer_setup(&q->adapt_timer, red_adaptative_timer, 0); + if (!opt) return -EINVAL; @@ -341,10 +345,6 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, if (err < 0) return err; - q->qdisc = &noop_qdisc; - q->sch = sch; - timer_setup(&q->adapt_timer, red_adaptative_timer, 0); - err = __red_change(sch, tb, extack); if (err) return err; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 832e36269b10..e7649bbc2b87 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -719,8 +719,11 @@ static int smc_connect_ism(struct smc_sock *smc, } /* Create send and receive buffers */ - if (smc_buf_create(smc, true)) - return smc_connect_abort(smc, SMC_CLC_DECL_MEM, + rc = smc_buf_create(smc, true); + if (rc) + return smc_connect_abort(smc, (rc == -ENOSPC) ? + SMC_CLC_DECL_MAX_DMB : + SMC_CLC_DECL_MEM, ini->cln_first_contact); smc_conn_save_peer_info(smc, aclc); @@ -1200,12 +1203,14 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, } /* Create send and receive buffers */ - if (smc_buf_create(new_smc, true)) { + rc = smc_buf_create(new_smc, true); + if (rc) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) smc_lgr_cleanup_early(&new_smc->conn); else smc_conn_free(&new_smc->conn); - return SMC_CLC_DECL_MEM; + return (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB : + SMC_CLC_DECL_MEM; } return 0; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 76c2b150d040..cf7b45306f4e 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -48,6 +48,7 @@ #define SMC_CLC_DECL_NOACTLINK 0x030a0000 /* no active smc-r link in lgr */ #define SMC_CLC_DECL_NOSRVLINK 0x030b0000 /* SMC-R link from srv not found */ #define SMC_CLC_DECL_VERSMISMAT 0x030c0000 /* SMC version mismatch */ +#define SMC_CLC_DECL_MAX_DMB 0x030d0000 /* SMC-D DMB limit exceeded */ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ #define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f82a2e599917..b42fa3b00d00 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1614,7 +1614,7 @@ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); if (rc) { kfree(buf_desc); - return ERR_PTR(-EAGAIN); + return (rc == -ENOMEM) ? ERR_PTR(-EAGAIN) : ERR_PTR(rc); } buf_desc->pages = virt_to_page(buf_desc->cpu_addr); /* CDC header stored in buf. So, pretend it was smaller */ @@ -1688,7 +1688,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) } if (IS_ERR(buf_desc)) - return -ENOMEM; + return PTR_ERR(buf_desc); if (!is_smcd) { if (smcr_buf_map_usable_links(lgr, buf_desc, is_rmb)) { diff --git a/net/socket.c b/net/socket.c index 94ca4547cd7c..aff52e81653c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2105,7 +2105,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, if (optlen < 0) return -EINVAL; - err = init_user_sockptr(&optval, user_optval); + err = init_user_sockptr(&optval, user_optval, optlen); if (err) return err; diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 8b0bb600602d..c68019697cfe 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -62,12 +62,10 @@ static int tipc_eth_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg) { - char bcast_mac[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; - memset(addr, 0, sizeof(*addr)); ether_addr_copy(addr->value, msg); addr->media_id = TIPC_MEDIA_TYPE_ETH; - addr->broadcast = !memcmp(addr->value, bcast_mac, ETH_ALEN); + addr->broadcast = is_broadcast_ether_addr(addr->value); return 0; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index d77f7d821130..bbc52b088d29 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -522,9 +522,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, goto err_crypto_info; } - sockptr_advance(optval, sizeof(*crypto_info)); - rc = copy_from_sockptr(crypto_info + 1, optval, - optlen - sizeof(*crypto_info)); + rc = copy_from_sockptr_offset(crypto_info + 1, optval, + sizeof(*crypto_info), + optlen - sizeof(*crypto_info)); if (rc) { rc = -EFAULT; goto err_crypto_info; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index cddf92c5d09e..90f0f82cd9ca 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -153,6 +153,11 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) control_freq = chandef->chan->center_freq; switch (chandef->width) { + case NL80211_CHAN_WIDTH_1: + case NL80211_CHAN_WIDTH_2: + case NL80211_CHAN_WIDTH_4: + case NL80211_CHAN_WIDTH_8: + case NL80211_CHAN_WIDTH_16: case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_20: @@ -263,6 +268,21 @@ static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) int width; switch (c->width) { + case NL80211_CHAN_WIDTH_1: + width = 1; + break; + case NL80211_CHAN_WIDTH_2: + width = 2; + break; + case NL80211_CHAN_WIDTH_4: + width = 4; + break; + case NL80211_CHAN_WIDTH_8: + width = 8; + break; + case NL80211_CHAN_WIDTH_16: + width = 16; + break; case NL80211_CHAN_WIDTH_5: width = 5; break; @@ -911,6 +931,21 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, control_freq = chandef->chan->center_freq; switch (chandef->width) { + case NL80211_CHAN_WIDTH_1: + width = 1; + break; + case NL80211_CHAN_WIDTH_2: + width = 2; + break; + case NL80211_CHAN_WIDTH_4: + width = 4; + break; + case NL80211_CHAN_WIDTH_8: + width = 8; + break; + case NL80211_CHAN_WIDTH_16: + width = 16; + break; case NL80211_CHAN_WIDTH_5: width = 5; break; diff --git a/net/wireless/core.c b/net/wireless/core.c index c623d9bf5096..1971d7e6eb55 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -803,10 +803,11 @@ int wiphy_register(struct wiphy *wiphy) if (WARN_ON(!sband->n_channels)) return -EINVAL; /* - * on 60GHz band, there are no legacy rates, so + * on 60GHz or sub-1Ghz band, there are no legacy rates, so * n_bitrates is 0 */ - if (WARN_ON(band != NL80211_BAND_60GHZ && + if (WARN_ON((band != NL80211_BAND_60GHZ && + band != NL80211_BAND_S1GHZ) && !sband->n_bitrates)) return -EINVAL; diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index eac5aa1419fc..e4e363138279 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -78,6 +78,7 @@ const struct mesh_config default_mesh_config = { .power_mode = NL80211_MESH_POWER_ACTIVE, .dot11MeshAwakeWindowDuration = MESH_DEFAULT_AWAKE_WINDOW, .plink_timeout = MESH_DEFAULT_PLINK_TIMEOUT, + .dot11MeshNolearn = false, }; const struct mesh_setup default_mesh_setup = { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0e07fb8585fb..814e23d3ce7c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4713,8 +4713,8 @@ static int nl80211_parse_he_bss_color(struct nlattr *attrs, he_bss_color->color = nla_get_u8(tb[NL80211_HE_BSS_COLOR_ATTR_COLOR]); - he_bss_color->disabled = - nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_DISABLED]); + he_bss_color->enabled = + !nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_DISABLED]); he_bss_color->partial = nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_PARTIAL]); @@ -5395,6 +5395,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO(PEER_PM, peer_pm, u32); PUT_SINFO(NONPEER_PM, nonpeer_pm, u32); PUT_SINFO(CONNECTED_TO_GATE, connected_to_gate, u8); + PUT_SINFO(CONNECTED_TO_AS, connected_to_as, u8); if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) { bss_param = nla_nest_start_noflag(msg, @@ -6885,7 +6886,11 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, nla_put_u32(msg, NL80211_MESHCONF_PLINK_TIMEOUT, cur_params.plink_timeout) || nla_put_u8(msg, NL80211_MESHCONF_CONNECTED_TO_GATE, - cur_params.dot11MeshConnectedToMeshGate)) + cur_params.dot11MeshConnectedToMeshGate) || + nla_put_u8(msg, NL80211_MESHCONF_NOLEARN, + cur_params.dot11MeshNolearn) || + nla_put_u8(msg, NL80211_MESHCONF_CONNECTED_TO_AS, + cur_params.dot11MeshConnectedToAuthServer)) goto nla_put_failure; nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); @@ -6943,6 +6948,8 @@ nl80211_meshconf_params_policy[NL80211_MESHCONF_ATTR_MAX+1] = { [NL80211_MESHCONF_AWAKE_WINDOW] = { .type = NLA_U16 }, [NL80211_MESHCONF_PLINK_TIMEOUT] = { .type = NLA_U32 }, [NL80211_MESHCONF_CONNECTED_TO_GATE] = NLA_POLICY_RANGE(NLA_U8, 0, 1), + [NL80211_MESHCONF_NOLEARN] = NLA_POLICY_RANGE(NLA_U8, 0, 1), + [NL80211_MESHCONF_CONNECTED_TO_AS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), }; static const struct nla_policy @@ -7055,6 +7062,9 @@ do { \ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConnectedToMeshGate, mask, NL80211_MESHCONF_CONNECTED_TO_GATE, nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConnectedToAuthServer, mask, + NL80211_MESHCONF_CONNECTED_TO_AS, + nla_get_u8); /* * Check HT operation mode based on * IEEE 802.11-2016 9.4.2.57 HT Operation element. @@ -7094,6 +7104,8 @@ do { \ NL80211_MESHCONF_AWAKE_WINDOW, nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, plink_timeout, mask, NL80211_MESHCONF_PLINK_TIMEOUT, nla_get_u32); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNolearn, mask, + NL80211_MESHCONF_NOLEARN, nla_get_u8); if (mask_out) *mask_out = mask; @@ -7774,10 +7786,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->scan) return -EOPNOTSUPP; - if (rdev->scan_req || rdev->scan_msg) { - err = -EBUSY; - goto unlock; - } + if (rdev->scan_req || rdev->scan_msg) + return -EBUSY; if (info->attrs[NL80211_ATTR_SCAN_FREQ_KHZ]) { if (!wiphy_ext_feature_isset(wiphy, @@ -7790,10 +7800,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (scan_freqs) { n_channels = validate_scan_freqs(scan_freqs); - if (!n_channels) { - err = -EINVAL; - goto unlock; - } + if (!n_channels) + return -EINVAL; } else { n_channels = ieee80211_get_num_supported_channels(wiphy); } @@ -7802,29 +7810,23 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) n_ssids++; - if (n_ssids > wiphy->max_scan_ssids) { - err = -EINVAL; - goto unlock; - } + if (n_ssids > wiphy->max_scan_ssids) + return -EINVAL; if (info->attrs[NL80211_ATTR_IE]) ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); else ie_len = 0; - if (ie_len > wiphy->max_scan_ie_len) { - err = -EINVAL; - goto unlock; - } + if (ie_len > wiphy->max_scan_ie_len) + return -EINVAL; request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); - if (!request) { - err = -ENOMEM; - goto unlock; - } + if (!request) + return -ENOMEM; if (n_ssids) request->ssids = (void *)&request->channels[n_channels]; @@ -8003,17 +8005,19 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) rdev->scan_req = request; err = rdev_scan(rdev, request); - if (!err) { - nl80211_send_scan_start(rdev, wdev); - if (wdev->netdev) - dev_hold(wdev->netdev); - } else { + if (err) + goto out_free; + + nl80211_send_scan_start(rdev, wdev); + if (wdev->netdev) + dev_hold(wdev->netdev); + + return 0; + out_free: - rdev->scan_req = NULL; - kfree(request); - } + rdev->scan_req = NULL; + kfree(request); - unlock: return err; } @@ -9438,7 +9442,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (nla_len(info->attrs[NL80211_ATTR_PMK]) != WLAN_PMK_LEN) return -EINVAL; if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK)) + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK) && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK)) return -EINVAL; settings->psk = nla_data(info->attrs[NL80211_ATTR_PMK]); } @@ -10394,8 +10400,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) memcpy(dev->ieee80211_ptr->disconnect_bssid, connect.bssid, ETH_ALEN); else - memset(dev->ieee80211_ptr->disconnect_bssid, - 0, ETH_ALEN); + eth_zero_addr(dev->ieee80211_ptr->disconnect_bssid); } wdev_unlock(dev->ieee80211_ptr); @@ -13266,13 +13271,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev_running(wdev)) return -ENETDOWN; } - - if (!vcmd->doit) - return -EOPNOTSUPP; } else { wdev = NULL; } + if (!vcmd->doit) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); @@ -13479,7 +13484,7 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb, if (err == -ENOBUFS || err == -ENOENT) { genlmsg_cancel(skb, hdr); break; - } else if (err) { + } else if (err <= 0) { genlmsg_cancel(skb, hdr); goto out; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 74ea4cfb39fb..e67a74488bbe 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -712,6 +712,16 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *rdev) __cfg80211_bss_expire(rdev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE); } +void cfg80211_bss_flush(struct wiphy *wiphy) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + + spin_lock_bh(&rdev->bss_lock); + __cfg80211_bss_expire(rdev, jiffies); + spin_unlock_bh(&rdev->bss_lock); +} +EXPORT_SYMBOL(cfg80211_bss_flush); + const struct element * cfg80211_find_elem_match(u8 eid, const u8 *ies, unsigned int len, const u8 *match, unsigned int match_len, diff --git a/net/wireless/trace.h b/net/wireless/trace.h index b23cab016521..6e218a0acd4e 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -68,7 +68,8 @@ __field(u16, ht_opmode) \ __field(u32, dot11MeshHWMPactivePathToRootTimeout) \ __field(u16, dot11MeshHWMProotInterval) \ - __field(u16, dot11MeshHWMPconfirmationInterval) + __field(u16, dot11MeshHWMPconfirmationInterval) \ + __field(bool, dot11MeshNolearn) #define MESH_CFG_ASSIGN \ do { \ __entry->dot11MeshRetryTimeout = conf->dot11MeshRetryTimeout; \ @@ -109,6 +110,7 @@ conf->dot11MeshHWMProotInterval; \ __entry->dot11MeshHWMPconfirmationInterval = \ conf->dot11MeshHWMPconfirmationInterval; \ + __entry->dot11MeshNolearn = conf->dot11MeshNolearn; \ } while (0) #define CHAN_ENTRY __field(enum nl80211_band, band) \ diff --git a/net/wireless/util.c b/net/wireless/util.c index 4d3b76f94f55..26a977343c3b 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -102,6 +102,8 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) if (chan < 7) return MHZ_TO_KHZ(56160 + chan * 2160); break; + case NL80211_BAND_S1GHZ: + return 902000 + chan * 500; default: ; } @@ -210,6 +212,12 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) WARN_ON(!sband->ht_cap.ht_supported); WARN_ON((sband->ht_cap.mcs.rx_mask[0] & 0x1e) != 0x1e); break; + case NL80211_BAND_S1GHZ: + /* Figure 9-589bd: 3 means unsupported, so != 3 means at least + * mandatory is ok. + */ + WARN_ON((sband->s1g_cap.nss_mcs[0] & 0x3) == 0x3); + break; case NUM_NL80211_BANDS: default: WARN_ON(1); diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 100e29682b48..827ccdf2db57 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -15,6 +15,7 @@ static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, { if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, skb->truesize)) { + XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } @@ -49,23 +50,51 @@ static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb) struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx, strp); struct strp_msg *rxm = strp_msg(skb); + int len = rxm->full_len - 2; u32 nonesp_marker; int err; + /* keepalive packet? */ + if (unlikely(len == 1)) { + u8 data; + + err = skb_copy_bits(skb, rxm->offset + 2, &data, 1); + if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + + if (data == 0xff) { + kfree_skb(skb); + return; + } + } + + /* drop other short messages */ + if (unlikely(len <= sizeof(nonesp_marker))) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker, sizeof(nonesp_marker)); if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); kfree_skb(skb); return; } /* remove header, leave non-ESP marker/SPI */ if (!__pskb_pull(skb, rxm->offset + 2)) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } if (pskb_trim(skb, rxm->full_len - 2) != 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } @@ -91,7 +120,7 @@ static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) return err; len = be16_to_cpu(blen); - if (len < 6) + if (len < 2) return -EINVAL; return len; @@ -109,8 +138,11 @@ static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, flags |= nonblock ? MSG_DONTWAIT : 0; skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err); - if (!skb) + if (!skb) { + if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) + return 0; return err; + } copied = len; if (copied > skb->len) @@ -213,7 +245,7 @@ retry: return 0; } -static int espintcp_push_msgs(struct sock *sk) +static int espintcp_push_msgs(struct sock *sk, int flags) { struct espintcp_ctx *ctx = espintcp_getctx(sk); struct espintcp_msg *emsg = &ctx->partial; @@ -227,12 +259,12 @@ static int espintcp_push_msgs(struct sock *sk) ctx->tx_running = 1; if (emsg->skb) - err = espintcp_sendskb_locked(sk, emsg, 0); + err = espintcp_sendskb_locked(sk, emsg, flags); else - err = espintcp_sendskmsg_locked(sk, emsg, 0); + err = espintcp_sendskmsg_locked(sk, emsg, flags); if (err == -EAGAIN) { ctx->tx_running = 0; - return 0; + return flags & MSG_DONTWAIT ? -EAGAIN : 0; } if (!err) memset(emsg, 0, sizeof(*emsg)); @@ -257,7 +289,7 @@ int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) offset = skb_transport_offset(skb); len = skb->len - offset; - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); if (emsg->len) { kfree_skb(skb); @@ -270,7 +302,7 @@ int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) emsg->len = len; emsg->skb = skb; - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); return 0; } @@ -287,7 +319,7 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) char buf[2] = {0}; int err, end; - if (msg->msg_flags) + if (msg->msg_flags & ~MSG_DONTWAIT) return -EOPNOTSUPP; if (size > MAX_ESPINTCP_MSG) @@ -298,9 +330,10 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) lock_sock(sk); - err = espintcp_push_msgs(sk); + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); if (err < 0) { - err = -ENOBUFS; + if (err != -EAGAIN || !(msg->msg_flags & MSG_DONTWAIT)) + err = -ENOBUFS; goto unlock; } @@ -337,10 +370,9 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) tcp_rate_check_app_limited(sk); - err = espintcp_push_msgs(sk); + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); /* this message could be partially sent, keep it */ - if (err < 0) - goto unlock; + release_sock(sk); return size; @@ -374,7 +406,7 @@ static void espintcp_tx_work(struct work_struct *work) lock_sock(sk); if (!ctx->tx_running) - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); release_sock(sk); } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index bd984ff17c2d..37456d022cfa 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -42,7 +42,7 @@ struct xfrm_trans_cb { #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); -static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[AF_INET6 + 1]; +static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[2][AF_INET6 + 1]; static struct gro_cells gro_cells; static struct net_device xfrm_napi_dev; @@ -53,14 +53,14 @@ int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; - if (WARN_ON(afinfo->family >= ARRAY_SIZE(xfrm_input_afinfo))) + if (WARN_ON(afinfo->family > AF_INET6)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_input_afinfo_lock); - if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL)) + if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) err = -EEXIST; else - rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo); + rcu_assign_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], afinfo); spin_unlock_bh(&xfrm_input_afinfo_lock); return err; } @@ -71,11 +71,11 @@ int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo) int err = 0; spin_lock_bh(&xfrm_input_afinfo_lock); - if (likely(xfrm_input_afinfo[afinfo->family] != NULL)) { - if (unlikely(xfrm_input_afinfo[afinfo->family] != afinfo)) + if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) { + if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo)) err = -EINVAL; else - RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->family], NULL); + RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL); } spin_unlock_bh(&xfrm_input_afinfo_lock); synchronize_rcu(); @@ -83,15 +83,15 @@ int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_input_unregister_afinfo); -static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(unsigned int family) +static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(u8 family, bool is_ipip) { const struct xfrm_input_afinfo *afinfo; - if (WARN_ON_ONCE(family >= ARRAY_SIZE(xfrm_input_afinfo))) + if (WARN_ON_ONCE(family > AF_INET6)) return NULL; rcu_read_lock(); - afinfo = rcu_dereference(xfrm_input_afinfo[family]); + afinfo = rcu_dereference(xfrm_input_afinfo[is_ipip][family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; @@ -100,9 +100,11 @@ static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(unsigned int family static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol, int err) { + bool is_ipip = (protocol == IPPROTO_IPIP || protocol == IPPROTO_IPV6); + const struct xfrm_input_afinfo *afinfo; int ret; - const struct xfrm_input_afinfo *afinfo = xfrm_input_get_afinfo(family); + afinfo = xfrm_input_get_afinfo(family, is_ipip); if (!afinfo) return -EAFNOSUPPORT; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index b615729812e5..eb8181987620 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -48,21 +48,30 @@ 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; +static const struct net_device_ops xfrmi_netdev_ops; + +#define XFRMI_HASH_BITS 8 +#define XFRMI_HASH_SIZE BIT(XFRMI_HASH_BITS) struct xfrmi_net { /* lists for storing interfaces in use */ - struct xfrm_if __rcu *xfrmi[1]; + struct xfrm_if __rcu *xfrmi[XFRMI_HASH_SIZE]; }; #define for_each_xfrmi_rcu(start, xi) \ for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) +static u32 xfrmi_hash(u32 if_id) +{ + return hash_32(if_id, XFRMI_HASH_BITS); +} + 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) { + for_each_xfrmi_rcu(xfrmn->xfrmi[xfrmi_hash(x->if_id)], xi) { if (x->if_id == xi->p.if_id && (xi->dev->flags & IFF_UP)) return xi; @@ -74,8 +83,7 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb, unsigned short family) { - struct xfrmi_net *xfrmn; - struct xfrm_if *xi; + struct net_device *dev; int ifindex = 0; if (!secpath_exists(skb) || !skb->dev) @@ -89,23 +97,26 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb, ifindex = inet_sdif(skb); break; } - if (!ifindex) - ifindex = skb->dev->ifindex; - xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); + if (ifindex) { + struct net *net = xs_net(xfrm_input_state(skb)); - for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { - if (ifindex == xi->dev->ifindex && - (xi->dev->flags & IFF_UP)) - return xi; + dev = dev_get_by_index_rcu(net, ifindex); + } else { + dev = skb->dev; } - return NULL; + if (!dev || !(dev->flags & IFF_UP)) + return NULL; + if (dev->netdev_ops != &xfrmi_netdev_ops) + return NULL; + + return netdev_priv(dev); } static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { - struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0]; + struct xfrm_if __rcu **xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)]; rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); rcu_assign_pointer(*xip, xi); @@ -116,7 +127,7 @@ 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]; + for (xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)]; (iter = rtnl_dereference(*xip)) != NULL; xip = &iter->next) { if (xi == iter) { @@ -160,7 +171,7 @@ static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p) struct xfrm_if *xi; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); - for (xip = &xfrmn->xfrmi[0]; + for (xip = &xfrmn->xfrmi[xfrmi_hash(p->if_id)]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) if (xi->p.if_id == p->if_id) @@ -760,11 +771,14 @@ static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if __rcu **xip; struct xfrm_if *xi; + int i; - for (xip = &xfrmn->xfrmi[0]; - (xi = rtnl_dereference(*xip)) != NULL; - xip = &xi->next) - unregister_netdevice_queue(xi->dev, &list); + for (i = 0; i < XFRMI_HASH_SIZE; i++) { + for (xip = &xfrmn->xfrmi[i]; + (xi = rtnl_dereference(*xip)) != NULL; + xip = &xi->next) + unregister_netdevice_queue(xi->dev, &list); + } } unregister_netdevice_many(&list); rtnl_unlock(); @@ -800,6 +814,33 @@ static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { .priority = 10, }; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) +static int xfrmi6_rcv_tunnel(struct sk_buff *skb) +{ + const xfrm_address_t *saddr; + __be32 spi; + + saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; + spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); + + return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL); +} + +static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = { + .handler = xfrmi6_rcv_tunnel, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = -1, +}; + +static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { + .handler = xfrmi6_rcv_tunnel, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = -1, +}; +#endif + static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, @@ -824,6 +865,27 @@ static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { .priority = 10, }; +#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) +static int xfrmi4_rcv_tunnel(struct sk_buff *skb) +{ + return xfrm4_rcv_spi(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr); +} + +static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = { + .handler = xfrmi4_rcv_tunnel, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = -1, +}; + +static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = { + .handler = xfrmi4_rcv_tunnel, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = -1, +}; +#endif + static int __init xfrmi4_init(void) { int err; @@ -837,9 +899,23 @@ static int __init xfrmi4_init(void) err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; +#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) + err = xfrm4_tunnel_register(&xfrmi_ipip_handler, AF_INET); + if (err < 0) + goto xfrm_tunnel_ipip_failed; + err = xfrm4_tunnel_register(&xfrmi_ipip6_handler, AF_INET6); + if (err < 0) + goto xfrm_tunnel_ipip6_failed; +#endif return 0; +#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) +xfrm_tunnel_ipip6_failed: + xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET); +xfrm_tunnel_ipip_failed: + xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); +#endif xfrm_proto_comp_failed: xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: @@ -850,6 +926,10 @@ xfrm_proto_esp_failed: static void xfrmi4_fini(void) { +#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) + xfrm4_tunnel_deregister(&xfrmi_ipip6_handler, AF_INET6); + xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET); +#endif xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); @@ -868,9 +948,23 @@ static int __init xfrmi6_init(void) err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + err = xfrm6_tunnel_register(&xfrmi_ipv6_handler, AF_INET6); + if (err < 0) + goto xfrm_tunnel_ipv6_failed; + err = xfrm6_tunnel_register(&xfrmi_ip6ip_handler, AF_INET); + if (err < 0) + goto xfrm_tunnel_ip6ip_failed; +#endif return 0; +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) +xfrm_tunnel_ip6ip_failed: + xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6); +xfrm_tunnel_ipv6_failed: + xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); +#endif xfrm_proto_comp_failed: xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: @@ -881,6 +975,10 @@ xfrm_proto_esp_failed: static void xfrmi6_fini(void) { +#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) + xfrm6_tunnel_deregister(&xfrmi_ip6ip_handler, AF_INET); + xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6); +#endif xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 564aa6492e7c..042ea9b40c7b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,7 +39,7 @@ #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif -#ifdef CONFIG_INET_ESPINTCP +#ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif @@ -1433,14 +1433,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_unlock_bh(&pq->hold_queue.lock); } -static bool xfrm_policy_mark_match(struct xfrm_policy *policy, - struct xfrm_policy *pol) +static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, + struct xfrm_policy *pol) { - if (policy->mark.v == pol->mark.v && - policy->priority == pol->priority) - return true; - - return false; + return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) @@ -1503,7 +1499,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; @@ -1538,7 +1534,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) @@ -1610,9 +1606,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * -__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, +__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; @@ -1623,7 +1618,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; @@ -1632,11 +1627,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, return NULL; } -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_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, struct xfrm_selector *sel, + struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; @@ -1703,9 +1697,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -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 * +xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -1720,8 +1714,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, 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) { + pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( @@ -2758,6 +2751,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; struct sk_buff_head list; + __u32 skb_mark; spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); @@ -2767,7 +2761,12 @@ static void xfrm_policy_queue_process(struct timer_list *t) } dst = skb_dst(skb); sk = skb->sk; + + /* Fixup the mark to support VTI. */ + skb_mark = skb->mark; + skb->mark = pol->mark.v; xfrm_decode_session(skb, &fl, dst->ops->family); + skb->mark = skb_mark; spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); @@ -2799,7 +2798,12 @@ static void xfrm_policy_queue_process(struct timer_list *t) while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); + /* Fixup the mark to support VTI. */ + skb_mark = skb->mark; + skb->mark = pol->mark.v; xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family); + skb->mark = skb_mark; + dst_hold(xfrm_dst_path(skb_dst(skb))); dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0); if (IS_ERR(dst)) { @@ -4156,7 +4160,7 @@ void __init xfrm_init(void) seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); -#ifdef CONFIG_INET_ESPINTCP +#ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 98943f8d01aa..c6a4338a0d08 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -89,7 +89,8 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq; XFRM_SKB_CB(skb)->seq.output.hi = 0; - if (unlikely(x->replay.oseq == 0)) { + if (unlikely(x->replay.oseq == 0) && + !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) { x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; @@ -168,7 +169,8 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq; XFRM_SKB_CB(skb)->seq.output.hi = 0; - if (unlikely(replay_esn->oseq == 0)) { + if (unlikely(replay_esn->oseq == 0) && + !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) { replay_esn->oseq--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; @@ -572,7 +574,8 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk XFRM_SKB_CB(skb)->seq.output.hi = 0; xo->seq.hi = 0; - if (unlikely(oseq < x->replay.oseq)) { + if (unlikely(oseq < x->replay.oseq) && + !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) { xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; @@ -611,7 +614,8 @@ static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff XFRM_SKB_CB(skb)->seq.output.hi = 0; xo->seq.hi = 0; - if (unlikely(oseq < replay_esn->oseq)) { + if (unlikely(oseq < replay_esn->oseq) && + !(x->props.extra_flags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP)) { xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e6cfaa680ef3..fbb7d9d06478 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1863,7 +1863,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int delete; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; p = nlmsg_data(nlh); @@ -1880,8 +1879,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, + p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1898,8 +1900,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, - ctx, delete, &err); + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, + &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -2166,7 +2168,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type = XFRM_POLICY_TYPE_MAIN; 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); @@ -2180,8 +2181,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, + 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2198,7 +2202,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 6aea65c65745..45f2ab2ec2d4 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -138,11 +138,19 @@ char *read_text_file(const char *filename) char *get_line(char **stringp) { + char *orig = *stringp, *next; + /* do not return the unwanted extra line at EOF */ - if (*stringp && **stringp == '\0') + if (!orig || *orig == '\0') return NULL; - return strsep(stringp, "\n"); + next = strchr(orig, '\n'); + if (next) + *next++ = '\0'; + + *stringp = next; + + return orig; } /* A list of all modules we processed */ diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 7e3ae4534df9..803978d69e3c 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2935,6 +2935,10 @@ static int hda_codec_runtime_suspend(struct device *dev) struct hda_codec *codec = dev_to_hda_codec(dev); unsigned int state; + /* Nothing to do if card registration fails and the component driver never probes */ + if (!codec->card) + return 0; + cancel_delayed_work_sync(&codec->jackpoll_work); state = hda_call_codec_suspend(codec); if (codec->link_down_at_suspend || @@ -2949,6 +2953,10 @@ static int hda_codec_runtime_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); + /* Nothing to do if card registration fails and the component driver never probes */ + if (!codec->card) + return 0; + codec_display_power(codec, true); snd_hdac_codec_link_up(&codec->core); hda_call_codec_resume(codec); diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 82e26442724b..a356fb0e5773 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -41,7 +41,7 @@ /* 24 unused */ #define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */ #define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */ -/* 27 unused */ +#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3565e2ab0965..3fbba2e51e36 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -298,7 +298,8 @@ enum { /* PCH for HSW/BDW; with runtime PM */ /* no i915 binding for this as HSW/BDW has another controller for HDMI */ #define AZX_DCAPS_INTEL_PCH \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME) + (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) /* HSW HDMI */ #define AZX_DCAPS_INTEL_HASWELL \ @@ -1028,7 +1029,14 @@ static int azx_suspend(struct device *dev) chip = card->private_data; bus = azx_bus(chip); snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); - pm_runtime_force_suspend(dev); + /* An ugly workaround: direct call of __azx_runtime_suspend() and + * __azx_runtime_resume() for old Intel platforms that suffer from + * spurious wakeups after S3 suspend + */ + if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + __azx_runtime_suspend(chip); + else + pm_runtime_force_suspend(dev); if (bus->irq >= 0) { free_irq(bus->irq, chip); bus->irq = -1; @@ -1057,7 +1065,10 @@ static int azx_resume(struct device *dev) if (azx_acquire_irq(chip, 1) < 0) return -EIO; - pm_runtime_force_resume(dev); + if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + __azx_runtime_resume(chip, false); + else + pm_runtime_force_resume(dev); snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 41eaa89660c3..cd46247988e4 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2440,6 +2440,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp, mutex_lock(&spec->bind_lock); spec->use_acomp_notifier = use_acomp; spec->codec->relaxed_resume = use_acomp; + spec->codec->bus->keep_power = 0; /* reprogram each jack detection logic depending on the notifier */ for (i = 0; i < spec->num_pins; i++) reprogram_jack_detect(spec->codec, @@ -2534,7 +2535,6 @@ static void generic_acomp_init(struct hda_codec *codec, if (!snd_hdac_acomp_init(&codec->bus->core, &spec->drm_audio_ops, match_bound_vga, 0)) { spec->acomp_registered = true; - codec->bus->keep_power = 0; } } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1b2d8e56390a..29f5878f0c50 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5975,6 +5975,16 @@ static void alc_fixup_disable_mic_vref(struct hda_codec *codec, snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); } +static void alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_INIT) + return; + + msleep(100); + alc_write_coef_idx(codec, 0x65, 0x0); +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6152,8 +6162,10 @@ enum { ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS, ALC269VC_FIXUP_ACER_HEADSET_MIC, ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE, - ALC289_FIXUP_ASUS_G401, + ALC289_FIXUP_ASUS_GA401, + ALC289_FIXUP_ASUS_GA502, ALC256_FIXUP_ACER_MIC_NO_PRESENCE, + ALC285_FIXUP_HP_GPIO_AMP_INIT, }; static const struct hda_fixup alc269_fixups[] = { @@ -7363,7 +7375,14 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, - [ALC289_FIXUP_ASUS_G401] = { + [ALC289_FIXUP_ASUS_GA401] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11020 }, /* headset mic with jack detect */ + { } + }, + }, + [ALC289_FIXUP_ASUS_GA502] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x03a11020 }, /* headset mic with jack detect */ @@ -7379,6 +7398,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE }, + [ALC285_FIXUP_HP_GPIO_AMP_INIT] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_gpio_amp_init, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_LED + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7529,7 +7554,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), @@ -7561,7 +7586,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), - SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_G401), + SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), + SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -7581,7 +7607,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), - SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC225_FIXUP_HEADSET_JACK), + SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 40b7cd13fed9..a69d9e75f66f 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -367,6 +367,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ifnum = 0; goto add_sync_ep_from_ifnum; case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */ case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ case USB_ID(0x0d9a, 0x00df): /* RTX6001 */ ep = 0x81; diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 5b36c589a029..ba4f33804af1 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2861,6 +2861,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg, if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; + free_token(token); type = read_token(&token); *tok = token; diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile index 349bb81482ab..680d883efe05 100644 --- a/tools/lib/traceevent/plugins/Makefile +++ b/tools/lib/traceevent/plugins/Makefile @@ -197,7 +197,7 @@ define do_generate_dynamic_list_file xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ if [ "$$symbol_type" = "U W" ];then \ (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + $(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\ echo '};'; \ ) > $2; \ else \ diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 0a6e75b8777a..28a5d0c18b1d 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -56,7 +56,7 @@ struct auxtrace_record struct perf_pmu *cs_etm_pmu; struct evsel *evsel; bool found_etm = false; - bool found_spe = false; + struct perf_pmu *found_spe = NULL; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; int i = 0; @@ -74,12 +74,12 @@ struct auxtrace_record evsel->core.attr.type == cs_etm_pmu->type) found_etm = true; - if (!nr_spes) + if (!nr_spes || found_spe) continue; for (i = 0; i < nr_spes; i++) { if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = true; + found_spe = arm_spe_pmus[i]; break; } } @@ -96,7 +96,7 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); #endif /* diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 63a91ec473bb..045723b3d992 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,8 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - $perf_tool record -o $trace_file -g -z -F 5000 -- \ + [[ "$(uname -m)" != s390x ]] && gflag='-g' + $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index f7ee8fa377ad..6ccecbd39476 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -5,10 +5,60 @@ #include "test_btf_map_in_map.skel.h" +static int duration; + +static __u32 bpf_map_id(struct bpf_map *map) +{ + struct bpf_map_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + if (err) + return 0; + return info.id; +} + +/* + * Trigger synchronize_rcu() in kernel. + * + * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu() + * if looking up an existing non-NULL element or updating the map with a valid + * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map, + * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then + * cleanup. At the end, at least one synchronize_rcu() would be called. + */ +static int kern_sync_rcu(void) +{ + int inner_map_fd, outer_map_fd, err, zero = 0; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno)) + return -1; + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), inner_map_fd, 1, 0); + if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) { + close(inner_map_fd); + return -1; + } + + err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0); + if (err) + err = -errno; + CHECK(err, "outer_map_update", "failed %d\n", err); + close(inner_map_fd); + close(outer_map_fd); + return err; +} + void test_btf_map_in_map(void) { - int duration = 0, err, key = 0, val; - struct test_btf_map_in_map* skel; + int err, key = 0, val, i; + struct test_btf_map_in_map *skel; + int outer_arr_fd, outer_hash_fd; + int fd, map1_fd, map2_fd, map1_id, map2_id; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -18,32 +68,78 @@ void test_btf_map_in_map(void) if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; + map1_fd = bpf_map__fd(skel->maps.inner_map1); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + outer_arr_fd = bpf_map__fd(skel->maps.outer_arr); + outer_hash_fd = bpf_map__fd(skel->maps.outer_hash); + /* inner1 = input, inner2 = input + 1 */ - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0); skel->bss->input = 1; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); /* inner1 = input + 1, inner2 = input */ - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0); + bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0); skel->bss->input = 3; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + for (i = 0; i < 5; i++) { + val = i % 2 ? map1_fd : map2_fd; + err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + } + + map1_id = bpf_map_id(skel->maps.inner_map1); + map2_id = bpf_map_id(skel->maps.inner_map2); + CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); + CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); + + test_btf_map_in_map__destroy(skel); + skel = NULL; + + /* we need to either wait for or force synchronize_rcu(), before + * checking for "still exists" condition, otherwise map could still be + * resolvable by ID, causing false positives. + * + * Older kernels (5.8 and earlier) freed map only after two + * synchronize_rcu()s, so trigger two, to be entirely sure. + */ + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + + fd = bpf_map_get_fd_by_id(map1_id); + if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { + close(fd); + goto cleanup; + } + fd = bpf_map_get_fd_by_id(map2_id); + if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { + close(fd); + goto cleanup; + } + cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 8294ae3ffb3c..43c9cda199b8 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -318,6 +318,9 @@ class DebugfsDir: continue if os.path.isfile(p): + # We need to init trap_flow_action_cookie before read it + if f == "trap_flow_action_cookie": + cmd('echo deadbeef > %s/%s' % (path, f)) _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() elif os.path.isdir(p): diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 99f8f582c02b..c5e805980409 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -112,6 +112,7 @@ "perfevent for cgroup sockopt", .insns = { __PERF_EVENT_INSNS__ }, .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .fixup_map_event_output = { 4 }, .result = ACCEPT, .retval = 1, diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 45042105ead7..517297a14ecf 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -568,17 +568,12 @@ do_drop_test() busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null check_fail $? "Spurious packets observed without buffer pressure" - qevent_rule_uninstall_$subtest - # Push to the queue until it's at the limit. The configured limit is # rounded by the qdisc and then by the driver, so this is the best we - # can do to get to the real limit of the system. Do this with the rules - # uninstalled so that the inevitable drops don't get counted. + # can do to get to the real limit of the system. build_backlog $vlan $((3 * limit / 2)) udp >/dev/null - qevent_rule_install_$subtest base=$($fetch_counter) - send_packets $vlan udp 11 now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter) @@ -631,3 +626,31 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } + +qevent_rule_install_trap() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap hw_stats disabled +} + +qevent_rule_uninstall_trap() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} + +qevent_counter_fetch_trap() +{ + local trap_name=$1; shift + + devlink_trap_rx_packets_get "$trap_name" +} + +do_drop_trap_test() +{ + local vlan=$1; shift + local limit=$1; shift + local trap_name=$1; shift + + do_drop_test "$vlan" "$limit" "$trap_name" trap \ + "qevent_counter_fetch_trap $trap_name" +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index c8968b041bea..3f007c5f8361 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -8,6 +8,7 @@ ALL_TESTS=" red_test mc_backlog_test red_mirror_test + red_trap_test " : ${QDISC:=ets} source sch_red_core.sh @@ -94,6 +95,16 @@ red_mirror_test() uninstall_qdisc } +red_trap_test() +{ + install_qdisc qevent early_drop block 10 + + do_drop_trap_test 10 $BACKLOG1 early_drop + do_drop_trap_test 11 $BACKLOG2 early_drop + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index ea7a11a9f788..dbb9fcf759e0 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -235,8 +235,6 @@ check_highest_speed_is_chosen() fi local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1)) - # Remove the first speed, h1 does not advertise this speed. - unset speeds_arr[0] max_speed=${speeds_arr[0]} for current in ${speeds_arr[@]}; do diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index c0589e071f20..57d75b7f6220 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -196,6 +196,9 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 +# use TCP syn cookies, even if no flooding was detected. +ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -407,6 +410,11 @@ do_transfer() sleep 1 fi + local stat_synrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do echo $count;done) + local stat_ackrx_last_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do echo $count;done) + local stat_cookietx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do echo $count;done) + local stat_cookierx_last=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do echo $count;done) + ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" & local spid=$! @@ -450,6 +458,45 @@ do_transfer() check_transfer $cin $sout "file received by server" rets=$? + local stat_synrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableSYNRX | while read a count c rest ;do echo $count;done) + local stat_ackrx_now_l=$(ip netns exec ${listener_ns} nstat -z -a MPTcpExtMPCapableACKRX | while read a count c rest ;do echo $count;done) + + local stat_cookietx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesSent | while read a count c rest ;do echo $count;done) + local stat_cookierx_now=$(ip netns exec ${listener_ns} nstat -z -a TcpExtSyncookiesRecv | while read a count c rest ;do echo $count;done) + + expect_synrx=$((stat_synrx_last_l)) + expect_ackrx=$((stat_ackrx_last_l)) + + cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) + cookies=${cookies##*=} + + if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then + expect_synrx=$((stat_synrx_last_l+1)) + expect_ackrx=$((stat_ackrx_last_l+1)) + fi + if [ $cookies -eq 2 ];then + if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: did not advance" + fi + if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: did not advance" + fi + else + if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + echo "${listener_ns} CookieSent: ${cl_proto} -> ${srv_proto}: changed" + fi + if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + echo "${listener_ns} CookieRecv: ${cl_proto} -> ${srv_proto}: changed" + fi + fi + + if [ $expect_synrx -ne $stat_synrx_now_l ] ;then + echo "${listener_ns} SYNRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}" + fi + if [ $expect_ackrx -ne $stat_ackrx_now_l ] ;then + echo "${listener_ns} ACKRX: ${cl_proto} -> ${srv_proto}: expect ${expect_synrx}, got ${stat_synrx_now_l}" + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then echo "$duration [ OK ]" cat "$capout" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dd42c2f692d0..f39c1129ce5f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -72,6 +72,15 @@ reset() init } +reset_with_cookies() +{ + reset + + for netns in "$ns1" "$ns2";do + ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 + done +} + for arg in "$@"; do if [ "$arg" = "-c" ]; then capture=1 @@ -138,7 +147,7 @@ do_transfer() capuser="-Z $SUDO_USER" fi - capfile="mp_join-${listener_ns}.pcap" + capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") echo "Capturing traffic for test $TEST_COUNT into $capfile" ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & @@ -227,7 +236,7 @@ chk_join_nr() local count local dump_stats - printf "%-36s %s" "$msg" "syn" + printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then @@ -354,4 +363,57 @@ ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows and signal" 3 3 3 +# single subflow, syncookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "single subflow with syn cookies" 1 1 1 + +# multiple subflows with syn cookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "multiple subflows with syn cookies" 2 2 2 + +# multiple subflows limited by server +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflows limited by server w cookies" 2 2 1 + +# test signal address with cookies +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "signal address with syn cookies" 1 1 1 + +# test cookie with subflow and signal +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 1 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflow and signal w cookies" 2 2 2 + +# accept and use add_addr with additional subflows +reset_with_cookies +ip netns exec $ns1 ./pm_nl_ctl limits 0 3 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +ip netns exec $ns2 ./pm_nl_ctl limits 1 3 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflows and signal w. cookies" 3 3 3 + exit $ret diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 221fdece47d4..e4613ce4ed69 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -359,8 +359,7 @@ int main(int argc, char **argv) bool strict = false; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index ceaad78e9667..3155fbbf644b 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (labs(tstop - texpect) > cfg_variance_us) + if (llabs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); return false; diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4555f88252ba..a61b7b3da549 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -344,7 +344,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - size_t total = 0; + uint64_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -473,12 +473,12 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - ssize_t wr = FILE_SZ - total; + int64_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; /* Note : we just want to fill the pipe with 0 bytes */ - wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0); if (wr <= 0) break; total += wr; diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index 011b0da6b033..490a8cca708a 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -64,6 +64,7 @@ static int cfg_payload_len = 10; static int cfg_poll_timeout = 100; static int cfg_delay_snd; static int cfg_delay_ack; +static int cfg_delay_tolerance_usec = 500; static bool cfg_show_payload; static bool cfg_do_pktinfo; static bool cfg_busy_poll; @@ -152,11 +153,12 @@ static void validate_key(int tskey, int tstype) static void validate_timestamp(struct timespec *cur, int min_delay) { - int max_delay = min_delay + 500 /* processing time upper bound */; int64_t cur64, start64; + int max_delay; cur64 = timespec_to_us64(cur); start64 = timespec_to_us64(&ts_usr); + max_delay = min_delay + cfg_delay_tolerance_usec; if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) { fprintf(stderr, "ERROR: %lu us expected between %d and %d\n", @@ -683,6 +685,7 @@ static void __attribute__((noreturn)) usage(const char *filepath) " -r: use raw\n" " -R: use raw (IP_HDRINCL)\n" " -S N: usec to sleep before reading error queue\n" + " -t N: tolerance (usec) for timestamp validation\n" " -u: use udp\n" " -v: validate SND delay (usec)\n" " -V: validate ACK delay (usec)\n" @@ -697,7 +700,7 @@ static void parse_opt(int argc, char **argv) int c; while ((c = getopt(argc, argv, - "46bc:CeEFhIl:LnNp:PrRS:uv:V:x")) != -1) { + "46bc:CeEFhIl:LnNp:PrRS:t:uv:V:x")) != -1) { switch (c) { case '4': do_ipv6 = 0; @@ -760,6 +763,9 @@ static void parse_opt(int argc, char **argv) case 'S': cfg_sleep_usec = strtoul(optarg, NULL, 10); break; + case 't': + cfg_delay_tolerance_usec = strtoul(optarg, NULL, 10); + break; case 'u': proto_count++; cfg_proto = SOCK_DGRAM; |