diff options
356 files changed, 12888 insertions, 3649 deletions
diff --git a/Documentation/ABI/stable/sysfs-class-rfkill b/Documentation/ABI/stable/sysfs-class-rfkill index e1ba4a104753..80151a409d67 100644 --- a/Documentation/ABI/stable/sysfs-class-rfkill +++ b/Documentation/ABI/stable/sysfs-class-rfkill @@ -11,7 +11,7 @@ KernelVersion: v2.6.22 Contact: linux-wireless@vger.kernel.org, Description: The rfkill class subsystem folder. Each registered rfkill driver is represented by an rfkillX - subfolder (X being an integer > 0). + subfolder (X being an integer >= 0). What: /sys/class/rfkill/rfkill[0-9]+/name @@ -48,8 +48,8 @@ Contact: linux-wireless@vger.kernel.org Description: Current state of the transmitter. This file was scheduled to be removed in 2014, but due to its large number of users it will be sticking around for a bit - longer. Despite it being marked as stabe, the newer "hard" and - "soft" interfaces should be preffered, since it is not possible + longer. Despite it being marked as stable, the newer "hard" and + "soft" interfaces should be preferred, since it is not possible to express the 'soft and hard block' state of the rfkill driver through this interface. There will likely be another attempt to remove it in the future. diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 0c0df91b1516..978b76358661 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -42,6 +42,17 @@ Description: network device transmit queue. Possible vaules depend on the number of available CPU(s) in the system. +What: /sys/class/<iface>/queues/tx-<queue>/xps_rxqs +Date: June 2018 +KernelVersion: 4.18.0 +Contact: netdev@vger.kernel.org +Description: + Mask of the receive queue(s) currently enabled to participate + into the Transmit Packet Steering packet processing flow for this + network device transmit queue. Possible values depend on the + number of available receive queue(s) in the network device. + Default is disabled. + What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time Date: November 2011 KernelVersion: 3.3 diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index df873d1f3b7c..74603dd0789e 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -356,30 +356,7 @@ ethernet@e0000 { ============================================================================ FMan IEEE 1588 Node -DESCRIPTION - -The FMan interface to support IEEE 1588 - - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: A standard property. - Must include "fsl,fman-ptp-timer". - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - -EXAMPLE - -ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; -}; +Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt ============================================================================= FMan MDIO Node diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt index 9c16ee2965a2..3b71da7e8742 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt @@ -4,6 +4,7 @@ The device node has following properties. Required properties: - compatible: should be "rockchip,<name>-gamc" + "rockchip,px30-gmac": found on PX30 SoCs "rockchip,rk3128-gmac": found on RK312x SoCs "rockchip,rk3228-gmac": found on RK322x SoCs "rockchip,rk3288-gmac": found on RK3288 SoCs diff --git a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt index 0f569d8e73a3..c5d0e7998e2b 100644 --- a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +++ b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt @@ -2,7 +2,8 @@ General Properties: - - compatible Should be "fsl,etsec-ptp" + - compatible Should be "fsl,etsec-ptp" for eTSEC + Should be "fsl,fman-ptp-timer" for DPAA FMan - reg Offset and length of the register set for the device - interrupts There should be at least two interrupts. Some devices have as many as four PTP related interrupts. @@ -43,14 +44,22 @@ Clock Properties: value, which will be directly written in those bits, that is why, according to reference manual, the next clock sources can be used: + For eTSEC, <0> - external high precision timer reference clock (TSEC_TMR_CLK input is used for this purpose); <1> - eTSEC system clock; <2> - eTSEC1 transmit clock; <3> - RTC clock input. - When this attribute is not used, eTSEC system clock will serve as - IEEE 1588 timer reference clock. + For DPAA FMan, + <0> - external high precision timer reference clock (TMR_1588_CLK) + <1> - MAC system clock (1/2 FMan clock) + <2> - reserved + <3> - RTC clock oscillator + + When this attribute is not used, the IEEE 1588 timer reference clock + will use the eTSEC system clock (for Gianfar) or the MAC system + clock (for DPAA). Example: diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ce8fbf5aa63c..f4c042be0216 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -733,11 +733,11 @@ tcp_limit_output_bytes - INTEGER Controls TCP Small Queue limit per tcp socket. TCP bulk sender tends to increase packets in flight until it gets losses notifications. With SNDBUF autotuning, this can - result in a large amount of packets queued in qdisc/device - on the local machine, hurting latency of other flows, for - typical pfifo_fast qdiscs. - tcp_limit_output_bytes limits the number of bytes on qdisc - or device to reduce artificial RTT/cwnd and reduce bufferbloat. + result in a large amount of packets queued on the local machine + (e.g.: qdiscs, CPU backlog, or device) hurting latency of other + flows, for typical pfifo_fast qdiscs. tcp_limit_output_bytes + limits the number of bytes on qdisc or device to reduce artificial + RTT/cwnd and reduce bufferbloat. Default: 262144 tcp_challenge_ack_limit - INTEGER diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index f55639d71d35..b7056a8a0540 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt @@ -366,8 +366,13 @@ XPS: Transmit Packet Steering Transmit Packet Steering is a mechanism for intelligently selecting which transmit queue to use when transmitting a packet on a multi-queue -device. To accomplish this, a mapping from CPU to hardware queue(s) is -recorded. The goal of this mapping is usually to assign queues +device. This can be accomplished by recording two kinds of maps, either +a mapping of CPU to hardware queue(s) or a mapping of receive queue(s) +to hardware transmit queue(s). + +1. XPS using CPUs map + +The goal of this mapping is usually to assign queues exclusively to a subset of CPUs, where the transmit completions for these queues are processed on a CPU within this set. This choice provides two benefits. First, contention on the device queue lock is @@ -377,15 +382,40 @@ transmit queue). Secondly, cache miss rate on transmit completion is reduced, in particular for data cache lines that hold the sk_buff structures. -XPS is configured per transmit queue by setting a bitmap of CPUs that -may use that queue to transmit. The reverse mapping, from CPUs to -transmit queues, is computed and maintained for each network device. -When transmitting the first packet in a flow, the function -get_xps_queue() is called to select a queue. This function uses the ID -of the running CPU as a key into the CPU-to-queue lookup table. If the +2. XPS using receive queues map + +This mapping is used to pick transmit queue based on the receive +queue(s) map configuration set by the administrator. A set of receive +queues can be mapped to a set of transmit queues (many:many), although +the common use case is a 1:1 mapping. This will enable sending packets +on the same queue associations for transmit and receive. This is useful for +busy polling multi-threaded workloads where there are challenges in +associating a given CPU to a given application thread. The application +threads are not pinned to CPUs and each thread handles packets +received on a single queue. The receive queue number is cached in the +socket for the connection. In this model, sending the packets on the same +transmit queue corresponding to the associated receive queue has benefits +in keeping the CPU overhead low. Transmit completion work is locked into +the same queue-association that a given application is polling on. This +avoids the overhead of triggering an interrupt on another CPU. When the +application cleans up the packets during the busy poll, transmit completion +may be processed along with it in the same thread context and so result in +reduced latency. + +XPS is configured per transmit queue by setting a bitmap of +CPUs/receive-queues that may use that queue to transmit. The reverse +mapping, from CPUs to transmit queues or from receive-queues to transmit +queues, is computed and maintained for each network device. When +transmitting the first packet in a flow, the function get_xps_queue() is +called to select a queue. This function uses the ID of the receive queue +for the socket connection for a match in the receive queue-to-transmit queue +lookup table. Alternatively, this function can also use the ID of the +running CPU as a key into the CPU-to-queue lookup table. If the ID matches a single queue, that is used for transmission. If multiple queues match, one is selected by using the flow hash to compute an index -into the set. +into the set. When selecting the transmit queue based on receive queue(s) +map, the transmit device is not validated against the receive device as it +requires expensive lookup operation in the datapath. The queue chosen for transmitting a particular flow is saved in the corresponding socket structure for the flow (e.g. a TCP connection). @@ -404,11 +434,15 @@ acknowledged. XPS is only available if the kconfig symbol CONFIG_XPS is enabled (on by default for SMP). The functionality remains disabled until explicitly -configured. To enable XPS, the bitmap of CPUs that may use a transmit -queue is configured using the sysfs file entry: +configured. To enable XPS, the bitmap of CPUs/receive-queues that may +use a transmit queue is configured using the sysfs file entry: +For selection based on CPUs map: /sys/class/net/<dev>/queues/tx-<n>/xps_cpus +For selection based on receive-queues map: +/sys/class/net/<dev>/queues/tx-<n>/xps_rxqs + == Suggested Configuration For a network device with a single transmission queue, XPS configuration @@ -421,6 +455,11 @@ best CPUs to share a given queue are probably those that share the cache with the CPU that processes transmit completions for that queue (transmit interrupts). +For transmit queue selection based on receive queue(s), XPS has to be +explicitly configured mapping receive-queue(s) to transmit queue(s). If the +user configuration for receive-queue map does not apply, then the transmit +queue is selected based on the CPUs map. + Per TX Queue rate limitation: ============================= diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt index a289285d2412..7d3684e81df6 100644 --- a/Documentation/rfkill.txt +++ b/Documentation/rfkill.txt @@ -9,7 +9,7 @@ rfkill - RF kill switch support Introduction ============ -The rfkill subsystem provides a generic interface to disabling any radio +The rfkill subsystem provides a generic interface for disabling any radio transmitter in the system. When a transmitter is blocked, it shall not radiate any power. @@ -45,7 +45,7 @@ The rfkill subsystem is composed of three main components: * the rfkill drivers. The rfkill core provides API for kernel drivers to register their radio -transmitter with the kernel, methods for turning it on and off and, letting +transmitter with the kernel, methods for turning it on and off, and letting the system know about hardware-disabled states that may be implemented on the device. @@ -54,7 +54,7 @@ ways for userspace to query the current states. See the "Userspace support" section below. When the device is hard-blocked (either by a call to rfkill_set_hw_state() -or from query_hw_block) set_block() will be invoked for additional software +or from query_hw_block), set_block() will be invoked for additional software block, but drivers can ignore the method call since they can use the return value of the function rfkill_set_hw_state() to sync the software state instead of keeping track of calls to set_block(). In fact, drivers should @@ -65,7 +65,6 @@ keeps track of soft and hard block separately. Kernel API ========== - Drivers for radio transmitters normally implement an rfkill driver. Platform drivers might implement input devices if the rfkill button is just @@ -75,14 +74,14 @@ a way to turn on/off the transmitter(s). For some platforms, it is possible that the hardware state changes during suspend/hibernation, in which case it will be necessary to update the rfkill -core with the current state is at resume time. +core with the current state at resume time. To create an rfkill driver, driver's Kconfig needs to have:: depends on RFKILL || !RFKILL to ensure the driver cannot be built-in when rfkill is modular. The !RFKILL -case allows the driver to be built when rfkill is not configured, which +case allows the driver to be built when rfkill is not configured, in which case all rfkill API can still be used but will be provided by static inlines which compile to almost nothing. @@ -91,7 +90,7 @@ rfkill drivers that control devices that can be hard-blocked unless they also assign the poll_hw_block() callback (then the rfkill core will poll the device). Don't do this unless you cannot get the event in any other way. -RFKill provides per-switch LED triggers, which can be used to drive LEDs +rfkill provides per-switch LED triggers, which can be used to drive LEDs according to the switch state (LED_FULL when blocked, LED_OFF otherwise). @@ -114,7 +113,7 @@ a specified type) into a state which also updates the default state for hotplugged devices. After an application opens /dev/rfkill, it can read the current state of all -devices. Changes can be either obtained by either polling the descriptor for +devices. Changes can be obtained by either polling the descriptor for hotplug or state change events or by listening for uevents emitted by the rfkill core framework. @@ -127,8 +126,7 @@ environment variables set:: RFKILL_STATE RFKILL_TYPE -The contents of these variables corresponds to the "name", "state" and +The content of these variables corresponds to the "name", "state" and "type" sysfs files explained above. - For further details consult Documentation/ABI/stable/sysfs-class-rfkill. diff --git a/MAINTAINERS b/MAINTAINERS index 07d1576fc766..b40d702337f2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9158,6 +9158,7 @@ S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlxsw/ +F: tools/testing/selftests/drivers/net/mlxsw/ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) M: mlxsw@mellanox.com @@ -12169,6 +12170,8 @@ S: Maintained F: Documentation/rfkill.txt F: Documentation/ABI/stable/sysfs-class-rfkill F: net/rfkill/ +F: include/linux/rfkill.h +F: include/uapi/linux/rfkill.h RHASHTABLE M: Thomas Graf <tgraf@suug.ch> @@ -12176,7 +12179,9 @@ M: Herbert Xu <herbert@gondor.apana.org.au> L: netdev@vger.kernel.org S: Maintained F: lib/rhashtable.c +F: lib/test_rhashtable.c F: include/linux/rhashtable.h +F: include/linux/rhashtable-types.h RICOH R5C592 MEMORYSTICK DRIVER M: Maxim Levitsky <maximlevitsky@gmail.com> diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index 4dd06767f839..a56a408e9bf7 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -11,13 +11,14 @@ fman0: fman@1a00000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0x0 0x0 0x1a00000 0x100000>; - reg = <0x0 0x1a00000 0x0 0x100000>; + ranges = <0x0 0x0 0x1a00000 0xfe000>; + reg = <0x0 0x1a00000 0x0 0xfe000>; interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -73,9 +74,10 @@ fman0: fman@1a00000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@1afe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x0 0x1afe000 0x0 0x1000>; + interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi index abd01d466de4..6b124f73f67a 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi @@ -37,12 +37,13 @@ fman0: fman@400000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; + ranges = <0 0x400000 0xfe000>; + reg = <0x400000 0xfe000>; interrupts = <96 2 0 0>, <16 2 1 1>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x40 0xc>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -93,9 +94,10 @@ fman0: fman@400000 { reg = <0x87000 0x1000>; status = "disabled"; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@4fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x4fe000 0x1000>; + interrupts = <96 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi index debea75fd3f0..b80aaf5f00a1 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi @@ -37,12 +37,13 @@ fman1: fman@500000 { #size-cells = <1>; cell-index = <1>; compatible = "fsl,fman"; - ranges = <0 0x500000 0x100000>; - reg = <0x500000 0x100000>; + ranges = <0 0x500000 0xfe000>; + reg = <0x500000 0xfe000>; interrupts = <97 2 0 0>, <16 2 1 0>; clocks = <&clockgen 3 1>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x60 0xc>; + ptimer-handle = <&ptp_timer1>; muram@0 { compatible = "fsl,fman-muram"; @@ -93,9 +94,10 @@ fman1: fman@500000 { reg = <0x87000 0x1000>; status = "disabled"; }; +}; - ptp_timer1: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer1: ptp-timer@5fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x5fe000 0x1000>; + interrupts = <97 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi index 3a20e0d1a6d2..d3720fdde26c 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi @@ -37,12 +37,13 @@ fman0: fman@400000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; + ranges = <0 0x400000 0xfe000>; + reg = <0x400000 0xfe000>; interrupts = <96 2 0 0>, <16 2 1 1>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -98,9 +99,10 @@ fman0: fman@400000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@4fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x4fe000 0x1000>; + interrupts = <96 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi index 82750ac944c7..ae34c204a5bc 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi @@ -37,12 +37,13 @@ fman1: fman@500000 { #size-cells = <1>; cell-index = <1>; compatible = "fsl,fman"; - ranges = <0 0x500000 0x100000>; - reg = <0x500000 0x100000>; + ranges = <0 0x500000 0xfe000>; + reg = <0x500000 0xfe000>; interrupts = <97 2 0 0>, <16 2 1 0>; clocks = <&clockgen 3 1>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x820 0x10>; + ptimer-handle = <&ptp_timer1>; muram@0 { compatible = "fsl,fman-muram"; @@ -98,9 +99,10 @@ fman1: fman@500000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer1: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer1: ptp-timer@5fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x5fe000 0x1000>; + interrupts = <97 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi index 7f60b6060176..02f2755842cc 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi @@ -37,12 +37,13 @@ fman0: fman@400000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; + ranges = <0 0x400000 0xfe000>; + reg = <0x400000 0xfe000>; interrupts = <96 2 0 0>, <16 2 1 1>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -86,9 +87,10 @@ fman0: fman@400000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@4fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x4fe000 0x1000>; + interrupts = <96 2 0 0>; }; diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 2c288d1f42bb..e89146ddede6 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1385,14 +1385,12 @@ static void zatm_close(struct atm_vcc *vcc) static int zatm_open(struct atm_vcc *vcc) { - struct zatm_dev *zatm_dev; struct zatm_vcc *zatm_vcc; short vpi = vcc->vpi; int vci = vcc->vci; int error; DPRINTK(">zatm_open\n"); - zatm_dev = ZATM_DEV(vcc->dev); if (!test_bit(ATM_VF_PARTIAL,&vcc->flags)) vcc->dev_data = NULL; if (vci != ATM_VPI_UNSPEC && vpi != ATM_VCI_UNSPEC) diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index 20d0a080a2b0..40c141163f0f 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -972,16 +972,14 @@ static int starturbs(struct bc_state *bcs) rc = -EFAULT; goto error; } + usb_fill_int_urb(urb, bcs->cs->hw.bas->udev, + usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel), + ubc->isoinbuf + k * BAS_INBUFSIZE, + BAS_INBUFSIZE, read_iso_callback, bcs, + BAS_FRAMETIME); - urb->dev = bcs->cs->hw.bas->udev; - urb->pipe = usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel); urb->transfer_flags = URB_ISO_ASAP; - urb->transfer_buffer = ubc->isoinbuf + k * BAS_INBUFSIZE; - urb->transfer_buffer_length = BAS_INBUFSIZE; urb->number_of_packets = BAS_NUMFRAMES; - urb->interval = BAS_FRAMETIME; - urb->complete = read_iso_callback; - urb->context = bcs; for (j = 0; j < BAS_NUMFRAMES; j++) { urb->iso_frame_desc[j].offset = j * BAS_MAXFRAME; urb->iso_frame_desc[j].length = BAS_MAXFRAME; @@ -1005,15 +1003,15 @@ static int starturbs(struct bc_state *bcs) rc = -EFAULT; goto error; } - urb->dev = bcs->cs->hw.bas->udev; - urb->pipe = usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel); + usb_fill_int_urb(urb, bcs->cs->hw.bas->udev, + usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel), + ubc->isooutbuf->data, + sizeof(ubc->isooutbuf->data), + write_iso_callback, &ubc->isoouturbs[k], + BAS_FRAMETIME); + urb->transfer_flags = URB_ISO_ASAP; - urb->transfer_buffer = ubc->isooutbuf->data; - urb->transfer_buffer_length = sizeof(ubc->isooutbuf->data); urb->number_of_packets = BAS_NUMFRAMES; - urb->interval = BAS_FRAMETIME; - urb->complete = write_iso_callback; - urb->context = &ubc->isoouturbs[k]; for (j = 0; j < BAS_NUMFRAMES; ++j) { urb->iso_frame_desc[j].offset = BAS_OUTBUFSIZE; urb->iso_frame_desc[j].length = BAS_NORMFRAME; diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 17cc879ad2bb..6d05946b445e 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -819,6 +819,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, int fifon = fifo->fifonum; int i; int hdlc = 0; + unsigned long flags; if (debug & DBG_HFC_CALL_TRACE) printk(KERN_DEBUG "%s: %s: fifo(%i) len(%i) " @@ -835,7 +836,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, return; } - spin_lock(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (fifo->dch) { rx_skb = fifo->dch->rx_skb; maxlen = fifo->dch->maxlen; @@ -844,7 +845,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, if (fifo->bch) { if (test_bit(FLG_RX_OFF, &fifo->bch->Flags)) { fifo->bch->dropcnt += len; - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } maxlen = bchannel_get_rxbuf(fifo->bch, len); @@ -854,7 +855,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, skb_trim(rx_skb, 0); pr_warning("%s.B%d: No bufferspace for %d bytes\n", hw->name, fifo->bch->nr, len); - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } maxlen = fifo->bch->maxlen; @@ -878,7 +879,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, } else { printk(KERN_DEBUG "%s: %s: No mem for rx_skb\n", hw->name, __func__); - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } } @@ -888,7 +889,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, "for fifo(%d) HFCUSB_D_RX\n", hw->name, __func__, fifon); skb_trim(rx_skb, 0); - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } } @@ -942,7 +943,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len, /* deliver transparent data to layer2 */ recv_Bchannel(fifo->bch, MISDN_ID_ANY, false); } - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); } static void @@ -979,18 +980,19 @@ rx_iso_complete(struct urb *urb) __u8 *buf; static __u8 eof[8]; __u8 s0_state; + unsigned long flags; fifon = fifo->fifonum; status = urb->status; - spin_lock(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (fifo->stop_gracefull) { fifo->stop_gracefull = 0; fifo->active = 0; - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); /* * ISO transfer only partially completed, @@ -1096,15 +1098,16 @@ rx_int_complete(struct urb *urb) struct usb_fifo *fifo = (struct usb_fifo *) urb->context; struct hfcsusb *hw = fifo->hw; static __u8 eof[8]; + unsigned long flags; - spin_lock(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (fifo->stop_gracefull) { fifo->stop_gracefull = 0; fifo->active = 0; - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); fifon = fifo->fifonum; if ((!fifo->active) || (urb->status)) { @@ -1172,12 +1175,13 @@ tx_iso_complete(struct urb *urb) int *tx_idx; int frame_complete, fifon, status, fillempty = 0; __u8 threshbit, *p; + unsigned long flags; - spin_lock(&hw->lock); + spin_lock_irqsave(&hw->lock, flags); if (fifo->stop_gracefull) { fifo->stop_gracefull = 0; fifo->active = 0; - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } @@ -1195,7 +1199,7 @@ tx_iso_complete(struct urb *urb) } else { printk(KERN_DEBUG "%s: %s: neither BCH nor DCH\n", hw->name, __func__); - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); return; } @@ -1375,7 +1379,7 @@ tx_iso_complete(struct urb *urb) hw->name, __func__, symbolic(urb_errlist, status), status, fifon); } - spin_unlock(&hw->lock); + spin_unlock_irqrestore(&hw->lock, flags); } /* diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c index 97ecb3073045..1d4cd01d4685 100644 --- a/drivers/isdn/hisax/hfc_usb.c +++ b/drivers/isdn/hisax/hfc_usb.c @@ -432,16 +432,12 @@ fill_isoc_urb(struct urb *urb, struct usb_device *dev, unsigned int pipe, { int k; - urb->dev = dev; - urb->pipe = pipe; - urb->complete = complete; + usb_fill_int_urb(urb, dev, pipe, buf, packet_size * num_packets, + complete, context, interval); + urb->number_of_packets = num_packets; - urb->transfer_buffer_length = packet_size * num_packets; - urb->context = context; - urb->transfer_buffer = buf; urb->transfer_flags = URB_ISO_ASAP; urb->actual_length = 0; - urb->interval = interval; for (k = 0; k < num_packets; k++) { urb->iso_frame_desc[k].offset = packet_size * k; urb->iso_frame_desc[k].length = packet_size; diff --git a/drivers/isdn/hisax/st5481_usb.c b/drivers/isdn/hisax/st5481_usb.c index 1cb9930d5e24..f207fda691c7 100644 --- a/drivers/isdn/hisax/st5481_usb.c +++ b/drivers/isdn/hisax/st5481_usb.c @@ -408,15 +408,10 @@ fill_isoc_urb(struct urb *urb, struct usb_device *dev, { int k; - urb->dev = dev; - urb->pipe = pipe; - urb->interval = 1; - urb->transfer_buffer = buf; + usb_fill_int_urb(urb, dev, pipe, buf, num_packets * packet_size, + complete, context, 1); + urb->number_of_packets = num_packets; - urb->transfer_buffer_length = num_packets * packet_size; - urb->actual_length = 0; - urb->complete = complete; - urb->context = context; urb->transfer_flags = URB_ISO_ASAP; for (k = 0; k < num_packets; k++) { urb->iso_frame_desc[k].offset = packet_size * k; diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c index 960f26348bb5..b730037a0e2d 100644 --- a/drivers/isdn/i4l/isdn_tty.c +++ b/drivers/isdn/i4l/isdn_tty.c @@ -787,7 +787,7 @@ isdn_tty_suspend(char *id, modem_info *info, atemu *m) cmd.parm.cmsg.para[3] = 4; /* 16 bit 0x0004 Suspend */ cmd.parm.cmsg.para[4] = 0; cmd.parm.cmsg.para[5] = l; - strncpy(&cmd.parm.cmsg.para[6], id, l); + memcpy(&cmd.parm.cmsg.para[6], id, l); cmd.command = CAPI_PUT_MESSAGE; cmd.driver = info->isdn_driver; cmd.arg = info->isdn_channel; @@ -877,7 +877,7 @@ isdn_tty_resume(char *id, modem_info *info, atemu *m) cmd.parm.cmsg.para[3] = 5; /* 16 bit 0x0005 Resume */ cmd.parm.cmsg.para[4] = 0; cmd.parm.cmsg.para[5] = l; - strncpy(&cmd.parm.cmsg.para[6], id, l); + memcpy(&cmd.parm.cmsg.para[6], id, l); cmd.command = CAPI_PUT_MESSAGE; info->dialing = 1; // strcpy(dev->num[i], n); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 22243c480a05..98d4c5a3ff21 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -6339,6 +6339,7 @@ int bnx2x_set_led(struct link_params *params, */ if (!vars->link_up) break; + /* else: fall through */ case LED_MODE_ON: if (((params->phy[EXT_PHY1].type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) || @@ -12521,11 +12522,13 @@ static void bnx2x_phy_def_cfg(struct link_params *params, switch (link_config & PORT_FEATURE_LINK_SPEED_MASK) { case PORT_FEATURE_LINK_SPEED_10M_HALF: phy->req_duplex = DUPLEX_HALF; + /* fall through */ case PORT_FEATURE_LINK_SPEED_10M_FULL: phy->req_line_speed = SPEED_10; break; case PORT_FEATURE_LINK_SPEED_100M_HALF: phy->req_duplex = DUPLEX_HALF; + /* fall through */ case PORT_FEATURE_LINK_SPEED_100M_FULL: phy->req_line_speed = SPEED_100; break; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 57348f2b49a3..71362b7f6040 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -8561,11 +8561,11 @@ int bnx2x_set_int_mode(struct bnx2x *bp) bp->num_queues, 1 + bp->num_cnic_queues); - /* falling through... */ + /* fall through */ case BNX2X_INT_MODE_MSI: bnx2x_enable_msi(bp); - /* falling through... */ + /* fall through */ case BNX2X_INT_MODE_INTX: bp->num_ethernet_queues = 1; bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 8baf9d3eb4b1..3f4d2c8da21a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -3258,7 +3258,7 @@ static int bnx2x_mcast_validate_e2(struct bnx2x *bp, /* DEL command deletes all currently configured MACs */ case BNX2X_MCAST_CMD_DEL: o->set_registry_size(o, 0); - /* Don't break */ + /* fall through */ /* RESTORE command will restore the entire multicast configuration */ case BNX2X_MCAST_CMD_RESTORE: @@ -3592,7 +3592,7 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp, /* DEL command deletes all currently configured MACs */ case BNX2X_MCAST_CMD_DEL: o->set_registry_size(o, 0); - /* Don't break */ + /* fall through */ /* RESTORE command will restore the entire multicast configuration */ case BNX2X_MCAST_CMD_RESTORE: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index dc77bfded865..62da46537734 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1827,6 +1827,7 @@ get_vf: DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n", vf->abs_vfid, qidx); bnx2x_vf_handle_rss_update_eqe(bp, vf); + /* fall through */ case EVENT_RING_OPCODE_VF_FLR: /* Do nothing for now */ return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 176fc9f4d7de..d2dadade1d0e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1727,7 +1727,7 @@ static int bnxt_async_event_process(struct bnxt *bp, speed); } set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event); - /* fall thru */ + /* fall through */ } case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE: set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event); @@ -7984,7 +7984,7 @@ static int bnxt_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb, - bp, bp); + bp, bp, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 795f45024c20..d0699f39ba34 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1544,22 +1544,16 @@ void bnxt_tc_flow_stats_work(struct bnxt *bp) int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid, struct tc_cls_flower_offload *cls_flower) { - int rc = 0; - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: - rc = bnxt_tc_add_flow(bp, src_fid, cls_flower); - break; - + return bnxt_tc_add_flow(bp, src_fid, cls_flower); case TC_CLSFLOWER_DESTROY: - rc = bnxt_tc_del_flow(bp, cls_flower); - break; - + return bnxt_tc_del_flow(bp, cls_flower); case TC_CLSFLOWER_STATS: - rc = bnxt_tc_get_flow_stats(bp, cls_flower); - break; + return bnxt_tc_get_flow_stats(bp, cls_flower); + default: + return -EOPNOTSUPP; } - return rc; } static const struct rhashtable_params bnxt_tc_flow_ht_params = { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index 05d405905906..0745f2dfc80c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -173,7 +173,7 @@ static int bnxt_vf_rep_setup_tc_block(struct net_device *dev, case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, bnxt_vf_rep_setup_tc_block_cb, - vf_rep, vf_rep); + vf_rep, vf_rep, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, bnxt_vf_rep_setup_tc_block_cb, vf_rep); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3be87efdc93d..0a796d5ec893 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -721,6 +721,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum) case TG3_APE_LOCK_GPIO: if (tg3_asic_rev(tp) == ASIC_REV_5761) return 0; + /* else: fall through */ case TG3_APE_LOCK_GRC: case TG3_APE_LOCK_MEM: if (!tp->pci_fn) @@ -781,6 +782,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum) case TG3_APE_LOCK_GPIO: if (tg3_asic_rev(tp) == ASIC_REV_5761) return; + /* else: fall through */ case TG3_APE_LOCK_GRC: case TG3_APE_LOCK_MEM: if (!tp->pci_fn) @@ -10706,28 +10708,40 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) switch (limit) { case 16: tw32(MAC_RCV_RULE_15, 0); tw32(MAC_RCV_VALUE_15, 0); + /* fall through */ case 15: tw32(MAC_RCV_RULE_14, 0); tw32(MAC_RCV_VALUE_14, 0); + /* fall through */ case 14: tw32(MAC_RCV_RULE_13, 0); tw32(MAC_RCV_VALUE_13, 0); + /* fall through */ case 13: tw32(MAC_RCV_RULE_12, 0); tw32(MAC_RCV_VALUE_12, 0); + /* fall through */ case 12: tw32(MAC_RCV_RULE_11, 0); tw32(MAC_RCV_VALUE_11, 0); + /* fall through */ case 11: tw32(MAC_RCV_RULE_10, 0); tw32(MAC_RCV_VALUE_10, 0); + /* fall through */ case 10: tw32(MAC_RCV_RULE_9, 0); tw32(MAC_RCV_VALUE_9, 0); + /* fall through */ case 9: tw32(MAC_RCV_RULE_8, 0); tw32(MAC_RCV_VALUE_8, 0); + /* fall through */ case 8: tw32(MAC_RCV_RULE_7, 0); tw32(MAC_RCV_VALUE_7, 0); + /* fall through */ case 7: tw32(MAC_RCV_RULE_6, 0); tw32(MAC_RCV_VALUE_6, 0); + /* fall through */ case 6: tw32(MAC_RCV_RULE_5, 0); tw32(MAC_RCV_VALUE_5, 0); + /* fall through */ case 5: tw32(MAC_RCV_RULE_4, 0); tw32(MAC_RCV_VALUE_4, 0); + /* fall through */ case 4: /* tw32(MAC_RCV_RULE_3, 0); tw32(MAC_RCV_VALUE_3, 0); */ case 3: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 8a815bb57177..7cb4e753829b 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3569,9 +3569,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) for (j = 0; j < octeon_dev->sriov_info.max_vfs; j++) { u8 vfmac[ETH_ALEN]; - random_ether_addr(&vfmac[0]); - if (__liquidio_set_vf_mac(netdev, j, - &vfmac[0], false)) { + eth_random_addr(vfmac); + if (__liquidio_set_vf_mac(netdev, j, vfmac, false)) { dev_err(&octeon_dev->pci_dev->dev, "Error setting VF%d MAC address\n", j); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 0dbe2d9e22d6..4a8cbd864ef7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -46,6 +46,7 @@ #include <linux/spinlock.h> #include <linux/timer.h> #include <linux/vmalloc.h> +#include <linux/rhashtable.h> #include <linux/etherdevice.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> @@ -521,6 +522,15 @@ enum { MAX_INGQ = MAX_ETH_QSETS + INGQ_EXTRAS, }; +enum { + PRIV_FLAG_PORT_TX_VM_BIT, +}; + +#define PRIV_FLAG_PORT_TX_VM BIT(PRIV_FLAG_PORT_TX_VM_BIT) + +#define PRIV_FLAGS_ADAP 0 +#define PRIV_FLAGS_PORT PRIV_FLAG_PORT_TX_VM + struct adapter; struct sge_rspq; @@ -557,6 +567,7 @@ struct port_info { struct hwtstamp_config tstamp_config; bool ptp_enable; struct sched_table *sched_tbl; + u32 eth_flags; }; struct dentry; @@ -867,6 +878,7 @@ struct adapter { unsigned int flags; unsigned int adap_idx; enum chip_type chip; + u32 eth_flags; int msg_enable; __be16 vxlan_port; @@ -956,6 +968,7 @@ struct adapter { struct chcr_stats_debug chcr_stats; /* TC flower offload */ + bool tc_flower_initialized; struct rhashtable flower_tbl; struct rhashtable_params flower_ht_params; struct timer_list flower_stats_timer; @@ -1333,7 +1346,7 @@ void t4_os_link_changed(struct adapter *adap, int port_id, int link_stat); void t4_free_sge_resources(struct adapter *adap); void t4_free_ofld_rxqs(struct adapter *adap, int n, struct sge_ofld_rxq *q); irq_handler_t t4_intr_handler(struct adapter *adap); -netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev); int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, const struct pkt_gl *gl); int t4_mgmt_tx(struct adapter *adap, struct sk_buff *skb); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index f7eef93ffc87..ddb8b9eba6bf 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -177,6 +177,10 @@ static char loopback_stats_strings[][ETH_GSTRING_LEN] = { "bg3_frames_trunc ", }; +static const char cxgb4_priv_flags_strings[][ETH_GSTRING_LEN] = { + [PRIV_FLAG_PORT_TX_VM_BIT] = "port_tx_vm_wr", +}; + static int get_sset_count(struct net_device *dev, int sset) { switch (sset) { @@ -185,6 +189,8 @@ static int get_sset_count(struct net_device *dev, int sset) ARRAY_SIZE(adapter_stats_strings) + ARRAY_SIZE(channel_stats_strings) + ARRAY_SIZE(loopback_stats_strings); + case ETH_SS_PRIV_FLAGS: + return ARRAY_SIZE(cxgb4_priv_flags_strings); default: return -EOPNOTSUPP; } @@ -235,6 +241,7 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) FW_HDR_FW_VER_MINOR_G(exprom_vers), FW_HDR_FW_VER_MICRO_G(exprom_vers), FW_HDR_FW_VER_BUILD_G(exprom_vers)); + info->n_priv_flags = ARRAY_SIZE(cxgb4_priv_flags_strings); } static void get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -250,6 +257,9 @@ static void get_strings(struct net_device *dev, u32 stringset, u8 *data) data += sizeof(channel_stats_strings); memcpy(data, loopback_stats_strings, sizeof(loopback_stats_strings)); + } else if (stringset == ETH_SS_PRIV_FLAGS) { + memcpy(data, cxgb4_priv_flags_strings, + sizeof(cxgb4_priv_flags_strings)); } } @@ -1499,6 +1509,36 @@ static int cxgb4_get_module_eeprom(struct net_device *dev, offset, len, &data[eprom->len - len]); } +static u32 cxgb4_get_priv_flags(struct net_device *netdev) +{ + struct port_info *pi = netdev_priv(netdev); + struct adapter *adapter = pi->adapter; + + return (adapter->eth_flags | pi->eth_flags); +} + +/** + * set_flags - set/unset specified flags if passed in new_flags + * @cur_flags: pointer to current flags + * @new_flags: new incoming flags + * @flags: set of flags to set/unset + */ +static inline void set_flags(u32 *cur_flags, u32 new_flags, u32 flags) +{ + *cur_flags = (*cur_flags & ~flags) | (new_flags & flags); +} + +static int cxgb4_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct port_info *pi = netdev_priv(netdev); + struct adapter *adapter = pi->adapter; + + set_flags(&adapter->eth_flags, flags, PRIV_FLAGS_ADAP); + set_flags(&pi->eth_flags, flags, PRIV_FLAGS_PORT); + + return 0; +} + static const struct ethtool_ops cxgb_ethtool_ops = { .get_link_ksettings = get_link_ksettings, .set_link_ksettings = set_link_ksettings, @@ -1535,6 +1575,8 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_dump_data = get_dump_data, .get_module_info = cxgb4_get_module_info, .get_module_eeprom = cxgb4_get_module_eeprom, + .get_priv_flags = cxgb4_get_priv_flags, + .set_priv_flags = cxgb4_set_priv_flags, }; void cxgb4_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc03c175a3cd..1c0374cbb890 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3016,7 +3016,7 @@ static int cxgb_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb, - pi, dev); + pi, dev, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi); return 0; @@ -3217,7 +3217,7 @@ static netdev_features_t cxgb_fix_features(struct net_device *dev, static const struct net_device_ops cxgb4_netdev_ops = { .ndo_open = cxgb_open, .ndo_stop = cxgb_close, - .ndo_start_xmit = t4_eth_xmit, + .ndo_start_xmit = t4_start_xmit, .ndo_select_queue = cxgb_select_queue, .ndo_get_stats64 = cxgb_get_stats, .ndo_set_rx_mode = cxgb_set_rxmode, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 3ddd2c4acf68..623f73dd7738 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -874,6 +874,9 @@ int cxgb4_init_tc_flower(struct adapter *adap) { int ret; + if (adap->tc_flower_initialized) + return -EEXIST; + adap->flower_ht_params = cxgb4_tc_flower_ht_params; ret = rhashtable_init(&adap->flower_tbl, &adap->flower_ht_params); if (ret) @@ -882,13 +885,18 @@ int cxgb4_init_tc_flower(struct adapter *adap) INIT_WORK(&adap->flower_stats_work, ch_flower_stats_handler); timer_setup(&adap->flower_stats_timer, ch_flower_stats_cb, 0); mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD); + adap->tc_flower_initialized = true; return 0; } void cxgb4_cleanup_tc_flower(struct adapter *adap) { + if (!adap->tc_flower_initialized) + return; + if (adap->flower_stats_timer.function) del_timer_sync(&adap->flower_stats_timer); cancel_work_sync(&adap->flower_stats_work); rhashtable_destroy(&adap->flower_tbl); + adap->tc_flower_initialized = false; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index 9148abb7994c..7fc656680299 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -539,6 +539,9 @@ void t4_cleanup_sched(struct adapter *adap) struct port_info *pi = netdev2pinfo(adap->port[j]); s = pi->sched_tbl; + if (!s) + continue; + for (i = 0; i < s->sched_size; i++) { struct sched_class *e; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 395e2a0e8d7f..ebb46c472d52 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1288,13 +1288,13 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb, } /** - * t4_eth_xmit - add a packet to an Ethernet Tx queue + * cxgb4_eth_xmit - add a packet to an Ethernet Tx queue * @skb: the packet * @dev: the egress net device * * Add a packet to an SGE Ethernet Tx queue. Runs with softirqs disabled. */ -netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) { u32 wr_mid, ctrl0, op; u64 cntrl, *end, *sgl; @@ -1547,6 +1547,374 @@ out_free: dev_kfree_skb_any(skb); return NETDEV_TX_OK; } +/* Constants ... */ +enum { + /* Egress Queue sizes, producer and consumer indices are all in units + * of Egress Context Units bytes. Note that as far as the hardware is + * concerned, the free list is an Egress Queue (the host produces free + * buffers which the hardware consumes) and free list entries are + * 64-bit PCI DMA addresses. + */ + EQ_UNIT = SGE_EQ_IDXSIZE, + FL_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64), + TXD_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64), + + T4VF_ETHTXQ_MAX_HDR = (sizeof(struct fw_eth_tx_pkt_vm_wr) + + sizeof(struct cpl_tx_pkt_lso_core) + + sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64), +}; + +/** + * t4vf_is_eth_imm - can an Ethernet packet be sent as immediate data? + * @skb: the packet + * + * Returns whether an Ethernet packet is small enough to fit completely as + * immediate data. + */ +static inline int t4vf_is_eth_imm(const struct sk_buff *skb) +{ + /* The VF Driver uses the FW_ETH_TX_PKT_VM_WR firmware Work Request + * which does not accommodate immediate data. We could dike out all + * of the support code for immediate data but that would tie our hands + * too much if we ever want to enhace the firmware. It would also + * create more differences between the PF and VF Drivers. + */ + return false; +} + +/** + * t4vf_calc_tx_flits - calculate the number of flits for a packet TX WR + * @skb: the packet + * + * Returns the number of flits needed for a TX Work Request for the + * given Ethernet packet, including the needed WR and CPL headers. + */ +static inline unsigned int t4vf_calc_tx_flits(const struct sk_buff *skb) +{ + unsigned int flits; + + /* If the skb is small enough, we can pump it out as a work request + * with only immediate data. In that case we just have to have the + * TX Packet header plus the skb data in the Work Request. + */ + if (t4vf_is_eth_imm(skb)) + return DIV_ROUND_UP(skb->len + sizeof(struct cpl_tx_pkt), + sizeof(__be64)); + + /* Otherwise, we're going to have to construct a Scatter gather list + * of the skb body and fragments. We also include the flits necessary + * for the TX Packet Work Request and CPL. We always have a firmware + * Write Header (incorporated as part of the cpl_tx_pkt_lso and + * cpl_tx_pkt structures), followed by either a TX Packet Write CPL + * message or, if we're doing a Large Send Offload, an LSO CPL message + * with an embedded TX Packet Write CPL message. + */ + flits = sgl_len(skb_shinfo(skb)->nr_frags + 1); + if (skb_shinfo(skb)->gso_size) + flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) + + sizeof(struct cpl_tx_pkt_lso_core) + + sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64); + else + flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) + + sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64); + return flits; +} + +/** + * cxgb4_vf_eth_xmit - add a packet to an Ethernet TX queue + * @skb: the packet + * @dev: the egress net device + * + * Add a packet to an SGE Ethernet TX queue. Runs with softirqs disabled. + */ +static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + dma_addr_t addr[MAX_SKB_FRAGS + 1]; + const struct skb_shared_info *ssi; + struct fw_eth_tx_pkt_vm_wr *wr; + int qidx, credits, max_pkt_len; + struct cpl_tx_pkt_core *cpl; + const struct port_info *pi; + unsigned int flits, ndesc; + struct sge_eth_txq *txq; + struct adapter *adapter; + u64 cntrl, *end; + u32 wr_mid; + const size_t fw_hdr_copy_len = sizeof(wr->ethmacdst) + + sizeof(wr->ethmacsrc) + + sizeof(wr->ethtype) + + sizeof(wr->vlantci); + + /* The chip minimum packet length is 10 octets but the firmware + * command that we are using requires that we copy the Ethernet header + * (including the VLAN tag) into the header so we reject anything + * smaller than that ... + */ + if (unlikely(skb->len < fw_hdr_copy_len)) + goto out_free; + + /* Discard the packet if the length is greater than mtu */ + max_pkt_len = ETH_HLEN + dev->mtu; + if (skb_vlan_tag_present(skb)) + max_pkt_len += VLAN_HLEN; + if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len))) + goto out_free; + + /* Figure out which TX Queue we're going to use. */ + pi = netdev_priv(dev); + adapter = pi->adapter; + qidx = skb_get_queue_mapping(skb); + WARN_ON(qidx >= pi->nqsets); + txq = &adapter->sge.ethtxq[pi->first_qset + qidx]; + + /* Take this opportunity to reclaim any TX Descriptors whose DMA + * transfers have completed. + */ + cxgb4_reclaim_completed_tx(adapter, &txq->q, true); + + /* Calculate the number of flits and TX Descriptors we're going to + * need along with how many TX Descriptors will be left over after + * we inject our Work Request. + */ + flits = t4vf_calc_tx_flits(skb); + ndesc = flits_to_desc(flits); + credits = txq_avail(&txq->q) - ndesc; + + if (unlikely(credits < 0)) { + /* Not enough room for this packet's Work Request. Stop the + * TX Queue and return a "busy" condition. The queue will get + * started later on when the firmware informs us that space + * has opened up. + */ + eth_txq_stop(txq); + dev_err(adapter->pdev_dev, + "%s: TX ring %u full while queue awake!\n", + dev->name, qidx); + return NETDEV_TX_BUSY; + } + + if (!t4vf_is_eth_imm(skb) && + unlikely(cxgb4_map_skb(adapter->pdev_dev, skb, addr) < 0)) { + /* We need to map the skb into PCI DMA space (because it can't + * be in-lined directly into the Work Request) and the mapping + * operation failed. Record the error and drop the packet. + */ + txq->mapping_err++; + goto out_free; + } + + wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2)); + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + /* After we're done injecting the Work Request for this + * packet, we'll be below our "stop threshold" so stop the TX + * Queue now and schedule a request for an SGE Egress Queue + * Update message. The queue will get started later on when + * the firmware processes this Work Request and sends us an + * Egress Queue Status Update message indicating that space + * has opened up. + */ + eth_txq_stop(txq); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + + /* Start filling in our Work Request. Note that we do _not_ handle + * the WR Header wrapping around the TX Descriptor Ring. If our + * maximum header size ever exceeds one TX Descriptor, we'll need to + * do something else here. + */ + WARN_ON(DIV_ROUND_UP(T4VF_ETHTXQ_MAX_HDR, TXD_PER_EQ_UNIT) > 1); + wr = (void *)&txq->q.desc[txq->q.pidx]; + wr->equiq_to_len16 = cpu_to_be32(wr_mid); + wr->r3[0] = cpu_to_be32(0); + wr->r3[1] = cpu_to_be32(0); + skb_copy_from_linear_data(skb, (void *)wr->ethmacdst, fw_hdr_copy_len); + end = (u64 *)wr + flits; + + /* If this is a Large Send Offload packet we'll put in an LSO CPL + * message with an encapsulated TX Packet CPL message. Otherwise we + * just use a TX Packet CPL message. + */ + ssi = skb_shinfo(skb); + if (ssi->gso_size) { + struct cpl_tx_pkt_lso_core *lso = (void *)(wr + 1); + bool v6 = (ssi->gso_type & SKB_GSO_TCPV6) != 0; + int l3hdr_len = skb_network_header_len(skb); + int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN; + + wr->op_immdlen = + cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) | + FW_WR_IMMDLEN_V(sizeof(*lso) + + sizeof(*cpl))); + /* Fill in the LSO CPL message. */ + lso->lso_ctrl = + cpu_to_be32(LSO_OPCODE_V(CPL_TX_PKT_LSO) | + LSO_FIRST_SLICE_F | + LSO_LAST_SLICE_F | + LSO_IPV6_V(v6) | + LSO_ETHHDR_LEN_V(eth_xtra_len / 4) | + LSO_IPHDR_LEN_V(l3hdr_len / 4) | + LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff)); + lso->ipid_ofst = cpu_to_be16(0); + lso->mss = cpu_to_be16(ssi->gso_size); + lso->seqno_offset = cpu_to_be32(0); + if (is_t4(adapter->params.chip)) + lso->len = cpu_to_be32(skb->len); + else + lso->len = cpu_to_be32(LSO_T5_XFER_SIZE_V(skb->len)); + + /* Set up TX Packet CPL pointer, control word and perform + * accounting. + */ + cpl = (void *)(lso + 1); + + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) + cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len); + else + cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len); + + cntrl |= TXPKT_CSUM_TYPE_V(v6 ? + TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) | + TXPKT_IPHDR_LEN_V(l3hdr_len); + txq->tso++; + txq->tx_cso += ssi->gso_segs; + } else { + int len; + + len = (t4vf_is_eth_imm(skb) + ? skb->len + sizeof(*cpl) + : sizeof(*cpl)); + wr->op_immdlen = + cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) | + FW_WR_IMMDLEN_V(len)); + + /* Set up TX Packet CPL pointer, control word and perform + * accounting. + */ + cpl = (void *)(wr + 1); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + cntrl = hwcsum(adapter->params.chip, skb) | + TXPKT_IPCSUM_DIS_F; + txq->tx_cso++; + } else { + cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F; + } + } + + /* If there's a VLAN tag present, add that to the list of things to + * do in this Work Request. + */ + if (skb_vlan_tag_present(skb)) { + txq->vlan_ins++; + cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb)); + } + + /* Fill in the TX Packet CPL message header. */ + cpl->ctrl0 = cpu_to_be32(TXPKT_OPCODE_V(CPL_TX_PKT_XT) | + TXPKT_INTF_V(pi->port_id) | + TXPKT_PF_V(0)); + cpl->pack = cpu_to_be16(0); + cpl->len = cpu_to_be16(skb->len); + cpl->ctrl1 = cpu_to_be64(cntrl); + + /* Fill in the body of the TX Packet CPL message with either in-lined + * data or a Scatter/Gather List. + */ + if (t4vf_is_eth_imm(skb)) { + /* In-line the packet's data and free the skb since we don't + * need it any longer. + */ + cxgb4_inline_tx_skb(skb, &txq->q, cpl + 1); + dev_consume_skb_any(skb); + } else { + /* Write the skb's Scatter/Gather list into the TX Packet CPL + * message and retain a pointer to the skb so we can free it + * later when its DMA completes. (We store the skb pointer + * in the Software Descriptor corresponding to the last TX + * Descriptor used by the Work Request.) + * + * The retained skb will be freed when the corresponding TX + * Descriptors are reclaimed after their DMAs complete. + * However, this could take quite a while since, in general, + * the hardware is set up to be lazy about sending DMA + * completion notifications to us and we mostly perform TX + * reclaims in the transmit routine. + * + * This is good for performamce but means that we rely on new + * TX packets arriving to run the destructors of completed + * packets, which open up space in their sockets' send queues. + * Sometimes we do not get such new packets causing TX to + * stall. A single UDP transmitter is a good example of this + * situation. We have a clean up timer that periodically + * reclaims completed packets but it doesn't run often enough + * (nor do we want it to) to prevent lengthy stalls. A + * solution to this problem is to run the destructor early, + * after the packet is queued but before it's DMAd. A con is + * that we lie to socket memory accounting, but the amount of + * extra memory is reasonable (limited by the number of TX + * descriptors), the packets do actually get freed quickly by + * new packets almost always, and for protocols like TCP that + * wait for acks to really free up the data the extra memory + * is even less. On the positive side we run the destructors + * on the sending CPU rather than on a potentially different + * completing CPU, usually a good thing. + * + * Run the destructor before telling the DMA engine about the + * packet to make sure it doesn't complete and get freed + * prematurely. + */ + struct ulptx_sgl *sgl = (struct ulptx_sgl *)(cpl + 1); + struct sge_txq *tq = &txq->q; + int last_desc; + + /* If the Work Request header was an exact multiple of our TX + * Descriptor length, then it's possible that the starting SGL + * pointer lines up exactly with the end of our TX Descriptor + * ring. If that's the case, wrap around to the beginning + * here ... + */ + if (unlikely((void *)sgl == (void *)tq->stat)) { + sgl = (void *)tq->desc; + end = (void *)((void *)tq->desc + + ((void *)end - (void *)tq->stat)); + } + + cxgb4_write_sgl(skb, tq, sgl, end, 0, addr); + skb_orphan(skb); + + last_desc = tq->pidx + ndesc - 1; + if (last_desc >= tq->size) + last_desc -= tq->size; + tq->sdesc[last_desc].skb = skb; + tq->sdesc[last_desc].sgl = sgl; + } + + /* Advance our internal TX Queue state, tell the hardware about + * the new TX descriptors and return success. + */ + txq_advance(&txq->q, ndesc); + + cxgb4_ring_tx_db(adapter, &txq->q, ndesc); + return NETDEV_TX_OK; + +out_free: + /* An error of some sort happened. Free the TX skb and tell the + * OS that we've "dealt" with the packet ... + */ + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; +} + +netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct port_info *pi = netdev_priv(dev); + + if (unlikely(pi->eth_flags & PRIV_FLAG_PORT_TX_VM)) + return cxgb4_vf_eth_xmit(skb, dev); + + return cxgb4_eth_xmit(skb, dev); +} + /** * reclaim_completed_tx_imm - reclaim completed control-queue Tx descs * @q: the SGE control Tx queue diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index c7f8d0441278..e3adf435913e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -188,6 +188,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */ CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */ CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */ + CH_PCI_ID_TABLE_FENTRY(0x50ae), /* Custom T540-XL-SO */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 6d7404f66f84..ce1f04fdbf70 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2435,7 +2435,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->mac_addr[0], port->mac_addr[1], port->mac_addr[2]); dev_info(dev, "using a random ethernet address\n"); - random_ether_addr(netdev->dev_addr); + eth_random_addr(netdev->dev_addr); } gmac_write_mac_address(netdev); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ab02057ac730..65a22cd9aef2 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1171,7 +1171,7 @@ static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, buf_prefix_content.priv_data_size = buf_layout->priv_data_size; buf_prefix_content.pass_prs_result = true; buf_prefix_content.pass_hash_result = true; - buf_prefix_content.pass_time_stamp = false; + buf_prefix_content.pass_time_stamp = true; buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT; params.specific_params.non_rx_params.err_fqid = errq->fqid; @@ -1213,7 +1213,7 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, buf_prefix_content.priv_data_size = buf_layout->priv_data_size; buf_prefix_content.pass_prs_result = true; buf_prefix_content.pass_hash_result = true; - buf_prefix_content.pass_time_stamp = false; + buf_prefix_content.pass_time_stamp = true; buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT; rx_p = ¶ms.specific_params.rx_params; @@ -1610,14 +1610,28 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, { const enum dma_data_direction dma_dir = DMA_TO_DEVICE; struct device *dev = priv->net_dev->dev.parent; + struct skb_shared_hwtstamps shhwtstamps; dma_addr_t addr = qm_fd_addr(fd); const struct qm_sg_entry *sgt; struct sk_buff **skbh, *skb; int nr_frags, i; + u64 ns; skbh = (struct sk_buff **)phys_to_virt(addr); skb = *skbh; + if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + + if (!fman_port_get_tstamp(priv->mac_dev->port[TX], (void *)skbh, + &ns)) { + shhwtstamps.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(skb, &shhwtstamps); + } else { + dev_warn(dev, "fman_port_get_tstamp failed!\n"); + } + } + if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) { nr_frags = skb_shinfo(skb)->nr_frags; dma_unmap_single(dev, addr, @@ -2087,6 +2101,11 @@ static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) if (unlikely(err < 0)) goto skb_to_fd_failed; + if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD); + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + } + if (likely(dpaa_xmit(priv, percpu_stats, queue_mapping, &fd) == 0)) return NETDEV_TX_OK; @@ -2228,6 +2247,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, struct qman_fq *fq, const struct qm_dqrr_entry *dq) { + struct skb_shared_hwtstamps *shhwtstamps; struct rtnl_link_stats64 *percpu_stats; struct dpaa_percpu_priv *percpu_priv; const struct qm_fd *fd = &dq->fd; @@ -2241,6 +2261,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, struct sk_buff *skb; int *count_ptr; void *vaddr; + u64 ns; fd_status = be32_to_cpu(fd->status); fd_format = qm_fd_get_format(fd); @@ -2305,6 +2326,16 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, if (!skb) return qman_cb_dqrr_consume; + if (priv->rx_tstamp) { + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + + if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns)) + shhwtstamps->hwtstamp = ns_to_ktime(ns); + else + dev_warn(net_dev->dev.parent, "fman_port_get_tstamp failed!\n"); + } + skb->protocol = eth_type_trans(skb, net_dev); if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use && @@ -2524,11 +2555,58 @@ static int dpaa_eth_stop(struct net_device *net_dev) return err; } +static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + struct dpaa_priv *priv = netdev_priv(dev); + struct hwtstamp_config config; + + if (copy_from_user(&config, rq->ifr_data, sizeof(config))) + return -EFAULT; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + /* Couldn't disable rx/tx timestamping separately. + * Do nothing here. + */ + priv->tx_tstamp = false; + break; + case HWTSTAMP_TX_ON: + priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true); + priv->tx_tstamp = true; + break; + default: + return -ERANGE; + } + + if (config.rx_filter == HWTSTAMP_FILTER_NONE) { + /* Couldn't disable rx/tx timestamping separately. + * Do nothing here. + */ + priv->rx_tstamp = false; + } else { + priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true); + priv->rx_tstamp = true; + /* TS is set for all frame types, not only those requested */ + config.rx_filter = HWTSTAMP_FILTER_ALL; + } + + return copy_to_user(rq->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd) { - if (!net_dev->phydev) - return -EINVAL; - return phy_mii_ioctl(net_dev->phydev, rq, cmd); + int ret = -EINVAL; + + if (cmd == SIOCGMIIREG) { + if (net_dev->phydev) + return phy_mii_ioctl(net_dev->phydev, rq, cmd); + } + + if (cmd == SIOCSHWTSTAMP) + return dpaa_ts_ioctl(net_dev, rq, cmd); + + return ret; } static const struct net_device_ops dpaa_ops = { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index bd9422082f83..af320f83c742 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -182,6 +182,9 @@ struct dpaa_priv { struct dpaa_buffer_layout buf_layout[2]; u16 rx_headroom; + + bool tx_tstamp; /* Tx timestamping enabled */ + bool rx_tstamp; /* Rx timestamping enabled */ }; /* from dpaa_ethtool.c */ diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 2f933b6b2f4e..3184c8f7cdd0 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -32,6 +32,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/string.h> +#include <linux/of_platform.h> +#include <linux/net_tstamp.h> +#include <linux/fsl/ptp_qoriq.h> #include "dpaa_eth.h" #include "mac.h" @@ -515,6 +518,41 @@ static int dpaa_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } +static int dpaa_get_ts_info(struct net_device *net_dev, + struct ethtool_ts_info *info) +{ + struct device *dev = net_dev->dev.parent; + struct device_node *mac_node = dev->of_node; + struct device_node *fman_node = NULL, *ptp_node = NULL; + struct platform_device *ptp_dev = NULL; + struct qoriq_ptp *ptp = NULL; + + info->phc_index = -1; + + fman_node = of_get_parent(mac_node); + if (fman_node) + ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0); + + if (ptp_node) + ptp_dev = of_find_device_by_node(ptp_node); + + if (ptp_dev) + ptp = platform_get_drvdata(ptp_dev); + + if (ptp) + info->phc_index = ptp->phc_index; + + info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); + info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_ALL); + + return 0; +} + const struct ethtool_ops dpaa_ethtool_ops = { .get_drvinfo = dpaa_get_drvinfo, .get_msglevel = dpaa_get_msglevel, @@ -530,4 +568,5 @@ const struct ethtool_ops dpaa_ethtool_ops = { .set_link_ksettings = dpaa_set_link_ksettings, .get_rxnfc = dpaa_get_rxnfc, .set_rxnfc = dpaa_set_rxnfc, + .get_ts_info = dpaa_get_ts_info, }; diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 9530405030a7..c415ac67cb7b 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2801,7 +2801,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) of_node_put(muram_node); of_node_put(fm_node); - err = devm_request_irq(&of_dev->dev, irq, fman_irq, 0, "fman", fman); + err = devm_request_irq(&of_dev->dev, irq, fman_irq, IRQF_SHARED, + "fman", fman); if (err < 0) { dev_err(&of_dev->dev, "%s: irq %d allocation failed (error = %d)\n", __func__, irq, err); diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index bfa02e0014ae..935c317fa696 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -41,6 +41,7 @@ /* Frame queue Context Override */ #define FM_FD_CMD_FCO 0x80000000 #define FM_FD_CMD_RPD 0x40000000 /* Read Prepended Data */ +#define FM_FD_CMD_UPD 0x20000000 /* Update Prepended Data */ #define FM_FD_CMD_DTC 0x10000000 /* Do L4 Checksum */ /* TX-Port: Unsupported Format */ diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 57b1e2b47c0a..1ca543ac8f2c 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -123,11 +123,13 @@ #define DTSEC_ECNTRL_R100M 0x00000008 #define DTSEC_ECNTRL_QSGMIIM 0x00000001 +#define TCTRL_TTSE 0x00000040 #define TCTRL_GTS 0x00000020 #define RCTRL_PAL_MASK 0x001f0000 #define RCTRL_PAL_SHIFT 16 #define RCTRL_GHTX 0x00000400 +#define RCTRL_RTSE 0x00000040 #define RCTRL_GRS 0x00000020 #define RCTRL_MPROM 0x00000008 #define RCTRL_RSF 0x00000004 @@ -1136,6 +1138,31 @@ int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable) return 0; } +int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 rctrl, tctrl; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + rctrl = ioread32be(®s->rctrl); + tctrl = ioread32be(®s->tctrl); + + if (enable) { + rctrl |= RCTRL_RTSE; + tctrl |= TCTRL_TTSE; + } else { + rctrl &= ~RCTRL_RTSE; + tctrl &= ~TCTRL_TTSE; + } + + iowrite32be(rctrl, ®s->rctrl); + iowrite32be(tctrl, ®s->tctrl); + + return 0; +} + int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) { struct dtsec_regs __iomem *regs = dtsec->regs; diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h index 1a689adf5a22..5149d96ec2c1 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -56,5 +56,6 @@ int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version); int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable); +int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable); #endif /* __DTSEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 446a97b792e3..bc6eb30aa20f 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -964,6 +964,11 @@ int memac_set_allmulti(struct fman_mac *memac, bool enable) return 0; } +int memac_set_tstamp(struct fman_mac *memac, bool enable) +{ + return 0; /* Always enabled. */ +} + int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) { struct memac_regs __iomem *regs = memac->regs; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index b5a50338ed9a..b2c671ec0ce7 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -58,5 +58,6 @@ int memac_set_exception(struct fman_mac *memac, int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); int memac_set_allmulti(struct fman_mac *memac, bool enable); +int memac_set_tstamp(struct fman_mac *memac, bool enable); #endif /* __MEMAC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index ecbf6187e13a..ee82ee1384eb 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1739,6 +1739,18 @@ int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset) } EXPORT_SYMBOL(fman_port_get_hash_result_offset); +int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp) +{ + if (port->buffer_offsets.time_stamp_offset == ILLEGAL_BASE) + return -EINVAL; + + *tstamp = be64_to_cpu(*(__be64 *)(data + + port->buffer_offsets.time_stamp_offset)); + + return 0; +} +EXPORT_SYMBOL(fman_port_get_tstamp); + static int fman_port_probe(struct platform_device *of_dev) { struct fman_port *port; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.h b/drivers/net/ethernet/freescale/fman/fman_port.h index e86ca6a34e4e..9dbb69f40121 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.h +++ b/drivers/net/ethernet/freescale/fman/fman_port.h @@ -153,6 +153,8 @@ u32 fman_port_get_qman_channel_id(struct fman_port *port); int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset); +int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp); + struct fman_port *fman_port_bind(struct device *dev); #endif /* __FMAN_PORT_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 284735d4ebe9..40705938eecc 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -44,6 +44,7 @@ #define TGEC_TX_IPG_LENGTH_MASK 0x000003ff /* Command and Configuration Register (COMMAND_CONFIG) */ +#define CMD_CFG_EN_TIMESTAMP 0x00100000 #define CMD_CFG_NO_LEN_CHK 0x00020000 #define CMD_CFG_PAUSE_IGNORE 0x00000100 #define CMF_CFG_CRC_FWD 0x00000040 @@ -588,6 +589,26 @@ int tgec_set_allmulti(struct fman_mac *tgec, bool enable) return 0; } +int tgec_set_tstamp(struct fman_mac *tgec, bool enable) +{ + struct tgec_regs __iomem *regs = tgec->regs; + u32 tmp; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + tmp = ioread32be(®s->command_config); + + if (enable) + tmp |= CMD_CFG_EN_TIMESTAMP; + else + tmp &= ~CMD_CFG_EN_TIMESTAMP; + + iowrite32be(tmp, ®s->command_config); + + return 0; +} + int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) { struct tgec_regs __iomem *regs = tgec->regs; diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h index cbbd3b422a98..3bfd1062b386 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.h +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -52,5 +52,6 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); int tgec_get_version(struct fman_mac *tgec, u32 *mac_version); int tgec_set_allmulti(struct fman_mac *tgec, bool enable); +int tgec_set_tstamp(struct fman_mac *tgec, bool enable); #endif /* __TGEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 7b5b95f52c09..a847b9c3b31a 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -471,6 +471,7 @@ static void setup_dtsec(struct mac_device *mac_dev) mac_dev->set_rx_pause = dtsec_accept_rx_pause_frames; mac_dev->set_exception = dtsec_set_exception; mac_dev->set_allmulti = dtsec_set_allmulti; + mac_dev->set_tstamp = dtsec_set_tstamp; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; @@ -490,6 +491,7 @@ static void setup_tgec(struct mac_device *mac_dev) mac_dev->set_rx_pause = tgec_accept_rx_pause_frames; mac_dev->set_exception = tgec_set_exception; mac_dev->set_allmulti = tgec_set_allmulti; + mac_dev->set_tstamp = tgec_set_tstamp; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; @@ -509,6 +511,7 @@ static void setup_memac(struct mac_device *mac_dev) mac_dev->set_rx_pause = memac_accept_rx_pause_frames; mac_dev->set_exception = memac_set_exception; mac_dev->set_allmulti = memac_set_allmulti; + mac_dev->set_tstamp = memac_set_tstamp; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index b520cec120ee..824a81a9f350 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -68,6 +68,7 @@ struct mac_device { int (*set_promisc)(struct fman_mac *mac_dev, bool enable); int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); + int (*set_tstamp)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, struct mac_device *mac_dev); int (*set_rx_pause)(struct fman_mac *mac_dev, bool en); diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 42fca3208c0b..22a817da861e 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3096,6 +3096,7 @@ static int ucc_geth_start_xmit(struct sk_buff *skb, struct net_device *dev) ugeth_vdbg("%s: IN", __func__); + netdev_sent_queue(dev, skb->len); spin_lock_irqsave(&ugeth->lock, flags); dev->stats.tx_bytes += skb->len; @@ -3240,6 +3241,8 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ) { /* Start from the next BD that should be filled */ struct ucc_geth_private *ugeth = netdev_priv(dev); + unsigned int bytes_sent = 0; + int howmany = 0; u8 __iomem *bd; /* BD pointer */ u32 bd_status; @@ -3257,7 +3260,8 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ) skb = ugeth->tx_skbuff[txQ][ugeth->skb_dirtytx[txQ]]; if (!skb) break; - + howmany++; + bytes_sent += skb->len; dev->stats.tx_packets++; dev_consume_skb_any(skb); @@ -3279,6 +3283,7 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ) bd_status = in_be32((u32 __iomem *)bd); } ugeth->confBd[txQ] = bd; + netdev_completed_queue(dev, howmany, bytes_sent); return 0; } @@ -3479,6 +3484,7 @@ static int ucc_geth_open(struct net_device *dev) phy_start(ugeth->phydev); napi_enable(&ugeth->napi); + netdev_reset_queue(dev); netif_start_queue(dev); device_set_wakeup_capable(&dev->dev, @@ -3509,6 +3515,7 @@ static int ucc_geth_close(struct net_device *dev) free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev); netif_stop_queue(dev); + netdev_reset_queue(dev); return 0; } diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index fb1a7251f45d..25152715396b 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -85,10 +85,12 @@ config HNS3 drivers(like ODP)to register with HNAE devices and their associated operations. +if HNS3 + config HNS3_HCLGE tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" + default m depends on PCI_MSI - depends on HNS3 ---help--- This selects the HNS3_HCLGE network acceleration engine & its hardware compatibility layer. The engine would be used in Hisilicon hip08 family of @@ -97,16 +99,15 @@ config HNS3_HCLGE config HNS3_DCB bool "Hisilicon HNS3 Data Center Bridge Support" default n - depends on HNS3 && HNS3_HCLGE && DCB + depends on HNS3_HCLGE && DCB ---help--- Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver. If unsure, say N. config HNS3_HCLGEVF - tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support" - depends on PCI_MSI - depends on HNS3 + tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support" + depends on PCI_MSI depends on HNS3_HCLGE ---help--- This selects the HNS3 VF drivers network acceleration engine & its hardware @@ -115,11 +116,13 @@ config HNS3_HCLGEVF config HNS3_ENET tristate "Hisilicon HNS3 Ethernet Device Support" + default m depends on 64BIT && PCI - depends on HNS3 ---help--- This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08 family of SoCs. This module depends upon HNAE3 driver to access the HNAE3 devices and their associated operations. +endif #HNS3 + endif # NET_VENDOR_HISILICON diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 340e28211135..14374a856d30 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -904,7 +904,7 @@ static int hip04_mac_probe(struct platform_device *pdev) hip04_config_port(ndev, SPEED_100, DUPLEX_FULL); hip04_config_fifo(priv); - random_ether_addr(ndev->dev_addr); + eth_random_addr(ndev->dev_addr); hip04_update_mac_address(ndev); ret = hip04_alloc_ring(ndev, d); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 9d79dad2c6aa..0762ad18fdcc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -8,7 +8,6 @@ */ #include <linux/list.h> -#include <linux/slab.h> #include <linux/spinlock.h> #include "hnae3.h" @@ -41,13 +40,13 @@ static void hnae3_set_client_init_flag(struct hnae3_client *client, { switch (client->type) { case HNAE3_CLIENT_KNIC: - hnae_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited); + hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited); break; case HNAE3_CLIENT_UNIC: - hnae_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited); + hnae3_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited); break; case HNAE3_CLIENT_ROCE: - hnae_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited); + hnae3_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited); break; default: break; @@ -61,16 +60,16 @@ static int hnae3_get_client_init_flag(struct hnae3_client *client, switch (client->type) { case HNAE3_CLIENT_KNIC: - inited = hnae_get_bit(ae_dev->flag, + inited = hnae3_get_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B); break; case HNAE3_CLIENT_UNIC: - inited = hnae_get_bit(ae_dev->flag, + inited = hnae3_get_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B); break; case HNAE3_CLIENT_ROCE: - inited = hnae_get_bit(ae_dev->flag, - HNAE3_ROCE_CLIENT_INITED_B); + inited = hnae3_get_bit(ae_dev->flag, + HNAE3_ROCE_CLIENT_INITED_B); break; default: break; @@ -86,7 +85,7 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client, /* check if this client matches the type of ae_dev */ if (!(hnae3_client_match(client->type, ae_dev->dev_type) && - hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) { + hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) { return 0; } @@ -95,7 +94,7 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client, ret = ae_dev->ops->init_client_instance(client, ae_dev); if (ret) { dev_err(&ae_dev->pdev->dev, - "fail to instantiate client\n"); + "fail to instantiate client, ret = %d\n", ret); return ret; } @@ -135,7 +134,8 @@ int hnae3_register_client(struct hnae3_client *client) ret = hnae3_match_n_instantiate(client, ae_dev, true); if (ret) dev_err(&ae_dev->pdev->dev, - "match and instantiation failed for port\n"); + "match and instantiation failed for port, ret = %d\n", + ret); } exit: @@ -185,11 +185,12 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) ae_dev->ops = ae_algo->ops; ret = ae_algo->ops->init_ae_dev(ae_dev); if (ret) { - dev_err(&ae_dev->pdev->dev, "init ae_dev error.\n"); + dev_err(&ae_dev->pdev->dev, + "init ae_dev error, ret = %d\n", ret); continue; } - hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); + hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); /* check the client list for the match with this ae_dev type and * initialize the figure out client instance @@ -198,7 +199,8 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) ret = hnae3_match_n_instantiate(client, ae_dev, true); if (ret) dev_err(&ae_dev->pdev->dev, - "match and instantiation failed\n"); + "match and instantiation failed, ret = %d\n", + ret); } } @@ -218,7 +220,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo) mutex_lock(&hnae3_common_lock); /* Check if there are matched ae_dev */ list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { - if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)) + if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)) continue; id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); @@ -232,7 +234,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo) hnae3_match_n_instantiate(client, ae_dev, false); ae_algo->ops->uninit_ae_dev(ae_dev); - hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); + hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); } list_del(&ae_algo->node); @@ -271,11 +273,12 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) /* ae_dev init should set flag */ ret = ae_dev->ops->init_ae_dev(ae_dev); if (ret) { - dev_err(&ae_dev->pdev->dev, "init ae_dev error\n"); + dev_err(&ae_dev->pdev->dev, + "init ae_dev error, ret = %d\n", ret); goto out_err; } - hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); + hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); break; } @@ -286,7 +289,8 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) ret = hnae3_match_n_instantiate(client, ae_dev, true); if (ret) dev_err(&ae_dev->pdev->dev, - "match and instantiation failed\n"); + "match and instantiation failed, ret = %d\n", + ret); } out_err: @@ -306,7 +310,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev) mutex_lock(&hnae3_common_lock); /* Check if there are matched ae_algo */ list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) { - if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)) + if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)) continue; id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); @@ -317,7 +321,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev) hnae3_match_n_instantiate(client, ae_dev, false); ae_algo->ops->uninit_ae_dev(ae_dev); - hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); + hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); } list_del(&ae_dev->node); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 8acb1d116a02..da806fdfbbe6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -62,10 +62,10 @@ BIT(HNAE3_DEV_SUPPORT_ROCE_B)) #define hnae3_dev_roce_supported(hdev) \ - hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) + hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) #define hnae3_dev_dcb_supported(hdev) \ - hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) + hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) #define ring_ptr_move_fw(ring, p) \ ((ring)->p = ((ring)->p + 1) % (ring)->desc_num) @@ -167,7 +167,6 @@ struct hnae3_client_ops { #define HNAE3_CLIENT_NAME_LENGTH 16 struct hnae3_client { char name[HNAE3_CLIENT_NAME_LENGTH]; - u16 version; unsigned long state; enum hnae3_client_type type; const struct hnae3_client_ops *ops; @@ -436,7 +435,6 @@ struct hnae3_dcb_ops { struct hnae3_ae_algo { const struct hnae3_ae_ops *ops; struct list_head node; - char name[HNAE3_CLASS_NAME_SIZE]; const struct pci_device_id *pdev_id_table; }; @@ -509,17 +507,17 @@ struct hnae3_handle { u32 numa_node_mask; /* for multi-chip support */ }; -#define hnae_set_field(origin, mask, shift, val) \ +#define hnae3_set_field(origin, mask, shift, val) \ do { \ (origin) &= (~(mask)); \ (origin) |= ((val) << (shift)) & (mask); \ } while (0) -#define hnae_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift)) +#define hnae3_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift)) -#define hnae_set_bit(origin, shift, val) \ - hnae_set_field((origin), (0x1 << (shift)), (shift), (val)) -#define hnae_get_bit(origin, shift) \ - hnae_get_field((origin), (0x1 << (shift)), (shift)) +#define hnae3_set_bit(origin, shift, val) \ + hnae3_set_field((origin), (0x1 << (shift)), (shift), (val)) +#define hnae3_get_bit(origin, shift) \ + hnae3_get_field((origin), (0x1 << (shift)), (shift)) void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 25a73bb2e642..7e34d5fff3ae 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -493,8 +493,8 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen, /* find the txbd field values */ *paylen = skb->len - hdr_len; - hnae_set_bit(*type_cs_vlan_tso, - HNS3_TXD_TSO_B, 1); + hnae3_set_bit(*type_cs_vlan_tso, + HNS3_TXD_TSO_B, 1); /* get MSS for TSO */ *mss = skb_shinfo(skb)->gso_size; @@ -586,21 +586,21 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, /* compute L2 header size for normal packet, defined in 2 Bytes */ l2_len = l3.hdr - skb->data; - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, - HNS3_TXD_L2LEN_S, l2_len >> 1); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, l2_len >> 1); /* tunnel packet*/ if (skb->encapsulation) { /* compute OL2 header size, defined in 2 Bytes */ ol2_len = l2_len; - hnae_set_field(*ol_type_vlan_len_msec, - HNS3_TXD_L2LEN_M, - HNS3_TXD_L2LEN_S, ol2_len >> 1); + hnae3_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, ol2_len >> 1); /* compute OL3 header size, defined in 4 Bytes */ ol3_len = l4.hdr - l3.hdr; - hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M, - HNS3_TXD_L3LEN_S, ol3_len >> 2); + hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M, + HNS3_TXD_L3LEN_S, ol3_len >> 2); /* MAC in UDP, MAC in GRE (0x6558)*/ if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) { @@ -609,16 +609,17 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, /* compute OL4 header size, defined in 4 Bytes. */ ol4_len = l2_hdr - l4.hdr; - hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_M, - HNS3_TXD_L4LEN_S, ol4_len >> 2); + hnae3_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_L4LEN_M, HNS3_TXD_L4LEN_S, + ol4_len >> 2); /* switch IP header ptr from outer to inner header */ l3.hdr = skb_inner_network_header(skb); /* compute inner l2 header size, defined in 2 Bytes. */ l2_len = l3.hdr - l2_hdr; - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, - HNS3_TXD_L2LEN_S, l2_len >> 1); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, l2_len >> 1); } else { /* skb packet types not supported by hardware, * txbd len fild doesn't be filled. @@ -634,22 +635,24 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, /* compute inner(/normal) L3 header size, defined in 4 Bytes */ l3_len = l4.hdr - l3.hdr; - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M, - HNS3_TXD_L3LEN_S, l3_len >> 2); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M, + HNS3_TXD_L3LEN_S, l3_len >> 2); /* compute inner(/normal) L4 header size, defined in 4 Bytes */ switch (l4_proto) { case IPPROTO_TCP: - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, - HNS3_TXD_L4LEN_S, l4.tcp->doff); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, l4.tcp->doff); break; case IPPROTO_SCTP: - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, - HNS3_TXD_L4LEN_S, (sizeof(struct sctphdr) >> 2)); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, + (sizeof(struct sctphdr) >> 2)); break; case IPPROTO_UDP: - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, - HNS3_TXD_L4LEN_S, (sizeof(struct udphdr) >> 2)); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, + (sizeof(struct udphdr) >> 2)); break; default: /* skb packet types not supported by hardware, @@ -703,32 +706,34 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto, /* define outer network header type.*/ if (skb->protocol == htons(ETH_P_IP)) { if (skb_is_gso(skb)) - hnae_set_field(*ol_type_vlan_len_msec, - HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S, - HNS3_OL3T_IPV4_CSUM); + hnae3_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_OL3T_M, + HNS3_TXD_OL3T_S, + HNS3_OL3T_IPV4_CSUM); else - hnae_set_field(*ol_type_vlan_len_msec, - HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S, - HNS3_OL3T_IPV4_NO_CSUM); + hnae3_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_OL3T_M, + HNS3_TXD_OL3T_S, + HNS3_OL3T_IPV4_NO_CSUM); } else if (skb->protocol == htons(ETH_P_IPV6)) { - hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M, - HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6); + hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M, + HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6); } /* define tunnel type(OL4).*/ switch (l4_proto) { case IPPROTO_UDP: - hnae_set_field(*ol_type_vlan_len_msec, - HNS3_TXD_TUNTYPE_M, - HNS3_TXD_TUNTYPE_S, - HNS3_TUN_MAC_IN_UDP); + hnae3_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_TUNTYPE_M, + HNS3_TXD_TUNTYPE_S, + HNS3_TUN_MAC_IN_UDP); break; case IPPROTO_GRE: - hnae_set_field(*ol_type_vlan_len_msec, - HNS3_TXD_TUNTYPE_M, - HNS3_TXD_TUNTYPE_S, - HNS3_TUN_NVGRE); + hnae3_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_TUNTYPE_M, + HNS3_TXD_TUNTYPE_S, + HNS3_TUN_NVGRE); break; default: /* drop the skb tunnel packet if hardware don't support, @@ -749,43 +754,43 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto, } if (l3.v4->version == 4) { - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, - HNS3_TXD_L3T_S, HNS3_L3T_IPV4); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, + HNS3_TXD_L3T_S, HNS3_L3T_IPV4); /* the stack computes the IP header already, the only time we * need the hardware to recompute it is in the case of TSO. */ if (skb_is_gso(skb)) - hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1); + hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1); - hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); + hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); } else if (l3.v6->version == 6) { - hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, - HNS3_TXD_L3T_S, HNS3_L3T_IPV6); - hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); + hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, + HNS3_TXD_L3T_S, HNS3_L3T_IPV6); + hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); } switch (l4_proto) { case IPPROTO_TCP: - hnae_set_field(*type_cs_vlan_tso, - HNS3_TXD_L4T_M, - HNS3_TXD_L4T_S, - HNS3_L4T_TCP); + hnae3_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_TCP); break; case IPPROTO_UDP: if (hns3_tunnel_csum_bug(skb)) break; - hnae_set_field(*type_cs_vlan_tso, - HNS3_TXD_L4T_M, - HNS3_TXD_L4T_S, - HNS3_L4T_UDP); + hnae3_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_UDP); break; case IPPROTO_SCTP: - hnae_set_field(*type_cs_vlan_tso, - HNS3_TXD_L4T_M, - HNS3_TXD_L4T_S, - HNS3_L4T_SCTP); + hnae3_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_SCTP); break; default: /* drop the skb tunnel packet if hardware don't support, @@ -807,11 +812,11 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto, static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end) { /* Config bd buffer end */ - hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M, - HNS3_TXD_BDTYPE_S, 0); - hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end); - hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1); - hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0); + hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M, + HNS3_TXD_BDTYPE_S, 0); + hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end); + hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1); + hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0); } static int hns3_fill_desc_vtags(struct sk_buff *skb, @@ -844,10 +849,10 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, * and use inner_vtag in one tag case. */ if (skb->protocol == htons(ETH_P_8021Q)) { - hnae_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1); + hnae3_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1); *out_vtag = vlan_tag; } else { - hnae_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1); + hnae3_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1); *inner_vtag = vlan_tag; } } else if (skb->protocol == htons(ETH_P_8021Q)) { @@ -1135,7 +1140,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) wmb(); /* Commit all data before submit */ - hnae_queue_xmit(ring->tqp, buf_num); + hnae3_queue_xmit(ring->tqp, buf_num); return NETDEV_TX_OK; @@ -1703,7 +1708,7 @@ static void hns3_set_default_feature(struct net_device *netdev) static int hns3_alloc_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) { - unsigned int order = hnae_page_order(ring); + unsigned int order = hnae3_page_order(ring); struct page *p; p = dev_alloc_pages(order); @@ -1714,7 +1719,7 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring, cb->page_offset = 0; cb->reuse_flag = 0; cb->buf = page_address(p); - cb->length = hnae_page_size(ring); + cb->length = hnae3_page_size(ring); cb->type = DESC_TYPE_PAGE; return 0; @@ -1780,33 +1785,27 @@ static void hns3_free_buffers(struct hns3_enet_ring *ring) /* free desc along with its attached buffer */ static void hns3_free_desc(struct hns3_enet_ring *ring) { + int size = ring->desc_num * sizeof(ring->desc[0]); + hns3_free_buffers(ring); - dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr, - ring->desc_num * sizeof(ring->desc[0]), - DMA_BIDIRECTIONAL); - ring->desc_dma_addr = 0; - kfree(ring->desc); - ring->desc = NULL; + if (ring->desc) { + dma_free_coherent(ring_to_dev(ring), size, + ring->desc, ring->desc_dma_addr); + ring->desc = NULL; + } } static int hns3_alloc_desc(struct hns3_enet_ring *ring) { int size = ring->desc_num * sizeof(ring->desc[0]); - ring->desc = kzalloc(size, GFP_KERNEL); + ring->desc = dma_zalloc_coherent(ring_to_dev(ring), size, + &ring->desc_dma_addr, + GFP_KERNEL); if (!ring->desc) return -ENOMEM; - ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), ring->desc, - size, DMA_BIDIRECTIONAL); - if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) { - ring->desc_dma_addr = 0; - kfree(ring->desc); - ring->desc = NULL; - return -ENOMEM; - } - return 0; } @@ -1887,7 +1886,7 @@ static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes, (*pkts) += (desc_cb->type == DESC_TYPE_SKB); (*bytes) += desc_cb->length; - /* desc_cb will be cleaned, after hnae_free_buffer_detach*/ + /* desc_cb will be cleaned, after hnae3_free_buffer_detach*/ hns3_free_buffer_detach(ring, ring->next_to_clean); ring_ptr_move_fw(ring, next_to_clean); @@ -1917,7 +1916,7 @@ bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) if (is_ring_empty(ring) || head == ring->next_to_clean) return true; /* no data to poll */ - if (!is_valid_clean_head(ring, head)) { + if (unlikely(!is_valid_clean_head(ring, head))) { netdev_err(netdev, "wrong head (%d, %d-%d)\n", head, ring->next_to_use, ring->next_to_clean); @@ -2016,15 +2015,15 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, bool twobufs; twobufs = ((PAGE_SIZE < 8192) && - hnae_buf_size(ring) == HNS3_BUFFER_SIZE_2048); + hnae3_buf_size(ring) == HNS3_BUFFER_SIZE_2048); desc = &ring->desc[ring->next_to_clean]; size = le16_to_cpu(desc->rx.size); - truesize = hnae_buf_size(ring); + truesize = hnae3_buf_size(ring); if (!twobufs) - last_offset = hnae_page_size(ring) - hnae_buf_size(ring); + last_offset = hnae3_page_size(ring) - hnae3_buf_size(ring); skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, size - pull_len, truesize); @@ -2076,13 +2075,13 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, return; /* check if hardware has done checksum */ - if (!hnae_get_bit(bd_base_info, HNS3_RXD_L3L4P_B)) + if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B)) return; - if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L3E_B) || - hnae_get_bit(l234info, HNS3_RXD_L4E_B) || - hnae_get_bit(l234info, HNS3_RXD_OL3E_B) || - hnae_get_bit(l234info, HNS3_RXD_OL4E_B))) { + if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L3E_B) || + hnae3_get_bit(l234info, HNS3_RXD_L4E_B) || + hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) || + hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) { netdev_err(netdev, "L3/L4 error pkt\n"); u64_stats_update_begin(&ring->syncp); ring->stats.l3l4_csum_err++; @@ -2091,23 +2090,24 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, return; } - l3_type = hnae_get_field(l234info, HNS3_RXD_L3ID_M, - HNS3_RXD_L3ID_S); - l4_type = hnae_get_field(l234info, HNS3_RXD_L4ID_M, - HNS3_RXD_L4ID_S); + l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M, + HNS3_RXD_L3ID_S); + l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M, + HNS3_RXD_L4ID_S); - ol4_type = hnae_get_field(l234info, HNS3_RXD_OL4ID_M, HNS3_RXD_OL4ID_S); + ol4_type = hnae3_get_field(l234info, HNS3_RXD_OL4ID_M, + HNS3_RXD_OL4ID_S); switch (ol4_type) { case HNS3_OL4_TYPE_MAC_IN_UDP: case HNS3_OL4_TYPE_NVGRE: skb->csum_level = 1; case HNS3_OL4_TYPE_NO_TUN: /* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */ - if (l3_type == HNS3_L3_TYPE_IPV4 || - (l3_type == HNS3_L3_TYPE_IPV6 && - (l4_type == HNS3_L4_TYPE_UDP || - l4_type == HNS3_L4_TYPE_TCP || - l4_type == HNS3_L4_TYPE_SCTP))) + if ((l3_type == HNS3_L3_TYPE_IPV4 || + l3_type == HNS3_L3_TYPE_IPV6) && + (l4_type == HNS3_L4_TYPE_UDP || + l4_type == HNS3_L4_TYPE_TCP || + l4_type == HNS3_L4_TYPE_SCTP)) skb->ip_summed = CHECKSUM_UNNECESSARY; break; } @@ -2135,8 +2135,8 @@ static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring, #define HNS3_STRP_OUTER_VLAN 0x1 #define HNS3_STRP_INNER_VLAN 0x2 - switch (hnae_get_field(l234info, HNS3_RXD_STRP_TAGP_M, - HNS3_RXD_STRP_TAGP_S)) { + switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M, + HNS3_RXD_STRP_TAGP_S)) { case HNS3_STRP_OUTER_VLAN: vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); break; @@ -2174,7 +2174,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, bd_base_info = le32_to_cpu(desc->rx.bd_base_info); /* Check valid BD */ - if (!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B)) + if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) return -EFAULT; va = (unsigned char *)desc_cb->buf + desc_cb->page_offset; @@ -2229,7 +2229,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb); ring_ptr_move_fw(ring, next_to_clean); - while (!hnae_get_bit(bd_base_info, HNS3_RXD_FE_B)) { + while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) { desc = &ring->desc[ring->next_to_clean]; desc_cb = &ring->desc_cb[ring->next_to_clean]; bd_base_info = le32_to_cpu(desc->rx.bd_base_info); @@ -2257,7 +2257,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, vlan_tag); } - if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))) { + if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) { netdev_err(netdev, "no valid bd,%016llx,%016llx\n", ((u64 *)desc)[0], ((u64 *)desc)[1]); u64_stats_update_begin(&ring->syncp); @@ -2269,7 +2269,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, } if (unlikely((!desc->rx.pkt_len) || - hnae_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) { + hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) { netdev_err(netdev, "truncated pkt\n"); u64_stats_update_begin(&ring->syncp); ring->stats.err_pkt_len++; @@ -2279,7 +2279,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, return -EFAULT; } - if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L2E_B))) { + if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) { netdev_err(netdev, "L2 error pkt\n"); u64_stats_update_begin(&ring->syncp); ring->stats.l2_err++; @@ -2532,10 +2532,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, tx_ring = tqp_vector->tx_group.ring; if (tx_ring) { cur_chain->tqp_index = tx_ring->tqp->tqp_index; - hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, - HNAE3_RING_TYPE_TX); - hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M, - HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX); + hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_TX); + hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX); cur_chain->next = NULL; @@ -2549,12 +2549,12 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, cur_chain->next = chain; chain->tqp_index = tx_ring->tqp->tqp_index; - hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B, - HNAE3_RING_TYPE_TX); - hnae_set_field(chain->int_gl_idx, - HNAE3_RING_GL_IDX_M, - HNAE3_RING_GL_IDX_S, - HNAE3_RING_GL_TX); + hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_TX); + hnae3_set_field(chain->int_gl_idx, + HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S, + HNAE3_RING_GL_TX); cur_chain = chain; } @@ -2564,10 +2564,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, if (!tx_ring && rx_ring) { cur_chain->next = NULL; cur_chain->tqp_index = rx_ring->tqp->tqp_index; - hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, - HNAE3_RING_TYPE_RX); - hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M, - HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX); + hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_RX); + hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX); rx_ring = rx_ring->next; } @@ -2579,10 +2579,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, cur_chain->next = chain; chain->tqp_index = rx_ring->tqp->tqp_index; - hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B, - HNAE3_RING_TYPE_RX); - hnae_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M, - HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX); + hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_RX); + hnae3_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX); cur_chain = chain; @@ -2745,10 +2745,6 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) if (ret) return ret; - ret = h->ae_algo->ops->put_vector(h, tqp_vector->vector_irq); - if (ret) - return ret; - hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) { @@ -2809,7 +2805,7 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, ring->io_base = q->io_base; } - hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type); + hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type); ring->tqp = q; ring->desc = NULL; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 3b083d5ae9ce..bf9aa02be994 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -499,7 +499,6 @@ struct hns3_enet_tqp_vector { u16 num_tqps; /* total number of tqps in TQP vector */ - cpumask_t affinity_mask; char name[HNAE3_INT_NAME_LEN]; /* when 0 should adjust interrupt coalesce parameter */ @@ -591,7 +590,7 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) #define hns3_write_dev(a, reg, value) \ hns3_write_reg((a)->io_base, (reg), (value)) -#define hnae_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \ +#define hnae3_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \ (tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG) #define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev) @@ -601,9 +600,9 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) #define tx_ring_data(priv, idx) ((priv)->ring_data[idx]) -#define hnae_buf_size(_ring) ((_ring)->buf_size) -#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring))) -#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring)) +#define hnae3_buf_size(_ring) ((_ring)->buf_size) +#define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring))) +#define hnae3_page_size(_ring) (PAGE_SIZE << hnae3_page_order(_ring)) /* iterator for handling rings in ring group */ #define hns3_for_each_ring(pos, head) \ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index c36d64710fa6..82cf12a07dc0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -18,8 +18,7 @@ #include "hclge_main.h" #define hclge_is_csq(ring) ((ring)->flag & HCLGE_TYPE_CSQ) -#define hclge_ring_to_dma_dir(ring) (hclge_is_csq(ring) ? \ - DMA_TO_DEVICE : DMA_FROM_DEVICE) + #define cmq_ring_to_dev(ring) (&(ring)->dev->pdev->dev) static int hclge_ring_space(struct hclge_cmq_ring *ring) @@ -46,31 +45,24 @@ static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring) { int size = ring->desc_num * sizeof(struct hclge_desc); - ring->desc = kzalloc(size, GFP_KERNEL); + ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring), + size, &ring->desc_dma_addr, + GFP_KERNEL); if (!ring->desc) return -ENOMEM; - ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc, - size, DMA_BIDIRECTIONAL); - if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) { - ring->desc_dma_addr = 0; - kfree(ring->desc); - ring->desc = NULL; - return -ENOMEM; - } - return 0; } static void hclge_free_cmd_desc(struct hclge_cmq_ring *ring) { - dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr, - ring->desc_num * sizeof(ring->desc[0]), - DMA_BIDIRECTIONAL); + int size = ring->desc_num * sizeof(struct hclge_desc); - ring->desc_dma_addr = 0; - kfree(ring->desc); - ring->desc = NULL; + if (ring->desc) { + dma_free_coherent(cmq_ring_to_dev(ring), size, + ring->desc, ring->desc_dma_addr); + ring->desc = NULL; + } } static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type) @@ -111,8 +103,6 @@ void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, if (is_read) desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR); - else - desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); } static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring) @@ -123,9 +113,9 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring) if (ring->flag == HCLGE_TYPE_CSQ) { hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, - (u32)dma); + lower_32_bits(dma)); hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, - (u32)((dma >> 31) >> 1)); + upper_32_bits(dma)); hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, (ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) | HCLGE_NIC_CMQ_ENABLE); @@ -133,9 +123,9 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring) hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0); } else { hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG, - (u32)dma); + lower_32_bits(dma)); hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG, - (u32)((dma >> 31) >> 1)); + upper_32_bits(dma)); hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG, (ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) | HCLGE_NIC_CMQ_ENABLE); @@ -152,33 +142,22 @@ static void hclge_cmd_init_regs(struct hclge_hw *hw) static int hclge_cmd_csq_clean(struct hclge_hw *hw) { - struct hclge_dev *hdev = (struct hclge_dev *)hw->back; + struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw); struct hclge_cmq_ring *csq = &hw->cmq.csq; - u16 ntc = csq->next_to_clean; - struct hclge_desc *desc; - int clean = 0; u32 head; + int clean; - desc = &csq->desc[ntc]; head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG); rmb(); /* Make sure head is ready before touch any data */ if (!is_valid_csq_clean_head(csq, head)) { - dev_warn(&hdev->pdev->dev, "wrong head (%d, %d-%d)\n", head, - csq->next_to_use, csq->next_to_clean); + dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head, + csq->next_to_use, csq->next_to_clean); return 0; } - while (head != ntc) { - memset(desc, 0, sizeof(*desc)); - ntc++; - if (ntc == csq->desc_num) - ntc = 0; - desc = &csq->desc[ntc]; - clean++; - } - csq->next_to_clean = ntc; - + clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num; + csq->next_to_clean = head; return clean; } @@ -216,7 +195,7 @@ static bool hclge_is_special_opcode(u16 opcode) **/ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) { - struct hclge_dev *hdev = (struct hclge_dev *)hw->back; + struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw); struct hclge_desc *desc_to_use; bool complete = false; u32 timeout = 0; @@ -256,33 +235,34 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) */ if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) { do { - if (hclge_cmd_csq_done(hw)) + if (hclge_cmd_csq_done(hw)) { + complete = true; break; + } udelay(1); timeout++; } while (timeout < hw->cmq.tx_timeout); } - if (hclge_cmd_csq_done(hw)) { - complete = true; + if (!complete) { + retval = -EAGAIN; + } else { handle = 0; while (handle < num) { /* Get the result of hardware write back */ desc_to_use = &hw->cmq.csq.desc[ntc]; desc[handle] = *desc_to_use; - pr_debug("Get cmd desc:\n"); if (likely(!hclge_is_special_opcode(opcode))) desc_ret = le16_to_cpu(desc[handle].retval); else desc_ret = le16_to_cpu(desc[0].retval); - if ((enum hclge_cmd_return_status)desc_ret == - HCLGE_CMD_EXEC_SUCCESS) + if (desc_ret == HCLGE_CMD_EXEC_SUCCESS) retval = 0; else retval = -EIO; - hw->cmq.last_status = (enum hclge_cmd_status)desc_ret; + hw->cmq.last_status = desc_ret; ntc++; handle++; if (ntc == hw->cmq.csq.desc_num) @@ -290,9 +270,6 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) } } - if (!complete) - retval = -EAGAIN; - /* Clean the command send queue */ handle = hclge_cmd_csq_clean(hw); if (handle != num) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d318d35e598f..6fffc69a7138 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -939,8 +939,8 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) if (hnae3_dev_roce_supported(hdev)) { hdev->num_roce_msi = - hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number), - HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), + HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); /* PF should have NIC vectors and Roce vectors, * NIC vectors are queued before Roce vectors. @@ -948,8 +948,8 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) hdev->num_msi = hdev->num_roce_msi + HCLGE_ROCE_VECTOR_OFFSET; } else { hdev->num_msi = - hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number), - HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), + HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); } return 0; @@ -1038,38 +1038,38 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) req = (struct hclge_cfg_param_cmd *)desc[0].data; /* get the configuration */ - cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]), - HCLGE_CFG_VMDQ_M, - HCLGE_CFG_VMDQ_S); - cfg->tc_num = hnae_get_field(__le32_to_cpu(req->param[0]), - HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S); - cfg->tqp_desc_num = hnae_get_field(__le32_to_cpu(req->param[0]), - HCLGE_CFG_TQP_DESC_N_M, - HCLGE_CFG_TQP_DESC_N_S); - - cfg->phy_addr = hnae_get_field(__le32_to_cpu(req->param[1]), - HCLGE_CFG_PHY_ADDR_M, - HCLGE_CFG_PHY_ADDR_S); - cfg->media_type = hnae_get_field(__le32_to_cpu(req->param[1]), - HCLGE_CFG_MEDIA_TP_M, - HCLGE_CFG_MEDIA_TP_S); - cfg->rx_buf_len = hnae_get_field(__le32_to_cpu(req->param[1]), - HCLGE_CFG_RX_BUF_LEN_M, - HCLGE_CFG_RX_BUF_LEN_S); + cfg->vmdq_vport_num = hnae3_get_field(__le32_to_cpu(req->param[0]), + HCLGE_CFG_VMDQ_M, + HCLGE_CFG_VMDQ_S); + cfg->tc_num = hnae3_get_field(__le32_to_cpu(req->param[0]), + HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S); + cfg->tqp_desc_num = hnae3_get_field(__le32_to_cpu(req->param[0]), + HCLGE_CFG_TQP_DESC_N_M, + HCLGE_CFG_TQP_DESC_N_S); + + cfg->phy_addr = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_PHY_ADDR_M, + HCLGE_CFG_PHY_ADDR_S); + cfg->media_type = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_MEDIA_TP_M, + HCLGE_CFG_MEDIA_TP_S); + cfg->rx_buf_len = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_RX_BUF_LEN_M, + HCLGE_CFG_RX_BUF_LEN_S); /* get mac_address */ mac_addr_tmp = __le32_to_cpu(req->param[2]); - mac_addr_tmp_high = hnae_get_field(__le32_to_cpu(req->param[3]), - HCLGE_CFG_MAC_ADDR_H_M, - HCLGE_CFG_MAC_ADDR_H_S); + mac_addr_tmp_high = hnae3_get_field(__le32_to_cpu(req->param[3]), + HCLGE_CFG_MAC_ADDR_H_M, + HCLGE_CFG_MAC_ADDR_H_S); mac_addr_tmp |= (mac_addr_tmp_high << 31) << 1; - cfg->default_speed = hnae_get_field(__le32_to_cpu(req->param[3]), - HCLGE_CFG_DEFAULT_SPEED_M, - HCLGE_CFG_DEFAULT_SPEED_S); - cfg->rss_size_max = hnae_get_field(__le32_to_cpu(req->param[3]), - HCLGE_CFG_RSS_SIZE_M, - HCLGE_CFG_RSS_SIZE_S); + cfg->default_speed = hnae3_get_field(__le32_to_cpu(req->param[3]), + HCLGE_CFG_DEFAULT_SPEED_M, + HCLGE_CFG_DEFAULT_SPEED_S); + cfg->rss_size_max = hnae3_get_field(__le32_to_cpu(req->param[3]), + HCLGE_CFG_RSS_SIZE_M, + HCLGE_CFG_RSS_SIZE_S); for (i = 0; i < ETH_ALEN; i++) cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff; @@ -1077,9 +1077,9 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) req = (struct hclge_cfg_param_cmd *)desc[1].data; cfg->numa_node_map = __le32_to_cpu(req->param[0]); - cfg->speed_ability = hnae_get_field(__le32_to_cpu(req->param[1]), - HCLGE_CFG_SPEED_ABILITY_M, - HCLGE_CFG_SPEED_ABILITY_S); + cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_SPEED_ABILITY_M, + HCLGE_CFG_SPEED_ABILITY_S); } /* hclge_get_cfg: query the static parameter from flash @@ -1098,11 +1098,11 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg) req = (struct hclge_cfg_param_cmd *)desc[i].data; hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM, true); - hnae_set_field(offset, HCLGE_CFG_OFFSET_M, - HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES); + hnae3_set_field(offset, HCLGE_CFG_OFFSET_M, + HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES); /* Len should be united by 4 bytes when send to hardware */ - hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S, - HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT); + hnae3_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S, + HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT); req->offset = cpu_to_le32(offset); } @@ -1189,7 +1189,7 @@ static int hclge_configure(struct hclge_dev *hdev) /* Currently not support uncontiuous tc */ for (i = 0; i < hdev->tm_info.num_tc; i++) - hnae_set_bit(hdev->hw_tc_map, i, 1); + hnae3_set_bit(hdev->hw_tc_map, i, 1); hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE; @@ -1208,13 +1208,13 @@ static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min, req = (struct hclge_cfg_tso_status_cmd *)desc.data; tso_mss = 0; - hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, - HCLGE_TSO_MSS_MIN_S, tso_mss_min); + hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, + HCLGE_TSO_MSS_MIN_S, tso_mss_min); req->tso_mss_min = cpu_to_le16(tso_mss); tso_mss = 0; - hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, - HCLGE_TSO_MSS_MIN_S, tso_mss_max); + hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, + HCLGE_TSO_MSS_MIN_S, tso_mss_max); req->tso_mss_max = cpu_to_le16(tso_mss); return hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2118,48 +2118,48 @@ int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false); - hnae_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex); + hnae3_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex); switch (speed) { case HCLGE_MAC_SPEED_10M: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 6); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 6); break; case HCLGE_MAC_SPEED_100M: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 7); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 7); break; case HCLGE_MAC_SPEED_1G: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 0); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 0); break; case HCLGE_MAC_SPEED_10G: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 1); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 1); break; case HCLGE_MAC_SPEED_25G: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 2); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 2); break; case HCLGE_MAC_SPEED_40G: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 3); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 3); break; case HCLGE_MAC_SPEED_50G: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 4); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 4); break; case HCLGE_MAC_SPEED_100G: - hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, - HCLGE_CFG_SPEED_S, 5); + hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 5); break; default: dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed); return -EINVAL; } - hnae_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B, - 1); + hnae3_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B, + 1); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -2201,9 +2201,9 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed, return ret; } - *duplex = hnae_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B); - speed_tmp = hnae_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M, - HCLGE_QUERY_SPEED_S); + *duplex = hnae3_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B); + speed_tmp = hnae3_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M, + HCLGE_QUERY_SPEED_S); ret = hclge_parse_speed(speed_tmp, speed); if (ret) { @@ -2225,7 +2225,7 @@ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false); req = (struct hclge_config_auto_neg_cmd *)desc.data; - hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); + hnae3_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); req->cfg_an_cmd_flag = cpu_to_le32(flag); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2269,8 +2269,8 @@ static int hclge_set_default_mac_vlan_mask(struct hclge_dev *hdev, req = (struct hclge_mac_vlan_mask_entry_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_MASK_SET, false); - hnae_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B, - mask_vlan ? 1 : 0); + hnae3_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B, + mask_vlan ? 1 : 0); ether_addr_copy(req->mac_mask, mac_mask); status = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2614,6 +2614,12 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) static void hclge_free_vector(struct hclge_dev *hdev, int vector_id) { + if (hdev->vector_status[vector_id] == HCLGE_INVALID_VPORT) { + dev_warn(&hdev->pdev->dev, + "vector(vector_id %d) has been freed.\n", vector_id); + return; + } + hdev->vector_status[vector_id] = HCLGE_INVALID_VPORT; hdev->num_msi_left += 1; hdev->num_msi_used -= 1; @@ -2705,7 +2711,7 @@ static int hclge_reset_wait(struct hclge_dev *hdev) } val = hclge_read_dev(&hdev->hw, reg); - while (hnae_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) { + while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) { msleep(HCLGE_RESET_WATI_MS); val = hclge_read_dev(&hdev->hw, reg); cnt++; @@ -2727,8 +2733,7 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id) int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false); - hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_MAC_B, 0); - hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1); + hnae3_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1); req->fun_reset_vfid = func_id; ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2747,13 +2752,13 @@ static void hclge_do_reset(struct hclge_dev *hdev) switch (hdev->reset_type) { case HNAE3_GLOBAL_RESET: val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG); - hnae_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1); + hnae3_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1); hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val); dev_info(&pdev->dev, "Global Reset requested\n"); break; case HNAE3_CORE_RESET: val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG); - hnae_set_bit(val, HCLGE_CORE_RESET_BIT, 1); + hnae3_set_bit(val, HCLGE_CORE_RESET_BIT, 1); hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val); dev_info(&pdev->dev, "Core Reset requested\n"); break; @@ -3110,11 +3115,11 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { u16 mode = 0; - hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1)); - hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M, - HCLGE_RSS_TC_SIZE_S, tc_size[i]); - hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M, - HCLGE_RSS_TC_OFFSET_S, tc_offset[i]); + hnae3_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1)); + hnae3_set_field(mode, HCLGE_RSS_TC_SIZE_M, + HCLGE_RSS_TC_SIZE_S, tc_size[i]); + hnae3_set_field(mode, HCLGE_RSS_TC_OFFSET_M, + HCLGE_RSS_TC_OFFSET_S, tc_offset[i]); req->rss_tc_mode[i] = cpu_to_le16(mode); } @@ -3491,16 +3496,16 @@ int hclge_bind_ring_with_vector(struct hclge_vport *vport, i = 0; for (node = ring_chain; node; node = node->next) { tqp_type_and_id = le16_to_cpu(req->tqp_type_and_id[i]); - hnae_set_field(tqp_type_and_id, HCLGE_INT_TYPE_M, - HCLGE_INT_TYPE_S, - hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - hnae_set_field(tqp_type_and_id, HCLGE_TQP_ID_M, - HCLGE_TQP_ID_S, node->tqp_index); - hnae_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M, - HCLGE_INT_GL_IDX_S, - hnae_get_field(node->int_gl_idx, - HNAE3_RING_GL_IDX_M, - HNAE3_RING_GL_IDX_S)); + hnae3_set_field(tqp_type_and_id, HCLGE_INT_TYPE_M, + HCLGE_INT_TYPE_S, + hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B)); + hnae3_set_field(tqp_type_and_id, HCLGE_TQP_ID_M, + HCLGE_TQP_ID_S, node->tqp_index); + hnae3_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + hnae3_get_field(node->int_gl_idx, + HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S)); req->tqp_type_and_id[i] = cpu_to_le16(tqp_type_and_id); if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD; @@ -3648,20 +3653,20 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false); - hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0); - hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0); - hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0); - hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0); - hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); - hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0); + hnae3_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0); + hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0); + hnae3_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0); + hnae3_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); + hnae3_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -3689,7 +3694,7 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en) /* 2 Then setup the loopback flag */ loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en); - hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0); + hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0); req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); @@ -3953,10 +3958,10 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, req = (struct hclge_mta_filter_mode_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false); - hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, - enable); - hnae_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M, - HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel); + hnae3_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, + enable); + hnae3_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M, + HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -3980,8 +3985,8 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false); - hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, - enable); + hnae3_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, + enable); req->function_id = func_id; ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -4007,10 +4012,10 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport, req = (struct hclge_cfg_func_mta_item_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); - hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); + hnae3_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); - hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, - HCLGE_CFG_MTA_ITEM_IDX_S, idx); + hnae3_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, + HCLGE_CFG_MTA_ITEM_IDX_S, idx); req->item_idx = cpu_to_le16(item_idx); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -4257,17 +4262,10 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, } memset(&req, 0, sizeof(req)); - hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0); - hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - - hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0); - hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0); - hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, - HCLGE_MAC_EPORT_VFID_S, vport->vport_id); - hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M, - HCLGE_MAC_EPORT_PFID_S, 0); + hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + + hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, + HCLGE_MAC_EPORT_VFID_S, vport->vport_id); req.egress_port = cpu_to_le16(egress_port); @@ -4318,8 +4316,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, } memset(&req, 0, sizeof(req)); - hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hclge_prepare_mac_addr(&req, addr); ret = hclge_remove_mac_vlan_tbl(vport, &req); @@ -4351,10 +4349,10 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, return -EINVAL; } memset(&req, 0, sizeof(req)); - hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); - hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); + hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hclge_prepare_mac_addr(&req, addr); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (!status) { @@ -4418,10 +4416,10 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, } memset(&req, 0, sizeof(req)); - hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); - hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); + hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hclge_prepare_mac_addr(&req, addr); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (!status) { @@ -4802,19 +4800,19 @@ static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport) req = (struct hclge_vport_vtag_tx_cfg_cmd *)desc.data; req->def_vlan_tag1 = cpu_to_le16(vcfg->default_tag1); req->def_vlan_tag2 = cpu_to_le16(vcfg->default_tag2); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B, - vcfg->accept_tag1 ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B, - vcfg->accept_untag1 ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B, - vcfg->accept_tag2 ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B, - vcfg->accept_untag2 ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B, - vcfg->insert_tag1_en ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B, - vcfg->insert_tag2_en ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B, + vcfg->accept_tag1 ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B, + vcfg->accept_untag1 ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B, + vcfg->accept_tag2 ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B, + vcfg->accept_untag2 ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B, + vcfg->insert_tag1_en ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B, + vcfg->insert_tag2_en ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0); req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD; req->vf_bitmap[req->vf_offset] = @@ -4840,14 +4838,14 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, false); req = (struct hclge_vport_vtag_rx_cfg_cmd *)desc.data; - hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B, - vcfg->strip_tag1_en ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B, - vcfg->strip_tag2_en ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B, - vcfg->vlan1_vlan_prionly ? 1 : 0); - hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B, - vcfg->vlan2_vlan_prionly ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B, + vcfg->strip_tag1_en ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B, + vcfg->strip_tag2_en ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B, + vcfg->vlan1_vlan_prionly ? 1 : 0); + hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B, + vcfg->vlan2_vlan_prionly ? 1 : 0); req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD; req->vf_bitmap[req->vf_offset] = @@ -5043,7 +5041,7 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id, req = (struct hclge_reset_tqp_queue_cmd *)desc.data; req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); - hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable); + hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -5073,7 +5071,7 @@ static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id) return ret; } - return hnae_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B); + return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B); } static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, @@ -5380,12 +5378,12 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle, phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_MDIX); retval = phy_read(phydev, HCLGE_PHY_CSC_REG); - mdix_ctrl = hnae_get_field(retval, HCLGE_PHY_MDIX_CTRL_M, - HCLGE_PHY_MDIX_CTRL_S); + mdix_ctrl = hnae3_get_field(retval, HCLGE_PHY_MDIX_CTRL_M, + HCLGE_PHY_MDIX_CTRL_S); retval = phy_read(phydev, HCLGE_PHY_CSS_REG); - mdix = hnae_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B); - is_resolved = hnae_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B); + mdix = hnae3_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B); + is_resolved = hnae3_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B); phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_COPPER); @@ -5531,7 +5529,6 @@ static int hclge_pci_init(struct hclge_dev *hdev) pci_set_master(pdev); hw = &hdev->hw; - hw->back = hdev; hw->io_base = pcim_iomap(pdev, 2, 0); if (!hw->io_base) { dev_err(&pdev->dev, "Can't map configuration register space\n"); @@ -5562,6 +5559,30 @@ static void hclge_pci_uninit(struct hclge_dev *hdev) pci_disable_device(pdev); } +static void hclge_state_init(struct hclge_dev *hdev) +{ + set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state); + set_bit(HCLGE_STATE_DOWN, &hdev->state); + clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state); + clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); + clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state); + clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state); +} + +static void hclge_state_uninit(struct hclge_dev *hdev) +{ + set_bit(HCLGE_STATE_DOWN, &hdev->state); + + if (hdev->service_timer.function) + del_timer_sync(&hdev->service_timer); + if (hdev->service_task.func) + cancel_work_sync(&hdev->service_task); + if (hdev->rst_service_task.func) + cancel_work_sync(&hdev->rst_service_task); + if (hdev->mbx_service_task.func) + cancel_work_sync(&hdev->mbx_service_task); +} + static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) { struct pci_dev *pdev = ae_dev->pdev; @@ -5702,12 +5723,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) /* Enable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, true); - set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state); - set_bit(HCLGE_STATE_DOWN, &hdev->state); - clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state); - clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); - clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state); - clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state); + hclge_state_init(hdev); pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME); return 0; @@ -5812,16 +5828,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) struct hclge_dev *hdev = ae_dev->priv; struct hclge_mac *mac = &hdev->hw.mac; - set_bit(HCLGE_STATE_DOWN, &hdev->state); - - if (hdev->service_timer.function) - del_timer_sync(&hdev->service_timer); - if (hdev->service_task.func) - cancel_work_sync(&hdev->service_task); - if (hdev->rst_service_task.func) - cancel_work_sync(&hdev->rst_service_task); - if (hdev->mbx_service_task.func) - cancel_work_sync(&hdev->mbx_service_task); + hclge_state_uninit(hdev); if (mac->phydev) mdiobus_unregister(mac->mdio_bus); @@ -6149,8 +6156,8 @@ static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_LED_STATUS_CFG, false); req = (struct hclge_set_led_state_cmd *)desc.data; - hnae_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M, - HCLGE_LED_LOCATE_STATE_S, locate_led_status); + hnae3_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M, + HCLGE_LED_LOCATE_STATE_S, locate_led_status); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) @@ -6280,7 +6287,6 @@ static const struct hnae3_ae_ops hclge_ops = { static struct hnae3_ae_algo ae_algo = { .ops = &hclge_ops, - .name = HCLGE_NAME, .pdev_id_table = ae_algo_pci_tbl, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 7488534528cd..71d38b852c56 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -190,7 +190,6 @@ struct hclge_hw { int num_vec; struct hclge_cmq cmq; struct hclge_caps caps; - void *back; }; /* TQP stats */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 7541cb9b71ce..50ae2f8f188d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -128,12 +128,12 @@ static int hclge_get_ring_chain_from_mbx( HCLGE_MBX_RING_NODE_VARIABLE_NUM)) return -ENOMEM; - hnae_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]); + hnae3_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]); ring_chain->tqp_index = hclge_get_queue_id(vport->nic.kinfo.tqp[req->msg[4]]); - hnae_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M, - HCLGE_INT_GL_IDX_S, - req->msg[5]); + hnae3_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + req->msg[5]); cur_chain = ring_chain; @@ -142,19 +142,19 @@ static int hclge_get_ring_chain_from_mbx( if (!new_chain) goto err; - hnae_set_bit(new_chain->flag, HNAE3_RING_TYPE_B, - req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i + - HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]); + hnae3_set_bit(new_chain->flag, HNAE3_RING_TYPE_B, + req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i + + HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]); new_chain->tqp_index = hclge_get_queue_id(vport->nic.kinfo.tqp [req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i + HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 1]]); - hnae_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M, - HCLGE_INT_GL_IDX_S, - req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i + - HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]); + hnae3_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i + + HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]); cur_chain->next = new_chain; cur_chain = new_chain; @@ -460,7 +460,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev) req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data; flag = le16_to_cpu(crq->desc[crq->next_to_use].flag); - if (unlikely(!hnae_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) { + if (unlikely(!hnae3_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) { dev_warn(&hdev->pdev->dev, "dropped invalid mailbox message, code = %d\n", req->msg[0]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 9f7932e423b5..b6cfe6ff988d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -67,16 +67,16 @@ static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum, mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data; - hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M, - HCLGE_MDIO_PHYID_S, phyid); - hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M, - HCLGE_MDIO_PHYREG_S, regnum); + hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M, + HCLGE_MDIO_PHYID_S, phyid); + hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M, + HCLGE_MDIO_PHYREG_S, regnum); - hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1); - hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M, - HCLGE_MDIO_CTRL_ST_S, 1); - hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M, - HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE); + hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1); + hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M, + HCLGE_MDIO_CTRL_ST_S, 1); + hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M, + HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE); mdio_cmd->data_wr = cpu_to_le16(data); @@ -105,16 +105,16 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum) mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data; - hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M, - HCLGE_MDIO_PHYID_S, phyid); - hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M, - HCLGE_MDIO_PHYREG_S, regnum); + hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M, + HCLGE_MDIO_PHYID_S, phyid); + hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M, + HCLGE_MDIO_PHYREG_S, regnum); - hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1); - hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M, - HCLGE_MDIO_CTRL_ST_S, 1); - hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M, - HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ); + hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1); + hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M, + HCLGE_MDIO_CTRL_ST_S, 1); + hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M, + HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ); /* Read out phy data */ ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -125,7 +125,7 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum) return ret; } - if (hnae_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) { + if (hnae3_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) { dev_err(&hdev->pdev->dev, "mdio read data error\n"); return -EIO; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 262c125f8137..82bc30fdff98 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1184,10 +1184,10 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) u16 qs_id = vport->qs_offset + tc; u8 grp, sub_grp; - grp = hnae_get_field(qs_id, HCLGE_BP_GRP_ID_M, - HCLGE_BP_GRP_ID_S); - sub_grp = hnae_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M, - HCLGE_BP_SUB_GRP_ID_S); + grp = hnae3_get_field(qs_id, HCLGE_BP_GRP_ID_M, + HCLGE_BP_GRP_ID_S); + sub_grp = hnae3_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M, + HCLGE_BP_SUB_GRP_ID_S); if (i == grp) qs_bitmap |= (1 << sub_grp); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index c2b6e8a6700f..c82d49ebd5bf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -123,10 +123,11 @@ struct hclge_port_shapping_cmd { }; #define hclge_tm_set_field(dest, string, val) \ - hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \ - (HCLGE_TM_SHAP_##string##_LSH), val) + hnae3_set_field((dest), \ + (HCLGE_TM_SHAP_##string##_MSK), \ + (HCLGE_TM_SHAP_##string##_LSH), val) #define hclge_tm_get_field(src, string) \ - hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \ + hnae3_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \ (HCLGE_TM_SHAP_##string##_LSH)) int hclge_tm_schd_init(struct hclge_dev *hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index 1bbfe131b596..fb471fe2c494 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -76,32 +76,24 @@ static int hclgevf_alloc_cmd_desc(struct hclgevf_cmq_ring *ring) { int size = ring->desc_num * sizeof(struct hclgevf_desc); - ring->desc = kzalloc(size, GFP_KERNEL); + ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring), + size, &ring->desc_dma_addr, + GFP_KERNEL); if (!ring->desc) return -ENOMEM; - ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc, - size, DMA_BIDIRECTIONAL); - - if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) { - ring->desc_dma_addr = 0; - kfree(ring->desc); - ring->desc = NULL; - return -ENOMEM; - } - return 0; } static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring) { - dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr, - ring->desc_num * sizeof(ring->desc[0]), - hclgevf_ring_to_dma_dir(ring)); + int size = ring->desc_num * sizeof(struct hclgevf_desc); - ring->desc_dma_addr = 0; - kfree(ring->desc); - ring->desc = NULL; + if (ring->desc) { + dma_free_coherent(cmq_ring_to_dev(ring), size, + ring->desc, ring->desc_dma_addr); + ring->desc = NULL; + } } static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a17872aab168..5a8653238e3f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -330,6 +330,12 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev) static void hclgevf_free_vector(struct hclgevf_dev *hdev, int vector_id) { + if (hdev->vector_status[vector_id] == HCLGEVF_INVALID_VPORT) { + dev_warn(&hdev->pdev->dev, + "vector(vector_id %d) has been freed.\n", vector_id); + return; + } + hdev->vector_status[vector_id] = HCLGEVF_INVALID_VPORT; hdev->num_msi_left += 1; hdev->num_msi_used -= 1; @@ -444,12 +450,12 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev, u16 rss_size) hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false); for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) { - hnae_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B, - (tc_valid[i] & 0x1)); - hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M, - HCLGEVF_RSS_TC_SIZE_S, tc_size[i]); - hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M, - HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]); + hnae3_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B, + (tc_valid[i] & 0x1)); + hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M, + HCLGEVF_RSS_TC_SIZE_S, tc_size[i]); + hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M, + HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]); } status = hclgevf_cmd_send(&hdev->hw, &desc, 1); if (status) @@ -547,24 +553,18 @@ static int hclgevf_get_tc_size(struct hnae3_handle *handle) } static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en, - int vector, + int vector_id, struct hnae3_ring_chain_node *ring_chain) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); struct hnae3_ring_chain_node *node; struct hclge_mbx_vf_to_pf_cmd *req; struct hclgevf_desc desc; - int i = 0, vector_id; + int i = 0; int status; u8 type; req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data; - vector_id = hclgevf_get_vector_index(hdev, vector); - if (vector_id < 0) { - dev_err(&handle->pdev->dev, - "Get vector index fail. ret =%d\n", vector_id); - return vector_id; - } for (node = ring_chain; node; node = node->next) { int idx_offset = HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + @@ -582,11 +582,11 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en, } req->msg[idx_offset] = - hnae_get_bit(node->flag, HNAE3_RING_TYPE_B); + hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B); req->msg[idx_offset + 1] = node->tqp_index; - req->msg[idx_offset + 2] = hnae_get_field(node->int_gl_idx, - HNAE3_RING_GL_IDX_M, - HNAE3_RING_GL_IDX_S); + req->msg[idx_offset + 2] = hnae3_get_field(node->int_gl_idx, + HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S); i++; if ((i == (HCLGE_MBX_VF_MSG_DATA_NUM - @@ -617,7 +617,17 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en, static int hclgevf_map_ring_to_vector(struct hnae3_handle *handle, int vector, struct hnae3_ring_chain_node *ring_chain) { - return hclgevf_bind_ring_to_vector(handle, true, vector, ring_chain); + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + int vector_id; + + vector_id = hclgevf_get_vector_index(hdev, vector); + if (vector_id < 0) { + dev_err(&handle->pdev->dev, + "Get vector index fail. ret =%d\n", vector_id); + return vector_id; + } + + return hclgevf_bind_ring_to_vector(handle, true, vector_id, ring_chain); } static int hclgevf_unmap_ring_from_vector( @@ -635,7 +645,7 @@ static int hclgevf_unmap_ring_from_vector( return vector_id; } - ret = hclgevf_bind_ring_to_vector(handle, false, vector, ring_chain); + ret = hclgevf_bind_ring_to_vector(handle, false, vector_id, ring_chain); if (ret) dev_err(&handle->pdev->dev, "Unmap ring from vector fail. vector=%d, ret =%d\n", @@ -990,8 +1000,8 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) /* wait to check the hardware reset completion status */ val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING); - while (hnae_get_bit(val, HCLGEVF_FUN_RST_ING_B) && - (cnt < HCLGEVF_RESET_WAIT_CNT)) { + while (hnae3_get_bit(val, HCLGEVF_FUN_RST_ING_B) && + (cnt < HCLGEVF_RESET_WAIT_CNT)) { msleep(HCLGEVF_RESET_WAIT_MS); val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING); cnt++; @@ -1582,9 +1592,10 @@ static void hclgevf_misc_irq_uninit(struct hclgevf_dev *hdev) hclgevf_free_vector(hdev, 0); } -static int hclgevf_init_instance(struct hclgevf_dev *hdev, - struct hnae3_client *client) +static int hclgevf_init_client_instance(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev) { + struct hclgevf_dev *hdev = ae_dev->priv; int ret; switch (client->type) { @@ -1635,9 +1646,11 @@ static int hclgevf_init_instance(struct hclgevf_dev *hdev, return 0; } -static void hclgevf_uninit_instance(struct hclgevf_dev *hdev, - struct hnae3_client *client) +static void hclgevf_uninit_client_instance(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev) { + struct hclgevf_dev *hdev = ae_dev->priv; + /* un-init roce, if it exists */ if (hdev->roce_client) hdev->roce_client->ops->uninit_instance(&hdev->roce, 0); @@ -1648,22 +1661,6 @@ static void hclgevf_uninit_instance(struct hclgevf_dev *hdev, client->ops->uninit_instance(&hdev->nic, 0); } -static int hclgevf_register_client(struct hnae3_client *client, - struct hnae3_ae_dev *ae_dev) -{ - struct hclgevf_dev *hdev = ae_dev->priv; - - return hclgevf_init_instance(hdev, client); -} - -static void hclgevf_unregister_client(struct hnae3_client *client, - struct hnae3_ae_dev *ae_dev) -{ - struct hclgevf_dev *hdev = ae_dev->priv; - - hclgevf_uninit_instance(hdev, client); -} - static int hclgevf_pci_init(struct hclgevf_dev *hdev) { struct pci_dev *pdev = hdev->pdev; @@ -1924,8 +1921,8 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed, static const struct hnae3_ae_ops hclgevf_ops = { .init_ae_dev = hclgevf_init_ae_dev, .uninit_ae_dev = hclgevf_uninit_ae_dev, - .init_client_instance = hclgevf_register_client, - .uninit_client_instance = hclgevf_unregister_client, + .init_client_instance = hclgevf_init_client_instance, + .uninit_client_instance = hclgevf_uninit_client_instance, .start = hclgevf_ae_start, .stop = hclgevf_ae_stop, .map_ring_to_vector = hclgevf_map_ring_to_vector, @@ -1962,7 +1959,6 @@ static const struct hnae3_ae_ops hclgevf_ops = { static struct hnae3_ae_algo ae_algovf = { .ops = &hclgevf_ops, - .name = HCLGEVF_NAME, .pdev_id_table = ae_algovf_pci_tbl, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index b598c06af8e0..173ca27957ef 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -152,7 +152,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data; flag = le16_to_cpu(crq->desc[crq->next_to_use].flag); - if (unlikely(!hnae_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) { + if (unlikely(!hnae3_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) { dev_warn(&hdev->pdev->dev, "dropped invalid mailbox message, code = %d\n", req->msg[0]); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c944bd10b03d..426b0ccb1fc6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7522,7 +7522,7 @@ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np, case TC_CLSFLOWER_STATS: return -EOPNOTSUPP; default: - return -EINVAL; + return -EOPNOTSUPP; } } @@ -7554,7 +7554,7 @@ static int i40e_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb, - np, np); + np, np, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np); return 0; @@ -11978,7 +11978,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d", IFNAMSIZ - 4, pf->vsi[pf->lan_vsi]->netdev->name); - random_ether_addr(mac_addr); + eth_random_addr(mac_addr); spin_lock_bh(&vsi->mac_filter_hash_lock); i40e_add_mac_filter(vsi, mac_addr); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index a7b87f935411..5906c1c1d19d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -2884,7 +2884,7 @@ static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, case TC_CLSFLOWER_STATS: return -EOPNOTSUPP; default: - return -EINVAL; + return -EOPNOTSUPP; } } @@ -2926,7 +2926,7 @@ static int i40evf_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, - adapter, adapter); + adapter, adapter, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index f707709969ac..f1e3397bd405 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2698,7 +2698,7 @@ static int igb_setup_tc_cls_flower(struct igb_adapter *adapter, case TC_CLSFLOWER_STATS: return -EOPNOTSUPP; default: - return -EINVAL; + return -EOPNOTSUPP; } } @@ -2728,7 +2728,7 @@ static int igb_setup_tc_block(struct igb_adapter *adapter, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, igb_setup_tc_block_cb, - adapter, adapter); + adapter, adapter, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb, adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 62e57b05a0ae..a8e21becb619 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9329,7 +9329,7 @@ static int ixgbe_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb, - adapter, adapter); + adapter, adapter, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb, adapter); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index def00dc3eb4e..81a66cce7fa8 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -553,6 +553,8 @@ ((total_size) - NET_SKB_PAD - MVPP2_SKB_SHINFO_SIZE) #define MVPP2_BIT_TO_BYTE(bit) ((bit) / 8) +#define MVPP2_BIT_TO_WORD(bit) ((bit) / 32) +#define MVPP2_BIT_IN_WORD(bit) ((bit) % 32) /* IPv6 max L3 address size */ #define MVPP2_MAX_L3_ADDR_SIZE 16 @@ -831,52 +833,52 @@ struct mvpp2_port { /* HW TX descriptor for PPv2.1 */ struct mvpp21_tx_desc { - u32 command; /* Options used by HW for packet transmitting.*/ + __le32 command; /* Options used by HW for packet transmitting.*/ u8 packet_offset; /* the offset from the buffer beginning */ u8 phys_txq; /* destination queue ID */ - u16 data_size; /* data size of transmitted packet in bytes */ - u32 buf_dma_addr; /* physical addr of transmitted buffer */ - u32 buf_cookie; /* cookie for access to TX buffer in tx path */ - u32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */ - u32 reserved2; /* reserved (for future use) */ + __le16 data_size; /* data size of transmitted packet in bytes */ + __le32 buf_dma_addr; /* physical addr of transmitted buffer */ + __le32 buf_cookie; /* cookie for access to TX buffer in tx path */ + __le32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */ + __le32 reserved2; /* reserved (for future use) */ }; /* HW RX descriptor for PPv2.1 */ struct mvpp21_rx_desc { - u32 status; /* info about received packet */ - u16 reserved1; /* parser_info (for future use, PnC) */ - u16 data_size; /* size of received packet in bytes */ - u32 buf_dma_addr; /* physical address of the buffer */ - u32 buf_cookie; /* cookie for access to RX buffer in rx path */ - u16 reserved2; /* gem_port_id (for future use, PON) */ - u16 reserved3; /* csum_l4 (for future use, PnC) */ + __le32 status; /* info about received packet */ + __le16 reserved1; /* parser_info (for future use, PnC) */ + __le16 data_size; /* size of received packet in bytes */ + __le32 buf_dma_addr; /* physical address of the buffer */ + __le32 buf_cookie; /* cookie for access to RX buffer in rx path */ + __le16 reserved2; /* gem_port_id (for future use, PON) */ + __le16 reserved3; /* csum_l4 (for future use, PnC) */ u8 reserved4; /* bm_qset (for future use, BM) */ u8 reserved5; - u16 reserved6; /* classify_info (for future use, PnC) */ - u32 reserved7; /* flow_id (for future use, PnC) */ - u32 reserved8; + __le16 reserved6; /* classify_info (for future use, PnC) */ + __le32 reserved7; /* flow_id (for future use, PnC) */ + __le32 reserved8; }; /* HW TX descriptor for PPv2.2 */ struct mvpp22_tx_desc { - u32 command; + __le32 command; u8 packet_offset; u8 phys_txq; - u16 data_size; - u64 reserved1; - u64 buf_dma_addr_ptp; - u64 buf_cookie_misc; + __le16 data_size; + __le64 reserved1; + __le64 buf_dma_addr_ptp; + __le64 buf_cookie_misc; }; /* HW RX descriptor for PPv2.2 */ struct mvpp22_rx_desc { - u32 status; - u16 reserved1; - u16 data_size; - u32 reserved2; - u32 reserved3; - u64 buf_dma_addr_key_hash; - u64 buf_cookie_misc; + __le32 status; + __le16 reserved1; + __le16 data_size; + __le32 reserved2; + __le32 reserved3; + __le64 buf_dma_addr_key_hash; + __le64 buf_cookie_misc; }; /* Opaque type used by the driver to manipulate the HW TX and RX diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 0319ed9ef8b8..88f3da184d76 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -151,9 +151,10 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { if (port->priv->hw_version == MVPP21) - return tx_desc->pp21.buf_dma_addr; + return le32_to_cpu(tx_desc->pp21.buf_dma_addr); else - return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK; + return le64_to_cpu(tx_desc->pp22.buf_dma_addr_ptp) & + MVPP2_DESC_DMA_MASK; } static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port, @@ -166,12 +167,12 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port, offset = dma_addr & MVPP2_TX_DESC_ALIGN; if (port->priv->hw_version == MVPP21) { - tx_desc->pp21.buf_dma_addr = addr; + tx_desc->pp21.buf_dma_addr = cpu_to_le32(addr); tx_desc->pp21.packet_offset = offset; } else { - u64 val = (u64)addr; + __le64 val = cpu_to_le64(addr); - tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK; + tx_desc->pp22.buf_dma_addr_ptp &= ~cpu_to_le64(MVPP2_DESC_DMA_MASK); tx_desc->pp22.buf_dma_addr_ptp |= val; tx_desc->pp22.packet_offset = offset; } @@ -181,9 +182,9 @@ static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port, struct mvpp2_tx_desc *tx_desc) { if (port->priv->hw_version == MVPP21) - return tx_desc->pp21.data_size; + return le16_to_cpu(tx_desc->pp21.data_size); else - return tx_desc->pp22.data_size; + return le16_to_cpu(tx_desc->pp22.data_size); } static void mvpp2_txdesc_size_set(struct mvpp2_port *port, @@ -191,9 +192,9 @@ static void mvpp2_txdesc_size_set(struct mvpp2_port *port, size_t size) { if (port->priv->hw_version == MVPP21) - tx_desc->pp21.data_size = size; + tx_desc->pp21.data_size = cpu_to_le16(size); else - tx_desc->pp22.data_size = size; + tx_desc->pp22.data_size = cpu_to_le16(size); } static void mvpp2_txdesc_txq_set(struct mvpp2_port *port, @@ -211,9 +212,9 @@ static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port, unsigned int command) { if (port->priv->hw_version == MVPP21) - tx_desc->pp21.command = command; + tx_desc->pp21.command = cpu_to_le32(command); else - tx_desc->pp22.command = command; + tx_desc->pp22.command = cpu_to_le32(command); } static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port, @@ -229,36 +230,38 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { if (port->priv->hw_version == MVPP21) - return rx_desc->pp21.buf_dma_addr; + return le32_to_cpu(rx_desc->pp21.buf_dma_addr); else - return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK; + return le64_to_cpu(rx_desc->pp22.buf_dma_addr_key_hash) & + MVPP2_DESC_DMA_MASK; } static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { if (port->priv->hw_version == MVPP21) - return rx_desc->pp21.buf_cookie; + return le32_to_cpu(rx_desc->pp21.buf_cookie); else - return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK; + return le64_to_cpu(rx_desc->pp22.buf_cookie_misc) & + MVPP2_DESC_DMA_MASK; } static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { if (port->priv->hw_version == MVPP21) - return rx_desc->pp21.data_size; + return le16_to_cpu(rx_desc->pp21.data_size); else - return rx_desc->pp22.data_size; + return le16_to_cpu(rx_desc->pp22.data_size); } static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port, struct mvpp2_rx_desc *rx_desc) { if (port->priv->hw_version == MVPP21) - return rx_desc->pp21.status; + return le32_to_cpu(rx_desc->pp21.status); else - return rx_desc->pp22.status; + return le32_to_cpu(rx_desc->pp22.status); } static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu) @@ -1735,7 +1738,7 @@ static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto, command |= (ip_hdr_len << MVPP2_TXD_IP_HLEN_SHIFT); command |= MVPP2_TXD_IP_CSUM_DISABLE; - if (l3_proto == swab16(ETH_P_IP)) { + if (l3_proto == htons(ETH_P_IP)) { command &= ~MVPP2_TXD_IP_CSUM_DISABLE; /* enable IPv4 csum */ command &= ~MVPP2_TXD_L3_IP6; /* enable IPv4 */ } else { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 6bb69f086794..a882c14d7d77 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -30,17 +30,17 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe) return -EINVAL; /* Clear entry invalidation bit */ - pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK; + pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK; /* Write tcam index - indirect access */ mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index); for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++) - mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam.word[i]); + mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]); /* Write sram index - indirect access */ mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index); for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++) - mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram.word[i]); + mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]); return 0; } @@ -60,18 +60,18 @@ static int mvpp2_prs_init_from_hw(struct mvpp2 *priv, /* Write tcam index - indirect access */ mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index); - pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv, + pe->tcam[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(MVPP2_PRS_TCAM_INV_WORD)); - if (pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK) + if (pe->tcam[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK) return MVPP2_PRS_TCAM_ENTRY_INVALID; for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++) - pe->tcam.word[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i)); + pe->tcam[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i)); /* Write sram index - indirect access */ mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index); for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++) - pe->sram.word[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i)); + pe->sram[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i)); return 0; } @@ -103,42 +103,35 @@ static void mvpp2_prs_shadow_ri_set(struct mvpp2 *priv, int index, /* Update lookup field in tcam sw entry */ static void mvpp2_prs_tcam_lu_set(struct mvpp2_prs_entry *pe, unsigned int lu) { - int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_LU_BYTE); - - pe->tcam.byte[MVPP2_PRS_TCAM_LU_BYTE] = lu; - pe->tcam.byte[enable_off] = MVPP2_PRS_LU_MASK; + pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU(MVPP2_PRS_LU_MASK); + pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK); + pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU(lu & MVPP2_PRS_LU_MASK); + pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK); } /* Update mask for single port in tcam sw entry */ static void mvpp2_prs_tcam_port_set(struct mvpp2_prs_entry *pe, unsigned int port, bool add) { - int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE); - if (add) - pe->tcam.byte[enable_off] &= ~(1 << port); + pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(BIT(port)); else - pe->tcam.byte[enable_off] |= 1 << port; + pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(BIT(port)); } /* Update port map in tcam sw entry */ static void mvpp2_prs_tcam_port_map_set(struct mvpp2_prs_entry *pe, unsigned int ports) { - unsigned char port_mask = MVPP2_PRS_PORT_MASK; - int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE); - - pe->tcam.byte[MVPP2_PRS_TCAM_PORT_BYTE] = 0; - pe->tcam.byte[enable_off] &= ~port_mask; - pe->tcam.byte[enable_off] |= ~ports & MVPP2_PRS_PORT_MASK; + pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT(MVPP2_PRS_PORT_MASK); + pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(MVPP2_PRS_PORT_MASK); + pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(~ports & MVPP2_PRS_PORT_MASK); } /* Obtain port map from tcam sw entry */ static unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe) { - int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE); - - return ~(pe->tcam.byte[enable_off]) & MVPP2_PRS_PORT_MASK; + return (~pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] >> 24) & MVPP2_PRS_PORT_MASK; } /* Set byte of data and its enable bits in tcam sw entry */ @@ -146,8 +139,12 @@ static void mvpp2_prs_tcam_data_byte_set(struct mvpp2_prs_entry *pe, unsigned int offs, unsigned char byte, unsigned char enable) { - pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)] = byte; - pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)] = enable; + int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE; + + pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(0xff << pos); + pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(MVPP2_PRS_TCAM_EN(0xff) << pos); + pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= byte << pos; + pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= MVPP2_PRS_TCAM_EN(enable << pos); } /* Get byte of data and its enable bits from tcam sw entry */ @@ -155,46 +152,45 @@ static void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe, unsigned int offs, unsigned char *byte, unsigned char *enable) { - *byte = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)]; - *enable = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)]; + int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE; + + *byte = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> pos) & 0xff; + *enable = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> (pos + 16)) & 0xff; } /* Compare tcam data bytes with a pattern */ static bool mvpp2_prs_tcam_data_cmp(struct mvpp2_prs_entry *pe, int offs, u16 data) { - int off = MVPP2_PRS_TCAM_DATA_BYTE(offs); u16 tcam_data; - tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off]; - if (tcam_data != data) - return false; - return true; + tcam_data = pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] & 0xffff; + return tcam_data == data; } /* Update ai bits in tcam sw entry */ static void mvpp2_prs_tcam_ai_update(struct mvpp2_prs_entry *pe, unsigned int bits, unsigned int enable) { - int i, ai_idx = MVPP2_PRS_TCAM_AI_BYTE; + int i; for (i = 0; i < MVPP2_PRS_AI_BITS; i++) { if (!(enable & BIT(i))) continue; if (bits & BIT(i)) - pe->tcam.byte[ai_idx] |= 1 << i; + pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= BIT(i); else - pe->tcam.byte[ai_idx] &= ~(1 << i); + pe->tcam[MVPP2_PRS_TCAM_AI_WORD] &= ~BIT(i); } - pe->tcam.byte[MVPP2_PRS_TCAM_EN_OFFS(ai_idx)] |= enable; + pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= MVPP2_PRS_TCAM_AI_EN(enable); } /* Get ai bits from tcam sw entry */ static int mvpp2_prs_tcam_ai_get(struct mvpp2_prs_entry *pe) { - return pe->tcam.byte[MVPP2_PRS_TCAM_AI_BYTE]; + return pe->tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK; } /* Set ethertype in tcam sw entry */ @@ -215,16 +211,16 @@ static void mvpp2_prs_match_vid(struct mvpp2_prs_entry *pe, int offset, /* Set bits in sram sw entry */ static void mvpp2_prs_sram_bits_set(struct mvpp2_prs_entry *pe, int bit_num, - int val) + u32 val) { - pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] |= (val << (bit_num % 8)); + pe->sram[MVPP2_BIT_TO_WORD(bit_num)] |= (val << (MVPP2_BIT_IN_WORD(bit_num))); } /* Clear bits in sram sw entry */ static void mvpp2_prs_sram_bits_clear(struct mvpp2_prs_entry *pe, int bit_num, - int val) + u32 val) { - pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] &= ~(val << (bit_num % 8)); + pe->sram[MVPP2_BIT_TO_WORD(bit_num)] &= ~(val << (MVPP2_BIT_IN_WORD(bit_num))); } /* Update ri bits in sram sw entry */ @@ -234,15 +230,16 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe, unsigned int i; for (i = 0; i < MVPP2_PRS_SRAM_RI_CTRL_BITS; i++) { - int ri_off = MVPP2_PRS_SRAM_RI_OFFS; - if (!(mask & BIT(i))) continue; if (bits & BIT(i)) - mvpp2_prs_sram_bits_set(pe, ri_off + i, 1); + mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_OFFS + i, + 1); else - mvpp2_prs_sram_bits_clear(pe, ri_off + i, 1); + mvpp2_prs_sram_bits_clear(pe, + MVPP2_PRS_SRAM_RI_OFFS + i, + 1); mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_CTRL_OFFS + i, 1); } @@ -251,7 +248,7 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe, /* Obtain ri bits from sram sw entry */ static int mvpp2_prs_sram_ri_get(struct mvpp2_prs_entry *pe) { - return pe->sram.word[MVPP2_PRS_SRAM_RI_WORD]; + return pe->sram[MVPP2_PRS_SRAM_RI_WORD]; } /* Update ai bits in sram sw entry */ @@ -259,16 +256,18 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe, unsigned int bits, unsigned int mask) { unsigned int i; - int ai_off = MVPP2_PRS_SRAM_AI_OFFS; for (i = 0; i < MVPP2_PRS_SRAM_AI_CTRL_BITS; i++) { if (!(mask & BIT(i))) continue; if (bits & BIT(i)) - mvpp2_prs_sram_bits_set(pe, ai_off + i, 1); + mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_OFFS + i, + 1); else - mvpp2_prs_sram_bits_clear(pe, ai_off + i, 1); + mvpp2_prs_sram_bits_clear(pe, + MVPP2_PRS_SRAM_AI_OFFS + i, + 1); mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_CTRL_OFFS + i, 1); } @@ -278,12 +277,12 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe, static int mvpp2_prs_sram_ai_get(struct mvpp2_prs_entry *pe) { u8 bits; - int ai_off = MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_AI_OFFS); - int ai_en_off = ai_off + 1; - int ai_shift = MVPP2_PRS_SRAM_AI_OFFS % 8; + /* ai is stored on bits 90->97; so it spreads across two u32 */ + int ai_off = MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_AI_OFFS); + int ai_shift = MVPP2_BIT_IN_WORD(MVPP2_PRS_SRAM_AI_OFFS); - bits = (pe->sram.byte[ai_off] >> ai_shift) | - (pe->sram.byte[ai_en_off] << (8 - ai_shift)); + bits = (pe->sram[ai_off] >> ai_shift) | + (pe->sram[ai_off + 1] << (32 - ai_shift)); return bits; } @@ -316,8 +315,7 @@ static void mvpp2_prs_sram_shift_set(struct mvpp2_prs_entry *pe, int shift, } /* Set value */ - pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_SHIFT_OFFS)] = - (unsigned char)shift; + pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK; /* Reset and set operation */ mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS, @@ -346,13 +344,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe, /* Set value */ mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_OFFS, MVPP2_PRS_SRAM_UDF_MASK); - mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS, offset); - pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS + - MVPP2_PRS_SRAM_UDF_BITS)] &= - ~(MVPP2_PRS_SRAM_UDF_MASK >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8))); - pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS + - MVPP2_PRS_SRAM_UDF_BITS)] |= - (offset >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8))); + mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS, + offset & MVPP2_PRS_SRAM_UDF_MASK); /* Set offset type */ mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_TYPE_OFFS, @@ -362,16 +355,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe, /* Set offset operation */ mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, MVPP2_PRS_SRAM_OP_SEL_UDF_MASK); - mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, op); - - pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS + - MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] &= - ~(MVPP2_PRS_SRAM_OP_SEL_UDF_MASK >> - (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8))); - - pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS + - MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] |= - (op >> (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8))); + mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, + op & MVPP2_PRS_SRAM_OP_SEL_UDF_MASK); /* Set base offset as current */ mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_BASE_OFFS, 1); @@ -662,7 +647,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai) continue; mvpp2_prs_init_from_hw(priv, &pe, tid); - match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid)); + match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid); if (!match) continue; @@ -790,8 +775,8 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1, mvpp2_prs_init_from_hw(priv, &pe, tid); - match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid1)) && - mvpp2_prs_tcam_data_cmp(&pe, 4, swab16(tpid2)); + match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) && + mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2); if (!match) continue; @@ -932,8 +917,8 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, pe.index = tid; /* Clear ri before updating */ - pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0; - pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; + pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0; + pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; mvpp2_prs_sram_ri_update(&pe, ri, ri_mask); mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE, @@ -1433,17 +1418,13 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv) pe.index = tid; - /* Clear tcam data before updating */ - pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(MVPP2_ETH_TYPE_LEN)] = 0x0; - pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(MVPP2_ETH_TYPE_LEN)] = 0x0; - mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN, MVPP2_PRS_IPV4_HEAD, MVPP2_PRS_IPV4_HEAD_MASK); /* Clear ri before updating */ - pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0; - pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; + pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0; + pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT, MVPP2_PRS_RI_L3_PROTO_MASK); @@ -1644,8 +1625,8 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv) MVPP2_PRS_IPV4_IHL_MASK); /* Clear ri before updating */ - pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0; - pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; + pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0; + pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4, MVPP2_PRS_RI_L3_PROTO_MASK); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h index 22fbbc4c8b28..a7c8d0818432 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h @@ -50,17 +50,25 @@ * The fields are represented by MVPP2_PRS_TCAM_DATA_REG(5)->(0). */ #define MVPP2_PRS_AI_BITS 8 +#define MVPP2_PRS_AI_MASK 0xff #define MVPP2_PRS_PORT_MASK 0xff #define MVPP2_PRS_LU_MASK 0xf -#define MVPP2_PRS_TCAM_DATA_BYTE(offs) \ - (((offs) - ((offs) % 2)) * 2 + ((offs) % 2)) -#define MVPP2_PRS_TCAM_DATA_BYTE_EN(offs) \ - (((offs) * 2) - ((offs) % 2) + 2) -#define MVPP2_PRS_TCAM_AI_BYTE 16 -#define MVPP2_PRS_TCAM_PORT_BYTE 17 -#define MVPP2_PRS_TCAM_LU_BYTE 20 -#define MVPP2_PRS_TCAM_EN_OFFS(offs) ((offs) + 2) -#define MVPP2_PRS_TCAM_INV_WORD 5 + +/* TCAM entries in registers are accessed using 16 data bits + 16 enable bits */ +#define MVPP2_PRS_BYTE_TO_WORD(byte) ((byte) / 2) +#define MVPP2_PRS_BYTE_IN_WORD(byte) ((byte) % 2) + +#define MVPP2_PRS_TCAM_EN(data) ((data) << 16) +#define MVPP2_PRS_TCAM_AI_WORD 4 +#define MVPP2_PRS_TCAM_AI(ai) (ai) +#define MVPP2_PRS_TCAM_AI_EN(ai) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_AI(ai)) +#define MVPP2_PRS_TCAM_PORT_WORD 4 +#define MVPP2_PRS_TCAM_PORT(p) ((p) << 8) +#define MVPP2_PRS_TCAM_PORT_EN(p) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_PORT(p)) +#define MVPP2_PRS_TCAM_LU_WORD 5 +#define MVPP2_PRS_TCAM_LU(lu) (lu) +#define MVPP2_PRS_TCAM_LU_EN(lu) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_LU(lu)) +#define MVPP2_PRS_TCAM_INV_WORD 5 #define MVPP2_PRS_VID_TCAM_BYTE 2 @@ -146,6 +154,7 @@ #define MVPP2_PRS_SRAM_RI_CTRL_BITS 32 #define MVPP2_PRS_SRAM_SHIFT_OFFS 64 #define MVPP2_PRS_SRAM_SHIFT_SIGN_BIT 72 +#define MVPP2_PRS_SRAM_SHIFT_MASK 0xff #define MVPP2_PRS_SRAM_UDF_OFFS 73 #define MVPP2_PRS_SRAM_UDF_BITS 8 #define MVPP2_PRS_SRAM_UDF_MASK 0xff @@ -255,20 +264,10 @@ enum mvpp2_prs_lookup { MVPP2_PRS_LU_LAST, }; -union mvpp2_prs_tcam_entry { - u32 word[MVPP2_PRS_TCAM_WORDS]; - u8 byte[MVPP2_PRS_TCAM_WORDS * 4]; -}; - -union mvpp2_prs_sram_entry { - u32 word[MVPP2_PRS_SRAM_WORDS]; - u8 byte[MVPP2_PRS_SRAM_WORDS * 4]; -}; - struct mvpp2_prs_entry { u32 index; - union mvpp2_prs_tcam_entry tcam; - union mvpp2_prs_sram_entry sram; + u32 tcam[MVPP2_PRS_TCAM_WORDS]; + u32 sram[MVPP2_PRS_SRAM_WORDS]; }; struct mvpp2_prs_shadow { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9efbf193ad5a..d923f2f58608 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o fpga/tls.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ - en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \ - en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o + en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o \ + vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index eb9eb7aa953a..e2b7586ed7a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -137,7 +137,6 @@ struct page_pool; #define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE >> 1) #define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC) #define MLX5E_TX_CQ_POLL_BUDGET 128 -#define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */ #define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */ #define MLX5E_UMR_WQE_INLINE_SZ \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index f20074dbef32..39a5d13ba459 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -34,12 +34,11 @@ #ifndef __MLX5E_EN_ACCEL_H__ #define __MLX5E_EN_ACCEL_H__ -#ifdef CONFIG_MLX5_ACCEL - #include <linux/skbuff.h> #include <linux/netdevice.h> #include "en_accel/ipsec_rxtx.h" #include "en_accel/tls_rxtx.h" +#include "en_accel/rxtx.h" #include "en.h" static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb, @@ -64,9 +63,13 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb, } #endif + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi); + if (unlikely(!skb)) + return NULL; + } + return skb; } -#endif /* CONFIG_MLX5_ACCEL */ - #endif /* __MLX5E_EN_ACCEL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c new file mode 100644 index 000000000000..7b7ec3998e84 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c @@ -0,0 +1,109 @@ +#include "en_accel/rxtx.h" + +static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb, + struct sk_buff *nskb, + int remaining) +{ + int bytes_needed = remaining, remaining_headlen, remaining_page_offset; + int headlen = skb_transport_offset(skb) + sizeof(struct udphdr); + int payload_len = remaining + sizeof(struct udphdr); + int k = 0, i, j; + + skb_copy_bits(skb, 0, nskb->data, headlen); + nskb->dev = skb->dev; + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, skb_network_offset(skb)); + skb_set_transport_header(nskb, skb_transport_offset(skb)); + skb_set_tail_pointer(nskb, headlen); + + /* How many frags do we need? */ + for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) { + bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]); + k++; + if (bytes_needed <= 0) + break; + } + + /* Fill the first frag and split it if necessary */ + j = skb_shinfo(skb)->nr_frags - k; + remaining_page_offset = -bytes_needed; + skb_fill_page_desc(nskb, 0, + skb_shinfo(skb)->frags[j].page.p, + skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset, + skb_shinfo(skb)->frags[j].size - remaining_page_offset); + + skb_frag_ref(skb, j); + + /* Fill the rest of the frags */ + for (i = 1; i < k; i++) { + j = skb_shinfo(skb)->nr_frags - k + i; + + skb_fill_page_desc(nskb, i, + skb_shinfo(skb)->frags[j].page.p, + skb_shinfo(skb)->frags[j].page_offset, + skb_shinfo(skb)->frags[j].size); + skb_frag_ref(skb, j); + } + skb_shinfo(nskb)->nr_frags = k; + + remaining_headlen = remaining - skb->data_len; + + /* headlen contains remaining data? */ + if (remaining_headlen > 0) + skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen, + remaining_headlen); + nskb->len = remaining + headlen; + nskb->data_len = payload_len - sizeof(struct udphdr) + + max_t(int, 0, remaining_headlen); + nskb->protocol = skb->protocol; + if (nskb->protocol == htons(ETH_P_IP)) { + ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) + + skb_shinfo(skb)->gso_segs); + ip_hdr(nskb)->tot_len = + htons(payload_len + sizeof(struct iphdr)); + } else { + ipv6_hdr(nskb)->payload_len = htons(payload_len); + } + udp_hdr(nskb)->len = htons(payload_len); + skb_shinfo(nskb)->gso_size = 0; + nskb->ip_summed = skb->ip_summed; + nskb->csum_start = skb->csum_start; + nskb->csum_offset = skb->csum_offset; + nskb->queue_mapping = skb->queue_mapping; +} + +/* might send skbs and update wqe and pi */ +struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev, + struct mlx5e_txqsq *sq, + struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ + int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr); + int headlen = skb_transport_offset(skb) + sizeof(struct udphdr); + int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size; + struct sk_buff *nskb; + + if (skb->protocol == htons(ETH_P_IP)) + ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr)); + else + ipv6_hdr(skb)->payload_len = htons(payload_len); + udp_hdr(skb)->len = htons(payload_len); + if (!remaining) + return skb; + + sq->stats->udp_seg_rem++; + nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC); + if (unlikely(!nskb)) { + sq->stats->dropped++; + return NULL; + } + + mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining); + + skb_shinfo(skb)->gso_segs--; + pskb_trim(skb, skb->len - remaining); + mlx5e_sq_xmit(sq, skb, *wqe, *pi); + mlx5e_sq_fetch_wqe(sq, wqe, pi); + return nskb; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h new file mode 100644 index 000000000000..ed42699a78b3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h @@ -0,0 +1,14 @@ + +#ifndef __MLX5E_EN_ACCEL_RX_TX_H__ +#define __MLX5E_EN_ACCEL_RX_TX_H__ + +#include <linux/skbuff.h> +#include "en.h" + +struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev, + struct mlx5e_txqsq *sq, + struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dae4156a710d..bbd2fd0b2e06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -270,12 +270,9 @@ void mlx5e_update_stats_work(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv, update_stats_work); + mutex_lock(&priv->state_lock); - if (test_bit(MLX5E_STATE_OPENED, &priv->state)) { - priv->profile->update_stats(priv); - queue_delayed_work(priv->wq, dwork, - msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL)); - } + priv->profile->update_stats(priv); mutex_unlock(&priv->state_lock); } @@ -352,8 +349,8 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, { int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); - rq->mpwqe.info = kcalloc_node(wq_sz, sizeof(*rq->mpwqe.info), - GFP_KERNEL, cpu_to_node(c->cpu)); + rq->mpwqe.info = kvzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->mpwqe.info) return -ENOMEM; @@ -670,7 +667,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err_free: switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - kfree(rq->mpwqe.info); + kvfree(rq->mpwqe.info); mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); break; default: /* MLX5_WQ_TYPE_CYCLIC */ @@ -702,7 +699,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - kfree(rq->mpwqe.info); + kvfree(rq->mpwqe.info); mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); break; default: /* MLX5_WQ_TYPE_CYCLIC */ @@ -965,15 +962,15 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq) static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq) { - kfree(sq->db.di); + kvfree(sq->db.di); } static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) { int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); - sq->db.di = kcalloc_node(wq_sz, sizeof(*sq->db.di), - GFP_KERNEL, numa); + sq->db.di = kvzalloc_node(sizeof(*sq->db.di) * wq_sz, + GFP_KERNEL, numa); if (!sq->db.di) { mlx5e_free_xdpsq_db(sq); return -ENOMEM; @@ -1024,15 +1021,15 @@ static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq) static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq) { - kfree(sq->db.ico_wqe); + kvfree(sq->db.ico_wqe); } static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa) { u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq); - sq->db.ico_wqe = kcalloc_node(wq_sz, sizeof(*sq->db.ico_wqe), - GFP_KERNEL, numa); + sq->db.ico_wqe = kvzalloc_node(sizeof(*sq->db.ico_wqe) * wq_sz, + GFP_KERNEL, numa); if (!sq->db.ico_wqe) return -ENOMEM; @@ -1077,8 +1074,8 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq) static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq) { - kfree(sq->db.wqe_info); - kfree(sq->db.dma_fifo); + kvfree(sq->db.wqe_info); + kvfree(sq->db.dma_fifo); } static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) @@ -1086,10 +1083,10 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) int wq_sz = mlx5_wq_cyc_get_size(&sq->wq); int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS; - sq->db.dma_fifo = kcalloc_node(df_sz, sizeof(*sq->db.dma_fifo), - GFP_KERNEL, numa); - sq->db.wqe_info = kcalloc_node(wq_sz, sizeof(*sq->db.wqe_info), - GFP_KERNEL, numa); + sq->db.dma_fifo = kvzalloc_node(df_sz * sizeof(*sq->db.dma_fifo), + GFP_KERNEL, numa); + sq->db.wqe_info = kvzalloc_node(wq_sz * sizeof(*sq->db.wqe_info), + GFP_KERNEL, numa); if (!sq->db.dma_fifo || !sq->db.wqe_info) { mlx5e_free_txqsq_db(sq); return -ENOMEM; @@ -1893,7 +1890,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, int err; int eqn; - c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); + c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); if (!c) return -ENOMEM; @@ -1979,7 +1976,7 @@ err_close_icosq_cq: err_napi_del: netif_napi_del(&c->napi); - kfree(c); + kvfree(c); return err; } @@ -2018,7 +2015,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) mlx5e_close_cq(&c->icosq.cq); netif_napi_del(&c->napi); - kfree(c); + kvfree(c); } #define DEFAULT_FRAG_SIZE (2048) @@ -2276,7 +2273,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, chs->num = chs->params.num_channels; chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL); - cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL); + cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL); if (!chs->c || !cparam) goto err_free; @@ -2287,7 +2284,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } - kfree(cparam); + kvfree(cparam); return 0; err_close_channels: @@ -2296,7 +2293,7 @@ err_close_channels: err_free: kfree(chs->c); - kfree(cparam); + kvfree(cparam); chs->num = 0; return err; } @@ -3371,7 +3368,7 @@ static int mlx5e_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb, - priv, priv); + priv, priv, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb, priv); @@ -3405,6 +3402,9 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; + /* update HW stats in background for next time */ + queue_delayed_work(priv->wq, &priv->update_stats_work, 0); + if (mlx5e_is_uplink_rep(priv)) { stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok); stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok); @@ -4592,6 +4592,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->features |= NETIF_F_HIGHDMA; netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER; + netdev->features |= NETIF_F_GSO_UDP_L4; + netdev->hw_features |= NETIF_F_GSO_UDP_L4; + netdev->priv_flags |= IFF_UNICAST_FLT; mlx5e_set_netdev_dev_addr(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 2b8040a3cdbd..8e3c5b4b90ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -797,7 +797,7 @@ static int mlx5e_rep_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb, - priv, priv); + priv, priv, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv); return 0; @@ -897,6 +897,9 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx5e_priv *priv = netdev_priv(dev); + /* update HW stats in background for next time */ + queue_delayed_work(priv->wq, &priv->update_stats_work, 0); + memcpy(stats, &priv->stats.vf_vport, sizeof(*stats)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index d3a1dd20e41d..f763a6aebc2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -487,7 +487,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR; sq->pc += MLX5E_UMR_WQEBBS; - mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl); + mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl); return 0; @@ -601,6 +601,8 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) if (!rq->mpwqe.umr_in_progress) mlx5e_alloc_rx_mpwqe(rq, wq->head); + else + rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2; return false; } @@ -1261,7 +1263,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) } if (unlikely(mpwrq_is_filler_cqe(cqe))) { - rq->stats->mpwqe_filler++; + struct mlx5e_rq_stats *stats = rq->stats; + + stats->mpwqe_filler_cqes++; + stats->mpwqe_filler_strides += cstrides; goto mpwrq_cqe_out; } @@ -1383,6 +1388,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) } while (!last_wqe); } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + rq->stats->xdp_tx_cqe += i; + mlx5_cqwq_update_db_record(&cq->wq); /* ensure cq space is freed before enabling more cqes */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 1646859974ce..c0507fada0be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -44,6 +44,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) }, #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) }, @@ -59,6 +60,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) }, @@ -67,10 +69,13 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) }, @@ -80,6 +85,11 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) }, }; @@ -133,9 +143,11 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; s->rx_xdp_drop += rq_stats->xdp_drop; s->rx_xdp_tx += rq_stats->xdp_tx; + s->rx_xdp_tx_cqe += rq_stats->xdp_tx_cqe; s->rx_xdp_tx_full += rq_stats->xdp_tx_full; s->rx_wqe_err += rq_stats->wqe_err; - s->rx_mpwqe_filler += rq_stats->mpwqe_filler; + s->rx_mpwqe_filler_cqes += rq_stats->mpwqe_filler_cqes; + s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides; s->rx_buff_alloc_err += rq_stats->buff_alloc_err; s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks; s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts; @@ -145,6 +157,11 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_cache_empty += rq_stats->cache_empty; s->rx_cache_busy += rq_stats->cache_busy; s->rx_cache_waive += rq_stats->cache_waive; + s->rx_congst_umr += rq_stats->congst_umr; + s->ch_events += ch_stats->events; + s->ch_poll += ch_stats->poll; + s->ch_arm += ch_stats->arm; + s->ch_aff_change += ch_stats->aff_change; s->ch_eq_rearm += ch_stats->eq_rearm; for (j = 0; j < priv->max_opened_tc; j++) { @@ -157,8 +174,10 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_tso_inner_packets += sq_stats->tso_inner_packets; s->tx_tso_inner_bytes += sq_stats->tso_inner_bytes; s->tx_added_vlan_packets += sq_stats->added_vlan_packets; + s->tx_nop += sq_stats->nop; s->tx_queue_stopped += sq_stats->stopped; s->tx_queue_wake += sq_stats->wake; + s->tx_udp_seg_rem += sq_stats->udp_seg_rem; s->tx_queue_dropped += sq_stats->dropped; s->tx_cqe_err += sq_stats->cqe_err; s->tx_recover += sq_stats->recover; @@ -170,6 +189,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_tls_ooo += sq_stats->tls_ooo; s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes; #endif + s->tx_cqes += sq_stats->cqes; } } @@ -1107,12 +1127,14 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) }, @@ -1122,6 +1144,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) }, }; static const struct counter_desc sq_stats_desc[] = { @@ -1140,11 +1163,16 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqes) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) }, }; static const struct counter_desc ch_stats_desc[] = { + { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) }, + { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) }, + { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) }, + { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) }, { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) }, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 643153bb3607..fc3f66003edd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -61,6 +61,7 @@ struct mlx5e_sw_stats { u64 tx_tso_inner_packets; u64 tx_tso_inner_bytes; u64 tx_added_vlan_packets; + u64 tx_nop; u64 rx_lro_packets; u64 rx_lro_bytes; u64 rx_removed_vlan_packets; @@ -70,6 +71,7 @@ struct mlx5e_sw_stats { u64 rx_csum_unnecessary_inner; u64 rx_xdp_drop; u64 rx_xdp_tx; + u64 rx_xdp_tx_cqe; u64 rx_xdp_tx_full; u64 tx_csum_none; u64 tx_csum_partial; @@ -78,10 +80,13 @@ struct mlx5e_sw_stats { u64 tx_queue_dropped; u64 tx_xmit_more; u64 tx_recover; + u64 tx_cqes; u64 tx_queue_wake; + u64 tx_udp_seg_rem; u64 tx_cqe_err; u64 rx_wqe_err; - u64 rx_mpwqe_filler; + u64 rx_mpwqe_filler_cqes; + u64 rx_mpwqe_filler_strides; u64 rx_buff_alloc_err; u64 rx_cqe_compress_blks; u64 rx_cqe_compress_pkts; @@ -91,6 +96,11 @@ struct mlx5e_sw_stats { u64 rx_cache_empty; u64 rx_cache_busy; u64 rx_cache_waive; + u64 rx_congst_umr; + u64 ch_events; + u64 ch_poll; + u64 ch_arm; + u64 ch_aff_change; u64 ch_eq_rearm; #ifdef CONFIG_MLX5_EN_TLS @@ -169,9 +179,11 @@ struct mlx5e_rq_stats { u64 removed_vlan_packets; u64 xdp_drop; u64 xdp_tx; + u64 xdp_tx_cqe; u64 xdp_tx_full; u64 wqe_err; - u64 mpwqe_filler; + u64 mpwqe_filler_cqes; + u64 mpwqe_filler_strides; u64 buff_alloc_err; u64 cqe_compress_blks; u64 cqe_compress_pkts; @@ -181,6 +193,7 @@ struct mlx5e_rq_stats { u64 cache_empty; u64 cache_busy; u64 cache_waive; + u64 congst_umr; }; struct mlx5e_sq_stats { @@ -196,6 +209,7 @@ struct mlx5e_sq_stats { u64 csum_partial_inner; u64 added_vlan_packets; u64 nop; + u64 udp_seg_rem; #ifdef CONFIG_MLX5_EN_TLS u64 tls_ooo; u64 tls_resync_bytes; @@ -206,11 +220,16 @@ struct mlx5e_sq_stats { u64 dropped; u64 recover; /* dirtied @completion */ - u64 wake ____cacheline_aligned_in_smp; + u64 cqes ____cacheline_aligned_in_smp; + u64 wake; u64 cqe_err; }; struct mlx5e_ch_stats { + u64 events; + u64 poll; + u64 arm; + u64 aff_change; u64 eq_rearm; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index f29deb44bf3b..f0739dae7b56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -228,7 +228,10 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb) stats->tso_inner_packets++; stats->tso_inner_bytes += skb->len - ihs; } else { - ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + ihs = skb_transport_offset(skb) + sizeof(struct udphdr); + else + ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); stats->tso_packets++; stats->tso_bytes += skb->len - ihs; } @@ -443,12 +446,11 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) sq = priv->txq2sq[skb_get_queue_mapping(skb)]; mlx5e_sq_fetch_wqe(sq, &wqe, &pi); -#ifdef CONFIG_MLX5_ACCEL /* might send skbs and update wqe and pi */ skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi); if (unlikely(!skb)) return NETDEV_TX_OK; -#endif + return mlx5e_sq_xmit(sq, skb, wqe, pi); } @@ -466,6 +468,7 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq, bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { + struct mlx5e_sq_stats *stats; struct mlx5e_txqsq *sq; struct mlx5_cqe64 *cqe; u32 dma_fifo_cc; @@ -483,6 +486,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) if (!cqe) return false; + stats = sq->stats; + npkts = 0; nbytes = 0; @@ -511,7 +516,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) queue_work(cq->channel->priv->wq, &sq->recover.recover_work); } - sq->stats->cqe_err++; + stats->cqe_err++; } do { @@ -556,6 +561,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + stats->cqes += i; + mlx5_cqwq_update_db_record(&cq->wq); /* ensure cq space is freed before enabling more cqes */ @@ -571,7 +578,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) MLX5E_SQ_STOP_ROOM) && !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { netif_tx_wake_queue(sq->txq); - sq->stats->wake++; + stats->wake++; } return (i == MLX5E_TX_CQ_POLL_BUDGET); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 1b17f682693b..4e1f99a98d5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -74,10 +74,13 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) { struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, napi); + struct mlx5e_ch_stats *ch_stats = c->stats; bool busy = false; int work_done = 0; int i; + ch_stats->poll++; + for (i = 0; i < c->num_tc; i++) busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget); @@ -94,6 +97,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (busy) { if (likely(mlx5e_channel_no_affinity_change(c))) return budget; + ch_stats->aff_change++; if (budget && work_done == budget) work_done--; } @@ -101,6 +105,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (unlikely(!napi_complete_done(napi, work_done))) return work_done; + ch_stats->arm++; + for (i = 0; i < c->num_tc; i++) { mlx5e_handle_tx_dim(&c->sq[i]); mlx5e_cq_arm(&c->sq[i].cq); @@ -118,8 +124,9 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq) { struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); - cq->event_ctr++; napi_schedule(cq->napi); + cq->event_ctr++; + cq->channel->stats->events++; } void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 0b47126815b6..2bd4c3184eba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -229,6 +229,11 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq) return !wq->cur_sz; } +static inline int mlx5_wq_ll_missing(struct mlx5_wq_ll *wq) +{ + return wq->fbc.sz_m1 - wq->cur_sz; +} + static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix) { return mlx5_frag_buf_get_wqe(&wq->fbc, ix); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 968b88af2ef5..52437363766a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1503,7 +1503,8 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type, static int mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, - struct tcf_block *block, bool ingress) + struct tcf_block *block, bool ingress, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_acl_block *acl_block; @@ -1518,7 +1519,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, return -ENOMEM; block_cb = __tcf_block_cb_register(block, mlxsw_sp_setup_tc_block_cb_flower, - mlxsw_sp, acl_block); + mlxsw_sp, acl_block, extack); if (IS_ERR(block_cb)) { err = PTR_ERR(block_cb); goto err_cb_register; @@ -1541,7 +1542,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, err_block_bind: if (!tcf_block_cb_decref(block_cb)) { - __tcf_block_cb_unregister(block_cb); + __tcf_block_cb_unregister(block, block_cb); err_cb_register: mlxsw_sp_acl_block_destroy(acl_block); } @@ -1571,7 +1572,7 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port, err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block, mlxsw_sp_port, ingress); if (!err && !tcf_block_cb_decref(block_cb)) { - __tcf_block_cb_unregister(block_cb); + __tcf_block_cb_unregister(block, block_cb); mlxsw_sp_acl_block_destroy(acl_block); } } @@ -1596,11 +1597,12 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, switch (f->command) { case TC_BLOCK_BIND: err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port, - mlxsw_sp_port); + mlxsw_sp_port, f->extack); if (err) return err; err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port, - f->block, ingress); + f->block, ingress, + f->extack); if (err) { tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 6aaaf3d9ba31..88bd27ace8d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -163,7 +163,8 @@ struct mlxsw_sp_rif_ops { const struct mlxsw_sp_rif_params *params); int (*configure)(struct mlxsw_sp_rif *rif); void (*deconfigure)(struct mlxsw_sp_rif *rif); - struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif); + struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack); }; static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree); @@ -342,10 +343,6 @@ static void mlxsw_sp_rif_counters_free(struct mlxsw_sp_rif *rif) mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS); } -static struct mlxsw_sp_rif * -mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *dev); - #define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE + 1) struct mlxsw_sp_prefix_usage { @@ -5967,7 +5964,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, return NOTIFY_DONE; } -static struct mlxsw_sp_rif * +struct mlxsw_sp_rif * mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { @@ -6125,6 +6122,11 @@ const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif) return rif->dev; } +struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif) +{ + return rif->fid; +} + static struct mlxsw_sp_rif * mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_rif_params *params, @@ -6162,7 +6164,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, rif->ops = ops; if (ops->fid_get) { - fid = ops->fid_get(rif); + fid = ops->fid_get(rif, extack); if (IS_ERR(fid)) { err = PTR_ERR(fid); goto err_fid_get; @@ -6267,7 +6269,7 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, } /* FID was already created, just take a reference */ - fid = rif->ops->fid_get(rif); + fid = rif->ops->fid_get(rif, extack); err = mlxsw_sp_fid_port_vid_map(fid, mlxsw_sp_port, vid); if (err) goto err_fid_port_vid_map; @@ -6775,7 +6777,8 @@ static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif) } static struct mlxsw_sp_fid * -mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif) +mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { return mlxsw_sp_fid_rfid_get(rif->mlxsw_sp, rif->rif_index); } @@ -6865,9 +6868,23 @@ static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif) } static struct mlxsw_sp_fid * -mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif) +mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { - u16 vid = is_vlan_dev(rif->dev) ? vlan_dev_vlan_id(rif->dev) : 1; + u16 vid; + int err; + + if (is_vlan_dev(rif->dev)) { + vid = vlan_dev_vlan_id(rif->dev); + } else { + err = br_vlan_get_pvid(rif->dev, &vid); + if (!vid) + err = -EINVAL; + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID"); + return ERR_PTR(err); + } + } return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid); } @@ -6937,7 +6954,8 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif) } static struct mlxsw_sp_fid * -mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif) +mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif, + struct netlink_ext_ack *extack) { return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index a01edcf56797..52e25695625c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -66,6 +66,8 @@ struct mlxsw_sp_neigh_entry; struct mlxsw_sp_nexthop; struct mlxsw_sp_ipip_entry; +struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp, u16 rif_index); u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif); @@ -75,6 +77,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev); int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif); u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp); const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif); +struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif); int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, enum mlxsw_sp_rif_counter_dir dir, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index eea5666a86b2..da94e1eb9e16 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1135,6 +1135,39 @@ err_port_vlan_set: return err; } +static int +mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp, + const struct net_device *br_dev, + const struct switchdev_obj_port_vlan *vlan) +{ + struct mlxsw_sp_rif *rif; + struct mlxsw_sp_fid *fid; + u16 pvid; + u16 vid; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev); + if (!rif) + return 0; + fid = mlxsw_sp_rif_fid(rif); + pvid = mlxsw_sp_fid_8021q_vid(fid); + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { + if (vlan->flags & BRIDGE_VLAN_INFO_PVID) { + if (vid != pvid) { + netdev_err(br_dev, "Can't change PVID, it's used by router interface\n"); + return -EBUSY; + } + } else { + if (vid == pvid) { + netdev_err(br_dev, "Can't remove PVID, it's used by router interface\n"); + return -EBUSY; + } + } + } + + return 0; +} + static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans) @@ -1146,8 +1179,18 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_bridge_port *bridge_port; u16 vid; - if (netif_is_bridge_master(orig_dev)) - return -EOPNOTSUPP; + if (netif_is_bridge_master(orig_dev)) { + int err = 0; + + if ((vlan->flags & BRIDGE_VLAN_INFO_BRENTRY) && + br_vlan_enabled(orig_dev) && + switchdev_trans_ph_prepare(trans)) + err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp, + orig_dev, vlan); + if (!err) + err = -EOPNOTSUPP; + return err; + } if (switchdev_trans_ph_prepare(trans)) return 0; diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index dd947e4dd3ce..e1747a490066 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -828,7 +828,7 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter) } if (!mac_address_valid) - random_ether_addr(adapter->mac_address); + eth_random_addr(adapter->mac_address); lan743x_mac_set_address(adapter, adapter->mac_address); ether_addr_copy(netdev->dev_addr, adapter->mac_address); return 0; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 776a8a9be8e3..1a4f2bb48ead 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -148,12 +148,191 @@ static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot) return 0; } +static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask) +{ + /* Select the VID to configure */ + ocelot_write(ocelot, ANA_TABLES_VLANTIDX_V_INDEX(vid), + ANA_TABLES_VLANTIDX); + /* Set the vlan port members mask and issue a write command */ + ocelot_write(ocelot, ANA_TABLES_VLANACCESS_VLAN_PORT_MASK(mask) | + ANA_TABLES_VLANACCESS_CMD_WRITE, + ANA_TABLES_VLANACCESS); + + return ocelot_vlant_wait_for_completion(ocelot); +} + +static void ocelot_vlan_mode(struct ocelot_port *port, + netdev_features_t features) +{ + struct ocelot *ocelot = port->ocelot; + u8 p = port->chip_port; + u32 val; + + /* Filtering */ + val = ocelot_read(ocelot, ANA_VLANMASK); + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) + val |= BIT(p); + else + val &= ~BIT(p); + ocelot_write(ocelot, val, ANA_VLANMASK); +} + +static void ocelot_vlan_port_apply(struct ocelot *ocelot, + struct ocelot_port *port) +{ + u32 val; + + /* Ingress clasification (ANA_PORT_VLAN_CFG) */ + /* Default vlan to clasify for untagged frames (may be zero) */ + val = ANA_PORT_VLAN_CFG_VLAN_VID(port->pvid); + if (port->vlan_aware) + val |= ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | + ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1); + + ocelot_rmw_gix(ocelot, val, + ANA_PORT_VLAN_CFG_VLAN_VID_M | + ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | + ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, + ANA_PORT_VLAN_CFG, port->chip_port); + + /* Drop frames with multicast source address */ + val = ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA; + if (port->vlan_aware && !port->vid) + /* If port is vlan-aware and tagged, drop untagged and priority + * tagged frames. + */ + val |= ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; + ocelot_write_gix(ocelot, val, ANA_PORT_DROP_CFG, port->chip_port); + + /* Egress configuration (REW_TAG_CFG): VLAN tag type to 8021Q. */ + val = REW_TAG_CFG_TAG_TPID_CFG(0); + + if (port->vlan_aware) { + if (port->vid) + /* Tag all frames except when VID == DEFAULT_VLAN */ + val |= REW_TAG_CFG_TAG_CFG(1); + else + /* Tag all frames */ + val |= REW_TAG_CFG_TAG_CFG(3); + } + ocelot_rmw_gix(ocelot, val, + REW_TAG_CFG_TAG_TPID_CFG_M | + REW_TAG_CFG_TAG_CFG_M, + REW_TAG_CFG, port->chip_port); + + /* Set default VLAN and tag type to 8021Q. */ + val = REW_PORT_VLAN_CFG_PORT_TPID(ETH_P_8021Q) | + REW_PORT_VLAN_CFG_PORT_VID(port->vid); + ocelot_rmw_gix(ocelot, val, + REW_PORT_VLAN_CFG_PORT_TPID_M | + REW_PORT_VLAN_CFG_PORT_VID_M, + REW_PORT_VLAN_CFG, port->chip_port); +} + +static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid, + bool untagged) +{ + struct ocelot_port *port = netdev_priv(dev); + struct ocelot *ocelot = port->ocelot; + int ret; + + /* Add the port MAC address to with the right VLAN information */ + ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, vid, + ENTRYTYPE_LOCKED); + + /* Make the port a member of the VLAN */ + ocelot->vlan_mask[vid] |= BIT(port->chip_port); + ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]); + if (ret) + return ret; + + /* Default ingress vlan classification */ + if (pvid) + port->pvid = vid; + + /* Untagged egress vlan clasification */ + if (untagged) + port->vid = vid; + + ocelot_vlan_port_apply(ocelot, port); + + return 0; +} + +static int ocelot_vlan_vid_del(struct net_device *dev, u16 vid) +{ + struct ocelot_port *port = netdev_priv(dev); + struct ocelot *ocelot = port->ocelot; + int ret; + + /* 8021q removes VID 0 on module unload for all interfaces + * with VLAN filtering feature. We need to keep it to receive + * untagged traffic. + */ + if (vid == 0) + return 0; + + /* Del the port MAC address to with the right VLAN information */ + ocelot_mact_forget(ocelot, dev->dev_addr, vid); + + /* Stop the port from being a member of the vlan */ + ocelot->vlan_mask[vid] &= ~BIT(port->chip_port); + ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]); + if (ret) + return ret; + + /* Ingress */ + if (port->pvid == vid) + port->pvid = 0; + + /* Egress */ + if (port->vid == vid) + port->vid = 0; + + ocelot_vlan_port_apply(ocelot, port); + + return 0; +} + static void ocelot_vlan_init(struct ocelot *ocelot) { + u16 port, vid; + /* Clear VLAN table, by default all ports are members of all VLANs */ ocelot_write(ocelot, ANA_TABLES_VLANACCESS_CMD_INIT, ANA_TABLES_VLANACCESS); ocelot_vlant_wait_for_completion(ocelot); + + /* Configure the port VLAN memberships */ + for (vid = 1; vid < VLAN_N_VID; vid++) { + ocelot->vlan_mask[vid] = 0; + ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]); + } + + /* Because VLAN filtering is enabled, we need VID 0 to get untagged + * traffic. It is added automatically if 8021q module is loaded, but + * we can't rely on it since module may be not loaded. + */ + ocelot->vlan_mask[0] = GENMASK(ocelot->num_phys_ports - 1, 0); + ocelot_vlant_set_mask(ocelot, 0, ocelot->vlan_mask[0]); + + /* Configure the CPU port to be VLAN aware */ + ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) | + ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | + ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1), + ANA_PORT_VLAN_CFG, ocelot->num_phys_ports); + + /* Set vlan ingress filter mask to all ports but the CPU port by + * default. + */ + ocelot_write(ocelot, GENMASK(9, 0), ANA_VLANMASK); + + for (port = 0; port < ocelot->num_phys_ports; port++) { + ocelot_write_gix(ocelot, 0, REW_PORT_VLAN_CFG, port); + ocelot_write_gix(ocelot, 0, REW_TAG_CFG, port); + } } /* Watermark encode @@ -539,6 +718,20 @@ static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct ocelot_port *port = netdev_priv(dev); struct ocelot *ocelot = port->ocelot; + if (!vid) { + if (!port->vlan_aware) + /* If the bridge is not VLAN aware and no VID was + * provided, set it to pvid to ensure the MAC entry + * matches incoming untagged packets + */ + vid = port->pvid; + else + /* If the bridge is VLAN aware a VID must be provided as + * otherwise the learnt entry wouldn't match any frame. + */ + return -EINVAL; + } + return ocelot_mact_learn(ocelot, port->chip_port, addr, vid, ENTRYTYPE_NORMAL); } @@ -690,6 +883,30 @@ end: return ret; } +static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto, + u16 vid) +{ + return ocelot_vlan_vid_add(dev, vid, false, true); +} + +static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, + u16 vid) +{ + return ocelot_vlan_vid_del(dev, vid); +} + +static int ocelot_set_features(struct net_device *dev, + netdev_features_t features) +{ + struct ocelot_port *port = netdev_priv(dev); + netdev_features_t changed = dev->features ^ features; + + if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) + ocelot_vlan_mode(port, features); + + return 0; +} + static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_open = ocelot_port_open, .ndo_stop = ocelot_port_stop, @@ -701,6 +918,9 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_fdb_add = ocelot_fdb_add, .ndo_fdb_del = ocelot_fdb_del, .ndo_fdb_dump = ocelot_fdb_dump, + .ndo_vlan_rx_add_vid = ocelot_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ocelot_vlan_rx_kill_vid, + .ndo_set_features = ocelot_set_features, }; static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data) @@ -780,6 +1000,8 @@ static const struct ethtool_ops ocelot_ethtool_ops = { .get_strings = ocelot_get_strings, .get_ethtool_stats = ocelot_get_ethtool_stats, .get_sset_count = ocelot_get_sset_count, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, }; static int ocelot_port_attr_get(struct net_device *dev, @@ -914,6 +1136,10 @@ static int ocelot_port_attr_set(struct net_device *dev, case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: ocelot_port_attr_ageing_set(ocelot_port, attr->u.ageing_time); break; + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + ocelot_port->vlan_aware = attr->u.vlan_filtering; + ocelot_vlan_port_apply(ocelot_port->ocelot, ocelot_port); + break; case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED: ocelot_port_attr_mc_set(ocelot_port, !attr->u.mc_disabled); break; @@ -925,6 +1151,40 @@ static int ocelot_port_attr_set(struct net_device *dev, return err; } +static int ocelot_port_obj_add_vlan(struct net_device *dev, + const struct switchdev_obj_port_vlan *vlan, + struct switchdev_trans *trans) +{ + int ret; + u16 vid; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + ret = ocelot_vlan_vid_add(dev, vid, + vlan->flags & BRIDGE_VLAN_INFO_PVID, + vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); + if (ret) + return ret; + } + + return 0; +} + +static int ocelot_port_vlan_del_vlan(struct net_device *dev, + const struct switchdev_obj_port_vlan *vlan) +{ + int ret; + u16 vid; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + ret = ocelot_vlan_vid_del(dev, vid); + + if (ret) + return ret; + } + + return 0; +} + static struct ocelot_multicast *ocelot_multicast_get(struct ocelot *ocelot, const unsigned char *addr, u16 vid) @@ -951,7 +1211,7 @@ static int ocelot_port_obj_add_mdb(struct net_device *dev, bool new = false; if (!vid) - vid = 1; + vid = port->pvid; mc = ocelot_multicast_get(ocelot, mdb->addr, vid); if (!mc) { @@ -992,7 +1252,7 @@ static int ocelot_port_obj_del_mdb(struct net_device *dev, u16 vid = mdb->vid; if (!vid) - vid = 1; + vid = port->pvid; mc = ocelot_multicast_get(ocelot, mdb->addr, vid); if (!mc) @@ -1024,6 +1284,11 @@ static int ocelot_port_obj_add(struct net_device *dev, int ret = 0; switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + ret = ocelot_port_obj_add_vlan(dev, + SWITCHDEV_OBJ_PORT_VLAN(obj), + trans); + break; case SWITCHDEV_OBJ_ID_PORT_MDB: ret = ocelot_port_obj_add_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj), trans); @@ -1041,6 +1306,10 @@ static int ocelot_port_obj_del(struct net_device *dev, int ret = 0; switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + ret = ocelot_port_vlan_del_vlan(dev, + SWITCHDEV_OBJ_PORT_VLAN(obj)); + break; case SWITCHDEV_OBJ_ID_PORT_MDB: ret = ocelot_port_obj_del_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj)); break; @@ -1086,6 +1355,142 @@ static void ocelot_port_bridge_leave(struct ocelot_port *ocelot_port, if (!ocelot->bridge_mask) ocelot->hw_bridge_dev = NULL; + + /* Clear bridge vlan settings before calling ocelot_vlan_port_apply */ + ocelot_port->vlan_aware = 0; + ocelot_port->pvid = 0; + ocelot_port->vid = 0; +} + +static void ocelot_set_aggr_pgids(struct ocelot *ocelot) +{ + int i, port, lag; + + /* Reset destination and aggregation PGIDS */ + for (port = 0; port < ocelot->num_phys_ports; port++) + ocelot_write_rix(ocelot, BIT(port), ANA_PGID_PGID, port); + + for (i = PGID_AGGR; i < PGID_SRC; i++) + ocelot_write_rix(ocelot, GENMASK(ocelot->num_phys_ports - 1, 0), + ANA_PGID_PGID, i); + + /* Now, set PGIDs for each LAG */ + for (lag = 0; lag < ocelot->num_phys_ports; lag++) { + unsigned long bond_mask; + int aggr_count = 0; + u8 aggr_idx[16]; + + bond_mask = ocelot->lags[lag]; + if (!bond_mask) + continue; + + for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) { + // Destination mask + ocelot_write_rix(ocelot, bond_mask, + ANA_PGID_PGID, port); + aggr_idx[aggr_count] = port; + aggr_count++; + } + + for (i = PGID_AGGR; i < PGID_SRC; i++) { + u32 ac; + + ac = ocelot_read_rix(ocelot, ANA_PGID_PGID, i); + ac &= ~bond_mask; + ac |= BIT(aggr_idx[i % aggr_count]); + ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i); + } + } +} + +static void ocelot_setup_lag(struct ocelot *ocelot, int lag) +{ + unsigned long bond_mask = ocelot->lags[lag]; + unsigned int p; + + for_each_set_bit(p, &bond_mask, ocelot->num_phys_ports) { + u32 port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p); + + port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M; + + /* Use lag port as logical port for port i */ + ocelot_write_gix(ocelot, port_cfg | + ANA_PORT_PORT_CFG_PORTID_VAL(lag), + ANA_PORT_PORT_CFG, p); + } +} + +static int ocelot_port_lag_join(struct ocelot_port *ocelot_port, + struct net_device *bond) +{ + struct ocelot *ocelot = ocelot_port->ocelot; + int p = ocelot_port->chip_port; + int lag, lp; + struct net_device *ndev; + u32 bond_mask = 0; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(bond, ndev) { + struct ocelot_port *port = netdev_priv(ndev); + + bond_mask |= BIT(port->chip_port); + } + rcu_read_unlock(); + + lp = __ffs(bond_mask); + + /* If the new port is the lowest one, use it as the logical port from + * now on + */ + if (p == lp) { + lag = p; + ocelot->lags[p] = bond_mask; + bond_mask &= ~BIT(p); + if (bond_mask) { + lp = __ffs(bond_mask); + ocelot->lags[lp] = 0; + } + } else { + lag = lp; + ocelot->lags[lp] |= BIT(p); + } + + ocelot_setup_lag(ocelot, lag); + ocelot_set_aggr_pgids(ocelot); + + return 0; +} + +static void ocelot_port_lag_leave(struct ocelot_port *ocelot_port, + struct net_device *bond) +{ + struct ocelot *ocelot = ocelot_port->ocelot; + int p = ocelot_port->chip_port; + u32 port_cfg; + int i; + + /* Remove port from any lag */ + for (i = 0; i < ocelot->num_phys_ports; i++) + ocelot->lags[i] &= ~BIT(ocelot_port->chip_port); + + /* if it was the logical port of the lag, move the lag config to the + * next port + */ + if (ocelot->lags[p]) { + int n = __ffs(ocelot->lags[p]); + + ocelot->lags[n] = ocelot->lags[p]; + ocelot->lags[p] = 0; + + ocelot_setup_lag(ocelot, n); + } + + port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p); + port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M; + ocelot_write_gix(ocelot, port_cfg | ANA_PORT_PORT_CFG_PORTID_VAL(p), + ANA_PORT_PORT_CFG, p); + + ocelot_set_aggr_pgids(ocelot); } /* Checks if the net_device instance given to us originate from our driver. */ @@ -1113,6 +1518,17 @@ static int ocelot_netdevice_port_event(struct net_device *dev, else ocelot_port_bridge_leave(ocelot_port, info->upper_dev); + + ocelot_vlan_port_apply(ocelot_port->ocelot, + ocelot_port); + } + if (netif_is_lag_master(info->upper_dev)) { + if (info->linking) + err = ocelot_port_lag_join(ocelot_port, + info->upper_dev); + else + ocelot_port_lag_leave(ocelot_port, + info->upper_dev); } break; default: @@ -1129,6 +1545,20 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); int ret = 0; + if (event == NETDEV_PRECHANGEUPPER && + netif_is_lag_master(info->upper_dev)) { + struct netdev_lag_upper_info *lag_upper_info = info->upper_info; + struct netlink_ext_ack *extack; + + if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { + extack = netdev_notifier_info_to_extack(&info->info); + NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type"); + + ret = -EINVAL; + goto notify; + } + } + if (netif_is_lag_master(dev)) { struct net_device *slave; struct list_head *iter; @@ -1176,6 +1606,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port, dev->ethtool_ops = &ocelot_ethtool_ops; dev->switchdev_ops = &ocelot_port_switchdev_ops; + dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN); dev->dev_addr[ETH_ALEN - 1] += port; ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid, @@ -1187,6 +1620,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port, goto err_register_netdev; } + /* Basic L2 initialization */ + ocelot_vlan_port_apply(ocelot, ocelot_port); + return 0; err_register_netdev: @@ -1201,6 +1637,11 @@ int ocelot_init(struct ocelot *ocelot) int i, cpu = ocelot->num_phys_ports; char queue_name[32]; + ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports, + sizeof(u32), GFP_KERNEL); + if (!ocelot->lags) + return -ENOMEM; + ocelot->stats = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports * ocelot->num_stats, sizeof(u64), GFP_KERNEL); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 097bd12a10d4..616bec30dfa3 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -493,7 +493,7 @@ struct ocelot { u8 num_cpu_ports; struct ocelot_port **ports; - u16 lags[16]; + u32 *lags; /* Keep track of the vlan port masks */ u32 vlan_mask[VLAN_N_VID]; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 40216d56dddc..4dbf7cba6377 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -209,7 +209,7 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev, case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, nfp_bpf_setup_tc_block_cb, - nn, nn); + nn, nn, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, nfp_bpf_setup_tc_block_cb, diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 4a6d2db75071..e56b815a8dc6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -34,6 +34,7 @@ #include <linux/bitfield.h> #include <net/pkt_cls.h> #include <net/switchdev.h> +#include <net/tc_act/tc_csum.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_pedit.h> @@ -44,6 +45,8 @@ #include "main.h" #include "../nfp_net_repr.h" +#define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS (TUNNEL_CSUM | TUNNEL_KEY) + static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan) { size_t act_size = sizeof(struct nfp_fl_pop_vlan); @@ -235,9 +238,12 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun, size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun); struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action); u32 tmp_set_ip_tun_type_index = 0; + struct flowi4 flow = {}; /* Currently support one pre-tunnel so index is always 0. */ int pretun_idx = 0; + struct rtable *rt; struct net *net; + int err; if (ip_tun->options_len) return -EOPNOTSUPP; @@ -254,7 +260,28 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun, set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index); set_tun->tun_id = ip_tun->key.tun_id; - set_tun->ttl = net->ipv4.sysctl_ip_default_ttl; + + /* Do a route lookup to determine ttl - if fails then use default. + * Note that CONFIG_INET is a requirement of CONFIG_NET_SWITCHDEV so + * must be defined here. + */ + flow.daddr = ip_tun->key.u.ipv4.dst; + flow.flowi4_proto = IPPROTO_UDP; + rt = ip_route_output_key(net, &flow); + err = PTR_ERR_OR_ZERO(rt); + if (!err) { + set_tun->ttl = ip4_dst_hoplimit(&rt->dst); + ip_rt_put(rt); + } else { + set_tun->ttl = net->ipv4.sysctl_ip_default_ttl; + } + + set_tun->tos = ip_tun->key.tos; + + if (!(ip_tun->key.tun_flags & TUNNEL_KEY) || + ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS) + return -EOPNOTSUPP; + set_tun->tun_flags = ip_tun->key.tun_flags; /* Complete pre_tunnel action. */ pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst; @@ -398,8 +425,27 @@ nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off, return 0; } +static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto) +{ + switch (ip_proto) { + case 0: + /* Filter doesn't force proto match, + * both TCP and UDP will be updated if encountered + */ + return TCA_CSUM_UPDATE_FLAG_TCP | TCA_CSUM_UPDATE_FLAG_UDP; + case IPPROTO_TCP: + return TCA_CSUM_UPDATE_FLAG_TCP; + case IPPROTO_UDP: + return TCA_CSUM_UPDATE_FLAG_UDP; + default: + /* All other protocols will be ignored by FW */ + return 0; + } +} + static int -nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) +nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow, + char *nfp_action, int *a_len, u32 *csum_updated) { struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src; struct nfp_fl_set_ip4_addrs set_ip_addr; @@ -409,6 +455,7 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) int idx, nkeys, err; size_t act_size; u32 offset, cmd; + u8 ip_proto = 0; memset(&set_ip6_dst, 0, sizeof(set_ip6_dst)); memset(&set_ip6_src, 0, sizeof(set_ip6_src)); @@ -451,6 +498,15 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) return err; } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *basic; + + basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + flow->key); + ip_proto = basic->ip_proto; + } + if (set_eth.head.len_lw) { act_size = sizeof(set_eth); memcpy(nfp_action, &set_eth, act_size); @@ -459,6 +515,10 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) act_size = sizeof(set_ip_addr); memcpy(nfp_action, &set_ip_addr, act_size); *a_len += act_size; + + /* Hardware will automatically fix IPv4 and TCP/UDP checksum. */ + *csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR | + nfp_fl_csum_l4_to_flag(ip_proto); } else if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) { /* TC compiles set src and dst IPv6 address as a single action, * the hardware requires this to be 2 separate actions. @@ -471,18 +531,30 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst, act_size); *a_len += act_size; + + /* Hardware will automatically fix TCP/UDP checksum. */ + *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto); } else if (set_ip6_dst.head.len_lw) { act_size = sizeof(set_ip6_dst); memcpy(nfp_action, &set_ip6_dst, act_size); *a_len += act_size; + + /* Hardware will automatically fix TCP/UDP checksum. */ + *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto); } else if (set_ip6_src.head.len_lw) { act_size = sizeof(set_ip6_src); memcpy(nfp_action, &set_ip6_src, act_size); *a_len += act_size; + + /* Hardware will automatically fix TCP/UDP checksum. */ + *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto); } else if (set_tport.head.len_lw) { act_size = sizeof(set_tport); memcpy(nfp_action, &set_tport, act_size); *a_len += act_size; + + /* Hardware will automatically fix TCP/UDP checksum. */ + *csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto); } return 0; @@ -493,12 +565,18 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, bool last, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, - int *out_cnt) + int *out_cnt, u32 *csum_updated) { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_output *output; int err, prelag_size; + /* If csum_updated has not been reset by now, it means HW will + * incorrectly update csums when they are not requested. + */ + if (*csum_updated) + return -EOPNOTSUPP; + if (*a_len + sizeof(struct nfp_fl_output) > NFP_FL_MAX_A_SIZ) return -EOPNOTSUPP; @@ -529,10 +607,11 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a, static int nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, + struct tc_cls_flower_offload *flow, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, - int *out_cnt) + int *out_cnt, u32 *csum_updated) { struct nfp_fl_set_ipv4_udp_tun *set_tun; struct nfp_fl_pre_tunnel *pre_tun; @@ -545,14 +624,14 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, } else if (is_tcf_mirred_egress_redirect(a)) { err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev, true, tun_type, tun_out_cnt, - out_cnt); + out_cnt, csum_updated); if (err) return err; } else if (is_tcf_mirred_egress_mirror(a)) { err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev, false, tun_type, tun_out_cnt, - out_cnt); + out_cnt, csum_updated); if (err) return err; @@ -602,8 +681,17 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, /* Tunnel decap is handled by default so accept action. */ return 0; } else if (is_tcf_pedit(a)) { - if (nfp_fl_pedit(a, &nfp_fl->action_data[*a_len], a_len)) + if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len], + a_len, csum_updated)) + return -EOPNOTSUPP; + } else if (is_tcf_csum(a)) { + /* csum action requests recalc of something we have not fixed */ + if (tcf_csum_update_flags(a) & ~*csum_updated) return -EOPNOTSUPP; + /* If we will correctly fix the csum we can remove it from the + * csum update list. Which will later be used to check support. + */ + *csum_updated &= ~tcf_csum_update_flags(a); } else { /* Currently we do not handle any other actions. */ return -EOPNOTSUPP; @@ -620,6 +708,7 @@ int nfp_flower_compile_action(struct nfp_app *app, int act_len, act_cnt, err, tun_out_cnt, out_cnt; enum nfp_flower_tun_type tun_type; const struct tc_action *a; + u32 csum_updated = 0; LIST_HEAD(actions); memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); @@ -632,8 +721,9 @@ int nfp_flower_compile_action(struct nfp_app *app, tcf_exts_to_list(flow->exts, &actions); list_for_each_entry(a, &actions, list) { - err = nfp_flower_loop_action(app, a, nfp_flow, &act_len, netdev, - &tun_type, &tun_out_cnt, &out_cnt); + err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len, + netdev, &tun_type, &tun_out_cnt, + &out_cnt, &csum_updated); if (err) return err; act_cnt++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 4a7f3510a296..15f1eacd76b6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -203,9 +203,9 @@ struct nfp_fl_set_ipv4_udp_tun { __be16 reserved; __be64 tun_id __packed; __be32 tun_type_index; - __be16 reserved2; + __be16 tun_flags; u8 ttl; - u8 reserved3; + u8 tos; __be32 extra[2]; }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c index 0c4c957717ea..bf10598f66ae 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c @@ -564,8 +564,9 @@ nfp_fl_lag_changeupper_event(struct nfp_fl_lag *lag, if (lag_upper_info && lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_ACTIVEBACKUP && (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH || - (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 && - lag_upper_info->hash_type != NETDEV_LAG_HASH_E34))) { + (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 && + lag_upper_info->hash_type != NETDEV_LAG_HASH_E34 && + lag_upper_info->hash_type != NETDEV_LAG_HASH_UNKNOWN))) { can_offload = false; nfp_flower_cmsg_warn(priv->app, "Unable to offload tx_type %u hash %u\n", diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 525057bee0ed..43b9bf12b174 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -584,9 +584,9 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev, return nfp_flower_del_offload(app, netdev, flower, egress); case TC_CLSFLOWER_STATS: return nfp_flower_get_stats(app, netdev, flower, egress); + default: + return -EOPNOTSUPP; } - - return -EOPNOTSUPP; } int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data, @@ -638,7 +638,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, nfp_flower_setup_tc_block_cb, - repr, repr); + repr, repr, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, nfp_flower_setup_tc_block_cb, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index d4c27f849f9b..7df5ca37bfb8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -945,11 +945,12 @@ err_free: /** * nfp_net_tx_complete() - Handled completed TX packets - * @tx_ring: TX ring structure + * @tx_ring: TX ring structure + * @budget: NAPI budget (only used as bool to determine if in NAPI context) * * Return: Number of completed TX descriptors */ -static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) +static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget) { struct nfp_net_r_vector *r_vec = tx_ring->r_vec; struct nfp_net_dp *dp = &r_vec->nfp_net->dp; @@ -999,7 +1000,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) /* check for last gather fragment */ if (fidx == nr_frags - 1) - dev_consume_skb_any(skb); + napi_consume_skb(skb, budget); tx_ring->txbufs[idx].dma_addr = 0; tx_ring->txbufs[idx].skb = NULL; @@ -1828,7 +1829,7 @@ static int nfp_net_poll(struct napi_struct *napi, int budget) unsigned int pkts_polled = 0; if (r_vec->tx_ring) - nfp_net_tx_complete(r_vec->tx_ring); + nfp_net_tx_complete(r_vec->tx_ring, budget); if (r_vec->rx_ring) pkts_polled = nfp_net_rx(r_vec->rx_ring, budget); @@ -2062,7 +2063,7 @@ static void nfp_ctrl_poll(unsigned long arg) struct nfp_net_r_vector *r_vec = (void *)arg; spin_lock_bh(&r_vec->lock); - nfp_net_tx_complete(r_vec->tx_ring); + nfp_net_tx_complete(r_vec->tx_ring, 0); __nfp_ctrl_tx_queued(r_vec); spin_unlock_bh(&r_vec->lock); @@ -3115,6 +3116,21 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL); } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void nfp_net_netpoll(struct net_device *netdev) +{ + struct nfp_net *nn = netdev_priv(netdev); + int i; + + /* nfp_net's NAPIs are statically allocated so even if there is a race + * with reconfig path this will simply try to schedule some disabled + * NAPI instances. + */ + for (i = 0; i < nn->dp.num_stack_tx_rings; i++) + napi_schedule_irqoff(&nn->r_vecs[i].napi); +} +#endif + static void nfp_net_stat64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -3482,6 +3498,9 @@ const struct net_device_ops nfp_net_netdev_ops = { .ndo_get_stats64 = nfp_net_stat64, .ndo_vlan_rx_add_vid = nfp_net_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = nfp_net_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = nfp_net_netpoll, +#endif .ndo_set_vf_mac = nfp_app_set_vf_mac, .ndo_set_vf_vlan = nfp_app_set_vf_vlan, .ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 26d1cc4e2906..6a79c8e4a7a4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -233,12 +233,10 @@ nfp_net_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) static void nfp_app_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { - struct nfp_app *app; - - app = nfp_app_from_netdev(netdev); - if (!app) - return; + struct nfp_app *app = nfp_app_from_netdev(netdev); + strlcpy(drvinfo->bus_info, pci_name(app->pdev), + sizeof(drvinfo->bus_info)); nfp_get_drvinfo(app, app->pdev, "*", drvinfo); } @@ -452,7 +450,7 @@ static unsigned int nfp_vnic_get_sw_stats_count(struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - return NN_RVEC_GATHER_STATS + nn->dp.num_r_vecs * NN_RVEC_PER_Q_STATS; + return NN_RVEC_GATHER_STATS + nn->max_r_vecs * NN_RVEC_PER_Q_STATS; } static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data) @@ -460,7 +458,7 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data) struct nfp_net *nn = netdev_priv(netdev); int i; - for (i = 0; i < nn->dp.num_r_vecs; i++) { + for (i = 0; i < nn->max_r_vecs; i++) { data = nfp_pr_et(data, "rvec_%u_rx_pkts", i); data = nfp_pr_et(data, "rvec_%u_tx_pkts", i); data = nfp_pr_et(data, "rvec_%u_tx_busy", i); @@ -486,7 +484,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) u64 tmp[NN_RVEC_GATHER_STATS]; unsigned int i, j; - for (i = 0; i < nn->dp.num_r_vecs; i++) { + for (i = 0; i < nn->max_r_vecs; i++) { unsigned int start; do { @@ -521,15 +519,13 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) return data; } -static unsigned int -nfp_vnic_get_hw_stats_count(unsigned int rx_rings, unsigned int tx_rings) +static unsigned int nfp_vnic_get_hw_stats_count(unsigned int num_vecs) { - return NN_ET_GLOBAL_STATS_LEN + (rx_rings + tx_rings) * 2; + return NN_ET_GLOBAL_STATS_LEN + num_vecs * 4; } static u8 * -nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings, - unsigned int tx_rings, bool repr) +nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int num_vecs, bool repr) { int swap_off, i; @@ -549,36 +545,29 @@ nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings, for (i = NN_ET_SWITCH_STATS_LEN * 2; i < NN_ET_GLOBAL_STATS_LEN; i++) data = nfp_pr_et(data, nfp_net_et_stats[i].name); - for (i = 0; i < tx_rings; i++) { - data = nfp_pr_et(data, "txq_%u_pkts", i); - data = nfp_pr_et(data, "txq_%u_bytes", i); - } - - for (i = 0; i < rx_rings; i++) { + for (i = 0; i < num_vecs; i++) { data = nfp_pr_et(data, "rxq_%u_pkts", i); data = nfp_pr_et(data, "rxq_%u_bytes", i); + data = nfp_pr_et(data, "txq_%u_pkts", i); + data = nfp_pr_et(data, "txq_%u_bytes", i); } return data; } static u64 * -nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem, - unsigned int rx_rings, unsigned int tx_rings) +nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem, unsigned int num_vecs) { unsigned int i; for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++) *data++ = readq(mem + nfp_net_et_stats[i].off); - for (i = 0; i < tx_rings; i++) { - *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i)); - *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8); - } - - for (i = 0; i < rx_rings; i++) { + for (i = 0; i < num_vecs; i++) { *data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i)); *data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i) + 8); + *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i)); + *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8); } return data; @@ -633,8 +622,7 @@ static void nfp_net_get_strings(struct net_device *netdev, switch (stringset) { case ETH_SS_STATS: data = nfp_vnic_get_sw_stats_strings(netdev, data); - data = nfp_vnic_get_hw_stats_strings(data, nn->dp.num_rx_rings, - nn->dp.num_tx_rings, + data = nfp_vnic_get_hw_stats_strings(data, nn->max_r_vecs, false); data = nfp_mac_get_stats_strings(netdev, data); data = nfp_app_port_get_stats_strings(nn->port, data); @@ -649,8 +637,7 @@ nfp_net_get_stats(struct net_device *netdev, struct ethtool_stats *stats, struct nfp_net *nn = netdev_priv(netdev); data = nfp_vnic_get_sw_stats(netdev, data); - data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar, - nn->dp.num_rx_rings, nn->dp.num_tx_rings); + data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar, nn->max_r_vecs); data = nfp_mac_get_stats(netdev, data); data = nfp_app_port_get_stats(nn->port, data); } @@ -662,8 +649,7 @@ static int nfp_net_get_sset_count(struct net_device *netdev, int sset) switch (sset) { case ETH_SS_STATS: return nfp_vnic_get_sw_stats_count(netdev) + - nfp_vnic_get_hw_stats_count(nn->dp.num_rx_rings, - nn->dp.num_tx_rings) + + nfp_vnic_get_hw_stats_count(nn->max_r_vecs) + nfp_mac_get_stats_count(netdev) + nfp_app_port_get_stats_count(nn->port); default: @@ -679,7 +665,7 @@ static void nfp_port_get_strings(struct net_device *netdev, switch (stringset) { case ETH_SS_STATS: if (nfp_port_is_vnic(port)) - data = nfp_vnic_get_hw_stats_strings(data, 0, 0, true); + data = nfp_vnic_get_hw_stats_strings(data, 0, true); else data = nfp_mac_get_stats_strings(netdev, data); data = nfp_app_port_get_stats_strings(port, data); @@ -694,7 +680,7 @@ nfp_port_get_stats(struct net_device *netdev, struct ethtool_stats *stats, struct nfp_port *port = nfp_port_from_netdev(netdev); if (nfp_port_is_vnic(port)) - data = nfp_vnic_get_hw_stats(data, port->vnic, 0, 0); + data = nfp_vnic_get_hw_stats(data, port->vnic, 0); else data = nfp_mac_get_stats(netdev, data); data = nfp_app_port_get_stats(port, data); @@ -708,7 +694,7 @@ static int nfp_port_get_sset_count(struct net_device *netdev, int sset) switch (sset) { case ETH_SS_STATS: if (nfp_port_is_vnic(port)) - count = nfp_vnic_get_hw_stats_count(0, 0); + count = nfp_vnic_get_hw_stats_count(0); else count = nfp_mac_get_stats_count(netdev); count += nfp_app_port_get_stats_count(port); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index 749655c329b2..c8d0b1016a64 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -1248,7 +1248,7 @@ static void nfp6000_free(struct nfp_cpp *cpp) kfree(nfp); } -static void nfp6000_read_serial(struct device *dev, u8 *serial) +static int nfp6000_read_serial(struct device *dev, u8 *serial) { struct pci_dev *pdev = to_pci_dev(dev); int pos; @@ -1256,25 +1256,29 @@ static void nfp6000_read_serial(struct device *dev, u8 *serial) pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN); if (!pos) { - memset(serial, 0, NFP_SERIAL_LEN); - return; + dev_err(dev, "can't find PCIe Serial Number Capability\n"); + return -EINVAL; } pci_read_config_dword(pdev, pos + 4, ®); put_unaligned_be16(reg >> 16, serial + 4); pci_read_config_dword(pdev, pos + 8, ®); put_unaligned_be32(reg, serial); + + return 0; } -static u16 nfp6000_get_interface(struct device *dev) +static int nfp6000_get_interface(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); int pos; u32 reg; pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN); - if (!pos) - return NFP_CPP_INTERFACE(NFP_CPP_INTERFACE_TYPE_PCI, 0, 0xff); + if (!pos) { + dev_err(dev, "can't find PCIe Serial Number Capability\n"); + return -EINVAL; + } pci_read_config_dword(pdev, pos + 4, ®); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h index b0da3d436850..c338d539fa96 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h @@ -364,8 +364,8 @@ struct nfp_cpp_operations { int (*init)(struct nfp_cpp *cpp); void (*free)(struct nfp_cpp *cpp); - void (*read_serial)(struct device *dev, u8 *serial); - u16 (*get_interface)(struct device *dev); + int (*read_serial)(struct device *dev, u8 *serial); + int (*get_interface)(struct device *dev); int (*area_init)(struct nfp_cpp_area *area, u32 dest, unsigned long long address, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c index ef30597aa319..73de57a09800 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c @@ -1163,10 +1163,10 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops, { const u32 arm = NFP_CPP_ID(NFP_CPP_TARGET_ARM, NFP_CPP_ACTION_RW, 0); struct nfp_cpp *cpp; + int ifc, err; u32 mask[2]; u32 xpbaddr; size_t tgt; - int err; cpp = kzalloc(sizeof(*cpp), GFP_KERNEL); if (!cpp) { @@ -1176,9 +1176,19 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops, cpp->op = ops; cpp->priv = priv; - cpp->interface = ops->get_interface(parent); - if (ops->read_serial) - ops->read_serial(parent, cpp->serial); + + ifc = ops->get_interface(parent); + if (ifc < 0) { + err = ifc; + goto err_free_cpp; + } + cpp->interface = ifc; + if (ops->read_serial) { + err = ops->read_serial(parent, cpp->serial); + if (err) + goto err_free_cpp; + } + rwlock_init(&cpp->resource_lock); init_waitqueue_head(&cpp->waitq); lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key); @@ -1191,7 +1201,7 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops, err = device_register(&cpp->dev); if (err < 0) { put_device(&cpp->dev); - goto err_dev; + goto err_free_cpp; } dev_set_drvdata(&cpp->dev, cpp); @@ -1238,7 +1248,7 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops, err_out: device_unregister(&cpp->dev); -err_dev: +err_free_cpp: kfree(cpp); err_malloc: return ERR_PTR(err); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile index 31288d4ad248..862de0f3bc41 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile +++ b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_PCH_GBE) += pch_gbe.o pch_gbe-y := pch_gbe_phy.o pch_gbe_ethtool.o pch_gbe_param.o -pch_gbe-y += pch_gbe_api.o pch_gbe_main.o +pch_gbe-y += pch_gbe_main.o diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h index 697e29dd4bd3..44c2f291e766 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h @@ -326,32 +326,6 @@ struct pch_gbe_regs { #define PCH_GBE_FC_FULL 3 #define PCH_GBE_FC_DEFAULT PCH_GBE_FC_FULL - -struct pch_gbe_hw; -/** - * struct pch_gbe_functions - HAL APi function pointer - * @get_bus_info: for pch_gbe_hal_get_bus_info - * @init_hw: for pch_gbe_hal_init_hw - * @read_phy_reg: for pch_gbe_hal_read_phy_reg - * @write_phy_reg: for pch_gbe_hal_write_phy_reg - * @reset_phy: for pch_gbe_hal_phy_hw_reset - * @sw_reset_phy: for pch_gbe_hal_phy_sw_reset - * @power_up_phy: for pch_gbe_hal_power_up_phy - * @power_down_phy: for pch_gbe_hal_power_down_phy - * @read_mac_addr: for pch_gbe_hal_read_mac_addr - */ -struct pch_gbe_functions { - void (*get_bus_info) (struct pch_gbe_hw *); - s32 (*init_hw) (struct pch_gbe_hw *); - s32 (*read_phy_reg) (struct pch_gbe_hw *, u32, u16 *); - s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16); - void (*reset_phy) (struct pch_gbe_hw *); - void (*sw_reset_phy) (struct pch_gbe_hw *); - void (*power_up_phy) (struct pch_gbe_hw *hw); - void (*power_down_phy) (struct pch_gbe_hw *hw); - s32 (*read_mac_addr) (struct pch_gbe_hw *); -}; - /** * struct pch_gbe_mac_info - MAC information * @addr[6]: Store the MAC address @@ -394,17 +368,6 @@ struct pch_gbe_phy_info { /*! * @ingroup Gigabit Ether driver Layer - * @struct pch_gbe_bus_info - * @brief Bus information - */ -struct pch_gbe_bus_info { - u8 type; - u8 speed; - u8 width; -}; - -/*! - * @ingroup Gigabit Ether driver Layer * @struct pch_gbe_hw * @brief Hardware information */ @@ -414,10 +377,8 @@ struct pch_gbe_hw { struct pch_gbe_regs __iomem *reg; spinlock_t miim_lock; - const struct pch_gbe_functions *func; struct pch_gbe_mac_info mac; struct pch_gbe_phy_info phy; - struct pch_gbe_bus_info bus; }; /** @@ -680,7 +641,6 @@ void pch_gbe_set_ethtool_ops(struct net_device *netdev); /* pch_gbe_mac.c */ s32 pch_gbe_mac_force_mac_fc(struct pch_gbe_hw *hw); -s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw); u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg, u16 data); #endif /* _PCH_GBE_H_ */ diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c deleted file mode 100644 index 51250363566b..000000000000 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c +++ /dev/null @@ -1,262 +0,0 @@ -/* - * Copyright (C) 1999 - 2010 Intel Corporation. - * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD. - * - * This code was derived from the Intel e1000e Linux driver. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ -#include "pch_gbe.h" -#include "pch_gbe_phy.h" -#include "pch_gbe_api.h" - -/* bus type values */ -#define pch_gbe_bus_type_unknown 0 -#define pch_gbe_bus_type_pci 1 -#define pch_gbe_bus_type_pcix 2 -#define pch_gbe_bus_type_pci_express 3 -#define pch_gbe_bus_type_reserved 4 - -/* bus speed values */ -#define pch_gbe_bus_speed_unknown 0 -#define pch_gbe_bus_speed_33 1 -#define pch_gbe_bus_speed_66 2 -#define pch_gbe_bus_speed_100 3 -#define pch_gbe_bus_speed_120 4 -#define pch_gbe_bus_speed_133 5 -#define pch_gbe_bus_speed_2500 6 -#define pch_gbe_bus_speed_reserved 7 - -/* bus width values */ -#define pch_gbe_bus_width_unknown 0 -#define pch_gbe_bus_width_pcie_x1 1 -#define pch_gbe_bus_width_pcie_x2 2 -#define pch_gbe_bus_width_pcie_x4 4 -#define pch_gbe_bus_width_32 5 -#define pch_gbe_bus_width_64 6 -#define pch_gbe_bus_width_reserved 7 - -/** - * pch_gbe_plat_get_bus_info - Obtain bus information for adapter - * @hw: Pointer to the HW structure - */ -static void pch_gbe_plat_get_bus_info(struct pch_gbe_hw *hw) -{ - hw->bus.type = pch_gbe_bus_type_pci_express; - hw->bus.speed = pch_gbe_bus_speed_2500; - hw->bus.width = pch_gbe_bus_width_pcie_x1; -} - -/** - * pch_gbe_plat_init_hw - Initialize hardware - * @hw: Pointer to the HW structure - * Returns: - * 0: Successfully - * Negative value: Failed-EBUSY - */ -static s32 pch_gbe_plat_init_hw(struct pch_gbe_hw *hw) -{ - s32 ret_val; - - ret_val = pch_gbe_phy_get_id(hw); - if (ret_val) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n"); - return ret_val; - } - pch_gbe_phy_init_setting(hw); - /* Setup Mac interface option RGMII */ -#ifdef PCH_GBE_MAC_IFOP_RGMII - pch_gbe_phy_set_rgmii(hw); -#endif - return ret_val; -} - -static const struct pch_gbe_functions pch_gbe_ops = { - .get_bus_info = pch_gbe_plat_get_bus_info, - .init_hw = pch_gbe_plat_init_hw, - .read_phy_reg = pch_gbe_phy_read_reg_miic, - .write_phy_reg = pch_gbe_phy_write_reg_miic, - .reset_phy = pch_gbe_phy_hw_reset, - .sw_reset_phy = pch_gbe_phy_sw_reset, - .power_up_phy = pch_gbe_phy_power_up, - .power_down_phy = pch_gbe_phy_power_down, - .read_mac_addr = pch_gbe_mac_read_mac_addr -}; - -/** - * pch_gbe_plat_init_function_pointers - Init func ptrs - * @hw: Pointer to the HW structure - */ -static void pch_gbe_plat_init_function_pointers(struct pch_gbe_hw *hw) -{ - /* Set PHY parameter */ - hw->phy.reset_delay_us = PCH_GBE_PHY_RESET_DELAY_US; - /* Set function pointers */ - hw->func = &pch_gbe_ops; -} - -/** - * pch_gbe_hal_setup_init_funcs - Initializes function pointers - * @hw: Pointer to the HW structure - * Returns: - * 0: Successfully - * ENOSYS: Function is not registered - */ -s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw) -{ - if (!hw->reg) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "ERROR: Registers not mapped\n"); - return -ENOSYS; - } - pch_gbe_plat_init_function_pointers(hw); - return 0; -} - -/** - * pch_gbe_hal_get_bus_info - Obtain bus information for adapter - * @hw: Pointer to the HW structure - */ -void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw) -{ - if (!hw->func->get_bus_info) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "ERROR: configuration\n"); - return; - } - hw->func->get_bus_info(hw); -} - -/** - * pch_gbe_hal_init_hw - Initialize hardware - * @hw: Pointer to the HW structure - * Returns: - * 0: Successfully - * ENOSYS: Function is not registered - */ -s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw) -{ - if (!hw->func->init_hw) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "ERROR: configuration\n"); - return -ENOSYS; - } - return hw->func->init_hw(hw); -} - -/** - * pch_gbe_hal_read_phy_reg - Reads PHY register - * @hw: Pointer to the HW structure - * @offset: The register to read - * @data: The buffer to store the 16-bit read. - * Returns: - * 0: Successfully - * Negative value: Failed - */ -s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, - u16 *data) -{ - if (!hw->func->read_phy_reg) - return 0; - return hw->func->read_phy_reg(hw, offset, data); -} - -/** - * pch_gbe_hal_write_phy_reg - Writes PHY register - * @hw: Pointer to the HW structure - * @offset: The register to read - * @data: The value to write. - * Returns: - * 0: Successfully - * Negative value: Failed - */ -s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, - u16 data) -{ - if (!hw->func->write_phy_reg) - return 0; - return hw->func->write_phy_reg(hw, offset, data); -} - -/** - * pch_gbe_hal_phy_hw_reset - Hard PHY reset - * @hw: Pointer to the HW structure - */ -void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw) -{ - if (!hw->func->reset_phy) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "ERROR: configuration\n"); - return; - } - hw->func->reset_phy(hw); -} - -/** - * pch_gbe_hal_phy_sw_reset - Soft PHY reset - * @hw: Pointer to the HW structure - */ -void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw) -{ - if (!hw->func->sw_reset_phy) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "ERROR: configuration\n"); - return; - } - hw->func->sw_reset_phy(hw); -} - -/** - * pch_gbe_hal_read_mac_addr - Reads MAC address - * @hw: Pointer to the HW structure - * Returns: - * 0: Successfully - * ENOSYS: Function is not registered - */ -s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw) -{ - if (!hw->func->read_mac_addr) { - struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - - netdev_err(adapter->netdev, "ERROR: configuration\n"); - return -ENOSYS; - } - return hw->func->read_mac_addr(hw); -} - -/** - * pch_gbe_hal_power_up_phy - Power up PHY - * @hw: Pointer to the HW structure - */ -void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw) -{ - if (hw->func->power_up_phy) - hw->func->power_up_phy(hw); -} - -/** - * pch_gbe_hal_power_down_phy - Power down PHY - * @hw: Pointer to the HW structure - */ -void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw) -{ - if (hw->func->power_down_phy) - hw->func->power_down_phy(hw); -} diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h deleted file mode 100644 index 91ce07c8306c..000000000000 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Copyright (C) 1999 - 2010 Intel Corporation. - * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD. - * - * This code was derived from the Intel e1000e Linux driver. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ -#ifndef _PCH_GBE_API_H_ -#define _PCH_GBE_API_H_ - -#include "pch_gbe_phy.h" - -s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw); -void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw); -s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw); -s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data); -s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data); -void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw); -void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw); -s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw); -void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw); -void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw); - -#endif diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index 731ce1e419e4..adaa0024adfe 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -17,7 +17,7 @@ * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "pch_gbe.h" -#include "pch_gbe_api.h" +#include "pch_gbe_phy.h" /** * pch_gbe_stats - Stats item information @@ -125,7 +125,7 @@ static int pch_gbe_set_link_ksettings(struct net_device *netdev, u32 advertising; int ret; - pch_gbe_hal_write_phy_reg(hw, MII_BMCR, BMCR_RESET); + pch_gbe_phy_write_reg_miic(hw, MII_BMCR, BMCR_RESET); memcpy(©_ecmd, ecmd, sizeof(*ecmd)); @@ -204,7 +204,7 @@ static void pch_gbe_get_regs(struct net_device *netdev, *regs_buff++ = ioread32(&hw->reg->INT_ST + i); /* PHY register */ for (i = 0; i < PCH_GBE_PHY_REGS_LEN; i++) { - pch_gbe_hal_read_phy_reg(&adapter->hw, i, &tmp); + pch_gbe_phy_read_reg_miic(&adapter->hw, i, &tmp); *regs_buff++ = tmp; } } @@ -349,25 +349,12 @@ static int pch_gbe_set_ringparam(struct net_device *netdev, err = pch_gbe_setup_tx_resources(adapter, adapter->tx_ring); if (err) goto err_setup_tx; - /* save the new, restore the old in order to free it, - * then restore the new back again */ -#ifdef RINGFREE - adapter->rx_ring = rx_old; - adapter->tx_ring = tx_old; - pch_gbe_free_rx_resources(adapter, adapter->rx_ring); - pch_gbe_free_tx_resources(adapter, adapter->tx_ring); - kfree(tx_old); - kfree(rx_old); - adapter->rx_ring = rxdr; - adapter->tx_ring = txdr; -#else pch_gbe_free_rx_resources(adapter, rx_old); pch_gbe_free_tx_resources(adapter, tx_old); kfree(tx_old); kfree(rx_old); adapter->rx_ring = rxdr; adapter->tx_ring = txdr; -#endif err = pch_gbe_up(adapter); } return err; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 34a1581eda95..43c0c10dfeb7 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -18,7 +18,7 @@ */ #include "pch_gbe.h" -#include "pch_gbe_api.h" +#include "pch_gbe_phy.h" #include <linux/module.h> #include <linux/net_tstamp.h> #include <linux/ptp_classify.h> @@ -34,7 +34,6 @@ const char pch_driver_version[] = DRV_VERSION; #define PCH_GBE_DMA_ALIGN 0 #define PCH_GBE_DMA_PADDING 2 #define PCH_GBE_WATCHDOG_PERIOD (5 * HZ) /* watchdog time */ -#define PCH_GBE_COPYBREAK_DEFAULT 256 #define PCH_GBE_PCI_BAR 1 #define PCH_GBE_RESERVE_MEMORY 0x200000 /* 2MB */ @@ -113,8 +112,6 @@ const char pch_driver_version[] = DRV_VERSION; #define MINNOW_PHY_RESET_GPIO 13 -static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT; - static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg); static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg, int data); @@ -290,7 +287,7 @@ static inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw) * Returns: * 0: Successful. */ -s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw) +static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw) { struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); u32 adr1a, adr1b; @@ -369,9 +366,7 @@ static void pch_gbe_mac_reset_hw(struct pch_gbe_hw *hw) /* Read the MAC address. and store to the private data */ pch_gbe_mac_read_mac_addr(hw); iowrite32(PCH_GBE_ALL_RST, &hw->reg->RESET); -#ifdef PCH_GBE_MAC_IFOP_RGMII iowrite32(PCH_GBE_MODE_GMII_ETHER, &hw->reg->MODE); -#endif pch_gbe_wait_clr_bit(&hw->reg->RESET, PCH_GBE_ALL_RST); /* Setup the receive addresses */ pch_gbe_mac_mar_set(hw, hw->mac.addr, 0); @@ -416,44 +411,6 @@ static void pch_gbe_mac_init_rx_addrs(struct pch_gbe_hw *hw, u16 mar_count) pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY); } - -/** - * pch_gbe_mac_mc_addr_list_update - Update Multicast addresses - * @hw: Pointer to the HW structure - * @mc_addr_list: Array of multicast addresses to program - * @mc_addr_count: Number of multicast addresses to program - * @mar_used_count: The first MAC Address register free to program - * @mar_total_num: Total number of supported MAC Address Registers - */ -static void pch_gbe_mac_mc_addr_list_update(struct pch_gbe_hw *hw, - u8 *mc_addr_list, u32 mc_addr_count, - u32 mar_used_count, u32 mar_total_num) -{ - u32 i, adrmask; - - /* Load the first set of multicast addresses into the exact - * filters (RAR). If there are not enough to fill the RAR - * array, clear the filters. - */ - for (i = mar_used_count; i < mar_total_num; i++) { - if (mc_addr_count) { - pch_gbe_mac_mar_set(hw, mc_addr_list, i); - mc_addr_count--; - mc_addr_list += ETH_ALEN; - } else { - /* Clear MAC address mask */ - adrmask = ioread32(&hw->reg->ADDR_MASK); - iowrite32((adrmask | (0x0001 << i)), - &hw->reg->ADDR_MASK); - /* wait busy */ - pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY); - /* Clear MAC address */ - iowrite32(0, &hw->reg->mac_adr[i].high); - iowrite32(0, &hw->reg->mac_adr[i].low); - } - } -} - /** * pch_gbe_mac_force_mac_fc - Force the MAC's flow control settings * @hw: Pointer to the HW structure @@ -763,14 +720,23 @@ void pch_gbe_reinit_locked(struct pch_gbe_adapter *adapter) void pch_gbe_reset(struct pch_gbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; + struct pch_gbe_hw *hw = &adapter->hw; + s32 ret_val; - pch_gbe_mac_reset_hw(&adapter->hw); + pch_gbe_mac_reset_hw(hw); /* reprogram multicast address register after reset */ pch_gbe_set_multi(netdev); /* Setup the receive address. */ - pch_gbe_mac_init_rx_addrs(&adapter->hw, PCH_GBE_MAR_ENTRIES); - if (pch_gbe_hal_init_hw(&adapter->hw)) - netdev_err(netdev, "Hardware Error\n"); + pch_gbe_mac_init_rx_addrs(hw, PCH_GBE_MAR_ENTRIES); + + ret_val = pch_gbe_phy_get_id(hw); + if (ret_val) { + netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n"); + return; + } + pch_gbe_phy_init_setting(hw); + /* Setup Mac interface option RGMII */ + pch_gbe_phy_set_rgmii(hw); } /** @@ -1036,7 +1002,6 @@ static void pch_gbe_set_rgmii_ctrl(struct pch_gbe_adapter *adapter, u16 speed, unsigned long rgmii = 0; /* Set the RGMII control. */ -#ifdef PCH_GBE_MAC_IFOP_RGMII switch (speed) { case SPEED_10: rgmii = (PCH_GBE_RGMII_RATE_2_5M | @@ -1052,10 +1017,6 @@ static void pch_gbe_set_rgmii_ctrl(struct pch_gbe_adapter *adapter, u16 speed, break; } iowrite32(rgmii, &hw->reg->RGMII_CTRL); -#else /* GMII */ - rgmii = 0; - iowrite32(rgmii, &hw->reg->RGMII_CTRL); -#endif } static void pch_gbe_set_mode(struct pch_gbe_adapter *adapter, u16 speed, u16 duplex) @@ -2029,12 +1990,8 @@ static int pch_gbe_sw_init(struct pch_gbe_adapter *adapter) adapter->rx_buffer_len = PCH_GBE_FRAME_SIZE_2048; hw->mac.max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; hw->mac.min_frame_size = ETH_ZLEN + ETH_FCS_LEN; + hw->phy.reset_delay_us = PCH_GBE_PHY_RESET_DELAY_US; - /* Initialize the hardware-specific values */ - if (pch_gbe_hal_setup_init_funcs(hw)) { - netdev_err(netdev, "Hardware Initialization Failure\n"); - return -EIO; - } if (pch_gbe_alloc_queues(adapter)) { netdev_err(netdev, "Unable to allocate memory for queues\n"); return -ENOMEM; @@ -2075,7 +2032,7 @@ static int pch_gbe_open(struct net_device *netdev) err = pch_gbe_setup_rx_resources(adapter, adapter->rx_ring); if (err) goto err_setup_rx; - pch_gbe_hal_power_up_phy(hw); + pch_gbe_phy_power_up(hw); err = pch_gbe_up(adapter); if (err) goto err_up; @@ -2084,7 +2041,7 @@ static int pch_gbe_open(struct net_device *netdev) err_up: if (!adapter->wake_up_evt) - pch_gbe_hal_power_down_phy(hw); + pch_gbe_phy_power_down(hw); pch_gbe_free_rx_resources(adapter, adapter->rx_ring); err_setup_rx: pch_gbe_free_tx_resources(adapter, adapter->tx_ring); @@ -2107,7 +2064,7 @@ static int pch_gbe_stop(struct net_device *netdev) pch_gbe_down(adapter); if (!adapter->wake_up_evt) - pch_gbe_hal_power_down_phy(hw); + pch_gbe_phy_power_down(hw); pch_gbe_free_tx_resources(adapter, adapter->tx_ring); pch_gbe_free_rx_resources(adapter, adapter->rx_ring); return 0; @@ -2148,50 +2105,52 @@ static void pch_gbe_set_multi(struct net_device *netdev) struct pch_gbe_adapter *adapter = netdev_priv(netdev); struct pch_gbe_hw *hw = &adapter->hw; struct netdev_hw_addr *ha; - u8 *mta_list; - u32 rctl; - int i; - int mc_count; + u32 rctl, adrmask; + int mc_count, i; netdev_dbg(netdev, "netdev->flags : 0x%08x\n", netdev->flags); - /* Check for Promiscuous and All Multicast modes */ + /* By default enable address & multicast filtering */ rctl = ioread32(&hw->reg->RX_MODE); + rctl |= PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN; + + /* Promiscuous mode disables all hardware address filtering */ + if (netdev->flags & IFF_PROMISC) + rctl &= ~(PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN); + + /* If we want to monitor more multicast addresses than the hardware can + * support then disable hardware multicast filtering. + */ mc_count = netdev_mc_count(netdev); - if ((netdev->flags & IFF_PROMISC)) { - rctl &= ~PCH_GBE_ADD_FIL_EN; - rctl &= ~PCH_GBE_MLT_FIL_EN; - } else if ((netdev->flags & IFF_ALLMULTI)) { - /* all the multicasting receive permissions */ - rctl |= PCH_GBE_ADD_FIL_EN; + if ((netdev->flags & IFF_ALLMULTI) || mc_count >= PCH_GBE_MAR_ENTRIES) rctl &= ~PCH_GBE_MLT_FIL_EN; - } else { - if (mc_count >= PCH_GBE_MAR_ENTRIES) { - /* all the multicasting receive permissions */ - rctl |= PCH_GBE_ADD_FIL_EN; - rctl &= ~PCH_GBE_MLT_FIL_EN; - } else { - rctl |= (PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN); - } - } + iowrite32(rctl, &hw->reg->RX_MODE); - if (mc_count >= PCH_GBE_MAR_ENTRIES) - return; - mta_list = kmalloc_array(ETH_ALEN, mc_count, GFP_ATOMIC); - if (!mta_list) + /* If we're not using multicast filtering then there's no point + * configuring the unused MAC address registers. + */ + if (!(rctl & PCH_GBE_MLT_FIL_EN)) return; - /* The shared function expects a packed array of only addresses. */ - i = 0; - netdev_for_each_mc_addr(ha, netdev) { - if (i == mc_count) - break; - memcpy(mta_list + (i++ * ETH_ALEN), &ha->addr, ETH_ALEN); + /* Load the first set of multicast addresses into MAC address registers + * for use by hardware filtering. + */ + i = 1; + netdev_for_each_mc_addr(ha, netdev) + pch_gbe_mac_mar_set(hw, ha->addr, i++); + + /* If there are spare MAC registers, mask & clear them */ + for (; i < PCH_GBE_MAR_ENTRIES; i++) { + /* Clear MAC address mask */ + adrmask = ioread32(&hw->reg->ADDR_MASK); + iowrite32(adrmask | BIT(i), &hw->reg->ADDR_MASK); + /* wait busy */ + pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY); + /* Clear MAC address */ + iowrite32(0, &hw->reg->mac_adr[i].high); + iowrite32(0, &hw->reg->mac_adr[i].low); } - pch_gbe_mac_mc_addr_list_update(hw, mta_list, i, 1, - PCH_GBE_MAR_ENTRIES); - kfree(mta_list); netdev_dbg(netdev, "RX_MODE reg(check bit31,30 ADD,MLT) : 0x%08x netdev->mc_count : 0x%08x\n", @@ -2437,7 +2396,7 @@ static pci_ers_result_t pch_gbe_io_slot_reset(struct pci_dev *pdev) } pci_set_master(pdev); pci_enable_wake(pdev, PCI_D0, 0); - pch_gbe_hal_power_up_phy(hw); + pch_gbe_phy_power_up(hw); pch_gbe_reset(adapter); /* Clear wake up status */ pch_gbe_mac_set_wol_event(hw, 0); @@ -2482,7 +2441,7 @@ static int __pch_gbe_suspend(struct pci_dev *pdev) pch_gbe_mac_set_wol_event(hw, wufc); pci_disable_device(pdev); } else { - pch_gbe_hal_power_down_phy(hw); + pch_gbe_phy_power_down(hw); pch_gbe_mac_set_wol_event(hw, wufc); pci_disable_device(pdev); } @@ -2511,7 +2470,7 @@ static int pch_gbe_resume(struct device *device) return err; } pci_set_master(pdev); - pch_gbe_hal_power_up_phy(hw); + pch_gbe_phy_power_up(hw); pch_gbe_reset(adapter); /* Clear wake on lan control and status */ pch_gbe_mac_set_wol_event(hw, 0); @@ -2541,7 +2500,7 @@ static void pch_gbe_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->reset_task); unregister_netdev(netdev); - pch_gbe_hal_phy_hw_reset(&adapter->hw); + pch_gbe_phy_hw_reset(&adapter->hw); free_netdev(netdev); } @@ -2627,10 +2586,9 @@ static int pch_gbe_probe(struct pci_dev *pdev, dev_err(&pdev->dev, "PHY initialize error\n"); goto err_free_adapter; } - pch_gbe_hal_get_bus_info(&adapter->hw); /* Read the MAC address. and store to the private data */ - ret = pch_gbe_hal_read_mac_addr(&adapter->hw); + ret = pch_gbe_mac_read_mac_addr(&adapter->hw); if (ret) { dev_err(&pdev->dev, "MAC address Read Error\n"); goto err_free_adapter; @@ -2677,7 +2635,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, return 0; err_free_adapter: - pch_gbe_hal_phy_hw_reset(&adapter->hw); + pch_gbe_phy_hw_reset(&adapter->hw); err_free_netdev: free_netdev(netdev); return ret; @@ -2776,32 +2734,7 @@ static struct pci_driver pch_gbe_driver = { .shutdown = pch_gbe_shutdown, .err_handler = &pch_gbe_err_handler }; - - -static int __init pch_gbe_init_module(void) -{ - int ret; - - pr_info("EG20T PCH Gigabit Ethernet Driver - version %s\n",DRV_VERSION); - ret = pci_register_driver(&pch_gbe_driver); - if (copybreak != PCH_GBE_COPYBREAK_DEFAULT) { - if (copybreak == 0) { - pr_info("copybreak disabled\n"); - } else { - pr_info("copybreak enabled for packets <= %u bytes\n", - copybreak); - } - } - return ret; -} - -static void __exit pch_gbe_exit_module(void) -{ - pci_unregister_driver(&pch_gbe_driver); -} - -module_init(pch_gbe_init_module); -module_exit(pch_gbe_exit_module); +module_pci_driver(pch_gbe_driver); MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver"); MODULE_AUTHOR("LAPIS SEMICONDUCTOR, <tshimizu818@gmail.com>"); @@ -2809,8 +2742,4 @@ MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id); -module_param(copybreak, uint, 0644); -MODULE_PARM_DESC(copybreak, - "Maximum size of packet that is copied to a new buffer on receive"); - /* pch_gbe_main.c */ diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c index a5cad5ea9436..6b35b573beef 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c @@ -184,7 +184,7 @@ s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data) * pch_gbe_phy_sw_reset - PHY software reset * @hw: Pointer to the HW structure */ -void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw) +static void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw) { u16 phy_ctrl; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h index 95ad0151ad02..23ac38711619 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h @@ -21,12 +21,10 @@ #define PCH_GBE_PHY_REGS_LEN 32 #define PCH_GBE_PHY_RESET_DELAY_US 10 -#define PCH_GBE_MAC_IFOP_RGMII s32 pch_gbe_phy_get_id(struct pch_gbe_hw *hw); s32 pch_gbe_phy_read_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 *data); s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data); -void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw); void pch_gbe_phy_hw_reset(struct pch_gbe_hw *hw); void pch_gbe_phy_power_up(struct pch_gbe_hw *hw); void pch_gbe_phy_power_down(struct pch_gbe_hw *hw); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 0c744b9c6e0a..77e386ebff09 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -212,7 +212,7 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs) vp->max_tx_bw = MAX_BW; vp->min_tx_bw = MIN_BW; vp->spoofchk = false; - random_ether_addr(vp->mac); + eth_random_addr(vp->mac); dev_info(&adapter->pdev->dev, "MAC Address %pM is configured for VF %d\n", vp->mac, i); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index b9a7548ec6a0..0afc3d335d56 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -210,7 +210,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev) rmnet_dev->netdev_ops = &rmnet_vnd_ops; rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE; rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM; - random_ether_addr(rmnet_dev->dev_addr); + eth_random_addr(rmnet_dev->dev_addr); rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN; /* Raw IP mode */ diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index f4cae2be0fda..f80ac894ef92 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -25,7 +25,6 @@ #include <linux/dma-mapping.h> #include <linux/pm_runtime.h> #include <linux/firmware.h> -#include <linux/pci-aspm.h> #include <linux/prefetch.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> @@ -35,7 +34,6 @@ #define RTL8169_VERSION "2.3LK-NAPI" #define MODULENAME "r8169" -#define PFX MODULENAME ": " #define FIRMWARE_8168D_1 "rtl_nic/rtl8168d-1.fw" #define FIRMWARE_8168D_2 "rtl_nic/rtl8168d-2.fw" @@ -57,19 +55,6 @@ #define FIRMWARE_8107E_1 "rtl_nic/rtl8107e-1.fw" #define FIRMWARE_8107E_2 "rtl_nic/rtl8107e-2.fw" -#ifdef RTL8169_DEBUG -#define assert(expr) \ - if (!(expr)) { \ - printk( "Assertion failed! %s,%s,%s,line=%d\n", \ - #expr,__FILE__,__func__,__LINE__); \ - } -#define dprintk(fmt, args...) \ - do { printk(KERN_DEBUG PFX fmt, ## args); } while (0) -#else -#define assert(expr) do {} while (0) -#define dprintk(fmt, args...) do {} while (0) -#endif /* RTL8169_DEBUG */ - #define R8169_MSG_DEFAULT \ (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN) @@ -95,7 +80,6 @@ static const int multicast_filter_limit = 32; #define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc)) #define RTL8169_TX_TIMEOUT (6*HZ) -#define RTL8169_PHY_TIMEOUT (10*HZ) /* write/read MMIO register */ #define RTL_W8(tp, reg, val8) writeb((val8), tp->mmio_addr + (reg)) @@ -399,12 +383,6 @@ enum rtl_registers { FuncForceEvent = 0xfc, }; -enum rtl8110_registers { - TBICSR = 0x64, - TBI_ANAR = 0x68, - TBI_LPAR = 0x6a, -}; - enum rtl8168_8101_registers { CSIDR = 0x64, CSIAR = 0x68, @@ -571,14 +549,6 @@ enum rtl_register_content { PMEStatus = (1 << 0), /* PME status can be reset by PCI RST# */ ASPM_en = (1 << 0), /* ASPM enable */ - /* TBICSR p.28 */ - TBIReset = 0x80000000, - TBILoopback = 0x40000000, - TBINwEnable = 0x20000000, - TBINwRestart = 0x10000000, - TBILinkOk = 0x02000000, - TBINwComplete = 0x01000000, - /* CPlusCmd p.31 */ EnableBist = (1 << 15), // 8168 8101 Mac_dbgo_oe = (1 << 14), // 8168 8101 @@ -732,7 +702,6 @@ enum rtl_flag { RTL_FLAG_TASK_ENABLED, RTL_FLAG_TASK_SLOW_PENDING, RTL_FLAG_TASK_RESET_PENDING, - RTL_FLAG_TASK_PHY_PENDING, RTL_FLAG_MAX }; @@ -760,7 +729,6 @@ struct rtl8169_private { dma_addr_t RxPhyAddr; void *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ struct ring_info tx_skb[NUM_TX_DESC]; /* Tx data buffers */ - struct timer_list timer; u16 cp_cmd; u16 event_slow; @@ -776,14 +744,7 @@ struct rtl8169_private { void (*disable)(struct rtl8169_private *); } jumbo_ops; - int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv); - int (*get_link_ksettings)(struct net_device *, - struct ethtool_link_ksettings *); - void (*phy_reset_enable)(struct rtl8169_private *tp); void (*hw_start)(struct rtl8169_private *tp); - unsigned int (*phy_reset_pending)(struct rtl8169_private *tp); - unsigned int (*link_ok)(struct rtl8169_private *tp); - int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd); bool (*tso_csum)(struct rtl8169_private *, struct sk_buff *, u32 *); struct { @@ -1478,31 +1439,16 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp) RTL_R8(tp, ChipCmd); } -static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp) -{ - return RTL_R32(tp, TBICSR) & TBIReset; -} - static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp) { return rtl_readphy(tp, MII_BMCR) & BMCR_RESET; } -static unsigned int rtl8169_tbi_link_ok(struct rtl8169_private *tp) -{ - return RTL_R32(tp, TBICSR) & TBILinkOk; -} - static unsigned int rtl8169_xmii_link_ok(struct rtl8169_private *tp) { return RTL_R8(tp, PHYstatus) & LinkStatus; } -static void rtl8169_tbi_reset_enable(struct rtl8169_private *tp) -{ - RTL_W32(tp, TBICSR, RTL_R32(tp, TBICSR) | TBIReset); -} - static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp) { unsigned int val; @@ -1572,7 +1518,7 @@ static void rtl8169_check_link_status(struct net_device *dev, { struct device *d = tp_to_dev(tp); - if (tp->link_ok(tp)) { + if (rtl8169_xmii_link_ok(tp)) { rtl_link_chg_patch(tp); /* This is to cancel a scheduled suspend if there's one. */ pm_request_resume(d); @@ -1588,6 +1534,12 @@ static void rtl8169_check_link_status(struct net_device *dev, #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST) +/* Currently we only enable WoL if explicitly told by userspace to circumvent + * issues on certain platforms, see commit bde135a672bf ("r8169: only enable + * PCI wakeups when WOL is active"). Let's keep __rtl8169_get_wol() for the + * case that we want to respect BIOS settings again. + */ +#if 0 static u32 __rtl8169_get_wol(struct rtl8169_private *tp) { u8 options; @@ -1622,25 +1574,16 @@ static u32 __rtl8169_get_wol(struct rtl8169_private *tp) return wolopts; } +#endif static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct rtl8169_private *tp = netdev_priv(dev); - struct device *d = tp_to_dev(tp); - - pm_runtime_get_noresume(d); rtl_lock_work(tp); - wol->supported = WAKE_ANY; - if (pm_runtime_active(d)) - wol->wolopts = __rtl8169_get_wol(tp); - else - wol->wolopts = tp->saved_wolopts; - + wol->wolopts = tp->saved_wolopts; rtl_unlock_work(tp); - - pm_runtime_put_noidle(d); } static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) @@ -1716,18 +1659,21 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct rtl8169_private *tp = netdev_priv(dev); struct device *d = tp_to_dev(tp); + if (wol->wolopts & ~WAKE_ANY) + return -EINVAL; + pm_runtime_get_noresume(d); rtl_lock_work(tp); + tp->saved_wolopts = wol->wolopts; + if (pm_runtime_active(d)) - __rtl8169_set_wol(tp, wol->wolopts); - else - tp->saved_wolopts = wol->wolopts; + __rtl8169_set_wol(tp, tp->saved_wolopts); rtl_unlock_work(tp); - device_set_wakeup_enable(d, wol->wolopts); + device_set_wakeup_enable(d, tp->saved_wolopts); pm_runtime_put_noidle(d); @@ -1759,28 +1705,6 @@ static int rtl8169_get_regs_len(struct net_device *dev) return R8169_REGS_SIZE; } -static int rtl8169_set_speed_tbi(struct net_device *dev, - u8 autoneg, u16 speed, u8 duplex, u32 ignored) -{ - struct rtl8169_private *tp = netdev_priv(dev); - int ret = 0; - u32 reg; - - reg = RTL_R32(tp, TBICSR); - if ((autoneg == AUTONEG_DISABLE) && (speed == SPEED_1000) && - (duplex == DUPLEX_FULL)) { - RTL_W32(tp, TBICSR, reg & ~(TBINwEnable | TBINwRestart)); - } else if (autoneg == AUTONEG_ENABLE) - RTL_W32(tp, TBICSR, reg | TBINwEnable | TBINwRestart); - else { - netif_warn(tp, link, dev, - "incorrect speed setting refused in TBI mode\n"); - ret = -EOPNOTSUPP; - } - - return ret; -} - static int rtl8169_set_speed_xmii(struct net_device *dev, u8 autoneg, u16 speed, u8 duplex, u32 adv) { @@ -1861,20 +1785,7 @@ out: static int rtl8169_set_speed(struct net_device *dev, u8 autoneg, u16 speed, u8 duplex, u32 advertising) { - struct rtl8169_private *tp = netdev_priv(dev); - int ret; - - ret = tp->set_speed(dev, autoneg, speed, duplex, advertising); - if (ret < 0) - goto out; - - if (netif_running(dev) && (autoneg == AUTONEG_ENABLE) && - (advertising & ADVERTISED_1000baseT_Full) && - !pci_is_pcie(tp->pci_dev)) { - mod_timer(&tp->timer, jiffies + RTL8169_PHY_TIMEOUT); - } -out: - return ret; + return rtl8169_set_speed_xmii(dev, autoneg, speed, duplex, advertising); } static netdev_features_t rtl8169_fix_features(struct net_device *dev, @@ -1940,53 +1851,14 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff)); } -static int rtl8169_get_link_ksettings_tbi(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct rtl8169_private *tp = netdev_priv(dev); - u32 status; - u32 supported, advertising; - - supported = - SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE; - cmd->base.port = PORT_FIBRE; - - status = RTL_R32(tp, TBICSR); - advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0; - cmd->base.autoneg = !!(status & TBINwEnable); - - cmd->base.speed = SPEED_1000; - cmd->base.duplex = DUPLEX_FULL; /* Always set */ - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); - - return 0; -} - -static int rtl8169_get_link_ksettings_xmii(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct rtl8169_private *tp = netdev_priv(dev); - - mii_ethtool_get_link_ksettings(&tp->mii, cmd); - - return 0; -} - static int rtl8169_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); - int rc; - rtl_lock_work(tp); - rc = tp->get_link_ksettings(dev, cmd); - rtl_unlock_work(tp); + mii_ethtool_get_link_ksettings(&tp->mii, cmd); - return rc; + return 0; } static int rtl8169_set_link_ksettings(struct net_device *dev, @@ -2000,8 +1872,6 @@ static int rtl8169_set_link_ksettings(struct net_device *dev, cmd->link_modes.advertising)) return -EINVAL; - del_timer_sync(&tp->timer); - rtl_lock_work(tp); rc = rtl8169_set_speed(dev, cmd->base.autoneg, cmd->base.speed, cmd->base.duplex, advertising); @@ -2553,7 +2423,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, static void rtl8169_print_mac_version(struct rtl8169_private *tp) { - dprintk("mac_version = 0x%02x\n", tp->mac_version); + netif_dbg(tp, drv, tp->dev, "mac_version = 0x%02x\n", tp->mac_version); } struct phy_reg { @@ -4405,62 +4275,28 @@ static void rtl_hw_phy_config(struct net_device *dev) } } -static void rtl_phy_work(struct rtl8169_private *tp) -{ - struct timer_list *timer = &tp->timer; - unsigned long timeout = RTL8169_PHY_TIMEOUT; - - assert(tp->mac_version > RTL_GIGA_MAC_VER_01); - - if (tp->phy_reset_pending(tp)) { - /* - * A busy loop could burn quite a few cycles on nowadays CPU. - * Let's delay the execution of the timer for a few ticks. - */ - timeout = HZ/10; - goto out_mod_timer; - } - - if (tp->link_ok(tp)) - return; - - netif_dbg(tp, link, tp->dev, "PHY reset until link up\n"); - - tp->phy_reset_enable(tp); - -out_mod_timer: - mod_timer(timer, jiffies + timeout); -} - static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag) { if (!test_and_set_bit(flag, tp->wk.flags)) schedule_work(&tp->wk.work); } -static void rtl8169_phy_timer(struct timer_list *t) -{ - struct rtl8169_private *tp = from_timer(tp, t, timer); - - rtl_schedule_task(tp, RTL_FLAG_TASK_PHY_PENDING); -} - DECLARE_RTL_COND(rtl_phy_reset_cond) { - return tp->phy_reset_pending(tp); + return rtl8169_xmii_reset_pending(tp); } static void rtl8169_phy_reset(struct net_device *dev, struct rtl8169_private *tp) { - tp->phy_reset_enable(tp); + rtl8169_xmii_reset_enable(tp); rtl_msleep_loop_wait_low(tp, &rtl_phy_reset_cond, 1, 100); } static bool rtl_tbi_enabled(struct rtl8169_private *tp) { return (tp->mac_version == RTL_GIGA_MAC_VER_01) && - (RTL_R8(tp, PHYstatus) & TBI_Enable); + (RTL_R8(tp, PHYstatus) & TBI_Enable); } static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) @@ -4468,7 +4304,8 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) rtl_hw_phy_config(dev); if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { - dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); + netif_dbg(tp, drv, dev, + "Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); RTL_W8(tp, 0x82, 0x01); } @@ -4478,9 +4315,11 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08); if (tp->mac_version == RTL_GIGA_MAC_VER_02) { - dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); + netif_dbg(tp, drv, dev, + "Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); RTL_W8(tp, 0x82, 0x01); - dprintk("Set PHY Reg 0x0bh = 0x00h\n"); + netif_dbg(tp, drv, dev, + "Set PHY Reg 0x0bh = 0x00h\n"); rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0 } @@ -4492,9 +4331,6 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) (tp->mii.supports_gmii ? ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full : 0)); - - if (rtl_tbi_enabled(tp)) - netif_info(tp, link, dev, "TBI auto-negotiating\n"); } static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr) @@ -4537,14 +4373,6 @@ static int rtl_set_mac_address(struct net_device *dev, void *p) return 0; } -static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct rtl8169_private *tp = netdev_priv(dev); - struct mii_ioctl_data *data = if_mii(ifr); - - return netif_running(dev) ? tp->do_ioctl(tp, data, cmd) : -ENODEV; -} - static int rtl_xmii_ioctl(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd) { @@ -4564,9 +4392,12 @@ static int rtl_xmii_ioctl(struct rtl8169_private *tp, return -EOPNOTSUPP; } -static int rtl_tbi_ioctl(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd) +static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - return -EOPNOTSUPP; + struct rtl8169_private *tp = netdev_priv(dev); + struct mii_ioctl_data *data = if_mii(ifr); + + return netif_running(dev) ? rtl_xmii_ioctl(tp, data, cmd) : -ENODEV; } static void rtl_init_mdio_ops(struct rtl8169_private *tp) @@ -4639,7 +4470,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) static bool rtl_wol_pll_power_down(struct rtl8169_private *tp) { - if (!(__rtl8169_get_wol(tp) & WAKE_ANY)) + if (!netif_running(tp->dev) || !tp->saved_wolopts) return false; rtl_speed_down(tp); @@ -5172,8 +5003,8 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp) if (tp->mac_version == RTL_GIGA_MAC_VER_02 || tp->mac_version == RTL_GIGA_MAC_VER_03) { - dprintk("Set MAC Reg C+CR Offset 0xe0. " - "Bit-3 and bit-14 MUST be 1\n"); + netif_dbg(tp, drv, tp->dev, + "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n"); tp->cp_cmd |= (1 << 14); } @@ -5236,12 +5067,7 @@ static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val) rtl_csi_write(tp, 0x070c, csi | val << 24); } -static void rtl_csi_access_enable_1(struct rtl8169_private *tp) -{ - rtl_csi_access_enable(tp, 0x17); -} - -static void rtl_csi_access_enable_2(struct rtl8169_private *tp) +static void rtl_set_def_aspm_entry_latency(struct rtl8169_private *tp) { rtl_csi_access_enable(tp, 0x27); } @@ -5290,6 +5116,17 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) RTL_W8(tp, Config3, data); } +static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) +{ + if (enable) { + RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); + } else { + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + } +} + static void rtl_hw_start_8168bb(struct rtl8169_private *tp) { RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); @@ -5337,7 +5174,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp) { 0x07, 0, 0x2000 } }; - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_ephy_init(tp, e_info_8168cp, ARRAY_SIZE(e_info_8168cp)); @@ -5346,7 +5183,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp) static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp) { - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); @@ -5359,7 +5196,7 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp) static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) { - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); @@ -5383,7 +5220,7 @@ static void rtl_hw_start_8168c_1(struct rtl8169_private *tp) { 0x06, 0x0080, 0x0000 } }; - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); RTL_W8(tp, DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2); @@ -5399,7 +5236,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp) { 0x03, 0x0400, 0x0220 } }; - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_ephy_init(tp, e_info_8168c_2, ARRAY_SIZE(e_info_8168c_2)); @@ -5413,14 +5250,14 @@ static void rtl_hw_start_8168c_3(struct rtl8169_private *tp) static void rtl_hw_start_8168c_4(struct rtl8169_private *tp) { - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); __rtl_hw_start_8168cp(tp); } static void rtl_hw_start_8168d(struct rtl8169_private *tp) { - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_disable_clock_request(tp); @@ -5435,7 +5272,7 @@ static void rtl_hw_start_8168d(struct rtl8169_private *tp) static void rtl_hw_start_8168dp(struct rtl8169_private *tp) { - rtl_csi_access_enable_1(tp); + rtl_set_def_aspm_entry_latency(tp); if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -5453,7 +5290,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) { 0x0c, 0x0100, 0x0020 } }; - rtl_csi_access_enable_1(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -5482,7 +5319,7 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) { 0x0a, 0x0000, 0x0040 } }; - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_ephy_init(tp, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1)); @@ -5507,7 +5344,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) { 0x19, 0x0000, 0x0224 } }; - rtl_csi_access_enable_1(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_ephy_init(tp, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2)); @@ -5536,11 +5373,13 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); + + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168f(struct rtl8169_private *tp) { - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -5611,7 +5450,7 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC); rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC); - rtl_csi_access_enable_1(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -5646,9 +5485,9 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) rtl_hw_start_8168g(tp); /* disable aspm and clock request before access ephy */ - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1)); + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) @@ -5681,9 +5520,9 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) rtl_hw_start_8168g(tp); /* disable aspm and clock request before access ephy */ - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2)); + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) @@ -5700,8 +5539,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1)); RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); @@ -5711,7 +5549,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC); rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC); - rtl_csi_access_enable_1(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -5780,6 +5618,8 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) r8168_mac_ocp_write(tp, 0xe63e, 0x0000); r8168_mac_ocp_write(tp, 0xc094, 0x0000); r8168_mac_ocp_write(tp, 0xc09e, 0x0000); + + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168ep(struct rtl8169_private *tp) @@ -5793,7 +5633,7 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp) rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC); rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC); - rtl_csi_access_enable_1(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -5831,11 +5671,12 @@ static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1)); rtl_hw_start_8168ep(tp); + + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) @@ -5847,14 +5688,15 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2)); rtl_hw_start_8168ep(tp); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); + + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) @@ -5868,8 +5710,7 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3)); rtl_hw_start_8168ep(tp); @@ -5889,6 +5730,8 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) data = r8168_mac_ocp_read(tp, 0xe860); data |= 0x0080; r8168_mac_ocp_write(tp, 0xe860, data); + + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8168(struct rtl8169_private *tp) @@ -6006,8 +5849,9 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp) break; default: - printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n", - tp->dev->name, tp->mac_version); + netif_err(tp, drv, tp->dev, + "unknown chipset (mac_version = %d)\n", + tp->mac_version); break; } } @@ -6026,7 +5870,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp) }; u8 cfg1; - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); RTL_W8(tp, DBG_REG, FIX_NAK_1); @@ -6045,7 +5889,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp) static void rtl_hw_start_8102e_2(struct rtl8169_private *tp) { - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); @@ -6100,7 +5944,7 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) { 0x1e, 0, 0x4000 } }; - rtl_csi_access_enable_2(tp); + rtl_set_def_aspm_entry_latency(tp); /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); @@ -7015,7 +6859,6 @@ static void rtl_task(struct work_struct *work) /* XXX - keep rtl_slow_event_work() as first element. */ { RTL_FLAG_TASK_SLOW_PENDING, rtl_slow_event_work }, { RTL_FLAG_TASK_RESET_PENDING, rtl_reset_work }, - { RTL_FLAG_TASK_PHY_PENDING, rtl_phy_work } }; struct rtl8169_private *tp = container_of(work, struct rtl8169_private, wk.work); @@ -7088,8 +6931,6 @@ static void rtl8169_down(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - del_timer_sync(&tp->timer); - napi_disable(&tp->napi); netif_stop_queue(dev); @@ -7208,7 +7049,6 @@ static int rtl_open(struct net_device *dev) rtl_unlock_work(tp); - tp->saved_wolopts = 0; pm_runtime_put_sync(&pdev->dev); rtl8169_check_link_status(dev, tp); @@ -7323,6 +7163,7 @@ static void __rtl8169_resume(struct net_device *dev) netif_device_attach(dev); rtl_pll_power_up(tp); + rtl8169_init_phy(dev, tp); rtl_lock_work(tp); napi_enable(&tp->napi); @@ -7336,9 +7177,6 @@ static int rtl8169_resume(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct net_device *dev = pci_get_drvdata(pdev); - struct rtl8169_private *tp = netdev_priv(dev); - - rtl8169_init_phy(dev, tp); if (netif_running(dev)) __rtl8169_resume(dev); @@ -7358,7 +7196,6 @@ static int rtl8169_runtime_suspend(struct device *device) } rtl_lock_work(tp); - tp->saved_wolopts = __rtl8169_get_wol(tp); __rtl8169_set_wol(tp, WAKE_ANY); rtl_unlock_work(tp); @@ -7383,11 +7220,8 @@ static int rtl8169_runtime_resume(struct device *device) rtl_lock_work(tp); __rtl8169_set_wol(tp, tp->saved_wolopts); - tp->saved_wolopts = 0; rtl_unlock_work(tp); - rtl8169_init_phy(dev, tp); - __rtl8169_resume(dev); return 0; @@ -7455,7 +7289,7 @@ static void rtl_shutdown(struct pci_dev *pdev) rtl8169_hw_reset(tp); if (system_state == SYSTEM_POWER_OFF) { - if (__rtl8169_get_wol(tp) & WAKE_ANY) { + if (tp->saved_wolopts) { rtl_wol_suspend_quirk(tp); rtl_wol_shutdown_quirk(tp); } @@ -7647,11 +7481,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) mii->reg_num_mask = 0x1f; mii->supports_gmii = cfg->has_gmii; - /* disable ASPM completely as that cause random device stop working - * problems as well as full system hangs for some PCIe devices users */ - pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 | - PCIE_LINK_STATE_CLKPM); - /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { @@ -7689,6 +7518,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Identify chip attached to board */ rtl8169_get_mac_version(tp, cfg->default_ver); + if (rtl_tbi_enabled(tp)) { + dev_err(&pdev->dev, "TBI fiber mode not supported\n"); + return -ENODEV; + } + tp->cp_cmd = RTL_R16(tp, CPlusCmd); if ((sizeof(dma_addr_t) > 4) && @@ -7737,22 +7571,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* override BIOS settings, use userspace tools to enable WOL */ __rtl8169_set_wol(tp, 0); - if (rtl_tbi_enabled(tp)) { - tp->set_speed = rtl8169_set_speed_tbi; - tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi; - tp->phy_reset_enable = rtl8169_tbi_reset_enable; - tp->phy_reset_pending = rtl8169_tbi_reset_pending; - tp->link_ok = rtl8169_tbi_link_ok; - tp->do_ioctl = rtl_tbi_ioctl; - } else { - tp->set_speed = rtl8169_set_speed_xmii; - tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii; - tp->phy_reset_enable = rtl8169_xmii_reset_enable; - tp->phy_reset_pending = rtl8169_xmii_reset_pending; - tp->link_ok = rtl8169_xmii_link_ok; - tp->do_ioctl = rtl_xmii_ioctl; - } - mutex_init(&tp->wk.mutex); u64_stats_init(&tp->rx_stats.syncp); u64_stats_init(&tp->tx_stats.syncp); @@ -7823,8 +7641,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->event_slow = cfg->event_slow; tp->coalesce_info = cfg->coalesce_info; - timer_setup(&tp->timer, rtl8169_phy_timer, 0); - tp->rtl_fw = RTL_FIRMWARE_UNKNOWN; tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters), diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index e9007b613f17..71651e47660a 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -622,7 +622,6 @@ static struct sh_eth_cpu_data r7s72100_data = { .tpauser = 1, .hw_swap = 1, .rpadir = 1, - .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, @@ -672,7 +671,6 @@ static struct sh_eth_cpu_data r8a7740_data = { .bculr = 1, .hw_swap = 1, .rpadir = 1, - .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, @@ -798,7 +796,6 @@ static struct sh_eth_cpu_data r8a77980_data = { .hw_swap = 1, .nbst = 1, .rpadir = 1, - .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, @@ -851,7 +848,6 @@ static struct sh_eth_cpu_data sh7724_data = { .tpauser = 1, .hw_swap = 1, .rpadir = 1, - .rpadir_value = 0x00020000, /* NET_IP_ALIGN assumed to be 2 */ }; static void sh_eth_set_rate_sh7757(struct net_device *ndev) @@ -898,7 +894,6 @@ static struct sh_eth_cpu_data sh7757_data = { .hw_swap = 1, .no_ade = 1, .rpadir = 1, - .rpadir_value = 2 << 16, .rtrate = 1, .dual_port = 1, }; @@ -978,7 +973,6 @@ static struct sh_eth_cpu_data sh7757_data_giga = { .bculr = 1, .hw_swap = 1, .rpadir = 1, - .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, @@ -1467,7 +1461,7 @@ static int sh_eth_dev_init(struct net_device *ndev) /* Descriptor format */ sh_eth_ring_format(ndev); if (mdp->cd->rpadir) - sh_eth_write(ndev, mdp->cd->rpadir_value, RPADIR); + sh_eth_write(ndev, NET_IP_ALIGN << 16, RPADIR); /* all sh_eth int mask */ sh_eth_write(ndev, 0, EESIPR); @@ -1527,9 +1521,9 @@ static int sh_eth_dev_init(struct net_device *ndev) /* mask reset */ if (mdp->cd->apr) - sh_eth_write(ndev, APR_AP, APR); + sh_eth_write(ndev, 1, APR); if (mdp->cd->mpr) - sh_eth_write(ndev, MPR_MP, MPR); + sh_eth_write(ndev, 1, MPR); if (mdp->cd->tpauser) sh_eth_write(ndev, TPAUSER_UNLIMITED, TPAUSER); diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 726c55a82dd7..140ad2c57095 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -383,12 +383,12 @@ enum ECSIPR_STATUS_MASK_BIT { /* APR */ enum APR_BIT { - APR_AP = 0x00000001, + APR_AP = 0x0000ffff, }; /* MPR */ enum MPR_BIT { - MPR_MP = 0x00000001, + MPR_MP = 0x0000ffff, }; /* TRSCER */ @@ -403,8 +403,7 @@ enum DESC_I_BIT { /* RPADIR */ enum RPADIR_BIT { - RPADIR_PADS1 = 0x20000, RPADIR_PADS0 = 0x10000, - RPADIR_PADR = 0x0003f, + RPADIR_PADS = 0x1f0000, RPADIR_PADR = 0xffff, }; /* FDR */ @@ -488,7 +487,6 @@ struct sh_eth_cpu_data { u32 ecsipr_value; u32 fdr_value; u32 fcftr_value; - u32 rpadir_value; /* interrupt checking mask */ u32 tx_check; diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 019cef1d3cf7..8820be83ce85 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -199,7 +199,7 @@ static int efx_ef10_sriov_alloc_vf_vswitching(struct efx_nic *efx) return -ENOMEM; for (i = 0; i < efx->vf_count; i++) { - random_ether_addr(nic_data->vf[i].mac); + eth_random_addr(nic_data->vf[i].mac); nic_data->vf[i].efx = NULL; nic_data->vf[i].vlan = EFX_EF10_NO_VLAN; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index f08625a02cea..7b923362ee55 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -61,6 +61,7 @@ struct rk_priv_data { struct clk *mac_clk_tx; struct clk *clk_mac_ref; struct clk *clk_mac_refout; + struct clk *clk_mac_speed; struct clk *aclk_mac; struct clk *pclk_mac; struct clk *clk_phy; @@ -83,6 +84,64 @@ struct rk_priv_data { (((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \ ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE)) +#define PX30_GRF_GMAC_CON1 0x0904 + +/* PX30_GRF_GMAC_CON1 */ +#define PX30_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \ + GRF_BIT(6)) +#define PX30_GMAC_SPEED_10M GRF_CLR_BIT(2) +#define PX30_GMAC_SPEED_100M GRF_BIT(2) + +static void px30_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "%s: Missing rockchip,grf property\n", __func__); + return; + } + + regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, + PX30_GMAC_PHY_INTF_SEL_RMII); +} + +static void px30_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + int ret; + + if (IS_ERR(bsp_priv->clk_mac_speed)) { + dev_err(dev, "%s: Missing clk_mac_speed clock\n", __func__); + return; + } + + if (speed == 10) { + regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, + PX30_GMAC_SPEED_10M); + + ret = clk_set_rate(bsp_priv->clk_mac_speed, 2500000); + if (ret) + dev_err(dev, "%s: set clk_mac_speed rate 2500000 failed: %d\n", + __func__, ret); + } else if (speed == 100) { + regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, + PX30_GMAC_SPEED_100M); + + ret = clk_set_rate(bsp_priv->clk_mac_speed, 25000000); + if (ret) + dev_err(dev, "%s: set clk_mac_speed rate 25000000 failed: %d\n", + __func__, ret); + + } else { + dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + } +} + +static const struct rk_gmac_ops px30_ops = { + .set_to_rmii = px30_set_to_rmii, + .set_rmii_speed = px30_set_rmii_speed, +}; + #define RK3128_GRF_MAC_CON0 0x0168 #define RK3128_GRF_MAC_CON1 0x016c @@ -1042,6 +1101,10 @@ static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat) } } + bsp_priv->clk_mac_speed = devm_clk_get(dev, "clk_mac_speed"); + if (IS_ERR(bsp_priv->clk_mac_speed)) + dev_err(dev, "cannot get clock %s\n", "clk_mac_speed"); + if (bsp_priv->clock_input) { dev_info(dev, "clock input from PHY\n"); } else { @@ -1094,6 +1157,9 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable) if (!IS_ERR(bsp_priv->mac_clk_tx)) clk_prepare_enable(bsp_priv->mac_clk_tx); + if (!IS_ERR(bsp_priv->clk_mac_speed)) + clk_prepare_enable(bsp_priv->clk_mac_speed); + /** * if (!IS_ERR(bsp_priv->clk_mac)) * clk_prepare_enable(bsp_priv->clk_mac); @@ -1118,6 +1184,8 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable) clk_disable_unprepare(bsp_priv->pclk_mac); clk_disable_unprepare(bsp_priv->mac_clk_tx); + + clk_disable_unprepare(bsp_priv->clk_mac_speed); /** * if (!IS_ERR(bsp_priv->clk_mac)) * clk_disable_unprepare(bsp_priv->clk_mac); @@ -1414,6 +1482,7 @@ static int rk_gmac_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume); static const struct of_device_id rk_gmac_dwmac_match[] = { + { .compatible = "rockchip,px30-gmac", .data = &px30_ops }, { .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops }, { .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops }, { .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 65bc3556bd8f..edb6053bd980 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -407,6 +407,19 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan) } } +static void dwmac4_qmode(void __iomem *ioaddr, u32 channel, u8 qmode) +{ + u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + + mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK; + if (qmode != MTL_QUEUE_AVB) + mtl_tx_op |= MTL_OP_MODE_TXQEN; + else + mtl_tx_op |= MTL_OP_MODE_TXQEN_AV; + + writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); +} + static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) { u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); @@ -441,6 +454,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { .set_rx_tail_ptr = dwmac4_set_rx_tail_ptr, .set_tx_tail_ptr = dwmac4_set_tx_tail_ptr, .enable_tso = dwmac4_enable_tso, + .qmode = dwmac4_qmode, .set_bfsize = dwmac4_set_bfsize, }; @@ -468,5 +482,6 @@ const struct stmmac_dma_ops dwmac410_dma_ops = { .set_rx_tail_ptr = dwmac4_set_rx_tail_ptr, .set_tx_tail_ptr = dwmac4_set_tx_tail_ptr, .enable_tso = dwmac4_enable_tso, + .qmode = dwmac4_qmode, .set_bfsize = dwmac4_set_bfsize, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index fe8b536b13f8..79911eefc2a7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -183,6 +183,7 @@ struct stmmac_dma_ops { void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); + void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode); void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan); }; @@ -236,6 +237,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args) #define stmmac_enable_tso(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, enable_tso, __args) +#define stmmac_dma_qmode(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, qmode, __args) #define stmmac_set_dma_bfsize(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, set_bfsize, __args) @@ -444,17 +447,22 @@ struct stmmac_mode_ops { struct stmmac_priv; struct tc_cls_u32_offload; +struct tc_cbs_qopt_offload; struct stmmac_tc_ops { int (*init)(struct stmmac_priv *priv); int (*setup_cls_u32)(struct stmmac_priv *priv, struct tc_cls_u32_offload *cls); + int (*setup_cbs)(struct stmmac_priv *priv, + struct tc_cbs_qopt_offload *qopt); }; #define stmmac_tc_init(__priv, __args...) \ stmmac_do_callback(__priv, tc, init, __args) #define stmmac_tc_setup_cls_u32(__priv, __args...) \ stmmac_do_callback(__priv, tc, setup_cls_u32, __args) +#define stmmac_tc_setup_cbs(__priv, __args...) \ + stmmac_do_callback(__priv, tc, setup_cbs, __args) struct stmmac_regs_off { u32 ptp_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 60f59abab009..d9e60cfd8a85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3778,7 +3778,7 @@ static int stmmac_setup_tc_block(struct stmmac_priv *priv, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb, - priv, priv); + priv, priv, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv); return 0; @@ -3795,6 +3795,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type, switch (type) { case TC_SETUP_BLOCK: return stmmac_setup_tc_block(priv, type_data); + case TC_SETUP_QDISC_CBS: + return stmmac_tc_setup_cbs(priv, priv, type_data); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 2258cd8cc844..0b0fca0200b2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -289,7 +289,69 @@ static int tc_init(struct stmmac_priv *priv) return 0; } +static int tc_setup_cbs(struct stmmac_priv *priv, + struct tc_cbs_qopt_offload *qopt) +{ + u32 tx_queues_count = priv->plat->tx_queues_to_use; + u32 queue = qopt->queue; + u32 ptr, speed_div; + u32 mode_to_use; + u64 value; + int ret; + + /* Queue 0 is not AVB capable */ + if (queue <= 0 || queue >= tx_queues_count) + return -EINVAL; + if (priv->speed != SPEED_100 && priv->speed != SPEED_1000) + return -EOPNOTSUPP; + + mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; + if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) { + ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB); + if (ret) + return ret; + + priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB; + } else if (!qopt->enable) { + return stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_DCB); + } + + /* Port Transmit Rate and Speed Divider */ + ptr = (priv->speed == SPEED_100) ? 4 : 8; + speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000; + + /* Final adjustments for HW */ + value = qopt->idleslope * 1024 * ptr; + do_div(value, speed_div); + priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0); + + value = -qopt->sendslope * 1024UL * ptr; + do_div(value, speed_div); + priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0); + + value = qopt->hicredit * 1024 * 8; + priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0); + + value = qopt->locredit * 1024 * 8; + priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0); + + ret = stmmac_config_cbs(priv, priv->hw, + priv->plat->tx_queues_cfg[queue].send_slope, + priv->plat->tx_queues_cfg[queue].idle_slope, + priv->plat->tx_queues_cfg[queue].high_credit, + priv->plat->tx_queues_cfg[queue].low_credit, + queue); + if (ret) + return ret; + + dev_info(priv->device, "CBS queue %d: send %d, idle %d, hi %d, lo %d\n", + queue, qopt->sendslope, qopt->idleslope, + qopt->hicredit, qopt->locredit); + return 0; +} + const struct stmmac_tc_ops dwmac510_tc_ops = { .init = tc_init, .setup_cls_u32 = tc_setup_cls_u32, + .setup_cbs = tc_setup_cbs, }; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 358edab9e72e..093998124149 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2927,7 +2927,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) dev_info(cpsw->dev, "cpsw: Detected MACID = %pM\n", priv_sl2->mac_addr); } else { - random_ether_addr(priv_sl2->mac_addr); + eth_random_addr(priv_sl2->mac_addr); dev_info(cpsw->dev, "cpsw: Random MACID = %pM\n", priv_sl2->mac_addr); } diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index e40aa3e31af2..6ebf110cd594 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2052,7 +2052,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device, if (is_valid_ether_addr(efuse_mac_addr)) ether_addr_copy(ndev->dev_addr, efuse_mac_addr); else - random_ether_addr(ndev->dev_addr); + eth_random_addr(ndev->dev_addr); devm_iounmap(dev, efuse); devm_release_mem_region(dev, res.start, size); @@ -2061,7 +2061,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device, if (mac_addr) ether_addr_copy(ndev->dev_addr, mac_addr); else - random_ether_addr(ndev->dev_addr); + eth_random_addr(ndev->dev_addr); } ret = of_property_read_string(node_interface, "rx-channel", diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 2a0c06e0f730..42f1f518dad6 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -70,7 +70,8 @@ #define XEL_TSR_XMIT_IE_MASK 0x00000008 /* Tx interrupt enable bit */ #define XEL_TSR_XMIT_ACTIVE_MASK 0x80000000 /* Buffer is active, SW bit * only. This is not documented - * in the HW spec */ + * in the HW spec + */ /* Define for programming the MAC address into the EmacLite */ #define XEL_TSR_PROG_MAC_ADDR (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_PROGRAM_MASK) @@ -94,11 +95,11 @@ -#define TX_TIMEOUT (60*HZ) /* Tx timeout is 60 seconds. */ +#define TX_TIMEOUT (60 * HZ) /* Tx timeout is 60 seconds. */ #define ALIGNMENT 4 /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */ -#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT) +#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32)adr)) % ALIGNMENT) #ifdef __BIG_ENDIAN #define xemaclite_readl ioread32be @@ -238,8 +239,8 @@ static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr, /* Set up to output the remaining data */ align_buffer = 0; - to_u8_ptr = (u8 *) &align_buffer; - from_u8_ptr = (u8 *) from_u16_ptr; + to_u8_ptr = (u8 *)&align_buffer; + from_u8_ptr = (u8 *)from_u16_ptr; /* Output the remaining data */ for (; length > 0; length--) @@ -272,7 +273,7 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr, u32 align_buffer; from_u32_ptr = src_ptr; - to_u16_ptr = (u16 *) dest_ptr; + to_u16_ptr = (u16 *)dest_ptr; for (; length > 3; length -= 4) { /* Copy each word into the temporary buffer */ @@ -288,9 +289,9 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr, u8 *to_u8_ptr, *from_u8_ptr; /* Set up to read the remaining data */ - to_u8_ptr = (u8 *) to_u16_ptr; + to_u8_ptr = (u8 *)to_u16_ptr; align_buffer = *from_u32_ptr++; - from_u8_ptr = (u8 *) &align_buffer; + from_u8_ptr = (u8 *)&align_buffer; /* Read the remaining data */ for (; length > 0; length--) @@ -336,7 +337,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, drvdata->next_tx_buf_to_use ^= XEL_BUFFER_OFFSET; } else if (drvdata->tx_ping_pong != 0) { /* If the expected buffer is full, try the other buffer, - * if it is configured in HW */ + * if it is configured in HW + */ addr = (void __iomem __force *)((u32 __force)addr ^ XEL_BUFFER_OFFSET); @@ -349,7 +351,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, return -1; /* Buffer was full, return failure */ /* Write the frame to the buffer */ - xemaclite_aligned_write(data, (u32 __force *) addr, byte_count); + xemaclite_aligned_write(data, (u32 __force *)addr, byte_count); xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK), addr + XEL_TPLR_OFFSET); @@ -357,7 +359,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, /* Update the Tx Status Register to indicate that there is a * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which * is used by the interrupt handler to check whether a frame - * has been transmitted */ + * has been transmitted + */ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET); reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK); xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET); @@ -369,6 +372,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data, * xemaclite_recv_data - Receive a frame * @drvdata: Pointer to the Emaclite device private data * @data: Address where the data is to be received + * @maxlen: Maximum supported ethernet packet length * * This function is intended to be called from the interrupt context or * with a wrapper which waits for the receive frame to be available. @@ -394,7 +398,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) /* The instance is out of sync, try other buffer if other * buffer is configured, return 0 otherwise. If the instance is * out of sync, do not update the 'next_rx_buf_to_use' since it - * will correct on subsequent calls */ + * will correct on subsequent calls + */ if (drvdata->rx_ping_pong != 0) addr = (void __iomem __force *)((u32 __force)addr ^ XEL_BUFFER_OFFSET); @@ -408,13 +413,15 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) return 0; /* No data was available */ } - /* Get the protocol type of the ethernet frame that arrived */ + /* Get the protocol type of the ethernet frame that arrived + */ proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET + XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) & XEL_RPLR_LENGTH_MASK); /* Check if received ethernet frame is a raw ethernet frame - * or an IP packet or an ARP packet */ + * or an IP packet or an ARP packet + */ if (proto_type > ETH_DATA_LEN) { if (proto_type == ETH_P_IP) { @@ -430,7 +437,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) length = XEL_ARP_PACKET_SIZE + ETH_HLEN + ETH_FCS_LEN; else /* Field contains type other than IP or ARP, use max - * frame size and let user parse it */ + * frame size and let user parse it + */ length = ETH_FRAME_LEN + ETH_FCS_LEN; } else /* Use the length in the frame, plus the header and trailer */ @@ -440,7 +448,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) length = maxlen; /* Read from the EmacLite device */ - xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET), + xemaclite_aligned_read((u32 __force *)(addr + XEL_RXBUFF_OFFSET), data, length); /* Acknowledge the frame */ @@ -471,7 +479,7 @@ static void xemaclite_update_address(struct net_local *drvdata, /* Determine the expected Tx buffer address */ addr = drvdata->base_addr + drvdata->next_tx_buf_to_use; - xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN); + xemaclite_aligned_write(address_ptr, (u32 __force *)addr, ETH_ALEN); xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET); @@ -488,7 +496,7 @@ static void xemaclite_update_address(struct net_local *drvdata, /** * xemaclite_set_mac_address - Set the MAC address for this device * @dev: Pointer to the network device instance - * @addr: Void pointer to the sockaddr structure + * @address: Void pointer to the sockaddr structure * * This function copies the HW address from the sockaddr strucutre to the * net_device structure and updates the address in HW. @@ -564,19 +572,19 @@ static void xemaclite_tx_handler(struct net_device *dev) struct net_local *lp = netdev_priv(dev); dev->stats.tx_packets++; - if (lp->deferred_skb) { - if (xemaclite_send_data(lp, - (u8 *) lp->deferred_skb->data, - lp->deferred_skb->len) != 0) - return; - else { - dev->stats.tx_bytes += lp->deferred_skb->len; - dev_kfree_skb_irq(lp->deferred_skb); - lp->deferred_skb = NULL; - netif_trans_update(dev); /* prevent tx timeout */ - netif_wake_queue(dev); - } - } + + if (!lp->deferred_skb) + return; + + if (xemaclite_send_data(lp, (u8 *)lp->deferred_skb->data, + lp->deferred_skb->len)) + return; + + dev->stats.tx_bytes += lp->deferred_skb->len; + dev_kfree_skb_irq(lp->deferred_skb); + lp->deferred_skb = NULL; + netif_trans_update(dev); /* prevent tx timeout */ + netif_wake_queue(dev); } /** @@ -602,18 +610,18 @@ static void xemaclite_rx_handler(struct net_device *dev) return; } - /* - * A new skb should have the data halfword aligned, but this code is + /* A new skb should have the data halfword aligned, but this code is * here just in case that isn't true. Calculate how many * bytes we should reserve to get the data to start on a word - * boundary */ + * boundary + */ align = BUFFER_ALIGN(skb->data); if (align) skb_reserve(skb, align); skb_reserve(skb, 2); - len = xemaclite_recv_data(lp, (u8 *) skb->data, len); + len = xemaclite_recv_data(lp, (u8 *)skb->data, len); if (!len) { dev->stats.rx_errors++; @@ -639,6 +647,8 @@ static void xemaclite_rx_handler(struct net_device *dev) * @dev_id: Void pointer to the network device instance used as callback * reference * + * Return: IRQ_HANDLED + * * This function handles the Tx and Rx interrupts of the EmacLite device. */ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id) @@ -706,8 +716,8 @@ static int xemaclite_mdio_wait(struct net_local *lp) unsigned long end = jiffies + 2; /* wait for the MDIO interface to not be busy or timeout - after some time. - */ + * after some time. + */ while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) & XEL_MDIOCTRL_MDIOSTS_MASK) { if (time_before_eq(end, jiffies)) { @@ -757,7 +767,7 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg) rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET); dev_dbg(&lp->ndev->dev, - "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n", + "%s(phy_id=%i, reg=%x) == %x\n", __func__, phy_id, reg, rc); return rc; @@ -772,6 +782,8 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg) * * This function waits till the device is ready to accept a new MDIO * request and then writes the val to the MDIO Write Data register. + * + * Return: 0 upon success or a negative error upon failure */ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val) @@ -780,7 +792,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, u32 ctrl_reg; dev_dbg(&lp->ndev->dev, - "xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n", + "%s(phy_id=%i, reg=%x, val=%x)\n", __func__, phy_id, reg, val); if (xemaclite_mdio_wait(lp)) @@ -805,7 +817,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, /** * xemaclite_mdio_setup - Register mii_bus for the Emaclite device * @lp: Pointer to the Emaclite device private data - * @ofdev: Pointer to OF device structure + * @dev: Pointer to OF device structure * * This function enables MDIO bus in the Emaclite device and registers a * mii_bus. @@ -905,6 +917,9 @@ static void xemaclite_adjust_link(struct net_device *ndev) * This function sets the MAC address, requests an IRQ and enables interrupts * for the Emaclite device and starts the Tx queue. * It also connects to the phy device, if MDIO is included in Emaclite device. + * + * Return: 0 on success. -ENODEV, if PHY cannot be connected. + * Non-zero error value on failure. */ static int xemaclite_open(struct net_device *dev) { @@ -975,6 +990,8 @@ static int xemaclite_open(struct net_device *dev) * This function stops the Tx queue, disables interrupts and frees the IRQ for * the Emaclite device. * It also disconnects the phy device associated with the Emaclite device. + * + * Return: 0, always. */ static int xemaclite_close(struct net_device *dev) { @@ -1017,10 +1034,11 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev) new_skb = orig_skb; spin_lock_irqsave(&lp->reset_lock, flags); - if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) { + if (xemaclite_send_data(lp, (u8 *)new_skb->data, len) != 0) { /* If the Emaclite Tx buffer is busy, stop the Tx queue and * defer the skb for transmission during the ISR, after the - * current transmission is complete */ + * current transmission is complete + */ netif_stop_queue(dev); lp->deferred_skb = new_skb; /* Take the time stamp now, since we can't do this in an ISR. */ @@ -1052,13 +1070,12 @@ static bool get_bool(struct platform_device *ofdev, const char *s) { u32 *p = (u32 *)of_get_property(ofdev->dev.of_node, s, NULL); - if (p) { - return (bool)*p; - } else { - dev_warn(&ofdev->dev, "Parameter %s not found," - "defaulting to false\n", s); + if (!p) { + dev_warn(&ofdev->dev, "Parameter %s not found, defaulting to false\n", s); return false; } + + return (bool)*p; } static const struct net_device_ops xemaclite_netdev_ops; @@ -1066,7 +1083,6 @@ static const struct net_device_ops xemaclite_netdev_ops; /** * xemaclite_of_probe - Probe method for the Emaclite device. * @ofdev: Pointer to OF device structure - * @match: Pointer to the structure used for matching a device * * This function probes for the Emaclite device in the device tree. * It initializes the driver data structure and the hardware, sets the MAC diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index ada33c2d9ac2..6acb6b5718b9 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -236,7 +236,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, } /* Update tunnel dst according to Geneve options. */ ip_tunnel_info_opts_set(&tun_dst->u.tun_info, - gnvh->options, gnvh->opt_len * 4); + gnvh->options, gnvh->opt_len * 4, + TUNNEL_GENEVE_OPT); } else { /* Drop packets w/ critical options, * since we don't support any... @@ -418,11 +419,12 @@ static int geneve_hlen(struct genevehdr *gh) return sizeof(*gh) + gh->opt_len * 4; } -static struct sk_buff **geneve_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *geneve_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct genevehdr *gh, *gh2; unsigned int hlen, gh_len, off_gnv; const struct packet_offload *ptype; @@ -449,7 +451,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, goto out; } - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -674,7 +676,8 @@ static void geneve_build_header(struct genevehdr *geneveh, geneveh->proto_type = htons(ETH_P_TEB); geneveh->rsvd2 = 0; - ip_tunnel_info_opts_get(geneveh->options, info); + if (info->key.tun_flags & TUNNEL_GENEVE_OPT) + ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile index 449b2a1a1800..0fee1d06c084 100644 --- a/drivers/net/netdevsim/Makefile +++ b/drivers/net/netdevsim/Makefile @@ -13,3 +13,7 @@ endif ifneq ($(CONFIG_NET_DEVLINK),) netdevsim-objs += devlink.o fib.o endif + +ifneq ($(CONFIG_XFRM_OFFLOAD),) +netdevsim-objs += ipsec.o +endif diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c new file mode 100644 index 000000000000..2dcf6cc269d0 --- /dev/null +++ b/drivers/net/netdevsim/ipsec.c @@ -0,0 +1,297 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ + +#include <crypto/aead.h> +#include <linux/debugfs.h> +#include <net/xfrm.h> + +#include "netdevsim.h" + +#define NSIM_IPSEC_AUTH_BITS 128 + +static ssize_t nsim_dbg_netdev_ops_read(struct file *filp, + char __user *buffer, + size_t count, loff_t *ppos) +{ + struct netdevsim *ns = filp->private_data; + struct nsim_ipsec *ipsec = &ns->ipsec; + size_t bufsize; + char *buf, *p; + int len; + int i; + + /* the buffer needed is + * (num SAs * 3 lines each * ~60 bytes per line) + one more line + */ + bufsize = (ipsec->count * 4 * 60) + 60; + buf = kzalloc(bufsize, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + p = buf; + p += snprintf(p, bufsize - (p - buf), + "SA count=%u tx=%u\n", + ipsec->count, ipsec->tx); + + for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { + struct nsim_sa *sap = &ipsec->sa[i]; + + if (!sap->used) + continue; + + p += snprintf(p, bufsize - (p - buf), + "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n", + i, (sap->rx ? 'r' : 't'), sap->ipaddr[0], + sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]); + p += snprintf(p, bufsize - (p - buf), + "sa[%i] spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n", + i, be32_to_cpu(sap->xs->id.spi), + sap->xs->id.proto, sap->salt, sap->crypt); + p += snprintf(p, bufsize - (p - buf), + "sa[%i] key=0x%08x %08x %08x %08x\n", + i, sap->key[0], sap->key[1], + sap->key[2], sap->key[3]); + } + + len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf); + + kfree(buf); + return len; +} + +static const struct file_operations ipsec_dbg_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = nsim_dbg_netdev_ops_read, +}; + +static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec) +{ + u32 i; + + if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search sa table */ + for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->sa[i].used) + return i; + } + + return -ENOSPC; +} + +static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs, + u32 *mykey, u32 *mysalt) +{ + const char aes_gcm_name[] = "rfc4106(gcm(aes))"; + struct net_device *dev = xs->xso.dev; + unsigned char *key_data; + char *alg_name = NULL; + int key_len; + + if (!xs->aead) { + netdev_err(dev, "Unsupported IPsec algorithm\n"); + return -EINVAL; + } + + if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) { + netdev_err(dev, "IPsec offload requires %d bit authentication\n", + NSIM_IPSEC_AUTH_BITS); + return -EINVAL; + } + + key_data = &xs->aead->alg_key[0]; + key_len = xs->aead->alg_key_len; + alg_name = xs->aead->alg_name; + + if (strcmp(alg_name, aes_gcm_name)) { + netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", + aes_gcm_name); + return -EINVAL; + } + + /* 160 accounts for 16 byte key and 4 byte salt */ + if (key_len > NSIM_IPSEC_AUTH_BITS) { + *mysalt = ((u32 *)key_data)[4]; + } else if (key_len == NSIM_IPSEC_AUTH_BITS) { + *mysalt = 0; + } else { + netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n"); + return -EINVAL; + } + memcpy(mykey, key_data, 16); + + return 0; +} + +static int nsim_ipsec_add_sa(struct xfrm_state *xs) +{ + struct nsim_ipsec *ipsec; + struct net_device *dev; + struct netdevsim *ns; + struct nsim_sa sa; + u16 sa_idx; + int ret; + + dev = xs->xso.dev; + ns = netdev_priv(dev); + ipsec = &ns->ipsec; + + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { + netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n", + xs->id.proto); + return -EINVAL; + } + + if (xs->calg) { + netdev_err(dev, "Compression offload not supported\n"); + return -EINVAL; + } + + /* find the first unused index */ + ret = nsim_ipsec_find_empty_idx(ipsec); + if (ret < 0) { + netdev_err(dev, "No space for SA in Rx table!\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&sa, 0, sizeof(sa)); + sa.used = true; + sa.xs = xs; + + if (sa.xs->id.proto & IPPROTO_ESP) + sa.crypt = xs->ealg || xs->aead; + + /* get the key and salt */ + ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for SA table\n"); + return ret; + } + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + sa.rx = true; + + if (xs->props.family == AF_INET6) + memcpy(sa.ipaddr, &xs->id.daddr.a6, 16); + else + memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4); + } + + /* the preparations worked, so save the info */ + memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa)); + + /* the XFRM stack doesn't like offload_handle == 0, + * so add a bitflag in case our array index is 0 + */ + xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID; + ipsec->count++; + + return 0; +} + +static void nsim_ipsec_del_sa(struct xfrm_state *xs) +{ + struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct nsim_ipsec *ipsec = &ns->ipsec; + u16 sa_idx; + + sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID; + if (!ipsec->sa[sa_idx].used) { + netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n", + sa_idx); + return; + } + + memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa)); + ipsec->count--; +} + +static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) +{ + struct netdevsim *ns = netdev_priv(xs->xso.dev); + struct nsim_ipsec *ipsec = &ns->ipsec; + + ipsec->ok++; + + return true; +} + +static const struct xfrmdev_ops nsim_xfrmdev_ops = { + .xdo_dev_state_add = nsim_ipsec_add_sa, + .xdo_dev_state_delete = nsim_ipsec_del_sa, + .xdo_dev_offload_ok = nsim_ipsec_offload_ok, +}; + +bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb) +{ + struct nsim_ipsec *ipsec = &ns->ipsec; + struct xfrm_state *xs; + struct nsim_sa *tsa; + u32 sa_idx; + + /* do we even need to check this packet? */ + if (!skb->sp) + return true; + + if (unlikely(!skb->sp->len)) { + netdev_err(ns->netdev, "no xfrm state len = %d\n", + skb->sp->len); + return false; + } + + xs = xfrm_input_state(skb); + if (unlikely(!xs)) { + netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs); + return false; + } + + sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID; + if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) { + netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n", + sa_idx, NSIM_IPSEC_MAX_SA_COUNT); + return false; + } + + tsa = &ipsec->sa[sa_idx]; + if (unlikely(!tsa->used)) { + netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx); + return false; + } + + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { + netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto); + return false; + } + + ipsec->tx++; + + return true; +} + +void nsim_ipsec_init(struct netdevsim *ns) +{ + ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops; + +#define NSIM_ESP_FEATURES (NETIF_F_HW_ESP | \ + NETIF_F_HW_ESP_TX_CSUM | \ + NETIF_F_GSO_ESP) + + ns->netdev->features |= NSIM_ESP_FEATURES; + ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES; + + ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->ddir, ns, + &ipsec_dbg_fops); +} + +void nsim_ipsec_teardown(struct netdevsim *ns) +{ + struct nsim_ipsec *ipsec = &ns->ipsec; + + if (ipsec->count) + netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n", + ipsec->count); + debugfs_remove_recursive(ipsec->pfile); +} diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index ec68f38213d9..b2f9d0df93b0 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -171,6 +171,8 @@ static int nsim_init(struct net_device *dev) if (err) goto err_unreg_dev; + nsim_ipsec_init(ns); + return 0; err_unreg_dev: @@ -186,6 +188,7 @@ static void nsim_uninit(struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); + nsim_ipsec_teardown(ns); nsim_devlink_teardown(ns); debugfs_remove_recursive(ns->ddir); nsim_bpf_uninit(ns); @@ -203,11 +206,15 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); + if (!nsim_ipsec_tx(ns, skb)) + goto out; + u64_stats_update_begin(&ns->syncp); ns->tx_packets++; ns->tx_bytes += skb->len; u64_stats_update_end(&ns->syncp); +out: dev_kfree_skb(skb); return NETDEV_TX_OK; @@ -260,7 +267,7 @@ nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f) switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb, - ns, ns); + ns, ns, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns); return 0; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 8ca50b72c328..d8a7cc995e88 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -29,6 +29,27 @@ struct bpf_prog; struct dentry; struct nsim_vf_config; +#define NSIM_IPSEC_MAX_SA_COUNT 33 +#define NSIM_IPSEC_VALID BIT(31) + +struct nsim_sa { + struct xfrm_state *xs; + __be32 ipaddr[4]; + u32 key[4]; + u32 salt; + bool used; + bool crypt; + bool rx; +}; + +struct nsim_ipsec { + struct nsim_sa sa[NSIM_IPSEC_MAX_SA_COUNT]; + struct dentry *pfile; + u32 count; + u32 tx; + u32 ok; +}; + struct netdevsim { struct net_device *netdev; @@ -67,6 +88,7 @@ struct netdevsim { #if IS_ENABLED(CONFIG_NET_DEVLINK) struct devlink *devlink; #endif + struct nsim_ipsec ipsec; }; extern struct dentry *nsim_ddir; @@ -148,6 +170,25 @@ static inline void nsim_devlink_exit(void) } #endif +#if IS_ENABLED(CONFIG_XFRM_OFFLOAD) +void nsim_ipsec_init(struct netdevsim *ns); +void nsim_ipsec_teardown(struct netdevsim *ns); +bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb); +#else +static inline void nsim_ipsec_init(struct netdevsim *ns) +{ +} + +static inline void nsim_ipsec_teardown(struct netdevsim *ns) +{ +} + +static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb) +{ + return true; +} +#endif + static inline struct netdevsim *to_nsim(struct device *ptr) { return container_of(ptr, struct netdevsim, dev); diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 9f6f7ccd44f7..b12023bc2cab 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -430,7 +430,7 @@ static int ntb_netdev_probe(struct device *client_dev) ndev->hw_features = ndev->features; ndev->watchdog_timeo = msecs_to_jiffies(NTB_TX_TIMEOUT_MS); - random_ether_addr(ndev->perm_addr); + eth_random_addr(ndev->perm_addr); memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len); ndev->netdev_ops = &ntb_netdev_ops; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 343989f9f9d9..ceede09a2845 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -92,7 +92,8 @@ config MDIO_CAVIUM config MDIO_GPIO tristate "GPIO lib-based bitbanged MDIO buses" - depends on MDIO_BITBANG && GPIOLIB + depends on MDIO_BITBANG + depends on GPIOLIB || COMPILE_TEST ---help--- Supports GPIO lib-based MDIO busses. diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 001fe1df7557..67b260877f30 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -259,10 +259,8 @@ static int __init fixed_mdio_bus_init(void) int ret; pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0); - if (IS_ERR(pdev)) { - ret = PTR_ERR(pdev); - goto err_pdev; - } + if (IS_ERR(pdev)) + return PTR_ERR(pdev); fmb->mii_bus = mdiobus_alloc(); if (fmb->mii_bus == NULL) { @@ -287,7 +285,6 @@ err_mdiobus_alloc: mdiobus_free(fmb->mii_bus); err_mdiobus_reg: platform_device_unregister(pdev); -err_pdev: return ret; } module_init(fixed_mdio_bus_init); diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c index 082ffef0dec4..bc90764a8b8d 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/phy/mdio-mux-gpio.c @@ -20,23 +20,23 @@ struct mdio_mux_gpio_state { struct gpio_descs *gpios; void *mux_handle; + int values[]; }; static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, void *data) { struct mdio_mux_gpio_state *s = data; - int values[s->gpios->ndescs]; unsigned int n; if (current_child == desired_child) return 0; for (n = 0; n < s->gpios->ndescs; n++) - values[n] = (desired_child >> n) & 1; + s->values[n] = (desired_child >> n) & 1; gpiod_set_array_value_cansleep(s->gpios->ndescs, s->gpios->desc, - values); + s->values); return 0; } @@ -44,15 +44,21 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, static int mdio_mux_gpio_probe(struct platform_device *pdev) { struct mdio_mux_gpio_state *s; + struct gpio_descs *gpios; int r; - s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); - if (!s) + gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW); + if (IS_ERR(gpios)) + return PTR_ERR(gpios); + + s = devm_kzalloc(&pdev->dev, struct_size(s, values, gpios->ndescs), + GFP_KERNEL); + if (!s) { + gpiod_put_array(gpios); return -ENOMEM; + } - s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW); - if (IS_ERR(s->gpios)) - return PTR_ERR(s->gpios); + s->gpios = gpios; r = mdio_mux_init(&pdev->dev, pdev->dev.of_node, mdio_mux_gpio_switch_fn, &s->mux_handle, s, NULL); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 082fb40c656d..f8f127831a92 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -128,6 +128,37 @@ static int rtl8211f_config_intr(struct phy_device *phydev) return phy_write_paged(phydev, 0xa42, RTL821x_INER, val); } +static int rtl8211_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = genphy_config_aneg(phydev); + if (ret < 0) + return ret; + + /* Quirk was copied from vendor driver. Unfortunately it includes no + * description of the magic numbers. + */ + if (phydev->speed == SPEED_100 && phydev->autoneg == AUTONEG_DISABLE) { + phy_write(phydev, 0x17, 0x2138); + phy_write(phydev, 0x0e, 0x0260); + } else { + phy_write(phydev, 0x17, 0x2108); + phy_write(phydev, 0x0e, 0x0000); + } + + return 0; +} + +static int rtl8211c_config_init(struct phy_device *phydev) +{ + /* RTL8211C has an issue when operating in Gigabit slave mode */ + phy_set_bits(phydev, MII_CTRL1000, + CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER); + + return genphy_config_init(phydev); +} + static int rtl8211f_config_init(struct phy_device *phydev) { int ret; @@ -179,6 +210,14 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { + .phy_id = 0x001cc910, + .name = "RTL8211 Gigabit Ethernet", + .phy_id_mask = 0x001fffff, + .features = PHY_GBIT_FEATURES, + .config_aneg = rtl8211_config_aneg, + .read_mmd = &genphy_read_mmd_unsupported, + .write_mmd = &genphy_write_mmd_unsupported, + }, { .phy_id = 0x001cc912, .name = "RTL8211B Gigabit Ethernet", .phy_id_mask = 0x001fffff, @@ -191,6 +230,14 @@ static struct phy_driver realtek_drvs[] = { .suspend = rtl8211b_suspend, .resume = rtl8211b_resume, }, { + .phy_id = 0x001cc913, + .name = "RTL8211C Gigabit Ethernet", + .phy_id_mask = 0x001fffff, + .features = PHY_GBIT_FEATURES, + .config_init = rtl8211c_config_init, + .read_mmd = &genphy_read_mmd_unsupported, + .write_mmd = &genphy_write_mmd_unsupported, + }, { .phy_id = 0x001cc914, .name = "RTL8211DN Gigabit Ethernet", .phy_id_mask = 0x001fffff, @@ -230,6 +277,7 @@ module_phy_driver(realtek_drvs); static struct mdio_device_id __maybe_unused realtek_tbl[] = { { 0x001cc816, 0x001fffff }, + { 0x001cc910, 0x001fffff }, { 0x001cc912, 0x001fffff }, { 0x001cc914, 0x001fffff }, { 0x001cc915, 0x001fffff }, diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index 2e5150b0b8d5..74a8782313cf 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -33,17 +33,22 @@ struct gmii2rgmii { struct phy_device *phy_dev; struct phy_driver *phy_drv; struct phy_driver conv_phy_drv; - int addr; + struct mdio_device *mdio; }; static int xgmiitorgmii_read_status(struct phy_device *phydev) { struct gmii2rgmii *priv = phydev->priv; + struct mii_bus *bus = priv->mdio->bus; + int addr = priv->mdio->addr; u16 val = 0; + int err; - priv->phy_drv->read_status(phydev); + err = priv->phy_drv->read_status(phydev); + if (err < 0) + return err; - val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG); + val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG); val &= ~XILINX_GMII2RGMII_SPEED_MASK; if (phydev->speed == SPEED_1000) @@ -53,7 +58,7 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev) else val |= BMCR_SPEED10; - mdiobus_write(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG, val); + mdiobus_write(bus, addr, XILINX_GMII2RGMII_REG, val); return 0; } @@ -81,7 +86,12 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev) return -EPROBE_DEFER; } - priv->addr = mdiodev->addr; + if (!priv->phy_dev->drv) { + dev_info(dev, "Attached phy not ready\n"); + return -EPROBE_DEFER; + } + + priv->mdio = mdiodev; priv->phy_drv = priv->phy_dev->drv; memcpy(&priv->conv_phy_drv, priv->phy_dev->drv, sizeof(struct phy_driver)); diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 18d36dff97ea..424053bd8b21 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -869,6 +869,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id default: dev_warn(&intf->dev, "Couldn't detect memory size, assuming 32k\n"); + /* fall through */ case 0x87654321: catc_set_reg(catc, TxBufCount, 4); catc_set_reg(catc, RxBufCount, 16); diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 288ecd999171..78b16eb9e58c 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -99,6 +99,7 @@ static void tx_complete(struct urb *req) struct net_device *dev = skb->dev; struct usbpn_dev *pnd = netdev_priv(dev); int status = req->status; + unsigned long flags; switch (status) { case 0: @@ -109,16 +110,17 @@ static void tx_complete(struct urb *req) case -ECONNRESET: case -ESHUTDOWN: dev->stats.tx_aborted_errors++; + /* fall through */ default: dev->stats.tx_errors++; dev_dbg(&dev->dev, "TX error (%d)\n", status); } dev->stats.tx_packets++; - spin_lock(&pnd->tx_lock); + spin_lock_irqsave(&pnd->tx_lock, flags); pnd->tx_queue--; netif_wake_queue(dev); - spin_unlock(&pnd->tx_lock); + spin_unlock_irqrestore(&pnd->tx_lock, flags); dev_kfree_skb_any(skb); usb_free_urb(req); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index e53883ad6107..de305ead32e6 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -999,6 +999,7 @@ static void read_bulk_callback(struct urb *urb) struct hso_net *odev = urb->context; struct net_device *net; int result; + unsigned long flags; int status = urb->status; /* is al ok? (Filip: Who's Al ?) */ @@ -1028,11 +1029,11 @@ static void read_bulk_callback(struct urb *urb) if (urb->actual_length) { /* Handle the IP stream, add header and push it onto network * stack if the packet is complete. */ - spin_lock(&odev->net_lock); + spin_lock_irqsave(&odev->net_lock, flags); packetizeRx(odev, urb->transfer_buffer, urb->actual_length, (urb->transfer_buffer_length > urb->actual_length) ? 1 : 0); - spin_unlock(&odev->net_lock); + spin_unlock_irqrestore(&odev->net_lock, flags); } /* We are done with this URB, resubmit it. Prep the USB to wait for @@ -1193,6 +1194,7 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb) { struct hso_serial *serial = urb->context; int status = urb->status; + unsigned long flags; hso_dbg(0x8, "--- Got serial_read_bulk callback %02x ---\n", status); @@ -1216,10 +1218,10 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb) if (serial->parent->port_spec & HSO_INFO_CRC_BUG) fix_crc_bug(urb, serial->in_endp->wMaxPacketSize); /* Valid data, handle RX data */ - spin_lock(&serial->serial_lock); + spin_lock_irqsave(&serial->serial_lock, flags); serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1; put_rxbuf_data_and_resubmit_bulk_urb(serial); - spin_unlock(&serial->serial_lock); + spin_unlock_irqrestore(&serial->serial_lock, flags); } /* @@ -1502,12 +1504,13 @@ static void tiocmget_intr_callback(struct urb *urb) DUMP(serial_state_notification, sizeof(struct hso_serial_state_notification)); } else { + unsigned long flags; UART_state_bitmap = le16_to_cpu(serial_state_notification-> UART_state_bitmap); prev_UART_state_bitmap = tiocmget->prev_UART_state_bitmap; icount = &tiocmget->icount; - spin_lock(&serial->serial_lock); + spin_lock_irqsave(&serial->serial_lock, flags); if ((UART_state_bitmap & B_OVERRUN) != (prev_UART_state_bitmap & B_OVERRUN)) icount->parity++; @@ -1530,7 +1533,7 @@ static void tiocmget_intr_callback(struct urb *urb) (prev_UART_state_bitmap & B_RX_CARRIER)) icount->dcd++; tiocmget->prev_UART_state_bitmap = UART_state_bitmap; - spin_unlock(&serial->serial_lock); + spin_unlock_irqrestore(&serial->serial_lock, flags); tiocmget->intr_completed = 1; wake_up_interruptible(&tiocmget->waitq); } @@ -1852,6 +1855,7 @@ static void intr_callback(struct urb *urb) struct hso_serial *serial; unsigned char *port_req; int status = urb->status; + unsigned long flags; int i; usb_mark_last_busy(urb->dev); @@ -1879,7 +1883,7 @@ static void intr_callback(struct urb *urb) if (serial != NULL) { hso_dbg(0x1, "Pending read interrupt on port %d\n", i); - spin_lock(&serial->serial_lock); + spin_lock_irqsave(&serial->serial_lock, flags); if (serial->rx_state == RX_IDLE && serial->port.count > 0) { /* Setup and send a ctrl req read on @@ -1893,7 +1897,8 @@ static void intr_callback(struct urb *urb) hso_dbg(0x1, "Already a read pending on port %d or port not open\n", i); } - spin_unlock(&serial->serial_lock); + spin_unlock_irqrestore(&serial->serial_lock, + flags); } } } @@ -1920,6 +1925,7 @@ static void hso_std_serial_write_bulk_callback(struct urb *urb) { struct hso_serial *serial = urb->context; int status = urb->status; + unsigned long flags; /* sanity check */ if (!serial) { @@ -1927,9 +1933,9 @@ static void hso_std_serial_write_bulk_callback(struct urb *urb) return; } - spin_lock(&serial->serial_lock); + spin_lock_irqsave(&serial->serial_lock, flags); serial->tx_urb_used = 0; - spin_unlock(&serial->serial_lock); + spin_unlock_irqrestore(&serial->serial_lock, flags); if (status) { handle_usb_error(status, __func__, serial->parent); return; @@ -1971,14 +1977,15 @@ static void ctrl_callback(struct urb *urb) struct hso_serial *serial = urb->context; struct usb_ctrlrequest *req; int status = urb->status; + unsigned long flags; /* sanity check */ if (!serial) return; - spin_lock(&serial->serial_lock); + spin_lock_irqsave(&serial->serial_lock, flags); serial->tx_urb_used = 0; - spin_unlock(&serial->serial_lock); + spin_unlock_irqrestore(&serial->serial_lock, flags); if (status) { handle_usb_error(status, __func__, serial->parent); return; @@ -1994,9 +2001,9 @@ static void ctrl_callback(struct urb *urb) (USB_DIR_IN | USB_TYPE_OPTION_VENDOR | USB_RECIP_INTERFACE)) { /* response to a read command */ serial->rx_urb_filled[0] = 1; - spin_lock(&serial->serial_lock); + spin_lock_irqsave(&serial->serial_lock, flags); put_rxbuf_data_and_resubmit_ctrl_urb(serial); - spin_unlock(&serial->serial_lock); + spin_unlock_irqrestore(&serial->serial_lock, flags); } else { hso_put_activity(serial->parent); tty_port_tty_wakeup(&serial->port); diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index f1605833c5cf..913e50bab0a2 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -587,7 +587,7 @@ static void kaweth_usb_receive(struct urb *urb) struct kaweth_device *kaweth = urb->context; struct net_device *net = kaweth->net; int status = urb->status; - + unsigned long flags; int count = urb->actual_length; int count2 = urb->transfer_buffer_length; @@ -619,12 +619,12 @@ static void kaweth_usb_receive(struct urb *urb) net->stats.rx_errors++; dev_dbg(dev, "Status was -EOVERFLOW.\n"); } - spin_lock(&kaweth->device_lock); + spin_lock_irqsave(&kaweth->device_lock, flags); if (IS_BLOCKED(kaweth->status)) { - spin_unlock(&kaweth->device_lock); + spin_unlock_irqrestore(&kaweth->device_lock, flags); return; } - spin_unlock(&kaweth->device_lock); + spin_unlock_irqrestore(&kaweth->device_lock, flags); if(status && status != -EREMOTEIO && count != 1) { dev_err(&kaweth->intf->dev, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 2e4130746c40..6f2ea84bf0b2 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1721,7 +1721,7 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev) "MAC address read from EEPROM"); } else { /* generate random MAC */ - random_ether_addr(addr); + eth_random_addr(addr); netif_dbg(dev, ifup, dev->net, "MAC address set to random addr"); } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2a58607a6aea..124211afb023 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1252,6 +1252,7 @@ static void read_bulk_callback(struct urb *urb) int status = urb->status; struct rx_agg *agg; struct r8152 *tp; + unsigned long flags; agg = urb->context; if (!agg) @@ -1281,9 +1282,9 @@ static void read_bulk_callback(struct urb *urb) if (urb->actual_length < ETH_ZLEN) break; - spin_lock(&tp->rx_lock); + spin_lock_irqsave(&tp->rx_lock, flags); list_add_tail(&agg->list, &tp->rx_done); - spin_unlock(&tp->rx_lock); + spin_unlock_irqrestore(&tp->rx_lock, flags); napi_schedule(&tp->napi); return; case -ESHUTDOWN: @@ -1311,6 +1312,7 @@ static void write_bulk_callback(struct urb *urb) struct net_device *netdev; struct tx_agg *agg; struct r8152 *tp; + unsigned long flags; int status = urb->status; agg = urb->context; @@ -1332,9 +1334,9 @@ static void write_bulk_callback(struct urb *urb) stats->tx_bytes += agg->skb_len; } - spin_lock(&tp->tx_lock); + spin_lock_irqsave(&tp->tx_lock, flags); list_add_tail(&agg->list, &tp->tx_free); - spin_unlock(&tp->tx_lock); + spin_unlock_irqrestore(&tp->tx_lock, flags); usb_autopm_put_interface_async(tp->intf); @@ -1374,6 +1376,7 @@ static void intr_callback(struct urb *urb) case -ECONNRESET: /* unlink */ case -ESHUTDOWN: netif_device_detach(tp->netdev); + /* fall through */ case -ENOENT: case -EPROTO: netif_info(tp, intr, tp->netdev, @@ -2739,6 +2742,7 @@ static void r8153b_ups_en(struct r8152 *tp, bool enable) r8152_mdio_write(tp, MII_BMCR, data); data = r8153_phy_status(tp, PHY_STAT_LAN_ON); + /* fall through */ default: if (data != PHY_STAT_LAN_ON) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 5f565bd574da..0e81d4c441d9 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -391,6 +391,7 @@ static void read_bulk_callback(struct urb *urb) u16 rx_stat; int status = urb->status; int result; + unsigned long flags; dev = urb->context; if (!dev) @@ -432,9 +433,9 @@ static void read_bulk_callback(struct urb *urb) netdev->stats.rx_packets++; netdev->stats.rx_bytes += pkt_len; - spin_lock(&dev->rx_pool_lock); + spin_lock_irqsave(&dev->rx_pool_lock, flags); skb = pull_skb(dev); - spin_unlock(&dev->rx_pool_lock); + spin_unlock_irqrestore(&dev->rx_pool_lock, flags); if (!skb) goto resched; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f6bb1d54d4bd..601ae176808d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -568,11 +568,12 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, return vh; } -static struct sk_buff **vxlan_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *vxlan_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; int flush = 1; @@ -607,7 +608,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -2119,7 +2120,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; - if (info->options_len) + if (info->options_len && + info->key.tun_flags & TUNNEL_VXLAN_OPT) md = ip_tunnel_info_opts(info); ttl = info->key.ttl; tos = info->key.tos; diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index e60bea4604e4..1665066f4e24 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -496,7 +496,7 @@ static void ath9k_hw_init_macaddr(struct ath_hw *ah) ath_err(common, "eeprom contains invalid mac address: %pM\n", common->macaddr); - random_ether_addr(common->macaddr); + eth_random_addr(common->macaddr); ath_err(common, "random mac address will be used: %pM\n", common->macaddr); diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index 39c817eddd78..31bd6f714052 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -1904,7 +1904,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv) reject_agg, ctrl_agg_size, agg_size); rtlpriv->hw->max_rx_aggregation_subframes = - (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF); + (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT); } EXPORT_SYMBOL(rtl_rx_ampdu_apply); diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 474c988d2e95..d137c480db46 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -43,7 +43,7 @@ config PTP_1588_CLOCK_DTE config PTP_1588_CLOCK_QORIQ tristate "Freescale QorIQ 1588 timer as PTP clock" - depends on GIANFAR + depends on GIANFAR || FSL_DPAA_ETH depends on PTP_1588_CLOCK default y help diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index e8652c148c52..a14c317b5a38 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -39,11 +39,12 @@ /* Caller must hold qoriq_ptp->lock. */ static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; u64 ns; u32 lo, hi; - lo = qoriq_read(&qoriq_ptp->regs->tmr_cnt_l); - hi = qoriq_read(&qoriq_ptp->regs->tmr_cnt_h); + lo = qoriq_read(®s->ctrl_regs->tmr_cnt_l); + hi = qoriq_read(®s->ctrl_regs->tmr_cnt_h); ns = ((u64) hi) << 32; ns |= lo; return ns; @@ -52,16 +53,18 @@ static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp) /* Caller must hold qoriq_ptp->lock. */ static void tmr_cnt_write(struct qoriq_ptp *qoriq_ptp, u64 ns) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; u32 hi = ns >> 32; u32 lo = ns & 0xffffffff; - qoriq_write(&qoriq_ptp->regs->tmr_cnt_l, lo); - qoriq_write(&qoriq_ptp->regs->tmr_cnt_h, hi); + qoriq_write(®s->ctrl_regs->tmr_cnt_l, lo); + qoriq_write(®s->ctrl_regs->tmr_cnt_h, hi); } /* Caller must hold qoriq_ptp->lock. */ static void set_alarm(struct qoriq_ptp *qoriq_ptp) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; u64 ns; u32 lo, hi; @@ -70,16 +73,18 @@ static void set_alarm(struct qoriq_ptp *qoriq_ptp) ns -= qoriq_ptp->tclk_period; hi = ns >> 32; lo = ns & 0xffffffff; - qoriq_write(&qoriq_ptp->regs->tmr_alarm1_l, lo); - qoriq_write(&qoriq_ptp->regs->tmr_alarm1_h, hi); + qoriq_write(®s->alarm_regs->tmr_alarm1_l, lo); + qoriq_write(®s->alarm_regs->tmr_alarm1_h, hi); } /* Caller must hold qoriq_ptp->lock. */ static void set_fipers(struct qoriq_ptp *qoriq_ptp) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + set_alarm(qoriq_ptp); - qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); - qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); + qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); + qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); } /* @@ -89,16 +94,17 @@ static void set_fipers(struct qoriq_ptp *qoriq_ptp) static irqreturn_t isr(int irq, void *priv) { struct qoriq_ptp *qoriq_ptp = priv; + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; struct ptp_clock_event event; u64 ns; u32 ack = 0, lo, hi, mask, val; - val = qoriq_read(&qoriq_ptp->regs->tmr_tevent); + val = qoriq_read(®s->ctrl_regs->tmr_tevent); if (val & ETS1) { ack |= ETS1; - hi = qoriq_read(&qoriq_ptp->regs->tmr_etts1_h); - lo = qoriq_read(&qoriq_ptp->regs->tmr_etts1_l); + hi = qoriq_read(®s->etts_regs->tmr_etts1_h); + lo = qoriq_read(®s->etts_regs->tmr_etts1_l); event.type = PTP_CLOCK_EXTTS; event.index = 0; event.timestamp = ((u64) hi) << 32; @@ -108,8 +114,8 @@ static irqreturn_t isr(int irq, void *priv) if (val & ETS2) { ack |= ETS2; - hi = qoriq_read(&qoriq_ptp->regs->tmr_etts2_h); - lo = qoriq_read(&qoriq_ptp->regs->tmr_etts2_l); + hi = qoriq_read(®s->etts_regs->tmr_etts2_h); + lo = qoriq_read(®s->etts_regs->tmr_etts2_l); event.type = PTP_CLOCK_EXTTS; event.index = 1; event.timestamp = ((u64) hi) << 32; @@ -130,16 +136,16 @@ static irqreturn_t isr(int irq, void *priv) hi = ns >> 32; lo = ns & 0xffffffff; spin_lock(&qoriq_ptp->lock); - qoriq_write(&qoriq_ptp->regs->tmr_alarm2_l, lo); - qoriq_write(&qoriq_ptp->regs->tmr_alarm2_h, hi); + qoriq_write(®s->alarm_regs->tmr_alarm2_l, lo); + qoriq_write(®s->alarm_regs->tmr_alarm2_h, hi); spin_unlock(&qoriq_ptp->lock); qoriq_ptp->alarm_value = ns; } else { - qoriq_write(&qoriq_ptp->regs->tmr_tevent, ALM2); + qoriq_write(®s->ctrl_regs->tmr_tevent, ALM2); spin_lock(&qoriq_ptp->lock); - mask = qoriq_read(&qoriq_ptp->regs->tmr_temask); + mask = qoriq_read(®s->ctrl_regs->tmr_temask); mask &= ~ALM2EN; - qoriq_write(&qoriq_ptp->regs->tmr_temask, mask); + qoriq_write(®s->ctrl_regs->tmr_temask, mask); spin_unlock(&qoriq_ptp->lock); qoriq_ptp->alarm_value = 0; qoriq_ptp->alarm_interval = 0; @@ -153,7 +159,7 @@ static irqreturn_t isr(int irq, void *priv) } if (ack) { - qoriq_write(&qoriq_ptp->regs->tmr_tevent, ack); + qoriq_write(®s->ctrl_regs->tmr_tevent, ack); return IRQ_HANDLED; } else return IRQ_NONE; @@ -169,6 +175,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) u32 tmr_add; int neg_adj = 0; struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; if (scaled_ppm < 0) { neg_adj = 1; @@ -186,7 +193,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff; - qoriq_write(&qoriq_ptp->regs->tmr_add, tmr_add); + qoriq_write(®s->ctrl_regs->tmr_add, tmr_add); return 0; } @@ -250,6 +257,7 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; unsigned long flags; u32 bit, mask; @@ -266,23 +274,23 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, return -EINVAL; } spin_lock_irqsave(&qoriq_ptp->lock, flags); - mask = qoriq_read(&qoriq_ptp->regs->tmr_temask); + mask = qoriq_read(®s->ctrl_regs->tmr_temask); if (on) mask |= bit; else mask &= ~bit; - qoriq_write(&qoriq_ptp->regs->tmr_temask, mask); + qoriq_write(®s->ctrl_regs->tmr_temask, mask); spin_unlock_irqrestore(&qoriq_ptp->lock, flags); return 0; case PTP_CLK_REQ_PPS: spin_lock_irqsave(&qoriq_ptp->lock, flags); - mask = qoriq_read(&qoriq_ptp->regs->tmr_temask); + mask = qoriq_read(®s->ctrl_regs->tmr_temask); if (on) mask |= PP1EN; else mask &= ~PP1EN; - qoriq_write(&qoriq_ptp->regs->tmr_temask, mask); + qoriq_write(®s->ctrl_regs->tmr_temask, mask); spin_unlock_irqrestore(&qoriq_ptp->lock, flags); return 0; @@ -313,10 +321,12 @@ static int qoriq_ptp_probe(struct platform_device *dev) { struct device_node *node = dev->dev.of_node; struct qoriq_ptp *qoriq_ptp; + struct qoriq_ptp_registers *regs; struct timespec64 now; int err = -ENOMEM; u32 tmr_ctrl; unsigned long flags; + void __iomem *base; qoriq_ptp = kzalloc(sizeof(*qoriq_ptp), GFP_KERNEL); if (!qoriq_ptp) @@ -351,7 +361,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) pr_err("irq not in device tree\n"); goto no_node; } - if (request_irq(qoriq_ptp->irq, isr, 0, DRIVER, qoriq_ptp)) { + if (request_irq(qoriq_ptp->irq, isr, IRQF_SHARED, DRIVER, qoriq_ptp)) { pr_err("request_irq failed\n"); goto no_node; } @@ -368,12 +378,27 @@ static int qoriq_ptp_probe(struct platform_device *dev) spin_lock_init(&qoriq_ptp->lock); - qoriq_ptp->regs = ioremap(qoriq_ptp->rsrc->start, - resource_size(qoriq_ptp->rsrc)); - if (!qoriq_ptp->regs) { + base = ioremap(qoriq_ptp->rsrc->start, + resource_size(qoriq_ptp->rsrc)); + if (!base) { pr_err("ioremap ptp registers failed\n"); goto no_ioremap; } + + qoriq_ptp->base = base; + + if (of_device_is_compatible(node, "fsl,fman-ptp-timer")) { + qoriq_ptp->regs.ctrl_regs = base + FMAN_CTRL_REGS_OFFSET; + qoriq_ptp->regs.alarm_regs = base + FMAN_ALARM_REGS_OFFSET; + qoriq_ptp->regs.fiper_regs = base + FMAN_FIPER_REGS_OFFSET; + qoriq_ptp->regs.etts_regs = base + FMAN_ETTS_REGS_OFFSET; + } else { + qoriq_ptp->regs.ctrl_regs = base + CTRL_REGS_OFFSET; + qoriq_ptp->regs.alarm_regs = base + ALARM_REGS_OFFSET; + qoriq_ptp->regs.fiper_regs = base + FIPER_REGS_OFFSET; + qoriq_ptp->regs.etts_regs = base + ETTS_REGS_OFFSET; + } + ktime_get_real_ts64(&now); ptp_qoriq_settime(&qoriq_ptp->caps, &now); @@ -383,13 +408,14 @@ static int qoriq_ptp_probe(struct platform_device *dev) spin_lock_irqsave(&qoriq_ptp->lock, flags); - qoriq_write(&qoriq_ptp->regs->tmr_ctrl, tmr_ctrl); - qoriq_write(&qoriq_ptp->regs->tmr_add, qoriq_ptp->tmr_add); - qoriq_write(&qoriq_ptp->regs->tmr_prsc, qoriq_ptp->tmr_prsc); - qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); - qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); + regs = &qoriq_ptp->regs; + qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl); + qoriq_write(®s->ctrl_regs->tmr_add, qoriq_ptp->tmr_add); + qoriq_write(®s->ctrl_regs->tmr_prsc, qoriq_ptp->tmr_prsc); + qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); + qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); set_alarm(qoriq_ptp); - qoriq_write(&qoriq_ptp->regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD); + qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD); spin_unlock_irqrestore(&qoriq_ptp->lock, flags); @@ -405,7 +431,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) return 0; no_clock: - iounmap(qoriq_ptp->regs); + iounmap(qoriq_ptp->base); no_ioremap: release_resource(qoriq_ptp->rsrc); no_resource: @@ -419,12 +445,13 @@ no_memory: static int qoriq_ptp_remove(struct platform_device *dev) { struct qoriq_ptp *qoriq_ptp = platform_get_drvdata(dev); + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; - qoriq_write(&qoriq_ptp->regs->tmr_temask, 0); - qoriq_write(&qoriq_ptp->regs->tmr_ctrl, 0); + qoriq_write(®s->ctrl_regs->tmr_temask, 0); + qoriq_write(®s->ctrl_regs->tmr_ctrl, 0); ptp_clock_unregister(qoriq_ptp->clock); - iounmap(qoriq_ptp->regs); + iounmap(qoriq_ptp->base); release_resource(qoriq_ptp->rsrc); free_irq(qoriq_ptp->irq, qoriq_ptp); kfree(qoriq_ptp); @@ -434,6 +461,7 @@ static int qoriq_ptp_remove(struct platform_device *dev) static const struct of_device_id match_table[] = { { .compatible = "fsl,etsec-ptp" }, + { .compatible = "fsl,fman-ptp-timer" }, {}, }; MODULE_DEVICE_TABLE(of, match_table); diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig index c7e484f70654..7c5a25ddf832 100644 --- a/drivers/s390/net/Kconfig +++ b/drivers/s390/net/Kconfig @@ -95,4 +95,14 @@ config CCWGROUP tristate default (LCS || CTCM || QETH) +config ISM + tristate "Support for ISM vPCI Adapter" + depends on PCI && SMC + default n + help + Select this option if you want to use the Internal Shared Memory + vPCI Adapter. + + To compile as a module choose M. The module name is ism. + If unsure, choose N. endmenu diff --git a/drivers/s390/net/Makefile b/drivers/s390/net/Makefile index 513b7ae64980..f2d6bbe57a6f 100644 --- a/drivers/s390/net/Makefile +++ b/drivers/s390/net/Makefile @@ -15,3 +15,6 @@ qeth_l2-y += qeth_l2_main.o qeth_l2_sys.o obj-$(CONFIG_QETH_L2) += qeth_l2.o qeth_l3-y += qeth_l3_main.o qeth_l3_sys.o obj-$(CONFIG_QETH_L3) += qeth_l3.o + +ism-y := ism_drv.o +obj-$(CONFIG_ISM) += ism.o diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h new file mode 100644 index 000000000000..0aab90817326 --- /dev/null +++ b/drivers/s390/net/ism.h @@ -0,0 +1,221 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef S390_ISM_H +#define S390_ISM_H + +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <net/smc.h> + +#define UTIL_STR_LEN 16 + +/* + * Do not use the first word of the DMB bits to ensure 8 byte aligned access. + */ +#define ISM_DMB_WORD_OFFSET 1 +#define ISM_DMB_BIT_OFFSET (ISM_DMB_WORD_OFFSET * 32) +#define ISM_NR_DMBS 1920 + +#define ISM_REG_SBA 0x1 +#define ISM_REG_IEQ 0x2 +#define ISM_READ_GID 0x3 +#define ISM_ADD_VLAN_ID 0x4 +#define ISM_DEL_VLAN_ID 0x5 +#define ISM_SET_VLAN 0x6 +#define ISM_RESET_VLAN 0x7 +#define ISM_QUERY_INFO 0x8 +#define ISM_QUERY_RGID 0x9 +#define ISM_REG_DMB 0xA +#define ISM_UNREG_DMB 0xB +#define ISM_SIGNAL_IEQ 0xE +#define ISM_UNREG_SBA 0x11 +#define ISM_UNREG_IEQ 0x12 + +#define ISM_ERROR 0xFFFF + +struct ism_req_hdr { + u32 cmd; + u16 : 16; + u16 len; +}; + +struct ism_resp_hdr { + u32 cmd; + u16 ret; + u16 len; +}; + +union ism_reg_sba { + struct { + struct ism_req_hdr hdr; + u64 sba; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(16); + +union ism_reg_ieq { + struct { + struct ism_req_hdr hdr; + u64 ieq; + u64 len; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(16); + +union ism_read_gid { + struct { + struct ism_req_hdr hdr; + } request; + struct { + struct ism_resp_hdr hdr; + u64 gid; + } response; +} __aligned(16); + +union ism_qi { + struct { + struct ism_req_hdr hdr; + } request; + struct { + struct ism_resp_hdr hdr; + u32 version; + u32 max_len; + u64 ism_state; + u64 my_gid; + u64 sba; + u64 ieq; + u32 ieq_len; + u32 : 32; + u32 dmbs_owned; + u32 dmbs_used; + u32 vlan_required; + u32 vlan_nr_ids; + u16 vlan_id[64]; + } response; +} __aligned(64); + +union ism_query_rgid { + struct { + struct ism_req_hdr hdr; + u64 rgid; + u32 vlan_valid; + u32 vlan_id; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(16); + +union ism_reg_dmb { + struct { + struct ism_req_hdr hdr; + u64 dmb; + u32 dmb_len; + u32 sba_idx; + u32 vlan_valid; + u32 vlan_id; + u64 rgid; + } request; + struct { + struct ism_resp_hdr hdr; + u64 dmb_tok; + } response; +} __aligned(32); + +union ism_sig_ieq { + struct { + struct ism_req_hdr hdr; + u64 rgid; + u32 trigger_irq; + u32 event_code; + u64 info; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(32); + +union ism_unreg_dmb { + struct { + struct ism_req_hdr hdr; + u64 dmb_tok; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(16); + +union ism_cmd_simple { + struct { + struct ism_req_hdr hdr; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(8); + +union ism_set_vlan_id { + struct { + struct ism_req_hdr hdr; + u64 vlan_id; + } request; + struct { + struct ism_resp_hdr hdr; + } response; +} __aligned(16); + +struct ism_eq_header { + u64 idx; + u64 ieq_len; + u64 entry_len; + u64 : 64; +}; + +struct ism_eq { + struct ism_eq_header header; + struct smcd_event entry[15]; +}; + +struct ism_sba { + u32 s : 1; /* summary bit */ + u32 e : 1; /* event bit */ + u32 : 30; + u32 dmb_bits[ISM_NR_DMBS / 32]; + u32 reserved[3]; + u16 dmbe_mask[ISM_NR_DMBS]; +}; + +struct ism_dev { + spinlock_t lock; + struct pci_dev *pdev; + struct smcd_dev *smcd; + + void __iomem *ctl; + + struct ism_sba *sba; + dma_addr_t sba_dma_addr; + DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS); + + struct ism_eq *ieq; + dma_addr_t ieq_dma_addr; + + int ieq_idx; +}; + +#define ISM_CREATE_REQ(dmb, idx, sf, offset) \ + ((dmb) | (idx) << 24 | (sf) << 23 | (offset)) + +static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data, + unsigned int size) +{ + struct zpci_dev *zdev = to_zpci(ism->pdev); + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size); + + return zpci_write_block(req, data, dmb_req); +} + +#endif /* S390_ISM_H */ diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c new file mode 100644 index 000000000000..c0631895154e --- /dev/null +++ b/drivers/s390/net/ism_drv.c @@ -0,0 +1,623 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ISM driver for s390. + * + * Copyright IBM Corp. 2018 + */ +#define KMSG_COMPONENT "ism" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/device.h> +#include <linux/pci.h> +#include <linux/err.h> +#include <net/smc.h> + +#include <asm/debug.h> + +#include "ism.h" + +MODULE_DESCRIPTION("ISM driver for s390"); +MODULE_LICENSE("GPL"); + +#define PCI_DEVICE_ID_IBM_ISM 0x04ED +#define DRV_NAME "ism" + +static const struct pci_device_id ism_device_table[] = { + { PCI_VDEVICE(IBM, PCI_DEVICE_ID_IBM_ISM), 0 }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, ism_device_table); + +static debug_info_t *ism_debug_info; + +static int ism_cmd(struct ism_dev *ism, void *cmd) +{ + struct ism_req_hdr *req = cmd; + struct ism_resp_hdr *resp = cmd; + + memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req)); + memcpy_toio(ism->ctl, req, sizeof(*req)); + + WRITE_ONCE(resp->ret, ISM_ERROR); + + memcpy_fromio(resp, ism->ctl, sizeof(*resp)); + if (resp->ret) { + debug_text_event(ism_debug_info, 0, "cmd failure"); + debug_event(ism_debug_info, 0, resp, sizeof(*resp)); + goto out; + } + memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp), + resp->len - sizeof(*resp)); +out: + return resp->ret; +} + +static int ism_cmd_simple(struct ism_dev *ism, u32 cmd_code) +{ + union ism_cmd_simple cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = cmd_code; + cmd.request.hdr.len = sizeof(cmd.request); + + return ism_cmd(ism, &cmd); +} + +static int query_info(struct ism_dev *ism) +{ + union ism_qi cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_QUERY_INFO; + cmd.request.hdr.len = sizeof(cmd.request); + + if (ism_cmd(ism, &cmd)) + goto out; + + debug_text_event(ism_debug_info, 3, "query info"); + debug_event(ism_debug_info, 3, &cmd.response, sizeof(cmd.response)); +out: + return 0; +} + +static int register_sba(struct ism_dev *ism) +{ + union ism_reg_sba cmd; + dma_addr_t dma_handle; + struct ism_sba *sba; + + sba = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE, + &dma_handle, GFP_KERNEL); + if (!sba) + return -ENOMEM; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_REG_SBA; + cmd.request.hdr.len = sizeof(cmd.request); + cmd.request.sba = dma_handle; + + if (ism_cmd(ism, &cmd)) { + dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, sba, dma_handle); + return -EIO; + } + + ism->sba = sba; + ism->sba_dma_addr = dma_handle; + + return 0; +} + +static int register_ieq(struct ism_dev *ism) +{ + union ism_reg_ieq cmd; + dma_addr_t dma_handle; + struct ism_eq *ieq; + + ieq = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE, + &dma_handle, GFP_KERNEL); + if (!ieq) + return -ENOMEM; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_REG_IEQ; + cmd.request.hdr.len = sizeof(cmd.request); + cmd.request.ieq = dma_handle; + cmd.request.len = sizeof(*ieq); + + if (ism_cmd(ism, &cmd)) { + dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ieq, dma_handle); + return -EIO; + } + + ism->ieq = ieq; + ism->ieq_idx = -1; + ism->ieq_dma_addr = dma_handle; + + return 0; +} + +static int unregister_sba(struct ism_dev *ism) +{ + if (!ism->sba) + return 0; + + if (ism_cmd_simple(ism, ISM_UNREG_SBA)) + return -EIO; + + dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, + ism->sba, ism->sba_dma_addr); + + ism->sba = NULL; + ism->sba_dma_addr = 0; + + return 0; +} + +static int unregister_ieq(struct ism_dev *ism) +{ + if (!ism->ieq) + return 0; + + if (ism_cmd_simple(ism, ISM_UNREG_IEQ)) + return -EIO; + + dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, + ism->ieq, ism->ieq_dma_addr); + + ism->ieq = NULL; + ism->ieq_dma_addr = 0; + + return 0; +} + +static int ism_read_local_gid(struct ism_dev *ism) +{ + union ism_read_gid cmd; + int ret; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_READ_GID; + cmd.request.hdr.len = sizeof(cmd.request); + + ret = ism_cmd(ism, &cmd); + if (ret) + goto out; + + ism->smcd->local_gid = cmd.response.gid; +out: + return ret; +} + +static int ism_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid, + u32 vid) +{ + struct ism_dev *ism = smcd->priv; + union ism_query_rgid cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_QUERY_RGID; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.rgid = rgid; + cmd.request.vlan_valid = vid_valid; + cmd.request.vlan_id = vid; + + return ism_cmd(ism, &cmd); +} + +static void ism_free_dmb(struct ism_dev *ism, struct smcd_dmb *dmb) +{ + clear_bit(dmb->sba_idx, ism->sba_bitmap); + dma_free_coherent(&ism->pdev->dev, dmb->dmb_len, + dmb->cpu_addr, dmb->dma_addr); +} + +static int ism_alloc_dmb(struct ism_dev *ism, struct smcd_dmb *dmb) +{ + unsigned long bit; + + if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev)) + return -EINVAL; + + if (!dmb->sba_idx) { + bit = find_next_zero_bit(ism->sba_bitmap, ISM_NR_DMBS, + ISM_DMB_BIT_OFFSET); + if (bit == ISM_NR_DMBS) + return -ENOMEM; + + dmb->sba_idx = bit; + } + if (dmb->sba_idx < ISM_DMB_BIT_OFFSET || + test_and_set_bit(dmb->sba_idx, ism->sba_bitmap)) + return -EINVAL; + + dmb->cpu_addr = dma_zalloc_coherent(&ism->pdev->dev, dmb->dmb_len, + &dmb->dma_addr, GFP_KERNEL | + __GFP_NOWARN | __GFP_NOMEMALLOC | + __GFP_COMP | __GFP_NORETRY); + if (!dmb->cpu_addr) + clear_bit(dmb->sba_idx, ism->sba_bitmap); + + return dmb->cpu_addr ? 0 : -ENOMEM; +} + +static int ism_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) +{ + struct ism_dev *ism = smcd->priv; + union ism_reg_dmb cmd; + int ret; + + ret = ism_alloc_dmb(ism, dmb); + if (ret) + goto out; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_REG_DMB; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.dmb = dmb->dma_addr; + cmd.request.dmb_len = dmb->dmb_len; + cmd.request.sba_idx = dmb->sba_idx; + cmd.request.vlan_valid = dmb->vlan_valid; + cmd.request.vlan_id = dmb->vlan_id; + cmd.request.rgid = dmb->rgid; + + ret = ism_cmd(ism, &cmd); + if (ret) { + ism_free_dmb(ism, dmb); + goto out; + } + dmb->dmb_tok = cmd.response.dmb_tok; +out: + return ret; +} + +static int ism_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) +{ + struct ism_dev *ism = smcd->priv; + union ism_unreg_dmb cmd; + int ret; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_UNREG_DMB; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.dmb_tok = dmb->dmb_tok; + + ret = ism_cmd(ism, &cmd); + if (ret) + goto out; + + ism_free_dmb(ism, dmb); +out: + return ret; +} + +static int ism_add_vlan_id(struct smcd_dev *smcd, u64 vlan_id) +{ + struct ism_dev *ism = smcd->priv; + union ism_set_vlan_id cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_ADD_VLAN_ID; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.vlan_id = vlan_id; + + return ism_cmd(ism, &cmd); +} + +static int ism_del_vlan_id(struct smcd_dev *smcd, u64 vlan_id) +{ + struct ism_dev *ism = smcd->priv; + union ism_set_vlan_id cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_DEL_VLAN_ID; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.vlan_id = vlan_id; + + return ism_cmd(ism, &cmd); +} + +static int ism_set_vlan_required(struct smcd_dev *smcd) +{ + return ism_cmd_simple(smcd->priv, ISM_SET_VLAN); +} + +static int ism_reset_vlan_required(struct smcd_dev *smcd) +{ + return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN); +} + +static int ism_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq, + u32 event_code, u64 info) +{ + struct ism_dev *ism = smcd->priv; + union ism_sig_ieq cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_SIGNAL_IEQ; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.rgid = rgid; + cmd.request.trigger_irq = trigger_irq; + cmd.request.event_code = event_code; + cmd.request.info = info; + + return ism_cmd(ism, &cmd); +} + +static unsigned int max_bytes(unsigned int start, unsigned int len, + unsigned int boundary) +{ + return min(boundary - (start & (boundary - 1)), len); +} + +static int ism_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx, + bool sf, unsigned int offset, void *data, unsigned int size) +{ + struct ism_dev *ism = smcd->priv; + unsigned int bytes; + u64 dmb_req; + int ret; + + while (size) { + bytes = max_bytes(offset, size, PAGE_SIZE); + dmb_req = ISM_CREATE_REQ(dmb_tok, idx, size == bytes ? sf : 0, + offset); + + ret = __ism_move(ism, dmb_req, data, bytes); + if (ret) + return ret; + + size -= bytes; + data += bytes; + offset += bytes; + } + + return 0; +} + +static void ism_handle_event(struct ism_dev *ism) +{ + struct smcd_event *entry; + + while ((ism->ieq_idx + 1) != READ_ONCE(ism->ieq->header.idx)) { + if (++(ism->ieq_idx) == ARRAY_SIZE(ism->ieq->entry)) + ism->ieq_idx = 0; + + entry = &ism->ieq->entry[ism->ieq_idx]; + debug_event(ism_debug_info, 2, entry, sizeof(*entry)); + smcd_handle_event(ism->smcd, entry); + } +} + +static irqreturn_t ism_handle_irq(int irq, void *data) +{ + struct ism_dev *ism = data; + unsigned long bit, end; + unsigned long *bv; + + bv = (void *) &ism->sba->dmb_bits[ISM_DMB_WORD_OFFSET]; + end = sizeof(ism->sba->dmb_bits) * BITS_PER_BYTE - ISM_DMB_BIT_OFFSET; + + spin_lock(&ism->lock); + ism->sba->s = 0; + barrier(); + for (bit = 0;;) { + bit = find_next_bit_inv(bv, end, bit); + if (bit >= end) + break; + + clear_bit_inv(bit, bv); + barrier(); + smcd_handle_irq(ism->smcd, bit + ISM_DMB_BIT_OFFSET); + ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET] = 0; + } + + if (ism->sba->e) { + ism->sba->e = 0; + barrier(); + ism_handle_event(ism); + } + spin_unlock(&ism->lock); + return IRQ_HANDLED; +} + +static const struct smcd_ops ism_ops = { + .query_remote_gid = ism_query_rgid, + .register_dmb = ism_register_dmb, + .unregister_dmb = ism_unregister_dmb, + .add_vlan_id = ism_add_vlan_id, + .del_vlan_id = ism_del_vlan_id, + .set_vlan_required = ism_set_vlan_required, + .reset_vlan_required = ism_reset_vlan_required, + .signal_event = ism_signal_ieq, + .move_data = ism_move, +}; + +static int ism_dev_init(struct ism_dev *ism) +{ + struct pci_dev *pdev = ism->pdev; + int ret; + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret <= 0) + goto out; + + ret = request_irq(pci_irq_vector(pdev, 0), ism_handle_irq, 0, + pci_name(pdev), ism); + if (ret) + goto free_vectors; + + ret = register_sba(ism); + if (ret) + goto free_irq; + + ret = register_ieq(ism); + if (ret) + goto unreg_sba; + + ret = ism_read_local_gid(ism); + if (ret) + goto unreg_ieq; + + ret = smcd_register_dev(ism->smcd); + if (ret) + goto unreg_ieq; + + query_info(ism); + return 0; + +unreg_ieq: + unregister_ieq(ism); +unreg_sba: + unregister_sba(ism); +free_irq: + free_irq(pci_irq_vector(pdev, 0), ism); +free_vectors: + pci_free_irq_vectors(pdev); +out: + return ret; +} + +static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct ism_dev *ism; + int ret; + + ism = kzalloc(sizeof(*ism), GFP_KERNEL); + if (!ism) + return -ENOMEM; + + spin_lock_init(&ism->lock); + dev_set_drvdata(&pdev->dev, ism); + ism->pdev = pdev; + + ret = pci_enable_device_mem(pdev); + if (ret) + goto err; + + ret = pci_request_mem_regions(pdev, DRV_NAME); + if (ret) + goto err_disable; + + ism->ctl = pci_iomap(pdev, 2, 0); + if (!ism->ctl) + goto err_resource; + + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret) + goto err_unmap; + + pci_set_dma_seg_boundary(pdev, SZ_1M - 1); + pci_set_dma_max_seg_size(pdev, SZ_1M); + pci_set_master(pdev); + + ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops, + ISM_NR_DMBS); + if (!ism->smcd) + goto err_unmap; + + ism->smcd->priv = ism; + ret = ism_dev_init(ism); + if (ret) + goto err_free; + + return 0; + +err_free: + smcd_free_dev(ism->smcd); +err_unmap: + pci_iounmap(pdev, ism->ctl); +err_resource: + pci_release_mem_regions(pdev); +err_disable: + pci_disable_device(pdev); +err: + kfree(ism); + dev_set_drvdata(&pdev->dev, NULL); + return ret; +} + +static void ism_dev_exit(struct ism_dev *ism) +{ + struct pci_dev *pdev = ism->pdev; + + smcd_unregister_dev(ism->smcd); + unregister_ieq(ism); + unregister_sba(ism); + free_irq(pci_irq_vector(pdev, 0), ism); + pci_free_irq_vectors(pdev); +} + +static void ism_remove(struct pci_dev *pdev) +{ + struct ism_dev *ism = dev_get_drvdata(&pdev->dev); + + ism_dev_exit(ism); + + smcd_free_dev(ism->smcd); + pci_iounmap(pdev, ism->ctl); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); + dev_set_drvdata(&pdev->dev, NULL); + kfree(ism); +} + +static int ism_suspend(struct device *dev) +{ + struct ism_dev *ism = dev_get_drvdata(dev); + + ism_dev_exit(ism); + return 0; +} + +static int ism_resume(struct device *dev) +{ + struct ism_dev *ism = dev_get_drvdata(dev); + + return ism_dev_init(ism); +} + +static SIMPLE_DEV_PM_OPS(ism_pm_ops, ism_suspend, ism_resume); + +static struct pci_driver ism_driver = { + .name = DRV_NAME, + .id_table = ism_device_table, + .probe = ism_probe, + .remove = ism_remove, + .driver = { + .pm = &ism_pm_ops, + }, +}; + +static int __init ism_init(void) +{ + int ret; + + ism_debug_info = debug_register("ism", 2, 1, 16); + if (!ism_debug_info) + return -ENODEV; + + debug_register_view(ism_debug_info, &debug_hex_ascii_view); + ret = pci_register_driver(&ism_driver); + if (ret) + debug_unregister(ism_debug_info); + + return ret; +} + +static void __exit ism_exit(void) +{ + pci_unregister_driver(&ism_driver); + debug_unregister(ism_debug_info); +} + +module_init(ism_init); +module_exit(ism_exit); diff --git a/drivers/staging/rtl8188eu/include/wifi.h b/drivers/staging/rtl8188eu/include/wifi.h index 084a246eec19..6790b7c8cfb1 100644 --- a/drivers/staging/rtl8188eu/include/wifi.h +++ b/drivers/staging/rtl8188eu/include/wifi.h @@ -575,7 +575,6 @@ enum ht_cap_ampdu_factor { * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) */ #define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 #define OP_MODE_PURE 0 diff --git a/drivers/staging/rtl8712/wifi.h b/drivers/staging/rtl8712/wifi.h index 0ed2f44ab4e9..00a4302e9983 100644 --- a/drivers/staging/rtl8712/wifi.h +++ b/drivers/staging/rtl8712/wifi.h @@ -574,7 +574,6 @@ struct ieee80211_ht_addt_info { * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) */ #define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 /* Spatial Multiplexing Power Save Modes */ diff --git a/drivers/staging/rtl8723bs/include/wifi.h b/drivers/staging/rtl8723bs/include/wifi.h index 08bc79840b23..559bf2606fb7 100644 --- a/drivers/staging/rtl8723bs/include/wifi.h +++ b/drivers/staging/rtl8723bs/include/wifi.h @@ -799,7 +799,6 @@ enum HT_CAP_AMPDU_FACTOR { * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) */ #define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 /* Spatial Multiplexing Power Save Modes */ diff --git a/drivers/staging/rtlwifi/base.c b/drivers/staging/rtlwifi/base.c index e46e47d93d7d..094827c1879a 100644 --- a/drivers/staging/rtlwifi/base.c +++ b/drivers/staging/rtlwifi/base.c @@ -1838,7 +1838,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv) reject_agg, ctrl_agg_size, agg_size); rtlpriv->hw->max_rx_aggregation_subframes = - (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF); + (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT); } /********************************************************* diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index bf53d893ad02..57f20a0a7794 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -115,12 +115,17 @@ extern struct cpumask __cpu_active_mask; #define cpu_active(cpu) ((cpu) == 0) #endif -/* verify cpu argument to cpumask_* operators */ -static inline unsigned int cpumask_check(unsigned int cpu) +static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS - WARN_ON_ONCE(cpu >= nr_cpumask_bits); + WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ +} + +/* verify cpu argument to cpumask_* operators */ +static inline unsigned int cpumask_check(unsigned int cpu) +{ + cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; } diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 79563840c295..572e11bb8696 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -59,8 +59,7 @@ struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) -struct sk_buff **eth_gro_receive(struct sk_buff **head, - struct sk_buff *skb); +struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index b462d9ea8007..dc3dac40f069 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -11,9 +11,8 @@ /* * qoriq ptp registers - * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010 */ -struct qoriq_ptp_registers { +struct ctrl_regs { u32 tmr_ctrl; /* Timer control register */ u32 tmr_tevent; /* Timestamp event register */ u32 tmr_temask; /* Timer event mask register */ @@ -28,22 +27,47 @@ struct qoriq_ptp_registers { u8 res1[4]; u32 tmroff_h; /* Timer offset high */ u32 tmroff_l; /* Timer offset low */ - u8 res2[8]; +}; + +struct alarm_regs { u32 tmr_alarm1_h; /* Timer alarm 1 high register */ u32 tmr_alarm1_l; /* Timer alarm 1 high register */ u32 tmr_alarm2_h; /* Timer alarm 2 high register */ u32 tmr_alarm2_l; /* Timer alarm 2 high register */ - u8 res3[48]; +}; + +struct fiper_regs { u32 tmr_fiper1; /* Timer fixed period interval */ u32 tmr_fiper2; /* Timer fixed period interval */ u32 tmr_fiper3; /* Timer fixed period interval */ - u8 res4[20]; +}; + +struct etts_regs { u32 tmr_etts1_h; /* Timestamp of general purpose external trigger */ u32 tmr_etts1_l; /* Timestamp of general purpose external trigger */ u32 tmr_etts2_h; /* Timestamp of general purpose external trigger */ u32 tmr_etts2_l; /* Timestamp of general purpose external trigger */ }; +struct qoriq_ptp_registers { + struct ctrl_regs __iomem *ctrl_regs; + struct alarm_regs __iomem *alarm_regs; + struct fiper_regs __iomem *fiper_regs; + struct etts_regs __iomem *etts_regs; +}; + +/* Offset definitions for the four register groups */ +#define CTRL_REGS_OFFSET 0x0 +#define ALARM_REGS_OFFSET 0x40 +#define FIPER_REGS_OFFSET 0x80 +#define ETTS_REGS_OFFSET 0xa0 + +#define FMAN_CTRL_REGS_OFFSET 0x80 +#define FMAN_ALARM_REGS_OFFSET 0xb8 +#define FMAN_FIPER_REGS_OFFSET 0xd0 +#define FMAN_ETTS_REGS_OFFSET 0xe0 + + /* Bit definitions for the TMR_CTRL register */ #define ALM1P (1<<31) /* Alarm1 output polarity */ #define ALM2P (1<<30) /* Alarm2 output polarity */ @@ -105,10 +129,10 @@ struct qoriq_ptp_registers { #define DRIVER "ptp_qoriq" #define DEFAULT_CKSEL 1 #define N_EXT_TS 2 -#define REG_SIZE sizeof(struct qoriq_ptp_registers) struct qoriq_ptp { - struct qoriq_ptp_registers __iomem *regs; + void __iomem *base; + struct qoriq_ptp_registers regs; spinlock_t lock; /* protects regs */ struct ptp_clock *clock; struct ptp_clock_info caps; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8fe7e4306816..9c03a7d5e400 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1433,11 +1433,13 @@ struct ieee80211_ht_operation { #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 /* - * A-PMDU buffer sizes - * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) + * A-MPDU buffer sizes + * According to HT size varies from 8 to 64 frames + * HE adds the ability to have up to 256 frames. */ -#define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 +#define IEEE80211_MIN_AMPDU_BUF 0x8 +#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 +#define IEEE80211_MAX_AMPDU_BUF 0x100 /* Spatial Multiplexing Power Save Modes (for capability) */ @@ -1539,6 +1541,106 @@ struct ieee80211_vht_operation { __le16 basic_mcs_set; } __packed; +/** + * struct ieee80211_he_cap_elem - HE capabilities element + * + * This structure is the "HE capabilities element" fixed fields as + * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + */ +struct ieee80211_he_cap_elem { + u8 mac_cap_info[5]; + u8 phy_cap_info[9]; +} __packed; + +#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 + +/** + * enum ieee80211_he_mcs_support - HE MCS support definitions + * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported + * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the rx_mcs_* + * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_he_mcs_support { + IEEE80211_HE_MCS_SUPPORT_0_7 = 0, + IEEE80211_HE_MCS_SUPPORT_0_9 = 1, + IEEE80211_HE_MCS_SUPPORT_0_11 = 2, + IEEE80211_HE_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field + * + * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field + * described in P802.11ax_D2.0 section 9.4.2.237.4 + * + * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + */ +struct ieee80211_he_mcs_nss_supp { + __le16 rx_mcs_80; + __le16 tx_mcs_80; + __le16 rx_mcs_160; + __le16 tx_mcs_160; + __le16 rx_mcs_80p80; + __le16 tx_mcs_80p80; +} __packed; + +/** + * struct ieee80211_he_operation - HE capabilities element + * + * This structure is the "HE operation element" fields as + * described in P802.11ax_D2.0 section 9.4.2.238 + */ +struct ieee80211_he_operation { + __le32 he_oper_params; + __le16 he_mcs_nss_set; + /* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */ + u8 optional[0]; +} __packed; + +/** + * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * + * This structure is the "MU AC Parameter Record" fields as + * described in P802.11ax_D2.0 section 9.4.2.240 + */ +struct ieee80211_he_mu_edca_param_ac_rec { + u8 aifsn; + u8 ecw_min_max; + u8 mu_edca_timer; +} __packed; + +/** + * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * + * This structure is the "MU EDCA Parameter Set element" fields as + * described in P802.11ax_D2.0 section 9.4.2.240 + */ +struct ieee80211_mu_edca_param_set { + u8 mu_qos_info; + struct ieee80211_he_mu_edca_param_ac_rec ac_be; + struct ieee80211_he_mu_edca_param_ac_rec ac_bk; + struct ieee80211_he_mu_edca_param_ac_rec ac_vi; + struct ieee80211_he_mu_edca_param_ac_rec ac_vo; +} __packed; /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 @@ -1577,6 +1679,328 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +/* 802.11ax HE MAC capabilities */ +#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 +#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 +#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 + +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 + +/* Link adaptation is split between byte HE_MAC_CAP1 and + * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE + * in which case the following values apply: + * 0 = No feedback. + * 1 = reserved. + * 2 = Unsolicited feedback. + * 3 = both + */ +#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 + +#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 +#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 +#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_BSR 0x08 +#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 +#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 +#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 +#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 + +#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 +#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 +#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 + +/* The maximum length of an A-MDPU is defined by the combination of the Maximum + * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the + * same field in the HE capabilities. + */ +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 +#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 + +#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 +#define IEEE80211_HE_MAC_CAP4_QTP 0x02 +#define IEEE80211_HE_MAC_CAP4_BQR 0x04 +#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 +#define IEEE80211_HE_MAC_CAP4_OPS 0x20 +#define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 + +/* 802.11ax HE PHY capabilities */ +#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe + +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f +#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 +#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 +#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 +/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 + +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 +#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 +#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 + +/* Note that the meaning of UL MU below is different between an AP and a non-AP + * sta, where in the AP case it indicates support for Rx and in the non-AP sta + * case it indicates support for Tx. + */ +#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 +#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 + +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 +#define IEEE80211_HE_PHY_CAP3_RX_HE_MU_PPDU_FROM_NON_AP_STA 0x40 +#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 + +#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 +#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 + +/* Minimal allowed value of Max STS under 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c + +/* Minimal allowed value of Max STS above 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 + +#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 +#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 + +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 +#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB 0x04 +#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB 0x08 +#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 +#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 + +#define IEEE80211_HE_PHY_CAP7_SRP_BASED_SR 0x01 +#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR 0x02 +#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 +#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 +#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 + +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 +#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 + +/* 802.11ax HE TX/RX MCS NSS Support */ +#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 + +/* TX/RX HE MCS Support field Highest MCS subfield encoding */ +enum ieee80211_he_highest_mcs_supported_subfield_enc { + HIGHEST_MCS_SUPPORTED_MCS7 = 0, + HIGHEST_MCS_SUPPORTED_MCS8, + HIGHEST_MCS_SUPPORTED_MCS9, + HIGHEST_MCS_SUPPORTED_MCS10, + HIGHEST_MCS_SUPPORTED_MCS11, +}; + +/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ +static inline u8 +ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) +{ + u8 count = 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + count += 4; + + return count; +} + +/* 802.11ax HE PPE Thresholds */ +#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) +#define IEEE80211_PPE_THRES_NSS_POS (0) +#define IEEE80211_PPE_THRES_NSS_MASK (7) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ + (BIT(5) | BIT(6)) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) +#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) + +/* + * Calculate 802.11ax HE capabilities IE PPE field size + * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* + */ +static inline u8 +ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u8 n; + + if ((phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + return 0; + + n = hweight8(ppe_thres_hdr & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + return n; +} + +/* HE Operation defines */ +#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x0000003f +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x000001c0 +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET 6 +#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 +#define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 + +/* + * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size + * @he_oper_ie: byte data of the He Operations IE, stating from the the byte + * after the ext ID byte. It is assumed that he_oper_ie has at least + * sizeof(struct ieee80211_he_operation) bytes, checked already in + * ieee802_11_parse_elems_crc() + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_oper_size(const u8 *he_oper_ie) +{ + struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + u8 oper_len = sizeof(struct ieee80211_he_operation); + u32 he_oper_params; + + /* Make sure the input is not NULL */ + if (!he_oper_ie) + return 0; + + /* Calc required length */ + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + oper_len += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_MULTI_BSSID_AP) + oper_len++; + + /* Add the first byte (extension ID) to the total length */ + oper_len++; + + return oper_len; +} + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -1992,6 +2416,11 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, WLAN_EID_EXT_FILS_NONCE = 13, + WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14, + WLAN_EID_EXT_HE_CAPABILITY = 35, + WLAN_EID_EXT_HE_OPERATION = 36, + WLAN_EID_EXT_UORA = 37, + WLAN_EID_EXT_HE_MU_EDCA = 38, }; /* Action category code */ diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 6cc2df7f7ac9..e1c9eea6015b 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -4,7 +4,7 @@ #include <linux/spinlock.h> #include <linux/uidgid.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> #include <uapi/linux/ipc.h> #include <linux/refcount.h> diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b5630c8eb2f3..6cea726612b7 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -9,7 +9,7 @@ #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/refcount.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> struct user_namespace; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index d633f737b3c6..fd436cdd4725 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -2,7 +2,7 @@ #define __LINUX_MROUTE_BASE_H #include <linux/netdevice.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/sock.h> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3d0cc0b5cec2..64480a0f2c16 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -305,6 +305,7 @@ int __init netdev_boot_setup(char *str); /* * Structure for NAPI scheduling similar to tasklet but with weighting */ +#define GRO_HASH_BUCKETS 8 struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means @@ -322,7 +323,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct sk_buff *gro_list; + struct list_head gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; @@ -730,10 +731,15 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map __rcu *cpu_map[0]; + struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */ }; -#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + +#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) + +#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ + (_rxqs * (_tcs) * sizeof(struct xps_map *))) + #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 @@ -1909,7 +1915,8 @@ struct net_device { int watchdog_timeo; #ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_maps; + struct xps_dev_maps __rcu *xps_cpus_map; + struct xps_dev_maps __rcu *xps_rxqs_map; #endif #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; @@ -2255,10 +2262,10 @@ static inline int gro_recursion_inc_test(struct sk_buff *skb) return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; } -typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); -static inline struct sk_buff **call_gro_receive(gro_receive_t cb, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2268,12 +2275,12 @@ static inline struct sk_buff **call_gro_receive(gro_receive_t cb, return cb(head, skb); } -typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **, - struct sk_buff *); -static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2299,8 +2306,8 @@ struct packet_type { struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); - struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); + struct sk_buff *(*gro_receive)(struct list_head *head, + struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; @@ -2568,7 +2575,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { @@ -2784,13 +2791,13 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, } #ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff **pp, + struct sk_buff *pp, int flush, struct gro_remcsum *grc) { @@ -2801,12 +2808,12 @@ static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, } } #else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff **pp, + struct sk_buff *pp, int flush, struct gro_remcsum *grc) { @@ -3278,6 +3285,92 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map); + +/** + * netif_attr_test_mask - Test a CPU or Rx queue set in a mask + * @j: CPU/Rx queue index + * @mask: bitmask of all cpus/rx queues + * @nr_bits: number of bits in the bitmask + * + * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. + */ +static inline bool netif_attr_test_mask(unsigned long j, + const unsigned long *mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + return test_bit(j, mask); +} + +/** + * netif_attr_test_online - Test for online CPU/Rx queue + * @j: CPU/Rx queue index + * @online_mask: bitmask for CPUs/Rx queues that are online + * @nr_bits: number of bits in the bitmask + * + * Returns true if a CPU/Rx queue is online. + */ +static inline bool netif_attr_test_online(unsigned long j, + const unsigned long *online_mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + + if (online_mask) + return test_bit(j, online_mask); + + return (j < nr_bits); +} + +/** + * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask + * @n: CPU/Rx queue index + * @srcp: the cpumask/Rx queue mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set. + */ +static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (srcp) + return find_next_bit(srcp, nr_bits, n + 1); + + return n + 1; +} + +/** + * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p + * @n: CPU/Rx queue index + * @src1p: the first CPUs/Rx queues mask pointer + * @src2p: the second CPUs/Rx queues mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set in both. + */ +static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, + const unsigned long *src2p, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (src1p && src2p) + return find_next_and_bit(src1p, src2p, nr_bits, n + 1); + else if (src1p) + return find_next_bit(src1p, nr_bits, n + 1); + else if (src2p) + return find_next_bit(src2p, nr_bits, n + 1); + + return n + 1; +} #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index e6a0031d1b1f..8ad2487a86d5 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -66,7 +66,7 @@ struct rfkill_ops { #if defined(CONFIG_RFKILL) || defined(CONFIG_RFKILL_MODULE) /** - * rfkill_alloc - allocate rfkill structure + * rfkill_alloc - Allocate rfkill structure * @name: name of the struct -- the string is not copied internally * @parent: device that has rf switch on it * @type: type of the switch (RFKILL_TYPE_*) @@ -112,7 +112,7 @@ void rfkill_pause_polling(struct rfkill *rfkill); /** * rfkill_resume_polling(struct rfkill *rfkill) * - * Pause polling -- say transmitter is off for other reasons. + * Resume polling * NOTE: not necessary for suspend/resume -- in that case the * core stops polling anyway */ @@ -130,7 +130,7 @@ void rfkill_resume_polling(struct rfkill *rfkill); void rfkill_unregister(struct rfkill *rfkill); /** - * rfkill_destroy - free rfkill structure + * rfkill_destroy - Free rfkill structure * @rfkill: rfkill structure to be destroyed * * Destroys the rfkill structure. @@ -140,7 +140,7 @@ void rfkill_destroy(struct rfkill *rfkill); /** * rfkill_set_hw_state - Set the internal rfkill hardware block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current hardware block state to set + * @blocked: the current hardware block state to set * * rfkill drivers that get events when the hard-blocked state changes * use this function to notify the rfkill core (and through that also @@ -161,7 +161,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked); /** * rfkill_set_sw_state - Set the internal rfkill software block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current software block state to set + * @blocked: the current software block state to set * * rfkill drivers that get events when the soft-blocked state changes * (yes, some platforms directly act on input but allow changing again) @@ -183,7 +183,7 @@ bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked); /** * rfkill_init_sw_state - Initialize persistent software block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current software block state to set + * @blocked: the current software block state to set * * rfkill drivers that preserve their software block state over power off * use this function to notify the rfkill core (and through that also @@ -208,17 +208,17 @@ void rfkill_init_sw_state(struct rfkill *rfkill, bool blocked); void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); /** - * rfkill_blocked - query rfkill block + * rfkill_blocked - Query rfkill block state * * @rfkill: rfkill struct to query */ bool rfkill_blocked(struct rfkill *rfkill); /** - * rfkill_find_type - Helpper for finding rfkill type by name + * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * - * Returns enum rfkill_type that conrresponds the name. + * Returns enum rfkill_type that corresponds to the name. */ enum rfkill_type rfkill_find_type(const char *name); @@ -296,7 +296,7 @@ static inline enum rfkill_type rfkill_find_type(const char *name) const char *rfkill_get_led_trigger_name(struct rfkill *rfkill); /** - * rfkill_set_led_trigger_name -- set the LED trigger name + * rfkill_set_led_trigger_name - Set the LED trigger name * @rfkill: rfkill struct * @name: LED trigger name * diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h new file mode 100644 index 000000000000..763d613ce2c2 --- /dev/null +++ b/include/linux/rhashtable-types.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Resizable, Scalable, Concurrent Hash Table + * + * Simple structures that might be needed in include + * files. + */ + +#ifndef _LINUX_RHASHTABLE_TYPES_H +#define _LINUX_RHASHTABLE_TYPES_H + +#include <linux/atomic.h> +#include <linux/compiler.h> +#include <linux/mutex.h> +#include <linux/workqueue.h> + +struct rhash_head { + struct rhash_head __rcu *next; +}; + +struct rhlist_head { + struct rhash_head rhead; + struct rhlist_head __rcu *next; +}; + +struct bucket_table; + +/** + * struct rhashtable_compare_arg - Key for the function rhashtable_compare + * @ht: Hash table + * @key: Key to compare against + */ +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + +typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); +typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); +typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, + const void *obj); + +/** + * struct rhashtable_params - Hash table construction parameters + * @nelem_hint: Hint on number of elements, should be 75% of desired size + * @key_len: Length of key + * @key_offset: Offset of key in struct to be hashed + * @head_offset: Offset of rhash_head in struct to be hashed + * @max_size: Maximum size while expanding + * @min_size: Minimum size while shrinking + * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) + * @automatic_shrinking: Enable automatic shrinking of tables + * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) + * @obj_hashfn: Function to hash object + * @obj_cmpfn: Function to compare key with object + */ +struct rhashtable_params { + u16 nelem_hint; + u16 key_len; + u16 key_offset; + u16 head_offset; + unsigned int max_size; + u16 min_size; + bool automatic_shrinking; + u8 locks_mul; + rht_hashfn_t hashfn; + rht_obj_hashfn_t obj_hashfn; + rht_obj_cmpfn_t obj_cmpfn; +}; + +/** + * struct rhashtable - Hash table handle + * @tbl: Bucket table + * @key_len: Key length for hashfn + * @max_elems: Maximum number of elements in table + * @p: Configuration parameters + * @rhlist: True if this is an rhltable + * @run_work: Deferred worker to expand/shrink asynchronously + * @mutex: Mutex to protect current/future table swapping + * @lock: Spin lock to protect walker list + * @nelems: Number of elements in table + */ +struct rhashtable { + struct bucket_table __rcu *tbl; + unsigned int key_len; + unsigned int max_elems; + struct rhashtable_params p; + bool rhlist; + struct work_struct run_work; + struct mutex mutex; + spinlock_t lock; + atomic_t nelems; +}; + +/** + * struct rhltable - Hash table with duplicate objects in a list + * @ht: Underlying rhtable + */ +struct rhltable { + struct rhashtable ht; +}; + +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @tbl: The table that we were walking over + */ +struct rhashtable_walker { + struct list_head list; + struct bucket_table *tbl; +}; + +/** + * struct rhashtable_iter - Hash table iterator + * @ht: Table to iterate through + * @p: Current pointer + * @list: Current hash list pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhlist_head *list; + struct rhashtable_walker walker; + unsigned int slot; + unsigned int skip; + bool end_of_table; +}; + +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params); +int rhltable_init(struct rhltable *hlt, + const struct rhashtable_params *params); + +#endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 4e1f535c2034..eb7111039247 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Resizable, Scalable, Concurrent Hash Table * @@ -17,37 +18,18 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H -#include <linux/atomic.h> -#include <linux/compiler.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> #include <linux/list_nulls.h> #include <linux/workqueue.h> -#include <linux/mutex.h> #include <linux/rculist.h> +#include <linux/rhashtable-types.h> /* * The end of the chain is marked with a special nulls marks which has - * the following format: - * - * +-------+-----------------------------------------------------+-+ - * | Base | Hash |1| - * +-------+-----------------------------------------------------+-+ - * - * Base (4 bits) : Reserved to distinguish between multiple tables. - * Specified via &struct rhashtable_params.nulls_base. - * Hash (27 bits): Full hash (unmasked) of first element added to bucket - * 1 (1 bit) : Nulls marker (always set) - * - * The remaining bits of the next pointer remain unused for now. + * the least significant bit set. */ -#define RHT_BASE_BITS 4 -#define RHT_HASH_BITS 27 -#define RHT_BASE_SHIFT RHT_HASH_BITS - -/* Base bits plus 1 bit for nulls marker */ -#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) /* Maximum chain length before rehash * @@ -64,15 +46,6 @@ */ #define RHT_ELASTICITY 16u -struct rhash_head { - struct rhash_head __rcu *next; -}; - -struct rhlist_head { - struct rhash_head rhead; - struct rhlist_head __rcu *next; -}; - /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets @@ -102,132 +75,14 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -/** - * struct rhashtable_compare_arg - Key for the function rhashtable_compare - * @ht: Hash table - * @key: Key to compare against - */ -struct rhashtable_compare_arg { - struct rhashtable *ht; - const void *key; -}; - -typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); -typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, - const void *obj); - -struct rhashtable; - -/** - * struct rhashtable_params - Hash table construction parameters - * @nelem_hint: Hint on number of elements, should be 75% of desired size - * @key_len: Length of key - * @key_offset: Offset of key in struct to be hashed - * @head_offset: Offset of rhash_head in struct to be hashed - * @max_size: Maximum size while expanding - * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) - * @automatic_shrinking: Enable automatic shrinking of tables - * @nulls_base: Base value to generate nulls marker - * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) - * @obj_hashfn: Function to hash object - * @obj_cmpfn: Function to compare key with object - */ -struct rhashtable_params { - u16 nelem_hint; - u16 key_len; - u16 key_offset; - u16 head_offset; - unsigned int max_size; - u16 min_size; - bool automatic_shrinking; - u8 locks_mul; - u32 nulls_base; - rht_hashfn_t hashfn; - rht_obj_hashfn_t obj_hashfn; - rht_obj_cmpfn_t obj_cmpfn; -}; - -/** - * struct rhashtable - Hash table handle - * @tbl: Bucket table - * @key_len: Key length for hashfn - * @max_elems: Maximum number of elements in table - * @p: Configuration parameters - * @rhlist: True if this is an rhltable - * @run_work: Deferred worker to expand/shrink asynchronously - * @mutex: Mutex to protect current/future table swapping - * @lock: Spin lock to protect walker list - * @nelems: Number of elements in table - */ -struct rhashtable { - struct bucket_table __rcu *tbl; - unsigned int key_len; - unsigned int max_elems; - struct rhashtable_params p; - bool rhlist; - struct work_struct run_work; - struct mutex mutex; - spinlock_t lock; - atomic_t nelems; -}; - -/** - * struct rhltable - Hash table with duplicate objects in a list - * @ht: Underlying rhtable - */ -struct rhltable { - struct rhashtable ht; -}; - -/** - * struct rhashtable_walker - Hash table walker - * @list: List entry on list of walkers - * @tbl: The table that we were walking over - */ -struct rhashtable_walker { - struct list_head list; - struct bucket_table *tbl; -}; - -/** - * struct rhashtable_iter - Hash table iterator - * @ht: Table to iterate through - * @p: Current pointer - * @list: Current hash list pointer - * @walker: Associated rhashtable walker - * @slot: Current slot - * @skip: Number of entries to skip in slot - */ -struct rhashtable_iter { - struct rhashtable *ht; - struct rhash_head *p; - struct rhlist_head *list; - struct rhashtable_walker walker; - unsigned int slot; - unsigned int skip; - bool end_of_table; -}; - -static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) -{ - return NULLS_MARKER(ht->p.nulls_base + hash); -} - -#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ - ((ptr) = (typeof(ptr)) rht_marker(ht, hash)) +#define INIT_RHT_NULLS_HEAD(ptr) \ + ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { return ((unsigned long) ptr & 1); } -static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr) -{ - return ((unsigned long) ptr) >> 1; -} - static inline void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) { @@ -237,7 +92,7 @@ static inline void *rht_obj(const struct rhashtable *ht, static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, unsigned int hash) { - return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1); + return hash & (tbl->size - 1); } static inline unsigned int rht_key_get_hash(struct rhashtable *ht, @@ -376,11 +231,6 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, } #endif /* CONFIG_PROVE_LOCKING */ -int rhashtable_init(struct rhashtable *ht, - const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, - const struct rhashtable_params *params); - void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj); @@ -745,7 +595,7 @@ static inline void *__rhashtable_insert_fast( lock = rht_bucket_lock(tbl, hash); spin_lock_bh(lock); - if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) { + if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: spin_unlock_bh(lock); rcu_read_unlock(); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 164cdedf6012..7601838c2513 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -677,7 +677,8 @@ struct sk_buff { int ip_defrag_offset; }; }; - struct rb_node rbnode; /* used in netem & tcp stack */ + struct rb_node rbnode; /* used in netem & tcp stack */ + struct list_head list; }; struct sock *sk; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 72705eaf4b84..3dbea6610304 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -350,6 +350,7 @@ struct tcp_sock { #endif /* Receiver side RTT estimation */ + u32 rcv_rtt_last_tsecr; struct { u32 rtt_us; u32 seq; diff --git a/include/linux/udp.h b/include/linux/udp.h index ca840345571b..320d49d85484 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -74,8 +74,8 @@ struct udp_sock { void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ - struct sk_buff ** (*gro_receive)(struct sock *sk, - struct sk_buff **head, + struct sk_buff * (*gro_receive)(struct sock *sk, + struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/act_api.h b/include/net/act_api.h index 9e59ebfded62..5ff11adbe2a6 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -190,9 +190,6 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, #endif } -typedef int tc_setup_cb_t(enum tc_setup_type type, - void *type_data, void *cb_priv); - #ifdef CONFIG_NET_CLS_ACT int tc_setup_cb_egdev_register(const struct net_device *dev, tc_setup_cb_t *cb, void *cb_priv); diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index c5187438af38..9e36fda652b7 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -151,6 +151,7 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = skb->napi_id; #endif + sk_rx_queue_set(sk, skb); } /* variant used for unconnected sockets */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5fbfe61f41c6..9ba1f289c439 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -285,6 +285,41 @@ struct ieee80211_sta_vht_cap { struct ieee80211_vht_mcs_info vht_mcs; }; +#define IEEE80211_HE_PPE_THRES_MAX_LEN 25 + +/** + * struct ieee80211_sta_he_cap - STA's HE capabilities + * + * This structure describes most essential parameters needed + * to describe 802.11ax HE capabilities for a STA. + * + * @has_he: true iff HE data is valid. + * @he_cap_elem: Fixed portion of the HE capabilities element. + * @he_mcs_nss_supp: The supported NSS/MCS combinations. + * @ppe_thres: Holds the PPE Thresholds data. + */ +struct ieee80211_sta_he_cap { + bool has_he; + struct ieee80211_he_cap_elem he_cap_elem; + struct ieee80211_he_mcs_nss_supp he_mcs_nss_supp; + u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN]; +}; + +/** + * struct ieee80211_sband_iftype_data + * + * This structure encapsulates sband data that is relevant for the + * interface types defined in @types_mask. Each type in the + * @types_mask must be unique across all instances of iftype_data. + * + * @types_mask: interface types mask + * @he_cap: holds the HE capabilities + */ +struct ieee80211_sband_iftype_data { + u16 types_mask; + struct ieee80211_sta_he_cap he_cap; +}; + /** * struct ieee80211_supported_band - frequency band definition * @@ -301,6 +336,11 @@ struct ieee80211_sta_vht_cap { * @n_bitrates: Number of bitrates in @bitrates * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band + * @n_iftype_data: number of iftype data entries + * @iftype_data: interface type data entries. Note that the bits in + * @types_mask inside this structure cannot overlap (i.e. only + * one occurrence of each type is allowed across all instances of + * iftype_data). */ struct ieee80211_supported_band { struct ieee80211_channel *channels; @@ -310,9 +350,56 @@ struct ieee80211_supported_band { int n_bitrates; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; + u16 n_iftype_data; + const struct ieee80211_sband_iftype_data *iftype_data; }; /** + * ieee80211_get_sband_iftype_data - return sband data for a given iftype + * @sband: the sband to search for the STA on + * @iftype: enum nl80211_iftype + * + * Return: pointer to struct ieee80211_sband_iftype_data, or NULL is none found + */ +static inline const struct ieee80211_sband_iftype_data * +ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, + u8 iftype) +{ + int i; + + if (WARN_ON(iftype >= NL80211_IFTYPE_MAX)) + return NULL; + + for (i = 0; i < sband->n_iftype_data; i++) { + const struct ieee80211_sband_iftype_data *data = + &sband->iftype_data[i]; + + if (data->types_mask & BIT(iftype)) + return data; + } + + return NULL; +} + +/** + * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA + * @sband: the sband to search for the STA on + * + * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_he_cap * +ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) +{ + const struct ieee80211_sband_iftype_data *data = + ieee80211_get_sband_iftype_data(sband, NL80211_IFTYPE_STATION); + + if (data && data->he_cap.has_he) + return &data->he_cap; + + return NULL; +} + +/** * wiphy_read_of_freq_limits - read frequency limits from device tree * * @wiphy: the wireless device to get extra limits for @@ -899,6 +986,8 @@ enum station_parameters_apply_mask { * @opmode_notif: operating mode field from Operating Mode Notification * @opmode_notif_used: information if operating mode field is used * @support_p2p_ps: information if station supports P2P PS mechanism + * @he_capa: HE capabilities of station + * @he_capa_len: the length of the HE capabilities */ struct station_parameters { const u8 *supported_rates; @@ -926,6 +1015,8 @@ struct station_parameters { u8 opmode_notif; bool opmode_notif_used; int support_p2p_ps; + const struct ieee80211_he_cap_elem *he_capa; + u8 he_capa_len; }; /** @@ -1000,12 +1091,14 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval * @RATE_INFO_FLAGS_60G: 60GHz MCS + * @RATE_INFO_FLAGS_HE_MCS: HE MCS information */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), RATE_INFO_FLAGS_VHT_MCS = BIT(1), RATE_INFO_FLAGS_SHORT_GI = BIT(2), RATE_INFO_FLAGS_60G = BIT(3), + RATE_INFO_FLAGS_HE_MCS = BIT(4), }; /** @@ -1019,6 +1112,7 @@ enum rate_info_flags { * @RATE_INFO_BW_40: 40 MHz bandwidth * @RATE_INFO_BW_80: 80 MHz bandwidth * @RATE_INFO_BW_160: 160 MHz bandwidth + * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation */ enum rate_info_bw { RATE_INFO_BW_20 = 0, @@ -1027,6 +1121,7 @@ enum rate_info_bw { RATE_INFO_BW_40, RATE_INFO_BW_80, RATE_INFO_BW_160, + RATE_INFO_BW_HE_RU, }; /** @@ -1035,10 +1130,14 @@ enum rate_info_bw { * Information about a receiving or transmitting bitrate * * @flags: bitflag of flags from &enum rate_info_flags - * @mcs: mcs index if struct describes a 802.11n bitrate + * @mcs: mcs index if struct describes an HT/VHT/HE rate * @legacy: bitrate in 100kbit/s for 802.11abg - * @nss: number of streams (VHT only) + * @nss: number of streams (VHT & HE only) * @bw: bandwidth (from &enum rate_info_bw) + * @he_gi: HE guard interval (from &enum nl80211_he_gi) + * @he_dcm: HE DCM value + * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc, + * only valid if bw is %RATE_INFO_BW_HE_RU) */ struct rate_info { u8 flags; @@ -1046,6 +1145,9 @@ struct rate_info { u16 legacy; u8 nss; u8 bw; + u8 he_gi; + u8 he_dcm; + u8 he_ru_alloc; }; /** diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 960236fb1681..feef706e1158 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -1,5 +1,6 @@ /* * Copyright (c) 2017 Intel Deutschland GmbH + * Copyright (c) 2018 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -72,6 +73,8 @@ enum ieee80211_radiotap_presence { IEEE80211_RADIOTAP_AMPDU_STATUS = 20, IEEE80211_RADIOTAP_VHT = 21, IEEE80211_RADIOTAP_TIMESTAMP = 22, + IEEE80211_RADIOTAP_HE = 23, + IEEE80211_RADIOTAP_HE_MU = 24, /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, @@ -202,6 +205,126 @@ enum ieee80211_radiotap_timestamp_flags { IEEE80211_RADIOTAP_TIMESTAMP_FLAG_ACCURACY = 0x02, }; +struct ieee80211_radiotap_he { + __le16 data1, data2, data3, data4, data5, data6; +}; + +enum ieee80211_radiotap_he_bits { + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MASK = 3, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU = 0, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_EXT_SU = 1, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MU = 2, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_TRIG = 3, + + IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN = 0x0004, + IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN = 0x0008, + IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN = 0x0010, + IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN = 0x0020, + IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN = 0x0040, + IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN = 0x0080, + IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN = 0x0100, + IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN = 0x0200, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN = 0x0400, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN = 0x0800, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN = 0x1000, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN = 0x2000, + IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN = 0x4000, + IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN = 0x0001, + IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN = 0x0002, + IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN = 0x0004, + IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN = 0x0008, + IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN = 0x0010, + IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN = 0x0020, + IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN = 0x0040, + IEEE80211_RADIOTAP_HE_DATA2_MIDAMBLE_KNOWN = 0x0080, + IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET = 0x3f00, + IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN = 0x4000, + IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR = 0x003f, + IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE = 0x0040, + IEEE80211_RADIOTAP_HE_DATA3_UL_DL = 0x0080, + IEEE80211_RADIOTAP_HE_DATA3_DATA_MCS = 0x0f00, + IEEE80211_RADIOTAP_HE_DATA3_DATA_DCM = 0x1000, + IEEE80211_RADIOTAP_HE_DATA3_CODING = 0x2000, + IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG = 0x4000, + IEEE80211_RADIOTAP_HE_DATA3_STBC = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE = 0x000f, + IEEE80211_RADIOTAP_HE_DATA4_MU_STA_ID = 0x7ff0, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1 = 0x000f, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2 = 0x00f0, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3 = 0x0f00, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4 = 0xf000, + + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC = 0x000f, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ = 0, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ = 1, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ = 2, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ = 3, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_26T = 4, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_52T = 5, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_106T = 6, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_242T = 7, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_484T = 8, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_996T = 9, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_2x996T = 10, + + IEEE80211_RADIOTAP_HE_DATA5_GI = 0x0030, + IEEE80211_RADIOTAP_HE_DATA5_GI_0_8 = 0, + IEEE80211_RADIOTAP_HE_DATA5_GI_1_6 = 1, + IEEE80211_RADIOTAP_HE_DATA5_GI_3_2 = 2, + + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE = 0x00c0, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN = 0, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_1X = 1, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X = 2, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X = 3, + IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS = 0x0700, + IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD = 0x3000, + IEEE80211_RADIOTAP_HE_DATA5_TXBF = 0x4000, + IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA6_NSTS = 0x000f, + IEEE80211_RADIOTAP_HE_DATA6_DOPPLER = 0x0010, + IEEE80211_RADIOTAP_HE_DATA6_TXOP = 0x7f00, + IEEE80211_RADIOTAP_HE_DATA6_MIDAMBLE_PDCTY = 0x8000, +}; + +struct ieee80211_radiotap_he_mu { + __le16 flags1, flags2; + u8 ru_ch1[4]; + u8 ru_ch2[4]; +}; + +enum ieee80211_radiotap_he_mu_bits { + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS = 0x000f, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN = 0x0010, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM = 0x0020, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN = 0x0040, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN = 0x0080, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN = 0x0100, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN = 0x0200, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN = 0x1000, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU = 0x2000, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN = 0x4000, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN = 0x8000, + + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW = 0x0003, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_20MHZ = 0x0000, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_40MHZ = 0x0001, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_80MHZ = 0x0002, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_160MHZ = 0x0003, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN = 0x0004, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP = 0x0008, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS = 0x00f0, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW = 0x0300, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN= 0x0400, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU = 0x0800, +}; + /** * ieee80211_get_radiotap_len - get radiotap header length */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 384b90c62c0b..3ca969cbd161 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -43,7 +43,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); -struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb); +struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb); int inet_gro_complete(struct sk_buff *skb, int nhoff); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index ed07e3786d98..f4272a29dc44 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -2,7 +2,7 @@ #ifndef __NET_FRAG_H__ #define __NET_FRAG_H__ -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> struct netns_frags { /* sysctls */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 90ff430f5e9d..b0d022ff6ea1 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -466,10 +466,12 @@ static inline void ip_tunnel_info_opts_get(void *to, } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, - const void *from, int len) + const void *from, int len, + __be16 flags) { memcpy(ip_tunnel_info_opts(info), from, len); info->options_len = len; + info->key.tun_flags |= flags; } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) @@ -511,9 +513,11 @@ static inline void ip_tunnel_info_opts_get(void *to, } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, - const void *from, int len) + const void *from, int len, + __be16 flags) { info->options_len = 0; + info->key.tun_flags |= flags; } #endif /* CONFIG_INET */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 851a5e19ae32..5790f55c241d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -23,6 +23,7 @@ #include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/codel.h> +#include <net/ieee80211_radiotap.h> #include <asm/unaligned.h> /** @@ -162,6 +163,8 @@ enum ieee80211_ac_numbers { * @txop: maximum burst time in units of 32 usecs, 0 meaning disabled * @acm: is mandatory admission control required for the access category * @uapsd: is U-APSD mode enabled for the queue + * @mu_edca: is the MU EDCA configured + * @mu_edca_param_rec: MU EDCA Parameter Record for HE */ struct ieee80211_tx_queue_params { u16 txop; @@ -170,6 +173,8 @@ struct ieee80211_tx_queue_params { u8 aifs; bool acm; bool uapsd; + bool mu_edca; + struct ieee80211_he_mu_edca_param_ac_rec mu_edca_param_rec; }; struct ieee80211_low_level_stats { @@ -463,6 +468,15 @@ struct ieee80211_mu_group_data { * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * + * @bss_color: 6-bit value to mark inter-BSS frame, if BSS supports HE + * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE + * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK + * @uora_exists: is the UORA element advertised by AP + * @ack_enabled: indicates support to receive a multi-TID that solicits either + * ACK, BACK or both + * @uora_ocw_range: UORA element's OCW Range field + * @frame_time_rts_th: HE duration RTS threshold, in units of 32us + * @he_support: does this BSS support HE * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -550,6 +564,14 @@ struct ieee80211_mu_group_data { */ struct ieee80211_bss_conf { const u8 *bssid; + u8 bss_color; + u8 htc_trig_based_pkt_ext; + bool multi_sta_back_32bit; + bool uora_exists; + bool ack_enabled; + u8 uora_ocw_range; + u16 frame_time_rts_th; + bool he_support; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -1106,6 +1128,18 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this * frame * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known + * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present + * (&struct ieee80211_radiotap_he, mac80211 will fill in + * - DATA3_DATA_MCS + * - DATA3_DATA_DCM + * - DATA3_CODING + * - DATA5_GI + * - DATA5_DATA_BW_RU_ALLOC + * - DATA6_NSTS + * - DATA3_STBC + * from the RX info data, so leave those zeroed when building this data) + * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present + * (&struct ieee80211_radiotap_he_mu) */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1134,6 +1168,8 @@ enum mac80211_rx_flags { RX_FLAG_ICV_STRIPPED = BIT(23), RX_FLAG_AMPDU_EOF_BIT = BIT(24), RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), + RX_FLAG_RADIOTAP_HE = BIT(26), + RX_FLAG_RADIOTAP_HE_MU = BIT(27), }; /** @@ -1164,6 +1200,7 @@ enum mac80211_rx_encoding { RX_ENC_LEGACY = 0, RX_ENC_HT, RX_ENC_VHT, + RX_ENC_HE, }; /** @@ -1198,6 +1235,9 @@ enum mac80211_rx_encoding { * @encoding: &enum mac80211_rx_encoding * @bw: &enum rate_info_bw * @enc_flags: uses bits from &enum mac80211_rx_encoding_flags + * @he_ru: HE RU, from &enum nl80211_he_ru_alloc + * @he_gi: HE GI, from &enum nl80211_he_gi + * @he_dcm: HE DCM value * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU @@ -1211,7 +1251,8 @@ struct ieee80211_rx_status { u32 flag; u16 freq; u8 enc_flags; - u8 encoding:2, bw:3; + u8 encoding:2, bw:3, he_ru:3; + u8 he_gi:2, he_dcm:1; u8 rate_idx; u8 nss; u8 rx_flags; @@ -1770,6 +1811,7 @@ struct ieee80211_sta_rates { * @supp_rates: Bitmap of supported rates (per band) * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities + * @he_cap: HE capabilities of this STA * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -1805,7 +1847,8 @@ struct ieee80211_sta { u16 aid; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; - u8 max_rx_aggregation_subframes; + struct ieee80211_sta_he_cap he_cap; + u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; @@ -2196,10 +2239,11 @@ enum ieee80211_hw_flags { * it shouldn't be set. * * @max_tx_aggregation_subframes: maximum number of subframes in an - * aggregate an HT driver will transmit. Though ADDBA will advertise - * a constant value of 64 as some older APs can crash if the window - * size is smaller (an example is LinkSys WRT120N with FW v1.0.07 - * build 002 Jun 18 2012). + * aggregate an HT/HE device will transmit. In HT AddBA we'll + * advertise a constant value of 64 as some older APs crash if + * the window size is smaller (an example is LinkSys WRT120N + * with FW v1.0.07 build 002 Jun 18 2012). + * For AddBA to HE capable peers this value will be used. * * @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum * of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list. @@ -2216,6 +2260,8 @@ enum ieee80211_hw_flags { * the default is _GI | _BANDWIDTH. * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values. * + * @radiotap_he: HE radiotap validity flags + * * @radiotap_timestamp: Information for the radiotap timestamp field; if the * 'units_pos' member is set to a non-negative value it must be set to * a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a @@ -2263,8 +2309,8 @@ struct ieee80211_hw { u8 max_rates; u8 max_report_rates; u8 max_rate_tries; - u8 max_rx_aggregation_subframes; - u8 max_tx_aggregation_subframes; + u16 max_rx_aggregation_subframes; + u16 max_tx_aggregation_subframes; u8 max_tx_fragments; u8 offchannel_tx_hw_queue; u8 radiotap_mcs_details; @@ -2904,7 +2950,7 @@ struct ieee80211_ampdu_params { struct ieee80211_sta *sta; u16 tid; u16 ssn; - u8 buf_size; + u16 buf_size; bool amsdu; u16 timeout; }; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ba9fa4592f2b..0e355f4a3d76 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -4,7 +4,7 @@ #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> #include <linux/rcupdate.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/dst.h> diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index e811ac07ea94..0d3920896d50 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -106,7 +106,8 @@ int nf_log_dump_udp_header(struct nf_log_buf *m, const struct sk_buff *skb, int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, u8 proto, int fragment, unsigned int offset, unsigned int logflags); -void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk); +void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk); void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index 24c78183a4c2..16a842456189 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -9,12 +9,7 @@ struct net; static inline u32 net_hash_mix(const struct net *net) { #ifdef CONFIG_NET_NS - /* - * shift this right to eliminate bits, that are - * always zeroed - */ - - return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT); + return (u32)(((unsigned long)net) >> ilog2(sizeof(*net))); #else return 0; #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 20b059574e60..6641584b27f1 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -73,11 +73,13 @@ void tcf_block_cb_incref(struct tcf_block_cb *block_cb); unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb); struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv); + void *cb_priv, + struct netlink_ext_ack *extack); int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv); -void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb); + void *cb_priv, struct netlink_ext_ack *extack); +void __tcf_block_cb_unregister(struct tcf_block *block, + struct tcf_block_cb *block_cb); void tcf_block_cb_unregister(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); @@ -166,7 +168,8 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) static inline struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, + struct netlink_ext_ack *extack) { return NULL; } @@ -174,13 +177,14 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, static inline int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, struct netlink_ext_ack *extack) { return 0; } static inline -void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb) +void __tcf_block_cb_unregister(struct tcf_block *block, + struct tcf_block_cb *block_cb) { } @@ -601,6 +605,7 @@ struct tc_block_offload { enum tc_block_command command; enum tcf_block_binder_type binder_type; struct tcf_block *block; + struct netlink_ext_ack *extack; }; struct tc_cls_common_offload { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6488daa32f82..7432100027b7 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -20,6 +20,9 @@ struct qdisc_walker; struct tcf_walker; struct module; +typedef int tc_setup_cb_t(enum tc_setup_type type, + void *type_data, void *cb_priv); + struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; @@ -256,6 +259,9 @@ struct tcf_proto_ops { bool *last, struct netlink_ext_ack *); void (*walk)(struct tcf_proto*, struct tcf_walker *arg); + int (*reoffload)(struct tcf_proto *tp, bool add, + tc_setup_cb_t *cb, void *cb_priv, + struct netlink_ext_ack *extack); void (*bind_class)(void *, u32, unsigned long); /* rtnetlink specific */ @@ -330,6 +336,21 @@ static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) block->offloadcnt--; } +static inline void +tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt, + u32 *flags, bool add) +{ + if (add) { + if (!*cnt) + tcf_block_offload_inc(block, flags); + (*cnt)++; + } else { + (*cnt)--; + if (!*cnt) + tcf_block_offload_dec(block, flags); + } +} + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index dbe1b911a24d..701a51736fa5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -48,7 +48,7 @@ #define __sctp_structs_h__ #include <linux/ktime.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> #include <linux/socket.h> /* linux/in.h needs this!! */ #include <linux/in.h> /* We get struct sockaddr_in. */ #include <linux/in6.h> /* We get struct in6_addr */ @@ -220,6 +220,7 @@ struct sctp_sock { __u32 adaptation_ind; __u32 pd_point; __u16 nodelay:1, + reuse:1, disable_fragments:1, v4mapped:1, frag_interleave:1, diff --git a/include/net/seg6.h b/include/net/seg6.h index e029e301faa5..2567941a2f32 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -18,7 +18,7 @@ #include <linux/ipv6.h> #include <net/lwtunnel.h> #include <linux/seg6.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h index 69c3a106056b..7fda469e2758 100644 --- a/include/net/seg6_hmac.h +++ b/include/net/seg6_hmac.h @@ -22,7 +22,7 @@ #include <linux/route.h> #include <net/seg6.h> #include <linux/seg6_hmac.h> -#include <linux/rhashtable.h> +#include <linux/rhashtable-types.h> #define SEG6_HMAC_MAX_DIGESTSIZE 160 #define SEG6_HMAC_RING_SIZE 256 diff --git a/include/net/smc.h b/include/net/smc.h index 8381d163fefa..9ef49f8b1002 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -11,6 +11,8 @@ #ifndef _SMC_H #define _SMC_H +#define SMC_MAX_PNETID_LEN 16 /* Max. length of PNET id */ + struct smc_hashinfo { rwlock_t lock; struct hlist_head ht; @@ -18,4 +20,67 @@ struct smc_hashinfo { int smc_hash_sk(struct sock *sk); void smc_unhash_sk(struct sock *sk); + +/* SMCD/ISM device driver interface */ +struct smcd_dmb { + u64 dmb_tok; + u64 rgid; + u32 dmb_len; + u32 sba_idx; + u32 vlan_valid; + u32 vlan_id; + void *cpu_addr; + dma_addr_t dma_addr; +}; + +#define ISM_EVENT_DMB 0 +#define ISM_EVENT_GID 1 +#define ISM_EVENT_SWR 2 + +struct smcd_event { + u32 type; + u32 code; + u64 tok; + u64 time; + u64 info; +}; + +struct smcd_dev; + +struct smcd_ops { + int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid, + u32 vid); + int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); + int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); + int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*set_vlan_required)(struct smcd_dev *dev); + int (*reset_vlan_required)(struct smcd_dev *dev); + int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq, + u32 event_code, u64 info); + int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, + bool sf, unsigned int offset, void *data, + unsigned int size); +}; + +struct smcd_dev { + const struct smcd_ops *ops; + struct device dev; + void *priv; + u64 local_gid; + struct list_head list; + spinlock_t lock; + struct smc_connection **conn; + struct list_head vlan; + struct workqueue_struct *event_wq; + u8 pnetid[SMC_MAX_PNETID_LEN]; +}; + +struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, + const struct smcd_ops *ops, int max_dmbs); +int smcd_register_dev(struct smcd_dev *smcd); +void smcd_unregister_dev(struct smcd_dev *smcd); +void smcd_free_dev(struct smcd_dev *smcd); +void smcd_handle_event(struct smcd_dev *dev, struct smcd_event *event); +void smcd_handle_irq(struct smcd_dev *dev, unsigned int bit); #endif /* _SMC_H */ diff --git a/include/net/sock.h b/include/net/sock.h index b3b75419eafe..2ed99bfa4595 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -139,6 +139,7 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings @@ -214,7 +215,10 @@ struct sock_common { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; - int skc_tx_queue_mapping; + unsigned short skc_tx_queue_mapping; +#ifdef CONFIG_XPS + unsigned short skc_rx_queue_mapping; +#endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; @@ -326,6 +330,9 @@ struct sock { #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping +#ifdef CONFIG_XPS +#define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping +#endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end @@ -1681,19 +1688,58 @@ static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { + /* sk_tx_queue_mapping accept only upto a 16-bit value */ + if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) + return; sk->sk_tx_queue_mapping = tx_queue; } +#define NO_QUEUE_MAPPING USHRT_MAX + static inline void sk_tx_queue_clear(struct sock *sk) { - sk->sk_tx_queue_mapping = -1; + sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; } static inline int sk_tx_queue_get(const struct sock *sk) { - return sk ? sk->sk_tx_queue_mapping : -1; + if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) + return sk->sk_tx_queue_mapping; + + return -1; } +static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + if (skb_rx_queue_recorded(skb)) { + u16 rx_queue = skb_get_rx_queue(skb); + + if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING)) + return; + + sk->sk_rx_queue_mapping = rx_queue; + } +#endif +} + +static inline void sk_rx_queue_clear(struct sock *sk) +{ +#ifdef CONFIG_XPS + sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; +#endif +} + +#ifdef CONFIG_XPS +static inline int sk_rx_queue_get(const struct sock *sk) +{ + if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) + return sk->sk_rx_queue_mapping; + + return -1; +} +#endif + static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk_tx_queue_clear(sk); diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 227a6f1d02f4..fac3ad4a86de 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -17,6 +17,7 @@ struct tcf_pedit { struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; + #define to_pedit(a) ((struct tcf_pedit *)a) static inline bool is_tcf_pedit(const struct tc_action *a) diff --git a/include/net/tcp.h b/include/net/tcp.h index 800582b5dd54..cce37694776e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1185,6 +1185,17 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) return tp->is_cwnd_limited; } +/* BBR congestion control needs pacing. + * Same remark for SO_MAX_PACING_RATE. + * sch_fq packet scheduler is efficiently handling pacing, + * but is not always installed/used. + * Return true if TCP stack should pace packets itself. + */ +static inline bool tcp_needs_internal_pacing(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; +} + /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window. * We do not want to add fuel to the fire, or abort too early, @@ -1778,7 +1789,7 @@ void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); -struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); int tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); diff --git a/include/net/udp.h b/include/net/udp.h index 81afdacd4fff..8482a990b0bb 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -170,8 +170,8 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport, __be16 dport); -struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup); +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, udp_lookup_t lookup); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index b95a6927c718..fe680ab6b15a 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -65,9 +65,9 @@ static inline int udp_sock_create(struct net *net, typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); -typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb); +typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, + struct list_head *head, + struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index 3176a3931107..a0c4b8a30966 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -35,6 +35,10 @@ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) +#define skmem_kind_names \ + EM(SK_MEM_SEND) \ + EMe(SK_MEM_RECV) + /* enums need to be exported to user space */ #undef EM #undef EMe @@ -44,6 +48,7 @@ family_names inet_protocol_names tcp_state_names +skmem_kind_names #undef EM #undef EMe @@ -59,6 +64,9 @@ tcp_state_names #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) +#define show_skmem_kind_names(val) \ + __print_symbolic(val, skmem_kind_names) + TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), @@ -83,9 +91,9 @@ TRACE_EVENT(sock_rcvqueue_full, TRACE_EVENT(sock_exceed_buf_limit, - TP_PROTO(struct sock *sk, struct proto *prot, long allocated), + TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), - TP_ARGS(sk, prot, allocated), + TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) @@ -93,6 +101,10 @@ TRACE_EVENT(sock_exceed_buf_limit, __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) + __field(int, sysctl_wmem) + __field(int, wmem_alloc) + __field(int, wmem_queued) + __field(int, kind) ), TP_fast_assign( @@ -101,17 +113,25 @@ TRACE_EVENT(sock_exceed_buf_limit, __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); + __entry->sysctl_wmem = sk_get_wmem0(sk, prot); + __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); + __entry->wmem_queued = sk->sk_wmem_queued; + __entry->kind = kind; ), - TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld " - "sysctl_rmem=%d rmem_alloc=%d", + TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, - __entry->rmem_alloc) + __entry->rmem_alloc, + __entry->sysctl_wmem, + __entry->wmem_alloc, + __entry->wmem_queued, + show_skmem_kind_names(__entry->kind) + ) ); TRACE_EVENT(inet_sock_set_state, diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 483b77af4eb8..db45d3e49a12 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -30,6 +30,7 @@ enum { ILA_CMD_ADD, ILA_CMD_DEL, ILA_CMD_GET, + ILA_CMD_FLUSH, __ILA_CMD_MAX, }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 27e4e441caac..7acc16f34942 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2237,6 +2237,9 @@ enum nl80211_commands { * enforced. * @NL80211_ATTR_TXQ_QUANTUM: TXQ scheduler quantum (bytes). Number of bytes * a flow is assigned on each round of the DRR scheduler. + * @NL80211_ATTR_HE_CAPABILITY: HE Capability information element (from + * association request when used with NL80211_CMD_NEW_STATION). Can be set + * only if %NL80211_STA_FLAG_WME is set. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2677,6 +2680,8 @@ enum nl80211_attrs { NL80211_ATTR_TXQ_MEMORY_LIMIT, NL80211_ATTR_TXQ_QUANTUM, + NL80211_ATTR_HE_CAPABILITY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2726,7 +2731,8 @@ enum nl80211_attrs { #define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY 24 #define NL80211_HT_CAPABILITY_LEN 26 #define NL80211_VHT_CAPABILITY_LEN 12 - +#define NL80211_HE_MIN_CAPABILITY_LEN 16 +#define NL80211_HE_MAX_CAPABILITY_LEN 51 #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 @@ -2854,6 +2860,38 @@ struct nl80211_sta_flag_update { } __attribute__((packed)); /** + * enum nl80211_he_gi - HE guard interval + * @NL80211_RATE_INFO_HE_GI_0_8: 0.8 usec + * @NL80211_RATE_INFO_HE_GI_1_6: 1.6 usec + * @NL80211_RATE_INFO_HE_GI_3_2: 3.2 usec + */ +enum nl80211_he_gi { + NL80211_RATE_INFO_HE_GI_0_8, + NL80211_RATE_INFO_HE_GI_1_6, + NL80211_RATE_INFO_HE_GI_3_2, +}; + +/** + * enum nl80211_he_ru_alloc - HE RU allocation values + * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_106: 106-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_242: 242-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_484: 484-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_996: 996-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_2x996: 2x996-tone RU allocation + */ +enum nl80211_he_ru_alloc { + NL80211_RATE_INFO_HE_RU_ALLOC_26, + NL80211_RATE_INFO_HE_RU_ALLOC_52, + NL80211_RATE_INFO_HE_RU_ALLOC_106, + NL80211_RATE_INFO_HE_RU_ALLOC_242, + NL80211_RATE_INFO_HE_RU_ALLOC_484, + NL80211_RATE_INFO_HE_RU_ALLOC_996, + NL80211_RATE_INFO_HE_RU_ALLOC_2x996, +}; + +/** * enum nl80211_rate_info - bitrate information * * These attribute types are used with %NL80211_STA_INFO_TXRATE @@ -2885,6 +2923,13 @@ struct nl80211_sta_flag_update { * @NL80211_RATE_INFO_5_MHZ_WIDTH: 5 MHz width - note that this is * a legacy rate and will be reported as the actual bitrate, i.e. * a quarter of the base (20 MHz) rate + * @NL80211_RATE_INFO_HE_MCS: HE MCS index (u8, 0-11) + * @NL80211_RATE_INFO_HE_NSS: HE NSS value (u8, 1-8) + * @NL80211_RATE_INFO_HE_GI: HE guard interval identifier + * (u8, see &enum nl80211_he_gi) + * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1) + * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then + * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc) * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ enum nl80211_rate_info { @@ -2901,6 +2946,11 @@ enum nl80211_rate_info { NL80211_RATE_INFO_160_MHZ_WIDTH, NL80211_RATE_INFO_10_MHZ_WIDTH, NL80211_RATE_INFO_5_MHZ_WIDTH, + NL80211_RATE_INFO_HE_MCS, + NL80211_RATE_INFO_HE_NSS, + NL80211_RATE_INFO_HE_GI, + NL80211_RATE_INFO_HE_DCM, + NL80211_RATE_INFO_HE_RU_ALLOC, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, @@ -3167,6 +3217,38 @@ enum nl80211_mpath_info { }; /** + * enum nl80211_band_iftype_attr - Interface type data attributes + * + * @__NL80211_BAND_IFTYPE_ATTR_INVALID: attribute number 0 is reserved + * @NL80211_BAND_IFTYPE_ATTR_IFTYPES: nested attribute containing a flag attribute + * for each interface type that supports the band data + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC: HE MAC capabilities as in HE + * capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY: HE PHY capabilities as in HE + * capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET: HE supported NSS/MCS as in HE + * capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE: HE PPE thresholds information as + * defined in HE capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently + * defined + * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use + */ +enum nl80211_band_iftype_attr { + __NL80211_BAND_IFTYPE_ATTR_INVALID, + + NL80211_BAND_IFTYPE_ATTR_IFTYPES, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, + + /* keep last */ + __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, + NL80211_BAND_IFTYPE_ATTR_MAX = __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST - 1 +}; + +/** * enum nl80211_band_attr - band attributes * @__NL80211_BAND_ATTR_INVALID: attribute number 0 is reserved * @NL80211_BAND_ATTR_FREQS: supported frequencies in this band, @@ -3181,6 +3263,8 @@ enum nl80211_mpath_info { * @NL80211_BAND_ATTR_VHT_MCS_SET: 32-byte attribute containing the MCS set as * defined in 802.11ac * @NL80211_BAND_ATTR_VHT_CAPA: VHT capabilities, as in the HT information IE + * @NL80211_BAND_ATTR_IFTYPE_DATA: nested array attribute, with each entry using + * attributes from &enum nl80211_band_iftype_attr * @NL80211_BAND_ATTR_MAX: highest band attribute currently defined * @__NL80211_BAND_ATTR_AFTER_LAST: internal use */ @@ -3196,6 +3280,7 @@ enum nl80211_band_attr { NL80211_BAND_ATTR_VHT_MCS_SET, NL80211_BAND_ATTR_VHT_CAPA, + NL80211_BAND_ATTR_IFTYPE_DATA, /* keep last */ __NL80211_BAND_ATTR_AFTER_LAST, @@ -5133,6 +5218,11 @@ enum nl80211_feature_flags { * support to nl80211. * @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate * TXQs. + * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the + * SN in probe request frames if requested by %NL80211_SCAN_FLAG_RANDOM_SN. + * @NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT: Driver/device can omit all data + * except for supported rates from the probe request content if requested + * by the %NL80211_SCAN_FLAG_MIN_PREQ_CONTENT flag. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -5167,6 +5257,8 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211, NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT, NL80211_EXT_FEATURE_TXQS, + NL80211_EXT_FEATURE_SCAN_RANDOM_SN, + NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5272,6 +5364,12 @@ enum nl80211_timeout_reason { * possible scan results. This flag hints the driver to use the best * possible scan configuration to improve the accuracy in scanning. * Latency and power use may get impacted with this flag. + * @NL80211_SCAN_FLAG_RANDOM_SN: randomize the sequence number in probe + * request frames from this scan to avoid correlation/tracking being + * possible. + * @NL80211_SCAN_FLAG_MIN_PREQ_CONTENT: minimize probe request content to + * only have supported rates and no additional capabilities (unless + * added by userspace explicitly.) */ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, @@ -5285,6 +5383,8 @@ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_SPAN = 1<<8, NL80211_SCAN_FLAG_LOW_POWER = 1<<9, NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10, + NL80211_SCAN_FLAG_RANDOM_SN = 1<<11, + NL80211_SCAN_FLAG_MIN_PREQ_CONTENT = 1<<12, }; /** diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 37b5096ae97b..bad3c03bcf43 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -539,6 +539,7 @@ enum { TCA_NETEM_LATENCY64, TCA_NETEM_JITTER64, TCA_NETEM_SLOT, + TCA_NETEM_SLOT_DIST, __TCA_NETEM_MAX, }; @@ -581,6 +582,8 @@ struct tc_netem_slot { __s64 max_delay; __s32 max_packets; __s32 max_bytes; + __s64 dist_delay; /* nsec */ + __s64 dist_jitter; /* nsec */ }; enum { diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index b64d583bf053..c02986a284db 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -100,6 +100,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_RECVNXTINFO 33 #define SCTP_DEFAULT_SNDINFO 34 #define SCTP_AUTH_DEACTIVATE_KEY 35 +#define SCTP_REUSE_PORT 36 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 0ae5d4685ba3..92be255e534c 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -35,6 +35,7 @@ enum { SMC_DIAG_CONNINFO, SMC_DIAG_LGRINFO, SMC_DIAG_SHUTDOWN, + SMC_DIAG_DMBINFO, __SMC_DIAG_MAX, }; @@ -83,4 +84,13 @@ struct smc_diag_lgrinfo { struct smc_diag_linkinfo lnk[1]; __u8 role; }; + +struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ + __u32 linkid; /* Link identifier */ + __u64 peer_gid; /* Peer GID */ + __u64 my_gid; /* My GID */ + __u64 token; /* Token of DMB */ + __u64 peer_token; /* Token of remote DMBE */ +}; + #endif /* _UAPI_SMC_DIAG_H_ */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 750d89120335..e5ebc83827ab 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -279,6 +279,8 @@ enum LINUX_MIB_TCPDELIVERED, /* TCPDelivered */ LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */ LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */ + LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */ + LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 162d1094c41c..24ec792dacc1 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -17,13 +17,15 @@ enum { TCA_PEDIT_KEY_EX, __TCA_PEDIT_MAX }; + #define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1) - + enum { TCA_PEDIT_KEY_EX_HTYPE = 1, TCA_PEDIT_KEY_EX_CMD = 2, __TCA_PEDIT_KEY_EX_MAX }; + #define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1) /* TCA_PEDIT_KEY_EX_HDR_TYPE_NETWROK is a special case for legacy users. It @@ -38,6 +40,7 @@ enum pedit_header_type { TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5, __PEDIT_HDR_TYPE_MAX, }; + #define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1) enum pedit_cmd { @@ -45,6 +48,7 @@ enum pedit_cmd { TCA_PEDIT_KEY_EX_CMD_ADD = 1, __PEDIT_CMD_MAX, }; + #define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1) struct tc_pedit_key { @@ -55,13 +59,14 @@ struct tc_pedit_key { __u32 offmask; __u32 shift; }; - + struct tc_pedit_sel { tc_gen; unsigned char nkeys; unsigned char flags; struct tc_pedit_key keys[0]; }; + #define tc_pedit tc_pedit_sel #endif diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index 72bbefe5d1d1..e284fec8c467 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -36,9 +36,35 @@ enum { TCA_TUNNEL_KEY_PAD, TCA_TUNNEL_KEY_ENC_DST_PORT, /* be16 */ TCA_TUNNEL_KEY_NO_CSUM, /* u8 */ + TCA_TUNNEL_KEY_ENC_OPTS, /* Nested TCA_TUNNEL_KEY_ENC_OPTS_ + * attributes + */ __TCA_TUNNEL_KEY_MAX, }; #define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1) +enum { + TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC, + TCA_TUNNEL_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_TUNNEL_KEY_ENC_OPTS_ + * attributes + */ + __TCA_TUNNEL_KEY_ENC_OPTS_MAX, +}; + +#define TCA_TUNNEL_KEY_ENC_OPTS_MAX (__TCA_TUNNEL_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, /* be16 */ + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX - 1) + #endif diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index 85c11982c89b..0ebe02ef1a86 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -121,6 +121,7 @@ enum { TIPC_NLA_SOCK_TIPC_STATE, /* u32 */ TIPC_NLA_SOCK_COOKIE, /* u64 */ TIPC_NLA_SOCK_PAD, /* flag */ + TIPC_NLA_SOCK_GROUP, /* nest */ __TIPC_NLA_SOCK_MAX, TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1 @@ -233,6 +234,19 @@ enum { TIPC_NLA_MON_PEER_MAX = __TIPC_NLA_MON_PEER_MAX - 1 }; +/* Nest, socket group info */ +enum { + TIPC_NLA_SOCK_GROUP_ID, /* u32 */ + TIPC_NLA_SOCK_GROUP_OPEN, /* flag */ + TIPC_NLA_SOCK_GROUP_NODE_SCOPE, /* flag */ + TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE, /* flag */ + TIPC_NLA_SOCK_GROUP_INSTANCE, /* u32 */ + TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, /* u32 */ + + __TIPC_NLA_SOCK_GROUP_MAX, + TIPC_NLA_SOCK_GROUP_MAX = __TIPC_NLA_SOCK_GROUP_MAX - 1 +}; + /* Nest, connection info */ enum { TIPC_NLA_CON_UNSPEC, diff --git a/ipc/msg.c b/ipc/msg.c index 3b6545302598..203281198079 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -38,6 +38,7 @@ #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> +#include <linux/rhashtable.h> #include <asm/current.h> #include <linux/uaccess.h> diff --git a/ipc/sem.c b/ipc/sem.c index 5af1943ad782..29c0347ef11d 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -86,6 +86,7 @@ #include <linux/ipc_namespace.h> #include <linux/sched/wake_q.h> #include <linux/nospec.h> +#include <linux/rhashtable.h> #include <linux/uaccess.h> #include "util.h" diff --git a/ipc/shm.c b/ipc/shm.c index 051a3e1fb8df..d4daf78df6da 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -43,6 +43,7 @@ #include <linux/nsproxy.h> #include <linux/mount.h> #include <linux/ipc_namespace.h> +#include <linux/rhashtable.h> #include <linux/uaccess.h> diff --git a/ipc/util.c b/ipc/util.c index 4e81182fa0ac..fdffff41f65b 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -63,6 +63,7 @@ #include <linux/rwsem.h> #include <linux/memory.h> #include <linux/ipc_namespace.h> +#include <linux/rhashtable.h> #include <asm/unistd.h> diff --git a/lib/nlattr.c b/lib/nlattr.c index dfa55c873c13..e335bcafa9e4 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -253,8 +253,8 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, if (policy) { err = validate_nla(nla, maxtype, policy); if (err < 0) { - if (extack) - extack->bad_attr = nla; + NL_SET_ERR_MSG_ATTR(extack, nla, + "Attribute failed policy validation"); goto errout; } } diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9427b5766134..0e04947b7e0c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -28,6 +28,7 @@ #include <linux/rhashtable.h> #include <linux/err.h> #include <linux/export.h> +#include <linux/rhashtable.h> #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U @@ -115,8 +116,7 @@ static void bucket_table_free_rcu(struct rcu_head *head) static union nested_table *nested_table_alloc(struct rhashtable *ht, union nested_table __rcu **prev, - unsigned int shifted, - unsigned int nhash) + bool leaf) { union nested_table *ntbl; int i; @@ -127,10 +127,9 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht, ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC); - if (ntbl && shifted) { - for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++) - INIT_RHT_NULLS_HEAD(ntbl[i].bucket, ht, - (i << shifted) | nhash); + if (ntbl && leaf) { + for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) + INIT_RHT_NULLS_HEAD(ntbl[i].bucket); } rcu_assign_pointer(*prev, ntbl); @@ -156,7 +155,7 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, return NULL; if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets, - 0, 0)) { + false)) { kfree(tbl); return NULL; } @@ -206,7 +205,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) - INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); + INIT_RHT_NULLS_HEAD(tbl->buckets[i]); return tbl; } @@ -227,8 +226,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - struct bucket_table *new_tbl = rhashtable_last_table(ht, - rht_dereference_rcu(old_tbl->future_tbl, ht)); + struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash); int err = -EAGAIN; struct rhash_head *head, *next, *entry; @@ -298,21 +296,14 @@ static int rhashtable_rehash_attach(struct rhashtable *ht, struct bucket_table *old_tbl, struct bucket_table *new_tbl) { - /* Protect future_tbl using the first bucket lock. */ - spin_lock_bh(old_tbl->locks); - - /* Did somebody beat us to it? */ - if (rcu_access_pointer(old_tbl->future_tbl)) { - spin_unlock_bh(old_tbl->locks); - return -EEXIST; - } - /* Make insertions go into the new, empty table right away. Deletions * and lookups will be attempted in both tables until we synchronize. + * As cmpxchg() provides strong barriers, we do not need + * rcu_assign_pointer(). */ - rcu_assign_pointer(old_tbl->future_tbl, new_tbl); - spin_unlock_bh(old_tbl->locks); + if (cmpxchg(&old_tbl->future_tbl, NULL, new_tbl) != NULL) + return -EEXIST; return 0; } @@ -475,7 +466,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht, fail: /* Do not fail the insert if someone else did a rehash. */ - if (likely(rcu_dereference_raw(tbl->future_tbl))) + if (likely(rcu_access_pointer(tbl->future_tbl))) return 0; /* Schedule async rehash to retry allocation in process context. */ @@ -548,7 +539,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT) return ERR_CAST(data); - new_tbl = rcu_dereference(tbl->future_tbl); + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (new_tbl) return new_tbl; @@ -607,7 +598,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, break; spin_unlock_bh(lock); - tbl = rcu_dereference(tbl->future_tbl); + tbl = rht_dereference_rcu(tbl->future_tbl, ht); } data = rhashtable_lookup_one(ht, tbl, hash, key, obj); @@ -994,7 +985,6 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) * .key_offset = offsetof(struct test_obj, key), * .key_len = sizeof(int), * .hashfn = jhash, - * .nulls_base = (1U << RHT_BASE_SHIFT), * }; * * Configuration Example 2: Variable length keys @@ -1028,9 +1018,6 @@ int rhashtable_init(struct rhashtable *ht, (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; - if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT)) - return -EINVAL; - memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); @@ -1095,10 +1082,6 @@ int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) { int err; - /* No rhlist NULLs marking for now. */ - if (params->nulls_base) - return -EINVAL; - err = rhashtable_init(&hlt->ht, params); hlt->ht.rhlist = true; return err; @@ -1216,25 +1199,18 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; union nested_table *ntbl; - unsigned int shifted; - unsigned int nhash; ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]); hash >>= tbl->nest; - nhash = index; - shifted = tbl->nest; ntbl = nested_table_alloc(ht, &ntbl[index].table, - size <= (1 << shift) ? shifted : 0, nhash); + size <= (1 << shift)); while (ntbl && size > (1 << shift)) { index = hash & ((1 << shift) - 1); size >>= shift; hash >>= shift; - nhash |= index << shifted; - shifted += shift; ntbl = nested_table_alloc(ht, &ntbl[index].table, - size <= (1 << shift) ? shifted : 0, - nhash); + size <= (1 << shift)); } if (!ntbl) diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index fb6968109113..82ac39ce5310 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -83,7 +83,7 @@ static u32 my_hashfn(const void *data, u32 len, u32 seed) { const struct test_obj_rhl *obj = data; - return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE; + return (obj->value.id % 10); } static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) @@ -99,7 +99,6 @@ static struct rhashtable_params test_rht_params = { .key_offset = offsetof(struct test_obj, value), .key_len = sizeof(struct test_obj_val), .hashfn = jhash, - .nulls_base = (3U << RHT_BASE_SHIFT), }; static struct rhashtable_params test_rht_params_dup = { @@ -296,8 +295,6 @@ static int __init test_rhltable(unsigned int entries) if (!obj_in_table) goto out_free; - /* nulls_base not supported in rhlist interface */ - test_rht_params.nulls_base = 0; err = rhltable_init(&rhlt, &test_rht_params); if (WARN_ON(err)) goto out_free; @@ -501,6 +498,8 @@ static unsigned int __init print_ht(struct rhltable *rhlt) unsigned int i, cnt = 0; ht = &rhlt->ht; + /* Take the mutex to avoid RCU warning */ + mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); for (i = 0; i < tbl->size; i++) { struct rhash_head *pos, *next; @@ -534,6 +533,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt) } } printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff); + mutex_unlock(&ht->mutex); return cnt; } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 8ccee3d01822..5e9950453955 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -647,13 +647,14 @@ out: return err; } -static struct sk_buff **vlan_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *vlan_gro_receive(struct list_head *head, + struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; - struct vlan_hdr *vhdr; - unsigned int hlen, off_vlan; const struct packet_offload *ptype; + unsigned int hlen, off_vlan; + struct sk_buff *pp = NULL; + struct vlan_hdr *vhdr; + struct sk_buff *p; __be16 type; int flush = 1; @@ -675,7 +676,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { struct vlan_hdr *vhdr2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index a2de5a44bd41..ff9659af6b91 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1449,7 +1449,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) * detection frames. Set the locally administered bit to avoid * collisions with users mac addresses. */ - random_ether_addr(bat_priv->bla.loopdetect_addr); + eth_random_addr(bat_priv->bla.loopdetect_addr); bat_priv->bla.loopdetect_addr[0] = 0xba; bat_priv->bla.loopdetect_addr[1] = 0xbe; bat_priv->bla.loopdetect_lasttime = jiffies; diff --git a/net/core/dev.c b/net/core/dev.c index a5aa1c7444e6..08d58e0debe5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2081,6 +2081,10 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS +struct static_key xps_needed __read_mostly; +EXPORT_SYMBOL(xps_needed); +struct static_key xps_rxqs_needed __read_mostly; +EXPORT_SYMBOL(xps_rxqs_needed); static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) @@ -2092,7 +2096,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, int pos; if (dev_maps) - map = xmap_dereference(dev_maps->cpu_map[tci]); + map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; @@ -2105,7 +2109,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, break; } - RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL); + RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } @@ -2135,33 +2139,68 @@ static bool remove_xps_queue_cpu(struct net_device *dev, return active; } +static void clean_xps_maps(struct net_device *dev, const unsigned long *mask, + struct xps_dev_maps *dev_maps, unsigned int nr_ids, + u16 offset, u16 count, bool is_rxqs_map) +{ + bool active = false; + int i, j; + + for (j = -1; j = netif_attrmask_next(j, mask, nr_ids), + j < nr_ids;) + active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, + count); + if (!active) { + if (is_rxqs_map) { + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + } else { + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); + + for (i = offset + (count - 1); count--; i--) + netdev_queue_numa_node_write( + netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + } + kfree_rcu(dev_maps, rcu); + } +} + static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { + const unsigned long *possible_mask = NULL; struct xps_dev_maps *dev_maps; - int cpu, i; - bool active = false; + unsigned int nr_ids; + + if (!static_key_false(&xps_needed)) + return; mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); + if (static_key_false(&xps_rxqs_needed)) { + dev_maps = xmap_dereference(dev->xps_rxqs_map); + if (dev_maps) { + nr_ids = dev->num_rx_queues; + clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, + offset, count, true); + } + } + + dev_maps = xmap_dereference(dev->xps_cpus_map); if (!dev_maps) goto out_no_maps; - for_each_possible_cpu(cpu) - active |= remove_xps_queue_cpu(dev, dev_maps, cpu, - offset, count); - - if (!active) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - kfree_rcu(dev_maps, rcu); - } - - for (i = offset + (count - 1); count--; i--) - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), - NUMA_NO_NODE); + if (num_possible_cpus() > 1) + possible_mask = cpumask_bits(cpu_possible_mask); + nr_ids = nr_cpu_ids; + clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count, + false); out_no_maps: + if (static_key_enabled(&xps_rxqs_needed)) + static_key_slow_dec(&xps_rxqs_needed); + + static_key_slow_dec(&xps_needed); mutex_unlock(&xps_map_mutex); } @@ -2170,8 +2209,8 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } -static struct xps_map *expand_xps_map(struct xps_map *map, - int cpu, u16 index) +static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, + u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; @@ -2183,7 +2222,7 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return map; } - /* Need to add queue to this CPU's existing map */ + /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; @@ -2191,9 +2230,14 @@ static struct xps_map *expand_xps_map(struct xps_map *map, alloc_len = map->alloc_len * 2; } - /* Need to allocate new map to store queue on this CPU's map */ - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, - cpu_to_node(cpu)); + /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's + * map + */ + if (is_rxqs_map) + new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); + else + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(attr_index)); if (!new_map) return NULL; @@ -2205,14 +2249,16 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return new_map; } -int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, - u16 index) +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map) { + const unsigned long *online_mask = NULL, *possible_mask = NULL; struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; - int i, cpu, tci, numa_node_id = -2; + int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; bool active = false; + unsigned int nr_ids; if (dev->num_tc) { num_tc = dev->num_tc; @@ -2221,16 +2267,27 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, return -EINVAL; } - maps_sz = XPS_DEV_MAPS_SIZE(num_tc); - if (maps_sz < L1_CACHE_BYTES) - maps_sz = L1_CACHE_BYTES; - mutex_lock(&xps_map_mutex); + if (is_rxqs_map) { + maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); + dev_maps = xmap_dereference(dev->xps_rxqs_map); + nr_ids = dev->num_rx_queues; + } else { + maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); + if (num_possible_cpus() > 1) { + online_mask = cpumask_bits(cpu_online_mask); + possible_mask = cpumask_bits(cpu_possible_mask); + } + dev_maps = xmap_dereference(dev->xps_cpus_map); + nr_ids = nr_cpu_ids; + } - dev_maps = xmap_dereference(dev->xps_maps); + if (maps_sz < L1_CACHE_BYTES) + maps_sz = L1_CACHE_BYTES; /* allocate memory for queue storage */ - for_each_cpu_and(cpu, cpu_online_mask, mask) { + for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), + j < nr_ids;) { if (!new_dev_maps) new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { @@ -2238,73 +2295,85 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, return -ENOMEM; } - tci = cpu * num_tc + tc; - map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) : + tci = j * num_tc + tc; + map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; - map = expand_xps_map(map, cpu, index); + map = expand_xps_map(map, j, index, is_rxqs_map); if (!map) goto error; - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; - for_each_possible_cpu(cpu) { + static_key_slow_inc(&xps_needed); + if (is_rxqs_map) + static_key_slow_inc(&xps_rxqs_needed); + + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { /* copy maps belonging to foreign traffic classes */ - for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) { + for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } /* We need to explicitly update tci as prevous loop * could break out early if dev_maps is NULL. */ - tci = cpu * num_tc + tc; + tci = j * num_tc + tc; - if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { - /* add queue to CPU maps */ + if (netif_attr_test_mask(j, mask, nr_ids) && + netif_attr_test_online(j, online_mask, nr_ids)) { + /* add tx-queue to CPU/rx-queue maps */ int pos = 0; - map = xmap_dereference(new_dev_maps->cpu_map[tci]); + map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA - if (numa_node_id == -2) - numa_node_id = cpu_to_node(cpu); - else if (numa_node_id != cpu_to_node(cpu)) - numa_node_id = -1; + if (!is_rxqs_map) { + if (numa_node_id == -2) + numa_node_id = cpu_to_node(j); + else if (numa_node_id != cpu_to_node(j)) + numa_node_id = -1; + } #endif } else if (dev_maps) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } /* copy maps belonging to foreign traffic classes */ for (i = num_tc - tc, tci++; dev_maps && --i; tci++) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } - rcu_assign_pointer(dev->xps_maps, new_dev_maps); + if (is_rxqs_map) + rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps); + else + rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; - for_each_possible_cpu(cpu) { - for (i = num_tc, tci = cpu * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); - map = xmap_dereference(dev_maps->cpu_map[tci]); + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = num_tc, tci = j * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); + map = xmap_dereference(dev_maps->attr_map[tci]); if (map && map != new_map) kfree_rcu(map, rcu); } @@ -2317,19 +2386,23 @@ out_no_old_maps: active = true; out_no_new_maps: - /* update Tx queue numa node */ - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), - (numa_node_id >= 0) ? numa_node_id : - NUMA_NO_NODE); + if (!is_rxqs_map) { + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? + numa_node_id : NUMA_NO_NODE); + } if (!dev_maps) goto out_no_maps; - /* removes queue from unused CPUs */ - for_each_possible_cpu(cpu) { - for (i = tc, tci = cpu * num_tc; i--; tci++) + /* removes tx-queue from unused CPUs/rx-queues */ + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = tc, tci = j * num_tc; i--; tci++) active |= remove_xps_queue(dev_maps, tci, index); - if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu)) + if (!netif_attr_test_mask(j, mask, nr_ids) || + !netif_attr_test_online(j, online_mask, nr_ids)) active |= remove_xps_queue(dev_maps, tci, index); for (i = num_tc - tc, tci++; --i; tci++) active |= remove_xps_queue(dev_maps, tci, index); @@ -2337,7 +2410,10 @@ out_no_new_maps: /* free map if not active */ if (!active) { - RCU_INIT_POINTER(dev->xps_maps, NULL); + if (is_rxqs_map) + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + else + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); kfree_rcu(dev_maps, rcu); } @@ -2347,11 +2423,12 @@ out_no_maps: return 0; error: /* remove any maps that we added */ - for_each_possible_cpu(cpu) { - for (i = num_tc, tci = cpu * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = num_tc, tci = j * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[tci]) : + xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); @@ -2363,6 +2440,12 @@ error: kfree(new_dev_maps); return -ENOMEM; } + +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) +{ + return __netif_set_xps_queue(dev, cpumask_bits(mask), index, false); +} EXPORT_SYMBOL(netif_set_xps_queue); #endif @@ -3376,32 +3459,63 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) } #endif /* CONFIG_NET_EGRESS */ -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +#ifdef CONFIG_XPS +static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, + struct xps_dev_maps *dev_maps, unsigned int tci) +{ + struct xps_map *map; + int queue_index = -1; + + if (dev->num_tc) { + tci *= dev->num_tc; + tci += netdev_get_prio_tc_map(dev, skb->priority); + } + + map = rcu_dereference(dev_maps->attr_map[tci]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else + queue_index = map->queues[reciprocal_scale( + skb_get_hash(skb), map->len)]; + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + return queue_index; +} +#endif + +static int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; - struct xps_map *map; + struct sock *sk = skb->sk; int queue_index = -1; + if (!static_key_false(&xps_needed)) + return -1; + rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); + if (!static_key_false(&xps_rxqs_needed)) + goto get_cpus_map; + + dev_maps = rcu_dereference(dev->xps_rxqs_map); if (dev_maps) { - unsigned int tci = skb->sender_cpu - 1; + int tci = sk_rx_queue_get(sk); - if (dev->num_tc) { - tci *= dev->num_tc; - tci += netdev_get_prio_tc_map(dev, skb->priority); - } + if (tci >= 0 && tci < dev->num_rx_queues) + queue_index = __get_xps_queue_idx(dev, skb, dev_maps, + tci); + } - map = rcu_dereference(dev_maps->cpu_map[tci]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else - queue_index = map->queues[reciprocal_scale(skb_get_hash(skb), - map->len)]; - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; +get_cpus_map: + if (queue_index < 0) { + dev_maps = rcu_dereference(dev->xps_cpus_map); + if (dev_maps) { + unsigned int tci = skb->sender_cpu - 1; + + queue_index = __get_xps_queue_idx(dev, skb, dev_maps, + tci); } } rcu_read_unlock(); @@ -4875,42 +4989,46 @@ out: return netif_receive_skb_internal(skb); } -/* napi->gro_list contains packets ordered by age. - * youngest packets at the head of it. - * Complete skbs in reverse order to reduce latencies. - */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) +static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *head, + bool flush_old) { - struct sk_buff *skb, *prev = NULL; - - /* scan list and build reverse chain */ - for (skb = napi->gro_list; skb != NULL; skb = skb->next) { - skb->prev = prev; - prev = skb; - } - - for (skb = prev; skb; skb = prev) { - skb->next = NULL; + struct sk_buff *skb, *p; + list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - - prev = skb->prev; + list_del_init(&skb->list); napi_gro_complete(skb); napi->gro_count--; } +} - napi->gro_list = NULL; +/* napi->gro_hash contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct list_head *head = &napi->gro_hash[i]; + + __napi_gro_flush_chain(napi, head, flush_old); + } } EXPORT_SYMBOL(napi_gro_flush); -static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +static struct list_head *gro_list_prepare(struct napi_struct *napi, + struct sk_buff *skb) { - struct sk_buff *p; unsigned int maclen = skb->dev->hard_header_len; u32 hash = skb_get_hash_raw(skb); + struct list_head *head; + struct sk_buff *p; - for (p = napi->gro_list; p; p = p->next) { + head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)]; + list_for_each_entry(p, head, list) { unsigned long diffs; NAPI_GRO_CB(p)->flush = 0; @@ -4933,6 +5051,8 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) maclen); NAPI_GRO_CB(p)->same_flow = !diffs; } + + return head; } static void skb_gro_reset_offset(struct sk_buff *skb) @@ -4975,20 +5095,54 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } +static void gro_flush_oldest(struct napi_struct *napi) +{ + struct sk_buff *oldest = NULL; + unsigned long age = jiffies; + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct list_head *head = &napi->gro_hash[i]; + struct sk_buff *skb; + + if (list_empty(head)) + continue; + + skb = list_last_entry(head, struct sk_buff, list); + if (!oldest || time_before(NAPI_GRO_CB(skb)->age, age)) { + oldest = skb; + age = NAPI_GRO_CB(skb)->age; + } + } + + /* We are called with napi->gro_count >= MAX_GRO_SKBS, so this is + * impossible. + */ + if (WARN_ON_ONCE(!oldest)) + return; + + /* Do not adjust napi->gro_count, caller is adding a new SKB to + * the chain. + */ + list_del(&oldest->list); + napi_gro_complete(oldest); +} + static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int same_flow; + struct list_head *gro_head; + struct sk_buff *pp = NULL; enum gro_result ret; + int same_flow; int grow; if (netif_elide_gro(skb->dev)) goto normal; - gro_list_prepare(napi, skb); + gro_head = gro_list_prepare(napi, skb); rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -5022,7 +5176,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->csum_valid = 0; } - pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(gro_head, skb); break; } rcu_read_unlock(); @@ -5039,11 +5193,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - struct sk_buff *nskb = *pp; - - *pp = nskb->next; - nskb->next = NULL; - napi_gro_complete(nskb); + list_del_init(&pp->list); + napi_gro_complete(pp); napi->gro_count--; } @@ -5054,16 +5205,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff goto normal; if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { - struct sk_buff *nskb = napi->gro_list; - - /* locate the end of the list to select the 'oldest' flow */ - while (nskb->next) { - pp = &nskb->next; - nskb = *pp; - } - *pp = NULL; - nskb->next = NULL; - napi_gro_complete(nskb); + gro_flush_oldest(napi); } else { napi->gro_count++; } @@ -5071,8 +5213,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); - skb->next = napi->gro_list; - napi->gro_list = skb; + list_add(&skb->list, gro_head); ret = GRO_HELD; pull: @@ -5478,7 +5619,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - if (n->gro_list) { + if (n->gro_count) { unsigned long timeout = 0; if (work_done) @@ -5687,7 +5828,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_list && !napi_disable_pending(napi) && + if (napi->gro_count && !napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); @@ -5697,11 +5838,14 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { + int i; + INIT_LIST_HEAD(&napi->poll_list); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; napi->gro_count = 0; - napi->gro_list = NULL; + for (i = 0; i < GRO_HASH_BUCKETS; i++) + INIT_LIST_HEAD(&napi->gro_hash[i]); napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) @@ -5734,6 +5878,18 @@ void napi_disable(struct napi_struct *n) } EXPORT_SYMBOL(napi_disable); +static void flush_gro_hash(struct napi_struct *napi) +{ + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct sk_buff *skb, *n; + + list_for_each_entry_safe(skb, n, &napi->gro_hash[i], list) + kfree_skb(skb); + } +} + /* Must be called in process context */ void netif_napi_del(struct napi_struct *napi) { @@ -5743,8 +5899,7 @@ void netif_napi_del(struct napi_struct *napi) list_del_init(&napi->dev_list); napi_free_frags(napi); - kfree_skb_list(napi->gro_list); - napi->gro_list = NULL; + flush_gro_hash(napi); napi->gro_count = 0; } EXPORT_SYMBOL(netif_napi_del); @@ -5787,7 +5942,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - if (n->gro_list) { + if (n->gro_count) { /* flush too old packets * If HZ < 1000, flush all packets. */ diff --git a/net/core/filter.c b/net/core/filter.c index 0ca6907d7efe..547fd34589be 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3582,7 +3582,7 @@ BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; - ip_tunnel_info_opts_set(info, from, size); + ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT); return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e3fda9e725c..cbe85d8d4cc2 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1148,7 +1148,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->nud_state = new; err = 0; notify = old & NUD_VALID; - if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && + if (((old & (NUD_INCOMPLETE | NUD_PROBE)) || + (flags & NEIGH_UPDATE_F_ADMIN)) && (new & NUD_FAILED)) { neigh_invalidate(neigh); notify = 1; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index bb7e80f4ced3..f25ac5ff48a6 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1227,13 +1227,13 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, return -ENOMEM; rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); + dev_maps = rcu_dereference(dev->xps_cpus_map); if (dev_maps) { for_each_possible_cpu(cpu) { int i, tci = cpu * num_tc + tc; struct xps_map *map; - map = rcu_dereference(dev_maps->cpu_map[tci]); + map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; @@ -1283,6 +1283,88 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue, static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); + +static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) +{ + struct net_device *dev = queue->dev; + struct xps_dev_maps *dev_maps; + unsigned long *mask, index; + int j, len, num_tc = 1, tc = 0; + + index = get_netdev_queue_index(queue); + + if (dev->num_tc) { + num_tc = dev->num_tc; + tc = netdev_txq_to_tc(dev, index); + if (tc < 0) + return -EINVAL; + } + mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long), + GFP_KERNEL); + if (!mask) + return -ENOMEM; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_rxqs_map); + if (!dev_maps) + goto out_no_maps; + + for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues), + j < dev->num_rx_queues;) { + int i, tci = j * num_tc + tc; + struct xps_map *map; + + map = rcu_dereference(dev_maps->attr_map[tci]); + if (!map) + continue; + + for (i = map->len; i--;) { + if (map->queues[i] == index) { + set_bit(j, mask); + break; + } + } + } +out_no_maps: + rcu_read_unlock(); + + len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues); + kfree(mask); + + return len < PAGE_SIZE ? len : -EINVAL; +} + +static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, + size_t len) +{ + struct net_device *dev = queue->dev; + struct net *net = dev_net(dev); + unsigned long *mask, index; + int err; + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long), + GFP_KERNEL); + if (!mask) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + err = bitmap_parse(buf, len, mask, dev->num_rx_queues); + if (err) { + kfree(mask); + return err; + } + + err = __netif_set_xps_queue(dev, mask, index, true); + kfree(mask); + return err ? : len; +} + +static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init + = __ATTR_RW(xps_rxqs); #endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { @@ -1290,6 +1372,7 @@ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_traffic_class.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, + &xps_rxqs_attribute.attr, &queue_tx_maxrate.attr, #endif NULL diff --git a/net/core/skbuff.c b/net/core/skbuff.c index eba8dae22c25..1357f36c8a5e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3815,14 +3815,14 @@ err: } EXPORT_SYMBOL_GPL(skb_segment); -int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) { struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); - struct sk_buff *lp, *p = *head; unsigned int delta_truesize; + struct sk_buff *lp; if (unlikely(p->len + len >= 65536)) return -E2BIG; @@ -4911,7 +4911,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) return; ipvs_reset(skb); - skb_orphan(skb); skb->mark = 0; } EXPORT_SYMBOL_GPL(skb_scrub_packet); diff --git a/net/core/sock.c b/net/core/sock.c index 9e8f65585b81..6429982eb976 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2401,9 +2401,10 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); + bool charged = true; if (mem_cgroup_sockets_enabled && sk->sk_memcg && - !mem_cgroup_charge_skmem(sk->sk_memcg, amt)) + !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) goto suppress_allocation; /* Under limit. */ @@ -2461,7 +2462,8 @@ suppress_allocation: return 1; } - trace_sock_exceed_buf_limit(sk, prot, allocated); + if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) + trace_sock_exceed_buf_limit(sk, prot, allocated, kind); sk_memory_allocated_sub(sk, amt); @@ -2818,6 +2820,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0U; sk->sk_pacing_shift = 10; sk->sk_incoming_cpu = -1; + + sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/core/xdp.c b/net/core/xdp.c index 9d1f22072d5d..31c58719b5a9 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -45,8 +45,8 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) != sizeof(u32)); - /* Use cyclic increasing ID as direct hash key, see rht_bucket_index */ - return key << RHT_HASH_RESERVED_SPACE; + /* Use cyclic increasing ID as direct hash key */ + return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1e3b6a6d8a40..71536c435132 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -900,7 +900,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: - return tcf_block_cb_register(f->block, cb, dev, dev); + return tcf_block_cb_register(f->block, cb, dev, dev, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, cb, dev); return 0; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index ee28440f57c5..fd8faa0dfa61 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -427,13 +427,13 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) } EXPORT_SYMBOL(sysfs_format_mac); -struct sk_buff **eth_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; - struct ethhdr *eh, *eh2; - unsigned int hlen, off_eth; const struct packet_offload *ptype; + unsigned int hlen, off_eth; + struct sk_buff *pp = NULL; + struct ethhdr *eh, *eh2; + struct sk_buff *p; __be16 type; int flush = 1; @@ -448,7 +448,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head, flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b403499fdabe..9263a2c114e0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1384,12 +1384,12 @@ out: } EXPORT_SYMBOL(inet_gso_segment); -struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) +struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; - struct sk_buff **pp = NULL; - struct sk_buff *p; + struct sk_buff *pp = NULL; const struct iphdr *iph; + struct sk_buff *p; unsigned int hlen; unsigned int off; unsigned int id; @@ -1425,7 +1425,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { struct iphdr *iph2; u16 flush_id; @@ -1505,8 +1505,8 @@ out: } EXPORT_SYMBOL(inet_gro_receive); -static struct sk_buff **ipip_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ipip_gro_receive(struct list_head *head, + struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 7cf755ef9efb..bbeecd13e534 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -28,8 +28,8 @@ #include <linux/spinlock.h> #include <net/udp.h> -static struct sk_buff **esp4_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *esp4_gro_receive(struct list_head *head, + struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index c9ec1603666b..500a59906b87 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -224,14 +224,14 @@ drop: return 0; } -static struct sk_buff **fou_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *fou_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - const struct net_offload *ops; - struct sk_buff **pp = NULL; u8 proto = fou_from_sock(sk)->protocol; const struct net_offload **offloads; + const struct net_offload *ops; + struct sk_buff *pp = NULL; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel @@ -305,13 +305,13 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, return guehdr; } -static struct sk_buff **gue_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *gue_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { const struct net_offload **offloads; const struct net_offload *ops; - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct guehdr *guehdr; size_t len, optlen, hdrlen, off; @@ -397,7 +397,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, skb_gro_pull(skb, hdrlen); - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct guehdr *guehdr2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 6a7d980105f6..6c63524f598a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -108,10 +108,10 @@ out: return segs; } -static struct sk_buff **gre_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *gre_gro_receive(struct list_head *head, + struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; const struct gre_base_hdr *greh; unsigned int hlen, grehlen; @@ -182,7 +182,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, null_compute_pseudo); } - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct gre_base_hdr *greh2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9e35b81d093..316518f87294 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -20,6 +20,7 @@ #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <linux/rhashtable.h> #include <net/sock.h> #include <net/inet_frag.h> diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2d8efeecf619..c8ca5d8f0f75 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -587,6 +587,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; key = &tun_info->key; + if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + goto err_free_rt; md = ip_tunnel_info_opts(tun_info); if (!md) goto err_free_rt; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9f79b9803a16..82f914122f1b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -60,6 +60,7 @@ #include <linux/netfilter_ipv4.h> #include <linux/compat.h> #include <linux/export.h> +#include <linux/rhashtable.h> #include <net/ip_tunnels.h> #include <net/checksum.h> #include <net/netlink.h> diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index cafb0506c8c9..1ad9aa62a97b 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -2,6 +2,7 @@ * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation */ +#include <linux/rhashtable.h> #include <linux/mroute_base.h> /* Sets everything common except 'dev', since that is done under locking */ diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4388de0e5380..1e6f28c97d3a 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -35,7 +35,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv4_packet(struct nf_log_buf *m, +static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { @@ -183,7 +183,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (!iphoff) { /* Only recurse once. */ nf_log_buf_add(m, "["); - dump_ipv4_packet(m, info, skb, + dump_ipv4_packet(net, m, info, skb, iphoff + ih->ihl*4+sizeof(_icmph)); nf_log_buf_add(m, "] "); } @@ -251,7 +251,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && !iphoff) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!iphoff && skb->mark) @@ -333,7 +333,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv4_mac_header(m, loginfo, skb); - dump_ipv4_packet(m, loginfo, skb, 0); + dump_ipv4_packet(net, m, loginfo, skb, 0); nf_log_buf_close(m); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 77350c1256ce..b46e4cf9a55a 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -287,6 +287,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED), SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE), SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED), + SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP), + SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e7b53d2a971f..bf461fa77ed6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2574,6 +2574,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; + tp->rcv_rtt_last_tsecr = 0; tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 58e2f479ffb4..3b5f45b9e81e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -205,7 +205,11 @@ static u32 bbr_bw(const struct sock *sk) */ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { - rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache); + unsigned int mss = tcp_sk(sk)->mss_cache; + + if (!tcp_needs_internal_pacing(sk)) + mss = tcp_mss_to_mtu(sk, mss); + rate *= mss; rate *= gain; rate >>= BBR_SCALE; rate *= USEC_PER_SEC; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8e5522c6833a..814ea43dd12f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -78,6 +78,7 @@ #include <linux/errqueue.h> #include <trace/events/tcp.h> #include <linux/static_key.h> +#include <net/busy_poll.h> int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -582,9 +583,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); - if (tp->rx_opt.rcv_tsecr && - (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + if (tp->rx_opt.rcv_tsecr == tp->rcv_rtt_last_tsecr) + return; + tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; + + if (TCP_SKB_CB(skb)->end_seq - + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; u32 delta_us; @@ -4617,8 +4621,10 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) skb->data_len = data_len; skb->len = size; - if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto err_free; + } err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); if (err) @@ -4674,15 +4680,19 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) * Out of sequence packets to the out_of_order_queue. */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { - if (tcp_receive_window(tp) == 0) + if (tcp_receive_window(tp) == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; + } /* Ok. In sequence. In window. */ queue_and_out: if (skb_queue_len(&sk->sk_receive_queue) == 0) sk_forced_mem_schedule(sk, skb->truesize); - else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto drop; + } eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); @@ -4741,8 +4751,10 @@ drop: /* If window is closed, drop tail of packet. But after * remembering D-SACK for its head made in previous line. */ - if (!tcp_receive_window(tp)) + if (!tcp_receive_window(tp)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; + } goto queue_and_out; } @@ -5484,6 +5496,11 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_ack(sk, skb, 0); __kfree_skb(skb); tcp_data_snd_check(sk); + /* When receiving pure ack in fast path, update + * last ts ecr directly instead of calling + * tcp_rcv_rtt_measure_ts() + */ + tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; return; } else { /* Header too small */ TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); @@ -5585,6 +5602,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); + sk_mark_napi_id(sk, skb); } tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); @@ -6413,6 +6431,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); + sk_rx_queue_set(req_to_sk(req), skb); if (!want_cookie) { tcp_reqsk_record_syn(sk, req, skb); fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 1dda1341a223..dac5893a52b4 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -449,119 +449,122 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct sk_buff *skb) { struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); + const struct inet_request_sock *ireq = inet_rsk(req); + struct tcp_request_sock *treq = tcp_rsk(req); + struct inet_connection_sock *newicsk; + struct tcp_sock *oldtp, *newtp; - if (newsk) { - const struct inet_request_sock *ireq = inet_rsk(req); - struct tcp_request_sock *treq = tcp_rsk(req); - struct inet_connection_sock *newicsk = inet_csk(newsk); - struct tcp_sock *newtp = tcp_sk(newsk); - struct tcp_sock *oldtp = tcp_sk(sk); - - smc_check_reset_syn_req(oldtp, req, newtp); - - /* Now setup tcp_sock */ - newtp->pred_flags = 0; - - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 1; - - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; - - INIT_LIST_HEAD(&newtp->tsq_node); - INIT_LIST_HEAD(&newtp->tsorted_sent_queue); - - tcp_init_wl(newtp, treq->rcv_isn); - - newtp->srtt_us = 0; - newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); - newicsk->icsk_rto = TCP_TIMEOUT_INIT; - newicsk->icsk_ack.lrcvtime = tcp_jiffies32; - - newtp->packets_out = 0; - newtp->retrans_out = 0; - newtp->sacked_out = 0; - newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - newtp->tlp_high_seq = 0; - newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; - newtp->last_oow_ack_time = 0; - newtp->total_retrans = req->num_retrans; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - newtp->snd_cwnd = TCP_INIT_CWND; - newtp->snd_cwnd_cnt = 0; - - /* There's a bubble in the pipe until at least the first ACK. */ - newtp->app_limited = ~0U; - - tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; - - newtp->rx_opt.saw_tstamp = 0; - - newtp->rx_opt.dsack = 0; - newtp->rx_opt.num_sacks = 0; - - newtp->urg_data = 0; - - if (sock_flag(newsk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(newsk, - keepalive_time_when(newtp)); - - newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; - newtp->rx_opt.sack_ok = ireq->sack_ok; - newtp->window_clamp = req->rsk_window_clamp; - newtp->rcv_ssthresh = req->rsk_rcv_wnd; - newtp->rcv_wnd = req->rsk_rcv_wnd; - newtp->rx_opt.wscale_ok = ireq->wscale_ok; - if (newtp->rx_opt.wscale_ok) { - newtp->rx_opt.snd_wscale = ireq->snd_wscale; - newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; - } else { - newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0; - newtp->window_clamp = min(newtp->window_clamp, 65535U); - } - newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) << - newtp->rx_opt.snd_wscale); - newtp->max_window = newtp->snd_wnd; - - if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; - newtp->rx_opt.ts_recent_stamp = get_seconds(); - newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; - } else { - newtp->rx_opt.ts_recent_stamp = 0; - newtp->tcp_header_len = sizeof(struct tcphdr); - } - newtp->tsoffset = treq->ts_off; + if (!newsk) + return NULL; + + newicsk = inet_csk(newsk); + newtp = tcp_sk(newsk); + oldtp = tcp_sk(sk); + + smc_check_reset_syn_req(oldtp, req, newtp); + + /* Now setup tcp_sock */ + newtp->pred_flags = 0; + + newtp->rcv_wup = newtp->copied_seq = + newtp->rcv_nxt = treq->rcv_isn + 1; + newtp->segs_in = 1; + + newtp->snd_sml = newtp->snd_una = + newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + + INIT_LIST_HEAD(&newtp->tsq_node); + INIT_LIST_HEAD(&newtp->tsorted_sent_queue); + + tcp_init_wl(newtp, treq->rcv_isn); + + newtp->srtt_us = 0; + newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); + newicsk->icsk_rto = TCP_TIMEOUT_INIT; + newicsk->icsk_ack.lrcvtime = tcp_jiffies32; + + newtp->packets_out = 0; + newtp->retrans_out = 0; + newtp->sacked_out = 0; + newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + newtp->tlp_high_seq = 0; + newtp->lsndtime = tcp_jiffies32; + newsk->sk_txhash = treq->txhash; + newtp->last_oow_ack_time = 0; + newtp->total_retrans = req->num_retrans; + + /* So many TCP implementations out there (incorrectly) count the + * initial SYN frame in their delayed-ACK and congestion control + * algorithms that we must have the following bandaid to talk + * efficiently to them. -DaveM + */ + newtp->snd_cwnd = TCP_INIT_CWND; + newtp->snd_cwnd_cnt = 0; + + /* There's a bubble in the pipe until at least the first ACK. */ + newtp->app_limited = ~0U; + + tcp_init_xmit_timers(newsk); + newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + + newtp->rx_opt.saw_tstamp = 0; + + newtp->rx_opt.dsack = 0; + newtp->rx_opt.num_sacks = 0; + + newtp->urg_data = 0; + + if (sock_flag(newsk, SOCK_KEEPOPEN)) + inet_csk_reset_keepalive_timer(newsk, + keepalive_time_when(newtp)); + + newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; + newtp->rx_opt.sack_ok = ireq->sack_ok; + newtp->window_clamp = req->rsk_window_clamp; + newtp->rcv_ssthresh = req->rsk_rcv_wnd; + newtp->rcv_wnd = req->rsk_rcv_wnd; + newtp->rx_opt.wscale_ok = ireq->wscale_ok; + if (newtp->rx_opt.wscale_ok) { + newtp->rx_opt.snd_wscale = ireq->snd_wscale; + newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; + } else { + newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0; + newtp->window_clamp = min(newtp->window_clamp, 65535U); + } + newtp->snd_wnd = ntohs(tcp_hdr(skb)->window) << newtp->rx_opt.snd_wscale; + newtp->max_window = newtp->snd_wnd; + + if (newtp->rx_opt.tstamp_ok) { + newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent_stamp = get_seconds(); + newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; + } else { + newtp->rx_opt.ts_recent_stamp = 0; + newtp->tcp_header_len = sizeof(struct tcphdr); + } + newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG - newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) - newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; + newtp->md5sig_info = NULL; /*XXX*/ + if (newtp->af_specific->md5_lookup(sk, newsk)) + newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif - if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) - newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; - newtp->rx_opt.mss_clamp = req->mss; - tcp_ecn_openreq_child(newtp, req); - newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; - newtp->syn_data_acked = 0; - newtp->rack.mstamp = 0; - newtp->rack.advanced = 0; - newtp->rack.reo_wnd_steps = 1; - newtp->rack.last_delivered = 0; - newtp->rack.reo_wnd_persist = 0; - newtp->rack.dsack_seen = 0; - - __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); - } + if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) + newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; + newtp->rx_opt.mss_clamp = req->mss; + tcp_ecn_openreq_child(newtp, req); + newtp->fastopen_req = NULL; + newtp->fastopen_rsk = NULL; + newtp->syn_data_acked = 0; + newtp->rack.mstamp = 0; + newtp->rack.advanced = 0; + newtp->rack.reo_wnd_steps = 1; + newtp->rack.last_delivered = 0; + newtp->rack.reo_wnd_persist = 0; + newtp->rack.dsack_seen = 0; + + __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 8cc7c3487330..f5aee641f825 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -180,9 +180,9 @@ out: return segs; } -struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct tcphdr *th; struct tcphdr *th2; @@ -220,7 +220,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) len = skb_gro_len(skb); flags = tcp_flag_word(th); - for (; (p = *head); head = &p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -233,7 +233,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) goto found; } - + p = NULL; goto out_check_final; found: @@ -263,7 +263,7 @@ found: flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); - if (flush || skb_gro_receive(head, skb)) { + if (flush || skb_gro_receive(p, skb)) { mss = 1; goto out_check_final; } @@ -277,7 +277,7 @@ out_check_final: TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) - pp = head; + pp = p; out: NAPI_GRO_CB(skb)->flush |= (flush != 0); @@ -302,7 +302,7 @@ int tcp_gro_complete(struct sk_buff *skb) } EXPORT_SYMBOL(tcp_gro_complete); -static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) +static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e08b409c71e..f8f6129160dd 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -973,17 +973,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) return HRTIMER_NORESTART; } -/* BBR congestion control needs pacing. - * Same remark for SO_MAX_PACING_RATE. - * sch_fq packet scheduler is efficiently handling pacing, - * but is not always installed/used. - * Return true if TCP stack should pace packets itself. - */ -static bool tcp_needs_internal_pacing(const struct sock *sk) -{ - return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; -} - static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) { u64 len_ns; @@ -995,9 +984,6 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) if (!rate || rate == ~0U) return; - /* Should account for header sizes as sch_fq does, - * but lets make things simple. - */ len_ns = (u64)skb->len * NSEC_PER_SEC; do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 69c54540d5b4..0c0522b79b43 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -343,10 +343,11 @@ out: return segs; } -struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup) +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, udp_lookup_t lookup) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; @@ -371,7 +372,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, unflush: flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -399,8 +400,8 @@ out: } EXPORT_SYMBOL(udp_gro_receive); -static struct sk_buff **udp4_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *udp4_gro_receive(struct list_head *head, + struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 27f59b61f70f..ddfa533a84e5 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -49,8 +49,8 @@ static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen) return 0; } -static struct sk_buff **esp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *esp6_gro_receive(struct list_head *head, + struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; diff --git a/net/ipv6/ila/Makefile b/net/ipv6/ila/Makefile index 4b32e5921e5c..b7739aba6e68 100644 --- a/net/ipv6/ila/Makefile +++ b/net/ipv6/ila/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_IPV6_ILA) += ila.o -ila-objs := ila_common.o ila_lwt.o ila_xlat.o +ila-objs := ila_main.o ila_common.o ila_lwt.o ila_xlat.o diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index 3c7a11b62334..1f747bcbec29 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -19,6 +19,7 @@ #include <linux/skbuff.h> #include <linux/types.h> #include <net/checksum.h> +#include <net/genetlink.h> #include <net/ip.h> #include <net/protocol.h> #include <uapi/linux/ila.h> @@ -104,9 +105,31 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, void ila_init_saved_csum(struct ila_params *p); +struct ila_net { + struct { + struct rhashtable rhash_table; + spinlock_t *locks; /* Bucket locks for entry manipulation */ + unsigned int locks_mask; + bool hooks_registered; + } xlat; +}; + int ila_lwt_init(void); void ila_lwt_fini(void); -int ila_xlat_init(void); -void ila_xlat_fini(void); + +int ila_xlat_init_net(struct net *net); +void ila_xlat_exit_net(struct net *net); + +int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info); +int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info); +int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info); +int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info); +int ila_xlat_nl_dump_start(struct netlink_callback *cb); +int ila_xlat_nl_dump_done(struct netlink_callback *cb); +int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb); + +extern unsigned int ila_net_id; + +extern struct genl_family ila_nl_family; #endif /* __ILA_H */ diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index 8c88ecf29b93..579310466eac 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -154,33 +154,3 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, iaddr->loc = p->locator; } -static int __init ila_init(void) -{ - int ret; - - ret = ila_lwt_init(); - - if (ret) - goto fail_lwt; - - ret = ila_xlat_init(); - if (ret) - goto fail_xlat; - - return 0; -fail_xlat: - ila_lwt_fini(); -fail_lwt: - return ret; -} - -static void __exit ila_fini(void) -{ - ila_xlat_fini(); - ila_lwt_fini(); -} - -module_init(ila_init); -module_exit(ila_fini); -MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); -MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c new file mode 100644 index 000000000000..18fac76b9520 --- /dev/null +++ b/net/ipv6/ila/ila_main.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <net/genetlink.h> +#include <net/ila.h> +#include <net/netns/generic.h> +#include <uapi/linux/genetlink.h> +#include "ila.h" + +static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { + [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, + [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, + [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, + [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, +}; + +static const struct genl_ops ila_nl_ops[] = { + { + .cmd = ILA_CMD_ADD, + .doit = ila_xlat_nl_cmd_add_mapping, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_DEL, + .doit = ila_xlat_nl_cmd_del_mapping, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_FLUSH, + .doit = ila_xlat_nl_cmd_flush, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_GET, + .doit = ila_xlat_nl_cmd_get_mapping, + .start = ila_xlat_nl_dump_start, + .dumpit = ila_xlat_nl_dump, + .done = ila_xlat_nl_dump_done, + .policy = ila_nl_policy, + }, +}; + +unsigned int ila_net_id; + +struct genl_family ila_nl_family __ro_after_init = { + .hdrsize = 0, + .name = ILA_GENL_NAME, + .version = ILA_GENL_VERSION, + .maxattr = ILA_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .ops = ila_nl_ops, + .n_ops = ARRAY_SIZE(ila_nl_ops), +}; + +static __net_init int ila_init_net(struct net *net) +{ + int err; + + err = ila_xlat_init_net(net); + if (err) + goto ila_xlat_init_fail; + + return 0; + +ila_xlat_init_fail: + return err; +} + +static __net_exit void ila_exit_net(struct net *net) +{ + ila_xlat_exit_net(net); +} + +static struct pernet_operations ila_net_ops = { + .init = ila_init_net, + .exit = ila_exit_net, + .id = &ila_net_id, + .size = sizeof(struct ila_net), +}; + +static int __init ila_init(void) +{ + int ret; + + ret = register_pernet_device(&ila_net_ops); + if (ret) + goto register_device_fail; + + ret = genl_register_family(&ila_nl_family); + if (ret) + goto register_family_fail; + + ret = ila_lwt_init(); + if (ret) + goto fail_lwt; + + return 0; + +fail_lwt: + genl_unregister_family(&ila_nl_family); +register_family_fail: + unregister_pernet_device(&ila_net_ops); +register_device_fail: + return ret; +} + +static void __exit ila_fini(void) +{ + ila_lwt_fini(); + genl_unregister_family(&ila_nl_family); + unregister_pernet_device(&ila_net_ops); +} + +module_init(ila_init); +module_exit(ila_fini); +MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 10ae13560b40..51a15ce50a64 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -22,36 +22,14 @@ struct ila_map { struct rcu_head rcu; }; -static unsigned int ila_net_id; - -struct ila_net { - struct rhashtable rhash_table; - spinlock_t *locks; /* Bucket locks for entry manipulation */ - unsigned int locks_mask; - bool hooks_registered; -}; - +#define MAX_LOCKS 1024 #define LOCKS_PER_CPU 10 static int alloc_ila_locks(struct ila_net *ilan) { - unsigned int i, size; - unsigned int nr_pcpus = num_possible_cpus(); - - nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); - size = roundup_pow_of_two(nr_pcpus * LOCKS_PER_CPU); - - if (sizeof(spinlock_t) != 0) { - ilan->locks = kvmalloc_array(size, sizeof(spinlock_t), - GFP_KERNEL); - if (!ilan->locks) - return -ENOMEM; - for (i = 0; i < size; i++) - spin_lock_init(&ilan->locks[i]); - } - ilan->locks_mask = size - 1; - - return 0; + return alloc_bucket_spinlocks(&ilan->xlat.locks, &ilan->xlat.locks_mask, + MAX_LOCKS, LOCKS_PER_CPU, + GFP_KERNEL); } static u32 hashrnd __read_mostly; @@ -71,7 +49,7 @@ static inline u32 ila_locator_hash(struct ila_locator loc) static inline spinlock_t *ila_get_lock(struct ila_net *ilan, struct ila_locator loc) { - return &ilan->locks[ila_locator_hash(loc) & ilan->locks_mask]; + return &ilan->xlat.locks[ila_locator_hash(loc) & ilan->xlat.locks_mask]; } static inline int ila_cmp_wildcards(struct ila_map *ila, @@ -115,16 +93,6 @@ static const struct rhashtable_params rht_params = { .obj_cmpfn = ila_cmpfn, }; -static struct genl_family ila_nl_family; - -static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { - [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, - [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, - [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, - [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, - [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, -}; - static int parse_nl_config(struct genl_info *info, struct ila_xlat_params *xp) { @@ -162,7 +130,7 @@ static inline struct ila_map *ila_lookup_wildcards(struct ila_addr *iaddr, { struct ila_map *ila; - ila = rhashtable_lookup_fast(&ilan->rhash_table, &iaddr->loc, + ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &iaddr->loc, rht_params); while (ila) { if (!ila_cmp_wildcards(ila, iaddr, ifindex)) @@ -179,7 +147,7 @@ static inline struct ila_map *ila_lookup_by_params(struct ila_xlat_params *xp, { struct ila_map *ila; - ila = rhashtable_lookup_fast(&ilan->rhash_table, + ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); while (ila) { @@ -196,9 +164,9 @@ static inline void ila_release(struct ila_map *ila) kfree_rcu(ila, rcu); } -static void ila_free_cb(void *ptr, void *arg) +static void ila_free_node(struct ila_map *ila) { - struct ila_map *ila = (struct ila_map *)ptr, *next; + struct ila_map *next; /* Assume rcu_readlock held */ while (ila) { @@ -208,6 +176,11 @@ static void ila_free_cb(void *ptr, void *arg) } } +static void ila_free_cb(void *ptr, void *arg) +{ + ila_free_node((struct ila_map *)ptr); +} + static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int @@ -235,7 +208,7 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = 0, order; - if (!ilan->hooks_registered) { + if (!ilan->xlat.hooks_registered) { /* We defer registering net hooks in the namespace until the * first mapping is added. */ @@ -244,7 +217,7 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) if (err) return err; - ilan->hooks_registered = true; + ilan->xlat.hooks_registered = true; } ila = kzalloc(sizeof(*ila), GFP_KERNEL); @@ -259,12 +232,12 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) spin_lock(lock); - head = rhashtable_lookup_fast(&ilan->rhash_table, + head = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); if (!head) { /* New entry for the rhash_table */ - err = rhashtable_lookup_insert_fast(&ilan->rhash_table, + err = rhashtable_lookup_insert_fast(&ilan->xlat.rhash_table, &ila->node, rht_params); } else { struct ila_map *tila = head, *prev = NULL; @@ -290,7 +263,7 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) } else { /* Make this ila new head */ RCU_INIT_POINTER(ila->next, head); - err = rhashtable_replace_fast(&ilan->rhash_table, + err = rhashtable_replace_fast(&ilan->xlat.rhash_table, &head->node, &ila->node, rht_params); if (err) @@ -316,7 +289,7 @@ static int ila_del_mapping(struct net *net, struct ila_xlat_params *xp) spin_lock(lock); - head = rhashtable_lookup_fast(&ilan->rhash_table, + head = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); ila = head; @@ -346,15 +319,15 @@ static int ila_del_mapping(struct net *net, struct ila_xlat_params *xp) * table */ err = rhashtable_replace_fast( - &ilan->rhash_table, &ila->node, + &ilan->xlat.rhash_table, &ila->node, &head->node, rht_params); if (err) goto out; } else { /* Entry no longer used */ - err = rhashtable_remove_fast(&ilan->rhash_table, - &ila->node, - rht_params); + err = rhashtable_remove_fast( + &ilan->xlat.rhash_table, + &ila->node, rht_params); } } @@ -369,7 +342,7 @@ out: return err; } -static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) +int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_xlat_params p; @@ -382,7 +355,7 @@ static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) return ila_add_mapping(net, &p); } -static int ila_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) +int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_xlat_params xp; @@ -397,6 +370,59 @@ static int ila_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) return 0; } +static inline spinlock_t *lock_from_ila_map(struct ila_net *ilan, + struct ila_map *ila) +{ + return ila_get_lock(ilan, ila->xp.ip.locator_match); +} + +int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_net *ilan = net_generic(net, ila_net_id); + struct rhashtable_iter iter; + struct ila_map *ila; + spinlock_t *lock; + int ret; + + ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter, GFP_KERNEL); + if (ret) + goto done; + + rhashtable_walk_start(&iter); + + for (;;) { + ila = rhashtable_walk_next(&iter); + + if (IS_ERR(ila)) { + if (PTR_ERR(ila) == -EAGAIN) + continue; + ret = PTR_ERR(ila); + goto done; + } else if (!ila) { + break; + } + + lock = lock_from_ila_map(ilan, ila); + + spin_lock(lock); + + ret = rhashtable_remove_fast(&ilan->xlat.rhash_table, + &ila->node, rht_params); + if (!ret) + ila_free_node(ila); + + spin_unlock(lock); + + if (ret) + break; + } + +done: + rhashtable_walk_stop(&iter); + return ret; +} + static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) { if (nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR, @@ -434,7 +460,7 @@ nla_put_failure: return -EMSGSIZE; } -static int ila_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) +int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_net *ilan = net_generic(net, ila_net_id); @@ -475,27 +501,34 @@ out_free: struct ila_dump_iter { struct rhashtable_iter rhiter; + int skip; }; -static int ila_nl_dump_start(struct netlink_callback *cb) +int ila_xlat_nl_dump_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct ila_net *ilan = net_generic(net, ila_net_id); - struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; + struct ila_dump_iter *iter; + int ret; - if (!iter) { - iter = kmalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) - return -ENOMEM; + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; - cb->args[0] = (long)iter; + ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter->rhiter, + GFP_KERNEL); + if (ret) { + kfree(iter); + return ret; } - return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter, - GFP_KERNEL); + iter->skip = 0; + cb->args[0] = (long)iter; + + return ret; } -static int ila_nl_dump_done(struct netlink_callback *cb) +int ila_xlat_nl_dump_done(struct netlink_callback *cb) { struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; @@ -506,24 +539,49 @@ static int ila_nl_dump_done(struct netlink_callback *cb) return 0; } -static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) +int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; struct rhashtable_iter *rhiter = &iter->rhiter; + int skip = iter->skip; struct ila_map *ila; int ret; rhashtable_walk_start(rhiter); - for (;;) { - ila = rhashtable_walk_next(rhiter); + /* Get first entry */ + ila = rhashtable_walk_peek(rhiter); + + if (ila && !IS_ERR(ila) && skip) { + /* Skip over visited entries */ + while (ila && skip) { + /* Skip over any ila entries in this list that we + * have already dumped. + */ + ila = rcu_access_pointer(ila->next); + skip--; + } + } + + skip = 0; + + for (;;) { if (IS_ERR(ila)) { - if (PTR_ERR(ila) == -EAGAIN) - continue; ret = PTR_ERR(ila); - goto done; + if (ret == -EAGAIN) { + /* Table has changed and iter has reset. Return + * -EAGAIN to the application even if we have + * written data to the skb. The application + * needs to deal with this. + */ + + goto out_ret; + } else { + break; + } } else if (!ila) { + ret = 0; break; } @@ -532,90 +590,54 @@ static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, ILA_CMD_GET); if (ret) - goto done; + goto out; + skip++; ila = rcu_access_pointer(ila->next); } + + skip = 0; + ila = rhashtable_walk_next(rhiter); } - ret = skb->len; +out: + iter->skip = skip; + ret = (skb->len ? : ret); -done: +out_ret: rhashtable_walk_stop(rhiter); return ret; } -static const struct genl_ops ila_nl_ops[] = { - { - .cmd = ILA_CMD_ADD, - .doit = ila_nl_cmd_add_mapping, - .policy = ila_nl_policy, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = ILA_CMD_DEL, - .doit = ila_nl_cmd_del_mapping, - .policy = ila_nl_policy, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = ILA_CMD_GET, - .doit = ila_nl_cmd_get_mapping, - .start = ila_nl_dump_start, - .dumpit = ila_nl_dump, - .done = ila_nl_dump_done, - .policy = ila_nl_policy, - }, -}; - -static struct genl_family ila_nl_family __ro_after_init = { - .hdrsize = 0, - .name = ILA_GENL_NAME, - .version = ILA_GENL_VERSION, - .maxattr = ILA_ATTR_MAX, - .netnsok = true, - .parallel_ops = true, - .module = THIS_MODULE, - .ops = ila_nl_ops, - .n_ops = ARRAY_SIZE(ila_nl_ops), -}; - #define ILA_HASH_TABLE_SIZE 1024 -static __net_init int ila_init_net(struct net *net) +int ila_xlat_init_net(struct net *net) { - int err; struct ila_net *ilan = net_generic(net, ila_net_id); + int err; err = alloc_ila_locks(ilan); if (err) return err; - rhashtable_init(&ilan->rhash_table, &rht_params); + rhashtable_init(&ilan->xlat.rhash_table, &rht_params); return 0; } -static __net_exit void ila_exit_net(struct net *net) +void ila_xlat_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); - rhashtable_free_and_destroy(&ilan->rhash_table, ila_free_cb, NULL); + rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL); - kvfree(ilan->locks); + free_bucket_spinlocks(ilan->xlat.locks); - if (ilan->hooks_registered) + if (ilan->xlat.hooks_registered) nf_unregister_net_hooks(net, ila_nf_hook_ops, ARRAY_SIZE(ila_nf_hook_ops)); } -static struct pernet_operations ila_net_ops = { - .init = ila_init_net, - .exit = ila_exit_net, - .id = &ila_net_id, - .size = sizeof(struct ila_net), -}; - static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) { struct ila_map *ila; @@ -642,28 +664,3 @@ static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) return 0; } -int __init ila_xlat_init(void) -{ - int ret; - - ret = register_pernet_device(&ila_net_ops); - if (ret) - goto exit; - - ret = genl_register_family(&ila_nl_family); - if (ret < 0) - goto unregister; - - return 0; - -unregister: - unregister_pernet_device(&ila_net_ops); -exit: - return ret; -} - -void ila_xlat_fini(void) -{ - genl_unregister_family(&ila_nl_family); - unregister_pernet_device(&ila_net_ops); -} diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c8cf2fdbb13b..367177786e34 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -990,6 +990,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = key->tos; + if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + goto tx_err; md = ip_tunnel_info_opts(tun_info); if (!md) goto tx_err; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 5b3f2f89ef41..37ff4805b20c 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -163,11 +163,11 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph, return len; } -static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ipv6_gro_receive(struct list_head *head, + struct sk_buff *skb) { const struct net_offload *ops; - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct ipv6hdr *iph; unsigned int nlen; @@ -214,7 +214,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, flush--; nlen = skb_network_header_len(skb); - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct ipv6hdr *iph2; __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ @@ -263,8 +263,8 @@ out: return pp; } -static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head, + struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ @@ -278,8 +278,8 @@ static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head, return ipv6_gro_receive(head, skb); } -static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ip4ip6_gro_receive(struct list_head *head, + struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0d0f0053bb11..d0b7e0249c13 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -32,6 +32,7 @@ #include <linux/seq_file.h> #include <linux/init.h> #include <linux/compat.h> +#include <linux/rhashtable.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/raw.h> diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index b397a8fe88b9..c6bf580d0f33 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -36,7 +36,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv6_packet(struct nf_log_buf *m, +static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int ip6hoff, int recurse) @@ -258,7 +258,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (recurse) { nf_log_buf_add(m, "["); - dump_ipv6_packet(m, info, skb, + dump_ipv6_packet(net, m, info, skb, ptr + sizeof(_icmp6h), 0); nf_log_buf_add(m, "] "); } @@ -278,7 +278,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && recurse) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (recurse && skb->mark) @@ -365,7 +365,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv6_mac_header(m, loginfo, skb); - dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + dump_ipv6_packet(net, m, loginfo, skb, skb_network_offset(skb), 1); nf_log_buf_close(m); } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 0fdf2a55e746..8d0ba757a46c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -17,6 +17,7 @@ #include <linux/net.h> #include <linux/in6.h> #include <linux/slab.h> +#include <linux/rhashtable.h> #include <net/ipv6.h> #include <net/protocol.h> diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 558fe8cc6d43..8546f94f30d4 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -22,6 +22,7 @@ #include <linux/icmpv6.h> #include <linux/mroute6.h> #include <linux/slab.h> +#include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 278e49cd67d4..e72947c99454 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -15,8 +15,8 @@ #include <net/ip6_checksum.h> #include "ip6_offload.h" -static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *tcp6_gro_receive(struct list_head *head, + struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 03a2ff3fe1e6..95dee9ca8d22 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -114,8 +114,8 @@ out: return segs; } -static struct sk_buff **udp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *udp6_gro_receive(struct list_head *head, + struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 40261cb68e83..1ea285bad84b 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -322,8 +322,7 @@ int l2tp_session_register(struct l2tp_session *session, if (tunnel->version == L2TP_HDR_VER_3) { pn = l2tp_pernet(tunnel->l2tp_net); - g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net), - session->session_id); + g_head = l2tp_session_id_hash_2(pn, session->session_id); spin_lock_bh(&pn->l2tp_session_hlist_lock); @@ -783,7 +782,7 @@ EXPORT_SYMBOL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ -int l2tp_session_queue_purge(struct l2tp_session *session) +static int l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; BUG_ON(!session); @@ -794,7 +793,6 @@ int l2tp_session_queue_purge(struct l2tp_session *session) } return 0; } -EXPORT_SYMBOL_GPL(l2tp_session_queue_purge); /* Internal UDP receive frame. Do the real work of receiving an L2TP data frame * here. The skb is not on a list when we get here. @@ -1009,8 +1007,8 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) return bufp - optr; } -static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, - struct flowi *fl, size_t data_len) +static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, + struct flowi *fl, size_t data_len) { struct l2tp_tunnel *tunnel = session->tunnel; unsigned int len = skb->len; @@ -1052,8 +1050,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, atomic_long_inc(&tunnel->stats.tx_errors); atomic_long_inc(&session->stats.tx_errors); } - - return 0; } /* If caller requires the skb to have a ppp header, the header must be @@ -1193,7 +1189,7 @@ end: /* When the tunnel is closed, all the attached sessions need to go too. */ -void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) +static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { int hash; struct hlist_node *walk; @@ -1242,7 +1238,6 @@ again: } write_unlock_bh(&tunnel->hlist_lock); } -EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index c199020f8a8a..a5c09d3a5698 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -180,9 +180,6 @@ struct l2tp_tunnel { struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; -#ifdef CONFIG_DEBUG_FS - void (*show)(struct seq_file *m, void *arg); -#endif int (*recv_payload_hook)(struct sk_buff *skb); void (*old_sk_destruct)(struct sock *); struct sock *sock; /* Parent socket */ @@ -190,8 +187,6 @@ struct l2tp_tunnel { * was created by userspace */ struct work_struct del_work; - - uint8_t priv[0]; /* private data */ }; struct l2tp_nl_cmd_ops { @@ -201,11 +196,6 @@ struct l2tp_nl_cmd_ops { int (*session_delete)(struct l2tp_session *session); }; -static inline void *l2tp_tunnel_priv(struct l2tp_tunnel *tunnel) -{ - return &tunnel->priv[0]; -} - static inline void *l2tp_session_priv(struct l2tp_session *session) { return &session->priv[0]; @@ -229,7 +219,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg); -void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, @@ -244,7 +233,6 @@ void l2tp_session_free(struct l2tp_session *session); void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length, int (*payload_hook)(struct sk_buff *skb)); -int l2tp_session_queue_purge(struct l2tp_session *session); int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); void l2tp_session_set_header_len(struct l2tp_session *session, int version); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index e87686f7d63c..b5d7dde003ef 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -177,9 +177,6 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) atomic_long_read(&tunnel->stats.rx_packets), atomic_long_read(&tunnel->stats.rx_bytes), atomic_long_read(&tunnel->stats.rx_errors)); - - if (tunnel->show != NULL) - tunnel->show(m, tunnel); } static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index e398797878a9..9ac02c93df98 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -424,12 +424,6 @@ static void pppol2tp_put_sk(struct rcu_head *head) sock_put(ps->__sk); } -/* Called by l2tp_core when a session socket is being closed. - */ -static void pppol2tp_session_close(struct l2tp_session *session) -{ -} - /* Really kill the session socket. (Called from sock_put() if * refcnt == 0.) */ @@ -573,7 +567,6 @@ static void pppol2tp_session_init(struct l2tp_session *session) struct dst_entry *dst; session->recv_skb = pppol2tp_recv; - session->session_close = pppol2tp_session_close; #if IS_ENABLED(CONFIG_L2TP_DEBUGFS) session->show = pppol2tp_show; #endif @@ -595,40 +588,113 @@ static void pppol2tp_session_init(struct l2tp_session *session) } } +struct l2tp_connect_info { + u8 version; + int fd; + u32 tunnel_id; + u32 peer_tunnel_id; + u32 session_id; + u32 peer_session_id; +}; + +static int pppol2tp_sockaddr_get_info(const void *sa, int sa_len, + struct l2tp_connect_info *info) +{ + switch (sa_len) { + case sizeof(struct sockaddr_pppol2tp): + { + const struct sockaddr_pppol2tp *sa_v2in4 = sa; + + if (sa_v2in4->sa_protocol != PX_PROTO_OL2TP) + return -EINVAL; + + info->version = 2; + info->fd = sa_v2in4->pppol2tp.fd; + info->tunnel_id = sa_v2in4->pppol2tp.s_tunnel; + info->peer_tunnel_id = sa_v2in4->pppol2tp.d_tunnel; + info->session_id = sa_v2in4->pppol2tp.s_session; + info->peer_session_id = sa_v2in4->pppol2tp.d_session; + + break; + } + case sizeof(struct sockaddr_pppol2tpv3): + { + const struct sockaddr_pppol2tpv3 *sa_v3in4 = sa; + + if (sa_v3in4->sa_protocol != PX_PROTO_OL2TP) + return -EINVAL; + + info->version = 3; + info->fd = sa_v3in4->pppol2tp.fd; + info->tunnel_id = sa_v3in4->pppol2tp.s_tunnel; + info->peer_tunnel_id = sa_v3in4->pppol2tp.d_tunnel; + info->session_id = sa_v3in4->pppol2tp.s_session; + info->peer_session_id = sa_v3in4->pppol2tp.d_session; + + break; + } + case sizeof(struct sockaddr_pppol2tpin6): + { + const struct sockaddr_pppol2tpin6 *sa_v2in6 = sa; + + if (sa_v2in6->sa_protocol != PX_PROTO_OL2TP) + return -EINVAL; + + info->version = 2; + info->fd = sa_v2in6->pppol2tp.fd; + info->tunnel_id = sa_v2in6->pppol2tp.s_tunnel; + info->peer_tunnel_id = sa_v2in6->pppol2tp.d_tunnel; + info->session_id = sa_v2in6->pppol2tp.s_session; + info->peer_session_id = sa_v2in6->pppol2tp.d_session; + + break; + } + case sizeof(struct sockaddr_pppol2tpv3in6): + { + const struct sockaddr_pppol2tpv3in6 *sa_v3in6 = sa; + + if (sa_v3in6->sa_protocol != PX_PROTO_OL2TP) + return -EINVAL; + + info->version = 3; + info->fd = sa_v3in6->pppol2tp.fd; + info->tunnel_id = sa_v3in6->pppol2tp.s_tunnel; + info->peer_tunnel_id = sa_v3in6->pppol2tp.d_tunnel; + info->session_id = sa_v3in6->pppol2tp.s_session; + info->peer_session_id = sa_v3in6->pppol2tp.d_session; + + break; + } + default: + return -EINVAL; + } + + return 0; +} + /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket */ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len, int flags) { struct sock *sk = sock->sk; - struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr; struct pppox_sock *po = pppox_sk(sk); struct l2tp_session *session = NULL; + struct l2tp_connect_info info; struct l2tp_tunnel *tunnel; struct pppol2tp_session *ps; struct l2tp_session_cfg cfg = { 0, }; - int error = 0; - u32 tunnel_id, peer_tunnel_id; - u32 session_id, peer_session_id; bool drop_refcnt = false; bool drop_tunnel = false; bool new_session = false; bool new_tunnel = false; - int ver = 2; - int fd; - - lock_sock(sk); - - error = -EINVAL; + int error; - if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) && - sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) && - sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) && - sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6)) - goto end; + error = pppol2tp_sockaddr_get_info(uservaddr, sockaddr_len, &info); + if (error < 0) + return error; - if (sp->sa_protocol != PX_PROTO_OL2TP) - goto end; + lock_sock(sk); /* Check for already bound sockets */ error = -EBUSY; @@ -640,56 +706,12 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (sk->sk_user_data) goto end; /* socket is already attached */ - /* Get params from socket address. Handle L2TPv2 and L2TPv3. - * This is nasty because there are different sockaddr_pppol2tp - * structs for L2TPv2, L2TPv3, over IPv4 and IPv6. We use - * the sockaddr size to determine which structure the caller - * is using. - */ - peer_tunnel_id = 0; - if (sockaddr_len == sizeof(struct sockaddr_pppol2tp)) { - fd = sp->pppol2tp.fd; - tunnel_id = sp->pppol2tp.s_tunnel; - peer_tunnel_id = sp->pppol2tp.d_tunnel; - session_id = sp->pppol2tp.s_session; - peer_session_id = sp->pppol2tp.d_session; - } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3)) { - struct sockaddr_pppol2tpv3 *sp3 = - (struct sockaddr_pppol2tpv3 *) sp; - ver = 3; - fd = sp3->pppol2tp.fd; - tunnel_id = sp3->pppol2tp.s_tunnel; - peer_tunnel_id = sp3->pppol2tp.d_tunnel; - session_id = sp3->pppol2tp.s_session; - peer_session_id = sp3->pppol2tp.d_session; - } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpin6)) { - struct sockaddr_pppol2tpin6 *sp6 = - (struct sockaddr_pppol2tpin6 *) sp; - fd = sp6->pppol2tp.fd; - tunnel_id = sp6->pppol2tp.s_tunnel; - peer_tunnel_id = sp6->pppol2tp.d_tunnel; - session_id = sp6->pppol2tp.s_session; - peer_session_id = sp6->pppol2tp.d_session; - } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3in6)) { - struct sockaddr_pppol2tpv3in6 *sp6 = - (struct sockaddr_pppol2tpv3in6 *) sp; - ver = 3; - fd = sp6->pppol2tp.fd; - tunnel_id = sp6->pppol2tp.s_tunnel; - peer_tunnel_id = sp6->pppol2tp.d_tunnel; - session_id = sp6->pppol2tp.s_session; - peer_session_id = sp6->pppol2tp.d_session; - } else { - error = -EINVAL; - goto end; /* bad socket address */ - } - /* Don't bind if tunnel_id is 0 */ error = -EINVAL; - if (tunnel_id == 0) + if (!info.tunnel_id) goto end; - tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id); + tunnel = l2tp_tunnel_get(sock_net(sk), info.tunnel_id); if (tunnel) drop_tunnel = true; @@ -697,7 +719,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, * peer_session_id is 0. Otherwise look up tunnel using supplied * tunnel id. */ - if ((session_id == 0) && (peer_session_id == 0)) { + if (!info.session_id && !info.peer_session_id) { if (tunnel == NULL) { struct l2tp_tunnel_cfg tcfg = { .encap = L2TP_ENCAPTYPE_UDP, @@ -707,12 +729,16 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, /* Prevent l2tp_tunnel_register() from trying to set up * a kernel socket. */ - if (fd < 0) { + if (info.fd < 0) { error = -EBADF; goto end; } - error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel); + error = l2tp_tunnel_create(sock_net(sk), info.fd, + info.version, + info.tunnel_id, + info.peer_tunnel_id, &tcfg, + &tunnel); if (error < 0) goto end; @@ -741,9 +767,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, tunnel->recv_payload_hook = pppol2tp_recv_payload_hook; if (tunnel->peer_tunnel_id == 0) - tunnel->peer_tunnel_id = peer_tunnel_id; + tunnel->peer_tunnel_id = info.peer_tunnel_id; - session = l2tp_session_get(sock_net(sk), tunnel, session_id); + session = l2tp_session_get(sock_net(sk), tunnel, info.session_id); if (session) { drop_refcnt = true; @@ -772,8 +798,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, cfg.pw_type = L2TP_PWTYPE_PPP; session = l2tp_session_create(sizeof(struct pppol2tp_session), - tunnel, session_id, - peer_session_id, &cfg); + tunnel, info.session_id, + info.peer_session_id, &cfg); if (IS_ERR(session)) { error = PTR_ERR(session); goto end; diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index e3589ade62e0..bb707789ef2b 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -12,6 +12,7 @@ mac80211-y := \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ vht.o \ + he.o \ ibss.o \ iface.o \ rate.o \ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index e83c19d4c292..6a4f154c99f6 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -245,6 +245,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, }; int i, ret = -EOPNOTSUPP; u16 status = WLAN_STATUS_REQUEST_DECLINED; + u16 max_buf_size; if (tid >= IEEE80211_FIRST_TSPEC_TSID) { ht_dbg(sta->sdata, @@ -268,13 +269,18 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, goto end; } + if (sta->sta.he_cap.has_he) + max_buf_size = IEEE80211_MAX_AMPDU_BUF; + else + max_buf_size = IEEE80211_MAX_AMPDU_BUF_HT; + /* sanity check for incoming parameters: * check if configuration can support the BA policy * and if buffer size does not exceeds max value */ /* XXX: check own ht delayed BA capability?? */ if (((ba_policy != 1) && (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) || - (buf_size > IEEE80211_MAX_AMPDU_BUF)) { + (buf_size > max_buf_size)) { status = WLAN_STATUS_INVALID_QOS_PARAM; ht_dbg_ratelimited(sta->sdata, "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", @@ -283,7 +289,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, } /* determine default buffer size */ if (buf_size == 0) - buf_size = IEEE80211_MAX_AMPDU_BUF; + buf_size = max_buf_size; /* make sure the size doesn't exceed the maximum supported by the hw */ if (buf_size > sta->sta.max_rx_aggregation_subframes) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index ac4295296514..69e831bc317b 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -463,6 +463,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) .timeout = 0, }; int ret; + u16 buf_size; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); @@ -511,11 +512,22 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) sta->ampdu_mlme.addba_req_num[tid]++; spin_unlock_bh(&sta->lock); + if (sta->sta.he_cap.has_he) { + buf_size = local->hw.max_tx_aggregation_subframes; + } else { + /* + * We really should use what the driver told us it will + * transmit as the maximum, but certain APs (e.g. the + * LinkSys WRT120N with FW v1.0.07 build 002 Jun 18 2012) + * will crash when we use a lower number. + */ + buf_size = IEEE80211_MAX_AMPDU_BUF_HT; + } + /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, tid_tx->dialog_token, params.ssn, - IEEE80211_MAX_AMPDU_BUF, - tid_tx->timeout); + buf_size, tid_tx->timeout); } /* @@ -905,8 +917,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, { struct tid_ampdu_tx *tid_tx; struct ieee80211_txq *txq; - u16 capab, tid; - u8 buf_size; + u16 capab, tid, buf_size; bool amsdu; capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index bdf6fa78d0d2..02f3672e7b5e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1412,6 +1412,11 @@ static int sta_apply_parameters(struct ieee80211_local *local, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, sta); + if (params->he_capa) + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, + (void *)params->he_capa, + params->he_capa_len, sta); + if (params->opmode_notif_used) { /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it @@ -3486,7 +3491,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, } local_bh_disable(); - ieee80211_xmit(sdata, sta, skb); + ieee80211_xmit(sdata, sta, skb, 0); local_bh_enable(); ret = 0; diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c index 690c142a7a44..5ac743816b59 100644 --- a/net/mac80211/ethtool.c +++ b/net/mac80211/ethtool.c @@ -116,16 +116,16 @@ static void ieee80211_get_stats(struct net_device *dev, data[i++] = sta->sta_state; - if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) data[i] = 100000ULL * cfg80211_calculate_bitrate(&sinfo.txrate); i++; - if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE)) + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE)) data[i] = 100000ULL * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; - if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL_AVG)) + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG)) data[i] = (u8)sinfo.signal_avg; i++; } else { diff --git a/net/mac80211/he.c b/net/mac80211/he.c new file mode 100644 index 000000000000..769078ed5a12 --- /dev/null +++ b/net/mac80211/he.c @@ -0,0 +1,55 @@ +/* + * HE handling + * + * Copyright(c) 2017 Intel Deutschland GmbH + * + * 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. + */ + +#include "ieee80211_i.h" + +void +ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + const u8 *he_cap_ie, u8 he_cap_len, + struct sta_info *sta) +{ + struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; + struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie; + u8 he_ppe_size; + u8 mcs_nss_size; + u8 he_total_size; + + memset(he_cap, 0, sizeof(*he_cap)); + + if (!he_cap_ie || !ieee80211_get_he_sta_cap(sband)) + return; + + /* Make sure size is OK */ + mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem); + he_ppe_size = + ieee80211_he_ppe_size(he_cap_ie[sizeof(he_cap->he_cap_elem) + + mcs_nss_size], + he_cap_ie_elem->phy_cap_info); + he_total_size = sizeof(he_cap->he_cap_elem) + mcs_nss_size + + he_ppe_size; + if (he_cap_len < he_total_size) + return; + + memcpy(&he_cap->he_cap_elem, he_cap_ie, sizeof(he_cap->he_cap_elem)); + + /* HE Tx/Rx HE MCS NSS Support Field */ + memcpy(&he_cap->he_mcs_nss_supp, + &he_cap_ie[sizeof(he_cap->he_cap_elem)], mcs_nss_size); + + /* Check if there are (optional) PPE Thresholds */ + if (he_cap->he_cap_elem.phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) + memcpy(he_cap->ppe_thres, + &he_cap_ie[sizeof(he_cap->he_cap_elem) + mcs_nss_size], + he_ppe_size); + + he_cap->has_he = true; +} diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 26a7ba3b698f..f849ea814993 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -352,7 +352,7 @@ void ieee80211_ba_session_work(struct work_struct *work) test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, - IEEE80211_MAX_AMPDU_BUF, + IEEE80211_MAX_AMPDU_BUF_HT, false, true); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d1978aa1c15d..172aeae21ae9 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -165,6 +165,7 @@ 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) @@ -364,6 +365,7 @@ enum ieee80211_sta_flags { IEEE80211_STA_DISABLE_160MHZ = BIT(13), IEEE80211_STA_DISABLE_WMM = BIT(14), IEEE80211_STA_ENABLE_RRM = BIT(15), + IEEE80211_STA_DISABLE_HE = BIT(16), }; struct ieee80211_mgd_auth_data { @@ -1453,6 +1455,10 @@ struct ieee802_11_elems { const struct ieee80211_vht_cap *vht_cap_elem; const struct ieee80211_vht_operation *vht_operation; const struct ieee80211_meshconf_ie *mesh_config; + const u8 *he_cap; + const struct ieee80211_he_operation *he_operation; + const struct ieee80211_mu_edca_param_set *mu_edca_param_set; + const u8 *uora_element; const u8 *mesh_id; const u8 *peering; const __le16 *awake_window; @@ -1482,6 +1488,7 @@ struct ieee802_11_elems { u8 ext_supp_rates_len; u8 wmm_info_len; u8 wmm_param_len; + u8 he_cap_len; u8 mesh_id_len; u8 peering_len; u8 preq_len; @@ -1824,6 +1831,13 @@ void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, enum nl80211_chan_width ieee80211_sta_rx_bw_to_chan_width(struct sta_info *sta); +/* HE */ +void +ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + const u8 *he_cap_ie, u8 he_cap_len, + struct sta_info *sta); + /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, @@ -1880,19 +1894,20 @@ 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); + struct sta_info *sta, struct sk_buff *skb, + u32 txdata_flags); void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, - enum nl80211_band band); + enum nl80211_band band, u32 txdata_flags); static inline void ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, - enum nl80211_band band) + enum nl80211_band band, u32 txdata_flags) { rcu_read_lock(); - __ieee80211_tx_skb_tid_band(sdata, skb, tid, band); + __ieee80211_tx_skb_tid_band(sdata, skb, tid, band, txdata_flags); rcu_read_unlock(); } @@ -1910,7 +1925,7 @@ 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); + chanctx_conf->def.chan->band, 0); rcu_read_unlock(); } @@ -2031,26 +2046,27 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, const u8 *bssid, u16 stype, u16 reason, bool send_frame, u8 *frame_buf); + +enum { + IEEE80211_PROBE_FLAG_DIRECTED = BIT(0), + IEEE80211_PROBE_FLAG_MIN_CONTENT = BIT(1), + IEEE80211_PROBE_FLAG_RANDOM_SN = BIT(2), +}; + int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, size_t buffer_len, struct ieee80211_scan_ies *ie_desc, const u8 *ie, size_t ie_len, u8 bands_used, u32 *rate_masks, - struct cfg80211_chan_def *chandef); + struct cfg80211_chan_def *chandef, + u32 flags); struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, const u8 *src, const u8 *dst, u32 ratemask, struct ieee80211_channel *chan, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, - bool directed); -void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, - const u8 *src, const u8 *dst, - const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len, - u32 ratemask, bool directed, u32 tx_flags, - struct ieee80211_channel *channel, bool scan); - + u32 flags); u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band band, u32 *basic_rates); @@ -2073,6 +2089,9 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef); +u8 *ieee80211_ie_build_he_cap(u8 *pos, + const struct ieee80211_sta_he_cap *he_cap, + u8 *end); int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index fb73451ed85e..4fb2709cb527 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -3,6 +3,7 @@ * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2017 Intel Deutschland GmbH * * 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 @@ -557,10 +558,19 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211); - if (!ops->hw_scan) + if (!ops->hw_scan) { wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN | NL80211_FEATURE_AP_SCAN; - + /* + * if the driver behaves correctly using the probe request + * (template) from mac80211, then both of these should be + * supported even with hw scan - but let drivers opt in. + */ + wiphy_ext_feature_set(wiphy, + NL80211_EXT_FEATURE_SCAN_RANDOM_SN); + wiphy_ext_feature_set(wiphy, + NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT); + } if (!ops->set_key) wiphy->flags |= WIPHY_FLAG_IBSS_RSN; @@ -588,8 +598,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local->hw.queues = 1; local->hw.max_rates = 1; local->hw.max_report_rates = 0; - local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; - local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; + local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT; + local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT; local->hw.offchannel_tx_hw_queue = IEEE80211_INVAL_HW_QUEUE; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; @@ -816,7 +826,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) int result, i; enum nl80211_band band; int channels, max_bitrates; - bool supp_ht, supp_vht; + bool supp_ht, supp_vht, supp_he; netdev_features_t feature_whitelist; struct cfg80211_chan_def dflt_chandef = {}; @@ -896,6 +906,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) max_bitrates = 0; supp_ht = false; supp_vht = false; + supp_he = false; for (band = 0; band < NUM_NL80211_BANDS; band++) { struct ieee80211_supported_band *sband; @@ -922,6 +933,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; + if (!supp_he) + supp_he = !!ieee80211_get_he_sta_cap(sband); + if (!sband->ht_cap.ht_supported) continue; @@ -1011,6 +1025,18 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->scan_ies_len += 2 + sizeof(struct ieee80211_vht_cap); + /* HE cap element is variable in size - set len to allow max size */ + /* + * TODO: 1 is added at the end of the calculation to accommodate for + * the temporary placing of the HE capabilities IE under EXT. + * Remove it once it is placed in the final place. + */ + if (supp_he) + local->scan_ies_len += + 2 + sizeof(struct ieee80211_he_cap_elem) + + sizeof(struct ieee80211_he_mcs_nss_supp) + + IEEE80211_HE_PPE_THRES_MAX_LEN + 1; + if (!local->ops->hw_scan) { /* For hw_scan, driver needs to set these up. */ local->hw.wiphy->max_scan_ssids = 4; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a59187c016e0..7fb9957359a3 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, + const struct ieee80211_he_operation *he_oper, struct cfg80211_chan_def *chandef, bool tracking) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -207,7 +208,27 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, } vht_chandef = *chandef; - if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && he_oper && + (le32_to_cpu(he_oper->he_oper_params) & + IEEE80211_HE_OPERATION_VHT_OPER_INFO)) { + struct ieee80211_vht_operation he_oper_vht_cap; + + /* + * Set only first 3 bytes (other 2 aren't used in + * ieee80211_chandef_vht_oper() anyway) + */ + memcpy(&he_oper_vht_cap, he_oper->optional, 3); + he_oper_vht_cap.basic_mcs_set = cpu_to_le16(0); + + if (!ieee80211_chandef_vht_oper(&he_oper_vht_cap, + &vht_chandef)) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + sdata_info(sdata, + "HE AP VHT information is invalid, disable HE\n"); + ret = IEEE80211_STA_DISABLE_HE; + goto out; + } + } else if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) { if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT information is invalid, disable VHT\n"); @@ -300,12 +321,14 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_cap *ht_cap, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, + const struct ieee80211_he_operation *he_oper, const u8 *bssid, u32 *changed) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_supported_band *sband; - struct ieee80211_channel *chan; + struct ieee80211_channel *chan = sdata->vif.bss_conf.chandef.chan; + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[chan->band]; struct cfg80211_chan_def chandef; u16 ht_opmode; u32 flags; @@ -320,6 +343,11 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT) vht_oper = NULL; + /* don't check HE if we associated as non-HE station */ + if (ifmgd->flags & IEEE80211_STA_DISABLE_HE || + !ieee80211_get_he_sta_cap(sband)) + he_oper = NULL; + if (WARN_ON_ONCE(!sta)) return -EINVAL; @@ -333,12 +361,9 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.ht_operation_mode = ht_opmode; } - chan = sdata->vif.bss_conf.chandef.chan; - sband = local->hw.wiphy->bands[chan->band]; - - /* calculate new channel (type) based on HT/VHT operation IEs */ + /* calculate new channel (type) based on HT/VHT/HE operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, - ht_oper, vht_oper, + ht_oper, vht_oper, he_oper, &chandef, true); /* @@ -582,6 +607,34 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, ieee80211_ie_build_vht_cap(pos, &vht_cap, cap); } +/* This function determines HE capability flags for the association + * and builds the IE. + */ +static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct ieee80211_supported_band *sband) +{ + u8 *pos; + const struct ieee80211_sta_he_cap *he_cap = NULL; + u8 he_cap_size; + + he_cap = ieee80211_get_he_sta_cap(sband); + if (!he_cap) + return; + + /* + * TODO: the 1 added is because this temporarily is under the EXTENSION + * IE. Get rid of it when it moves. + */ + he_cap_size = + 2 + 1 + sizeof(he_cap->he_cap_elem) + + ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) + + ieee80211_he_ppe_size(he_cap->ppe_thres[0], + he_cap->he_cap_elem.phy_cap_info); + pos = skb_put(skb, he_cap_size); + ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size); +} + static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -643,6 +696,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) 2 + 2 * sband->n_channels + /* supported channels */ 2 + sizeof(struct ieee80211_ht_cap) + /* HT */ 2 + sizeof(struct ieee80211_vht_cap) + /* VHT */ + 2 + 1 + sizeof(struct ieee80211_he_cap_elem) + /* HE */ + sizeof(struct ieee80211_he_mcs_nss_supp) + + IEEE80211_HE_PPE_THRES_MAX_LEN + assoc_data->ie_len + /* extra IEs */ (assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) + 9, /* WMM */ @@ -827,11 +883,41 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) offset = noffset; } + /* if present, add any custom IEs that go before HE */ + if (assoc_data->ie_len) { + static const u8 before_he[] = { + /* + * no need to list the ones split off before VHT + * or generated here + */ + WLAN_EID_OPMODE_NOTIF, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE, + /* 11ai elements */ + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_SESSION, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_PUBLIC_KEY, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_KEY_CONFIRM, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_HLP_CONTAINER, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN, + /* TODO: add 11ah/11aj/11ak elements */ + }; + + /* RIC already taken above, so no need to handle here anymore */ + noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len, + before_he, ARRAY_SIZE(before_he), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, assoc_data->ie + offset, noffset - offset); + offset = noffset; + } + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) ieee80211_add_vht_ie(sdata, skb, sband, &assoc_data->ap_vht_cap); - /* if present, add any custom non-vendor IEs that go after HT */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + ieee80211_add_he_ie(sdata, skb, sband); + + /* if present, add any custom non-vendor IEs that go after HE */ if (assoc_data->ie_len) { noffset = ieee80211_ie_split_vendor(assoc_data->ie, assoc_data->ie_len, @@ -898,6 +984,11 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + /* Don't send NDPs when STA is connected HE */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + return; + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) @@ -929,6 +1020,10 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return; + /* Don't send NDPs when connected HE */ + if (!(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) + return; + skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30); if (!skb) return; @@ -1700,9 +1795,11 @@ static void ieee80211_sta_handle_tspec_ac_params_wk(struct work_struct *work) } /* MLME */ -static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - const u8 *wmm_param, size_t wmm_param_len) +static bool +ieee80211_sta_wmm_params(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + const u8 *wmm_param, size_t wmm_param_len, + const struct ieee80211_mu_edca_param_set *mu_edca) { struct ieee80211_tx_queue_params params[IEEE80211_NUM_ACS]; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -1749,6 +1846,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(1) | BIT(2); /* BK/- */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_bk; break; case 2: /* AC_VI */ ac = IEEE80211_AC_VI; @@ -1756,6 +1856,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(4) | BIT(5); /* CL/VI */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_vi; break; case 3: /* AC_VO */ ac = IEEE80211_AC_VO; @@ -1763,6 +1866,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(6) | BIT(7); /* VO/NC */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_vo; break; case 0: /* AC_BE */ default: @@ -1771,6 +1877,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(0) | BIT(3); /* BE/EE */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_be; break; } @@ -2219,6 +2328,20 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, ieee80211_sta_reset_conn_monitor(sdata); } +static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata, + const u8 *src, const u8 *dst, + const u8 *ssid, size_t ssid_len, + struct ieee80211_channel *channel) +{ + struct sk_buff *skb; + + skb = ieee80211_build_probe_req(sdata, src, dst, (u32)-1, channel, + ssid, ssid_len, NULL, 0, + IEEE80211_PROBE_FLAG_DIRECTED); + if (skb) + ieee80211_tx_skb(sdata, skb); +} + static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -2265,10 +2388,9 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) else ssid_len = ssid[1]; - ieee80211_send_probe_req(sdata, sdata->vif.addr, dst, - ssid + 2, ssid_len, NULL, - 0, (u32) -1, true, 0, - ifmgd->associated->channel, false); + ieee80211_mlme_send_probe_req(sdata, sdata->vif.addr, dst, + ssid + 2, ssid_len, + ifmgd->associated->channel); rcu_read_unlock(); } @@ -2370,7 +2492,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, skb = ieee80211_build_probe_req(sdata, sdata->vif.addr, cbss->bssid, (u32) -1, cbss->channel, ssid + 2, ssid_len, - NULL, 0, true); + NULL, 0, IEEE80211_PROBE_FLAG_DIRECTED); rcu_read_unlock(); return skb; @@ -3008,6 +3130,25 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, goto out; } + /* + * If AP doesn't support HT, or it doesn't have HE mandatory IEs, mark + * HE as disabled. If on the 5GHz band, make sure it supports VHT. + */ + if (ifmgd->flags & IEEE80211_STA_DISABLE_HT || + (sband->band == NL80211_BAND_5GHZ && + ifmgd->flags & IEEE80211_STA_DISABLE_VHT) || + (!elems.he_cap && !elems.he_operation)) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && + (!elems.he_cap || !elems.he_operation)) { + mutex_unlock(&sdata->local->sta_mtx); + sdata_info(sdata, + "HE AP is missing HE capability/operation\n"); + ret = false; + goto out; + } + /* Set up internal HT/VHT capabilities */ if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, @@ -3017,6 +3158,48 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, elems.vht_cap_elem, sta); + if (elems.he_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && + elems.he_cap) { + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, + elems.he_cap, + elems.he_cap_len, + sta); + + bss_conf->he_support = sta->sta.he_cap.has_he; + } else { + bss_conf->he_support = false; + } + + if (bss_conf->he_support) { + u32 he_oper_params = + le32_to_cpu(elems.he_operation->he_oper_params); + + bss_conf->bss_color = he_oper_params & + IEEE80211_HE_OPERATION_BSS_COLOR_MASK; + bss_conf->htc_trig_based_pkt_ext = + (he_oper_params & + IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK) << + IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET; + bss_conf->frame_time_rts_th = + (he_oper_params & + IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK) << + IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET; + + bss_conf->multi_sta_back_32bit = + sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP; + + bss_conf->ack_enabled = + sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_ACK_EN; + + bss_conf->uora_exists = !!elems.uora_element; + if (elems.uora_element) + bss_conf->uora_ocw_range = elems.uora_element[0]; + + /* TODO: OPEN: what happens if BSS color disable is set? */ + } + /* * Some APs, e.g. Netgear WNDR3700, report invalid HT operation data * in their association response, so ignore that data for our own @@ -3076,7 +3259,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { ieee80211_set_wmm_default(sdata, false, false); } else if (!ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, - elems.wmm_param_len)) { + elems.wmm_param_len, + elems.mu_edca_param_set)) { /* still enable QoS since we might have HT/VHT */ ieee80211_set_wmm_default(sdata, false, true); /* set the disable-WMM flag in this case to disable @@ -3590,7 +3774,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) && ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, - elems.wmm_param_len)) + elems.wmm_param_len, + elems.mu_edca_param_set)) changed |= BSS_CHANGED_QOS; /* @@ -3629,7 +3814,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem, elems.ht_operation, - elems.vht_operation, bssid, &changed)) { + elems.vht_operation, elems.he_operation, + bssid, &changed)) { mutex_unlock(&local->sta_mtx); sdata_info(sdata, "failed to follow AP %pM bandwidth change, disconnect\n", @@ -4266,6 +4452,68 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, return chains; } +static bool +ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband, + const struct ieee80211_he_operation *he_op) +{ + const struct ieee80211_sta_he_cap *sta_he_cap = + ieee80211_get_he_sta_cap(sband); + u16 ap_min_req_set; + int i; + + if (!sta_he_cap || !he_op) + return false; + + ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); + + /* Need to go over for 80MHz, 160MHz and for 80+80 */ + for (i = 0; i < 3; i++) { + const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp = + &sta_he_cap->he_mcs_nss_supp; + u16 sta_mcs_map_rx = + le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i]); + u16 sta_mcs_map_tx = + le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i + 1]); + u8 nss; + bool verified = true; + + /* + * For each band there is a maximum of 8 spatial streams + * possible. Each of the sta_mcs_map_* is a 16-bit struct built + * of 2 bits per NSS (1-8), with the values defined in enum + * ieee80211_he_mcs_support. Need to make sure STA TX and RX + * capabilities aren't less than the AP's minimum requirements + * for this HE BSS per SS. + * It is enough to find one such band that meets the reqs. + */ + for (nss = 8; nss > 0; nss--) { + u8 sta_rx_val = (sta_mcs_map_rx >> (2 * (nss - 1))) & 3; + u8 sta_tx_val = (sta_mcs_map_tx >> (2 * (nss - 1))) & 3; + u8 ap_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + + if (ap_val == IEEE80211_HE_MCS_NOT_SUPPORTED) + continue; + + /* + * Make sure the HE AP doesn't require MCSs that aren't + * supported by the client + */ + if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + (ap_val > sta_rx_val) || (ap_val > sta_tx_val)) { + verified = false; + break; + } + } + + if (verified) + return true; + } + + /* If here, STA doesn't meet AP's HE min requirements */ + return false; +} + static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss) { @@ -4274,6 +4522,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_cap *ht_cap = NULL; const struct ieee80211_ht_operation *ht_oper = NULL; const struct ieee80211_vht_operation *vht_oper = NULL; + const struct ieee80211_he_operation *he_oper = NULL; struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; int ret; @@ -4329,6 +4578,24 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && + ieee80211_get_he_sta_cap(sband)) { + const struct cfg80211_bss_ies *ies; + const u8 *he_oper_ie; + + ies = rcu_dereference(cbss->ies); + he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, + ies->data, ies->len); + if (he_oper_ie && + he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3])) + he_oper = (void *)(he_oper_ie + 3); + else + he_oper = NULL; + + if (!ieee80211_verify_sta_he_mcs_support(sband, he_oper)) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + } + /* Allow VHT if at least one channel on the sband supports 80 MHz */ have_80mhz = false; for (i = 0; i < sband->n_channels; i++) { @@ -4345,7 +4612,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, - ht_oper, vht_oper, + ht_oper, vht_oper, he_oper, &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), @@ -4751,8 +5018,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) { ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; netdev_info(sdata->dev, - "disabling HT/VHT due to WEP/TKIP use\n"); + "disabling HE/HT/VHT due to WEP/TKIP use\n"); } } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f1d40b6645ff..8ef4153cd299 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -262,7 +262,7 @@ 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); + roc->chan->band, 0); roc->frame = NULL; } } else { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0a38cc1cbebc..a16ba568e2a3 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -175,6 +175,20 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, len += 12; } + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE) { + len = ALIGN(len, 2); + len += 12; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he) != 12); + } + + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE_MU) { + len = ALIGN(len, 2); + len += 12; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) != 12); + } + if (status->chains) { /* antenna and antenna signal fields */ len += 2 * hweight8(status->chains); @@ -263,6 +277,19 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, int mpdulen, chain; unsigned long chains = status->chains; struct ieee80211_vendor_radiotap rtap = {}; + struct ieee80211_radiotap_he he = {}; + struct ieee80211_radiotap_he_mu he_mu = {}; + + if (status->flag & RX_FLAG_RADIOTAP_HE) { + he = *(struct ieee80211_radiotap_he *)skb->data; + skb_pull(skb, sizeof(he)); + WARN_ON_ONCE(status->encoding != RX_ENC_HE); + } + + if (status->flag & RX_FLAG_RADIOTAP_HE_MU) { + he_mu = *(struct ieee80211_radiotap_he_mu *)skb->data; + skb_pull(skb, sizeof(he_mu)); + } if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) { rtap = *(struct ieee80211_vendor_radiotap *)skb->data; @@ -520,6 +547,89 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos++ = flags; } + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE) { +#define HE_PREP(f, val) cpu_to_le16(FIELD_PREP(IEEE80211_RADIOTAP_HE_##f, val)) + + if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) { + he.data6 |= HE_PREP(DATA6_NSTS, + FIELD_GET(RX_ENC_FLAG_STBC_MASK, + status->enc_flags)); + he.data3 |= HE_PREP(DATA3_STBC, 1); + } else { + he.data6 |= HE_PREP(DATA6_NSTS, status->nss); + } + +#define CHECK_GI(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \ + (int)NL80211_RATE_INFO_HE_GI_##s) + + CHECK_GI(0_8); + CHECK_GI(1_6); + CHECK_GI(3_2); + + he.data3 |= HE_PREP(DATA3_DATA_MCS, status->rate_idx); + he.data3 |= HE_PREP(DATA3_DATA_DCM, status->he_dcm); + he.data3 |= HE_PREP(DATA3_CODING, + !!(status->enc_flags & RX_ENC_FLAG_LDPC)); + + he.data5 |= HE_PREP(DATA5_GI, status->he_gi); + + switch (status->bw) { + case RATE_INFO_BW_20: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ); + break; + case RATE_INFO_BW_40: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ); + break; + case RATE_INFO_BW_80: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ); + break; + case RATE_INFO_BW_160: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ); + break; + case RATE_INFO_BW_HE_RU: +#define CHECK_RU_ALLOC(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \ + NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4) + + CHECK_RU_ALLOC(26); + CHECK_RU_ALLOC(52); + CHECK_RU_ALLOC(106); + CHECK_RU_ALLOC(242); + CHECK_RU_ALLOC(484); + CHECK_RU_ALLOC(996); + CHECK_RU_ALLOC(2x996); + + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + status->he_ru + 4); + break; + default: + WARN_ONCE(1, "Invalid SU BW %d\n", status->bw); + } + + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE); + memcpy(pos, &he, sizeof(he)); + pos += sizeof(he); + } + + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE_MU) { + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE_MU); + memcpy(pos, &he_mu, sizeof(he_mu)); + pos += sizeof(he_mu); + } + for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) { *pos++ = status->chain_signal[chain]; *pos++ = chain; @@ -613,6 +723,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, rcu_dereference(local->monitor_sdata); bool only_monitor = false; + if (status->flag & RX_FLAG_RADIOTAP_HE) + rtap_space += sizeof(struct ieee80211_radiotap_he); + + if (status->flag & RX_FLAG_RADIOTAP_HE_MU) + rtap_space += sizeof(struct ieee80211_radiotap_he_mu); + if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) { struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data; @@ -3241,7 +3357,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) } __ieee80211_tx_skb_tid_band(rx->sdata, nskb, 7, - status->band); + status->band, 0); } dev_kfree_skb(rx->skb); return RX_QUEUED; @@ -3386,8 +3502,7 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx, status = IEEE80211_SKB_RXCB((rx->skb)); sband = rx->local->hw.wiphy->bands[status->band]; - if (!(status->encoding == RX_ENC_HT) && - !(status->encoding == RX_ENC_VHT)) + if (status->encoding == RX_ENC_LEGACY) rate = &sband->bitrates[status->rate_idx]; ieee80211_rx_cooked_monitor(rx, rate); @@ -4386,6 +4501,14 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, status->rate_idx, status->nss)) goto drop; break; + case RX_ENC_HE: + if (WARN_ONCE(status->rate_idx > 11 || + !status->nss || + status->nss > 8, + "Rate marked as an HE rate but data is invalid: MCS: %d, NSS: %d\n", + status->rate_idx, status->nss)) + goto drop; + break; default: WARN_ON_ONCE(1); /* fall through */ diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 2e917a6d239d..5d2a11777718 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -20,6 +20,7 @@ #include <net/sch_generic.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/random.h> #include <net/mac80211.h> #include "ieee80211_i.h" @@ -293,6 +294,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) struct cfg80211_chan_def chandef; u8 bands_used = 0; int i, ielen, n_chans; + u32 flags = 0; req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); @@ -331,12 +333,16 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) local->hw_scan_req->req.n_channels = n_chans; ieee80211_prepare_scan_chandef(&chandef, req->scan_width); + if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) + flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; + ielen = ieee80211_build_preq_ies(local, (u8 *)local->hw_scan_req->req.ie, local->hw_scan_ies_bufsize, &local->hw_scan_req->ies, req->ie, req->ie_len, - bands_used, req->rates, &chandef); + bands_used, req->rates, &chandef, + flags); local->hw_scan_req->req.ie_len = ielen; local->hw_scan_req->req.no_cck = req->no_cck; ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr); @@ -528,6 +534,35 @@ void ieee80211_run_deferred_scan(struct ieee80211_local *local) round_jiffies_relative(0)); } +static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, + const u8 *src, const u8 *dst, + const u8 *ssid, size_t ssid_len, + const u8 *ie, size_t ie_len, + u32 ratemask, u32 flags, u32 tx_flags, + 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, + ie, ie_len, flags); + + if (skb) { + if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { + struct ieee80211_hdr *hdr = (void *)skb->data; + u16 sn = get_random_u32(); + + txdata_flags |= IEEE80211_TX_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); + } +} + static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, unsigned long *next_delay) { @@ -535,7 +570,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; enum nl80211_band band = local->hw.conf.chandef.chan->band; - u32 tx_flags; + u32 flags = 0, tx_flags; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); @@ -543,17 +578,21 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK; if (scan_req->no_cck) tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE; + if (scan_req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) + flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; + if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_SN) + flags |= IEEE80211_PROBE_FLAG_RANDOM_SN; sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->mtx)); for (i = 0; i < scan_req->n_ssids; i++) - ieee80211_send_probe_req( + ieee80211_send_scan_probe_req( sdata, local->scan_addr, scan_req->bssid, scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len, scan_req->ie, scan_req->ie_len, - scan_req->rates[band], false, - tx_flags, local->hw.conf.chandef.chan, true); + scan_req->rates[band], flags, + tx_flags, local->hw.conf.chandef.chan); /* * After sending probe requests, wait for probe responses @@ -1141,6 +1180,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, u32 rate_masks[NUM_NL80211_BANDS] = {}; u8 bands_used = 0; u8 *ie; + u32 flags = 0; iebufsz = local->scan_ies_len + req->ie_len; @@ -1157,6 +1197,9 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, } } + if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) + flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; + ie = kcalloc(iebufsz, num_bands, GFP_KERNEL); if (!ie) { ret = -ENOMEM; @@ -1167,7 +1210,8 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, ieee80211_build_preq_ies(local, ie, num_bands * iebufsz, &sched_scan_ies, req->ie, - req->ie_len, bands_used, rate_masks, &chandef); + req->ie_len, bands_used, rate_masks, &chandef, + flags); ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); if (ret == 0) { diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 6428f1ac37b6..f34202242d24 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1323,6 +1323,11 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, struct ieee80211_tx_info *info; struct ieee80211_chanctx_conf *chanctx_conf; + /* Don't send NDPs when STA is connected HE */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) + return; + if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | @@ -1391,7 +1396,7 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, } info->band = chanctx_conf->def.chan->band; - ieee80211_xmit(sdata, sta, skb); + ieee80211_xmit(sdata, sta, skb, 0); rcu_read_unlock(); } @@ -1968,7 +1973,7 @@ sta_get_last_rx_stats(struct sta_info *sta) return stats; } -static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, +static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, struct rate_info *rinfo) { rinfo->bw = STA_STATS_GET(BW, rate); @@ -2005,6 +2010,14 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); break; } + case STA_STATS_RATE_TYPE_HE: + rinfo->flags = RATE_INFO_FLAGS_HE_MCS; + rinfo->mcs = STA_STATS_GET(HE_MCS, rate); + rinfo->nss = STA_STATS_GET(HE_NSS, rate); + rinfo->he_gi = STA_STATS_GET(HE_GI, rate); + rinfo->he_ru_alloc = STA_STATS_GET(HE_RU, rate); + rinfo->he_dcm = STA_STATS_GET(HE_DCM, rate); + break; } } @@ -2101,38 +2114,38 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, drv_sta_statistics(local, sdata, &sta->sta, sinfo); - sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) | - BIT(NL80211_STA_INFO_STA_FLAGS) | - BIT(NL80211_STA_INFO_BSS_PARAM) | - BIT(NL80211_STA_INFO_CONNECTED_TIME) | - BIT(NL80211_STA_INFO_RX_DROP_MISC); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) | + BIT_ULL(NL80211_STA_INFO_STA_FLAGS) | + BIT_ULL(NL80211_STA_INFO_BSS_PARAM) | + BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME) | + BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC); if (sdata->vif.type == NL80211_IFTYPE_STATION) { sinfo->beacon_loss_count = sdata->u.mgd.beacon_loss_count; - sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_LOSS); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_LOSS); } sinfo->connected_time = ktime_get_seconds() - sta->last_connected; sinfo->inactive_time = jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta)); - if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) | - BIT(NL80211_STA_INFO_TX_BYTES)))) { + if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) | + BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) { sinfo->tx_bytes = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) sinfo->tx_bytes += sta->tx_stats.bytes[ac]; - sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64); } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_PACKETS))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_PACKETS))) { sinfo->tx_packets = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) sinfo->tx_packets += sta->tx_stats.packets[ac]; - sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS); } - if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) | - BIT(NL80211_STA_INFO_RX_BYTES)))) { + if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) | + BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) { sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats); if (sta->pcpu_rx_stats) { @@ -2144,10 +2157,10 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, } } - sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64); } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_PACKETS))) { sinfo->rx_packets = sta->rx_stats.packets; if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { @@ -2157,17 +2170,17 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->rx_packets += cpurxs->packets; } } - sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS); } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_RETRIES))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_RETRIES))) { sinfo->tx_retries = sta->status_stats.retry_count; - sinfo->filled |= BIT(NL80211_STA_INFO_TX_RETRIES); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES); } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_FAILED))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))) { sinfo->tx_failed = sta->status_stats.retry_failed; - sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } sinfo->rx_dropped_misc = sta->rx_stats.dropped; @@ -2182,23 +2195,23 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, if (sdata->vif.type == NL80211_IFTYPE_STATION && !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) { - sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX) | - BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX) | + BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG); sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif); } if (ieee80211_hw_check(&sta->local->hw, SIGNAL_DBM) || ieee80211_hw_check(&sta->local->hw, SIGNAL_UNSPEC)) { - if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL))) { sinfo->signal = (s8)last_rxstats->last_signal; - sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL); } if (!sta->pcpu_rx_stats && - !(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) { + !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))) { sinfo->signal_avg = -ewma_signal_read(&sta->rx_stats_avg.signal); - sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG); } } @@ -2207,11 +2220,11 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, * pcpu statistics */ if (last_rxstats->chains && - !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) | - BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) { - sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL); + !(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL) | + BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) { + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL); if (!sta->pcpu_rx_stats) - sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); sinfo->chains = last_rxstats->chains; @@ -2223,15 +2236,15 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, } } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) { sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &sinfo->txrate); - sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE); } - if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE))) { if (sta_set_rate_info_rx(sta, &sinfo->rxrate) == 0) - sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE); } if (tidstats && !cfg80211_sinfo_alloc_tid_stats(sinfo, GFP_KERNEL)) { @@ -2244,18 +2257,18 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, if (ieee80211_vif_is_mesh(&sdata->vif)) { #ifdef CONFIG_MAC80211_MESH - sinfo->filled |= BIT(NL80211_STA_INFO_LLID) | - BIT(NL80211_STA_INFO_PLID) | - BIT(NL80211_STA_INFO_PLINK_STATE) | - BIT(NL80211_STA_INFO_LOCAL_PM) | - BIT(NL80211_STA_INFO_PEER_PM) | - BIT(NL80211_STA_INFO_NONPEER_PM); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_LLID) | + BIT_ULL(NL80211_STA_INFO_PLID) | + BIT_ULL(NL80211_STA_INFO_PLINK_STATE) | + BIT_ULL(NL80211_STA_INFO_LOCAL_PM) | + BIT_ULL(NL80211_STA_INFO_PEER_PM) | + BIT_ULL(NL80211_STA_INFO_NONPEER_PM); sinfo->llid = sta->mesh->llid; sinfo->plid = sta->mesh->plid; sinfo->plink_state = sta->mesh->plink_state; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { - sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_T_OFFSET); sinfo->t_offset = sta->mesh->t_offset; } sinfo->local_pm = sta->mesh->local_pm; @@ -2300,7 +2313,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, thr = sta_get_expected_throughput(sta); if (thr != 0) { - sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_EXPECTED_THROUGHPUT); sinfo->expected_throughput = thr; } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 81b35f623792..9a04327d71d1 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -170,7 +170,7 @@ struct tid_ampdu_tx { u8 dialog_token; u8 stop_initiator; bool tx_stop; - u8 buf_size; + u16 buf_size; u16 failed_bar_ssn; bool bar_pending; @@ -405,7 +405,7 @@ struct ieee80211_sta_rx_stats { int last_signal; u8 chains; s8 chain_signal_last[IEEE80211_MAX_CHAINS]; - u16 last_rate; + u32 last_rate; struct u64_stats_sync syncp; u64 bytes; u64 msdu[IEEE80211_NUM_TIDS + 1]; @@ -764,6 +764,7 @@ enum sta_stats_type { STA_STATS_RATE_TYPE_LEGACY, STA_STATS_RATE_TYPE_HT, STA_STATS_RATE_TYPE_VHT, + STA_STATS_RATE_TYPE_HE, }; #define STA_STATS_FIELD_HT_MCS GENMASK( 7, 0) @@ -771,9 +772,14 @@ enum sta_stats_type { #define STA_STATS_FIELD_LEGACY_BAND GENMASK( 7, 4) #define STA_STATS_FIELD_VHT_MCS GENMASK( 3, 0) #define STA_STATS_FIELD_VHT_NSS GENMASK( 7, 4) +#define STA_STATS_FIELD_HE_MCS GENMASK( 3, 0) +#define STA_STATS_FIELD_HE_NSS GENMASK( 7, 4) #define STA_STATS_FIELD_BW GENMASK(11, 8) #define STA_STATS_FIELD_SGI GENMASK(12, 12) #define STA_STATS_FIELD_TYPE GENMASK(15, 13) +#define STA_STATS_FIELD_HE_RU GENMASK(18, 16) +#define STA_STATS_FIELD_HE_GI GENMASK(20, 19) +#define STA_STATS_FIELD_HE_DCM GENMASK(21, 21) #define STA_STATS_FIELD(_n, _v) FIELD_PREP(STA_STATS_FIELD_ ## _n, _v) #define STA_STATS_GET(_n, _v) FIELD_GET(STA_STATS_FIELD_ ## _n, _v) @@ -782,7 +788,7 @@ enum sta_stats_type { static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s) { - u16 r; + u32 r; r = STA_STATS_FIELD(BW, s->bw); @@ -804,6 +810,14 @@ static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s) r |= STA_STATS_FIELD(LEGACY_BAND, s->band); r |= STA_STATS_FIELD(LEGACY_IDX, s->rate_idx); break; + case RX_ENC_HE: + r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HE); + r |= STA_STATS_FIELD(HE_NSS, s->nss); + r |= STA_STATS_FIELD(HE_MCS, s->rate_idx); + r |= STA_STATS_FIELD(HE_GI, s->he_gi); + r |= STA_STATS_FIELD(HE_RU, s->he_ru); + r |= STA_STATS_FIELD(HE_DCM, s->he_dcm); + break; default: WARN_ON(1); return STA_STATS_RATE_INVALID; diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 80a7edf8d314..0ab69a1964f8 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -92,7 +92,7 @@ STA_ENTRY \ __field(u16, tid) \ __field(u16, ssn) \ - __field(u8, buf_size) \ + __field(u16, buf_size) \ __field(bool, amsdu) \ __field(u16, timeout) \ __field(u16, action) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index fa1f1e63a264..6a79d564de35 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -825,6 +825,8 @@ 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 */ @@ -1854,7 +1856,7 @@ 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) + bool txpending, u32 txdata_flags) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_data tx; @@ -1872,6 +1874,8 @@ 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; @@ -1933,7 +1937,8 @@ 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) + struct sta_info *sta, struct sk_buff *skb, + u32 txdata_flags) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -1968,7 +1973,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, } ieee80211_set_qos_hdr(sdata, skb); - ieee80211_tx(sdata, sta, skb, false); + ieee80211_tx(sdata, sta, skb, false, txdata_flags); } static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, @@ -2289,7 +2294,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, if (!ieee80211_parse_tx_radiotap(local, skb)) goto fail_rcu; - ieee80211_xmit(sdata, NULL, skb); + ieee80211_xmit(sdata, NULL, skb, 0); rcu_read_unlock(); return NETDEV_TX_OK; @@ -3648,7 +3653,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, ieee80211_tx_stats(dev, skb->len); - ieee80211_xmit(sdata, sta, skb); + ieee80211_xmit(sdata, sta, skb, 0); } goto out; out_free: @@ -3867,7 +3872,7 @@ 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); + result = ieee80211_tx(sdata, NULL, skb, true, 0); } else { struct sk_buff_head skbs; @@ -4783,7 +4788,7 @@ 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) + enum nl80211_band band, u32 txdata_flags) { int ac = ieee80211_ac_from_tid(tid); @@ -4800,7 +4805,7 @@ 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); + ieee80211_xmit(sdata, NULL, skb, txdata_flags); local_bh_enable(); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 5e2e511c4a6f..3e68132a41fa 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1095,6 +1095,21 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, if (elen >= sizeof(*elems->max_idle_period_ie)) elems->max_idle_period_ie = (void *)pos; break; + case WLAN_EID_EXTENSION: + if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA && + elen >= (sizeof(*elems->mu_edca_param_set) + 1)) { + elems->mu_edca_param_set = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) { + elems->he_cap = (void *)&pos[1]; + elems->he_cap_len = elen - 1; + } else if (pos[0] == WLAN_EID_EXT_HE_OPERATION && + elen >= sizeof(*elems->he_operation) && + elen >= ieee80211_he_oper_size(&pos[1])) { + elems->he_operation = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_UORA && elen >= 1) { + elems->uora_element = (void *)&pos[1]; + } + break; default: break; } @@ -1353,9 +1368,10 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, enum nl80211_band band, u32 rate_mask, struct cfg80211_chan_def *chandef, - size_t *offset) + size_t *offset, u32 flags) { struct ieee80211_supported_band *sband; + const struct ieee80211_sta_he_cap *he_cap; u8 *pos = buffer, *end = buffer + buffer_len; size_t noffset; int supp_rates_len, i; @@ -1433,6 +1449,9 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, chandef->chan->center_freq); } + if (flags & IEEE80211_PROBE_FLAG_MIN_CONTENT) + goto done; + /* insert custom IEs that go before HT */ if (ie && ie_len) { static const u8 before_ht[] = { @@ -1460,11 +1479,6 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, sband->ht_cap.cap); } - /* - * If adding more here, adjust code in main.c - * that calculates local->scan_ies_len. - */ - /* insert custom IEs that go before VHT */ if (ie && ie_len) { static const u8 before_vht[] = { @@ -1507,9 +1521,43 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, sband->vht_cap.cap); } + /* insert custom IEs that go before HE */ + if (ie && ie_len) { + static const u8 before_he[] = { + /* + * no need to list the ones split off before VHT + * or generated here + */ + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS, + WLAN_EID_AP_CSN, + /* TODO: add 11ah/11aj/11ak elements */ + }; + noffset = ieee80211_ie_split(ie, ie_len, + before_he, ARRAY_SIZE(before_he), + *offset); + if (end - pos < noffset - *offset) + goto out_err; + memcpy(pos, ie + *offset, noffset - *offset); + pos += noffset - *offset; + *offset = noffset; + } + + he_cap = ieee80211_get_he_sta_cap(sband); + if (he_cap) { + pos = ieee80211_ie_build_he_cap(pos, he_cap, end); + if (!pos) + goto out_err; + } + + /* + * If adding more here, adjust code in main.c + * that calculates local->scan_ies_len. + */ + return pos - buffer; out_err: WARN_ONCE(1, "not enough space for preq IEs\n"); + done: return pos - buffer; } @@ -1518,7 +1566,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, struct ieee80211_scan_ies *ie_desc, const u8 *ie, size_t ie_len, u8 bands_used, u32 *rate_masks, - struct cfg80211_chan_def *chandef) + struct cfg80211_chan_def *chandef, + u32 flags) { size_t pos = 0, old_pos = 0, custom_ie_offset = 0; int i; @@ -1533,7 +1582,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, ie, ie_len, i, rate_masks[i], chandef, - &custom_ie_offset); + &custom_ie_offset, + flags); ie_desc->ies[i] = buffer + old_pos; ie_desc->len[i] = pos - old_pos; old_pos = pos; @@ -1561,7 +1611,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *chan, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, - bool directed) + u32 flags) { struct ieee80211_local *local = sdata->local; struct cfg80211_chan_def chandef; @@ -1577,7 +1627,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, * badly-behaved APs don't respond when this parameter is included. */ chandef.width = sdata->vif.bss_conf.chandef.width; - if (directed) + if (flags & IEEE80211_PROBE_FLAG_DIRECTED) chandef.chan = NULL; else chandef.chan = chan; @@ -1591,7 +1641,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, ies_len = ieee80211_build_preq_ies(local, skb_tail_pointer(skb), skb_tailroom(skb), &dummy_ie_desc, ie, ie_len, BIT(chan->band), - rate_masks, &chandef); + rate_masks, &chandef, flags); skb_put(skb, ies_len); if (dst) { @@ -1605,27 +1655,6 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, return skb; } -void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, - const u8 *src, const u8 *dst, - const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len, - u32 ratemask, bool directed, u32 tx_flags, - struct ieee80211_channel *channel, bool scan) -{ - struct sk_buff *skb; - - skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel, - ssid, ssid_len, - ie, ie_len, directed); - if (skb) { - IEEE80211_SKB_CB(skb)->flags |= tx_flags; - if (scan) - ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); - else - ieee80211_tx_skb(sdata, skb); - } -} - u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band band, u32 *basic_rates) @@ -2412,6 +2441,72 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos; } +u8 *ieee80211_ie_build_he_cap(u8 *pos, + const struct ieee80211_sta_he_cap *he_cap, + u8 *end) +{ + u8 n; + u8 ie_len; + u8 *orig_pos = pos; + + /* Make sure we have place for the IE */ + /* + * TODO: the 1 added is because this temporarily is under the EXTENSION + * IE. Get rid of it when it moves. + */ + if (!he_cap) + return orig_pos; + + n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem); + ie_len = 2 + 1 + + sizeof(he_cap->he_cap_elem) + n + + ieee80211_he_ppe_size(he_cap->ppe_thres[0], + he_cap->he_cap_elem.phy_cap_info); + + if ((end - pos) < ie_len) + return orig_pos; + + *pos++ = WLAN_EID_EXTENSION; + pos++; /* We'll set the size later below */ + *pos++ = WLAN_EID_EXT_HE_CAPABILITY; + + /* Fixed data */ + memcpy(pos, &he_cap->he_cap_elem, sizeof(he_cap->he_cap_elem)); + pos += sizeof(he_cap->he_cap_elem); + + memcpy(pos, &he_cap->he_mcs_nss_supp, n); + pos += n; + + /* Check if PPE Threshold should be present */ + if ((he_cap->he_cap_elem.phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + goto end; + + /* + * Calculate how many PPET16/PPET8 pairs are to come. Algorithm: + * (NSS_M1 + 1) x (num of 1 bits in RU_INDEX_BITMASK) + */ + n = hweight8(he_cap->ppe_thres[0] & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((he_cap->ppe_thres[0] & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + /* Copy PPE Thresholds */ + memcpy(pos, &he_cap->ppe_thres, n); + pos += n; + +end: + orig_pos[1] = (pos - orig_pos) - 2; + return pos; +} + u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, const struct cfg80211_chan_def *chandef, u16 prot_mode, bool rifs_mode) diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index a1086bdec242..5423b197d98a 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -32,7 +32,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, __be32 mask = 0; /* we're only interested in locally generated packets */ - if (skb->sk == NULL) + if (skb->sk == NULL || !net_eq(nf_ct_net(ct), sock_net(skb->sk))) goto out; if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) goto out; diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index dc61399e30be..a8c5c846aec1 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -132,9 +132,10 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header); -void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk) +void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk) { - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk))) return; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 46f9df99d276..86df2a1666fd 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -108,6 +108,7 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) struct flowi fl; unsigned int hh_len; struct dst_entry *dst; + struct sock *sk = skb->sk; int err; err = xfrm_decode_session(skb, &fl, family); @@ -119,7 +120,10 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); - dst = xfrm_lookup(net, dst, &fl, skb->sk, 0); + if (sk && !net_eq(net, sock_net(sk))) + sk = NULL; + + dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 896d4a36081d..3f211e1025c1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -14,6 +14,7 @@ #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/vmalloc.h> +#include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 1105a23bda5e..2b94dcc43456 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -107,7 +107,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, break; case NFT_META_SKUID: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; read_lock_bh(&sk->sk_callback_lock); @@ -123,7 +124,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, break; case NFT_META_SKGID: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; read_lock_bh(&sk->sk_callback_lock); @@ -214,7 +216,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, #ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; *dest = sock_cgroup_classid(&sk->sk_cgrp_data); break; diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 74e1b3bd6954..998c2b546f6d 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -23,6 +23,9 @@ static void nft_socket_eval(const struct nft_expr *expr, struct sock *sk = skb->sk; u32 *dest = ®s->data[priv->dreg]; + if (sk && !net_eq(nft_net(pkt), sock_net(sk))) + sk = NULL; + if (!sk) switch(nft_pf(pkt)) { case NFPROTO_IPV4: @@ -39,7 +42,7 @@ static void nft_socket_eval(const struct nft_expr *expr, return; } - if(!sk) { + if (!sk) { nft_reg_store8(dest, 0); return; } diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 7df2dece57d3..5d92e1781980 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -72,8 +72,9 @@ static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v0 *info = par->matchinfo; + struct sock *sk = skb->sk; - if (skb->sk == NULL || !sk_fullsock(skb->sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^ @@ -85,8 +86,9 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) const struct xt_cgroup_info_v1 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; + struct sock *sk = skb->sk; - if (!skb->sk || !sk_fullsock(skb->sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 3d705c688a27..46686fb73784 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -67,7 +67,7 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) struct sock *sk = skb_to_full_sk(skb); struct net *net = xt_net(par); - if (sk == NULL || sk->sk_socket == NULL) + if (!sk || !sk->sk_socket || !net_eq(net, sock_net(sk))) return (info->match ^ info->invert) == 0; else if (info->match & info->invert & XT_OWNER_SOCKET) /* diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 07085c22b19c..f44de4bc2100 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -265,7 +265,8 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) } /* use TTL as seen before forwarding */ - if (xt_out(par) != NULL && skb->sk == NULL) + if (xt_out(par) != NULL && + (!skb->sk || !net_eq(net, sock_net(skb->sk)))) ttl++; spin_lock_bh(&recent_lock); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 5c0779c4fa3c..0472f3472842 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -56,8 +56,12 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; + if (!net_eq(xt_net(par), sock_net(sk))) + sk = NULL; + if (!sk) sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par)); + if (sk) { bool wildcard; bool transparent = true; @@ -113,8 +117,12 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; + if (!net_eq(xt_net(par), sock_net(sk))) + sk = NULL; + if (!sk) sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par)); + if (sk) { bool wildcard; bool transparent = true; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 492ab0c36f7c..391c4073a6dc 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2516,7 +2516,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; + __be16 dst_opt_type; + dst_opt_type = 0; ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) @@ -2528,10 +2530,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, err = validate_geneve_opts(&key); if (err < 0) return err; + dst_opt_type = TUNNEL_GENEVE_OPT; break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: + dst_opt_type = TUNNEL_VXLAN_OPT; break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + dst_opt_type = TUNNEL_ERSPAN_OPT; break; } } @@ -2574,7 +2579,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, */ ip_tunnel_info_opts_set(tun_info, TUN_METADATA_OPTS(&key, key.tun_opts_len), - key.tun_opts_len); + key.tun_opts_len, dst_opt_type); add_nested_action_end(*sfa, start); return err; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 8a925c72db5f..55bc96b610e8 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -136,16 +136,18 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; - struct nlattr *pattr; - struct tc_pedit *parm; - int ret = 0, err; - struct tcf_pedit *p; struct tc_pedit_key *keys = NULL; struct tcf_pedit_key_ex *keys_ex; + struct tc_pedit *parm; + struct nlattr *pattr; + struct tcf_pedit *p; + int ret = 0, err; int ksize; - if (nla == NULL) + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed"); return -EINVAL; + } err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL); if (err < 0) @@ -154,28 +156,34 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, pattr = tb[TCA_PEDIT_PARMS]; if (!pattr) pattr = tb[TCA_PEDIT_PARMS_EX]; - if (!pattr) + if (!pattr) { + NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute"); return -EINVAL; + } parm = nla_data(pattr); ksize = parm->nkeys * sizeof(struct tc_pedit_key); - if (nla_len(pattr) < sizeof(*parm) + ksize) + if (nla_len(pattr) < sizeof(*parm) + ksize) { + NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); return -EINVAL; + } keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); if (IS_ERR(keys_ex)) return PTR_ERR(keys_ex); if (!tcf_idr_check(tn, parm->index, a, bind)) { - if (!parm->nkeys) + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); return -EINVAL; + } ret = tcf_idr_create(tn, parm->index, est, a, &act_pedit_ops, bind, false); if (ret) return ret; p = to_pedit(*a); keys = kmalloc(ksize, GFP_KERNEL); - if (keys == NULL) { + if (!keys) { tcf_idr_release(*a, bind); kfree(keys_ex); return -ENOMEM; @@ -220,6 +228,7 @@ static void tcf_pedit_cleanup(struct tc_action *a) { struct tcf_pedit *p = to_pedit(a); struct tc_pedit_key *keys = p->tcfp_keys; + kfree(keys); kfree(p->tcfp_keys_ex); } @@ -284,11 +293,12 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, if (p->tcfp_nkeys > 0) { struct tc_pedit_key *tkey = p->tcfp_keys; struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex; - enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; + enum pedit_header_type htype = + TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET; for (i = p->tcfp_nkeys; i > 0; i--, tkey++) { - u32 *ptr, _data; + u32 *ptr, hdata; int offset = tkey->off; int hoffset; u32 val; @@ -303,39 +313,39 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, rc = pedit_skb_hdr_offset(skb, htype, &hoffset); if (rc) { - pr_info("tc filter pedit bad header type specified (0x%x)\n", + pr_info("tc action pedit bad header type specified (0x%x)\n", htype); goto bad; } if (tkey->offmask) { - char *d, _d; + u8 *d, _d; if (!offset_valid(skb, hoffset + tkey->at)) { - pr_info("tc filter pedit 'at' offset %d out of bounds\n", + pr_info("tc action pedit 'at' offset %d out of bounds\n", hoffset + tkey->at); goto bad; } - d = skb_header_pointer(skb, hoffset + tkey->at, 1, - &_d); + d = skb_header_pointer(skb, hoffset + tkey->at, + sizeof(_d), &_d); if (!d) goto bad; offset += (*d & tkey->offmask) >> tkey->shift; } if (offset % 4) { - pr_info("tc filter pedit" - " offset must be on 32 bit boundaries\n"); + pr_info("tc action pedit offset must be on 32 bit boundaries\n"); goto bad; } if (!offset_valid(skb, hoffset + offset)) { - pr_info("tc filter pedit offset %d out of bounds\n", + pr_info("tc action pedit offset %d out of bounds\n", hoffset + offset); goto bad; } - ptr = skb_header_pointer(skb, hoffset + offset, 4, &_data); + ptr = skb_header_pointer(skb, hoffset + offset, + sizeof(hdata), &hdata); if (!ptr) goto bad; /* just do it, baby */ @@ -347,19 +357,20 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, val = (*ptr + tkey->val) & ~tkey->mask; break; default: - pr_info("tc filter pedit bad command (%d)\n", + pr_info("tc action pedit bad command (%d)\n", cmd); goto bad; } *ptr = ((*ptr & tkey->mask) ^ val); - if (ptr == &_data) + if (ptr == &hdata) skb_store_bits(skb, hoffset + offset, ptr, 4); } goto done; - } else + } else { WARN(1, "pedit BUG: index %d\n", p->tcf_index); + } bad: p->tcf_qstats.overlimits++; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 626dac81a48a..ea203e386a92 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> +#include <net/geneve.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -57,6 +58,135 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, return action; } +static const struct nla_policy +enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, + .len = 128 }, +}; + +static int +tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1]; + int err, data_len, opt_len; + u8 *data; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, + nla, geneve_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); + return -EINVAL; + } + + data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); + data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); + if (data_len < 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); + return -ERANGE; + } + if (data_len % 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); + return -ERANGE; + } + + opt_len = sizeof(struct geneve_opt) + data_len; + if (dst) { + struct geneve_opt *opt = dst; + + WARN_ON(dst_len < opt_len); + + opt->opt_class = + nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]); + opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]); + opt->length = data_len / 4; /* length is in units of 4 bytes */ + opt->r1 = 0; + opt->r2 = 0; + opt->r3 = 0; + + memcpy(opt + 1, data, data_len); + } + + return opt_len; +} + +static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, + int dst_len, struct netlink_ext_ack *extack) +{ + int err, rem, opt_len, len = nla_len(nla), opts_len = 0; + const struct nlattr *attr, *head = nla_data(nla); + + err = nla_validate(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + + nla_for_each_attr(attr, head, len, rem) { + switch (nla_type(attr)) { + case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: + opt_len = tunnel_key_copy_geneve_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + if (dst) { + dst_len -= opt_len; + dst += opt_len; + } + break; + } + } + + if (!opts_len) { + NL_SET_ERR_MSG(extack, "Empty list of tunnel options"); + return -EINVAL; + } + + if (rem > 0) { + NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes"); + return -EINVAL; + } + + return opts_len; +} + +static int tunnel_key_get_opts_len(struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + return tunnel_key_copy_opts(nla, NULL, 0, extack); +} + +static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, + int opts_len, struct netlink_ext_ack *extack) +{ + info->options_len = opts_len; + switch (nla_type(nla_data(nla))) { + case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: +#if IS_ENABLED(CONFIG_INET) + info->key.tun_flags |= TUNNEL_GENEVE_OPT; + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif + default: + NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type"); + return -EINVAL; + } +} + static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) }, [TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, @@ -66,6 +196,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED }, }; static int tunnel_key_init(struct net *net, struct nlattr *nla, @@ -81,21 +212,28 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, struct tcf_tunnel_key *t; bool exists = false; __be16 dst_port = 0; + int opts_len = 0; __be64 key_id; __be16 flags; int ret = 0; int err; - if (!nla) + if (!nla) { + NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed"); return -EINVAL; + } err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy, - NULL); - if (err < 0) + extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes"); return err; + } - if (!tb[TCA_TUNNEL_KEY_PARMS]) + if (!tb[TCA_TUNNEL_KEY_PARMS]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key parameters"); return -EINVAL; + } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); exists = tcf_idr_check(tn, parm->index, a, bind); @@ -107,6 +245,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, break; case TCA_TUNNEL_KEY_ACT_SET: if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key id"); ret = -EINVAL; goto err_out; } @@ -121,6 +260,15 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); + if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) { + opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS], + extack); + if (opts_len < 0) { + ret = opts_len; + goto err_out; + } + } + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; @@ -131,7 +279,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, dst_port, flags, - key_id, 0); + key_id, opts_len); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { struct in6_addr saddr; @@ -143,16 +291,30 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port, 0, flags, key_id, 0); + } else { + NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); + ret = -EINVAL; + goto err_out; } if (!metadata) { - ret = -EINVAL; + NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst"); + ret = -ENOMEM; goto err_out; } + if (opts_len) { + ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS], + &metadata->u.tun_info, + opts_len, extack); + if (ret < 0) + goto err_out; + } + metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: + NL_SET_ERR_MSG(extack, "Unknown tunnel key action"); ret = -EINVAL; goto err_out; } @@ -160,14 +322,18 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_tunnel_key_ops, bind, true); - if (ret) + if (ret) { + NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); return ret; + } ret = ACT_P_CREATED; } else { tcf_idr_release(*a, bind); - if (!ovr) + if (!ovr) { + NL_SET_ERR_MSG(extack, "TC IDR already exists"); return -EEXIST; + } } t = to_tunnel_key(*a); @@ -177,6 +343,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (unlikely(!params_new)) { if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); + NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); return -ENOMEM; } @@ -216,6 +383,61 @@ static void tunnel_key_release(struct tc_action *a) } } +static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + int len = info->options_len; + u8 *src = (u8 *)(info + 1); + struct nlattr *start; + + start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); + if (!start) + return -EMSGSIZE; + + while (len > 0) { + struct geneve_opt *opt = (struct geneve_opt *)src; + + if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, + opt->opt_class) || + nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, + opt->type) || + nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, + opt->length * 4, opt + 1)) + return -EMSGSIZE; + + len -= sizeof(struct geneve_opt) + opt->length * 4; + src += sizeof(struct geneve_opt) + opt->length * 4; + } + + nla_nest_end(skb, start); + return 0; +} + +static int tunnel_key_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + struct nlattr *start; + int err; + + if (!info->options_len) + return 0; + + start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS); + if (!start) + return -EMSGSIZE; + + if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + err = tunnel_key_geneve_opts_dump(skb, info); + if (err) + return err; + } else { + return -EINVAL; + } + + nla_nest_end(skb, start); + return 0; +} + static int tunnel_key_dump_addresses(struct sk_buff *skb, const struct ip_tunnel_info *info) { @@ -266,8 +488,9 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, goto nla_put_failure; if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { - struct ip_tunnel_key *key = - ¶ms->tcft_enc_metadata->u.tun_info.key; + struct ip_tunnel_info *info = + ¶ms->tcft_enc_metadata->u.tun_info; + struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || @@ -275,7 +498,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, ¶ms->tcft_enc_metadata->u.tun_info) || nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, - !(key->tun_flags & TUNNEL_CSUM))) + !(key->tun_flags & TUNNEL_CSUM)) || + tunnel_key_opts_dump(skb, info)) goto nla_put_failure; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index cdc3c87c53e6..bbf8dda96b0e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -277,18 +277,21 @@ static bool tcf_block_offload_in_use(struct tcf_block *block) static int tcf_block_offload_cmd(struct tcf_block *block, struct net_device *dev, struct tcf_block_ext_info *ei, - enum tc_block_command command) + enum tc_block_command command, + struct netlink_ext_ack *extack) { struct tc_block_offload bo = {}; bo.command = command; bo.binder_type = ei->binder_type; bo.block = block; + bo.extack = extack; return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); } static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei) + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) { struct net_device *dev = q->dev_queue->dev; int err; @@ -299,10 +302,12 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, /* If tc offload feature is disabled and the block we try to bind * to already has some offloaded filters, forbid to bind. */ - if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) + if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) { + NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled"); return -EOPNOTSUPP; + } - err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND); + err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack); if (err == -EOPNOTSUPP) goto no_offload_dev_inc; return err; @@ -322,7 +327,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, if (!dev->netdev_ops->ndo_setup_tc) goto no_offload_dev_dec; - err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND); + err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL); if (err == -EOPNOTSUPP) goto no_offload_dev_dec; return; @@ -612,7 +617,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, if (err) goto err_chain_head_change_cb_add; - err = tcf_block_offload_bind(block, q, ei); + err = tcf_block_offload_bind(block, q, ei, extack); if (err) goto err_block_offload_bind; @@ -746,18 +751,53 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) } EXPORT_SYMBOL(tcf_block_cb_decref); +static int +tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, + void *cb_priv, bool add, bool offload_in_use, + struct netlink_ext_ack *extack) +{ + struct tcf_chain *chain; + struct tcf_proto *tp; + int err; + + list_for_each_entry(chain, &block->chain_list, list) { + for (tp = rtnl_dereference(chain->filter_chain); tp; + tp = rtnl_dereference(tp->next)) { + if (tp->ops->reoffload) { + err = tp->ops->reoffload(tp, add, cb, cb_priv, + extack); + if (err && add) + goto err_playback_remove; + } else if (add && offload_in_use) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support"); + goto err_playback_remove; + } + } + } + + return 0; + +err_playback_remove: + tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use, + extack); + return err; +} + struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, + struct netlink_ext_ack *extack) { struct tcf_block_cb *block_cb; + int err; - /* At this point, playback of previous block cb calls is not supported, - * so forbid to register to block which already has some offloaded - * filters present. - */ - if (tcf_block_offload_in_use(block)) - return ERR_PTR(-EOPNOTSUPP); + /* Replay any already present rules */ + err = tcf_block_playback_offloads(block, cb, cb_priv, true, + tcf_block_offload_in_use(block), + extack); + if (err) + return ERR_PTR(err); block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); if (!block_cb) @@ -772,17 +812,22 @@ EXPORT_SYMBOL(__tcf_block_cb_register); int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, struct netlink_ext_ack *extack) { struct tcf_block_cb *block_cb; - block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv); + block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv, + extack); return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0; } EXPORT_SYMBOL(tcf_block_cb_register); -void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb) +void __tcf_block_cb_unregister(struct tcf_block *block, + struct tcf_block_cb *block_cb) { + tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv, + false, tcf_block_offload_in_use(block), + NULL); list_del(&block_cb->list); kfree(block_cb); } @@ -796,7 +841,7 @@ void tcf_block_cb_unregister(struct tcf_block *block, block_cb = tcf_block_cb_lookup(block, cb, cb_ident); if (!block_cb) return; - __tcf_block_cb_unregister(block_cb); + __tcf_block_cb_unregister(block, block_cb); } EXPORT_SYMBOL(tcf_block_cb_unregister); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 1aa7f6511065..66e0ac9811f9 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -43,6 +43,7 @@ struct cls_bpf_prog { struct tcf_result res; bool exts_integrated; u32 gen_flags; + unsigned int in_hw_count; struct tcf_exts exts; u32 handle; u16 bpf_num_ops; @@ -174,6 +175,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, cls_bpf_offload_cmd(tp, oldprog, prog, extack); return err; } else if (err > 0) { + prog->in_hw_count = err; tcf_block_offload_inc(block, &prog->gen_flags); } } @@ -652,6 +654,42 @@ skip: } } +static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct cls_bpf_head *head = rtnl_dereference(tp->root); + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + struct cls_bpf_prog *prog; + int err; + + list_for_each_entry(prog, &head->plist, link) { + if (tc_skip_hw(prog->gen_flags)) + continue; + + tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, + extack); + cls_bpf.command = TC_CLSBPF_OFFLOAD; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = add ? prog->filter : NULL; + cls_bpf.oldprog = add ? NULL : prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; + + err = cb(TC_SETUP_CLSBPF, &cls_bpf, cb_priv); + if (err) { + if (add && tc_skip_sw(prog->gen_flags)) + return err; + continue; + } + + tc_cls_offload_cnt_update(block, &prog->in_hw_count, + &prog->gen_flags, add); + } + + return 0; +} + static struct tcf_proto_ops cls_bpf_ops __read_mostly = { .kind = "bpf", .owner = THIS_MODULE, @@ -662,6 +700,7 @@ static struct tcf_proto_ops cls_bpf_ops __read_mostly = { .change = cls_bpf_change, .delete = cls_bpf_delete, .walk = cls_bpf_walk, + .reoffload = cls_bpf_reoffload, .dump = cls_bpf_dump, .bind_class = cls_bpf_bind_class, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9e8b26a80fb3..352876bb901b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -87,6 +87,7 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; + unsigned int in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; }; @@ -289,6 +290,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, fl_hw_destroy_filter(tp, f, NULL); return err; } else if (err > 0) { + f->in_hw_count = err; tcf_block_offload_inc(block, &f->flags); } @@ -1087,6 +1089,47 @@ skip: } } +static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct tc_cls_flower_offload cls_flower = {}; + struct tcf_block *block = tp->chain->block; + struct fl_flow_mask *mask; + struct cls_fl_filter *f; + int err; + + list_for_each_entry(mask, &head->masks, list) { + list_for_each_entry(f, &mask->filters, list) { + if (tc_skip_hw(f->flags)) + continue; + + tc_cls_common_offload_init(&cls_flower.common, tp, + f->flags, extack); + cls_flower.command = add ? + TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; + cls_flower.cookie = (unsigned long)f; + cls_flower.dissector = &mask->dissector; + cls_flower.mask = &f->mkey; + cls_flower.key = &f->key; + cls_flower.exts = &f->exts; + cls_flower.classid = f->res.classid; + + err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + if (err) { + if (add && tc_skip_sw(f->flags)) + return err; + continue; + } + + tc_cls_offload_cnt_update(block, &f->in_hw_count, + &f->flags, add); + } + } + + return 0; +} + static int fl_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) @@ -1438,6 +1481,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .change = fl_change, .delete = fl_delete, .walk = fl_walk, + .reoffload = fl_reoffload, .dump = fl_dump, .bind_class = fl_bind_class, .owner = THIS_MODULE, diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 47b207ef7762..af16f36ed578 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -21,6 +21,7 @@ struct cls_mall_head { struct tcf_result res; u32 handle; u32 flags; + unsigned int in_hw_count; struct rcu_work rwork; }; @@ -95,6 +96,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, mall_destroy_hw_filter(tp, head, cookie, NULL); return err; } else if (err > 0) { + head->in_hw_count = err; tcf_block_offload_inc(block, &head->flags); } @@ -235,6 +237,35 @@ skip: arg->count++; } +static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct cls_mall_head *head = rtnl_dereference(tp->root); + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + int err; + + if (tc_skip_hw(head->flags)) + return 0; + + tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack); + cls_mall.command = add ? + TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY; + cls_mall.exts = &head->exts; + cls_mall.cookie = (unsigned long)head; + + err = cb(TC_SETUP_CLSMATCHALL, &cls_mall, cb_priv); + if (err) { + if (add && tc_skip_sw(head->flags)) + return err; + return 0; + } + + tc_cls_offload_cnt_update(block, &head->in_hw_count, &head->flags, add); + + return 0; +} + static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { @@ -289,6 +320,7 @@ static struct tcf_proto_ops cls_mall_ops __read_mostly = { .change = mall_change, .delete = mall_delete, .walk = mall_walk, + .reoffload = mall_reoffload, .dump = mall_dump, .bind_class = mall_bind_class, .owner = THIS_MODULE, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index fb861f90fde6..d5d2a6dc3921 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -62,6 +62,7 @@ struct tc_u_knode { struct tc_u32_pcnt __percpu *pf; #endif u32 flags; + unsigned int in_hw_count; #ifdef CONFIG_CLS_U32_MARK u32 val; u32 mask; @@ -571,6 +572,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32_remove_hw_knode(tp, n, NULL); return err; } else if (err > 0) { + n->in_hw_count = err; tcf_block_offload_inc(block, &n->flags); } @@ -1199,6 +1201,114 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } +static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + bool add, tc_setup_cb_t *cb, void *cb_priv, + struct netlink_ext_ack *extack) +{ + struct tc_cls_u32_offload cls_u32 = {}; + int err; + + tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack); + cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE; + cls_u32.hnode.divisor = ht->divisor; + cls_u32.hnode.handle = ht->handle; + cls_u32.hnode.prio = ht->prio; + + err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv); + if (err && add && tc_skip_sw(ht->flags)) + return err; + + return 0; +} + +static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, + bool add, tc_setup_cb_t *cb, void *cb_priv, + struct netlink_ext_ack *extack) +{ + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + struct tcf_block *block = tp->chain->block; + struct tc_cls_u32_offload cls_u32 = {}; + int err; + + tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack); + cls_u32.command = add ? + TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE; + cls_u32.knode.handle = n->handle; + + if (add) { + cls_u32.knode.fshift = n->fshift; +#ifdef CONFIG_CLS_U32_MARK + cls_u32.knode.val = n->val; + cls_u32.knode.mask = n->mask; +#else + cls_u32.knode.val = 0; + cls_u32.knode.mask = 0; +#endif + cls_u32.knode.sel = &n->sel; + cls_u32.knode.exts = &n->exts; + if (n->ht_down) + cls_u32.knode.link_handle = ht->handle; + } + + err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv); + if (err) { + if (add && tc_skip_sw(n->flags)) + return err; + return 0; + } + + tc_cls_offload_cnt_update(block, &n->in_hw_count, &n->flags, add); + + return 0; +} + +static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct tc_u_common *tp_c = tp->data; + struct tc_u_hnode *ht; + struct tc_u_knode *n; + unsigned int h; + int err; + + for (ht = rtnl_dereference(tp_c->hlist); + ht; + ht = rtnl_dereference(ht->next)) { + if (ht->prio != tp->prio) + continue; + + /* When adding filters to a new dev, try to offload the + * hashtable first. When removing, do the filters before the + * hashtable. + */ + if (add && !tc_skip_hw(ht->flags)) { + err = u32_reoffload_hnode(tp, ht, add, cb, cb_priv, + extack); + if (err) + return err; + } + + for (h = 0; h <= ht->divisor; h++) { + for (n = rtnl_dereference(ht->ht[h]); + n; + n = rtnl_dereference(n->next)) { + if (tc_skip_hw(n->flags)) + continue; + + err = u32_reoffload_knode(tp, n, add, cb, + cb_priv, extack); + if (err) + return err; + } + } + + if (!add && !tc_skip_hw(ht->flags)) + u32_reoffload_hnode(tp, ht, add, cb, cb_priv, extack); + } + + return 0; +} + static void u32_bind_class(void *fh, u32 classid, unsigned long cl) { struct tc_u_knode *n = fh; @@ -1336,6 +1446,7 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = { .change = u32_change, .delete = u32_delete, .walk = u32_walk, + .reoffload = u32_reoffload, .dump = u32_dump, .bind_class = u32_bind_class, .owner = THIS_MODULE, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 2a4ab7caf553..43c4bfe625a9 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -126,7 +126,6 @@ struct htb_class { union { struct htb_class_leaf { - struct list_head drop_list; int deficit[TC_HTB_MAXDEPTH]; struct Qdisc *q; } leaf; @@ -171,7 +170,6 @@ struct htb_sched { struct qdisc_watchdog watchdog; s64 now; /* cached dequeue time */ - struct list_head drops[TC_HTB_NUMPRIO];/* active leaves (for drops) */ /* time of nearest event per level (row) */ s64 near_ev_cache[TC_HTB_MAXDEPTH]; @@ -562,8 +560,6 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; htb_activate_prios(q, cl); - list_add_tail(&cl->un.leaf.drop_list, - q->drops + cl->prio); } } @@ -579,7 +575,6 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) htb_deactivate_prios(q, cl); cl->prio_activity = 0; - list_del_init(&cl->un.leaf.drop_list); } static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, @@ -981,7 +976,6 @@ static void htb_reset(struct Qdisc *sch) else { if (cl->un.leaf.q) qdisc_reset(cl->un.leaf.q); - INIT_LIST_HEAD(&cl->un.leaf.drop_list); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; @@ -993,8 +987,6 @@ static void htb_reset(struct Qdisc *sch) sch->qstats.backlog = 0; memset(q->hlevel, 0, sizeof(q->hlevel)); memset(q->row_mask, 0, sizeof(q->row_mask)); - for (i = 0; i < TC_HTB_NUMPRIO; i++) - INIT_LIST_HEAD(q->drops + i); } static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = { @@ -1024,7 +1016,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_glob *gopt; int err; - int i; qdisc_watchdog_init(&q->watchdog, sch); INIT_WORK(&q->work, htb_work_func); @@ -1050,8 +1041,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; - for (i = 0; i < TC_HTB_NUMPRIO; i++) - INIT_LIST_HEAD(q->drops + i); qdisc_skb_head_init(&q->direct_queue); @@ -1224,7 +1213,6 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, parent->level = 0; memset(&parent->un.inner, 0, sizeof(parent->un.inner)); - INIT_LIST_HEAD(&parent->un.leaf.drop_list); parent->un.leaf.q = new_q ? new_q : &noop_qdisc; parent->tokens = parent->buffer; parent->ctokens = parent->cbuffer; @@ -1418,7 +1406,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } cl->children = 0; - INIT_LIST_HEAD(&cl->un.leaf.drop_list); RB_CLEAR_NODE(&cl->pq_node); for (prio = 0; prio < TC_HTB_NUMPRIO; prio++) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7d6801fc5340..ad18a2052416 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -68,6 +68,11 @@ Fabio Ludovici <fabio.ludovici at yahoo.it> */ +struct disttable { + u32 size; + s16 table[0]; +}; + struct netem_sched_data { /* internal t(ime)fifo qdisc uses t_root and sch->limit */ struct rb_root t_root; @@ -99,10 +104,7 @@ struct netem_sched_data { u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; - struct disttable { - u32 size; - s16 table[0]; - } *delay_dist; + struct disttable *delay_dist; enum { CLG_RANDOM, @@ -142,6 +144,7 @@ struct netem_sched_data { s32 bytes_left; } slot; + struct disttable *slot_dist; }; /* Time stamp put into socket buffer control block @@ -180,7 +183,7 @@ static u32 get_crandom(struct crndstate *state) u64 value, rho; unsigned long answer; - if (state->rho == 0) /* no correlation */ + if (!state || state->rho == 0) /* no correlation */ return prandom_u32(); value = prandom_u32(); @@ -601,10 +604,19 @@ finish_segs: static void get_slot_next(struct netem_sched_data *q, u64 now) { - q->slot.slot_next = now + q->slot_config.min_delay + - (prandom_u32() * - (q->slot_config.max_delay - - q->slot_config.min_delay) >> 32); + s64 next_delay; + + if (!q->slot_dist) + next_delay = q->slot_config.min_delay + + (prandom_u32() * + (q->slot_config.max_delay - + q->slot_config.min_delay) >> 32); + else + next_delay = tabledist(q->slot_config.dist_delay, + (s32)(q->slot_config.dist_jitter), + NULL, q->slot_dist); + + q->slot.slot_next = now + next_delay; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; } @@ -721,9 +733,9 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) +static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, + const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); spinlock_t *root_lock; @@ -744,7 +756,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) root_lock = qdisc_root_sleeping_lock(sch); spin_lock_bh(root_lock); - swap(q->delay_dist, d); + swap(*tbl, d); spin_unlock_bh(root_lock); dist_free(d); @@ -762,7 +774,8 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) q->slot_config.max_bytes = INT_MAX; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; - if (q->slot_config.min_delay | q->slot_config.max_delay) + if (q->slot_config.min_delay | q->slot_config.max_delay | + q->slot_config.dist_jitter) q->slot.slot_next = ktime_get_ns(); else q->slot.slot_next = 0; @@ -926,16 +939,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); - if (ret) { - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - return ret; - } + ret = get_dist_table(sch, &q->delay_dist, + tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto get_table_failure; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(sch, &q->slot_dist, + tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto get_table_failure; } sch->limit = qopt->limit; @@ -983,6 +997,15 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, get_slot(q, tb[TCA_NETEM_SLOT]); return ret; + +get_table_failure: + /* recover clg and loss_model, in case of + * q->clg and q->loss_model were modified + * in get_loss_clg() + */ + q->clg = old_clg; + q->loss_model = old_loss_model; + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, @@ -1011,6 +1034,7 @@ static void netem_destroy(struct Qdisc *sch) if (q->qdisc) qdisc_destroy(q->qdisc); dist_free(q->delay_dist); + dist_free(q->slot_dist); } static int dump_loss_model(const struct netem_sched_data *q, @@ -1127,7 +1151,8 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (dump_loss_model(q, skb) != 0) goto nla_put_failure; - if (q->slot_config.min_delay | q->slot_config.max_delay) { + if (q->slot_config.min_delay | q->slot_config.max_delay | + q->slot_config.dist_jitter) { slot = q->slot_config; if (slot.max_packets == INT_MAX) slot.max_packets = 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index ba8a6e6c36fa..9bbc5f92c941 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -56,6 +56,7 @@ #include <net/sctp/sm.h> #include <net/sctp/checksum.h> #include <net/net_namespace.h> +#include <linux/rhashtable.h> /* Forward declarations for internal helpers. */ static int sctp_rcv_ootb(struct sk_buff *); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ce620e878538..0e4c8332771a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -66,6 +66,7 @@ #include <linux/slab.h> #include <linux/file.h> #include <linux/compat.h> +#include <linux/rhashtable.h> #include <net/ip.h> #include <net/icmp.h> @@ -4169,6 +4170,28 @@ out: return retval; } +static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval, + unsigned int optlen) +{ + int val; + + if (!sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + if (sctp_sk(sk)->ep->base.bind_addr.port) + return -EFAULT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EFAULT; + + sctp_sk(sk)->reuse = !!val; + + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4363,6 +4386,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_interleaving_supported(sk, optval, optlen); break; + case SCTP_REUSE_PORT: + retval = sctp_setsockopt_reuse_port(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7196,6 +7222,26 @@ out: return retval; } +static int sctp_getsockopt_reuse_port(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + int val; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + val = sctp_sk(sk)->reuse; + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -7391,6 +7437,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_interleaving_supported(sk, len, optval, optlen); break; + case SCTP_REUSE_PORT: + retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7428,6 +7477,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { + bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse); struct sctp_bind_hashbucket *head; /* hash list */ struct sctp_bind_bucket *pp; unsigned short snum; @@ -7500,13 +7550,11 @@ pp_found: * used by other socket (pp->owner not empty); that other * socket is going to be sk2. */ - int reuse = sk->sk_reuse; struct sock *sk2; pr_debug("%s: found a possible match\n", __func__); - if (pp->fastreuse && sk->sk_reuse && - sk->sk_state != SCTP_SS_LISTENING) + if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING) goto success; /* Run through the list of sockets bound to the port @@ -7524,7 +7572,7 @@ pp_found: ep2 = sctp_sk(sk2)->ep; if (sk == sk2 || - (reuse && sk2->sk_reuse && + (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) && sk2->sk_state != SCTP_SS_LISTENING)) continue; @@ -7548,12 +7596,12 @@ pp_not_found: * SO_REUSEADDR on this socket -sk-). */ if (hlist_empty(&pp->owner)) { - if (sk->sk_reuse && sk->sk_state != SCTP_SS_LISTENING) + if (reuse && sk->sk_state != SCTP_SS_LISTENING) pp->fastreuse = 1; else pp->fastreuse = 0; } else if (pp->fastreuse && - (!sk->sk_reuse || sk->sk_state == SCTP_SS_LISTENING)) + (!reuse || sk->sk_state == SCTP_SS_LISTENING)) pp->fastreuse = 0; /* We are set, so fill up all the data in the hash table @@ -7684,7 +7732,7 @@ int sctp_inet_listen(struct socket *sock, int backlog) err = 0; sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; - if (sk->sk_reuse) + if (sk->sk_reuse || sctp_sk(sk)->reuse) sctp_sk(sk)->bind_hash->fastreuse = 1; goto out; } @@ -8551,6 +8599,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; + sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; newsk->sk_destruct = sctp_destruct_sock; diff --git a/net/smc/Makefile b/net/smc/Makefile index 188104654b54..4df96b4b8130 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o -smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o +smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e017b6a4452b..f3fdf3714f8b 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -23,6 +23,7 @@ #include <linux/workqueue.h> #include <linux/in.h> #include <linux/sched/signal.h> +#include <linux/if_vlan.h> #include <net/sock.h> #include <net/tcp.h> @@ -35,6 +36,7 @@ #include "smc_cdc.h" #include "smc_core.h" #include "smc_ib.h" +#include "smc_ism.h" #include "smc_pnet.h" #include "smc_tx.h" #include "smc_rx.h" @@ -380,8 +382,8 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) return 0; } -static void smc_conn_save_peer_info(struct smc_sock *smc, - struct smc_clc_msg_accept_confirm *clc) +static void smcr_conn_save_peer_info(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *clc) { int bufsize = smc_uncompress_bufsize(clc->rmbe_size); @@ -392,6 +394,28 @@ static void smc_conn_save_peer_info(struct smc_sock *smc, smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); } +static void smcd_conn_save_peer_info(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *clc) +{ + int bufsize = smc_uncompress_bufsize(clc->dmbe_size); + + smc->conn.peer_rmbe_idx = clc->dmbe_idx; + smc->conn.peer_token = clc->token; + /* msg header takes up space in the buffer */ + smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); + atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); + smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx; +} + +static void smc_conn_save_peer_info(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *clc) +{ + if (smc->conn.lgr->is_smcd) + smcd_conn_save_peer_info(smc, clc); + else + smcr_conn_save_peer_info(smc, clc); +} + static void smc_link_save_peer_info(struct smc_link *link, struct smc_clc_msg_accept_confirm *clc) { @@ -458,15 +482,51 @@ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev, return reason_code; } +/* check if there is an ISM device available for this connection. */ +/* called for connect and listen */ +static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev) +{ + /* Find ISM device with same PNETID as connecting interface */ + smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev); + if (!(*ismdev)) + return SMC_CLC_DECL_CNFERR; /* configuration error */ + return 0; +} + +/* Check for VLAN ID and register it on ISM device just for CLC handshake */ +static int smc_connect_ism_vlan_setup(struct smc_sock *smc, + struct smcd_dev *ismdev, + unsigned short vlan_id) +{ + if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id)) + return SMC_CLC_DECL_CNFERR; + return 0; +} + +/* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is + * used, the VLAN ID will be registered again during the connection setup. + */ +static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd, + struct smcd_dev *ismdev, + unsigned short vlan_id) +{ + if (!is_smcd) + return 0; + if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id)) + return SMC_CLC_DECL_CNFERR; + return 0; +} + /* CLC handshake during connect */ -static int smc_connect_clc(struct smc_sock *smc, +static int smc_connect_clc(struct smc_sock *smc, int smc_type, struct smc_clc_msg_accept_confirm *aclc, - struct smc_ib_device *ibdev, u8 ibport) + struct smc_ib_device *ibdev, u8 ibport, + struct smcd_dev *ismdev) { int rc = 0; /* do inband token exchange */ - rc = smc_clc_send_proposal(smc, ibdev, ibport); + rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev); if (rc) return rc; /* receive SMC Accept CLC message */ @@ -483,8 +543,8 @@ static int smc_connect_rdma(struct smc_sock *smc, int reason_code = 0; mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(smc, ibdev, ibport, &aclc->lcl, - aclc->hdr.flag); + local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev, + ibport, &aclc->lcl, NULL, 0); if (local_contact < 0) { if (local_contact == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ @@ -499,7 +559,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_conn_save_peer_info(smc, aclc); /* create send buffer and rmb */ - if (smc_buf_create(smc)) + if (smc_buf_create(smc, false)) return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact); if (local_contact == SMC_FIRST_CONTACT) @@ -546,11 +606,50 @@ static int smc_connect_rdma(struct smc_sock *smc, return 0; } +/* setup for ISM connection of client */ +static int smc_connect_ism(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *aclc, + struct smcd_dev *ismdev) +{ + int local_contact = SMC_FIRST_CONTACT; + int rc = 0; + + mutex_lock(&smc_create_lgr_pending); + local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, + NULL, ismdev, aclc->gid); + if (local_contact < 0) + return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0); + + /* Create send and receive buffers */ + if (smc_buf_create(smc, true)) + return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact); + + smc_conn_save_peer_info(smc, aclc); + smc_close_init(smc); + smc_rx_init(smc); + smc_tx_init(smc); + + rc = smc_clc_send_confirm(smc); + if (rc) + return smc_connect_abort(smc, rc, local_contact); + mutex_unlock(&smc_create_lgr_pending); + + smc_copy_sock_settings_to_clc(smc); + if (smc->sk.sk_state == SMC_INIT) + smc->sk.sk_state = SMC_ACTIVE; + + return 0; +} + /* perform steps before actually connecting */ static int __smc_connect(struct smc_sock *smc) { + bool ism_supported = false, rdma_supported = false; struct smc_clc_msg_accept_confirm aclc; struct smc_ib_device *ibdev; + struct smcd_dev *ismdev; + unsigned short vlan; + int smc_type; int rc = 0; u8 ibport; @@ -567,20 +666,52 @@ static int __smc_connect(struct smc_sock *smc) if (using_ipsec(smc)) return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC); - /* check if a RDMA device is available; if not, fall back */ - if (smc_check_rdma(smc, &ibdev, &ibport)) + /* check for VLAN ID */ + if (smc_vlan_by_tcpsk(smc->clcsock, &vlan)) + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR); + + /* check if there is an ism device available */ + if (!smc_check_ism(smc, &ismdev) && + !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) { + /* ISM is supported for this connection */ + ism_supported = true; + smc_type = SMC_TYPE_D; + } + + /* check if there is a rdma device available */ + if (!smc_check_rdma(smc, &ibdev, &ibport)) { + /* RDMA is supported for this connection */ + rdma_supported = true; + if (ism_supported) + smc_type = SMC_TYPE_B; /* both */ + else + smc_type = SMC_TYPE_R; /* only RDMA */ + } + + /* if neither ISM nor RDMA are supported, fallback */ + if (!rdma_supported && !ism_supported) return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR); /* perform CLC handshake */ - rc = smc_connect_clc(smc, &aclc, ibdev, ibport); - if (rc) + rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev); + if (rc) { + smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan); return smc_connect_decline_fallback(smc, rc); + } - /* connect using rdma */ - rc = smc_connect_rdma(smc, &aclc, ibdev, ibport); - if (rc) + /* depending on previous steps, connect using rdma or ism */ + if (rdma_supported && aclc.hdr.path == SMC_TYPE_R) + rc = smc_connect_rdma(smc, &aclc, ibdev, ibport); + else if (ism_supported && aclc.hdr.path == SMC_TYPE_D) + rc = smc_connect_ism(smc, &aclc, ismdev); + else + rc = SMC_CLC_DECL_CNFERR; + if (rc) { + smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan); return smc_connect_decline_fallback(smc, rc); + } + smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan); return 0; } @@ -948,7 +1079,8 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, int *local_contact) { /* allocate connection / link group */ - *local_contact = smc_conn_create(new_smc, ibdev, ibport, &pclc->lcl, 0); + *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, + &pclc->lcl, NULL, 0); if (*local_contact < 0) { if (*local_contact == -ENOMEM) return SMC_CLC_DECL_MEM;/* insufficient memory*/ @@ -956,12 +1088,50 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, } /* create send buffer and rmb */ - if (smc_buf_create(new_smc)) + if (smc_buf_create(new_smc, false)) return SMC_CLC_DECL_MEM; return 0; } +/* listen worker: initialize connection and buffers for SMC-D */ +static int smc_listen_ism_init(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smcd_dev *ismdev, + int *local_contact) +{ + struct smc_clc_msg_smcd *pclc_smcd; + + pclc_smcd = smc_get_clc_msg_smcd(pclc); + *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL, + ismdev, pclc_smcd->gid); + if (*local_contact < 0) { + if (*local_contact == -ENOMEM) + return SMC_CLC_DECL_MEM;/* insufficient memory*/ + return SMC_CLC_DECL_INTERR; /* other error */ + } + + /* Check if peer can be reached via ISM device */ + if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid, + new_smc->conn.lgr->vlan_id, + new_smc->conn.lgr->smcd)) { + if (*local_contact == SMC_FIRST_CONTACT) + smc_lgr_forget(new_smc->conn.lgr); + smc_conn_free(&new_smc->conn); + return SMC_CLC_DECL_CNFERR; + } + + /* Create send and receive buffers */ + if (smc_buf_create(new_smc, true)) { + if (*local_contact == SMC_FIRST_CONTACT) + smc_lgr_forget(new_smc->conn.lgr); + smc_conn_free(&new_smc->conn); + return SMC_CLC_DECL_MEM; + } + + return 0; +} + /* listen worker: register buffers */ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) { @@ -1020,6 +1190,8 @@ static void smc_listen_work(struct work_struct *work) struct smc_clc_msg_accept_confirm cclc; struct smc_clc_msg_proposal *pclc; struct smc_ib_device *ibdev; + bool ism_supported = false; + struct smcd_dev *ismdev; u8 buf[SMC_CLC_MAX_LEN]; int local_contact = 0; int reason_code = 0; @@ -1060,12 +1232,21 @@ static void smc_listen_work(struct work_struct *work) smc_rx_init(new_smc); smc_tx_init(new_smc); + /* check if ISM is available */ + if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) && + !smc_check_ism(new_smc, &ismdev) && + !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) { + ism_supported = true; + } + /* check if RDMA is available */ - if (smc_check_rdma(new_smc, &ibdev, &ibport) || - smc_listen_rdma_check(new_smc, pclc) || - smc_listen_rdma_init(new_smc, pclc, ibdev, ibport, - &local_contact) || - smc_listen_rdma_reg(new_smc, local_contact)) { + if (!ism_supported && + ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) || + smc_check_rdma(new_smc, &ibdev, &ibport) || + smc_listen_rdma_check(new_smc, pclc) || + smc_listen_rdma_init(new_smc, pclc, ibdev, ibport, + &local_contact) || + smc_listen_rdma_reg(new_smc, local_contact))) { /* SMC not supported, decline */ mutex_unlock(&smc_create_lgr_pending); smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact); @@ -1090,7 +1271,8 @@ static void smc_listen_work(struct work_struct *work) } /* finish worker */ - smc_listen_rdma_finish(new_smc, &cclc, local_contact); + if (!ism_supported) + smc_listen_rdma_finish(new_smc, &cclc, local_contact); smc_conn_save_peer_info(new_smc, &cclc); mutex_unlock(&smc_create_lgr_pending); smc_listen_out_connected(new_smc); diff --git a/net/smc/smc.h b/net/smc/smc.h index d7ca26570482..be20acd7b5ab 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -21,8 +21,6 @@ #define SMCPROTO_SMC 0 /* SMC protocol, IPv4 */ #define SMCPROTO_SMC6 1 /* SMC protocol, IPv6 */ -#define SMC_MAX_PORTS 2 /* Max # of ports */ - extern struct proto smc_proto; extern struct proto smc_proto6; @@ -185,6 +183,11 @@ struct smc_connection { spinlock_t acurs_lock; /* protect cursors */ #endif struct work_struct close_work; /* peer sent some closing */ + struct tasklet_struct rx_tsklet; /* Receiver tasklet for SMC-D */ + u8 rx_off; /* receive offset: + * 0 for SMC-R, 32 for SMC-D + */ + u64 peer_token; /* SMC-D token of peer */ }; struct smc_connect_info { diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a7e8d63fc8ae..621d8cca570b 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -117,7 +117,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, return rc; } -int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) +static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) { struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; @@ -130,6 +130,21 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) return smc_cdc_msg_send(conn, wr_buf, pend); } +int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) +{ + int rc; + + if (conn->lgr->is_smcd) { + spin_lock_bh(&conn->send_lock); + rc = smcd_cdc_msg_send(conn); + spin_unlock_bh(&conn->send_lock); + } else { + rc = smcr_cdc_get_slot_and_msg_send(conn); + } + + return rc; +} + static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend, unsigned long data) { @@ -157,6 +172,45 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn) (unsigned long)conn); } +/* Send a SMC-D CDC header. + * This increments the free space available in our send buffer. + * Also update the confirmed receive buffer with what was sent to the peer. + */ +int smcd_cdc_msg_send(struct smc_connection *conn) +{ + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + struct smcd_cdc_msg cdc; + int rc, diff; + + memset(&cdc, 0, sizeof(cdc)); + cdc.common.type = SMC_CDC_MSG_TYPE; + cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap; + cdc.prod_count = conn->local_tx_ctrl.prod.count; + + cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap; + cdc.cons_count = conn->local_tx_ctrl.cons.count; + cdc.prod_flags = conn->local_tx_ctrl.prod_flags; + cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags; + rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1); + if (rc) + return rc; + smc_curs_write(&conn->rx_curs_confirmed, + smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn); + /* Calculate transmitted data and increment free send buffer space */ + diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin, + &conn->tx_curs_sent); + /* increased by confirmed number of bytes */ + smp_mb__before_atomic(); + atomic_add(diff, &conn->sndbuf_space); + /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ + smp_mb__after_atomic(); + smc_curs_write(&conn->tx_curs_fin, + smc_curs_read(&conn->tx_curs_sent, conn), conn); + + smc_tx_sndbuf_nonfull(smc); + return rc; +} + /********************************* receive ***********************************/ static inline bool smc_cdc_before(u16 seq1, u16 seq2) @@ -178,7 +232,7 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc, if (!sock_flag(&smc->sk, SOCK_URGINLINE)) /* we'll skip the urgent byte, so don't account for it */ (*diff_prod)--; - base = (char *)conn->rmb_desc->cpu_addr; + base = (char *)conn->rmb_desc->cpu_addr + conn->rx_off; if (conn->urg_curs.count) conn->urg_rx_byte = *(base + conn->urg_curs.count - 1); else @@ -276,6 +330,34 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc) sock_put(&smc->sk); /* no free sk in softirq-context */ } +/* Schedule a tasklet for this connection. Triggered from the ISM device IRQ + * handler to indicate update in the DMBE. + * + * Context: + * - tasklet context + */ +static void smcd_cdc_rx_tsklet(unsigned long data) +{ + struct smc_connection *conn = (struct smc_connection *)data; + struct smcd_cdc_msg cdc; + struct smc_sock *smc; + + if (!conn) + return; + + memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc)); + smc = container_of(conn, struct smc_sock, conn); + smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc); +} + +/* Initialize receive tasklet. Called from ISM device IRQ handler to start + * receiver side. + */ +void smcd_cdc_rx_init(struct smc_connection *conn) +{ + tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn); +} + /***************************** init, exit, misc ******************************/ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index f60082fee5b8..8fbce4fee3e4 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -50,6 +50,20 @@ struct smc_cdc_msg { u8 reserved[18]; } __packed; /* format defined in RFC7609 */ +/* CDC message for SMC-D */ +struct smcd_cdc_msg { + struct smc_wr_rx_hdr common; /* Type = 0xFE */ + u8 res1[7]; + u16 prod_wrap; + u32 prod_count; + u8 res2[2]; + u16 cons_wrap; + u32 cons_count; + struct smc_cdc_producer_flags prod_flags; + struct smc_cdc_conn_state_flags conn_state_flags; + u8 res3[8]; +} __packed; + static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { return conn->local_rx_ctrl.conn_state_flags.peer_conn_abort || @@ -204,9 +218,9 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local, smc_curs_write(local, smc_curs_read(&temp, conn), conn); } -static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, - struct smc_cdc_msg *peer, - struct smc_connection *conn) +static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, + struct smc_cdc_msg *peer, + struct smc_connection *conn) { local->common.type = peer->common.type; local->len = peer->len; @@ -218,6 +232,27 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, local->conn_state_flags = peer->conn_state_flags; } +static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, + struct smcd_cdc_msg *peer) +{ + local->prod.wrap = peer->prod_wrap; + local->prod.count = peer->prod_count; + local->cons.wrap = peer->cons_wrap; + local->cons.count = peer->cons_count; + local->prod_flags = peer->prod_flags; + local->conn_state_flags = peer->conn_state_flags; +} + +static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, + struct smc_cdc_msg *peer, + struct smc_connection *conn) +{ + if (conn->lgr->is_smcd) + smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer); + else + smcr_cdc_msg_to_host(local, peer, conn); +} + struct smc_cdc_tx_pend; int smc_cdc_get_free_slot(struct smc_connection *conn, @@ -227,6 +262,8 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend); int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn); +int smcd_cdc_msg_send(struct smc_connection *conn); int smc_cdc_init(void) __init; +void smcd_cdc_rx_init(struct smc_connection *conn); #endif /* SMC_CDC_H */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 717449b1da0b..038d70ef7892 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -23,9 +23,15 @@ #include "smc_core.h" #include "smc_clc.h" #include "smc_ib.h" +#include "smc_ism.h" + +#define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 +#define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 /* eye catcher "SMCR" EBCDIC for CLC messages */ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; +/* eye catcher "SMCD" EBCDIC for CLC messages */ +static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; /* check if received message has a correct header length and contains valid * heading and trailing eyecatchers @@ -38,10 +44,14 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) struct smc_clc_msg_decline *dclc; struct smc_clc_msg_trail *trl; - if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER))) + if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && + memcmp(clcm->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER))) return false; switch (clcm->type) { case SMC_CLC_PROPOSAL: + if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D && + clcm->path != SMC_TYPE_B) + return false; pclc = (struct smc_clc_msg_proposal *)clcm; pclc_prfx = smc_clc_proposal_get_prefix(pclc); if (ntohs(pclc->hdr.length) != @@ -56,10 +66,16 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) break; case SMC_CLC_ACCEPT: case SMC_CLC_CONFIRM: + if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D) + return false; clc = (struct smc_clc_msg_accept_confirm *)clcm; - if (ntohs(clc->hdr.length) != sizeof(*clc)) + if ((clcm->path == SMC_TYPE_R && + ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) || + (clcm->path == SMC_TYPE_D && + ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN)) return false; - trl = &clc->trl; + trl = (struct smc_clc_msg_trail *) + ((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl)); break; case SMC_CLC_DECLINE: dclc = (struct smc_clc_msg_decline *)clcm; @@ -70,7 +86,8 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) default: return false; } - if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER))) + if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && + memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER))) return false; return true; } @@ -295,6 +312,9 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || (datlen > buflen) || + (clcm->version != SMC_CLC_V1) || + (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D && + clcm->path != SMC_TYPE_B) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; @@ -356,17 +376,18 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) } /* send CLC PROPOSAL message across internal TCP socket */ -int smc_clc_send_proposal(struct smc_sock *smc, - struct smc_ib_device *smcibdev, - u8 ibport) +int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, + struct smc_ib_device *ibdev, u8 ibport, + struct smcd_dev *ismdev) { struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX]; struct smc_clc_msg_proposal_prefix pclc_prfx; + struct smc_clc_msg_smcd pclc_smcd; struct smc_clc_msg_proposal pclc; struct smc_clc_msg_trail trl; int len, i, plen, rc; int reason_code = 0; - struct kvec vec[4]; + struct kvec vec[5]; struct msghdr msg; /* retrieve ip prefixes for CLC proposal msg */ @@ -381,18 +402,34 @@ int smc_clc_send_proposal(struct smc_sock *smc, memset(&pclc, 0, sizeof(pclc)); memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); pclc.hdr.type = SMC_CLC_PROPOSAL; - pclc.hdr.length = htons(plen); pclc.hdr.version = SMC_CLC_V1; /* SMC version */ - memcpy(pclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&pclc.lcl.gid, &smcibdev->gid[ibport - 1], SMC_GID_SIZE); - memcpy(&pclc.lcl.mac, &smcibdev->mac[ibport - 1], ETH_ALEN); - pclc.iparea_offset = htons(0); + pclc.hdr.path = smc_type; + if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) { + /* add SMC-R specifics */ + memcpy(pclc.lcl.id_for_peer, local_systemid, + sizeof(local_systemid)); + memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE); + memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN); + pclc.iparea_offset = htons(0); + } + if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) { + /* add SMC-D specifics */ + memset(&pclc_smcd, 0, sizeof(pclc_smcd)); + plen += sizeof(pclc_smcd); + pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET); + pclc_smcd.gid = ismdev->local_gid; + } + pclc.hdr.length = htons(plen); memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); memset(&msg, 0, sizeof(msg)); i = 0; vec[i].iov_base = &pclc; vec[i++].iov_len = sizeof(pclc); + if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) { + vec[i].iov_base = &pclc_smcd; + vec[i++].iov_len = sizeof(pclc_smcd); + } vec[i].iov_base = &pclc_prfx; vec[i++].iov_len = sizeof(pclc_prfx); if (pclc_prfx.ipv6_prefixes_cnt > 0) { @@ -428,35 +465,56 @@ int smc_clc_send_confirm(struct smc_sock *smc) struct kvec vec; int len; - link = &conn->lgr->lnk[SMC_SINGLE_LINK]; /* send SMC Confirm CLC msg */ memset(&cclc, 0, sizeof(cclc)); - memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); cclc.hdr.type = SMC_CLC_CONFIRM; - cclc.hdr.length = htons(sizeof(cclc)); cclc.hdr.version = SMC_CLC_V1; /* SMC version */ - memcpy(cclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1], - SMC_GID_SIZE); - memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); - hton24(cclc.qpn, link->roce_qp->qp_num); - cclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); - cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ - cclc.rmbe_alert_token = htonl(conn->alert_token_local); - cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); - cclc.rmbe_size = conn->rmbe_size_short; - cclc.rmb_dma_addr = cpu_to_be64( - (u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl)); - hton24(cclc.psn, link->psn_initial); - - memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + if (smc->conn.lgr->is_smcd) { + /* SMC-D specific settings */ + memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER, + sizeof(SMCD_EYECATCHER)); + cclc.hdr.path = SMC_TYPE_D; + cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); + cclc.gid = conn->lgr->smcd->local_gid; + cclc.token = conn->rmb_desc->token; + cclc.dmbe_size = conn->rmbe_size_short; + cclc.dmbe_idx = 0; + memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); + memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER, + sizeof(SMCD_EYECATCHER)); + } else { + /* SMC-R specific settings */ + link = &conn->lgr->lnk[SMC_SINGLE_LINK]; + memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + cclc.hdr.path = SMC_TYPE_R; + cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + memcpy(cclc.lcl.id_for_peer, local_systemid, + sizeof(local_systemid)); + memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1], + SMC_GID_SIZE); + memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], + ETH_ALEN); + hton24(cclc.qpn, link->roce_qp->qp_num); + cclc.rmb_rkey = + htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ + cclc.rmbe_alert_token = htonl(conn->alert_token_local); + cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); + cclc.rmbe_size = conn->rmbe_size_short; + cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address + (conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl)); + hton24(cclc.psn, link->psn_initial); + memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + } memset(&msg, 0, sizeof(msg)); vec.iov_base = &cclc; - vec.iov_len = sizeof(cclc); - len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(cclc)); - if (len < sizeof(cclc)) { + vec.iov_len = ntohs(cclc.hdr.length); + len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, + ntohs(cclc.hdr.length)); + if (len < ntohs(cclc.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; @@ -479,35 +537,58 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) int rc = 0; int len; - link = &conn->lgr->lnk[SMC_SINGLE_LINK]; memset(&aclc, 0, sizeof(aclc)); - memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); aclc.hdr.type = SMC_CLC_ACCEPT; - aclc.hdr.length = htons(sizeof(aclc)); aclc.hdr.version = SMC_CLC_V1; /* SMC version */ if (srv_first_contact) aclc.hdr.flag = 1; - memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1], - SMC_GID_SIZE); - memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN); - hton24(aclc.qpn, link->roce_qp->qp_num); - aclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); - aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */ - aclc.rmbe_alert_token = htonl(conn->alert_token_local); - aclc.qp_mtu = link->path_mtu; - aclc.rmbe_size = conn->rmbe_size_short, - aclc.rmb_dma_addr = cpu_to_be64( - (u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl)); - hton24(aclc.psn, link->psn_initial); - memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + + if (new_smc->conn.lgr->is_smcd) { + /* SMC-D specific settings */ + aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); + memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER, + sizeof(SMCD_EYECATCHER)); + aclc.hdr.path = SMC_TYPE_D; + aclc.gid = conn->lgr->smcd->local_gid; + aclc.token = conn->rmb_desc->token; + aclc.dmbe_size = conn->rmbe_size_short; + aclc.dmbe_idx = 0; + memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); + memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER, + sizeof(SMCD_EYECATCHER)); + } else { + /* SMC-R specific settings */ + aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + aclc.hdr.path = SMC_TYPE_R; + link = &conn->lgr->lnk[SMC_SINGLE_LINK]; + memcpy(aclc.lcl.id_for_peer, local_systemid, + sizeof(local_systemid)); + memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1], + SMC_GID_SIZE); + memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], + ETH_ALEN); + hton24(aclc.qpn, link->roce_qp->qp_num); + aclc.rmb_rkey = + htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */ + aclc.rmbe_alert_token = htonl(conn->alert_token_local); + aclc.qp_mtu = link->path_mtu; + aclc.rmbe_size = conn->rmbe_size_short, + aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address + (conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl)); + hton24(aclc.psn, link->psn_initial); + memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + } memset(&msg, 0, sizeof(msg)); vec.iov_base = &aclc; - vec.iov_len = sizeof(aclc); - len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, sizeof(aclc)); - if (len < sizeof(aclc)) { + vec.iov_len = ntohs(aclc.hdr.length); + len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, + ntohs(aclc.hdr.length)); + if (len < ntohs(aclc.hdr.length)) { if (len >= 0) new_smc->sk.sk_err = EPROTO; else diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 41ff9ea96139..100e988ad1a8 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -23,6 +23,9 @@ #define SMC_CLC_DECLINE 0x04 #define SMC_CLC_V1 0x1 /* SMC version */ +#define SMC_TYPE_R 0 /* SMC-R only */ +#define SMC_TYPE_D 1 /* SMC-D only */ +#define SMC_TYPE_B 3 /* SMC-R and SMC-D */ #define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */ #define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */ #define SMC_CLC_DECL_TIMEOUT 0x02000000 /* timeout */ @@ -42,9 +45,11 @@ struct smc_clc_msg_hdr { /* header1 of clc messages */ #if defined(__BIG_ENDIAN_BITFIELD) u8 version : 4, flag : 1, - rsvd : 3; + rsvd : 1, + path : 2; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 rsvd : 3, + u8 path : 2, + rsvd : 1, flag : 1, version : 4; #endif @@ -77,6 +82,11 @@ struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/ u8 ipv6_prefixes_cnt; /* number of IPv6 prefixes in prefix array */ } __aligned(4); +struct smc_clc_msg_smcd { /* SMC-D GID information */ + u64 gid; /* ISM GID of requestor */ + u8 res[32]; +}; + struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ struct smc_clc_msg_hdr hdr; struct smc_clc_msg_local lcl; @@ -94,23 +104,45 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_hdr hdr; - struct smc_clc_msg_local lcl; - u8 qpn[3]; /* QP number */ - __be32 rmb_rkey; /* RMB rkey */ - u8 rmbe_idx; /* Index of RMBE in RMB */ - __be32 rmbe_alert_token;/* unique connection id */ + union { + struct { /* SMC-R */ + struct smc_clc_msg_local lcl; + u8 qpn[3]; /* QP number */ + __be32 rmb_rkey; /* RMB rkey */ + u8 rmbe_idx; /* Index of RMBE in RMB */ + __be32 rmbe_alert_token;/* unique connection id */ #if defined(__BIG_ENDIAN_BITFIELD) - u8 rmbe_size : 4, /* RMBE buf size (compressed notation) */ - qp_mtu : 4; /* QP mtu */ + u8 rmbe_size : 4, /* buf size (compressed) */ + qp_mtu : 4; /* QP mtu */ #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 qp_mtu : 4, - rmbe_size : 4; + u8 qp_mtu : 4, + rmbe_size : 4; #endif - u8 reserved; - __be64 rmb_dma_addr; /* RMB virtual address */ - u8 reserved2; - u8 psn[3]; /* initial packet sequence number */ - struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */ + u8 reserved; + __be64 rmb_dma_addr; /* RMB virtual address */ + u8 reserved2; + u8 psn[3]; /* packet sequence number */ + struct smc_clc_msg_trail smcr_trl; + /* eye catcher "SMCR" EBCDIC */ + } __packed; + struct { /* SMC-D */ + u64 gid; /* Sender GID */ + u64 token; /* DMB token */ + u8 dmbe_idx; /* DMBE index */ +#if defined(__BIG_ENDIAN_BITFIELD) + u8 dmbe_size : 4, /* buf size (compressed) */ + reserved3 : 4; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved3 : 4, + dmbe_size : 4; +#endif + u16 reserved4; + u32 linkid; /* Link identifier */ + u32 reserved5[3]; + struct smc_clc_msg_trail smcd_trl; + /* eye catcher "SMCD" EBCDIC */ + } __packed; + }; } __packed; /* format defined in RFC7609 */ struct smc_clc_msg_decline { /* clc decline message */ @@ -129,13 +161,26 @@ smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); } +/* get SMC-D info from proposal message */ +static inline struct smc_clc_msg_smcd * +smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop) +{ + if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd)) + return NULL; + + return (struct smc_clc_msg_smcd *)(prop + 1); +} + +struct smcd_dev; + int smc_clc_prfx_match(struct socket *clcsock, struct smc_clc_msg_proposal_prefix *prop); int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type); int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info); -int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev, - u8 ibport); +int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, + struct smc_ib_device *smcibdev, u8 ibport, + struct smcd_dev *ismdev); int smc_clc_send_confirm(struct smc_sock *smc); int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index add82b0266f3..66741e61a3b0 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -25,6 +25,7 @@ #include "smc_llc.h" #include "smc_cdc.h" #include "smc_close.h" +#include "smc_ism.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) @@ -46,8 +47,8 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) * otherwise there is a risk of out-of-sync link groups. */ mod_delayed_work(system_wq, &lgr->free_work, - lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT : - SMC_LGR_FREE_DELAY_SERV); + (!lgr->is_smcd && lgr->role == SMC_CLNT) ? + SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV); } /* Register connection's alert token in our lookup structure. @@ -153,16 +154,18 @@ static void smc_lgr_free_work(struct work_struct *work) free: spin_unlock_bh(&smc_lgr_list.lock); if (!delayed_work_pending(&lgr->free_work)) { - if (lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE) + if (!lgr->is_smcd && + lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE) smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); smc_lgr_free(lgr); } } /* create a new SMC link group */ -static int smc_lgr_create(struct smc_sock *smc, +static int smc_lgr_create(struct smc_sock *smc, bool is_smcd, struct smc_ib_device *smcibdev, u8 ibport, - char *peer_systemid, unsigned short vlan_id) + char *peer_systemid, unsigned short vlan_id, + struct smcd_dev *smcismdev, u64 peer_gid) { struct smc_link_group *lgr; struct smc_link *lnk; @@ -170,17 +173,23 @@ static int smc_lgr_create(struct smc_sock *smc, int rc = 0; int i; + if (is_smcd && vlan_id) { + rc = smc_ism_get_vlan(smcismdev, vlan_id); + if (rc) + goto out; + } + lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = -ENOMEM; goto out; } - lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; + lgr->is_smcd = is_smcd; lgr->sync_err = 0; - memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN); lgr->vlan_id = vlan_id; rwlock_init(&lgr->sndbufs_lock); rwlock_init(&lgr->rmbs_lock); + rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); INIT_LIST_HEAD(&lgr->rmbs[i]); @@ -189,36 +198,44 @@ static int smc_lgr_create(struct smc_sock *smc, memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE); INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work); lgr->conns_all = RB_ROOT; - - lnk = &lgr->lnk[SMC_SINGLE_LINK]; - /* initialize link */ - lnk->state = SMC_LNK_ACTIVATING; - lnk->link_id = SMC_SINGLE_LINK; - lnk->smcibdev = smcibdev; - lnk->ibport = ibport; - lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; - if (!smcibdev->initialized) - smc_ib_setup_per_ibdev(smcibdev); - get_random_bytes(rndvec, sizeof(rndvec)); - lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); - rc = smc_llc_link_init(lnk); - if (rc) - goto free_lgr; - rc = smc_wr_alloc_link_mem(lnk); - if (rc) - goto clear_llc_lnk; - rc = smc_ib_create_protection_domain(lnk); - if (rc) - goto free_link_mem; - rc = smc_ib_create_queue_pair(lnk); - if (rc) - goto dealloc_pd; - rc = smc_wr_create_link(lnk); - if (rc) - goto destroy_qp; - + if (is_smcd) { + /* SMC-D specific settings */ + lgr->peer_gid = peer_gid; + lgr->smcd = smcismdev; + } else { + /* SMC-R specific settings */ + lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; + memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN); + + lnk = &lgr->lnk[SMC_SINGLE_LINK]; + /* initialize link */ + lnk->state = SMC_LNK_ACTIVATING; + lnk->link_id = SMC_SINGLE_LINK; + lnk->smcibdev = smcibdev; + lnk->ibport = ibport; + lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; + if (!smcibdev->initialized) + smc_ib_setup_per_ibdev(smcibdev); + get_random_bytes(rndvec, sizeof(rndvec)); + lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + + (rndvec[2] << 16); + rc = smc_llc_link_init(lnk); + if (rc) + goto free_lgr; + rc = smc_wr_alloc_link_mem(lnk); + if (rc) + goto clear_llc_lnk; + rc = smc_ib_create_protection_domain(lnk); + if (rc) + goto free_link_mem; + rc = smc_ib_create_queue_pair(lnk); + if (rc) + goto dealloc_pd; + rc = smc_wr_create_link(lnk); + if (rc) + goto destroy_qp; + } smc->conn.lgr = lgr; - rwlock_init(&lgr->conns_lock); spin_lock_bh(&smc_lgr_list.lock); list_add(&lgr->list, &smc_lgr_list.list); spin_unlock_bh(&smc_lgr_list.lock); @@ -264,7 +281,12 @@ void smc_conn_free(struct smc_connection *conn) { if (!conn->lgr) return; - smc_cdc_tx_dismiss_slots(conn); + if (conn->lgr->is_smcd) { + smc_ism_unset_conn(conn); + tasklet_kill(&conn->rx_tsklet); + } else { + smc_cdc_tx_dismiss_slots(conn); + } smc_lgr_unregister_conn(conn); smc_buf_unuse(conn); } @@ -280,8 +302,8 @@ static void smc_link_clear(struct smc_link *lnk) smc_wr_free_link_mem(lnk); } -static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, - struct smc_buf_desc *buf_desc) +static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb, + struct smc_buf_desc *buf_desc) { struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; @@ -301,6 +323,28 @@ static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, kfree(buf_desc); } +static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb, + struct smc_buf_desc *buf_desc) +{ + if (is_dmb) { + /* restore original buf len */ + buf_desc->len += sizeof(struct smcd_cdc_msg); + smc_ism_unregister_dmb(lgr->smcd, buf_desc); + } else { + kfree(buf_desc->cpu_addr); + } + kfree(buf_desc); +} + +static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, + struct smc_buf_desc *buf_desc) +{ + if (lgr->is_smcd) + smcd_buf_free(lgr, is_rmb, buf_desc); + else + smcr_buf_free(lgr, is_rmb, buf_desc); +} + static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf_desc; @@ -332,7 +376,10 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr) void smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); - smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); + if (lgr->is_smcd) + smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); + else + smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); kfree(lgr); } @@ -357,7 +404,8 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr) lgr->terminating = 1; if (!list_empty(&lgr->list)) /* forget lgr */ list_del_init(&lgr->list); - smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + if (!lgr->is_smcd) + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); write_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); @@ -374,7 +422,8 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr) node = rb_first(&lgr->conns_all); } write_unlock_bh(&lgr->conns_lock); - wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait); + if (!lgr->is_smcd) + wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait); smc_lgr_schedule_free_work(lgr); } @@ -392,17 +441,44 @@ void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport) spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { - if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev && + if (!lgr->is_smcd && + lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev && lgr->lnk[SMC_SINGLE_LINK].ibport == ibport) __smc_lgr_terminate(lgr); } spin_unlock_bh(&smc_lgr_list.lock); } +/* Called when SMC-D device is terminated or peer is lost */ +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) +{ + struct smc_link_group *lgr, *l; + LIST_HEAD(lgr_free_list); + + /* run common cleanup function and build free list */ + spin_lock_bh(&smc_lgr_list.lock); + list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { + if (lgr->is_smcd && lgr->smcd == dev && + (!peer_gid || lgr->peer_gid == peer_gid) && + !list_empty(&lgr->list)) { + __smc_lgr_terminate(lgr); + list_move(&lgr->list, &lgr_free_list); + } + } + spin_unlock_bh(&smc_lgr_list.lock); + + /* cancel the regular free workers and actually free lgrs */ + list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { + list_del_init(&lgr->list); + cancel_delayed_work_sync(&lgr->free_work); + smc_lgr_free(lgr); + } +} + /* Determine vlan of internal TCP socket. * @vlan_id: address to store the determined vlan id into */ -static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id) +int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id) { struct dst_entry *dst = sk_dst_get(clcsock->sk); struct net_device *ndev; @@ -477,10 +553,30 @@ static int smc_link_determine_gid(struct smc_link_group *lgr) return -ENODEV; } +static bool smcr_lgr_match(struct smc_link_group *lgr, + struct smc_clc_msg_local *lcl, + enum smc_lgr_role role) +{ + return !memcmp(lgr->peer_systemid, lcl->id_for_peer, + SMC_SYSTEMID_LEN) && + !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid, + SMC_GID_SIZE) && + !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac, + sizeof(lcl->mac)) && + lgr->role == role; +} + +static bool smcd_lgr_match(struct smc_link_group *lgr, + struct smcd_dev *smcismdev, u64 peer_gid) +{ + return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev; +} + /* create a new SMC connection (and a new link group if necessary) */ -int smc_conn_create(struct smc_sock *smc, +int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, struct smc_ib_device *smcibdev, u8 ibport, - struct smc_clc_msg_local *lcl, int srv_first_contact) + struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, + u64 peer_gid) { struct smc_connection *conn = &smc->conn; int local_contact = SMC_FIRST_CONTACT; @@ -502,17 +598,12 @@ int smc_conn_create(struct smc_sock *smc, spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry(lgr, &smc_lgr_list.list, list) { write_lock_bh(&lgr->conns_lock); - if (!memcmp(lgr->peer_systemid, lcl->id_for_peer, - SMC_SYSTEMID_LEN) && - !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid, - SMC_GID_SIZE) && - !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac, - sizeof(lcl->mac)) && + if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) : + smcr_lgr_match(lgr, lcl, role)) && !lgr->sync_err && - (lgr->role == role) && - (lgr->vlan_id == vlan_id) && - ((role == SMC_CLNT) || - (lgr->conns_num < SMC_RMBS_PER_LGR_MAX))) { + lgr->vlan_id == vlan_id && + (role == SMC_CLNT || + lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; @@ -535,16 +626,21 @@ int smc_conn_create(struct smc_sock *smc, create: if (local_contact == SMC_FIRST_CONTACT) { - rc = smc_lgr_create(smc, smcibdev, ibport, - lcl->id_for_peer, vlan_id); + rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport, + lcl->id_for_peer, vlan_id, smcd, peer_gid); if (rc) goto out; smc_lgr_register_conn(conn); /* add smc conn to lgr */ - rc = smc_link_determine_gid(conn->lgr); + if (!is_smcd) + rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; conn->urg_state = SMC_URG_READ; + if (is_smcd) { + conn->rx_off = sizeof(struct smcd_cdc_msg); + smcd_cdc_rx_init(conn); /* init tasklet for this conn */ + } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif @@ -609,8 +705,8 @@ static inline int smc_rmb_wnd_update_limit(int rmbe_size) return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); } -static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, - bool is_rmb, int bufsize) +static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, + bool is_rmb, int bufsize) { struct smc_buf_desc *buf_desc; struct smc_link *lnk; @@ -668,7 +764,44 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, return buf_desc; } -static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) +#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ + +static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, + bool is_dmb, int bufsize) +{ + struct smc_buf_desc *buf_desc; + int rc; + + if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES) + return ERR_PTR(-EAGAIN); + + /* try to alloc a new DMB */ + buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); + if (!buf_desc) + return ERR_PTR(-ENOMEM); + if (is_dmb) { + rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); + if (rc) { + kfree(buf_desc); + return ERR_PTR(-EAGAIN); + } + buf_desc->pages = virt_to_page(buf_desc->cpu_addr); + /* CDC header stored in buf. So, pretend it was smaller */ + buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg); + } else { + buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL | + __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC); + if (!buf_desc->cpu_addr) { + kfree(buf_desc); + return ERR_PTR(-EAGAIN); + } + buf_desc->len = bufsize; + } + return buf_desc; +} + +static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) { struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct smc_connection *conn = &smc->conn; @@ -706,7 +839,11 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) break; /* found reusable slot */ } - buf_desc = smc_new_buf_create(lgr, is_rmb, bufsize); + if (is_smcd) + buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); + else + buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize); + if (PTR_ERR(buf_desc) == -ENOMEM) break; if (IS_ERR(buf_desc)) @@ -727,7 +864,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) conn->rmbe_size_short = bufsize_short; smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); - conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize); + conn->rmbe_update_limit = + smc_rmb_wnd_update_limit(buf_desc->len); + if (is_smcd) + smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; smc->sk.sk_sndbuf = bufsize * 2; @@ -740,6 +880,8 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -748,6 +890,8 @@ void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -756,6 +900,8 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->rmb_desc, DMA_FROM_DEVICE); } @@ -764,6 +910,8 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->rmb_desc, DMA_FROM_DEVICE); } @@ -774,16 +922,16 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) * the Linux implementation uses just one RMB-element per RMB, i.e. uses an * extra RMB for every connection in a link group */ -int smc_buf_create(struct smc_sock *smc) +int smc_buf_create(struct smc_sock *smc, bool is_smcd) { int rc; /* create send buffer */ - rc = __smc_buf_create(smc, false); + rc = __smc_buf_create(smc, is_smcd, false); if (rc) return rc; /* create rmb */ - rc = __smc_buf_create(smc, true); + rc = __smc_buf_create(smc, is_smcd, true); if (rc) smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); return rc; @@ -865,7 +1013,8 @@ void smc_core_exit(void) spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) { list_del_init(&lgr->list); - smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + if (!lgr->is_smcd) + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); cancel_delayed_work_sync(&lgr->free_work); smc_lgr_free(lgr); /* free link group */ } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 93cb3523bf50..8b47e0168fc3 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -124,15 +124,28 @@ struct smc_buf_desc { void *cpu_addr; /* virtual address of buffer */ struct page *pages; int len; /* length of buffer */ - struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */ - struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; - /* for rmb only: memory region - * incl. rkey provided to peer - */ - u32 order; /* allocation order */ u32 used; /* currently used / unused */ u8 reused : 1; /* new created / reused */ u8 regerr : 1; /* err during registration */ + union { + struct { /* SMC-R */ + struct sg_table sgt[SMC_LINKS_PER_LGR_MAX]; + /* virtual buffer */ + struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; + /* for rmb only: memory region + * incl. rkey provided to peer + */ + u32 order; /* allocation order */ + }; + struct { /* SMC-D */ + unsigned short sba_idx; + /* SBA index number */ + u64 token; + /* DMB token number */ + dma_addr_t dma_addr; + /* DMA address */ + }; + }; }; struct smc_rtoken { /* address/key of remote RMB */ @@ -148,12 +161,10 @@ struct smc_rtoken { /* address/key of remote RMB */ * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) */ +struct smcd_dev; + struct smc_link_group { struct list_head list; - enum smc_lgr_role role; /* client or server */ - struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ - char peer_systemid[SMC_SYSTEMID_LEN]; - /* unique system_id of peer */ struct rb_root conns_all; /* connection tree */ rwlock_t conns_lock; /* protects conns_all */ unsigned int conns_num; /* current # of connections */ @@ -163,17 +174,35 @@ struct smc_link_group { rwlock_t sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ rwlock_t rmbs_lock; /* protects rx buffers */ - struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] - [SMC_LINKS_PER_LGR_MAX]; - /* remote addr/key pairs */ - unsigned long rtokens_used_mask[BITS_TO_LONGS( - SMC_RMBS_PER_LGR_MAX)]; - /* used rtoken elements */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ + + bool is_smcd; /* SMC-R or SMC-D */ + union { + struct { /* SMC-R */ + enum smc_lgr_role role; + /* client or server */ + struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; + /* smc link */ + char peer_systemid[SMC_SYSTEMID_LEN]; + /* unique system_id of peer */ + struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] + [SMC_LINKS_PER_LGR_MAX]; + /* remote addr/key pairs */ + unsigned long rtokens_used_mask[BITS_TO_LONGS + (SMC_RMBS_PER_LGR_MAX)]; + /* used rtoken elements */ + }; + struct { /* SMC-D */ + u64 peer_gid; + /* Peer GID (remote) */ + struct smcd_dev *smcd; + /* ISM device for VLAN reg. */ + }; + }; }; /* Find the connection associated with the given alert token in the link group. @@ -217,7 +246,8 @@ void smc_lgr_free(struct smc_link_group *lgr); void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_terminate(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); -int smc_buf_create(struct smc_sock *smc); +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid); +int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_clc_msg_accept_confirm *clc); @@ -227,9 +257,13 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); void smc_rmb_sync_sg_for_device(struct smc_connection *conn); +int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id); + void smc_conn_free(struct smc_connection *conn); -int smc_conn_create(struct smc_sock *smc, +int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, struct smc_ib_device *smcibdev, u8 ibport, - struct smc_clc_msg_local *lcl, int srv_first_contact); + struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, + u64 peer_gid); +void smcd_conn_free(struct smc_connection *conn); void smc_core_exit(void); #endif diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 839354402215..6d83eef1b743 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -136,7 +136,8 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, goto errout; } - if ((req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && smc->conn.lgr && + if (smc->conn.lgr && !smc->conn.lgr->is_smcd && + (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_diag_lgrinfo linfo = { .role = smc->conn.lgr->role, @@ -155,6 +156,21 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0) goto errout; } + if (smc->conn.lgr && smc->conn.lgr->is_smcd && + (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && + !list_empty(&smc->conn.lgr->list)) { + struct smc_connection *conn = &smc->conn; + struct smcd_diag_dmbinfo dinfo = { + .linkid = *((u32 *)conn->lgr->id), + .peer_gid = conn->lgr->peer_gid, + .my_gid = conn->lgr->smcd->local_gid, + .token = conn->rmb_desc->token, + .peer_token = conn->peer_token + }; + + if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0) + goto errout; + } nlmsg_end(skb, nlh); return 0; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 0eed7ab9f28b..36de2fd76170 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -143,6 +143,62 @@ out: return rc; } +static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) +{ + struct ib_gid_attr gattr; + int rc; + + rc = ib_query_gid(smcibdev->ibdev, ibport, 0, + &smcibdev->gid[ibport - 1], &gattr); + if (rc || !gattr.ndev) + return -ENODEV; + + memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); + dev_put(gattr.ndev); + return 0; +} + +/* Create an identifier unique for this instance of SMC-R. + * The MAC-address of the first active registered IB device + * plus a random 2-byte number is used to create this identifier. + * This name is delivered to the peer during connection initialization. + */ +static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev, + u8 ibport) +{ + memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1], + sizeof(smcibdev->mac[ibport - 1])); + get_random_bytes(&local_systemid[0], 2); +} + +bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) +{ + return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; +} + +static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) +{ + int rc; + + memset(&smcibdev->pattr[ibport - 1], 0, + sizeof(smcibdev->pattr[ibport - 1])); + rc = ib_query_port(smcibdev->ibdev, ibport, + &smcibdev->pattr[ibport - 1]); + if (rc) + goto out; + /* the SMC protocol requires specification of the RoCE MAC address */ + rc = smc_ib_fill_gid_and_mac(smcibdev, ibport); + if (rc) + goto out; + if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET, + sizeof(local_systemid)) && + smc_ib_port_active(smcibdev, ibport)) + /* create unique system identifier */ + smc_ib_define_local_systemid(smcibdev, ibport); +out: + return rc; +} + /* process context wrapper for might_sleep smc_ib_remember_port_attr */ static void smc_ib_port_event_work(struct work_struct *work) { @@ -370,62 +426,6 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev, buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0; } -static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) -{ - struct ib_gid_attr gattr; - int rc; - - rc = ib_query_gid(smcibdev->ibdev, ibport, 0, - &smcibdev->gid[ibport - 1], &gattr); - if (rc || !gattr.ndev) - return -ENODEV; - - memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); - dev_put(gattr.ndev); - return 0; -} - -/* Create an identifier unique for this instance of SMC-R. - * The MAC-address of the first active registered IB device - * plus a random 2-byte number is used to create this identifier. - * This name is delivered to the peer during connection initialization. - */ -static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev, - u8 ibport) -{ - memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1], - sizeof(smcibdev->mac[ibport - 1])); - get_random_bytes(&local_systemid[0], 2); -} - -bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) -{ - return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; -} - -int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) -{ - int rc; - - memset(&smcibdev->pattr[ibport - 1], 0, - sizeof(smcibdev->pattr[ibport - 1])); - rc = ib_query_port(smcibdev->ibdev, ibport, - &smcibdev->pattr[ibport - 1]); - if (rc) - goto out; - /* the SMC protocol requires specification of the RoCE MAC address */ - rc = smc_ib_fill_gid_and_mac(smcibdev, ibport); - if (rc) - goto out; - if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET, - sizeof(local_systemid)) && - smc_ib_port_active(smcibdev, ibport)) - /* create unique system identifier */ - smc_ib_define_local_systemid(smcibdev, ibport); -out: - return rc; -} - long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) { struct ib_cq_init_attr cqattr = { @@ -454,9 +454,6 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) smcibdev->roce_cq_recv = NULL; goto err; } - INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev, - smc_ib_global_event_handler); - ib_register_event_handler(&smcibdev->event_handler); smc_wr_add_dev(smcibdev); smcibdev->initialized = 1; return rc; @@ -472,7 +469,6 @@ static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev) return; smcibdev->initialized = 0; smc_wr_remove_dev(smcibdev); - ib_unregister_event_handler(&smcibdev->event_handler); ib_destroy_cq(smcibdev->roce_cq_recv); ib_destroy_cq(smcibdev->roce_cq_send); } @@ -483,6 +479,8 @@ static struct ib_client smc_ib_client; static void smc_ib_add_dev(struct ib_device *ibdev) { struct smc_ib_device *smcibdev; + u8 port_cnt; + int i; if (ibdev->node_type != RDMA_NODE_IB_CA) return; @@ -498,6 +496,21 @@ static void smc_ib_add_dev(struct ib_device *ibdev) list_add_tail(&smcibdev->list, &smc_ib_devices.list); spin_unlock(&smc_ib_devices.lock); ib_set_client_data(ibdev, &smc_ib_client, smcibdev); + INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev, + smc_ib_global_event_handler); + ib_register_event_handler(&smcibdev->event_handler); + + /* trigger reading of the port attributes */ + port_cnt = smcibdev->ibdev->phys_port_cnt; + for (i = 0; + i < min_t(size_t, port_cnt, SMC_MAX_PORTS); + i++) { + set_bit(i, &smcibdev->port_event_mask); + /* determine pnetids of the port */ + smc_pnetid_by_dev_port(ibdev->dev.parent, i, + smcibdev->pnetid[i]); + } + schedule_work(&smcibdev->port_event_work); } /* callback function for ib_register_client() */ @@ -512,6 +525,7 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) spin_unlock(&smc_ib_devices.lock); smc_pnet_remove_by_ibdev(smcibdev); smc_ib_cleanup_per_ibdev(smcibdev); + ib_unregister_event_handler(&smcibdev->event_handler); kfree(smcibdev); } diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index e90630dadf8e..7c1223c91229 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -15,6 +15,7 @@ #include <linux/interrupt.h> #include <linux/if_ether.h> #include <rdma/ib_verbs.h> +#include <net/smc.h> #define SMC_MAX_PORTS 2 /* Max # of ports */ #define SMC_GID_SIZE sizeof(union ib_gid) @@ -40,6 +41,8 @@ struct smc_ib_device { /* ib-device infos for smc */ char mac[SMC_MAX_PORTS][ETH_ALEN]; /* mac address per port*/ union ib_gid gid[SMC_MAX_PORTS]; /* gid per port */ + u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN]; + /* pnetid per port */ u8 initialized : 1; /* ib dev CQ, evthdl done */ struct work_struct port_event_work; unsigned long port_event_mask; @@ -51,7 +54,6 @@ struct smc_link; int smc_ib_register_client(void) __init; void smc_ib_unregister_client(void); bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport); -int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport); int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c new file mode 100644 index 000000000000..cfade7fdcc6d --- /dev/null +++ b/net/smc/smc_ism.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Shared Memory Communications Direct over ISM devices (SMC-D) + * + * Functions for ISM device. + * + * Copyright IBM Corp. 2018 + */ + +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <asm/page.h> + +#include "smc.h" +#include "smc_core.h" +#include "smc_ism.h" +#include "smc_pnet.h" + +struct smcd_dev_list smcd_dev_list = { + .list = LIST_HEAD_INIT(smcd_dev_list.list), + .lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock) +}; + +/* Test if an ISM communication is possible. */ +int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd) +{ + return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0, + vlan_id); +} + +int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos, + void *data, size_t len) +{ + int rc; + + rc = smcd->ops->move_data(smcd, pos->token, pos->index, pos->signal, + pos->offset, data, len); + + return rc < 0 ? rc : 0; +} + +/* Set a connection using this DMBE. */ +void smc_ism_set_conn(struct smc_connection *conn) +{ + unsigned long flags; + + spin_lock_irqsave(&conn->lgr->smcd->lock, flags); + conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = conn; + spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags); +} + +/* Unset a connection using this DMBE. */ +void smc_ism_unset_conn(struct smc_connection *conn) +{ + unsigned long flags; + + if (!conn->rmb_desc) + return; + + spin_lock_irqsave(&conn->lgr->smcd->lock, flags); + conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = NULL; + spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags); +} + +/* Register a VLAN identifier with the ISM device. Use a reference count + * and add a VLAN identifier only when the first DMB using this VLAN is + * registered. + */ +int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid) +{ + struct smc_ism_vlanid *new_vlan, *vlan; + unsigned long flags; + int rc = 0; + + if (!vlanid) /* No valid vlan id */ + return -EINVAL; + + /* create new vlan entry, in case we need it */ + new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL); + if (!new_vlan) + return -ENOMEM; + new_vlan->vlanid = vlanid; + refcount_set(&new_vlan->refcnt, 1); + + /* if there is an existing entry, increase count and return */ + spin_lock_irqsave(&smcd->lock, flags); + list_for_each_entry(vlan, &smcd->vlan, list) { + if (vlan->vlanid == vlanid) { + refcount_inc(&vlan->refcnt); + kfree(new_vlan); + goto out; + } + } + + /* no existing entry found. + * add new entry to device; might fail, e.g., if HW limit reached + */ + if (smcd->ops->add_vlan_id(smcd, vlanid)) { + kfree(new_vlan); + rc = -EIO; + goto out; + } + list_add_tail(&new_vlan->list, &smcd->vlan); +out: + spin_unlock_irqrestore(&smcd->lock, flags); + return rc; +} + +/* Unregister a VLAN identifier with the ISM device. Use a reference count + * and remove a VLAN identifier only when the last DMB using this VLAN is + * unregistered. + */ +int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid) +{ + struct smc_ism_vlanid *vlan; + unsigned long flags; + bool found = false; + int rc = 0; + + if (!vlanid) /* No valid vlan id */ + return -EINVAL; + + spin_lock_irqsave(&smcd->lock, flags); + list_for_each_entry(vlan, &smcd->vlan, list) { + if (vlan->vlanid == vlanid) { + if (!refcount_dec_and_test(&vlan->refcnt)) + goto out; + found = true; + break; + } + } + if (!found) { + rc = -ENOENT; + goto out; /* VLAN id not in table */ + } + + /* Found and the last reference just gone */ + if (smcd->ops->del_vlan_id(smcd, vlanid)) + rc = -EIO; + list_del(&vlan->list); + kfree(vlan); +out: + spin_unlock_irqrestore(&smcd->lock, flags); + return rc; +} + +int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc) +{ + struct smcd_dmb dmb; + + memset(&dmb, 0, sizeof(dmb)); + dmb.dmb_tok = dmb_desc->token; + dmb.sba_idx = dmb_desc->sba_idx; + dmb.cpu_addr = dmb_desc->cpu_addr; + dmb.dma_addr = dmb_desc->dma_addr; + dmb.dmb_len = dmb_desc->len; + return smcd->ops->unregister_dmb(smcd, &dmb); +} + +int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, + struct smc_buf_desc *dmb_desc) +{ + struct smcd_dmb dmb; + int rc; + + memset(&dmb, 0, sizeof(dmb)); + dmb.dmb_len = dmb_len; + dmb.sba_idx = dmb_desc->sba_idx; + dmb.vlan_id = lgr->vlan_id; + dmb.rgid = lgr->peer_gid; + rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb); + if (!rc) { + dmb_desc->sba_idx = dmb.sba_idx; + dmb_desc->token = dmb.dmb_tok; + dmb_desc->cpu_addr = dmb.cpu_addr; + dmb_desc->dma_addr = dmb.dma_addr; + dmb_desc->len = dmb.dmb_len; + } + return rc; +} + +struct smc_ism_event_work { + struct work_struct work; + struct smcd_dev *smcd; + struct smcd_event event; +}; + +/* worker for SMC-D events */ +static void smc_ism_event_work(struct work_struct *work) +{ + struct smc_ism_event_work *wrk = + container_of(work, struct smc_ism_event_work, work); + + switch (wrk->event.type) { + case ISM_EVENT_GID: /* GID event, token is peer GID */ + smc_smcd_terminate(wrk->smcd, wrk->event.tok); + break; + case ISM_EVENT_DMB: + break; + } + kfree(wrk); +} + +static void smcd_release(struct device *dev) +{ + struct smcd_dev *smcd = container_of(dev, struct smcd_dev, dev); + + kfree(smcd->conn); + kfree(smcd); +} + +struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, + const struct smcd_ops *ops, int max_dmbs) +{ + struct smcd_dev *smcd; + + smcd = kzalloc(sizeof(*smcd), GFP_KERNEL); + if (!smcd) + return NULL; + smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *), + GFP_KERNEL); + if (!smcd->conn) { + kfree(smcd); + return NULL; + } + + smcd->dev.parent = parent; + smcd->dev.release = smcd_release; + device_initialize(&smcd->dev); + dev_set_name(&smcd->dev, name); + smcd->ops = ops; + smc_pnetid_by_dev_port(parent, 0, smcd->pnetid); + + spin_lock_init(&smcd->lock); + INIT_LIST_HEAD(&smcd->vlan); + smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)", + WQ_MEM_RECLAIM, name); + return smcd; +} +EXPORT_SYMBOL_GPL(smcd_alloc_dev); + +int smcd_register_dev(struct smcd_dev *smcd) +{ + spin_lock(&smcd_dev_list.lock); + list_add_tail(&smcd->list, &smcd_dev_list.list); + spin_unlock(&smcd_dev_list.lock); + + return device_add(&smcd->dev); +} +EXPORT_SYMBOL_GPL(smcd_register_dev); + +void smcd_unregister_dev(struct smcd_dev *smcd) +{ + spin_lock(&smcd_dev_list.lock); + list_del(&smcd->list); + spin_unlock(&smcd_dev_list.lock); + flush_workqueue(smcd->event_wq); + destroy_workqueue(smcd->event_wq); + smc_smcd_terminate(smcd, 0); + + device_del(&smcd->dev); +} +EXPORT_SYMBOL_GPL(smcd_unregister_dev); + +void smcd_free_dev(struct smcd_dev *smcd) +{ + put_device(&smcd->dev); +} +EXPORT_SYMBOL_GPL(smcd_free_dev); + +/* SMCD Device event handler. Called from ISM device interrupt handler. + * Parameters are smcd device pointer, + * - event->type (0 --> DMB, 1 --> GID), + * - event->code (event code), + * - event->tok (either DMB token when event type 0, or GID when event type 1) + * - event->time (time of day) + * - event->info (debug info). + * + * Context: + * - Function called in IRQ context from ISM device driver event handler. + */ +void smcd_handle_event(struct smcd_dev *smcd, struct smcd_event *event) +{ + struct smc_ism_event_work *wrk; + + /* copy event to event work queue, and let it be handled there */ + wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC); + if (!wrk) + return; + INIT_WORK(&wrk->work, smc_ism_event_work); + wrk->smcd = smcd; + wrk->event = *event; + queue_work(smcd->event_wq, &wrk->work); +} +EXPORT_SYMBOL_GPL(smcd_handle_event); + +/* SMCD Device interrupt handler. Called from ISM device interrupt handler. + * Parameters are smcd device pointer and DMB number. Find the connection and + * schedule the tasklet for this connection. + * + * Context: + * - Function called in IRQ context from ISM device driver IRQ handler. + */ +void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno) +{ + struct smc_connection *conn = NULL; + unsigned long flags; + + spin_lock_irqsave(&smcd->lock, flags); + conn = smcd->conn[dmbno]; + if (conn) + tasklet_schedule(&conn->rx_tsklet); + spin_unlock_irqrestore(&smcd->lock, flags); +} +EXPORT_SYMBOL_GPL(smcd_handle_irq); diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h new file mode 100644 index 000000000000..aee45b860b79 --- /dev/null +++ b/net/smc/smc_ism.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Shared Memory Communications Direct over ISM devices (SMC-D) + * + * SMC-D ISM device structure definitions. + * + * Copyright IBM Corp. 2018 + */ + +#ifndef SMCD_ISM_H +#define SMCD_ISM_H + +#include <linux/uio.h> + +#include "smc.h" + +struct smcd_dev_list { /* List of SMCD devices */ + struct list_head list; + spinlock_t lock; /* Protects list of devices */ +}; + +extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */ + +struct smc_ism_vlanid { /* VLAN id set on ISM device */ + struct list_head list; + unsigned short vlanid; /* Vlan id */ + refcount_t refcnt; /* Reference count */ +}; + +struct smc_ism_position { /* ISM device position to write to */ + u64 token; /* Token of DMB */ + u32 offset; /* Offset into DMBE */ + u8 index; /* Index of DMBE */ + u8 signal; /* Generate interrupt on owner side */ +}; + +struct smcd_dev; + +int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev); +void smc_ism_set_conn(struct smc_connection *conn); +void smc_ism_unset_conn(struct smc_connection *conn); +int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id); +int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id); +int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size, + struct smc_buf_desc *dmb_desc); +int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); +int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos, + void *data, size_t len); +#endif diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index d7b88b2d1b22..1b6c066d3495 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -22,13 +22,12 @@ #include "smc_pnet.h" #include "smc_ib.h" - -#define SMC_MAX_PNET_ID_LEN 16 /* Max. length of PNET id */ +#include "smc_ism.h" static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNET_ID_LEN - 1 + .len = SMC_MAX_PNETID_LEN - 1 }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, @@ -65,7 +64,7 @@ static struct smc_pnettable { */ struct smc_pnetentry { struct list_head list; - char pnet_name[SMC_MAX_PNET_ID_LEN + 1]; + char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct net_device *ndev; struct smc_ib_device *smcibdev; u8 ib_port; @@ -209,7 +208,7 @@ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) return false; while (--end >= bf && isspace(*end)) ; - if (end - bf >= SMC_MAX_PNET_ID_LEN) + if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) @@ -358,9 +357,6 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) kfree(pnetelem); return rc; } - rc = smc_ib_remember_port_attr(pnetelem->smcibdev, pnetelem->ib_port); - if (rc) - smc_pnet_remove_by_pnetid(pnetelem->pnet_name); return rc; } @@ -485,10 +481,10 @@ static int smc_pnet_netdev_event(struct notifier_block *this, case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); + return NOTIFY_OK; default: - break; + return NOTIFY_DONE; } - return NOTIFY_DONE; } static struct notifier_block smc_netdev_notifier = { @@ -515,26 +511,91 @@ void smc_pnet_exit(void) genl_unregister_family(&smc_pnet_nl_family); } -/* PNET table analysis for a given sock: - * determine ib_device and port belonging to used internal TCP socket - * ethernet interface. +/* Determine one base device for stacked net devices. + * If the lower device level contains more than one devices + * (for instance with bonding slaves), just the first device + * is used to reach a base device. */ -void smc_pnet_find_roce_resource(struct sock *sk, - struct smc_ib_device **smcibdev, u8 *ibport) +static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { - struct dst_entry *dst = sk_dst_get(sk); - struct smc_pnetentry *pnetelem; + int i, nest_lvl; - *smcibdev = NULL; - *ibport = 0; + rtnl_lock(); + nest_lvl = dev_get_nest_level(ndev); + for (i = 0; i < nest_lvl; i++) { + struct list_head *lower = &ndev->adj_list.lower; + + if (list_empty(lower)) + break; + lower = lower->next; + ndev = netdev_lower_get_next(ndev, &lower); + } + rtnl_unlock(); + return ndev; +} + +/* Determine the corresponding IB device port based on the hardware PNETID. + * Searching stops at the first matching active IB device port. + */ +static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, + struct smc_ib_device **smcibdev, + u8 *ibport) +{ + u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct smc_ib_device *ibdev; + int i; + + ndev = pnet_find_base_ndev(ndev); + if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + ndev_pnetid)) + return; /* pnetid could not be determined */ + + spin_lock(&smc_ib_devices.lock); + list_for_each_entry(ibdev, &smc_ib_devices.list, list) { + for (i = 1; i <= SMC_MAX_PORTS; i++) { + if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid, + SMC_MAX_PNETID_LEN) && + smc_ib_port_active(ibdev, i)) { + *smcibdev = ibdev; + *ibport = i; + break; + } + } + } + spin_unlock(&smc_ib_devices.lock); +} + +static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, + struct smcd_dev **smcismdev) +{ + u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct smcd_dev *ismdev; + + ndev = pnet_find_base_ndev(ndev); + if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + ndev_pnetid)) + return; /* pnetid could not be determined */ + + spin_lock(&smcd_dev_list.lock); + list_for_each_entry(ismdev, &smcd_dev_list.list, list) { + if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) { + *smcismdev = ismdev; + break; + } + } + spin_unlock(&smcd_dev_list.lock); +} + +/* Lookup of coupled ib_device via SMC pnet table */ +static void smc_pnet_find_roce_by_table(struct net_device *netdev, + struct smc_ib_device **smcibdev, + u8 *ibport) +{ + struct smc_pnetentry *pnetelem; - if (!dst) - return; - if (!dst->dev) - goto out_rel; read_lock(&smc_pnettable.lock); list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { - if (dst->dev == pnetelem->ndev) { + if (netdev == pnetelem->ndev) { if (smc_ib_port_active(pnetelem->smcibdev, pnetelem->ib_port)) { *smcibdev = pnetelem->smcibdev; @@ -544,6 +605,54 @@ void smc_pnet_find_roce_resource(struct sock *sk, } } read_unlock(&smc_pnettable.lock); +} + +/* PNET table analysis for a given sock: + * determine ib_device and port belonging to used internal TCP socket + * ethernet interface. + */ +void smc_pnet_find_roce_resource(struct sock *sk, + struct smc_ib_device **smcibdev, u8 *ibport) +{ + struct dst_entry *dst = sk_dst_get(sk); + + *smcibdev = NULL; + *ibport = 0; + + if (!dst) + goto out; + if (!dst->dev) + goto out_rel; + + /* if possible, lookup via hardware-defined pnetid */ + smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport); + if (*smcibdev) + goto out_rel; + + /* lookup via SMC PNET table */ + smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport); + +out_rel: + dst_release(dst); +out: + return; +} + +void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev) +{ + struct dst_entry *dst = sk_dst_get(sk); + + *smcismdev = NULL; + if (!dst) + goto out; + if (!dst->dev) + goto out_rel; + + /* if possible, lookup via hardware-defined pnetid */ + smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev); + out_rel: dst_release(dst); +out: + return; } diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h index 5a29519db976..1e94fd4df7bc 100644 --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -12,12 +12,28 @@ #ifndef _SMC_PNET_H #define _SMC_PNET_H +#if IS_ENABLED(CONFIG_HAVE_PNETID) +#include <asm/pnet.h> +#endif + struct smc_ib_device; +struct smcd_dev; + +static inline int smc_pnetid_by_dev_port(struct device *dev, + unsigned short port, u8 *pnetid) +{ +#if IS_ENABLED(CONFIG_HAVE_PNETID) + return pnet_id_by_dev_port(dev, port, pnetid); +#else + return -ENOENT; +#endif +} int smc_pnet_init(void) __init; void smc_pnet_exit(void); int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev); void smc_pnet_find_roce_resource(struct sock *sk, struct smc_ib_device **smcibdev, u8 *ibport); +void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev); #endif diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 3d77b383cccd..b329803c8339 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -305,7 +305,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); /* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */ - rcvbuf_base = conn->rmb_desc->cpu_addr; + rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr; do { /* while (read_remaining) */ if (read_done >= target || (pipe && read_done)) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index cee666400752..142bcb134dd6 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -24,6 +24,7 @@ #include "smc.h" #include "smc_wr.h" #include "smc_cdc.h" +#include "smc_ism.h" #include "smc_tx.h" #define SMC_TX_WORK_DELAY HZ @@ -250,6 +251,24 @@ out_err: /***************************** sndbuf consumer *******************************/ +/* sndbuf consumer: actual data transfer of one target chunk with ISM write */ +int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, + u32 offset, int signal) +{ + struct smc_ism_position pos; + int rc; + + memset(&pos, 0, sizeof(pos)); + pos.token = conn->peer_token; + pos.index = conn->peer_rmbe_idx; + pos.offset = conn->tx_off + offset; + pos.signal = signal; + rc = smc_ism_write(conn->lgr->smcd, &pos, data, len); + if (rc) + conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; + return rc; +} + /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, int num_sges, struct ib_sge sges[]) @@ -297,21 +316,104 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, smc_curs_add(conn->sndbuf_desc->len, sent, len); } +/* SMC-R helper for smc_tx_rdma_writes() */ +static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, + size_t src_off, size_t src_len, + size_t dst_off, size_t dst_len) +{ + dma_addr_t dma_addr = + sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); + struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; + int src_len_sum = src_len, dst_len_sum = dst_len; + struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; + int sent_count = src_off; + int srcchunk, dstchunk; + int num_sges; + int rc; + + for (dstchunk = 0; dstchunk < 2; dstchunk++) { + num_sges = 0; + for (srcchunk = 0; srcchunk < 2; srcchunk++) { + sges[srcchunk].addr = dma_addr + src_off; + sges[srcchunk].length = src_len; + sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; + num_sges++; + + src_off += src_len; + if (src_off >= conn->sndbuf_desc->len) + src_off -= conn->sndbuf_desc->len; + /* modulo in send ring */ + if (src_len_sum == dst_len) + break; /* either on 1st or 2nd iteration */ + /* prepare next (== 2nd) iteration */ + src_len = dst_len - src_len; /* remainder */ + src_len_sum += src_len; + } + rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); + if (rc) + return rc; + if (dst_len_sum == len) + break; /* either on 1st or 2nd iteration */ + /* prepare next (== 2nd) iteration */ + dst_off = 0; /* modulo offset in RMBE ring buffer */ + dst_len = len - dst_len; /* remainder */ + dst_len_sum += dst_len; + src_len = min_t(int, dst_len, conn->sndbuf_desc->len - + sent_count); + src_len_sum = src_len; + } + return 0; +} + +/* SMC-D helper for smc_tx_rdma_writes() */ +static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, + size_t src_off, size_t src_len, + size_t dst_off, size_t dst_len) +{ + int src_len_sum = src_len, dst_len_sum = dst_len; + int srcchunk, dstchunk; + int rc; + + for (dstchunk = 0; dstchunk < 2; dstchunk++) { + for (srcchunk = 0; srcchunk < 2; srcchunk++) { + void *data = conn->sndbuf_desc->cpu_addr + src_off; + + rc = smcd_tx_ism_write(conn, data, src_len, dst_off + + sizeof(struct smcd_cdc_msg), 0); + if (rc) + return rc; + dst_off += src_len; + src_off += src_len; + if (src_off >= conn->sndbuf_desc->len) + src_off -= conn->sndbuf_desc->len; + /* modulo in send ring */ + if (src_len_sum == dst_len) + break; /* either on 1st or 2nd iteration */ + /* prepare next (== 2nd) iteration */ + src_len = dst_len - src_len; /* remainder */ + src_len_sum += src_len; + } + if (dst_len_sum == len) + break; /* either on 1st or 2nd iteration */ + /* prepare next (== 2nd) iteration */ + dst_off = 0; /* modulo offset in RMBE ring buffer */ + dst_len = len - dst_len; /* remainder */ + dst_len_sum += dst_len; + src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off); + src_len_sum = src_len; + } + return 0; +} + /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ static int smc_tx_rdma_writes(struct smc_connection *conn) { - size_t src_off, src_len, dst_off, dst_len; /* current chunk values */ - size_t len, dst_len_sum, src_len_sum, dstchunk, srcchunk; + size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; - struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; - struct smc_link_group *lgr = conn->lgr; struct smc_cdc_producer_flags *pflags; int to_send, rmbespace; - struct smc_link *link; - dma_addr_t dma_addr; - int num_sges; int rc; /* source: sndbuf */ @@ -341,7 +443,6 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) len = min(to_send, rmbespace); /* initialize variables for first iteration of subsequent nested loop */ - link = &lgr->lnk[SMC_SINGLE_LINK]; dst_off = prod.count; if (prod.wrap == cons.wrap) { /* the filled destination area is unwrapped, @@ -358,8 +459,6 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) */ dst_len = len; } - dst_len_sum = dst_len; - src_off = sent.count; /* dst_len determines the maximum src_len */ if (sent.count + dst_len <= conn->sndbuf_desc->len) { /* unwrapped src case: single chunk of entire dst_len */ @@ -368,38 +467,15 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) /* wrapped src case: 2 chunks of sum dst_len; start with 1st: */ src_len = conn->sndbuf_desc->len - sent.count; } - src_len_sum = src_len; - dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); - for (dstchunk = 0; dstchunk < 2; dstchunk++) { - num_sges = 0; - for (srcchunk = 0; srcchunk < 2; srcchunk++) { - sges[srcchunk].addr = dma_addr + src_off; - sges[srcchunk].length = src_len; - sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; - num_sges++; - src_off += src_len; - if (src_off >= conn->sndbuf_desc->len) - src_off -= conn->sndbuf_desc->len; - /* modulo in send ring */ - if (src_len_sum == dst_len) - break; /* either on 1st or 2nd iteration */ - /* prepare next (== 2nd) iteration */ - src_len = dst_len - src_len; /* remainder */ - src_len_sum += src_len; - } - rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); - if (rc) - return rc; - if (dst_len_sum == len) - break; /* either on 1st or 2nd iteration */ - /* prepare next (== 2nd) iteration */ - dst_off = 0; /* modulo offset in RMBE ring buffer */ - dst_len = len - dst_len; /* remainder */ - dst_len_sum += dst_len; - src_len = min_t(int, - dst_len, conn->sndbuf_desc->len - sent.count); - src_len_sum = src_len; - } + + if (conn->lgr->is_smcd) + rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len, + dst_off, dst_len); + else + rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, + dst_off, dst_len); + if (rc) + return rc; if (conn->urg_tx_pend && len == to_send) pflags->urg_data_present = 1; @@ -420,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ -int smc_tx_sndbuf_nonempty(struct smc_connection *conn) +static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags; struct smc_cdc_tx_pend *pend; @@ -467,6 +543,37 @@ out_unlock: return rc; } +static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) +{ + struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; + int rc = 0; + + spin_lock_bh(&conn->send_lock); + if (!pflags->urg_data_present) + rc = smc_tx_rdma_writes(conn); + if (!rc) + rc = smcd_cdc_msg_send(conn); + + if (!rc && pflags->urg_data_present) { + pflags->urg_data_pending = 0; + pflags->urg_data_present = 0; + } + spin_unlock_bh(&conn->send_lock); + return rc; +} + +int smc_tx_sndbuf_nonempty(struct smc_connection *conn) +{ + int rc; + + if (conn->lgr->is_smcd) + rc = smcd_tx_sndbuf_nonempty(conn); + else + rc = smcr_tx_sndbuf_nonempty(conn); + + return rc; +} + /* Wakeup sndbuf consumers from process context * since there is more data to transmit */ @@ -495,7 +602,8 @@ out: void smc_tx_consumer_update(struct smc_connection *conn, bool force) { - union smc_host_cursor cfed, cons; + union smc_host_cursor cfed, cons, prod; + int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_write(&cons, @@ -505,11 +613,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) smc_curs_read(&conn->rx_curs_confirmed, conn), conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); + if (to_confirm > conn->rmbe_update_limit) { + smc_curs_write(&prod, + smc_curs_read(&conn->local_rx_ctrl.prod, conn), + conn); + sender_free = conn->rmb_desc->len - + smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && - ((to_confirm > (conn->rmb_desc->len / 2)) || + ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && conn->alert_token_local) { /* connection healthy */ diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h index 9d2238909fa0..b22bdc5694c4 100644 --- a/net/smc/smc_tx.h +++ b/net/smc/smc_tx.h @@ -33,5 +33,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len); int smc_tx_sndbuf_nonempty(struct smc_connection *conn); void smc_tx_sndbuf_nonfull(struct smc_sock *smc); void smc_tx_consumer_update(struct smc_connection *conn, bool force); +int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, + u32 offset, int signal); #endif /* SMC_TX_H */ diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 625acb27efcc..3a512936eea9 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -140,11 +140,13 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* We are going to append to the frags_list of head. * Need to unshare the frag_list. */ - err = skb_unclone(head, GFP_ATOMIC); - if (err) { - STRP_STATS_INCR(strp->stats.mem_fail); - desc->error = err; - return 0; + if (skb_has_frag_list(head)) { + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.mem_fail); + desc->error = err; + return 0; + } } if (unlikely(skb_shinfo(head)->frag_list)) { @@ -201,14 +203,16 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, memset(stm, 0, sizeof(*stm)); stm->strp.offset = orig_offset + eaten; } else { - /* Unclone since we may be appending to an skb that we + /* Unclone if we are appending to an skb that we * already share a frag_list with. */ - err = skb_unclone(skb, GFP_ATOMIC); - if (err) { - STRP_STATS_INCR(strp->stats.mem_fail); - desc->error = err; - break; + if (skb_has_frag_list(skb)) { + err = skb_unclone(skb, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.mem_fail); + desc->error = err; + break; + } } stm = _strp_msg(head); diff --git a/net/tipc/group.c b/net/tipc/group.c index d7a7befeddd4..cbe39e8db39c 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -918,3 +918,35 @@ void tipc_group_member_evt(struct tipc_group *grp, } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } + +int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) +{ + struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP); + + if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID, + grp->type) || + nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE, + grp->instance) || + nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, + grp->bc_snd_nxt)) + goto group_msg_cancel; + + if (grp->scope == TIPC_NODE_SCOPE) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE)) + goto group_msg_cancel; + + if (grp->scope == TIPC_CLUSTER_SCOPE) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE)) + goto group_msg_cancel; + + if (*grp->open) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN)) + goto group_msg_cancel; + + nla_nest_end(skb, group); + return 0; + +group_msg_cancel: + nla_nest_cancel(skb, group); + return -1; +} diff --git a/net/tipc/group.h b/net/tipc/group.h index 5996af6e9f1d..76b4e5a7b39d 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -72,4 +72,5 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); void tipc_group_update_member(struct tipc_member *m, int len); +int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb); #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index b6c45dccba3d..b61891054709 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -416,26 +416,31 @@ bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu) */ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) { - struct tipc_msg *msg; - int imsz, offset; + struct tipc_msg *hdr, *ihdr; + int imsz; *iskb = NULL; if (unlikely(skb_linearize(skb))) goto none; - msg = buf_msg(skb); - offset = msg_hdr_sz(msg) + *pos; - if (unlikely(offset > (msg_size(msg) - MIN_H_SIZE))) + hdr = buf_msg(skb); + if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE))) goto none; - *iskb = skb_clone(skb, GFP_ATOMIC); - if (unlikely(!*iskb)) + ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos); + imsz = msg_size(ihdr); + + if ((*pos + imsz) > msg_data_sz(hdr)) goto none; - skb_pull(*iskb, offset); - imsz = msg_size(buf_msg(*iskb)); - skb_trim(*iskb, imsz); + + *iskb = tipc_buf_acquire(imsz, GFP_ATOMIC); + if (!*iskb) + goto none; + + skb_copy_to_linear_data(*iskb, ihdr, imsz); if (unlikely(!tipc_msg_validate(iskb))) goto none; + *pos += align(imsz); return true; none: @@ -531,12 +536,6 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) msg_set_hdr_sz(hdr, BASIC_H_SIZE); } - if (skb_cloned(_skb) && - pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) - goto exit; - - /* reassign after skb header modifications */ - hdr = buf_msg(_skb); /* Now reverse the concerned fields */ msg_set_errcode(hdr, err); msg_set_non_seq(hdr, 0); @@ -595,10 +594,6 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) if (!skb_cloned(skb)) return true; - /* Unclone buffer in case it was bundled */ - if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) - return false; - return true; } diff --git a/net/tipc/node.c b/net/tipc/node.c index 6a44eb812baf..cfdbaf479fd1 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -45,6 +45,7 @@ #include "netlink.h" #define INVALID_NODE_SIG 0x10000 +#define NODE_CLEANUP_AFTER 300000 /* Flags used to take different actions according to flag type * TIPC_NOTIFY_NODE_DOWN: notify node is down @@ -96,6 +97,7 @@ struct tipc_bclink_entry { * @link_id: local and remote bearer ids of changing link, if any * @publ_list: list of publications * @rcu: rcu struct for tipc_node + * @delete_at: indicates the time for deleting a down node */ struct tipc_node { u32 addr; @@ -121,6 +123,7 @@ struct tipc_node { unsigned long keepalive_intv; struct timer_list timer; struct rcu_head rcu; + unsigned long delete_at; }; /* Node FSM states and events: @@ -160,6 +163,7 @@ static struct tipc_node *tipc_node_find(struct net *net, u32 addr); static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id); static void tipc_node_put(struct tipc_node *node); static bool node_is_up(struct tipc_node *n); +static void tipc_node_delete_from_list(struct tipc_node *node); struct tipc_sock_conn { u32 port; @@ -390,6 +394,7 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, for (i = 0; i < MAX_BEARERS; i++) spin_lock_init(&n->links[i].lock); n->state = SELF_DOWN_PEER_LEAVING; + n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER); n->signature = INVALID_NODE_SIG; n->active_links[0] = INVALID_BEARER_ID; n->active_links[1] = INVALID_BEARER_ID; @@ -433,11 +438,16 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) tipc_link_set_abort_limit(l, tol / n->keepalive_intv); } -static void tipc_node_delete(struct tipc_node *node) +static void tipc_node_delete_from_list(struct tipc_node *node) { list_del_rcu(&node->list); hlist_del_rcu(&node->hash); tipc_node_put(node); +} + +static void tipc_node_delete(struct tipc_node *node) +{ + tipc_node_delete_from_list(node); del_timer_sync(&node->timer); tipc_node_put(node); @@ -544,6 +554,42 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) tipc_node_put(node); } +static void tipc_node_clear_links(struct tipc_node *node) +{ + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + struct tipc_link_entry *le = &node->links[i]; + + if (le->link) { + kfree(le->link); + le->link = NULL; + node->link_cnt--; + } + } +} + +/* tipc_node_cleanup - delete nodes that does not + * have active links for NODE_CLEANUP_AFTER time + */ +static int tipc_node_cleanup(struct tipc_node *peer) +{ + struct tipc_net *tn = tipc_net(peer->net); + bool deleted = false; + + spin_lock_bh(&tn->node_list_lock); + tipc_node_write_lock(peer); + + if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) { + tipc_node_clear_links(peer); + tipc_node_delete_from_list(peer); + deleted = true; + } + tipc_node_write_unlock(peer); + spin_unlock_bh(&tn->node_list_lock); + return deleted; +} + /* tipc_node_timeout - handle expiration of node timer */ static void tipc_node_timeout(struct timer_list *t) @@ -551,21 +597,29 @@ static void tipc_node_timeout(struct timer_list *t) struct tipc_node *n = from_timer(n, t, timer); struct tipc_link_entry *le; struct sk_buff_head xmitq; + int remains = n->link_cnt; int bearer_id; int rc = 0; + if (!node_is_up(n) && tipc_node_cleanup(n)) { + /*Removing the reference of Timer*/ + tipc_node_put(n); + return; + } + __skb_queue_head_init(&xmitq); - for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) { tipc_node_read_lock(n); le = &n->links[bearer_id]; - spin_lock_bh(&le->lock); if (le->link) { + spin_lock_bh(&le->lock); /* Link tolerance may change asynchronously: */ tipc_node_calculate_timer(n, le->link); rc = tipc_link_timeout(le->link, &xmitq); + spin_unlock_bh(&le->lock); + remains--; } - spin_unlock_bh(&le->lock); tipc_node_read_unlock(n); tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr); if (rc & TIPC_LINK_DOWN_EVT) @@ -1171,6 +1225,7 @@ static void node_lost_contact(struct tipc_node *n, uint i; pr_debug("Lost contact with %x\n", n->addr); + n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER); /* Clean up broadcast state */ tipc_bcast_remove_peer(n->net, n->bc_entry.link); @@ -1740,7 +1795,6 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) struct tipc_node *peer; u32 addr; int err; - int i; /* We identify the peer by its net */ if (!info->attrs[TIPC_NLA_NET]) @@ -1775,15 +1829,7 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) goto err_out; } - for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link_entry *le = &peer->links[i]; - - if (le->link) { - kfree(le->link); - le->link = NULL; - peer->link_cnt--; - } - } + tipc_node_clear_links(peer); tipc_node_write_unlock(peer); tipc_node_delete(peer); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 930852c54d7a..3d21414ba357 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3320,6 +3320,11 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, goto stat_msg_cancel; nla_nest_end(skb, stat); + + if (tsk->group) + if (tipc_group_fill_sock_diag(tsk->group, skb)) + goto stat_msg_cancel; + nla_nest_end(skb, attrs); return 0; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d2380548f8f6..0d670c8adf18 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -942,7 +942,7 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) { struct tls_context *tls_ctx = tls_get_ctx(strp->sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - char header[tls_ctx->rx.prepend_size]; + char header[TLS_HEADER_SIZE + MAX_IV_SIZE]; struct strp_msg *rxm = strp_msg(skb); size_t cipher_overhead; size_t data_len = 0; @@ -952,6 +952,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) if (rxm->offset + tls_ctx->rx.prepend_size > skb->len) return 0; + /* Sanity-check size of on-stack buffer. */ + if (WARN_ON(tls_ctx->rx.prepend_size > sizeof(header))) { + ret = -EINVAL; + goto read_failure; + } + /* Linearize header to local buffer */ ret = skb_copy_bits(skb, rxm->offset, header, tls_ctx->rx.prepend_size); @@ -991,9 +997,6 @@ static void tls_queue(struct strparser *strp, struct sk_buff *skb) { struct tls_context *tls_ctx = tls_get_ctx(strp->sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - struct strp_msg *rxm; - - rxm = strp_msg(skb); ctx->decrypted = false; @@ -1112,7 +1115,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } /* Sanity-check the IV size for stack allocations. */ - if (iv_size > MAX_IV_SIZE) { + if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE) { rc = -EINVAL; goto free_priv; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 48e8097339ab..a88551f3bc43 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -3,7 +3,7 @@ * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015-2017 Intel Deutschland GmbH */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -744,6 +744,8 @@ int wiphy_register(struct wiphy *wiphy) /* sanity check supported bands/channels */ for (band = 0; band < NUM_NL80211_BANDS; band++) { + u16 types = 0; + sband = wiphy->bands[band]; if (!sband) continue; @@ -788,6 +790,23 @@ int wiphy_register(struct wiphy *wiphy) sband->channels[i].band = band; } + for (i = 0; i < sband->n_iftype_data; i++) { + const struct ieee80211_sband_iftype_data *iftd; + + iftd = &sband->iftype_data[i]; + + if (WARN_ON(!iftd->types_mask)) + return -EINVAL; + if (WARN_ON(types & iftd->types_mask)) + return -EINVAL; + + /* at least one piece of information must be present */ + if (WARN_ON(!iftd->he_cap.has_he)) + return -EINVAL; + + types |= iftd->types_mask; + } + have_band = true; } diff --git a/net/wireless/core.h b/net/wireless/core.h index 63eb1b5fdd04..7f52ef569320 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -76,7 +76,7 @@ struct cfg80211_registered_device { struct cfg80211_scan_request *scan_req; /* protected by RTNL */ struct sk_buff *scan_msg; struct list_head sched_scan_req_list; - unsigned long suspend_at; + time64_t suspend_at; struct work_struct scan_done_wk; struct genl_info *cur_cmd_info; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4eece06be1e7..e4e5f025d16b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -428,6 +428,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, + [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, + .len = NL80211_HE_MAX_CAPABILITY_LEN }, }; /* policy for the key attributes */ @@ -1324,6 +1326,34 @@ static int nl80211_send_coalesce(struct sk_buff *msg, return 0; } +static int +nl80211_send_iftype_data(struct sk_buff *msg, + const struct ieee80211_sband_iftype_data *iftdata) +{ + const struct ieee80211_sta_he_cap *he_cap = &iftdata->he_cap; + + if (nl80211_put_iftypes(msg, NL80211_BAND_IFTYPE_ATTR_IFTYPES, + iftdata->types_mask)) + return -ENOBUFS; + + if (he_cap->has_he) { + if (nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC, + sizeof(he_cap->he_cap_elem.mac_cap_info), + he_cap->he_cap_elem.mac_cap_info) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY, + sizeof(he_cap->he_cap_elem.phy_cap_info), + he_cap->he_cap_elem.phy_cap_info) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET, + sizeof(he_cap->he_mcs_nss_supp), + &he_cap->he_mcs_nss_supp) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, + sizeof(he_cap->ppe_thres), he_cap->ppe_thres)) + return -ENOBUFS; + } + + return 0; +} + static int nl80211_send_band_rateinfo(struct sk_buff *msg, struct ieee80211_supported_band *sband) { @@ -1353,6 +1383,32 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, sband->vht_cap.cap))) return -ENOBUFS; + if (sband->n_iftype_data) { + struct nlattr *nl_iftype_data = + nla_nest_start(msg, NL80211_BAND_ATTR_IFTYPE_DATA); + int err; + + if (!nl_iftype_data) + return -ENOBUFS; + + for (i = 0; i < sband->n_iftype_data; i++) { + struct nlattr *iftdata; + + iftdata = nla_nest_start(msg, i + 1); + if (!iftdata) + return -ENOBUFS; + + err = nl80211_send_iftype_data(msg, + &sband->iftype_data[i]); + if (err) + return err; + + nla_nest_end(msg, iftdata); + } + + nla_nest_end(msg, nl_iftype_data); + } + /* add bitrates */ nl_rates = nla_nest_start(msg, NL80211_BAND_ATTR_RATES); if (!nl_rates) @@ -2757,7 +2813,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, wdev_address(wdev)) || nla_put_u32(msg, NL80211_ATTR_GENERATION, rdev->devlist_generation ^ - (cfg80211_rdev_list_generation << 2))) + (cfg80211_rdev_list_generation << 2)) || + nla_put_u8(msg, NL80211_ATTR_4ADDR, wdev->use_4addr)) goto nla_put_failure; if (rdev->ops->get_channel) { @@ -4471,6 +4528,9 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, case RATE_INFO_BW_160: rate_flg = NL80211_RATE_INFO_160_MHZ_WIDTH; break; + case RATE_INFO_BW_HE_RU: + rate_flg = 0; + WARN_ON(!(info->flags & RATE_INFO_FLAGS_HE_MCS)); } if (rate_flg && nla_put_flag(msg, rate_flg)) @@ -4490,6 +4550,19 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, if (info->flags & RATE_INFO_FLAGS_SHORT_GI && nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI)) return false; + } else if (info->flags & RATE_INFO_FLAGS_HE_MCS) { + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_MCS, info->mcs)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_NSS, info->nss)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_GI, info->he_gi)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_DCM, info->he_dcm)) + return false; + if (info->bw == RATE_INFO_BW_HE_RU && + nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC, + info->he_ru_alloc)) + return false; } nla_nest_end(msg, rate); @@ -4546,13 +4619,13 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, #define PUT_SINFO(attr, memb, type) do { \ BUILD_BUG_ON(sizeof(type) == sizeof(u64)); \ - if (sinfo->filled & (1ULL << NL80211_STA_INFO_ ## attr) && \ + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_ ## attr) && \ nla_put_ ## type(msg, NL80211_STA_INFO_ ## attr, \ sinfo->memb)) \ goto nla_put_failure; \ } while (0) #define PUT_SINFO_U64(attr, memb) do { \ - if (sinfo->filled & (1ULL << NL80211_STA_INFO_ ## attr) && \ + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_ ## attr) && \ nla_put_u64_64bit(msg, NL80211_STA_INFO_ ## attr, \ sinfo->memb, NL80211_STA_INFO_PAD)) \ goto nla_put_failure; \ @@ -4561,14 +4634,14 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO(CONNECTED_TIME, connected_time, u32); PUT_SINFO(INACTIVE_TIME, inactive_time, u32); - if (sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES) | - BIT(NL80211_STA_INFO_RX_BYTES64)) && + if (sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES) | + BIT_ULL(NL80211_STA_INFO_RX_BYTES64)) && nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES, (u32)sinfo->rx_bytes)) goto nla_put_failure; - if (sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES) | - BIT(NL80211_STA_INFO_TX_BYTES64)) && + if (sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES) | + BIT_ULL(NL80211_STA_INFO_TX_BYTES64)) && nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES, (u32)sinfo->tx_bytes)) goto nla_put_failure; @@ -4588,24 +4661,24 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, default: break; } - if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL)) { + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) { if (!nl80211_put_signal(msg, sinfo->chains, sinfo->chain_signal, NL80211_STA_INFO_CHAIN_SIGNAL)) goto nla_put_failure; } - if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) { + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) { if (!nl80211_put_signal(msg, sinfo->chains, sinfo->chain_signal_avg, NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) goto nla_put_failure; } - if (sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE)) { + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) { if (!nl80211_put_sta_rate(msg, &sinfo->txrate, NL80211_STA_INFO_TX_BITRATE)) goto nla_put_failure; } - if (sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE)) { + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE)) { if (!nl80211_put_sta_rate(msg, &sinfo->rxrate, NL80211_STA_INFO_RX_BITRATE)) goto nla_put_failure; @@ -4621,7 +4694,7 @@ 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); - if (sinfo->filled & BIT(NL80211_STA_INFO_BSS_PARAM)) { + if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) { bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM); if (!bss_param) goto nla_put_failure; @@ -4640,7 +4713,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, nla_nest_end(msg, bss_param); } - if ((sinfo->filled & BIT(NL80211_STA_INFO_STA_FLAGS)) && + if ((sinfo->filled & BIT_ULL(NL80211_STA_INFO_STA_FLAGS)) && nla_put(msg, NL80211_STA_INFO_STA_FLAGS, sizeof(struct nl80211_sta_flag_update), &sinfo->sta_flags)) @@ -4886,7 +4959,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EINVAL; if (params->supported_rates) return -EINVAL; - if (params->ext_capab || params->ht_capa || params->vht_capa) + if (params->ext_capab || params->ht_capa || params->vht_capa || + params->he_capa) return -EINVAL; } @@ -5092,6 +5166,15 @@ static int nl80211_set_station_tdls(struct genl_info *info, if (info->attrs[NL80211_ATTR_VHT_CAPABILITY]) params->vht_capa = nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) { + params->he_capa = + nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + params->he_capa_len = + nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) + return -EINVAL; + } err = nl80211_parse_sta_channel_info(info, params); if (err) @@ -5319,6 +5402,17 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.vht_capa = nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) { + params.he_capa = + nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + params.he_capa_len = + nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + /* max len is validated in nla policy */ + if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) + return -EINVAL; + } + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { params.opmode_notif_used = true; params.opmode_notif = @@ -5351,6 +5445,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { params.ht_capa = NULL; params.vht_capa = NULL; + + /* HE requires WME */ + if (params.he_capa_len) + return -EINVAL; } /* When you run into this, adjust the code below for the new flag */ @@ -6848,6 +6946,16 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev) return regulatory_pre_cac_allowed(wdev->wiphy); } +static bool nl80211_check_scan_feat(struct wiphy *wiphy, u32 flags, u32 flag, + enum nl80211_ext_feature_index feat) +{ + if (!(flags & flag)) + return true; + if (wiphy_ext_feature_isset(wiphy, feat)) + return true; + return false; +} + static int nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, void *request, struct nlattr **attrs, @@ -6882,15 +6990,33 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, if (((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || - ((*flags & NL80211_SCAN_FLAG_LOW_SPAN) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_LOW_SPAN_SCAN)) || - ((*flags & NL80211_SCAN_FLAG_LOW_POWER) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_LOW_POWER_SCAN)) || - ((*flags & NL80211_SCAN_FLAG_HIGH_ACCURACY) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN))) + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_LOW_SPAN, + NL80211_EXT_FEATURE_LOW_SPAN_SCAN) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_LOW_POWER, + NL80211_EXT_FEATURE_LOW_POWER_SCAN) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_HIGH_ACCURACY, + NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_RANDOM_SN, + NL80211_EXT_FEATURE_SCAN_RANDOM_SN) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_MIN_PREQ_CONTENT, + NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT)) return -EOPNOTSUPP; if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { @@ -6905,26 +7031,6 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, return err; } - if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME)) - return -EOPNOTSUPP; - - if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP)) - return -EOPNOTSUPP; - - if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION)) - return -EOPNOTSUPP; - - if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) && - !wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE)) - return -EOPNOTSUPP; - return 0; } @@ -10147,7 +10253,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, if (err) return err; - if (sinfo.filled & BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) wdev->cqm_config->last_rssi_event_value = (s8) sinfo.rx_beacon_signal_avg; } diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 570a2b67ca10..6ab32f6a1961 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -102,7 +102,7 @@ static int wiphy_suspend(struct device *dev) struct cfg80211_registered_device *rdev = dev_to_rdev(dev); int ret = 0; - rdev->suspend_at = get_seconds(); + rdev->suspend_at = ktime_get_boottime_seconds(); rtnl_lock(); if (rdev->wiphy.registered) { @@ -130,7 +130,7 @@ static int wiphy_resume(struct device *dev) int ret = 0; /* Age scan results with time spent in suspend */ - cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at); + cfg80211_bss_age(rdev, ktime_get_boottime_seconds() - rdev->suspend_at); rtnl_lock(); if (rdev->wiphy.registered && rdev->ops->resume) diff --git a/net/wireless/util.c b/net/wireless/util.c index 3c654cd7ba56..e0825a019e9f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -4,6 +4,7 @@ * * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2017 Intel Deutschland GmbH */ #include <linux/export.h> #include <linux/bitops.h> @@ -1142,6 +1143,85 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) return 0; } +static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) +{ +#define SCALE 2048 + u16 mcs_divisors[12] = { + 34133, /* 16.666666... */ + 17067, /* 8.333333... */ + 11378, /* 5.555555... */ + 8533, /* 4.166666... */ + 5689, /* 2.777777... */ + 4267, /* 2.083333... */ + 3923, /* 1.851851... */ + 3413, /* 1.666666... */ + 2844, /* 1.388888... */ + 2560, /* 1.250000... */ + 2276, /* 1.111111... */ + 2048, /* 1.000000... */ + }; + u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; + u32 rates_969[3] = { 480388888, 453700000, 408333333 }; + u32 rates_484[3] = { 229411111, 216666666, 195000000 }; + u32 rates_242[3] = { 114711111, 108333333, 97500000 }; + u32 rates_106[3] = { 40000000, 37777777, 34000000 }; + u32 rates_52[3] = { 18820000, 17777777, 16000000 }; + u32 rates_26[3] = { 9411111, 8888888, 8000000 }; + u64 tmp; + u32 result; + + if (WARN_ON_ONCE(rate->mcs > 11)) + return 0; + + if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2)) + return 0; + if (WARN_ON_ONCE(rate->he_ru_alloc > + NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) + return 0; + if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) + return 0; + + if (rate->bw == RATE_INFO_BW_160) + result = rates_160M[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_80 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) + result = rates_969[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_40 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) + result = rates_484[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_20 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242)) + result = rates_242[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106) + result = rates_106[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52) + result = rates_52[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26) + result = rates_26[rate->he_gi]; + else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", + rate->bw, rate->he_ru_alloc)) + return 0; + + /* now scale to the appropriate MCS */ + tmp = result; + tmp *= SCALE; + do_div(tmp, mcs_divisors[rate->mcs]); + result = tmp; + + /* and take NSS, DCM into account */ + result = (result * rate->nss) / 8; + if (rate->he_dcm) + result /= 2; + + return result; +} + u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) @@ -1150,6 +1230,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate) return cfg80211_calculate_bitrate_60g(rate); if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) return cfg80211_calculate_bitrate_vht(rate); + if (rate->flags & RATE_INFO_FLAGS_HE_MCS) + return cfg80211_calculate_bitrate_he(rate); return rate->legacy; } @@ -1791,8 +1873,9 @@ bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp) { - sinfo->pertid = kcalloc(sizeof(*(sinfo->pertid)), - IEEE80211_NUM_TIDS + 1, gfp); + sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1, + sizeof(*(sinfo->pertid)), + gfp); if (!sinfo->pertid) return -ENOMEM; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 05186a47878f..167f7025ac98 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1278,7 +1278,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; - if (!(sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))) + if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) return -EOPNOTSUPP; rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); @@ -1320,7 +1320,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: - if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) { + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { int sig = sinfo.signal; wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; @@ -1334,7 +1334,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) break; } case CFG80211_SIGNAL_TYPE_UNSPEC: - if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) { + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.level = sinfo.signal; @@ -1347,9 +1347,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) } wstats.qual.updated |= IW_QUAL_NOISE_INVALID; - if (sinfo.filled & BIT(NL80211_STA_INFO_RX_DROP_MISC)) + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC)) wstats.discard.misc = sinfo.rx_dropped_misc; - if (sinfo.filled & BIT(NL80211_STA_INFO_TX_FAILED)) + if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; return &wstats; diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh new file mode 100644 index 000000000000..6f3a70df63bc --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh @@ -0,0 +1,197 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Test offloading a number of mirrors-to-gretap. The test creates a number of +# tunnels. Then it adds one flower mirror for each of the tunnels, matching a +# given host IP. Then it generates traffic at each of the host IPs and checks +# that the traffic has been mirrored at the appropriate tunnel. +# +# +--------------------------+ +--------------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 2001:db8:1:X::1/64 | | 2001:db8:1:X::2/64 | | +# +-----|--------------------+ +--------------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirrors | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | + $swp3 + gt6-<X> (ip6gretap) | +# | | 2001:db8:2:X::1/64 : loc=2001:db8:2:X::1 | +# | | : rem=2001:db8:2:X::2 | +# | | : ttl=100 | +# | | : tos=inherit | +# | | : | +# +-----|--------------------------------:----------------------------------+ +# | : +# +-----|--------------------------------:----------------------------------+ +# | H3 + $h3 + h3-gt6-<X> (ip6gretap) | +# | 2001:db8:2:X::2/64 loc=2001:db8:2:X::2 | +# | rem=2001:db8:2:X::1 | +# | ttl=100 | +# | tos=inherit | +# | | +# +-------------------------------------------------------------------------+ + +source ../../../../net/forwarding/mirror_lib.sh + +MIRROR_NUM_NETIFS=6 + +mirror_gre_ipv6_addr() +{ + local net=$1; shift + local num=$1; shift + + printf "2001:db8:%x:%x" $net $num +} + +mirror_gre_tunnels_create() +{ + local count=$1; shift + local should_fail=$1; shift + + MIRROR_GRE_BATCH_FILE="$(mktemp)" + for ((i=0; i < count; ++i)); do + local match_dip=$(mirror_gre_ipv6_addr 1 $i)::2 + local htun=h3-gt6-$i + local tun=gt6-$i + + ((mirror_gre_tunnels++)) + + ip address add dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64 + ip address add dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64 + + ip address add dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64 + ip address add dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64 + + tunnel_create $tun ip6gretap \ + $(mirror_gre_ipv6_addr 2 $i)::1 \ + $(mirror_gre_ipv6_addr 2 $i)::2 \ + ttl 100 tos inherit allow-localremote + + tunnel_create $htun ip6gretap \ + $(mirror_gre_ipv6_addr 2 $i)::2 \ + $(mirror_gre_ipv6_addr 2 $i)::1 + ip link set $htun vrf v$h3 + matchall_sink_create $htun + + cat >> $MIRROR_GRE_BATCH_FILE <<-EOF + filter add dev $swp1 ingress pref 1000 \ + protocol ipv6 \ + flower $tcflags dst_ip $match_dip \ + action mirred egress mirror dev $tun + EOF + done + + tc -b $MIRROR_GRE_BATCH_FILE + check_err_fail $should_fail $? "Mirror rule insertion" +} + +mirror_gre_tunnels_destroy() +{ + local count=$1; shift + + for ((i=0; i < count; ++i)); do + local htun=h3-gt6-$i + local tun=gt6-$i + + ip address del dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64 + ip address del dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64 + + ip address del dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64 + ip address del dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64 + + tunnel_destroy $htun + tunnel_destroy $tun + done +} + +__mirror_gre_test() +{ + local count=$1; shift + local should_fail=$1; shift + + mirror_gre_tunnels_create $count $should_fail + if ((should_fail)); then + return + fi + + sleep 5 + + for ((i = 0; i < count; ++i)); do + local dip=$(mirror_gre_ipv6_addr 1 $i)::2 + local htun=h3-gt6-$i + local message + + icmp6_capture_install $htun + mirror_test v$h1 "" $dip $htun 100 10 + icmp6_capture_uninstall $htun + done +} + +mirror_gre_test() +{ + local count=$1; shift + local should_fail=$1; shift + + if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then + check_err 1 "Could not test offloaded functionality" + return + fi + + tcflags="skip_sw" + __mirror_gre_test $count $should_fail +} + +mirror_gre_setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + mirror_gre_tunnels=0 + + vrf_prepare + + simple_if_init $h1 + simple_if_init $h2 + simple_if_init $h3 + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + tc qdisc add dev $swp1 clsact + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + ip link set dev $swp3 up +} + +mirror_gre_cleanup() +{ + mirror_gre_tunnels_destroy $mirror_gre_tunnels + + ip link set dev $swp3 down + + ip link set dev $swp2 down + + tc qdisc del dev $swp1 clsact + ip link set dev $swp1 down + + ip link del dev br1 + + simple_if_fini $h3 + simple_if_fini $h2 + simple_if_fini $h1 + + vrf_cleanup +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh new file mode 100644 index 000000000000..d231649b4f01 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh @@ -0,0 +1,167 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ROUTER_NUM_NETIFS=4 + +router_h1_create() +{ + simple_if_init $h1 192.0.1.1/24 + ip route add 193.0.0.0/8 via 192.0.1.2 dev $h1 +} + +router_h1_destroy() +{ + ip route del 193.0.0.0/8 via 192.0.1.2 dev $h1 + simple_if_fini $h1 192.0.1.1/24 +} + +router_h2_create() +{ + simple_if_init $h2 192.0.2.1/24 + tc qdisc add dev $h2 handle ffff: ingress +} + +router_h2_destroy() +{ + tc qdisc del dev $h2 handle ffff: ingress + simple_if_fini $h2 192.0.2.1/24 +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + + ip address add 192.0.1.2/24 dev $rp1 + ip address add 192.0.2.2/24 dev $rp2 +} + +router_destroy() +{ + ip address del 192.0.2.2/24 dev $rp2 + ip address del 192.0.1.2/24 dev $rp1 + + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +router_setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h1mac=$(mac_get $h1) + rp1mac=$(mac_get $rp1) + + vrf_prepare + + router_h1_create + router_h2_create + + router_create +} + +router_offload_validate() +{ + local route_count=$1 + local offloaded_count + + offloaded_count=$(ip route | grep -o 'offload' | wc -l) + [[ $offloaded_count -ge $route_count ]] +} + +router_routes_create() +{ + local route_count=$1 + local count=0 + + ROUTE_FILE="$(mktemp)" + + for i in {0..255} + do + for j in {0..255} + do + for k in {0..255} + do + if [[ $count -eq $route_count ]]; then + break 3 + fi + + echo route add 193.${i}.${j}.${k}/32 via \ + 192.0.2.1 dev $rp2 >> $ROUTE_FILE + ((count++)) + done + done + done + + ip -b $ROUTE_FILE &> /dev/null +} + +router_routes_destroy() +{ + if [[ -v ROUTE_FILE ]]; then + rm -f $ROUTE_FILE + fi +} + +router_test() +{ + local route_count=$1 + local should_fail=$2 + local count=0 + + RET=0 + + router_routes_create $route_count + + router_offload_validate $route_count + check_err_fail $should_fail $? "Offload of $route_count routes" + if [[ $RET -ne 0 ]] || [[ $should_fail -eq 1 ]]; then + return + fi + + tc filter add dev $h2 ingress protocol ip pref 1 flower \ + skip_sw dst_ip 193.0.0.0/8 action drop + + for i in {0..255} + do + for j in {0..255} + do + for k in {0..255} + do + if [[ $count -eq $route_count ]]; then + break 3 + fi + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $rp1mac \ + -A 192.0.1.1 -B 193.${i}.${j}.${k} \ + -t ip -q + ((count++)) + done + done + done + + tc_check_packets "dev $h2 ingress" 1 $route_count + check_err $? "Offload mismatch" + + tc filter del dev $h2 ingress protocol ip pref 1 flower \ + skip_sw dst_ip 193.0.0.0/8 action drop + + router_routes_destroy +} + +router_cleanup() +{ + pre_cleanup + + router_routes_destroy + router_destroy + + router_h2_destroy + router_h1_destroy + + vrf_cleanup +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh new file mode 100644 index 000000000000..73035e25085d --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh @@ -0,0 +1,119 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source "../../../../net/forwarding/devlink_lib.sh" + +if [ "$DEVLINK_VIDDID" != "15b3:cb84" ]; then + echo "SKIP: test is tailored for Mellanox Spectrum" + exit 1 +fi + +# Needed for returning to default +declare -A KVD_DEFAULTS + +KVD_CHILDREN="linear hash_single hash_double" +KVDL_CHILDREN="singles chunks large_chunks" + +devlink_sp_resource_minimize() +{ + local size + local i + + for i in $KVD_CHILDREN; do + size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]') + devlink_resource_size_set "$size" kvd "$i" + done + + for i in $KVDL_CHILDREN; do + size=$(devlink_resource_get kvd linear "$i" | \ + jq '.["size_min"]') + devlink_resource_size_set "$size" kvd linear "$i" + done +} + +devlink_sp_size_kvd_to_default() +{ + local need_reload=0 + local i + + for i in $KVD_CHILDREN; do + local size=$(echo "${KVD_DEFAULTS[kvd_$i]}" | jq '.["size"]') + current_size=$(devlink_resource_size_get kvd "$i") + + if [ "$size" -ne "$current_size" ]; then + devlink_resource_size_set "$size" kvd "$i" + need_reload=1 + fi + done + + for i in $KVDL_CHILDREN; do + local size=$(echo "${KVD_DEFAULTS[kvd_linear_$i]}" | \ + jq '.["size"]') + current_size=$(devlink_resource_size_get kvd linear "$i") + + if [ "$size" -ne "$current_size" ]; then + devlink_resource_size_set "$size" kvd linear "$i" + need_reload=1 + fi + done + + if [ "$need_reload" -ne "0" ]; then + devlink_reload + fi +} + +devlink_sp_read_kvd_defaults() +{ + local key + local i + + KVD_DEFAULTS[kvd]=$(devlink_resource_get "kvd") + for i in $KVD_CHILDREN; do + key=kvd_$i + KVD_DEFAULTS[$key]=$(devlink_resource_get kvd "$i") + done + + for i in $KVDL_CHILDREN; do + key=kvd_linear_$i + KVD_DEFAULTS[$key]=$(devlink_resource_get kvd linear "$i") + done +} + +KVD_PROFILES="default scale ipv4_max" + +devlink_sp_resource_kvd_profile_set() +{ + local profile=$1 + + case "$profile" in + scale) + devlink_resource_size_set 64000 kvd linear + devlink_resource_size_set 15616 kvd linear singles + devlink_resource_size_set 32000 kvd linear chunks + devlink_resource_size_set 16384 kvd linear large_chunks + devlink_resource_size_set 128000 kvd hash_single + devlink_resource_size_set 48000 kvd hash_double + devlink_reload + ;; + ipv4_max) + devlink_resource_size_set 64000 kvd linear + devlink_resource_size_set 15616 kvd linear singles + devlink_resource_size_set 32000 kvd linear chunks + devlink_resource_size_set 16384 kvd linear large_chunks + devlink_resource_size_set 144000 kvd hash_single + devlink_resource_size_set 32768 kvd hash_double + devlink_reload + ;; + default) + devlink_resource_size_set 98304 kvd linear + devlink_resource_size_set 16384 kvd linear singles + devlink_resource_size_set 49152 kvd linear chunks + devlink_resource_size_set 32768 kvd linear large_chunks + devlink_resource_size_set 87040 kvd hash_single + devlink_resource_size_set 60416 kvd hash_double + devlink_reload + ;; + *) + check_err 1 "Unknown profile $profile" + esac +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh new file mode 100755 index 000000000000..b1fe960e398a --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh @@ -0,0 +1,117 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=1 +source devlink_lib_spectrum.sh + +setup_prepare() +{ + devlink_sp_read_kvd_defaults +} + +cleanup() +{ + pre_cleanup + devlink_sp_size_kvd_to_default +} + +trap cleanup EXIT + +setup_prepare + +profiles_test() +{ + local i + + log_info "Running profile tests" + + for i in $KVD_PROFILES; do + RET=0 + devlink_sp_resource_kvd_profile_set $i + log_test "'$i' profile" + done + + # Default is explicitly tested at end to ensure it's actually applied + RET=0 + devlink_sp_resource_kvd_profile_set "default" + log_test "'default' profile" +} + +resources_min_test() +{ + local size + local i + local j + + log_info "Running KVD-minimum tests" + + for i in $KVD_CHILDREN; do + RET=0 + size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]') + devlink_resource_size_set "$size" kvd "$i" + + # In case of linear, need to minimize sub-resources as well + if [[ "$i" == "linear" ]]; then + for j in $KVDL_CHILDREN; do + devlink_resource_size_set 0 kvd linear "$j" + done + fi + + devlink_reload + devlink_sp_size_kvd_to_default + log_test "'$i' minimize [$size]" + done +} + +resources_max_test() +{ + local min_size + local size + local i + local j + + log_info "Running KVD-maximum tests" + for i in $KVD_CHILDREN; do + RET=0 + devlink_sp_resource_minimize + + # Calculate the maximum possible size for the given partition + size=$(devlink_resource_size_get kvd) + for j in $KVD_CHILDREN; do + if [ "$i" != "$j" ]; then + min_size=$(devlink_resource_get kvd "$j" | \ + jq '.["size_min"]') + size=$((size - min_size)) + fi + done + + # Test almost maximum size + devlink_resource_size_set "$((size - 128))" kvd "$i" + devlink_reload + log_test "'$i' almost maximize [$((size - 128))]" + + # Test above maximum size + devlink resource set "$DEVLINK_DEV" \ + path "kvd/$i" size $((size + 128)) &> /dev/null + check_fail $? "Set kvd/$i to size $((size + 128)) should fail" + log_test "'$i' Overflow rejection [$((size + 128))]" + + # Test maximum size + if [ "$i" == "hash_single" ] || [ "$i" == "hash_double" ]; then + echo "SKIP: Observed problem with exact max $i" + continue + fi + + devlink_resource_size_set "$size" kvd "$i" + devlink_reload + log_test "'$i' maximize [$size]" + + devlink_sp_size_kvd_to_default + done +} + +profiles_test +resources_min_test +resources_max_test + +exit "$RET" diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh new file mode 100644 index 000000000000..8d2186c7c62b --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../mirror_gre_scale.sh + +mirror_gre_get_target() +{ + local should_fail=$1; shift + + if ((! should_fail)); then + echo 3 + else + echo 4 + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh new file mode 100755 index 000000000000..a0a80e1a69e8 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -0,0 +1,55 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=6 +source ../../../../net/forwarding/lib.sh +source ../../../../net/forwarding/tc_common.sh +source devlink_lib_spectrum.sh + +current_test="" + +cleanup() +{ + pre_cleanup + if [ ! -z $current_test ]; then + ${current_test}_cleanup + fi + devlink_sp_size_kvd_to_default +} + +devlink_sp_read_kvd_defaults +trap cleanup EXIT + +ALL_TESTS="router tc_flower mirror_gre" +for current_test in ${TESTS:-$ALL_TESTS}; do + source ${current_test}_scale.sh + + num_netifs_var=${current_test^^}_NUM_NETIFS + num_netifs=${!num_netifs_var:-$NUM_NETIFS} + + for profile in $KVD_PROFILES; do + RET=0 + devlink_sp_resource_kvd_profile_set $profile + if [[ $RET -gt 0 ]]; then + log_test "'$current_test' [$profile] setting" + continue + fi + + for should_fail in 0 1; do + RET=0 + target=$(${current_test}_get_target "$should_fail") + ${current_test}_setup_prepare + setup_wait $num_netifs + ${current_test}_test "$target" "$should_fail" + ${current_test}_cleanup + if [[ "$should_fail" -eq 0 ]]; then + log_test "'$current_test' [$profile] $target" + else + log_test "'$current_test' [$profile] overflow $target" + fi + done + done +done +current_test="" + +exit "$RET" diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh new file mode 100644 index 000000000000..21c4697d5bab --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../router_scale.sh + +router_get_target() +{ + local should_fail=$1 + local target + + target=$(devlink_resource_size_get kvd hash_single) + + if [[ $should_fail -eq 0 ]]; then + target=$((target * 85 / 100)) + else + target=$((target + 1)) + fi + + echo $target +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh new file mode 100644 index 000000000000..f9bfd8937765 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 +source ../tc_flower_scale.sh + +tc_flower_get_target() +{ + local should_fail=$1; shift + + # 6144 (6x1024) is the theoretical maximum. + # One bank of 512 rules is taken by the 18-byte MC router rule. + # One rule is the ACL catch-all. + # 6144 - 512 - 1 = 5631 + local target=5631 + + if ((! should_fail)); then + echo $target + else + echo $((target + 1)) + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh new file mode 100644 index 000000000000..a6d733d2a4b4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh @@ -0,0 +1,134 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for resource limit of offloaded flower rules. The test adds a given +# number of flower matches for different IPv6 addresses, then generates traffic, +# and ensures each was hit exactly once. This file contains functions to set up +# a testing topology and run the test, and is meant to be sourced from a test +# script that calls the testing routine with a given number of rules. + +TC_FLOWER_NUM_NETIFS=2 + +tc_flower_h1_create() +{ + simple_if_init $h1 + tc qdisc add dev $h1 clsact +} + +tc_flower_h1_destroy() +{ + tc qdisc del dev $h1 clsact + simple_if_fini $h1 +} + +tc_flower_h2_create() +{ + simple_if_init $h2 + tc qdisc add dev $h2 clsact +} + +tc_flower_h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 +} + +tc_flower_setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + + vrf_prepare + + tc_flower_h1_create + tc_flower_h2_create +} + +tc_flower_cleanup() +{ + pre_cleanup + + tc_flower_h2_destroy + tc_flower_h1_destroy + + vrf_cleanup + + if [[ -v TC_FLOWER_BATCH_FILE ]]; then + rm -f $TC_FLOWER_BATCH_FILE + fi +} + +tc_flower_addr() +{ + local num=$1; shift + + printf "2001:db8:1::%x" $num +} + +tc_flower_rules_create() +{ + local count=$1; shift + local should_fail=$1; shift + + TC_FLOWER_BATCH_FILE="$(mktemp)" + + for ((i = 0; i < count; ++i)); do + cat >> $TC_FLOWER_BATCH_FILE <<-EOF + filter add dev $h2 ingress \ + prot ipv6 \ + pref 1000 \ + flower $tcflags dst_ip $(tc_flower_addr $i) \ + action drop + EOF + done + + tc -b $TC_FLOWER_BATCH_FILE + check_err_fail $should_fail $? "Rule insertion" +} + +__tc_flower_test() +{ + local count=$1; shift + local should_fail=$1; shift + local last=$((count - 1)) + + tc_flower_rules_create $count $should_fail + + for ((i = 0; i < count; ++i)); do + $MZ $h1 -q -c 1 -t ip -p 20 -b bc -6 \ + -A 2001:db8:2::1 \ + -B $(tc_flower_addr $i) + done + + MISMATCHES=$( + tc -j -s filter show dev $h2 ingress | + jq -r '[ .[] | select(.kind == "flower") | .options | + values as $rule | .actions[].stats.packets | + select(. != 1) | "\(.) on \($rule.keys.dst_ip)" ] | + join(", ")' + ) + + test -z "$MISMATCHES" + check_err $? "Expected to capture 1 packet for each IP, but got $MISMATCHES" +} + +tc_flower_test() +{ + local count=$1; shift + local should_fail=$1; shift + + # We use lower 16 bits of IPv6 address for match. Also there are only 16 + # bits of rule priority space. + if ((count > 65536)); then + check_err 1 "Invalid count of $count. At most 65536 rules supported" + return + fi + + if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then + check_err 1 "Could not test offloaded functionality" + return + fi + + tcflags="skip_sw" + __tc_flower_test $count $should_fail +} diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README index 4a0964c42860..b8a2af8fcfb7 100644 --- a/tools/testing/selftests/net/forwarding/README +++ b/tools/testing/selftests/net/forwarding/README @@ -46,6 +46,8 @@ Guidelines for Writing Tests o Where possible, reuse an existing topology for different tests instead of recreating the same topology. +o Tests that use anything but the most trivial topologies should include + an ASCII art showing the topology. o Where possible, IPv6 and IPv4 addresses shall conform to RFC 3849 and RFC 5737, respectively. o Where possible, tests shall be written so that they can be reused by diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh new file mode 100644 index 000000000000..5ab1e5f43022 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +############################################################################## +# Source library + +relative_path="${BASH_SOURCE%/*}" +if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then + relative_path="." +fi + +source "$relative_path/lib.sh" + +############################################################################## +# Defines + +DEVLINK_DEV=$(devlink port show | grep "${NETIFS[p1]}" | \ + grep -v "${NETIFS[p1]}[0-9]" | cut -d" " -f1 | \ + rev | cut -d"/" -f2- | rev) +if [ -z "$DEVLINK_DEV" ]; then + echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" + exit 1 +fi +if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then + echo "SKIP: devlink device's bus is not PCI" + exit 1 +fi + +DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ + -n | cut -d" " -f3) + +############################################################################## +# Sanity checks + +devlink -j resource show "$DEVLINK_DEV" &> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing devlink resource support" + exit 1 +fi + +############################################################################## +# Devlink helpers + +devlink_resource_names_to_path() +{ + local resource + local path="" + + for resource in "${@}"; do + if [ "$path" == "" ]; then + path="$resource" + else + path="${path}/$resource" + fi + done + + echo "$path" +} + +devlink_resource_get() +{ + local name=$1 + local resource_name=.[][\"$DEVLINK_DEV\"] + + resource_name="$resource_name | .[] | select (.name == \"$name\")" + + shift + for resource in "${@}"; do + resource_name="${resource_name} | .[\"resources\"][] | \ + select (.name == \"$resource\")" + done + + devlink -j resource show "$DEVLINK_DEV" | jq "$resource_name" +} + +devlink_resource_size_get() +{ + local size=$(devlink_resource_get "$@" | jq '.["size_new"]') + + if [ "$size" == "null" ]; then + devlink_resource_get "$@" | jq '.["size"]' + else + echo "$size" + fi +} + +devlink_resource_size_set() +{ + local new_size=$1 + local path + + shift + path=$(devlink_resource_names_to_path "$@") + devlink resource set "$DEVLINK_DEV" path "$path" size "$new_size" + check_err $? "Failed setting path $path to size $size" +} + +devlink_reload() +{ + local still_pending + + devlink dev reload "$DEVLINK_DEV" &> /dev/null + check_err $? "Failed reload" + + still_pending=$(devlink resource show "$DEVLINK_DEV" | \ + grep -c "size_new") + check_err $still_pending "Failed reload - There are still unset sizes" +} diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh new file mode 100755 index 000000000000..982cc8c23200 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -0,0 +1,354 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test traffic distribution when a wECMP route forwards traffic to two GRE +# tunnels. +# +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# | 2001:db8:1::1/64 | | +# +-------------------|-----+ +# | +# +-------------------|------------------------+ +# | SW1 | | +# | $ol1 + | +# | 192.0.2.2/28 | +# | 2001:db8:1::2/64 | +# | | +# | + g1a (gre) + g1b (gre) | +# | loc=192.0.2.65 loc=192.0.2.81 | +# | rem=192.0.2.66 --. rem=192.0.2.82 --. | +# | tos=inherit | tos=inherit | | +# | .------------------' | | +# | | .------------------' | +# | v v | +# | + $ul1.111 (vlan) + $ul1.222 (vlan) | +# | | 192.0.2.129/28 | 192.0.2.145/28 | +# | \ / | +# | \________________/ | +# | | | +# | + $ul1 | +# +------------|-------------------------------+ +# | +# +------------|-------------------------------+ +# | SW2 + $ul2 | +# | _______|________ | +# | / \ | +# | / \ | +# | + $ul2.111 (vlan) + $ul2.222 (vlan) | +# | ^ 192.0.2.130/28 ^ 192.0.2.146/28 | +# | | | | +# | | '------------------. | +# | '------------------. | | +# | + g2a (gre) | + g2b (gre) | | +# | loc=192.0.2.66 | loc=192.0.2.82 | | +# | rem=192.0.2.65 --' rem=192.0.2.81 --' | +# | tos=inherit tos=inherit | +# | | +# | $ol2 + | +# | 192.0.2.17/28 | | +# | 2001:db8:2::1/64 | | +# +-------------------|------------------------+ +# | +# +-------------------|-----+ +# | H2 | | +# | $h2 + | +# | 192.0.2.18/28 | +# | 2001:db8:2::2/64 | +# +-------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + multipath_ipv4 + multipath_ipv6 + multipath_ipv6_l4 +" + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2 + ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 +} + +h1_destroy() +{ + ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 + ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2 + simple_if_fini $h1 192.0.2.1/28 +} + +sw1_create() +{ + simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64 + __simple_if_init $ul1 v$ol1 + vlan_create $ul1 111 v$ol1 192.0.2.129/28 + vlan_create $ul1 222 v$ol1 192.0.2.145/28 + + tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1 + __simple_if_init g1a v$ol1 192.0.2.65/32 + ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130 + + tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1 + __simple_if_init g1b v$ol1 192.0.2.81/32 + ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146 + + ip route add vrf v$ol1 192.0.2.16/28 \ + nexthop dev g1a \ + nexthop dev g1b + ip route add vrf v$ol1 2001:db8:2::/64 \ + nexthop dev g1a \ + nexthop dev g1b + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress pref 111 prot 802.1q \ + flower vlan_id 111 action pass + tc filter add dev $ul1 egress pref 222 prot 802.1q \ + flower vlan_id 222 action pass +} + +sw1_destroy() +{ + tc qdisc del dev $ul1 clsact + + ip route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 192.0.2.16/28 + + ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 + __simple_if_fini g1b 192.0.2.81/32 + tunnel_destroy g1b + + ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130 + __simple_if_fini g1a 192.0.2.65/32 + tunnel_destroy g1a + + vlan_destroy $ul1 222 + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64 +} + +sw2_create() +{ + simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 192.0.2.130/28 + vlan_create $ul2 222 v$ol2 192.0.2.146/28 + + tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2 + __simple_if_init g2a v$ol2 192.0.2.66/32 + ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129 + + tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2 + __simple_if_init g2b v$ol2 192.0.2.82/32 + ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145 + + ip route add vrf v$ol2 192.0.2.0/28 \ + nexthop dev g2a \ + nexthop dev g2b + ip route add vrf v$ol2 2001:db8:1::/64 \ + nexthop dev g2a \ + nexthop dev g2b +} + +sw2_destroy() +{ + ip route del vrf v$ol2 2001:db8:1::/64 + ip route del vrf v$ol2 192.0.2.0/28 + + ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 + __simple_if_fini g2b 192.0.2.82/32 + tunnel_destroy g2b + + ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129 + __simple_if_fini g2a 192.0.2.66/32 + tunnel_destroy g2a + + vlan_destroy $ul2 222 + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64 + ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17 + ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1 +} + +h2_destroy() +{ + ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1 + ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17 + simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + vrf_prepare + h1_create + sw1_create + sw2_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +multipath4_test() +{ + local what=$1; shift + local weight1=$1; shift + local weight2=$1; shift + + sysctl_set net.ipv4.fib_multipath_hash_policy 1 + ip route replace vrf v$ol1 192.0.2.16/28 \ + nexthop dev g1a weight $weight1 \ + nexthop dev g1b weight $weight2 + + local t0_111=$(tc_rule_stats_get $ul1 111 egress) + local t0_222=$(tc_rule_stats_get $ul1 222 egress) + + ip vrf exec v$h1 \ + $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ + -d 1msec -t udp "sp=1024,dp=0-32768" + + local t1_111=$(tc_rule_stats_get $ul1 111 egress) + local t1_222=$(tc_rule_stats_get $ul1 222 egress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + multipath_eval "$what" $weight1 $weight2 $d111 $d222 + + ip route replace vrf v$ol1 192.0.2.16/28 \ + nexthop dev g1a \ + nexthop dev g1b + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +multipath6_l4_test() +{ + local what=$1; shift + local weight1=$1; shift + local weight2=$1; shift + + sysctl_set net.ipv6.fib_multipath_hash_policy 1 + ip route replace vrf v$ol1 2001:db8:2::/64 \ + nexthop dev g1a weight $weight1 \ + nexthop dev g1b weight $weight2 + + local t0_111=$(tc_rule_stats_get $ul1 111 egress) + local t0_222=$(tc_rule_stats_get $ul1 222 egress) + + ip vrf exec v$h1 \ + $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=1024,dp=0-32768" + + local t1_111=$(tc_rule_stats_get $ul1 111 egress) + local t1_222=$(tc_rule_stats_get $ul1 222 egress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + multipath_eval "$what" $weight1 $weight2 $d111 $d222 + + ip route replace vrf v$ol1 2001:db8:2::/64 \ + nexthop dev g1a \ + nexthop dev g1b + sysctl_restore net.ipv6.fib_multipath_hash_policy +} + +multipath6_test() +{ + local what=$1; shift + local weight1=$1; shift + local weight2=$1; shift + + ip route replace vrf v$ol1 2001:db8:2::/64 \ + nexthop dev g1a weight $weight1 \ + nexthop dev g1b weight $weight2 + + local t0_111=$(tc_rule_stats_get $ul1 111 egress) + local t0_222=$(tc_rule_stats_get $ul1 222 egress) + + # Generate 16384 echo requests, each with a random flow label. + for ((i=0; i < 16384; ++i)); do + ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null + done + + local t1_111=$(tc_rule_stats_get $ul1 111 egress) + local t1_222=$(tc_rule_stats_get $ul1 222 egress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + multipath_eval "$what" $weight1 $weight2 $d111 $d222 + + ip route replace vrf v$ol1 2001:db8:2::/64 \ + nexthop dev g1a \ + nexthop dev g1b +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.18 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +multipath_ipv4() +{ + log_info "Running IPv4 multipath tests" + multipath4_test "ECMP" 1 1 + multipath4_test "Weighted MP 2:1" 2 1 + multipath4_test "Weighted MP 11:45" 11 45 +} + +multipath_ipv6() +{ + log_info "Running IPv6 multipath tests" + multipath6_test "ECMP" 1 1 + multipath6_test "Weighted MP 2:1" 2 1 + multipath6_test "Weighted MP 11:45" 11 45 +} + +multipath_ipv6_l4() +{ + log_info "Running IPv6 L4 hash multipath tests" + multipath6_l4_test "ECMP" 1 1 + multipath6_l4_test "Weighted MP 2:1" 2 1 + multipath6_l4_test "Weighted MP 11:45" 11 45 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7b18a53aa556..e073918bbe15 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -14,8 +14,13 @@ PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no} NETIF_TYPE=${NETIF_TYPE:=veth} NETIF_CREATE=${NETIF_CREATE:=yes} -if [[ -f forwarding.config ]]; then - source forwarding.config +relative_path="${BASH_SOURCE%/*}" +if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then + relative_path="." +fi + +if [[ -f $relative_path/forwarding.config ]]; then + source "$relative_path/forwarding.config" fi ############################################################################## @@ -151,6 +156,19 @@ check_fail() fi } +check_err_fail() +{ + local should_fail=$1; shift + local err=$1; shift + local what=$1; shift + + if ((should_fail)); then + check_fail $err "$what succeeded, but should have failed" + else + check_err $err "$what failed" + fi +} + log_test() { local test_name=$1 @@ -185,18 +203,27 @@ log_info() echo "INFO: $msg" } +setup_wait_dev() +{ + local dev=$1; shift + + while true; do + ip link show dev $dev up \ + | grep 'state UP' &> /dev/null + if [[ $? -ne 0 ]]; then + sleep 1 + else + break + fi + done +} + setup_wait() { - for i in $(eval echo {1..$NUM_NETIFS}); do - while true; do - ip link show dev ${NETIFS[p$i]} up \ - | grep 'state UP' &> /dev/null - if [[ $? -ne 0 ]]; then - sleep 1 - else - break - fi - done + local num_netifs=${1:-$NUM_NETIFS} + + for ((i = 1; i <= num_netifs; ++i)); do + setup_wait_dev ${NETIFS[p$i]} done # Make sure links are ready. @@ -287,6 +314,29 @@ __addr_add_del() done } +__simple_if_init() +{ + local if_name=$1; shift + local vrf_name=$1; shift + local addrs=("${@}") + + ip link set dev $if_name master $vrf_name + ip link set dev $if_name up + + __addr_add_del $if_name add "${addrs[@]}" +} + +__simple_if_fini() +{ + local if_name=$1; shift + local addrs=("${@}") + + __addr_add_del $if_name del "${addrs[@]}" + + ip link set dev $if_name down + ip link set dev $if_name nomaster +} + simple_if_init() { local if_name=$1 @@ -298,11 +348,8 @@ simple_if_init() array=("${@}") vrf_create $vrf_name - ip link set dev $if_name master $vrf_name ip link set dev $vrf_name up - ip link set dev $if_name up - - __addr_add_del $if_name add "${array[@]}" + __simple_if_init $if_name $vrf_name "${array[@]}" } simple_if_fini() @@ -315,9 +362,7 @@ simple_if_fini() vrf_name=v$if_name array=("${@}") - __addr_add_del $if_name del "${array[@]}" - - ip link set dev $if_name down + __simple_if_fini $if_name "${array[@]}" vrf_destroy $vrf_name } @@ -383,9 +428,10 @@ tc_rule_stats_get() { local dev=$1; shift local pref=$1; shift + local dir=$1; shift - tc -j -s filter show dev $dev ingress pref $pref | - jq '.[1].options.actions[].stats.packets' + tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ + | jq '.[1].options.actions[].stats.packets' } mac_get() @@ -437,7 +483,9 @@ forwarding_restore() tc_offload_check() { - for i in $(eval echo {1..$NUM_NETIFS}); do + local num_netifs=${1:-$NUM_NETIFS} + + for ((i = 1; i <= num_netifs; ++i)); do ethtool -k ${NETIFS[p$i]} \ | grep "hw-tc-offload: on" &> /dev/null if [[ $? -ne 0 ]]; then @@ -453,9 +501,15 @@ trap_install() local dev=$1; shift local direction=$1; shift - # For slow-path testing, we need to install a trap to get to - # slow path the packets that would otherwise be switched in HW. - tc filter add dev $dev $direction pref 1 flower skip_sw action trap + # Some devices may not support or need in-hardware trapping of traffic + # (e.g. the veth pairs that this library creates for non-existent + # loopbacks). Use continue instead, so that there is a filter in there + # (some tests check counters), and so that other filters are still + # processed. + tc filter add dev $dev $direction pref 1 \ + flower skip_sw action trap 2>/dev/null \ + || tc filter add dev $dev $direction pref 1 \ + flower action continue } trap_uninstall() @@ -463,11 +517,13 @@ trap_uninstall() local dev=$1; shift local direction=$1; shift - tc filter del dev $dev $direction pref 1 flower skip_sw + tc filter del dev $dev $direction pref 1 flower } slow_path_trap_install() { + # For slow-path testing, we need to install a trap to get to + # slow path the packets that would otherwise be switched in HW. if [ "${tcflags/skip_hw}" != "$tcflags" ]; then trap_install "$@" fi @@ -557,6 +613,49 @@ tests_run() done } +multipath_eval() +{ + local desc="$1" + local weight_rp12=$2 + local weight_rp13=$3 + local packets_rp12=$4 + local packets_rp13=$5 + local weights_ratio packets_ratio diff + + RET=0 + + if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then + weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \ + | bc -l) + else + weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" \ + | bc -l) + fi + + if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then + check_err 1 "Packet difference is 0" + log_test "Multipath" + log_info "Expected ratio $weights_ratio" + return + fi + + if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then + packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \ + | bc -l) + else + packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" \ + | bc -l) + fi + + diff=$(echo $weights_ratio - $packets_ratio | bc -l) + diff=${diff#-} + + test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 + check_err $? "Too large discrepancy between expected and measured ratios" + log_test "$desc" + log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" +} + ############################################################################## # Tests diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh index 3bb4c2ba7b14..197e769c2ed1 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh @@ -74,12 +74,14 @@ test_vlan_match() test_gretap() { - test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" + test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to gretap" } test_ip6gretap() { - test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to ip6gretap" } test_gretap_stp() diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index aa29d46186a8..135902aa8b11 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -122,15 +122,8 @@ test_span_gre_egress_up() # After setting the device up, wait for neighbor to get resolved so that # we can expect mirroring to work. ip link set dev $swp3 up - while true; do - ip neigh sh dev $swp3 $remote_ip nud reachable | - grep -q ^ - if [[ $? -ne 0 ]]; then - sleep 1 - else - break - fi - done + setup_wait_dev $swp3 + ping -c 1 -I $swp3 $remote_ip &>/dev/null quick_test_span_gre_dir $tundev ingress mirror_uninstall $swp1 ingress diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh index 619b469365be..1c18e332cd4f 100644 --- a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh @@ -62,7 +62,7 @@ full_test_span_gre_dir_vlan_ips() "$backward_type" "$ip1" "$ip2" tc filter add dev $h3 ingress pref 77 prot 802.1q \ - flower $vlan_match ip_proto 0x2f \ + flower $vlan_match \ action pass mirror_test v$h1 $ip1 $ip2 $h3 77 10 tc filter del dev $h3 ingress pref 77 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 5dbc7a08f4bd..d3e75bb6a2d8 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -39,6 +39,12 @@ setup_prepare() swp3=${NETIFS[p5]} h3=${NETIFS[p6]} + # gt4's remote address is at $h3.555, not $h3. Thus the packets arriving + # directly to $h3 for test_gretap_untagged_egress() are rejected by + # rp_filter and the test spuriously fails. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$h3.rp_filter 0 + vrf_prepare mirror_gre_topo_create @@ -65,6 +71,9 @@ cleanup() mirror_gre_topo_destroy vrf_cleanup + + sysctl_restore net.ipv4.conf.$h3.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter } test_vlan_match() @@ -79,12 +88,14 @@ test_vlan_match() test_gretap() { - test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap" + test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to gretap" } test_ip6gretap() { - test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap" + test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \ + "mirror to ip6gretap" } test_span_gre_forbidden_cpu() diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh new file mode 100755 index 000000000000..ebc596a272f7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge.sh @@ -0,0 +1,113 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64 +} + +router_create() +{ + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 +} + +router_destroy() +{ + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp2 down + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh new file mode 100755 index 000000000000..fef88eb4b873 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -0,0 +1,132 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + vlan +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 + ip -4 route del 192.0.2.128/28 vrf v$h1 + vlan_destroy $h1 555 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64 + ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 + ip -4 route del 192.0.2.0/28 vrf v$h2 + simple_if_fini $h2 192.0.2.130/28 +} + +router_create() +{ + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + bridge vlan add dev br1 vid 555 self pvid untagged + bridge vlan add dev $swp1 vid 555 + + __addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64 + + ip link set dev $swp2 up + __addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64 +} + +router_destroy() +{ + __addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64 + ip link set dev $swp2 down + + __addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64 + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +vlan() +{ + RET=0 + + bridge vlan add dev br1 vid 333 self + check_err $? "Can't add a non-PVID VLAN" + bridge vlan del dev br1 vid 333 self + check_err $? "Can't remove a non-PVID VLAN" + + log_test "vlan" +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.130 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 8b6d0fb6d604..79a209927962 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -159,45 +159,6 @@ router2_destroy() vrf_destroy "vrf-r2" } -multipath_eval() -{ - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 - local packets_rp12=$4 - local packets_rp13=$5 - local weights_ratio packets_ratio diff - - RET=0 - - if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then - check_err 1 "Packet difference is 0" - log_test "Multipath" - log_info "Expected ratio $weights_ratio" - return - fi - - if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then - weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \ - | bc -l) - packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \ - | bc -l) - else - weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \ - bc -l) - packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \ - bc -l) - fi - - diff=$(echo $weights_ratio - $packets_ratio | bc -l) - diff=${diff#-} - - test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 - check_err $? "Too large discrepancy between expected and measured ratios" - log_test "$desc" - log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" -} - multipath4_test() { local desc="$1" diff --git a/tools/testing/selftests/net/ip6_gre_headroom.sh b/tools/testing/selftests/net/ip6_gre_headroom.sh new file mode 100755 index 000000000000..5b41e8bb6e2d --- /dev/null +++ b/tools/testing/selftests/net/ip6_gre_headroom.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that enough headroom is reserved for the first packet passing through an +# IPv6 GRE-like netdevice. + +setup_prepare() +{ + ip link add h1 type veth peer name swp1 + ip link add h3 type veth peer name swp3 + + ip link set dev h1 up + ip address add 192.0.2.1/28 dev h1 + + ip link add dev vh3 type vrf table 20 + ip link set dev h3 master vh3 + ip link set dev vh3 up + ip link set dev h3 up + + ip link set dev swp3 up + ip address add dev swp3 2001:db8:2::1/64 + ip address add dev swp3 2001:db8:2::3/64 + + ip link set dev swp1 up + tc qdisc add dev swp1 clsact + + ip link add name er6 type ip6erspan \ + local 2001:db8:2::1 remote 2001:db8:2::2 oseq okey 123 + ip link set dev er6 up + + ip link add name gt6 type ip6gretap \ + local 2001:db8:2::3 remote 2001:db8:2::4 + ip link set dev gt6 up + + sleep 1 +} + +cleanup() +{ + ip link del dev gt6 + ip link del dev er6 + ip link del dev swp1 + ip link del dev swp3 + ip link del dev vh3 +} + +test_headroom() +{ + local type=$1; shift + local tundev=$1; shift + + tc filter add dev swp1 ingress pref 1000 matchall skip_hw \ + action mirred egress mirror dev $tundev + ping -I h1 192.0.2.2 -c 1 -w 2 &> /dev/null + tc filter del dev swp1 ingress pref 1000 + + # If it doesn't panic, it passes. + printf "TEST: %-60s [PASS]\n" "$type headroom" +} + +trap cleanup EXIT + +setup_prepare +test_headroom ip6gretap gt6 +test_headroom ip6erspan er6 diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 0d7a44fa30af..08c341b49760 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -525,18 +525,21 @@ kci_test_macsec() #------------------------------------------------------------------- kci_test_ipsec() { - srcip="14.0.0.52" - dstip="14.0.0.70" + ret=0 algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + srcip=192.168.123.1 + dstip=192.168.123.2 + spi=7 + + ip addr add $srcip dev $devdummy # flush to be sure there's nothing configured ip x s flush ; ip x p flush check_err $? # start the monitor in the background - tmpfile=`mktemp ipsectestXXX` - ip x m > $tmpfile & - mpid=$! + tmpfile=`mktemp /var/run/ipsectestXXX` + mpid=`(ip x m > $tmpfile & echo $!) 2>/dev/null` sleep 0.2 ipsecid="proto esp src $srcip dst $dstip spi 0x07" @@ -599,6 +602,7 @@ kci_test_ipsec() check_err $? ip x p flush check_err $? + ip addr del $srcip/32 dev $devdummy if [ $ret -ne 0 ]; then echo "FAIL: ipsec" @@ -607,6 +611,119 @@ kci_test_ipsec() echo "PASS: ipsec" } +#------------------------------------------------------------------- +# Example commands +# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 replay-window 32 \ +# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \ +# sel src 14.0.0.52/24 dst 14.0.0.70/24 +# offload dev sim1 dir out +# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \ +# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 +# +#------------------------------------------------------------------- +kci_test_ipsec_offload() +{ + ret=0 + algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + srcip=192.168.123.3 + dstip=192.168.123.4 + dev=simx1 + sysfsd=/sys/kernel/debug/netdevsim/$dev + sysfsf=$sysfsd/ipsec + + # setup netdevsim since dummydev doesn't have offload support + modprobe netdevsim + check_err $? + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec_offload can't load netdevsim" + return 1 + fi + + ip link add $dev type netdevsim + ip addr add $srcip dev $dev + ip link set $dev up + if [ ! -d $sysfsd ] ; then + echo "FAIL: ipsec_offload can't create device $dev" + return 1 + fi + if [ ! -f $sysfsf ] ; then + echo "FAIL: ipsec_offload netdevsim doesn't support IPsec offload" + return 1 + fi + + # flush to be sure there's nothing configured + ip x s flush ; ip x p flush + + # create offloaded SAs, both in and out + ip x p add dir out src $srcip/24 dst $dstip/24 \ + tmpl proto esp src $srcip dst $dstip spi 9 \ + mode transport reqid 42 + check_err $? + ip x p add dir out src $dstip/24 dst $srcip/24 \ + tmpl proto esp src $dstip dst $srcip spi 9 \ + mode transport reqid 42 + check_err $? + + ip x s add proto esp src $srcip dst $dstip spi 9 \ + mode transport reqid 42 $algo sel src $srcip/24 dst $dstip/24 \ + offload dev $dev dir out + check_err $? + ip x s add proto esp src $dstip dst $srcip spi 9 \ + mode transport reqid 42 $algo sel src $dstip/24 dst $srcip/24 \ + offload dev $dev dir in + check_err $? + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec_offload can't create SA" + return 1 + fi + + # does offload show up in ip output + lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"` + if [ $lines -ne 2 ] ; then + echo "FAIL: ipsec_offload SA offload missing from list output" + check_err 1 + fi + + # use ping to exercise the Tx path + ping -I $dev -c 3 -W 1 -i 0 $dstip >/dev/null + + # does driver have correct offload info + diff $sysfsf - << EOF +SA count=2 tx=3 +sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000 +sa[0] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 +sa[0] key=0x34333231 38373635 32313039 36353433 +sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0 +sa[1] spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1 +sa[1] key=0x34333231 38373635 32313039 36353433 +EOF + if [ $? -ne 0 ] ; then + echo "FAIL: ipsec_offload incorrect driver data" + check_err 1 + fi + + # does offload get removed from driver + ip x s flush + ip x p flush + lines=`grep -c "SA count=0" $sysfsf` + if [ $lines -ne 1 ] ; then + echo "FAIL: ipsec_offload SA not removed from driver" + check_err 1 + fi + + # clean up any leftovers + ip link del $dev + rmmod netdevsim + + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec_offload" + return 1 + fi + echo "PASS: ipsec_offload" +} + kci_test_gretap() { testns="testns" @@ -861,6 +978,7 @@ kci_test_rtnl() kci_test_encap kci_test_macsec kci_test_ipsec + kci_test_ipsec_offload kci_del_dummy } diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index 3a2f51fc7fd4..a022792d392a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -336,6 +336,30 @@ ] }, { + "id": "b10b", + "name": "Add all 7 csum actions", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action csum icmp ip4h sctp igmp udplite udp tcp index 7", + "expExitCode": "0", + "verifyCmd": "$TC actions get action csum index 7", + "matchPattern": "action order [0-9]*: csum \\(iph, icmp, igmp, tcp, udp, udplite, sctp\\).*index 7 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action csum" + ] + }, + { "id": "ce92", "name": "Add csum udp action with cookie", "category": [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json new file mode 100644 index 000000000000..d878ce1c7d08 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json @@ -0,0 +1,749 @@ +[ + { + "id": "2b11", + "name": "Add tunnel_key set action with mandatory parameters", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action tunnel_key", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "dc6b", + "name": "Add tunnel_key set action with missing mandatory src_ip parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set dst_ip 20.20.20.2 id 100", + "expExitCode": "255", + "verifyCmd": "$TC actions list action tunnel_key", + "matchPattern": "action order [0-9]+: tunnel_key set.*dst_ip 20.20.20.2.*key_id 100", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "7f25", + "name": "Add tunnel_key set action with missing mandatory dst_ip parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 id 100", + "expExitCode": "255", + "verifyCmd": "$TC actions list action tunnel_key", + "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*key_id 100", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "ba4e", + "name": "Add tunnel_key set action with missing mandatory id parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2", + "expExitCode": "255", + "verifyCmd": "$TC actions list action tunnel_key", + "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "a5e0", + "name": "Add tunnel_key set action with invalid src_ip parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 300.168.100.1 dst_ip 192.168.200.1 id 7 index 1", + "expExitCode": "1", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 300.168.100.1.*dst_ip 192.168.200.1.*key_id 7.*index 1 ref", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "eaa8", + "name": "Add tunnel_key set action with invalid dst_ip parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.800.1 id 10 index 11", + "expExitCode": "1", + "verifyCmd": "$TC actions get action tunnel_key index 11", + "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 192.168.100.1.*dst_ip 192.168.800.1.*key_id 10.*index 11 ref", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "3b09", + "name": "Add tunnel_key set action with invalid id parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 112233445566778899 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 112233445566778899.*index 1 ref", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "9625", + "name": "Add tunnel_key set action with invalid dst_port parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 dst_port 998877 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 11.*dst_port 998877.*index 1 ref", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "05af", + "name": "Add tunnel_key set action with optional dst_port parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.200.1 id 789 dst_port 4000 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 10", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.100.1.*dst_ip 192.168.200.1.*key_id 789.*dst_port 4000.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "da80", + "name": "Add tunnel_key set action with index at 32-bit maximum", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 4294967295", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*id 11.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "d407", + "name": "Add tunnel_key set action with index exceeding 32-bit maximum", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295678", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 4294967295678", + "matchPattern": "action order [0-9]+: tunnel_key set.*index 4294967295678 ref", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "5cba", + "name": "Add tunnel_key set action with id value at 32-bit maximum", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 4294967295 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 4294967295.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "e84a", + "name": "Add tunnel_key set action with id value exceeding 32-bit maximum", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42949672955 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 4294967295", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42949672955.*index 1", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "9c19", + "name": "Add tunnel_key set action with dst_port value at 16-bit maximum", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "3bd9", + "name": "Add tunnel_key set action with dst_port value exceeding 16-bit maximum", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535789 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535789.*index 1", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "68e2", + "name": "Add tunnel_key unset action", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key unset index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*unset.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "6192", + "name": "Add tunnel_key unset continue action", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key unset continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*unset continue.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "061d", + "name": "Add tunnel_key set continue action with cookie", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "8acb", + "name": "Add tunnel_key set continue action with invalid cookie", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "a07e", + "name": "Add tunnel_key action with no set/unset command specified", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "b227", + "name": "Add tunnel_key action with csum option", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1 csum index 99", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 99", + "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*csum pipe.*index 99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "58a7", + "name": "Add tunnel_key action with nocsum option", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7823 nocsum index 234", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 234", + "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7823.*nocsum pipe.*index 234", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "2575", + "name": "Add tunnel_key action with not-supported parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 foobar 999 index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 4", + "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*foobar 999.*index 4", + "matchCount": "0", + "teardown": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ] + }, + { + "id": "7a88", + "name": "Add tunnel_key action with cookie parameter", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 index 4 cookie aa11bb22cc33dd44ee55ff66aa11b1b2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 4", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*dst_port 0.*csum pipe.*index 4 ref.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "7afc", + "name": "Replace tunnel_key set action with all parameters", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ], + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 csum id 1 index 1" + ], + "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 nocsum id 11 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*nocsum pipe.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "364d", + "name": "Replace tunnel_key set action with all parameters and cookie", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ], + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 index 1 cookie aabbccddeeff112233445566778800a" + ], + "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 id 11 csum reclassify index 1 cookie a1b1c1d1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action tunnel_key index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*csum reclassify.*index 1.*cookie a1b1c1d1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "937c", + "name": "Fetch all existing tunnel_key actions", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ], + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1", + "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 jump 10 index 2", + "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3", + "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4" + ], + "cmdUnderTest": "$TC actions list action tunnel_key", + "expExitCode": "0", + "verifyCmd": "$TC actions list action tunnel_key", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*nocsum pipe.*index 1.*set.*src_ip 11.10.10.1.*dst_ip 21.20.20.2.*key_id 2.*dst_port 3129.*csum jump 10.*index 2.*set.*src_ip 12.10.10.1.*dst_ip 22.20.20.2.*key_id 3.*dst_port 3130.*csum pass.*index 3.*set.*src_ip 13.10.10.1.*dst_ip 23.20.20.2.*key_id 4.*dst_port 3131.*nocsum continue.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + }, + { + "id": "6783", + "name": "Flush all existing tunnel_key actions", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ], + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1", + "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 reclassify index 2", + "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3", + "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4" + ], + "cmdUnderTest": "$TC actions flush action tunnel_key", + "expExitCode": "0", + "verifyCmd": "$TC actions list action tunnel_key", + "matchPattern": "action order [0-9]+:.*", + "matchCount": "0", + "teardown": [ + "$TC actions flush action tunnel_key" + ] + } +] |