diff options
573 files changed, 12860 insertions, 3576 deletions
diff --git a/.gitignore b/.gitignore index 72ef86a5570d..2763fce8766c 100644 --- a/.gitignore +++ b/.gitignore @@ -100,6 +100,10 @@ modules.order /include/ksym/ /arch/*/include/generated/ +# Generated lkdtm tests +/tools/testing/selftests/lkdtm/*.sh +!/tools/testing/selftests/lkdtm/run.sh + # stgit generated dirs patches-* @@ -567,6 +567,11 @@ D: Original author of Amiga FFS filesystem S: Orlando, Florida S: USA +N: Paul Burton +E: paulburton@kernel.org +W: https://pburton.com +D: MIPS maintainer 2018-2020 + N: Lennert Buytenhek E: kernel@wantstofly.org D: Original (2.4) rewrite of the ethernet bridging code diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst index b342a6796392..cf2edcd09183 100644 --- a/Documentation/admin-guide/bootconfig.rst +++ b/Documentation/admin-guide/bootconfig.rst @@ -62,6 +62,30 @@ Or more shorter, written as following:: In both styles, same key words are automatically merged when parsing it at boot time. So you can append similar trees or key-values. +Same-key Values +--------------- + +It is prohibited that two or more values or arrays share a same-key. +For example,:: + + foo = bar, baz + foo = qux # !ERROR! we can not re-define same key + +If you want to append the value to existing key as an array member, +you can use ``+=`` operator. For example:: + + foo = bar, baz + foo += qux + +In this case, the key ``foo`` has ``bar``, ``baz`` and ``qux``. + +However, a sub-key and a value can not co-exist under a parent key. +For example, following config is NOT allowed.:: + + foo = value1 + foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist + + Comments -------- @@ -102,9 +126,13 @@ Boot Kernel With a Boot Config ============================== Since the boot configuration file is loaded with initrd, it will be added -to the end of the initrd (initramfs) image file. The Linux kernel decodes -the last part of the initrd image in memory to get the boot configuration -data. +to the end of the initrd (initramfs) image file with size, checksum and +12-byte magic word as below. + +[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n] + +The Linux kernel decodes the last part of the initrd image in memory to +get the boot configuration data. Because of this "piggyback" method, there is no need to change or update the boot loader and the kernel image itself. diff --git a/Documentation/arm64/memory.rst b/Documentation/arm64/memory.rst index 02e02175e6f5..cf03b3290800 100644 --- a/Documentation/arm64/memory.rst +++ b/Documentation/arm64/memory.rst @@ -129,7 +129,7 @@ this logic. As a single binary will need to support both 48-bit and 52-bit VA spaces, the VMEMMAP must be sized large enough for 52-bit VAs and -also must be sized large enought to accommodate a fixed PAGE_OFFSET. +also must be sized large enough to accommodate a fixed PAGE_OFFSET. Most code in the kernel should not need to consider the VA_BITS, for code that does need to know the VA size the variables are diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst index d4a85d535bf9..4a9d9c794ee5 100644 --- a/Documentation/arm64/tagged-address-abi.rst +++ b/Documentation/arm64/tagged-address-abi.rst @@ -44,8 +44,15 @@ The AArch64 Tagged Address ABI has two stages of relaxation depending how the user addresses are used by the kernel: 1. User addresses not accessed by the kernel but used for address space - management (e.g. ``mmap()``, ``mprotect()``, ``madvise()``). The use - of valid tagged pointers in this context is always allowed. + management (e.g. ``mprotect()``, ``madvise()``). The use of valid + tagged pointers in this context is allowed with the exception of + ``brk()``, ``mmap()`` and the ``new_address`` argument to + ``mremap()`` as these have the potential to alias with existing + user addresses. + + NOTE: This behaviour changed in v5.6 and so some earlier kernels may + incorrectly accept valid tagged pointers for the ``brk()``, + ``mmap()`` and ``mremap()`` system calls. 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI relaxation is disabled by default and the application thread needs to diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 7cd56a1993b1..607758a66a99 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -551,6 +551,7 @@ options to your ``.config``: Once the kernel is built and installed, a simple .. code-block:: bash + modprobe example-test ...will run the tests. diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml index 9af873b43acd..8453ee340b9f 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml @@ -33,24 +33,40 @@ properties: maxItems: 1 clocks: - minItems: 2 - maxItems: 3 - items: - - description: The CSI interface clock - - description: The CSI ISP clock - - description: The CSI DRAM clock + oneOf: + - items: + - description: The CSI interface clock + - description: The CSI DRAM clock + + - items: + - description: The CSI interface clock + - description: The CSI ISP clock + - description: The CSI DRAM clock clock-names: - minItems: 2 - maxItems: 3 - items: - - const: bus - - const: isp - - const: ram + oneOf: + - items: + - const: bus + - const: ram + + - items: + - const: bus + - const: isp + - const: ram resets: maxItems: 1 + # FIXME: This should be made required eventually once every SoC will + # have the MBUS declared. + interconnects: + maxItems: 1 + + # FIXME: This should be made required eventually once every SoC will + # have the MBUS declared. + interconnect-names: + const: dma-mem + # See ./video-interfaces.txt for details port: type: object diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml index dd1843489ad1..3e0a8a92d652 100644 --- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml @@ -347,6 +347,7 @@ examples: interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>; #iommu-cells = <1>; + #reset-cells = <1>; }; external-memory-controller@7001b000 { @@ -363,20 +364,23 @@ examples: timing-0 { clock-frequency = <12750000>; - nvidia,emc-zcal-cnt-long = <0x00000042>; - nvidia,emc-auto-cal-interval = <0x001fffff>; - nvidia,emc-ctt-term-ctrl = <0x00000802>; - nvidia,emc-cfg = <0x73240000>; - nvidia,emc-cfg-2 = <0x000008c5>; - nvidia,emc-sel-dpd-ctrl = <0x00040128>; - nvidia,emc-bgbias-ctl0 = <0x00000008>; nvidia,emc-auto-cal-config = <0xa1430000>; nvidia,emc-auto-cal-config2 = <0x00000000>; nvidia,emc-auto-cal-config3 = <0x00000000>; - nvidia,emc-mode-reset = <0x80001221>; + nvidia,emc-auto-cal-interval = <0x001fffff>; + nvidia,emc-bgbias-ctl0 = <0x00000008>; + nvidia,emc-cfg = <0x73240000>; + nvidia,emc-cfg-2 = <0x000008c5>; + nvidia,emc-ctt-term-ctrl = <0x00000802>; nvidia,emc-mode-1 = <0x80100003>; nvidia,emc-mode-2 = <0x80200008>; nvidia,emc-mode-4 = <0x00000000>; + nvidia,emc-mode-reset = <0x80001221>; + nvidia,emc-mrs-wait-cnt = <0x000e000e>; + nvidia,emc-sel-dpd-ctrl = <0x00040128>; + nvidia,emc-xm2dqspadctrl2 = <0x0130b118>; + nvidia,emc-zcal-cnt-long = <0x00000042>; + nvidia,emc-zcal-interval = <0x00000000>; nvidia,emc-configuration = < 0x00000000 /* EMC_RC */ diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt index 19f5508a7569..4a9145ef15d6 100644 --- a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt +++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt @@ -124,7 +124,7 @@ not every application needs SDIO irq, e.g. MMC cards. pinctrl-1 = <&mmc1_idle>; pinctrl-2 = <&mmc1_sleep>; ... - interrupts-extended = <&intc 64 &gpio2 28 GPIO_ACTIVE_LOW>; + interrupts-extended = <&intc 64 &gpio2 28 IRQ_TYPE_LEVEL_LOW>; }; mmc1_idle : pinmux_cirq_pin { diff --git a/Documentation/devicetree/bindings/net/dsa/ocelot.txt b/Documentation/devicetree/bindings/net/dsa/ocelot.txt new file mode 100644 index 000000000000..66a129fea705 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/ocelot.txt @@ -0,0 +1,116 @@ +Microchip Ocelot switch driver family +===================================== + +Felix +----- + +The VSC9959 core is currently the only switch supported by the driver, and is +found in the NXP LS1028A. It is a PCI device, part of the larger ENETC root +complex. As a result, the ethernet-switch node is a sub-node of the PCIe root +complex node and its "reg" property conforms to the parent node bindings: + +* reg: Specifies PCIe Device Number and Function Number of the endpoint device, + in this case for the Ethernet L2Switch it is PF5 (of device 0, bus 0). + +It does not require a "compatible" string. + +The interrupt line is used to signal availability of PTP TX timestamps and for +TSN frame preemption. + +For the external switch ports, depending on board configuration, "phy-mode" and +"phy-handle" are populated by board specific device tree instances. Ports 4 and +5 are fixed as internal ports in the NXP LS1028A instantiation. + +The CPU port property ("ethernet") configures the feature called "NPI port" in +the Ocelot hardware core. The CPU port in Ocelot is a set of queues, which are +connected, in the Node Processor Interface (NPI) mode, to an Ethernet port. +By default, in fsl-ls1028a.dtsi, the NPI port is assigned to the internal +2.5Gbps port@4, but can be moved to the 1Gbps port@5, depending on the specific +use case. Moving the NPI port to an external switch port is hardware possible, +but there is no platform support for the Linux system on the LS1028A chip to +operate as an entire slave DSA chip. NPI functionality (and therefore DSA +tagging) is supported on a single port at a time. + +Any port can be disabled (and in fsl-ls1028a.dtsi, they are indeed all disabled +by default, and should be enabled on a per-board basis). But if any external +switch port is enabled at all, the ENETC PF2 (enetc_port2) should be enabled as +well, regardless of whether it is configured as the DSA master or not. This is +because the Felix PHYLINK implementation accesses the MAC PCS registers, which +in hardware truly belong to the ENETC port #2 and not to Felix. + +Supported PHY interface types (appropriate SerDes protocol setting changes are +needed in the RCW binary): + +* phy_mode = "internal": on ports 4 and 5 +* phy_mode = "sgmii": on ports 0, 1, 2, 3 +* phy_mode = "qsgmii": on ports 0, 1, 2, 3 +* phy_mode = "usxgmii": on ports 0, 1, 2, 3 +* phy_mode = "2500base-x": on ports 0, 1, 2, 3 + +For the rest of the device tree binding definitions, which are standard DSA and +PCI, refer to the following documents: + +Documentation/devicetree/bindings/net/dsa/dsa.txt +Documentation/devicetree/bindings/pci/pci.txt + +Example: + +&soc { + pcie@1f0000000 { /* Integrated Endpoint Root Complex */ + ethernet-switch@0,5 { + reg = <0x000500 0 0 0 0>; + /* IEP INT_B */ + interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* External ports */ + port@0 { + reg = <0>; + label = "swp0"; + }; + + port@1 { + reg = <1>; + label = "swp1"; + }; + + port@2 { + reg = <2>; + label = "swp2"; + }; + + port@3 { + reg = <3>; + label = "swp3"; + }; + + /* Tagging CPU port */ + port@4 { + reg = <4>; + ethernet = <&enetc_port2>; + phy-mode = "internal"; + + fixed-link { + speed = <2500>; + full-duplex; + }; + }; + + /* Non-tagging CPU port */ + port@5 { + reg = <5>; + phy-mode = "internal"; + status = "disabled"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index 5d08d2ffd4eb..50c3397a82bc 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -56,7 +56,6 @@ patternProperties: examples: - | davinci_mdio: mdio@5c030000 { - compatible = "ti,davinci_mdio"; reg = <0x5c030000 0x1000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/ptp/ptp-idt82p33.yaml b/Documentation/devicetree/bindings/ptp/ptp-idt82p33.yaml new file mode 100644 index 000000000000..9bc664f414a1 --- /dev/null +++ b/Documentation/devicetree/bindings/ptp/ptp-idt82p33.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/ptp/ptp-idt82p33.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: IDT 82P33 PTP Clock Device Tree Bindings + +description: | + IDT 82P33XXX Synchronization Management Unit (SMU) based PTP clock + +maintainers: + - Min Li <min.li.xe@renesas.com> + +properties: + compatible: + enum: + - idt,82p33810 + - idt,82p33813 + - idt,82p33814 + - idt,82p33831 + - idt,82p33910 + - idt,82p33913 + - idt,82p33914 + - idt,82p33931 + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + phc@51 { + compatible = "idt,82p33810"; + reg = <0x51>; + }; + }; diff --git a/Documentation/filesystems/zonefs.txt b/Documentation/filesystems/zonefs.txt index 935bf22031ca..d54fa98ac158 100644 --- a/Documentation/filesystems/zonefs.txt +++ b/Documentation/filesystems/zonefs.txt @@ -134,7 +134,7 @@ Sequential zone files can only be written sequentially, starting from the file end, that is, write operations can only be append writes. Zonefs makes no attempt at accepting random writes and will fail any write request that has a start offset not corresponding to the end of the file, or to the end of the last -write issued and still in-flight (for asynchrnous I/O operations). +write issued and still in-flight (for asynchronous I/O operations). Since dirty page writeback by the page cache does not guarantee a sequential write pattern, zonefs prevents buffered writes and writeable shared mappings @@ -142,7 +142,7 @@ on sequential files. Only direct I/O writes are accepted for these files. zonefs relies on the sequential delivery of write I/O requests to the device implemented by the block layer elevator. An elevator implementing the sequential write feature for zoned block device (ELEVATOR_F_ZBD_SEQ_WRITE elevator feature) -must be used. This type of elevator (e.g. mq-deadline) is the set by default +must be used. This type of elevator (e.g. mq-deadline) is set by default for zoned block devices on device initialization. There are no restrictions on the type of I/O used for read operations in @@ -196,7 +196,7 @@ additional conditions that result in I/O errors. may still happen in the case of a partial failure of a very large direct I/O operation split into multiple BIOs/requests or asynchronous I/O operations. If one of the write request within the set of sequential write requests - issued to the device fails, all write requests after queued after it will + issued to the device fails, all write requests queued after it will become unaligned and fail. * Delayed write errors: similarly to regular block devices, if the device side @@ -207,7 +207,7 @@ additional conditions that result in I/O errors. causing all data to be dropped after the sector that caused the error. All I/O errors detected by zonefs are notified to the user with an error code -return for the system call that trigered or detected the error. The recovery +return for the system call that triggered or detected the error. The recovery actions taken by zonefs in response to I/O errors depend on the I/O type (read vs write) and on the reason for the error (bad sector, unaligned writes or zone condition change). @@ -222,7 +222,7 @@ condition change). * A zone condition change to read-only or offline also always triggers zonefs I/O error recovery. -Zonefs minimal I/O error recovery may change a file size and a file access +Zonefs minimal I/O error recovery may change a file size and file access permissions. * File size changes: @@ -237,7 +237,7 @@ permissions. A file size may also be reduced to reflect a delayed write error detected on fsync(): in this case, the amount of data effectively written in the zone may be less than originally indicated by the file inode size. After such I/O - error, zonefs always fixes a file inode size to reflect the amount of data + error, zonefs always fixes the file inode size to reflect the amount of data persistently stored in the file zone. * Access permission changes: @@ -281,11 +281,11 @@ Further notes: permissions to read-only applies to all files. The file system is remounted read-only. * Access permission and file size changes due to the device transitioning zones - to the offline condition are permanent. Remounting or reformating the device + to the offline condition are permanent. Remounting or reformatting the device with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good state. * File access permission changes to read-only due to the device transitioning - zones to the read-only condition are permanent. Remounting or reformating + zones to the read-only condition are permanent. Remounting or reformatting the device will not re-enable file write access. * File access permission changes implied by the remount-ro, zone-ro and zone-offline mount options are temporary for zones in a good condition. @@ -301,13 +301,13 @@ Mount options zonefs define the "errors=<behavior>" mount option to allow the user to specify zonefs behavior in response to I/O errors, inode size inconsistencies or zone -condition chages. The defined behaviors are as follow: +condition changes. The defined behaviors are as follow: * remount-ro (default) * zone-ro * zone-offline * repair -The I/O error actions defined for each behavior is detailed in the previous +The I/O error actions defined for each behavior are detailed in the previous section. Zonefs User Space Tools diff --git a/Documentation/hwmon/xdpe12284.rst b/Documentation/hwmon/xdpe12284.rst index 6b7ae98cc536..67d1f87808e5 100644 --- a/Documentation/hwmon/xdpe12284.rst +++ b/Documentation/hwmon/xdpe12284.rst @@ -24,6 +24,7 @@ This driver implements support for Infineon Multi-phase XDPE122 family dual loop voltage regulators. The family includes XDPE12284 and XDPE12254 devices. The devices from this family complaint with: + - Intel VR13 and VR13HC rev 1.3, IMVP8 rev 1.2 and IMPVP9 rev 1.3 DC-DC converter specification. - Intel SVID rev 1.9. protocol. diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 0e0eb2c8da7d..6bc126a14b3d 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -765,7 +765,7 @@ is not sufficient this sometimes needs to be explicit. Example:: #arch/x86/boot/Makefile - subdir- := compressed/ + subdir- := compressed The above assignment instructs kbuild to descend down in the directory compressed/ when "make clean" is executed. @@ -1379,9 +1379,6 @@ See subsequent chapter for the syntax of the Kbuild file. in arch/$(ARCH)/include/(uapi/)/asm, Kbuild will automatically generate a wrapper of the asm-generic one. - The convention is to list one subdir per line and - preferably in alphabetic order. - 8 Kbuild Variables ================== diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst new file mode 100644 index 000000000000..465a8b251bfe --- /dev/null +++ b/Documentation/networking/bareudp.rst @@ -0,0 +1,52 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================== +Bare UDP Tunnelling Module Documentation +======================================== + +There are various L3 encapsulation standards using UDP being discussed to +leverage the UDP based load balancing capability of different networks. +MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them. + +The Bareudp tunnel module provides a generic L3 encapsulation tunnelling +support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside +a UDP tunnel. + +Special Handling +---------------- +The bareudp device supports special handling for MPLS & IP as they can have +multiple ethertypes. +MPLS procotcol can have ethertypes ETH_P_MPLS_UC (unicast) & ETH_P_MPLS_MC (multicast). +IP protocol can have ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6). +This special handling can be enabled only for ethertypes ETH_P_IP & ETH_P_MPLS_UC +with a flag called multiproto mode. + +Usage +------ + +1) Device creation & deletion + + a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847. + + This creates a bareudp tunnel device which tunnels L3 traffic with ethertype + 0x8847 (MPLS traffic). The destination port of the UDP header will be set to + 6635.The device will listen on UDP port 6635 to receive traffic. + + b) ip link delete bareudp0 + +2) Device creation with multiple proto mode enabled + +There are two ways to create a bareudp device for MPLS & IP with multiproto mode +enabled. + + a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847 multiproto + + b) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls + +3) Device Usage + +The bareudp device could be used along with OVS or flower filter in TC. +The OVS or TC flower layer must set the tunnel information in SKB dst field before +sending packet buffer to the bareudp device for transmission. On reception the +bareudp device extracts and stores the tunnel information in SKB dst field before +passing the packet buffer to the network stack. diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst index f575a49790e8..e9b65035cd47 100644 --- a/Documentation/networking/device_drivers/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst @@ -101,7 +101,7 @@ Enabling the driver and kconfig options **External options** ( Choose if the corresponding mlx5 feature is required ) - CONFIG_PTP_1588_CLOCK: When chosen, mlx5 ptp support will be enabled -- CONFIG_VXLAN: When chosen, mlx5 vxaln support will be enabled. +- CONFIG_VXLAN: When chosen, mlx5 vxlan support will be enabled. - CONFIG_MLXFW: When chosen, mlx5 firmware flashing support will be enabled (via devlink and ethtool). Devlink info diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 47a429bb8658..63350e7332ce 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -238,6 +238,12 @@ be added to the following table: - ``drop`` - Traps NVE packets that the device decided to drop because their overlay source MAC is multicast + * - ``ingress_flow_action_drop`` + - ``drop`` + - Traps packets dropped during processing of ingress flow action drop + * - ``egress_flow_action_drop`` + - ``drop`` + - Traps packets dropped during processing of egress flow action drop Driver-specific Packet Traps ============================ @@ -277,6 +283,9 @@ narrow. The description of these groups must be added to the following table: * - ``tunnel_drops`` - Contains packet traps for packets that were dropped by the device during tunnel encapsulation / decapsulation + * - ``acl_drops`` + - Contains packet traps for packets that were dropped by the device during + ACL processing Testing ======= diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 629a6e69c036..4e4b97f7971a 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -37,6 +37,12 @@ parameters. * ``smfs`` Software managed flow steering. In SMFS mode, the HW steering entities are created and manage through the driver without firmware intervention. + * - ``fdb_large_groups`` + - u32 + - driverinit + - Control the number of large groups (size > 1) in the FDB table. + + * The default value is 15, and the range is between 1 and 1024. The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD`` diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index d07d9855dcd3..3a83cfb66704 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -8,6 +8,7 @@ Contents: netdev-FAQ af_xdp + bareudp batman-adv can can_ucan_protocol diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 1e4735cc0553..256106054c8c 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -487,8 +487,9 @@ phy_register_fixup_for_id():: The stubs set one of the two matching criteria, and set the other one to match anything. -When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module, -unregister fixup and free allocate memory are required. +When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module load +time, the module needs to unregister the fixup and free allocated memory when +it's unloaded. Call one of following function before unloading module:: diff --git a/Documentation/networking/sfp-phylink.rst b/Documentation/networking/sfp-phylink.rst index d753a309f9d1..8d7af28cd835 100644 --- a/Documentation/networking/sfp-phylink.rst +++ b/Documentation/networking/sfp-phylink.rst @@ -74,10 +74,13 @@ phylib to the sfp/phylink support. Please send patches to improve this documentation. 1. Optionally split the network driver's phylib update function into - three parts dealing with link-down, link-up and reconfiguring the - MAC settings. This can be done as a separate preparation commit. + two parts dealing with link-down and link-up. This can be done as + a separate preparation commit. - An example of this preparation can be found in git commit fc548b991fb0. + An older example of this preparation can be found in git commit + fc548b991fb0, although this was splitting into three parts; the + link-up part now includes configuring the MAC for the link settings. + Please see :c:func:`mac_link_up` for more information on this. 2. Replace:: @@ -207,6 +210,14 @@ this documentation. using. This is particularly important for in-band negotiation methods such as 1000base-X and SGMII. + The :c:func:`mac_link_up` method is used to inform the MAC that the + link has come up. The call includes the negotiation mode and interface + for reference only. The finalised link parameters are also supplied + (speed, duplex and flow control/pause enablement settings) which + should be used to configure the MAC when the MAC and PCS are not + tightly integrated, or when the settings are not coming from in-band + negotiation. + The :c:func:`mac_config` method is used to update the MAC with the requested state, and must avoid unnecessarily taking the link down when making changes to the MAC configuration. This means the diff --git a/Documentation/sphinx/parallel-wrapper.sh b/Documentation/sphinx/parallel-wrapper.sh index 7daf5133bdd3..e54c44ce117d 100644 --- a/Documentation/sphinx/parallel-wrapper.sh +++ b/Documentation/sphinx/parallel-wrapper.sh @@ -30,4 +30,4 @@ if [ -n "$parallel" ] ; then parallel="-j$parallel" fi -exec "$sphinx" "$parallel" "$@" +exec "$sphinx" $parallel "$@" diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 97a72a53fa4b..ebd383fba939 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4611,35 +4611,38 @@ unpins the VPA pages and releases all the device pages that are used to track the secure pages by hypervisor. 4.122 KVM_S390_NORMAL_RESET +--------------------------- -Capability: KVM_CAP_S390_VCPU_RESETS -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: KVM_CAP_S390_VCPU_RESETS +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the cpu reset definition in the POP (Principles Of Operation). 4.123 KVM_S390_INITIAL_RESET +---------------------------- -Capability: none -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: none +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the initial cpu reset definition in the POP. However, the cpu is not put into ESA mode. This reset is a superset of the normal reset. 4.124 KVM_S390_CLEAR_RESET +-------------------------- -Capability: KVM_CAP_S390_VCPU_RESETS -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: KVM_CAP_S390_VCPU_RESETS +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the clear cpu reset definition in the POP. However, the cpu is not put diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index a8de2fbc1caa..265d9e9a093b 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -19,7 +19,6 @@ x86-specific Documentation tlb mtrr pat - intel_mpx intel-iommu intel_txt amd-memory-encryption diff --git a/MAINTAINERS b/MAINTAINERS index 2af5fa73155e..8f27f40d22bb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3649,6 +3649,7 @@ F: sound/pci/oxygen/ C-SKY ARCHITECTURE M: Guo Ren <guoren@kernel.org> +L: linux-csky@vger.kernel.org T: git https://github.com/c-sky/csky-linux.git S: Supported F: arch/csky/ @@ -11114,14 +11115,12 @@ S: Maintained F: drivers/usb/image/microtek.* MIPS -M: Ralf Baechle <ralf@linux-mips.org> -M: Paul Burton <paulburton@kernel.org> +M: Thomas Bogendoerfer <tsbogend@alpha.franken.de> L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/ -T: git git://git.linux-mips.org/pub/scm/ralf/linux.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git Q: http://patchwork.linux-mips.org/project/linux-mips/list/ -S: Supported +S: Maintained F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -68,6 +68,7 @@ unexport GREP_OPTIONS # # If KBUILD_VERBOSE equals 0 then the above command will be hidden. # If KBUILD_VERBOSE equals 1 then the above command is displayed. +# If KBUILD_VERBOSE equals 2 then give the reason why each target is rebuilt. # # To put more focus on warnings, be less verbose as default # Use 'make V=1' to see the full commands @@ -1238,7 +1239,7 @@ ifneq ($(dtstree),) %.dtb: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ -PHONY += dtbs dtbs_install dt_binding_check +PHONY += dtbs dtbs_install dtbs_check dtbs dtbs_check: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) @@ -1258,6 +1259,7 @@ PHONY += scripts_dtc scripts_dtc: scripts_basic $(Q)$(MAKE) $(build)=scripts/dtc +PHONY += dt_binding_check dt_binding_check: scripts_dtc $(Q)$(MAKE) $(build)=Documentation/devicetree/bindings diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index d429f7701c36..5d10051c3e62 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -6,7 +6,7 @@ #ifdef CONFIG_ARM64_LSE_ATOMICS -#define __LSE_PREAMBLE ".arch armv8-a+lse\n" +#define __LSE_PREAMBLE ".arch_extension lse\n" #include <linux/compiler_types.h> #include <linux/export.h> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a4f9ca5479b0..4d94676e5a8b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -213,7 +213,7 @@ static inline unsigned long kaslr_offset(void) ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #define untagged_addr(addr) ({ \ - u64 __addr = (__force u64)addr; \ + u64 __addr = (__force u64)(addr); \ __addr &= __untagged_addr(__addr); \ (__force __typeof__(addr))__addr; \ }) diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index da09c884cc30..047427f71d83 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -9,7 +9,6 @@ config CSKY select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2 select COMMON_CLK select CLKSRC_MMIO - select CLKSRC_OF select CSKY_MPINTC if CPU_CK860 select CSKY_MP_TIMER if CPU_CK860 select CSKY_APB_INTC @@ -37,6 +36,7 @@ config CSKY select GX6605S_TIMER if CPU_CK610 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_AUDITSYSCALL + select HAVE_COPY_THREAD_TLS select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER @@ -47,8 +47,8 @@ config CSKY select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS + select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES @@ -59,6 +59,11 @@ config CSKY select TIMER_OF select USB_ARCH_HAS_EHCI select USB_ARCH_HAS_OHCI + select GENERIC_PCI_IOMAP + select HAVE_PCI + select PCI_DOMAINS_GENERIC if PCI + select PCI_SYSCALL if PCI + select PCI_MSI if PCI config CPU_HAS_CACHEV2 bool @@ -75,7 +80,7 @@ config CPU_HAS_TLBI config CPU_HAS_LDSTEX bool help - For SMP, CPU needs "ldex&stex" instrcutions to atomic operations. + For SMP, CPU needs "ldex&stex" instructions for atomic operations. config CPU_NEED_TLBSYNC bool @@ -188,6 +193,40 @@ config CPU_PM_STOP bool "stop" endchoice +menuconfig HAVE_TCM + bool "Tightly-Coupled/Sram Memory" + select GENERIC_ALLOCATOR + help + The implementation are not only used by TCM (Tightly-Coupled Meory) + but also used by sram on SOC bus. It follow existed linux tcm + software interface, so that old tcm application codes could be + re-used directly. + +if HAVE_TCM +config ITCM_RAM_BASE + hex "ITCM ram base" + default 0xffffffff + +config ITCM_NR_PAGES + int "Page count of ITCM size: NR*4KB" + range 1 256 + default 32 + +config HAVE_DTCM + bool "DTCM Support" + +config DTCM_RAM_BASE + hex "DTCM ram base" + depends on HAVE_DTCM + default 0xffffffff + +config DTCM_NR_PAGES + int "Page count of DTCM size: NR*4KB" + depends on HAVE_DTCM + range 1 256 + default 32 +endif + config CPU_HAS_VDSP bool "CPU has VDSP coprocessor" depends on CPU_HAS_FPU && CPU_HAS_FPUV2 @@ -196,6 +235,10 @@ config CPU_HAS_FPU bool "CPU has FPU coprocessor" depends on CPU_CK807 || CPU_CK810 || CPU_CK860 +config CPU_HAS_ICACHE_INS + bool "CPU has Icache invalidate instructions" + depends on CPU_HAS_CACHEV2 + config CPU_HAS_TEE bool "CPU has Trusted Execution Environment" depends on CPU_CK810 @@ -235,4 +278,6 @@ config HOTPLUG_CPU Say N if you want to disable CPU hotplug. endmenu +source "arch/csky/Kconfig.platforms" + source "kernel/Kconfig.hz" diff --git a/arch/csky/Kconfig.platforms b/arch/csky/Kconfig.platforms new file mode 100644 index 000000000000..639e17f4eacb --- /dev/null +++ b/arch/csky/Kconfig.platforms @@ -0,0 +1,9 @@ +menu "Platform drivers selection" + +config ARCH_CSKY_DW_APB_ICTL + bool "Select dw-apb interrupt controller" + select DW_APB_ICTL + default y + help + This enables support for snps dw-apb-ictl +endmenu diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 79ef9e8c1afd..d3e04208d53c 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -48,9 +48,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, u #define flush_icache_page(vma, page) do {} while (0); #define flush_icache_range(start, end) cache_wbinv_range(start, end) - -#define flush_icache_user_range(vma,page,addr,len) \ - flush_dcache_page(page) +#define flush_icache_mm_range(mm, start, end) cache_wbinv_range(start, end) +#define flush_icache_deferred(mm) do {} while (0); #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ do { \ diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h index 7ab78bd0f3b1..f35a9f3315ee 100644 --- a/arch/csky/abiv1/inc/abi/entry.h +++ b/arch/csky/abiv1/inc/abi/entry.h @@ -16,14 +16,16 @@ #define LSAVE_A4 40 #define LSAVE_A5 44 +#define usp ss1 + .macro USPTOKSP - mtcr sp, ss1 + mtcr sp, usp mfcr sp, ss0 .endm .macro KSPTOUSP mtcr sp, ss0 - mfcr sp, ss1 + mfcr sp, usp .endm .macro SAVE_ALL epc_inc @@ -45,7 +47,13 @@ add lr, r13 stw lr, (sp, 8) + mov lr, sp + addi lr, 32 + addi lr, 32 + addi lr, 16 + bt 2f mfcr lr, ss1 +2: stw lr, (sp, 16) stw a0, (sp, 20) @@ -79,9 +87,10 @@ ldw a0, (sp, 12) mtcr a0, epsr btsti a0, 31 + bt 1f ldw a0, (sp, 16) mtcr a0, ss1 - +1: ldw a0, (sp, 24) ldw a1, (sp, 28) ldw a2, (sp, 32) @@ -102,9 +111,9 @@ addi sp, 32 addi sp, 8 - bt 1f + bt 2f KSPTOUSP -1: +2: rte .endm diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c index 5bb887b275e1..790f1ebfba44 100644 --- a/arch/csky/abiv2/cacheflush.c +++ b/arch/csky/abiv2/cacheflush.c @@ -6,46 +6,80 @@ #include <linux/mm.h> #include <asm/cache.h> -void flush_icache_page(struct vm_area_struct *vma, struct page *page) +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, + pte_t *pte) { - unsigned long start; + unsigned long addr; + struct page *page; - start = (unsigned long) kmap_atomic(page); + page = pfn_to_page(pte_pfn(*pte)); + if (page == ZERO_PAGE(0)) + return; - cache_wbinv_range(start, start + PAGE_SIZE); + if (test_and_set_bit(PG_dcache_clean, &page->flags)) + return; - kunmap_atomic((void *)start); -} + addr = (unsigned long) kmap_atomic(page); -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long vaddr, int len) -{ - unsigned long kaddr; + dcache_wb_range(addr, addr + PAGE_SIZE); - kaddr = (unsigned long) kmap_atomic(page) + (vaddr & ~PAGE_MASK); + if (vma->vm_flags & VM_EXEC) + icache_inv_range(addr, addr + PAGE_SIZE); + + kunmap_atomic((void *) addr); +} - cache_wbinv_range(kaddr, kaddr + len); +void flush_icache_deferred(struct mm_struct *mm) +{ + unsigned int cpu = smp_processor_id(); + cpumask_t *mask = &mm->context.icache_stale_mask; - kunmap_atomic((void *)kaddr); + if (cpumask_test_cpu(cpu, mask)) { + cpumask_clear_cpu(cpu, mask); + /* + * Ensure the remote hart's writes are visible to this hart. + * This pairs with a barrier in flush_icache_mm. + */ + smp_mb(); + local_icache_inv_all(NULL); + } } -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, - pte_t *pte) +void flush_icache_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long addr, pfn; - struct page *page; + unsigned int cpu; + cpumask_t others, *mask; - pfn = pte_pfn(*pte); - if (unlikely(!pfn_valid(pfn))) - return; + preempt_disable(); - page = pfn_to_page(pfn); - if (page == ZERO_PAGE(0)) +#ifdef CONFIG_CPU_HAS_ICACHE_INS + if (mm == current->mm) { + icache_inv_range(start, end); + preempt_enable(); return; + } +#endif - addr = (unsigned long) kmap_atomic(page); + /* Mark every hart's icache as needing a flush for this MM. */ + mask = &mm->context.icache_stale_mask; + cpumask_setall(mask); - cache_wbinv_range(addr, addr + PAGE_SIZE); + /* Flush this hart's I$ now, and mark it as flushed. */ + cpu = smp_processor_id(); + cpumask_clear_cpu(cpu, mask); + local_icache_inv_all(NULL); - kunmap_atomic((void *) addr); + /* + * Flush the I$ of other harts concurrently executing, and mark them as + * flushed. + */ + cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu)); + + if (mm != current->active_mm || !cpumask_empty(&others)) { + on_each_cpu_mask(&others, local_icache_inv_all, NULL, 1); + cpumask_clear(mask); + } + + preempt_enable(); } diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index b8db5e0b2fe3..a565e00c3f70 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -13,24 +13,27 @@ #define flush_cache_all() do { } while (0) #define flush_cache_mm(mm) do { } while (0) #define flush_cache_dup_mm(mm) do { } while (0) +#define flush_cache_range(vma, start, end) do { } while (0) +#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define flush_cache_range(vma, start, end) \ - do { \ - if (vma->vm_flags & VM_EXEC) \ - icache_inv_all(); \ - } while (0) +#define PG_dcache_clean PG_arch_1 + +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 +static inline void flush_dcache_page(struct page *page) +{ + if (test_bit(PG_dcache_clean, &page->flags)) + clear_bit(PG_dcache_clean, &page->flags); +} -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) +#define flush_icache_page(vma, page) do { } while (0) #define flush_icache_range(start, end) cache_wbinv_range(start, end) -void flush_icache_page(struct vm_area_struct *vma, struct page *page); -void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, - unsigned long vaddr, int len); +void flush_icache_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end); +void flush_icache_deferred(struct mm_struct *mm); #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) @@ -38,7 +41,13 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ - cache_wbinv_range((unsigned long)dst, (unsigned long)dst + len); \ + if (vma->vm_flags & VM_EXEC) { \ + dcache_wb_range((unsigned long)dst, \ + (unsigned long)dst + len); \ + flush_icache_mm_range(current->mm, \ + (unsigned long)dst, \ + (unsigned long)dst + len); \ + } \ } while (0) #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h index 9897a16b45e5..94a7a58765df 100644 --- a/arch/csky/abiv2/inc/abi/entry.h +++ b/arch/csky/abiv2/inc/abi/entry.h @@ -31,7 +31,13 @@ mfcr lr, epsr stw lr, (sp, 12) + btsti lr, 31 + bf 1f + addi lr, sp, 152 + br 2f +1: mfcr lr, usp +2: stw lr, (sp, 16) stw a0, (sp, 20) @@ -64,8 +70,10 @@ mtcr a0, epc ldw a0, (sp, 12) mtcr a0, epsr + btsti a0, 31 ldw a0, (sp, 16) mtcr a0, usp + mtcr a0, ss0 #ifdef CONFIG_CPU_HAS_HILO ldw a0, (sp, 140) @@ -86,6 +94,9 @@ addi sp, 40 ldm r16-r30, (sp) addi sp, 72 + bf 1f + mfcr sp, ss0 +1: rte .endm diff --git a/arch/csky/configs/defconfig b/arch/csky/configs/defconfig index 7ef42895dfb0..af722e4dfb47 100644 --- a/arch/csky/configs/defconfig +++ b/arch/csky/configs/defconfig @@ -10,9 +10,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_CPU_CK807=y -CONFIG_CPU_HAS_FPU=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -27,10 +24,7 @@ CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y -CONFIG_TTY_PRINTK=y # CONFIG_VGA_CONSOLE is not set -CONFIG_CSKY_MPTIMER=y -CONFIG_GX6605S_TIMER=y CONFIG_PM_DEVFREQ=y CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y CONFIG_DEVFREQ_GOV_PERFORMANCE=y @@ -56,6 +50,4 @@ CONFIG_CRAMFS=y CONFIG_ROMFS_FS=y CONFIG_NFS_FS=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index bc15a26c782f..4130e3eaa766 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -28,7 +28,6 @@ generic-y += local64.h generic-y += mm-arch-hooks.h generic-y += mmiowb.h generic-y += module.h -generic-y += pci.h generic-y += percpu.h generic-y += preempt.h generic-y += qrwlock.h diff --git a/arch/csky/include/asm/cache.h b/arch/csky/include/asm/cache.h index 1d5fc2f78fd7..4b5c09bf1d25 100644 --- a/arch/csky/include/asm/cache.h +++ b/arch/csky/include/asm/cache.h @@ -16,6 +16,7 @@ void dcache_wb_line(unsigned long start); void icache_inv_range(unsigned long start, unsigned long end); void icache_inv_all(void); +void local_icache_inv_all(void *priv); void dcache_wb_range(unsigned long start, unsigned long end); void dcache_wbinv_all(void); diff --git a/arch/csky/include/asm/cacheflush.h b/arch/csky/include/asm/cacheflush.h index a96da67261ae..f0b8f25429a2 100644 --- a/arch/csky/include/asm/cacheflush.h +++ b/arch/csky/include/asm/cacheflush.h @@ -4,6 +4,7 @@ #ifndef __ASM_CSKY_CACHEFLUSH_H #define __ASM_CSKY_CACHEFLUSH_H +#include <linux/mm.h> #include <abi/cacheflush.h> #endif /* __ASM_CSKY_CACHEFLUSH_H */ diff --git a/arch/csky/include/asm/fixmap.h b/arch/csky/include/asm/fixmap.h index 380ff0a307df..81f9477d5330 100644 --- a/arch/csky/include/asm/fixmap.h +++ b/arch/csky/include/asm/fixmap.h @@ -5,12 +5,16 @@ #define __ASM_CSKY_FIXMAP_H #include <asm/page.h> +#include <asm/memory.h> #ifdef CONFIG_HIGHMEM #include <linux/threads.h> #include <asm/kmap_types.h> #endif enum fixed_addresses { +#ifdef CONFIG_HAVE_TCM + FIX_TCM = TCM_NR_PAGES, +#endif #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1, @@ -18,10 +22,13 @@ enum fixed_addresses { __end_of_fixed_addresses }; -#define FIXADDR_TOP 0xffffc000 #define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) #include <asm-generic/fixmap.h> +extern void fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base); +extern void __init fixaddr_init(void); + #endif /* __ASM_CSKY_FIXMAP_H */ diff --git a/arch/csky/include/asm/memory.h b/arch/csky/include/asm/memory.h new file mode 100644 index 000000000000..a65c6759f537 --- /dev/null +++ b/arch/csky/include/asm/memory.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_MEMORY_H +#define __ASM_CSKY_MEMORY_H + +#include <linux/compiler.h> +#include <linux/const.h> +#include <linux/types.h> +#include <linux/sizes.h> + +#define FIXADDR_TOP _AC(0xffffc000, UL) +#define PKMAP_BASE _AC(0xff800000, UL) +#define VMALLOC_START _AC(0xc0008000, UL) +#define VMALLOC_END (PKMAP_BASE - (PAGE_SIZE * 2)) + +#ifdef CONFIG_HAVE_TCM +#ifdef CONFIG_HAVE_DTCM +#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES + CONFIG_DTCM_NR_PAGES) +#else +#define TCM_NR_PAGES (CONFIG_ITCM_NR_PAGES) +#endif +#define FIXADDR_TCM _AC(FIXADDR_TOP - (TCM_NR_PAGES * PAGE_SIZE), UL) +#endif + +#endif diff --git a/arch/csky/include/asm/mmu.h b/arch/csky/include/asm/mmu.h index b382a14ea4ec..26fbb1d15df0 100644 --- a/arch/csky/include/asm/mmu.h +++ b/arch/csky/include/asm/mmu.h @@ -7,6 +7,7 @@ typedef struct { atomic64_t asid; void *vdso; + cpumask_t icache_stale_mask; } mm_context_t; #endif /* __ASM_CSKY_MMU_H */ diff --git a/arch/csky/include/asm/mmu_context.h b/arch/csky/include/asm/mmu_context.h index 0285b0ad18b6..abdf1f1cb6ec 100644 --- a/arch/csky/include/asm/mmu_context.h +++ b/arch/csky/include/asm/mmu_context.h @@ -43,5 +43,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, TLBMISS_HANDLER_SETUP_PGD(next->pgd); write_mmu_entryhi(next->context.asid.counter); + + flush_icache_deferred(next); } #endif /* __ASM_CSKY_MMU_CONTEXT_H */ diff --git a/arch/csky/include/asm/pci.h b/arch/csky/include/asm/pci.h new file mode 100644 index 000000000000..ebc765b1f78b --- /dev/null +++ b/arch/csky/include/asm/pci.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_CSKY_PCI_H +#define __ASM_CSKY_PCI_H + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> + +#include <asm/io.h> + +#define PCIBIOS_MIN_IO 0 +#define PCIBIOS_MIN_MEM 0 + +/* C-SKY shim does not initialize PCI bus */ +#define pcibios_assign_all_busses() 1 + +extern int isa_dma_bridge_buggy; + +#ifdef CONFIG_PCI +static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) +{ + /* no legacy IRQ on csky */ + return -ENODEV; +} + +static inline int pci_proc_domain(struct pci_bus *bus) +{ + /* always show the domain in /proc */ + return 1; +} +#endif /* CONFIG_PCI */ + +#endif /* __ASM_CSKY_PCI_H */ diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index 4b2a41e15f2e..9b7764cb7645 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -5,6 +5,7 @@ #define __ASM_CSKY_PGTABLE_H #include <asm/fixmap.h> +#include <asm/memory.h> #include <asm/addrspace.h> #include <abi/pgtable-bits.h> #include <asm-generic/pgtable-nopmd.h> @@ -16,11 +17,6 @@ #define USER_PTRS_PER_PGD (0x80000000UL/PGDIR_SIZE) #define FIRST_USER_ADDRESS 0UL -#define PKMAP_BASE (0xff800000) - -#define VMALLOC_START (0xc0008000) -#define VMALLOC_END (PKMAP_BASE - 2*PAGE_SIZE) - /* * C-SKY is two-level paging structure: */ diff --git a/arch/csky/include/asm/stackprotector.h b/arch/csky/include/asm/stackprotector.h new file mode 100644 index 000000000000..d7cd4e51edd9 --- /dev/null +++ b/arch/csky/include/asm/stackprotector.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_STACKPROTECTOR_H +#define _ASM_STACKPROTECTOR_H 1 + +#include <linux/random.h> +#include <linux/version.h> + +extern unsigned long __stack_chk_guard; + +/* + * Initialize the stackprotector canary value. + * + * NOTE: this must only be called from functions that never return, + * and it must always be inlined. + */ +static __always_inline void boot_init_stack_canary(void) +{ + unsigned long canary; + + /* Try to get a semi random initial value. */ + get_random_bytes(&canary, sizeof(canary)); + canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; + + current->stack_canary = canary; + __stack_chk_guard = current->stack_canary; +} + +#endif /* __ASM_SH_STACKPROTECTOR_H */ diff --git a/arch/csky/include/asm/tcm.h b/arch/csky/include/asm/tcm.h new file mode 100644 index 000000000000..2b135cefb73f --- /dev/null +++ b/arch/csky/include/asm/tcm.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_CSKY_TCM_H +#define __ASM_CSKY_TCM_H + +#ifndef CONFIG_HAVE_TCM +#error "You should not be including tcm.h unless you have a TCM!" +#endif + +#include <linux/compiler.h> + +/* Tag variables with this */ +#define __tcmdata __section(.tcm.data) +/* Tag constants with this */ +#define __tcmconst __section(.tcm.rodata) +/* Tag functions inside TCM called from outside TCM with this */ +#define __tcmfunc __section(.tcm.text) noinline +/* Tag function inside TCM called from inside TCM with this */ +#define __tcmlocalfunc __section(.tcm.text) + +void *tcm_alloc(size_t len); +void tcm_free(void *addr, size_t len); + +#endif diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index 211c983c7282..ba4018929733 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -1,7 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #include <asm-generic/unistd.h> diff --git a/arch/csky/kernel/atomic.S b/arch/csky/kernel/atomic.S index 5b84f11485ae..3821ef9b7567 100644 --- a/arch/csky/kernel/atomic.S +++ b/arch/csky/kernel/atomic.S @@ -17,10 +17,12 @@ ENTRY(csky_cmpxchg) mfcr a3, epc addi a3, TRAP0_SIZE - subi sp, 8 + subi sp, 16 stw a3, (sp, 0) mfcr a3, epsr stw a3, (sp, 4) + mfcr a3, usp + stw a3, (sp, 8) psrset ee #ifdef CONFIG_CPU_HAS_LDSTEX @@ -47,7 +49,9 @@ ENTRY(csky_cmpxchg) mtcr a3, epc ldw a3, (sp, 4) mtcr a3, epsr - addi sp, 8 + ldw a3, (sp, 8) + mtcr a3, usp + addi sp, 16 KSPTOUSP rte END(csky_cmpxchg) diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f320d9248a22..f7b231ca269a 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -16,6 +16,12 @@ struct cpuinfo_csky cpu_data[NR_CPUS]; +#ifdef CONFIG_STACKPROTECTOR +#include <linux/stackprotector.h> +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); @@ -34,10 +40,11 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sw->r15; } -int copy_thread(unsigned long clone_flags, +int copy_thread_tls(unsigned long clone_flags, unsigned long usp, unsigned long kthread_arg, - struct task_struct *p) + struct task_struct *p, + unsigned long tls) { struct switch_stack *childstack; struct pt_regs *childregs = task_pt_regs(p); @@ -64,7 +71,7 @@ int copy_thread(unsigned long clone_flags, childregs->usp = usp; if (clone_flags & CLONE_SETTLS) task_thread_info(p)->tp_value = childregs->tls - = childregs->regs[0]; + = tls; childregs->a0 = 0; childstack->r15 = (unsigned long) ret_from_fork; diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index 52eaf31ba27f..3821e55742f4 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -47,9 +47,6 @@ static void __init csky_memblock_init(void) signed long size; memblock_reserve(__pa(_stext), _end - _stext); -#ifdef CONFIG_BLK_DEV_INITRD - memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); -#endif early_init_fdt_reserve_self(); early_init_fdt_scan_reserved_mem(); @@ -133,6 +130,8 @@ void __init setup_arch(char **cmdline_p) sparse_init(); + fixaddr_init(); + #ifdef CONFIG_HIGHMEM kmap_init(); #endif diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index b753d382e4ce..0bb0954d5570 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -120,7 +120,7 @@ void __init setup_smp_ipi(void) int rc; if (ipi_irq == 0) - panic("%s IRQ mapping failed\n", __func__); + return; rc = request_percpu_irq(ipi_irq, handle_ipi, "IPI Interrupt", &ipi_dummy_dev); diff --git a/arch/csky/kernel/time.c b/arch/csky/kernel/time.c index b5fc9447d93f..52379d866fe4 100644 --- a/arch/csky/kernel/time.c +++ b/arch/csky/kernel/time.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. -#include <linux/clk-provider.h> #include <linux/clocksource.h> +#include <linux/of_clk.h> void __init time_init(void) { diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S index 2ff37beaf2bf..f05b413df328 100644 --- a/arch/csky/kernel/vmlinux.lds.S +++ b/arch/csky/kernel/vmlinux.lds.S @@ -2,6 +2,7 @@ #include <asm/vmlinux.lds.h> #include <asm/page.h> +#include <asm/memory.h> OUTPUT_ARCH(csky) ENTRY(_start) @@ -53,6 +54,54 @@ SECTIONS RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) _edata = .; +#ifdef CONFIG_HAVE_TCM + .tcm_start : { + . = ALIGN(PAGE_SIZE); + __tcm_start = .; + } + + .text_data_tcm FIXADDR_TCM : AT(__tcm_start) + { + . = ALIGN(4); + __stcm_text_data = .; + *(.tcm.text) + *(.tcm.rodata) +#ifndef CONFIG_HAVE_DTCM + *(.tcm.data) +#endif + . = ALIGN(4); + __etcm_text_data = .; + } + + . = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_data_tcm); + +#ifdef CONFIG_HAVE_DTCM + #define ITCM_SIZE CONFIG_ITCM_NR_PAGES * PAGE_SIZE + + .dtcm_start : { + __dtcm_start = .; + } + + .data_tcm FIXADDR_TCM + ITCM_SIZE : AT(__dtcm_start) + { + . = ALIGN(4); + __stcm_data = .; + *(.tcm.data) + . = ALIGN(4); + __etcm_data = .; + } + + . = ADDR(.dtcm_start) + SIZEOF(.data_tcm); + + .tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_tcm)) { +#else + .tcm_end : AT(ADDR(.tcm_start) + SIZEOF(.text_data_tcm)) { +#endif + . = ALIGN(PAGE_SIZE); + __tcm_end = .; + } +#endif + EXCEPTION_TABLE(L1_CACHE_BYTES) BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES) VBR_BASE diff --git a/arch/csky/mm/Makefile b/arch/csky/mm/Makefile index c94ef6481098..6e7696e55f71 100644 --- a/arch/csky/mm/Makefile +++ b/arch/csky/mm/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only ifeq ($(CONFIG_CPU_HAS_CACHEV2),y) obj-y += cachev2.o +CFLAGS_REMOVE_cachev2.o = $(CC_FLAGS_FTRACE) else obj-y += cachev1.o +CFLAGS_REMOVE_cachev1.o = $(CC_FLAGS_FTRACE) endif obj-y += dma-mapping.o @@ -14,3 +16,4 @@ obj-y += syscache.o obj-y += tlb.o obj-y += asid.o obj-y += context.o +obj-$(CONFIG_HAVE_TCM) += tcm.o diff --git a/arch/csky/mm/cachev1.c b/arch/csky/mm/cachev1.c index 494ec912abff..5a5a9804a0e3 100644 --- a/arch/csky/mm/cachev1.c +++ b/arch/csky/mm/cachev1.c @@ -94,6 +94,11 @@ void icache_inv_all(void) cache_op_all(INS_CACHE|CACHE_INV, 0); } +void local_icache_inv_all(void *priv) +{ + cache_op_all(INS_CACHE|CACHE_INV, 0); +} + void dcache_wb_range(unsigned long start, unsigned long end) { cache_op_range(start, end, DATA_CACHE|CACHE_CLR, 0); diff --git a/arch/csky/mm/cachev2.c b/arch/csky/mm/cachev2.c index b61be6518e21..bc419f8039d3 100644 --- a/arch/csky/mm/cachev2.c +++ b/arch/csky/mm/cachev2.c @@ -3,15 +3,25 @@ #include <linux/spinlock.h> #include <linux/smp.h> +#include <linux/mm.h> #include <asm/cache.h> #include <asm/barrier.h> -inline void dcache_wb_line(unsigned long start) +#define INS_CACHE (1 << 0) +#define CACHE_INV (1 << 4) + +void local_icache_inv_all(void *priv) { - asm volatile("dcache.cval1 %0\n"::"r"(start):"memory"); + mtcr("cr17", INS_CACHE|CACHE_INV); sync_is(); } +void icache_inv_all(void) +{ + on_each_cpu(local_icache_inv_all, NULL, 1); +} + +#ifdef CONFIG_CPU_HAS_ICACHE_INS void icache_inv_range(unsigned long start, unsigned long end) { unsigned long i = start & ~(L1_CACHE_BYTES - 1); @@ -20,43 +30,32 @@ void icache_inv_range(unsigned long start, unsigned long end) asm volatile("icache.iva %0\n"::"r"(i):"memory"); sync_is(); } - -void icache_inv_all(void) +#else +void icache_inv_range(unsigned long start, unsigned long end) { - asm volatile("icache.ialls\n":::"memory"); - sync_is(); + icache_inv_all(); } +#endif -void dcache_wb_range(unsigned long start, unsigned long end) +inline void dcache_wb_line(unsigned long start) { - unsigned long i = start & ~(L1_CACHE_BYTES - 1); - - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); + asm volatile("dcache.cval1 %0\n"::"r"(start):"memory"); sync_is(); } -void dcache_inv_range(unsigned long start, unsigned long end) +void dcache_wb_range(unsigned long start, unsigned long end) { unsigned long i = start & ~(L1_CACHE_BYTES - 1); for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.civa %0\n"::"r"(i):"memory"); + asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); sync_is(); } void cache_wbinv_range(unsigned long start, unsigned long end) { - unsigned long i = start & ~(L1_CACHE_BYTES - 1); - - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("dcache.cval1 %0\n"::"r"(i):"memory"); - sync_is(); - - i = start & ~(L1_CACHE_BYTES - 1); - for (; i < end; i += L1_CACHE_BYTES) - asm volatile("icache.iva %0\n"::"r"(i):"memory"); - sync_is(); + dcache_wb_range(start, end); + icache_inv_range(start, end); } EXPORT_SYMBOL(cache_wbinv_range); diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c index 3317b774f6dc..813129145f3d 100644 --- a/arch/csky/mm/highmem.c +++ b/arch/csky/mm/highmem.c @@ -117,85 +117,29 @@ struct page *kmap_atomic_to_page(void *ptr) return pte_page(*pte); } -static void __init fixrange_init(unsigned long start, unsigned long end, - pgd_t *pgd_base) +static void __init kmap_pages_init(void) { -#ifdef CONFIG_HIGHMEM - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int i, j, k; unsigned long vaddr; - - vaddr = start; - i = __pgd_offset(vaddr); - j = __pud_offset(vaddr); - k = __pmd_offset(vaddr); - pgd = pgd_base + i; - - for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) { - pud = (pud_t *)pgd; - for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) { - pmd = (pmd_t *)pud; - for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { - if (pmd_none(*pmd)) { - pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); - if (!pte) - panic("%s: Failed to allocate %lu bytes align=%lx\n", - __func__, PAGE_SIZE, - PAGE_SIZE); - - set_pmd(pmd, __pmd(__pa(pte))); - BUG_ON(pte != pte_offset_kernel(pmd, 0)); - } - vaddr += PMD_SIZE; - } - k = 0; - } - j = 0; - } -#endif -} - -void __init fixaddr_kmap_pages_init(void) -{ - unsigned long vaddr; - pgd_t *pgd_base; -#ifdef CONFIG_HIGHMEM pgd_t *pgd; pmd_t *pmd; pud_t *pud; pte_t *pte; -#endif - pgd_base = swapper_pg_dir; - - /* - * Fixed mappings: - */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, 0, pgd_base); - -#ifdef CONFIG_HIGHMEM - /* - * Permanent kmaps: - */ + vaddr = PKMAP_BASE; - fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); + fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir); pgd = swapper_pg_dir + __pgd_offset(vaddr); pud = (pud_t *)pgd; pmd = pmd_offset(pud, vaddr); pte = pte_offset_kernel(pmd, vaddr); pkmap_page_table = pte; -#endif } void __init kmap_init(void) { unsigned long vaddr; - fixaddr_kmap_pages_init(); + kmap_pages_init(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN); diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index d4c2292ea46b..cb64d8647a78 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -19,6 +19,7 @@ #include <linux/swap.h> #include <linux/proc_fs.h> #include <linux/pfn.h> +#include <linux/initrd.h> #include <asm/setup.h> #include <asm/cachectl.h> @@ -31,10 +32,50 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; +EXPORT_SYMBOL(invalid_pte_table); unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); +#ifdef CONFIG_BLK_DEV_INITRD +static void __init setup_initrd(void) +{ + unsigned long size; + + if (initrd_start >= initrd_end) { + pr_err("initrd not found or empty"); + goto disable; + } + + if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { + pr_err("initrd extends beyond end of memory"); + goto disable; + } + + size = initrd_end - initrd_start; + + if (memblock_is_region_reserved(__pa(initrd_start), size)) { + pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region", + __pa(initrd_start), size); + goto disable; + } + + memblock_reserve(__pa(initrd_start), size); + + pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", + (void *)(initrd_start), size); + + initrd_below_start_ok = 1; + + return; + +disable: + initrd_start = initrd_end = 0; + + pr_err(" - disabling initrd\n"); +} +#endif + void __init mem_init(void) { #ifdef CONFIG_HIGHMEM @@ -46,6 +87,10 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); +#ifdef CONFIG_BLK_DEV_INITRD + setup_initrd(); +#endif + memblock_free_all(); #ifdef CONFIG_HIGHMEM @@ -101,3 +146,50 @@ void __init pre_mmu_init(void) /* Setup page mask to 4k */ write_mmu_pagemask(0); } + +void __init fixrange_init(unsigned long start, unsigned long end, + pgd_t *pgd_base) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i, j, k; + unsigned long vaddr; + + vaddr = start; + i = __pgd_offset(vaddr); + j = __pud_offset(vaddr); + k = __pmd_offset(vaddr); + pgd = pgd_base + i; + + for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) { + pud = (pud_t *)pgd; + for ( ; (j < PTRS_PER_PUD) && (vaddr != end); pud++, j++) { + pmd = (pmd_t *)pud; + for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { + if (pmd_none(*pmd)) { + pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); + if (!pte) + panic("%s: Failed to allocate %lu bytes align=%lx\n", + __func__, PAGE_SIZE, + PAGE_SIZE); + + set_pmd(pmd, __pmd(__pa(pte))); + BUG_ON(pte != pte_offset_kernel(pmd, 0)); + } + vaddr += PMD_SIZE; + } + k = 0; + } + j = 0; + } +} + +void __init fixaddr_init(void) +{ + unsigned long vaddr; + + vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; + fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir); +} diff --git a/arch/csky/mm/syscache.c b/arch/csky/mm/syscache.c index c4645e4e97f4..ffade2f9a4c8 100644 --- a/arch/csky/mm/syscache.c +++ b/arch/csky/mm/syscache.c @@ -3,7 +3,7 @@ #include <linux/syscalls.h> #include <asm/page.h> -#include <asm/cache.h> +#include <asm/cacheflush.h> #include <asm/cachectl.h> SYSCALL_DEFINE3(cacheflush, @@ -13,17 +13,14 @@ SYSCALL_DEFINE3(cacheflush, { switch (cache) { case ICACHE: - icache_inv_range((unsigned long)addr, - (unsigned long)addr + bytes); - break; + case BCACHE: + flush_icache_mm_range(current->mm, + (unsigned long)addr, + (unsigned long)addr + bytes); case DCACHE: dcache_wb_range((unsigned long)addr, (unsigned long)addr + bytes); break; - case BCACHE: - cache_wbinv_range((unsigned long)addr, - (unsigned long)addr + bytes); - break; default: return -EINVAL; } diff --git a/arch/csky/mm/tcm.c b/arch/csky/mm/tcm.c new file mode 100644 index 000000000000..ddeb36328819 --- /dev/null +++ b/arch/csky/mm/tcm.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/highmem.h> +#include <linux/genalloc.h> +#include <asm/tlbflush.h> +#include <asm/fixmap.h> + +#if (CONFIG_ITCM_RAM_BASE == 0xffffffff) +#error "You should define ITCM_RAM_BASE" +#endif + +#ifdef CONFIG_HAVE_DTCM +#if (CONFIG_DTCM_RAM_BASE == 0xffffffff) +#error "You should define DTCM_RAM_BASE" +#endif + +#if (CONFIG_DTCM_RAM_BASE == CONFIG_ITCM_RAM_BASE) +#error "You should define correct DTCM_RAM_BASE" +#endif +#endif + +extern char __tcm_start, __tcm_end, __dtcm_start; + +static struct gen_pool *tcm_pool; + +static void __init tcm_mapping_init(void) +{ + pte_t *tcm_pte; + unsigned long vaddr, paddr; + int i; + + paddr = CONFIG_ITCM_RAM_BASE; + + if (pfn_valid(PFN_DOWN(CONFIG_ITCM_RAM_BASE))) + goto panic; + +#ifndef CONFIG_HAVE_DTCM + for (i = 0; i < TCM_NR_PAGES; i++) { +#else + for (i = 0; i < CONFIG_ITCM_NR_PAGES; i++) { +#endif + vaddr = __fix_to_virt(FIX_TCM - i); + + tcm_pte = + pte_offset_kernel((pmd_t *)pgd_offset_k(vaddr), vaddr); + + set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL)); + + flush_tlb_one(vaddr); + + paddr = paddr + PAGE_SIZE; + } + +#ifdef CONFIG_HAVE_DTCM + if (pfn_valid(PFN_DOWN(CONFIG_DTCM_RAM_BASE))) + goto panic; + + paddr = CONFIG_DTCM_RAM_BASE; + + for (i = 0; i < CONFIG_DTCM_NR_PAGES; i++) { + vaddr = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES - i); + + tcm_pte = + pte_offset_kernel((pmd_t *) pgd_offset_k(vaddr), vaddr); + + set_pte(tcm_pte, pfn_pte(__phys_to_pfn(paddr), PAGE_KERNEL)); + + flush_tlb_one(vaddr); + + paddr = paddr + PAGE_SIZE; + } +#endif + +#ifndef CONFIG_HAVE_DTCM + memcpy((void *)__fix_to_virt(FIX_TCM), + &__tcm_start, &__tcm_end - &__tcm_start); + + pr_info("%s: mapping tcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE); + + pr_info("%s: __tcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__tcm_start, &__tcm_end - &__tcm_start); +#else + memcpy((void *)__fix_to_virt(FIX_TCM), + &__tcm_start, &__dtcm_start - &__tcm_start); + + pr_info("%s: mapping itcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM), CONFIG_ITCM_RAM_BASE); + + pr_info("%s: __itcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__tcm_start, &__dtcm_start - &__tcm_start); + + memcpy((void *)__fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES), + &__dtcm_start, &__tcm_end - &__dtcm_start); + + pr_info("%s: mapping dtcm va:0x%08lx to pa:0x%08x\n", + __func__, __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES), + CONFIG_DTCM_RAM_BASE); + + pr_info("%s: __dtcm_start va:0x%08lx size:%d\n", + __func__, (unsigned long)&__dtcm_start, &__tcm_end - &__dtcm_start); + +#endif + return; +panic: + panic("TCM init error"); +} + +void *tcm_alloc(size_t len) +{ + unsigned long vaddr; + + if (!tcm_pool) + return NULL; + + vaddr = gen_pool_alloc(tcm_pool, len); + if (!vaddr) + return NULL; + + return (void *) vaddr; +} +EXPORT_SYMBOL(tcm_alloc); + +void tcm_free(void *addr, size_t len) +{ + gen_pool_free(tcm_pool, (unsigned long) addr, len); +} +EXPORT_SYMBOL(tcm_free); + +static int __init tcm_setup_pool(void) +{ +#ifndef CONFIG_HAVE_DTCM + u32 pool_size = (u32) (TCM_NR_PAGES * PAGE_SIZE) + - (u32) (&__tcm_end - &__tcm_start); + + u32 tcm_pool_start = __fix_to_virt(FIX_TCM) + + (u32) (&__tcm_end - &__tcm_start); +#else + u32 pool_size = (u32) (CONFIG_DTCM_NR_PAGES * PAGE_SIZE) + - (u32) (&__tcm_end - &__dtcm_start); + + u32 tcm_pool_start = __fix_to_virt(FIX_TCM - CONFIG_ITCM_NR_PAGES) + + (u32) (&__tcm_end - &__dtcm_start); +#endif + int ret; + + tcm_pool = gen_pool_create(2, -1); + + ret = gen_pool_add(tcm_pool, tcm_pool_start, pool_size, -1); + if (ret) { + pr_err("%s: gen_pool add failed!\n", __func__); + return ret; + } + + pr_info("%s: Added %d bytes @ 0x%08x to memory pool\n", + __func__, pool_size, tcm_pool_start); + + return 0; +} + +static int __init tcm_init(void) +{ + tcm_mapping_init(); + + tcm_setup_pool(); + + return 0; +} +arch_initcall(tcm_init); diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 5accda2767be..a3301bab9231 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/jz4740-cgu.h> +#include <dt-bindings/clock/ingenic,tcu.h> / { #address-cells = <1>; @@ -45,14 +46,6 @@ #clock-cells = <1>; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4740-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4740_CLK_RTC>; - clock-names = "rtc"; - }; - tcu: timer@10002000 { compatible = "ingenic,jz4740-tcu", "simple-mfd"; reg = <0x10002000 0x1000>; @@ -73,6 +66,14 @@ interrupt-parent = <&intc>; interrupts = <23 22 21>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4740-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index f928329b034b..bb89653d16a3 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/jz4780-cgu.h> +#include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/dma/jz4780-dma.h> / { @@ -67,6 +68,14 @@ interrupt-parent = <&intc>; interrupts = <27 26 25>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4780-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { @@ -348,14 +357,6 @@ status = "disabled"; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4780-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4780_CLK_RTCLK>; - clock-names = "rtc"; - }; - nemc: nemc@13410000 { compatible = "ingenic,jz4780-nemc"; reg = <0x13410000 0x10000>; diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index 4994c695a1a7..147f7d5c243a 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/clock/x1000-cgu.h> #include <dt-bindings/dma/x1000-dma.h> @@ -72,7 +73,7 @@ compatible = "ingenic,x1000-watchdog", "ingenic,jz4780-watchdog"; reg = <0x0 0x10>; - clocks = <&cgu X1000_CLK_RTCLK>; + clocks = <&tcu TCU_CLK_WDT>; clock-names = "wdt"; }; }; @@ -158,7 +159,6 @@ i2c0: i2c-controller@10050000 { compatible = "ingenic,x1000-i2c"; reg = <0x10050000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -173,7 +173,6 @@ i2c1: i2c-controller@10051000 { compatible = "ingenic,x1000-i2c"; reg = <0x10051000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -188,7 +187,6 @@ i2c2: i2c-controller@10052000 { compatible = "ingenic,x1000-i2c"; reg = <0x10052000 0x1000>; - #address-cells = <1>; #size-cells = <0>; diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h index 7c6a1095f556..aabd097933fe 100644 --- a/arch/mips/include/asm/sync.h +++ b/arch/mips/include/asm/sync.h @@ -155,9 +155,11 @@ * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use * optimized memory barrier primitives."). Here we specify that the affected * sync instructions should be emitted twice. + * Note that this expression is evaluated by the assembler (not the compiler), + * and that the assembler evaluates '==' as 0 or -1, not 0 or 1. */ #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +# define __SYNC_rpt(type) (1 - (type == __SYNC_wmb)) #else # define __SYNC_rpt(type) 1 #endif diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 6176b9acba95..d0d832ab3d3b 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -134,7 +134,7 @@ void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) - release_progmem(v); + release_progmem(v->load_addr); kfree(v); } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index aa89a41dc5dd..d7fe8408603e 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -33,6 +33,7 @@ endif cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ + -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-asynchronous-unwind-tables) \ $(call cc-option, -fno-stack-protector) @@ -51,6 +52,8 @@ endif CFLAGS_REMOVE_vgettimeofday.o = -pg +DISABLE_VDSO := n + # # For the pre-R6 code in arch/mips/vdso/vdso.h for locating # the base address of VDSO, the linker will emit a R_MIPS_PC32 @@ -64,11 +67,24 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) - ccflags-vdso += -DDISABLE_MIPS_VDSO + DISABLE_VDSO := y endif endif +# +# GCC (at least up to version 9.2) appears to emit function calls that make use +# of the GOT when targeting microMIPS, which we can't use in the VDSO due to +# the lack of relocations. As such, we disable the VDSO for microMIPS builds. +# +ifdef CONFIG_CPU_MICROMIPS + DISABLE_VDSO := y +endif + +ifeq ($(DISABLE_VDSO),y) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) + ccflags-vdso += -DDISABLE_MIPS_VDSO +endif + # VDSO linker flags. VDSO_LDFLAGS := \ -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \ @@ -81,12 +97,18 @@ GCOV_PROFILE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Check that we don't have PIC 'jalr t9' calls left +quiet_cmd_vdso_mips_check = VDSOCHK $@ + cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | egrep -h "jalr.*t9" > /dev/null; \ + then (echo >&2 "$@: PIC 'jalr t9' calls are not supported"; \ + rm -f $@; /bin/false); fi + # # Shared build commands. # quiet_cmd_vdsold_and_vdso_check = LD $@ - cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check); $(cmd_vdso_mips_check) quiet_cmd_vdsold = VDSO $@ cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 86332080399a..080a0bf8e54b 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -295,8 +295,13 @@ static inline bool pfn_valid(unsigned long pfn) /* * Some number of bits at the level of the page table that points to * a hugepte are used to encode the size. This masks those bits. + * On 8xx, HW assistance requires 4k alignment for the hugepte. */ +#ifdef CONFIG_PPC_8xx +#define HUGEPD_SHIFT_MASK 0xfff +#else #define HUGEPD_SHIFT_MASK 0x3f +#endif #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8387698bd5b6..eedcbfb9a6ff 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -168,6 +168,10 @@ struct thread_struct { unsigned long srr1; unsigned long dar; unsigned long dsisr; +#ifdef CONFIG_PPC_BOOK3S_32 + unsigned long r0, r3, r4, r5, r6, r8, r9, r11; + unsigned long lr, ctr; +#endif #endif /* Debug Registers */ struct debug_reg debug; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c25e562f1cd9..fcf24a365fc0 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -132,6 +132,18 @@ int main(void) OFFSET(SRR1, thread_struct, srr1); OFFSET(DAR, thread_struct, dar); OFFSET(DSISR, thread_struct, dsisr); +#ifdef CONFIG_PPC_BOOK3S_32 + OFFSET(THR0, thread_struct, r0); + OFFSET(THR3, thread_struct, r3); + OFFSET(THR4, thread_struct, r4); + OFFSET(THR5, thread_struct, r5); + OFFSET(THR6, thread_struct, r6); + OFFSET(THR8, thread_struct, r8); + OFFSET(THR9, thread_struct, r9); + OFFSET(THR11, thread_struct, r11); + OFFSET(THLR, thread_struct, lr); + OFFSET(THCTR, thread_struct, ctr); +#endif #endif #ifdef CONFIG_SPE OFFSET(THREAD_EVR0, thread_struct, evr[0]); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index a1eaffe868de..7b048cee767c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1184,6 +1184,17 @@ void eeh_handle_special_event(void) eeh_pe_state_mark(pe, EEH_PE_RECOVERING); eeh_handle_normal_event(pe); } else { + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) + edev->mode &= ~EEH_DEV_NO_HANDLER; + + /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_pe_report( + "error_detected(permanent failure)", pe, + eeh_report_failure, NULL); + pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); @@ -1192,16 +1203,6 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; - eeh_for_each_pe(pe, tmp_pe) - eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) - edev->mode &= ~EEH_DEV_NO_HANDLER; - - /* Notify all devices to be down */ - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_pe_report( - "error_detected(permanent failure)", pe, - eeh_report_failure, NULL); bus = eeh_pe_bus_get(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 0713daa651d9..16af0d8d90a8 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -783,7 +783,7 @@ fast_exception_return: 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 bge 2b #else bge 3f @@ -791,7 +791,7 @@ fast_exception_return: lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 blt 2b #else blt 3f @@ -1354,12 +1354,17 @@ _GLOBAL(enter_rtas) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 RFI -1: tophys(r9,r1) +1: tophys_novmstack r9, r1 +#ifdef CONFIG_VMAP_STACK + li r0, MSR_KERNEL & ~MSR_IR /* can take DTLB miss */ + mtmsr r0 + isync +#endif lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */ lwz r9,8(r9) /* original msr value */ addi r1,r1,INT_FRAME_SIZE li r0,0 - tophys(r7, r2) + tophys_novmstack r7, r2 stw r0, THREAD + RTAS_SP(r7) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 0493fcac6409..97c887950c3c 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -290,17 +290,55 @@ MachineCheck: 7: EXCEPTION_PROLOG_2 addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_CHRP - bne cr1,1f +#ifdef CONFIG_VMAP_STACK + mfspr r4, SPRN_SPRG_THREAD + tovirt(r4, r4) + lwz r4, RTAS_SP(r4) + cmpwi cr1, r4, 0 #endif - EXC_XFER_STD(0x200, machine_check_exception) -#ifdef CONFIG_PPC_CHRP -1: b machine_check_in_rtas + beq cr1, machine_check_tramp + b machine_check_in_rtas +#else + b machine_check_tramp #endif /* Data access exception. */ . = 0x300 DO_KVM 0x300 DataAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mfspr r10, SPRN_SPRG_THREAD +BEGIN_MMU_FTR_SECTION + stw r11, THR11(r10) + mfspr r10, SPRN_DSISR + mfcr r11 +#ifdef CONFIG_PPC_KUAP + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h +#else + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h +#endif + mfspr r10, SPRN_SPRG_THREAD + beq hash_page_dsi +.Lhash_page_dsi_cont: + mtcr r11 + lwz r11, THR11(r10) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r11, SPRN_DAR + stw r11, DAR(r10) + mfspr r11, SPRN_DSISR + stw r11, DSISR(r10) + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + b handle_page_fault_tramp_1 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG handle_dar_dsisr=1 get_and_save_dar_dsisr_on_stack r4, r5, r11 BEGIN_MMU_FTR_SECTION @@ -316,11 +354,32 @@ BEGIN_MMU_FTR_SECTION FTR_SECTION_ELSE b handle_page_fault_tramp_2 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ /* Instruction access exception. */ . = 0x400 DO_KVM 0x400 InstructionAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r10, SPRN_SPRG_THREAD + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 +BEGIN_MMU_FTR_SECTION + andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */ + bne hash_page_isi +.Lhash_page_isi_cont: + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */ beq 1f /* if so, try to put a PTE */ @@ -329,6 +388,7 @@ InstructionAccess: BEGIN_MMU_FTR_SECTION bl hash_page END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ 1: mr r4,r12 andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ stw r4, _DAR(r11) @@ -344,7 +404,7 @@ Alignment: EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_STD(0x600, alignment_exception) + b alignment_exception_tramp /* Program check exception */ EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) @@ -645,15 +705,100 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) . = 0x3000 +machine_check_tramp: + EXC_XFER_STD(0x200, machine_check_exception) + +alignment_exception_tramp: + EXC_XFER_STD(0x600, alignment_exception) + handle_page_fault_tramp_1: +#ifdef CONFIG_VMAP_STACK + EXCEPTION_PROLOG_2 handle_dar_dsisr=1 +#endif lwz r4, _DAR(r11) lwz r5, _DSISR(r11) /* fall through */ handle_page_fault_tramp_2: EXC_XFER_LITE(0x300, handle_page_fault) +#ifdef CONFIG_VMAP_STACK +.macro save_regs_thread thread + stw r0, THR0(\thread) + stw r3, THR3(\thread) + stw r4, THR4(\thread) + stw r5, THR5(\thread) + stw r6, THR6(\thread) + stw r8, THR8(\thread) + stw r9, THR9(\thread) + mflr r0 + stw r0, THLR(\thread) + mfctr r0 + stw r0, THCTR(\thread) +.endm + +.macro restore_regs_thread thread + lwz r0, THLR(\thread) + mtlr r0 + lwz r0, THCTR(\thread) + mtctr r0 + lwz r0, THR0(\thread) + lwz r3, THR3(\thread) + lwz r4, THR4(\thread) + lwz r5, THR5(\thread) + lwz r6, THR6(\thread) + lwz r8, THR8(\thread) + lwz r9, THR9(\thread) +.endm + +hash_page_dsi: + save_regs_thread r10 + mfdsisr r3 + mfdar r4 + mfsrr0 r5 + mfsrr1 r9 + rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */ + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + b .Lhash_page_dsi_cont + +hash_page_isi: + mr r11, r10 + mfspr r10, SPRN_SPRG_THREAD + save_regs_thread r10 + li r3, 0 + lwz r4, SRR0(r10) + lwz r9, SRR1(r10) + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + mr r10, r11 + b .Lhash_page_isi_cont + + .globl fast_hash_page_return +fast_hash_page_return: + andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */ + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + bne 1f + + /* DSI */ + mtcr r11 + lwz r11, THR11(r10) + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + +1: /* ISI */ + mtcr r11 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + stack_overflow: vmap_stack_overflow_exception +#endif AltiVecUnavailable: EXCEPTION_PROLOG diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index a6a5fbbf8504..9db162f79fe6 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -64,11 +64,25 @@ .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mtcr r10 +FTR_SECTION_ELSE + stw r10, _CCR(r11) +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#else stw r10,_CCR(r11) /* save registers */ +#endif + mfspr r10, SPRN_SPRG_SCRATCH0 stw r12,GPR12(r11) stw r9,GPR9(r11) - mfspr r10,SPRN_SPRG_SCRATCH0 stw r10,GPR10(r11) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mfcr r10 + stw r10, _CCR(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif mfspr r12,SPRN_SPRG_SCRATCH1 stw r12,GPR11(r11) mflr r10 @@ -83,6 +97,11 @@ stw r10, _DSISR(r11) .endif lwz r9, SRR1(r12) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + andi. r10, r9, MSR_PR +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif lwz r12, SRR0(r12) #else mfspr r12,SPRN_SRR0 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9922306ae512..073a651787df 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -256,7 +256,7 @@ InstructionTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 0ffdd18b9f26..433d97bea1f3 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -166,7 +166,11 @@ BEGIN_FTR_SECTION mfspr r9,SPRN_HID0 andis. r9,r9,HID0_NAP@h beq 1f +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_msscr0@ha +#else addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha +#endif lwz r9,nap_save_msscr0@l(r9) mtspr SPRN_MSSCR0, r9 sync @@ -174,7 +178,11 @@ BEGIN_FTR_SECTION 1: END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) BEGIN_FTR_SECTION +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_hid1@ha +#else addis r9,r11,(nap_save_hid1-KERNELBASE)@ha +#endif lwz r9,nap_save_hid1@l(r9) mtspr SPRN_HID1, r9 END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e6c30cee6abf..d215f9554553 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct task_struct *tsk) * normal/non-checkpointed stack pointer. */ + unsigned long ret = tsk->thread.regs->gpr[1]; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BUG_ON(tsk != current); if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { + preempt_disable(); tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) - return tsk->thread.ckpt_regs.gpr[1]; + ret = tsk->thread.ckpt_regs.gpr[1]; + + /* + * If we treclaim, we must clear the current thread's TM bits + * before re-enabling preemption. Otherwise we might be + * preempted and have the live MSR[TS] changed behind our back + * (tm_recheckpoint_new_task() would recheckpoint). Besides, we + * enter the signal handler in non-transactional state. + */ + tsk->thread.regs->msr &= ~MSR_TS_MASK; + preempt_enable(); } #endif - return tsk->thread.regs->gpr[1]; + return ret; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 98600b276f76..1b090a76b444 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, */ static int save_tm_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, int sigret) + struct mcontext __user *tm_frame, int sigret, + unsigned long msr) { - unsigned long msr = regs->msr; - WARN_ON(tm_suspend_disabled); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_frame = &rt_sf->uc_transact.uc_mcontext; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (__put_user((unsigned long)&rt_sf->uc_transact, &rt_sf->uc.uc_link) || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) goto badframe; - if (save_tm_user_regs(regs, frame, tm_frame, sigret)) + if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr)) goto badframe; } else @@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_mctx = &frame->mctx_transact; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact, - sigret)) + sigret, msr)) goto badframe; } else diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 117515564ec7..84ed2e77ef9c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, struct task_struct *tsk, - int signr, sigset_t *set, unsigned long handler) + int signr, sigset_t *set, unsigned long handler, + unsigned long msr) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif struct pt_regs *regs = tsk->thread.regs; - unsigned long msr = tsk->thread.regs->msr; long err = 0; BUG_ON(tsk != current); - BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + BUG_ON(!MSR_TM_ACTIVE(msr)); WARN_ON(tm_suspend_disabled); @@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); @@ -824,6 +817,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, unsigned long newsp = 0; long err = 0; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -841,7 +838,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= __put_user(0, &frame->uc.uc_flags); err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { /* The ucontext_t passed to userland points to the second * ucontext_t (for transactional state) with its uc_link ptr. */ @@ -849,7 +846,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, tsk, ksig->sig, NULL, - (unsigned long)ksig->ka.sa.sa_handler); + (unsigned long)ksig->ka.sa.sa_handler, + msr); } else #endif { diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index c11b0a005196..2015c4f96238 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -25,12 +25,6 @@ #include <asm/feature-fixups.h> #include <asm/code-patching-asm.h> -#ifdef CONFIG_VMAP_STACK -#define ADDR_OFFSET 0 -#else -#define ADDR_OFFSET PAGE_OFFSET -#endif - #ifdef CONFIG_SMP .section .bss .align 2 @@ -53,8 +47,8 @@ mmu_hash_lock: .text _GLOBAL(hash_page) #ifdef CONFIG_SMP - lis r8, (mmu_hash_lock - ADDR_OFFSET)@h - ori r8, r8, (mmu_hash_lock - ADDR_OFFSET)@l + lis r8, (mmu_hash_lock - PAGE_OFFSET)@h + ori r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l lis r0,0x0fff b 10f 11: lwz r6,0(r8) @@ -72,12 +66,9 @@ _GLOBAL(hash_page) cmplw 0,r4,r0 ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */ mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */ -#ifdef CONFIG_VMAP_STACK - tovirt(r5, r5) -#endif blt+ 112f /* assume user more likely */ - lis r5, (swapper_pg_dir - ADDR_OFFSET)@ha /* if kernel address, use */ - addi r5 ,r5 ,(swapper_pg_dir - ADDR_OFFSET)@l /* kernel page table */ + lis r5, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ + addi r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */ 112: #ifndef CONFIG_PTE_64BIT @@ -89,9 +80,6 @@ _GLOBAL(hash_page) lwzx r8,r8,r5 /* Get L1 entry */ rlwinm. r8,r8,0,0,20 /* extract pt base address */ #endif -#ifdef CONFIG_VMAP_STACK - tovirt(r8, r8) -#endif #ifdef CONFIG_SMP beq- hash_page_out /* return if no mapping */ #else @@ -143,30 +131,36 @@ retry: bne- retry /* retry if someone got there first */ mfsrin r3,r4 /* get segment reg for segment */ +#ifndef CONFIG_VMAP_STACK mfctr r0 stw r0,_CTR(r11) +#endif bl create_hpte /* add the hash table entry */ #ifdef CONFIG_SMP eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) #endif +#ifdef CONFIG_VMAP_STACK + b fast_hash_page_return +#else /* Return from the exception */ lwz r5,_CTR(r11) mtctr r5 lwz r0,GPR0(r11) lwz r8,GPR8(r11) b fast_exception_return +#endif #ifdef CONFIG_SMP hash_page_out: eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) blr #endif /* CONFIG_SMP */ @@ -341,7 +335,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) patch_site 1f, patch__hash_page_A1 patch_site 2f, patch__hash_page_A2 /* Get the address of the primary PTE group in the hash table (r3) */ -0: lis r0, (Hash_base - ADDR_OFFSET)@h /* base address of hash table */ +0: lis r0, (Hash_base - PAGE_OFFSET)@h /* base address of hash table */ 1: rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ 2: rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ xor r3,r3,r0 /* make primary hash */ @@ -355,10 +349,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ 10f /* no PTE: go look for an empty slot */ tlbie r4 - lis r4, (htab_hash_searches - ADDR_OFFSET)@ha - lwz r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + lis r4, (htab_hash_searches - PAGE_OFFSET)@ha + lwz r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) addi r6,r6,1 /* count how many searches we do */ - stw r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + stw r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) /* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */ mtctr r0 @@ -390,10 +384,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ found_empty /* update counter of times that the primary PTEG is full */ - lis r4, (primary_pteg_full - ADDR_OFFSET)@ha - lwz r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + lis r4, (primary_pteg_full - PAGE_OFFSET)@ha + lwz r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) addi r6,r6,1 - stw r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + stw r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) patch_site 0f, patch__hash_page_C /* Search the secondary PTEG for an empty slot */ @@ -427,8 +421,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) * lockup here but that shouldn't happen */ -1: lis r4, (next_slot - ADDR_OFFSET)@ha /* get next evict slot */ - lwz r6, (next_slot - ADDR_OFFSET)@l(r4) +1: lis r4, (next_slot - PAGE_OFFSET)@ha /* get next evict slot */ + lwz r6, (next_slot - PAGE_OFFSET)@l(r4) addi r6,r6,HPTE_SIZE /* search for candidate */ andi. r6,r6,7*HPTE_SIZE stw r6,next_slot@l(r4) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 0a1c65a2c565..f888cbb109b9 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -413,7 +413,7 @@ void __init MMU_init_hw(void) void __init MMU_init_hw_patch(void) { unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE); - unsigned int hash; + unsigned int hash = (unsigned int)Hash - PAGE_OFFSET; if (ppc_md.progress) ppc_md.progress("hash:patch", 0x345); @@ -425,11 +425,6 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:create_hpte */ - if (IS_ENABLED(CONFIG_VMAP_STACK)) - hash = (unsigned int)Hash; - else - hash = (unsigned int)Hash - PAGE_OFFSET; - modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6); @@ -439,8 +434,7 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:flush_hash_page */ - modify_instruction_site(&patch__flush_hash_A0, 0xffff, - ((unsigned int)Hash - PAGE_OFFSET) >> 16); + modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6); modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 73d4873fc7f8..33b3461d91e8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -53,20 +53,24 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (pshift >= pdshift) { cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + new = NULL; } else if (IS_ENABLED(CONFIG_PPC_8xx)) { - cachep = PGT_CACHE(PTE_INDEX_SIZE); + cachep = NULL; num_hugepd = 1; + new = pte_alloc_one(mm); } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; + new = NULL; } - if (!cachep) { + if (!cachep && !new) { WARN_ONCE(1, "No page table cache created for hugetlb tables"); return -ENOMEM; } - new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + if (cachep) + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -97,7 +101,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (i < num_hugepd) { for (i = i - 1 ; i >= 0; i--, hpdp--) *hpdp = __hugepd(0); - kmem_cache_free(cachep, new); + if (cachep) + kmem_cache_free(cachep, new); + else + pte_free(mm, new); } else { kmemleak_ignore(new); } @@ -324,8 +331,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else if (IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(PTE_INDEX_SIZE)); + pgtable_free_tlb(tlb, hugepte, 0); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -639,12 +645,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_INDEX_SIZE); - else if (pdshift > shift) - pgtable_cache_add(pdshift - shift); - else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) + if (pdshift > shift) { + if (!IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(pdshift - shift); + } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || + IS_ENABLED(CONFIG_PPC_8xx)) { pgtable_cache_add(PTE_T_ORDER); + } configured = true; } diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 16dd95bd0749..db5664dde5ff 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -185,8 +185,7 @@ u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0}; static void __init kasan_early_hash_table(void) { - unsigned int hash = IS_ENABLED(CONFIG_VMAP_STACK) ? (unsigned int)early_hash : - __pa(early_hash); + unsigned int hash = __pa(early_hash); modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e8c84d265602..0ec9640335bb 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -3435,6 +3435,11 @@ getstring(char *s, int size) int c; c = skipbl(); + if (c == '\n') { + *s = 0; + return; + } + do { if( size > 1 ){ *s++ = c; diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore index 8dab0bb6ae66..8a45a37d2af4 100644 --- a/arch/riscv/boot/.gitignore +++ b/arch/riscv/boot/.gitignore @@ -1,2 +1,4 @@ Image Image.gz +loader +loader.lds diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 435b65532e29..8e18d2c64399 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -72,6 +72,16 @@ #define EXC_LOAD_PAGE_FAULT 13 #define EXC_STORE_PAGE_FAULT 15 +/* PMP configuration */ +#define PMP_R 0x01 +#define PMP_W 0x02 +#define PMP_X 0x04 +#define PMP_A 0x18 +#define PMP_A_TOR 0x08 +#define PMP_A_NA4 0x10 +#define PMP_A_NAPOT 0x18 +#define PMP_L 0x80 + /* symbolic CSR names: */ #define CSR_CYCLE 0xc00 #define CSR_TIME 0xc01 @@ -100,6 +110,8 @@ #define CSR_MCAUSE 0x342 #define CSR_MTVAL 0x343 #define CSR_MIP 0x344 +#define CSR_PMPCFG0 0x3a0 +#define CSR_PMPADDR0 0x3b0 #define CSR_MHARTID 0xf14 #ifdef CONFIG_RISCV_M_MODE diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 271860fc2c3f..85f2073e7fe4 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -58,6 +58,12 @@ _start_kernel: /* Reset all registers except ra, a0, a1 */ call reset_regs + /* Setup a PMP to permit access to all of memory. */ + li a0, -1 + csrw CSR_PMPADDR0, a0 + li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) + csrw CSR_PMPCFG0, a0 + /* * The hartid in a0 is expected later on, and we have no firmware * to hand it to us. diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f4cad5163bf2..ffb3d94bf0cc 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -156,6 +156,6 @@ void __init trap_init(void) csr_write(CSR_SCRATCH, 0); /* Set the exception vector address */ csr_write(CSR_TVEC, &handle_exception); - /* Enable all interrupts */ - csr_write(CSR_IE, -1); + /* Enable interrupts */ + csr_write(CSR_IE, IE_SIE | IE_EIE); } diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index f0cc86040587..ec0ca90dd900 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -19,18 +19,20 @@ asmlinkage void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, mk_pte(virt_to_page(kasan_early_shadow_page), - PAGE_KERNEL)); + PAGE_KERNEL)); for (i = 0; i < PTRS_PER_PMD; ++i) set_pmd(kasan_early_shadow_pmd + i, - pfn_pmd(PFN_DOWN(__pa((uintptr_t)kasan_early_shadow_pte)), - __pgprot(_PAGE_TABLE))); + pfn_pmd(PFN_DOWN + (__pa((uintptr_t) kasan_early_shadow_pte)), + __pgprot(_PAGE_TABLE))); for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); /* init for swapper_pg_dir */ pgd = pgd_offset_k(KASAN_SHADOW_START); @@ -38,37 +40,43 @@ asmlinkage void __init kasan_early_init(void) for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); flush_tlb_all(); } static void __init populate(void *start, void *end) { - unsigned long i; + unsigned long i, offset; unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); unsigned long n_pages = (vend - vaddr) / PAGE_SIZE; + unsigned long n_ptes = + ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE; unsigned long n_pmds = - (n_pages % PTRS_PER_PTE) ? n_pages / PTRS_PER_PTE + 1 : - n_pages / PTRS_PER_PTE; + ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD; + + pte_t *pte = + memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + pmd_t *pmd = + memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); pgd_t *pgd = pgd_offset_k(vaddr); - pmd_t *pmd = memblock_alloc(n_pmds * sizeof(pmd_t), PAGE_SIZE); - pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); for (i = 0; i < n_pages; i++) { phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); - - set_pte(pte + i, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); + set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); } - for (i = 0; i < n_pmds; ++pgd, i += PTRS_PER_PMD) - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(((uintptr_t)(pmd + i)))), + for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE) + set_pmd(&pmd[i], + pfn_pmd(PFN_DOWN(__pa(&pte[offset])), __pgprot(_PAGE_TABLE))); - for (i = 0; i < n_pages; ++pmd, i += PTRS_PER_PTE) - set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa((uintptr_t)(pte + i))), + for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD) + set_pgd(&pgd[i], + pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), __pgprot(_PAGE_TABLE))); flush_tlb_all(); @@ -81,7 +89,8 @@ void __init kasan_init(void) unsigned long i; kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + (void *)kasan_mem_to_shadow((void *) + VMALLOC_END)); for_each_memblock(memory, reg) { void *start = (void *)__va(reg->base); @@ -90,14 +99,14 @@ void __init kasan_init(void) if (start >= end) break; - populate(kasan_mem_to_shadow(start), - kasan_mem_to_shadow(end)); + populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); }; for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], mk_pte(virt_to_page(kasan_early_shadow_page), - __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED))); + __pgprot(_PAGE_PRESENT | _PAGE_READ | + _PAGE_ACCESSED))); memset(kasan_early_shadow_page, 0, PAGE_SIZE); init_task.kasan_depth = 0; diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e0e3a465bbfd..8dfa2cf1f05c 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -146,7 +146,7 @@ all: bzImage #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg... KBUILD_IMAGE := $(boot)/bzImage -install: vmlinux +install: $(Q)$(MAKE) $(build)=$(boot) $@ bzImage: vmlinux diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index e2c47d3a1c89..0ff9261c915e 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -70,7 +70,7 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE $(obj)/startup.a: $(OBJECTS) FORCE $(call if_changed,ar) -install: $(CONFIGURE) $(obj)/bzImage +install: sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 5d12352545c5..5591243d673e 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -75,7 +75,7 @@ static unsigned long get_random(unsigned long limit) *(unsigned long *) prng.parm_block ^= seed; for (i = 0; i < 16; i++) { cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, - (char *) entropy, (char *) entropy, + (u8 *) entropy, (u8 *) entropy, sizeof(entropy)); memcpy(prng.parm_block, entropy, sizeof(entropy)); } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 2e60c80395ab..0c86ba19fa2b 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -474,7 +475,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -684,7 +684,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -748,7 +747,6 @@ CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_HEADERS_INSTALL=y -CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y @@ -772,9 +770,9 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_DEBUG_SHIRQ=y +CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y -CONFIG_PANIC_ON_OOPS=y CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y @@ -783,9 +781,20 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 +CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_PREEMPT_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y @@ -796,15 +805,6 @@ CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y -CONFIG_LATENCYTOP=y -CONFIG_IRQSOFF_TRACER=y -CONFIG_PREEMPT_TRACER=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -CONFIG_HIST_TRIGGERS=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_TEST_SORT=y @@ -814,5 +814,3 @@ CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 25f799849582..6b27d861a9a3 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -470,7 +471,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -677,7 +677,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -739,18 +738,18 @@ CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 85e944f04c70..1019efd85b9d 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -42,7 +42,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end); static inline void storage_key_init_range(unsigned long start, unsigned long end) { - if (PAGE_DEFAULT_KEY) + if (PAGE_DEFAULT_KEY != 0) __storage_key_init_range(start, end); } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 361ef5eda468..aadb3d0e2adc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -84,7 +84,6 @@ void s390_update_cpu_mhz(void); void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; -extern int sysctl_ieee_emulation_warnings; extern void execve_tail(void); extern void __bpon(void); diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 71e3f0146cda..1e3517b0518b 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -201,7 +201,7 @@ struct slib { * @scount: SBAL count * @sflags: whole SBAL flags * @length: length - * @addr: address + * @addr: absolute data address */ struct qdio_buffer_element { u8 eflags; @@ -211,7 +211,7 @@ struct qdio_buffer_element { u8 scount; u8 sflags; u32 length; - void *addr; + u64 addr; } __attribute__ ((packed, aligned(16))); /** @@ -227,7 +227,7 @@ struct qdio_buffer { * @sbal: absolute SBAL address */ struct sl_element { - unsigned long sbal; + u64 sbal; } __attribute__ ((packed)); /** diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c index 748456c365f4..9557c5a15b91 100644 --- a/arch/x86/boot/compressed/kaslr_64.c +++ b/arch/x86/boot/compressed/kaslr_64.c @@ -29,9 +29,6 @@ #define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" -/* Used by pgtable.h asm code to force instruction serialization. */ -unsigned long __force_order; - /* Used to track our page table allocation area. */ struct alloc_pgt_data { unsigned char *pgt_buf; diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 03946eb3e2b9..2a8f2bd2e5cf 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -292,6 +292,14 @@ enum x86emul_mode { #define X86EMUL_SMM_MASK (1 << 6) #define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) +/* + * fastop functions are declared as taking a never-defined fastop parameter, + * so they can't be called from C directly. + */ +struct fastop; + +typedef void (*fastop_t)(struct fastop *); + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -324,7 +332,10 @@ struct x86_emulate_ctxt { struct operand src; struct operand src2; struct operand dst; - int (*execute)(struct x86_emulate_ctxt *ctxt); + union { + int (*execute)(struct x86_emulate_ctxt *ctxt); + fastop_t fop; + }; int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* * The following six fields are cleared together, diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 40a0c0fd95ca..98959e8cd448 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1122,6 +1122,7 @@ struct kvm_x86_ops { int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, @@ -1146,7 +1147,7 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ebe1685e92dd..d5e517d1c3dd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -512,6 +512,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2a85287b3685..8521af3fef27 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -72,7 +72,7 @@ #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) -#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000 +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index a50e4a0de315..9915990fd8cf 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -81,6 +81,7 @@ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ #define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 503d3f42da16..3f3f780c8c65 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ac83a0fef628..1f875fbe1384 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -28,6 +28,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; +static const int amd_erratum_1054[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -972,6 +973,15 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + /* + * Turn on the Instructions Retired free counter on machines not + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (cpu_has(c, X86_FEATURE_IRPERF) && + !cpu_has_amd_erratum(c, amd_erratum_1054)) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); } #ifdef CONFIG_X86_32 @@ -1099,6 +1109,10 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index b3a50d962851..52de616a8065 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1163,9 +1163,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static const char *get_name(unsigned int bank, struct threshold_block *b) @@ -1198,8 +1201,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return buf_mcatype; } -static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, - unsigned int block, u32 address) +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -1243,16 +1247,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, INIT_LIST_HEAD(&b->miscj); - if (per_cpu(threshold_banks, cpu)[bank]->blocks) { - list_add(&b->miscj, - &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj); - } else { - per_cpu(threshold_banks, cpu)[bank]->blocks = b; - } + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, - per_cpu(threshold_banks, cpu)[bank]->kobj, - get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); if (err) goto out_free; recurse: @@ -1260,7 +1260,7 @@ recurse: if (!address) return 0; - err = allocate_threshold_blocks(cpu, bank, block, address); + err = allocate_threshold_blocks(cpu, tb, bank, block, address); if (err) goto out_free; @@ -1345,8 +1345,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out_free; } - per_cpu(threshold_banks, cpu)[bank] = b; - if (is_shared_bank(bank)) { refcount_set(&b->cpus, 1); @@ -1357,9 +1355,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); - if (!err) - goto out; + err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + if (err) + goto out_free; + + per_cpu(threshold_banks, cpu)[bank] = b; + + return 0; out_free: kfree(b); @@ -1368,8 +1370,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -1379,13 +1385,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddbc61984227..dd19fb3539e0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -191,25 +191,6 @@ #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) #define FASTOP_SIZE 8 -/* - * fastop functions have a special calling convention: - * - * dst: rax (in/out) - * src: rdx (in/out) - * src2: rcx (in) - * flags: rflags (in/out) - * ex: rsi (in:fastop pointer, out:zero if exception) - * - * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for - * different operand sizes can be reached by calculation, rather than a jump - * table (which would be bigger than the code). - * - * fastop functions are declared as taking a never-defined fastop parameter, - * so they can't be called from C directly. - */ - -struct fastop; - struct opcode { u64 flags : 56; u64 intercept : 8; @@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -typedef void (*fastop_t)(struct fastop *); - +/* + * fastop functions have a special calling convention: + * + * dst: rax (in/out) + * src: rdx (in/out) + * src2: rcx (in) + * flags: rflags (in/out) + * ex: rsi (in:fastop pointer, out:zero if exception) + * + * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for + * different operand sizes can be reached by calculation, rather than a jump + * table (which would be bigger than the code). + */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ @@ -5683,7 +5675,7 @@ special_insn: if (ctxt->execute) { if (ctxt->d & Fastop) - rc = fastop(ctxt, (fastop_t)ctxt->execute); + rc = fastop(ctxt, ctxt->fop); else rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 79afa0bb5f41..c47d2acec529 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -417,7 +417,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && + if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afcd30d44cbb..e3099c642fec 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } @@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3c6522b84ff1..ffcd96fc02d0 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index bef0ba35f121..ad3f5b178a03 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1005,33 +1005,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1350,6 +1349,24 @@ static __init void svm_adjust_mmio_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); } +static void svm_hardware_teardown(void) +{ + int cpu; + + if (svm_sev_enabled()) { + bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } + + for_each_possible_cpu(cpu) + svm_cpu_uninit(cpu); + + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + iopm_base = 0; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1463,29 +1480,10 @@ static __init int svm_hardware_setup(void) return 0; err: - __free_pages(iopm_pages, IOPM_ALLOC_ORDER); - iopm_base = 0; + svm_hardware_teardown(); return r; } -static __exit void svm_hardware_unsetup(void) -{ - int cpu; - - if (svm_sev_enabled()) { - bitmap_free(sev_asid_bitmap); - bitmap_free(sev_reclaim_asid_bitmap); - - sev_flush_asids(); - } - - for_each_possible_cpu(cpu) - svm_cpu_uninit(cpu); - - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); - iopm_base = 0; -} - static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; @@ -5232,6 +5230,9 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; bool activated = kvm_vcpu_apicv_active(vcpu); + if (!avic) + return; + if (activated) { /** * During AVIC temporary deactivation, guest could update @@ -5255,8 +5256,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5268,6 +5272,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) put_cpu(); } else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) @@ -7378,7 +7384,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .hardware_unsetup = svm_hardware_unsetup, + .hardware_unsetup = svm_hardware_teardown, .check_processor_compatibility = svm_check_processor_compat, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, @@ -7433,6 +7439,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .run = svm_vcpu_run, .handle_exit = handle_exit, .skip_emulated_instruction = skip_emulated_instruction, + .update_emulated_instruction = NULL, .set_interrupt_shadow = svm_set_interrupt_shadow, .get_interrupt_shadow = svm_get_interrupt_shadow, .patch_hypercall = svm_patch_hypercall, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 283bdb7071af..f486e2606247 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; +extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 3589cd3c0fcc..e920d7834d73 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3161,10 +3161,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. * * Returns: - * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode - * NVMX_ENTRY_VMFAIL: Consistency check VMFail - * NVMX_ENTRY_VMEXIT: Consistency check VMExit - * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error + * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_VMENTRY_VMFAIL: Consistency check VMFail + * NVMX_VMENTRY_VMEXIT: Consistency check VMExit + * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error */ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) @@ -3609,8 +3609,15 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; + /* + * Clear the MTF state. If a higher priority VM-exit is delivered first, + * this state is discarded. + */ + vmx->nested.mtf_pending = false; + if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) @@ -3621,8 +3628,28 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } + /* + * Process any exceptions that are not debug traps before MTF. + */ + if (vcpu->arch.exception.pending && + !vmx_pending_dbg_trap(vcpu) && + nested_vmx_check_exception(vcpu, &exit_qual)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 0; + } + + if (mtf_pending) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0); + return 0; + } + if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + nested_vmx_check_exception(vcpu, &exit_qual)) { if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); @@ -5285,24 +5312,17 @@ fail: return 1; } - -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -5329,8 +5349,26 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, return false; } +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* - * Return 1 if we should exit from L2 to L1 to handle an MSR access access, + * Return 1 if we should exit from L2 to L1 to handle an MSR access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed * disinterest in the current event (read or write a specific MSR) by using an * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. @@ -5712,6 +5750,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx->nested.nested_run_pending) kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + + if (vmx->nested.mtf_pending) + kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; } } @@ -5892,6 +5933,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + vmx->nested.mtf_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); + ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != -1ull) { @@ -5949,8 +5993,7 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv) +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) { /* * Note that as a general rule, the high half of the MSRs (bits in @@ -5977,7 +6020,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | - (apicv ? PIN_BASED_POSTED_INTR : 0); + (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index fc874d4ead0f..9aeda46f473e 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,8 +17,7 @@ enum nvmx_vmentry_status { }; void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv); +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); @@ -34,6 +33,8 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -175,6 +176,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12) +{ + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); +} + static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3be25ecae145..63aaf44edd1f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv = 1; +bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -1175,6 +1175,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->guest_msrs[i].mask); } + + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); + if (vmx->guest_state_loaded) return; @@ -1599,6 +1603,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) return 1; } + +/* + * Recognizes a pending MTF VM-exit and records the nested state for later + * delivery. + */ +static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!is_guest_mode(vcpu)) + return; + + /* + * Per the SDM, MTF takes priority over debug-trap exceptions besides + * T-bit traps. As instruction emulation is completed (i.e. at the + * instruction boundary), any #DB exception pending delivery must be a + * debug-trap. Record the pending MTF state to be delivered in + * vmx_check_nested_events(). + */ + if (nested_cpu_has_mtf(vmcs12) && + (!vcpu->arch.exception.pending || + vcpu->arch.exception.nr == DB_VECTOR)) + vmx->nested.mtf_pending = true; + else + vmx->nested.mtf_pending = false; +} + +static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + vmx_update_emulated_instruction(vcpu); + return skip_emulated_instruction(vcpu); +} + static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* @@ -3818,24 +3856,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* @@ -6482,8 +6525,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); + /* + * We did this in prepare_switch_to_guest, because it needs to + * be within srcu_read_lock. + */ + WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -6757,8 +6803,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(vcpu)); + vmx_capability.ept); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); @@ -6839,8 +6884,7 @@ static int __init vmx_check_processor_compat(void) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); + nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -7101,6 +7145,39 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) to_vmx(vcpu)->req_immediate_exit = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) @@ -7108,19 +7185,31 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + switch (info->intercept) { /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -7702,7 +7791,7 @@ static __init int hardware_setup(void) if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); + vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -7786,7 +7875,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, .set_interrupt_shadow = vmx_set_interrupt_shadow, .get_interrupt_shadow = vmx_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f42cf3dcd70..e64da06c7009 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -150,6 +150,9 @@ struct nested_vmx { /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + /* Pending MTF VM-exit into L1. */ + bool mtf_pending; + struct loaded_vmcs vmcs02; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fb5d64ebc35d..359fcd395132 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6891,6 +6891,8 @@ restart: kvm_rip_write(vcpu, ctxt->eip); if (r && ctxt->tf) r = kvm_vcpu_do_singlestep(vcpu); + if (kvm_x86_ops->update_emulated_instruction) + kvm_x86_ops->update_emulated_instruction(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 1f756ffffe8b..79409120a603 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -896,14 +896,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; +#ifdef CONFIG_X86_64 + unsigned int which; + u64 base; +#endif ret = 0; switch (msr) { #ifdef CONFIG_X86_64 - unsigned which; - u64 base; - case MSR_FS_BASE: which = SEGBASE_FS; goto set; case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; diff --git a/drivers/base/core.c b/drivers/base/core.c index 42a672456432..fb8b7990f6fd 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3458,6 +3458,126 @@ out: } EXPORT_SYMBOL_GPL(device_move); +static int device_attrs_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + struct kobject *kobj = &dev->kobj; + struct class *class = dev->class; + const struct device_type *type = dev->type; + int error; + + if (class) { + /* + * Change the device groups of the device class for @dev to + * @kuid/@kgid. + */ + error = sysfs_groups_change_owner(kobj, class->dev_groups, kuid, + kgid); + if (error) + return error; + } + + if (type) { + /* + * Change the device groups of the device type for @dev to + * @kuid/@kgid. + */ + error = sysfs_groups_change_owner(kobj, type->groups, kuid, + kgid); + if (error) + return error; + } + + /* Change the device groups of @dev to @kuid/@kgid. */ + error = sysfs_groups_change_owner(kobj, dev->groups, kuid, kgid); + if (error) + return error; + + if (device_supports_offline(dev) && !dev->offline_disabled) { + /* Change online device attributes of @dev to @kuid/@kgid. */ + error = sysfs_file_change_owner(kobj, dev_attr_online.attr.name, + kuid, kgid); + if (error) + return error; + } + + return 0; +} + +/** + * device_change_owner - change the owner of an existing device. + * @dev: device. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * This changes the owner of @dev and its corresponding sysfs entries to + * @kuid/@kgid. This function closely mirrors how @dev was added via driver + * core. + * + * Returns 0 on success or error code on failure. + */ +int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) +{ + int error; + struct kobject *kobj = &dev->kobj; + + dev = get_device(dev); + if (!dev) + return -EINVAL; + + /* + * Change the kobject and the default attributes and groups of the + * ktype associated with it to @kuid/@kgid. + */ + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + goto out; + + /* + * Change the uevent file for @dev to the new owner. The uevent file + * was created in a separate step when @dev got added and we mirror + * that step here. + */ + error = sysfs_file_change_owner(kobj, dev_attr_uevent.attr.name, kuid, + kgid); + if (error) + goto out; + + /* + * Change the device groups, the device groups associated with the + * device class, and the groups associated with the device type of @dev + * to @kuid/@kgid. + */ + error = device_attrs_change_owner(dev, kuid, kgid); + if (error) + goto out; + + error = dpm_sysfs_change_owner(dev, kuid, kgid); + if (error) + goto out; + +#ifdef CONFIG_BLOCK + if (sysfs_deprecated && dev->class == &block_class) + goto out; +#endif + + /* + * Change the owner of the symlink located in the class directory of + * the device class associated with @dev which points to the actual + * directory entry for @dev to @kuid/@kgid. This ensures that the + * symlink shows the same permissions as its target. + */ + error = sysfs_link_change_owner(&dev->class->p->subsys.kobj, &dev->kobj, + dev_name(dev), kuid, kgid); + if (error) + goto out; + +out: + put_device(dev); + return error; +} +EXPORT_SYMBOL_GPL(device_change_owner); + /** * device_shutdown - call ->shutdown() on each device to shutdown. */ diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index 444f5c169a0b..54292cdd7808 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -74,6 +74,7 @@ extern int pm_qos_sysfs_add_flags(struct device *dev); extern void pm_qos_sysfs_remove_flags(struct device *dev); extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev); extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev); +extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); #else /* CONFIG_PM */ @@ -88,6 +89,8 @@ static inline void pm_runtime_remove(struct device *dev) {} static inline int dpm_sysfs_add(struct device *dev) { return 0; } static inline void dpm_sysfs_remove(struct device *dev) {} +static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) { return 0; } #endif diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index d7d82db2e4bc..2b99fe1eb207 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -480,6 +480,14 @@ static ssize_t wakeup_last_time_ms_show(struct device *dev, return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); } +static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + if (dev->power.wakeup && dev->power.wakeup->dev) + return device_change_owner(dev->power.wakeup->dev, kuid, kgid); + return 0; +} + static DEVICE_ATTR_RO(wakeup_last_time_ms); #ifdef CONFIG_PM_AUTOSLEEP @@ -501,7 +509,13 @@ static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); #endif /* CONFIG_PM_AUTOSLEEP */ -#endif /* CONFIG_PM_SLEEP */ +#else /* CONFIG_PM_SLEEP */ +static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} +#endif #ifdef CONFIG_PM_ADVANCED_DEBUG static ssize_t runtime_usage_show(struct device *dev, @@ -684,6 +698,45 @@ int dpm_sysfs_add(struct device *dev) return rc; } +int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) +{ + int rc; + + if (device_pm_not_required(dev)) + return 0; + + rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid); + if (rc) + return rc; + + if (pm_runtime_callbacks_present(dev)) { + rc = sysfs_group_change_owner( + &dev->kobj, &pm_runtime_attr_group, kuid, kgid); + if (rc) + return rc; + } + + if (device_can_wakeup(dev)) { + rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group, + kuid, kgid); + if (rc) + return rc; + + rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid); + if (rc) + return rc; + } + + if (dev->power.set_latency_tolerance) { + rc = sysfs_group_change_owner( + &dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid, + kgid); + if (rc) + return rc; + } + return 0; +} + int wakeup_sysfs_add(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cd3612e4e2e1..8ef65c085640 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -853,14 +853,17 @@ static void reset_fdc_info(int mode) /* selects the fdc and drive, and enables the fdc's input/dma. */ static void set_fdc(int drive) { + unsigned int new_fdc = fdc; + if (drive >= 0 && drive < N_DRIVE) { - fdc = FDC(drive); + new_fdc = FDC(drive); current_drive = drive; } - if (fdc != 1 && fdc != 0) { + if (new_fdc >= N_FDC) { pr_info("bad fdc value\n"); return; } + fdc = new_fdc; set_dor(fdc, ~0, 8); #if N_FDC > 1 set_dor(1 - fdc, ~8, 0); diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index ae79a7c66737..fa704153cb00 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -730,7 +730,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) if (data->has_sp) { input2 = input_allocate_device(); if (!input2) { - input_free_device(input2); + ret = -ENOMEM; goto exit; } diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 6ac8becc2372..d732d1d10caf 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -340,7 +340,8 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, unsigned long **bit, int *max) { if (usage->hid == (HID_UP_CUSTOM | 0x0003) || - usage->hid == (HID_UP_MSVENDOR | 0x0003)) { + usage->hid == (HID_UP_MSVENDOR | 0x0003) || + usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index 3f6abd190df4..db6da21ade06 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -174,6 +174,7 @@ static __u8 pid0902_rdesc_fixed[] = { struct bigben_device { struct hid_device *hid; struct hid_report *report; + bool removed; u8 led_state; /* LED1 = 1 .. LED4 = 8 */ u8 right_motor_on; /* right motor off/on 0/1 */ u8 left_motor_force; /* left motor force 0-255 */ @@ -190,6 +191,9 @@ static void bigben_worker(struct work_struct *work) struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; + if (bigben->removed) + return; + if (bigben->work_led) { bigben->work_led = false; report_field->value[0] = 0x01; /* 1 = led message */ @@ -220,10 +224,16 @@ static void bigben_worker(struct work_struct *work) static int hid_bigben_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { - struct bigben_device *bigben = data; + struct hid_device *hid = input_get_drvdata(dev); + struct bigben_device *bigben = hid_get_drvdata(hid); u8 right_motor_on; u8 left_motor_force; + if (!bigben) { + hid_err(hid, "no device data\n"); + return 0; + } + if (effect->type != FF_RUMBLE) return 0; @@ -298,8 +308,8 @@ static void bigben_remove(struct hid_device *hid) { struct bigben_device *bigben = hid_get_drvdata(hid); + bigben->removed = true; cancel_work_sync(&bigben->worker); - hid_hw_close(hid); hid_hw_stop(hid); } @@ -319,6 +329,7 @@ static int bigben_probe(struct hid_device *hid, return -ENOMEM; hid_set_drvdata(hid, bigben); bigben->hid = hid; + bigben->removed = false; error = hid_parse(hid); if (error) { @@ -341,10 +352,10 @@ static int bigben_probe(struct hid_device *hid, INIT_WORK(&bigben->worker, bigben_worker); - error = input_ff_create_memless(hidinput->input, bigben, + error = input_ff_create_memless(hidinput->input, NULL, hid_bigben_play_effect); if (error) - return error; + goto error_hw_stop; name_sz = strlen(dev_name(&hid->dev)) + strlen(":red:bigben#") + 1; @@ -354,8 +365,10 @@ static int bigben_probe(struct hid_device *hid, sizeof(struct led_classdev) + name_sz, GFP_KERNEL ); - if (!led) - return -ENOMEM; + if (!led) { + error = -ENOMEM; + goto error_hw_stop; + } name = (void *)(&led[1]); snprintf(name, name_sz, "%s:red:bigben%d", @@ -369,7 +382,7 @@ static int bigben_probe(struct hid_device *hid, bigben->leds[n] = led; error = devm_led_classdev_register(&hid->dev, led); if (error) - return error; + goto error_hw_stop; } /* initial state: LED1 is on, no rumble effect */ @@ -383,6 +396,10 @@ static int bigben_probe(struct hid_device *hid, hid_info(hid, "LED and force feedback support for BigBen gamepad\n"); return 0; + +error_hw_stop: + hid_hw_stop(hid); + return error; } static __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 851fe54ea59e..359616e3efbb 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1741,7 +1741,9 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = ((report->size - 1) >> 3) + 1; - if (rsize > HID_MAX_BUFFER_SIZE) + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; + else if (rsize > HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE; if (csize < rsize) { diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index c436e12feb23..6c55682c5974 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -41,8 +41,9 @@ static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ - { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 70e1cb928bf0..094f4f1b6555 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1256,36 +1256,35 @@ static int hidpp20_battery_map_status_voltage(u8 data[3], int *voltage, { int status; - long charge_sts = (long)data[2]; + long flags = (long) data[2]; - *level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN; - switch (data[2] & 0xe0) { - case 0x00: - status = POWER_SUPPLY_STATUS_CHARGING; - break; - case 0x20: - status = POWER_SUPPLY_STATUS_FULL; - *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL; - break; - case 0x40: + if (flags & 0x80) + switch (flags & 0x07) { + case 0: + status = POWER_SUPPLY_STATUS_CHARGING; + break; + case 1: + status = POWER_SUPPLY_STATUS_FULL; + *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL; + break; + case 2: + status = POWER_SUPPLY_STATUS_NOT_CHARGING; + break; + default: + status = POWER_SUPPLY_STATUS_UNKNOWN; + break; + } + else status = POWER_SUPPLY_STATUS_DISCHARGING; - break; - case 0xe0: - status = POWER_SUPPLY_STATUS_NOT_CHARGING; - break; - default: - status = POWER_SUPPLY_STATUS_UNKNOWN; - } *charge_type = POWER_SUPPLY_CHARGE_TYPE_STANDARD; - if (test_bit(3, &charge_sts)) { + if (test_bit(3, &flags)) { *charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST; } - if (test_bit(4, &charge_sts)) { + if (test_bit(4, &flags)) { *charge_type = POWER_SUPPLY_CHARGE_TYPE_TRICKLE; } - - if (test_bit(5, &charge_sts)) { + if (test_bit(5, &flags)) { *level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL; } diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index d31ea82b84c1..a66f08041a1a 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -342,6 +342,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { .driver_data = (void *)&sipodev_desc }, { + .ident = "Trekstor SURFBOOK E11B", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SURFBOOK E11B"), + }, + .driver_data = (void *)&sipodev_desc + }, + { .ident = "Direkt-Tek DTLAPY116-2", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index a970b809d778..4140dea693e9 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -932,9 +932,9 @@ void hiddev_disconnect(struct hid_device *hid) hiddev->exist = 0; if (hiddev->open) { - mutex_unlock(&hiddev->existancelock); hid_hw_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); + mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 4cf25458f0b9..0db8ef4fd6e1 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -355,7 +355,9 @@ static ssize_t show_str(struct device *dev, struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_power_meter_resource *resource = acpi_dev->driver_data; acpi_string val; + int ret; + mutex_lock(&resource->lock); switch (attr->index) { case 0: val = resource->model_number; @@ -372,8 +374,9 @@ static ssize_t show_str(struct device *dev, val = ""; break; } - - return sprintf(buf, "%s\n", val); + ret = sprintf(buf, "%s\n", val); + mutex_unlock(&resource->lock); + return ret; } static ssize_t show_val(struct device *dev, @@ -817,11 +820,12 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) resource = acpi_driver_data(device); - mutex_lock(&resource->lock); switch (event) { case METER_NOTIFY_CONFIG: + mutex_lock(&resource->lock); free_capabilities(resource); res = read_capabilities(resource); + mutex_unlock(&resource->lock); if (res) break; @@ -830,15 +834,12 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) break; case METER_NOTIFY_TRIP: sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME); - update_meter(resource); break; case METER_NOTIFY_CAP: sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME); - update_cap(resource); break; case METER_NOTIFY_INTERVAL: sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME); - update_avg_interval(resource); break; case METER_NOTIFY_CAPPING: sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME); @@ -848,7 +849,6 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) WARN(1, "Unexpected event %d\n", event); break; } - mutex_unlock(&resource->lock); acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS, dev_name(&device->dev), event, 0); @@ -912,8 +912,8 @@ static int acpi_power_meter_remove(struct acpi_device *device) resource = acpi_driver_data(device); hwmon_device_unregister(resource->hwmon_dev); - free_capabilities(resource); remove_attrs(resource); + free_capabilities(resource); kfree(resource); return 0; diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index 7ffadc2da57b..5a5120121e50 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -1346,8 +1346,13 @@ w83627ehf_is_visible(const void *drvdata, enum hwmon_sensor_types type, /* channel 0.., name 1.. */ if (!(data->have_temp & (1 << channel))) return 0; - if (attr == hwmon_temp_input || attr == hwmon_temp_label) + if (attr == hwmon_temp_input) return 0444; + if (attr == hwmon_temp_label) { + if (data->temp_label) + return 0444; + return 0; + } if (channel == 2 && data->temp3_val_only) return 0; if (attr == hwmon_temp_max) { diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index b273e421e910..a1a035270cab 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2575,6 +2575,17 @@ isert_wait4logout(struct isert_conn *isert_conn) } } +static void +isert_wait4cmds(struct iscsi_conn *conn) +{ + isert_info("iscsi_conn %p\n", conn); + + if (conn->sess) { + target_sess_cmd_list_set_waiting(conn->sess->se_sess); + target_wait_for_sess_cmds(conn->sess->se_sess); + } +} + /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -2622,6 +2633,7 @@ static void isert_wait_conn(struct iscsi_conn *conn) ib_drain_qp(isert_conn->qp); isert_put_unsol_pending_cmds(conn); + isert_wait4cmds(conn); isert_wait4logout(isert_conn); queue_work(isert_release_wq, &isert_conn->release_work); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 25a8f9387d5a..66e410e58c8e 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -258,6 +258,19 @@ config GENEVE To compile this driver as a module, choose M here: the module will be called geneve. +config BAREUDP + tristate "Bare UDP Encapsulation" + depends on INET + depends on IPV6 || !IPV6 + select NET_UDP_TUNNEL + select GRO_CELLS + help + This adds a bare UDP tunnel module for tunnelling different + kinds of traffic like MPLS, IP, etc. inside a UDP tunnel. + + To compile this driver as a module, choose M here: the module + will be called bareudp. + config GTP tristate "GPRS Tunneling Protocol datapath (GTP-U)" depends on INET diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 71b88ffc5587..65967246f240 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_VETH) += veth.o obj-$(CONFIG_VIRTIO_NET) += virtio_net.o obj-$(CONFIG_VXLAN) += vxlan.o obj-$(CONFIG_GENEVE) += geneve.o +obj-$(CONFIG_BAREUDP) += bareudp.o obj-$(CONFIG_GTP) += gtp.o obj-$(CONFIG_NLMON) += nlmon.o obj-$(CONFIG_NET_VRF) += vrf.o diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c new file mode 100644 index 000000000000..15337e9d4fad --- /dev/null +++ b/drivers/net/bareudp.c @@ -0,0 +1,806 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Bareudp: UDP tunnel encasulation for different Payload types like + * MPLS, NSH, IP, etc. + * Copyright (c) 2019 Nokia, Inc. + * Authors: Martin Varghese, <martin.varghese@nokia.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/etherdevice.h> +#include <linux/hash.h> +#include <net/dst_metadata.h> +#include <net/gro_cells.h> +#include <net/rtnetlink.h> +#include <net/protocol.h> +#include <net/ip6_tunnel.h> +#include <net/ip_tunnels.h> +#include <net/udp_tunnel.h> +#include <net/bareudp.h> + +#define BAREUDP_BASE_HLEN sizeof(struct udphdr) +#define BAREUDP_IPV4_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr)) +#define BAREUDP_IPV6_HLEN (sizeof(struct ipv6hdr) + \ + sizeof(struct udphdr)) + +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + +/* per-network namespace private data for this module */ + +static unsigned int bareudp_net_id; + +struct bareudp_net { + struct list_head bareudp_list; +}; + +/* Pseudo network device */ +struct bareudp_dev { + struct net *net; /* netns for packet i/o */ + struct net_device *dev; /* netdev for bareudp tunnel */ + __be16 ethertype; + __be16 port; + u16 sport_min; + bool multi_proto_mode; + struct socket __rcu *sock; + struct list_head next; /* bareudp node on namespace list */ + struct gro_cells gro_cells; +}; + +static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) +{ + struct metadata_dst *tun_dst = NULL; + struct pcpu_sw_netstats *stats; + struct bareudp_dev *bareudp; + unsigned short family; + unsigned int len; + __be16 proto; + void *oiph; + int err; + + bareudp = rcu_dereference_sk_user_data(sk); + if (!bareudp) + goto drop; + + if (skb->protocol == htons(ETH_P_IP)) + family = AF_INET; + else + family = AF_INET6; + + if (bareudp->ethertype == htons(ETH_P_IP)) { + struct iphdr *iphdr; + + iphdr = (struct iphdr *)(skb->data + BAREUDP_BASE_HLEN); + if (iphdr->version == 4) { + proto = bareudp->ethertype; + } else if (bareudp->multi_proto_mode && (iphdr->version == 6)) { + proto = htons(ETH_P_IPV6); + } else { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) { + struct iphdr *tunnel_hdr; + + tunnel_hdr = (struct iphdr *)skb_network_header(skb); + if (tunnel_hdr->version == 4) { + if (!ipv4_is_multicast(tunnel_hdr->daddr)) { + proto = bareudp->ethertype; + } else if (bareudp->multi_proto_mode && + ipv4_is_multicast(tunnel_hdr->daddr)) { + proto = htons(ETH_P_MPLS_MC); + } else { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + } else { + int addr_type; + struct ipv6hdr *tunnel_hdr_v6; + + tunnel_hdr_v6 = (struct ipv6hdr *)skb_network_header(skb); + addr_type = + ipv6_addr_type((struct in6_addr *)&tunnel_hdr_v6->daddr); + if (!(addr_type & IPV6_ADDR_MULTICAST)) { + proto = bareudp->ethertype; + } else if (bareudp->multi_proto_mode && + (addr_type & IPV6_ADDR_MULTICAST)) { + proto = htons(ETH_P_MPLS_MC); + } else { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + } + } else { + proto = bareudp->ethertype; + } + + if (iptunnel_pull_header(skb, BAREUDP_BASE_HLEN, + proto, + !net_eq(bareudp->net, + dev_net(bareudp->dev)))) { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + + tun_dst = udp_tun_rx_dst(skb, family, TUNNEL_KEY, 0, 0); + if (!tun_dst) { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + skb_dst_set(skb, &tun_dst->dst); + skb->dev = bareudp->dev; + oiph = skb_network_header(skb); + skb_reset_network_header(skb); + + if (family == AF_INET) + err = IP_ECN_decapsulate(oiph, skb); +#if IS_ENABLED(CONFIG_IPV6) + else + err = IP6_ECN_decapsulate(oiph, skb); +#endif + + if (unlikely(err)) { + if (log_ecn_error) { + if (family == AF_INET) + net_info_ratelimited("non-ECT from %pI4 " + "with TOS=%#x\n", + &((struct iphdr *)oiph)->saddr, + ((struct iphdr *)oiph)->tos); +#if IS_ENABLED(CONFIG_IPV6) + else + net_info_ratelimited("non-ECT from %pI6\n", + &((struct ipv6hdr *)oiph)->saddr); +#endif + } + if (err > 1) { + ++bareudp->dev->stats.rx_frame_errors; + ++bareudp->dev->stats.rx_errors; + goto drop; + } + } + + len = skb->len; + err = gro_cells_receive(&bareudp->gro_cells, skb); + if (likely(err == NET_RX_SUCCESS)) { + stats = this_cpu_ptr(bareudp->dev->tstats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += len; + u64_stats_update_end(&stats->syncp); + } + return 0; +drop: + /* Consume bad packet */ + kfree_skb(skb); + + return 0; +} + +static int bareudp_err_lookup(struct sock *sk, struct sk_buff *skb) +{ + return 0; +} + +static int bareudp_init(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + int err; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&bareudp->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + return 0; +} + +static void bareudp_uninit(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + gro_cells_destroy(&bareudp->gro_cells); + free_percpu(dev->tstats); +} + +static struct socket *bareudp_create_sock(struct net *net, __be16 port) +{ + struct udp_port_cfg udp_conf; + struct socket *sock; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); +#if IS_ENABLED(CONFIG_IPV6) + udp_conf.family = AF_INET6; +#else + udp_conf.family = AF_INET; +#endif + udp_conf.local_udp_port = port; + /* Open UDP socket */ + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + return ERR_PTR(err); + + return sock; +} + +/* Create new listen socket if needed */ +static int bareudp_socket_create(struct bareudp_dev *bareudp, __be16 port) +{ + struct udp_tunnel_sock_cfg tunnel_cfg; + struct socket *sock; + + sock = bareudp_create_sock(bareudp->net, port); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + /* Mark socket as an encapsulation socket */ + memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); + tunnel_cfg.sk_user_data = bareudp; + tunnel_cfg.encap_type = 1; + tunnel_cfg.encap_rcv = bareudp_udp_encap_recv; + tunnel_cfg.encap_err_lookup = bareudp_err_lookup; + tunnel_cfg.encap_destroy = NULL; + setup_udp_tunnel_sock(bareudp->net, sock, &tunnel_cfg); + + if (sock->sk->sk_family == AF_INET6) + udp_encap_enable(); + + rcu_assign_pointer(bareudp->sock, sock); + return 0; +} + +static int bareudp_open(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + int ret = 0; + + ret = bareudp_socket_create(bareudp, bareudp->port); + return ret; +} + +static void bareudp_sock_release(struct bareudp_dev *bareudp) +{ + struct socket *sock; + + sock = bareudp->sock; + rcu_assign_pointer(bareudp->sock, NULL); + synchronize_net(); + udp_tunnel_sock_release(sock); +} + +static int bareudp_stop(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + bareudp_sock_release(bareudp); + return 0; +} + +static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct bareudp_dev *bareudp, + const struct ip_tunnel_info *info) +{ + bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct socket *sock = rcu_dereference(bareudp->sock); + bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + const struct ip_tunnel_key *key = &info->key; + struct rtable *rt; + __be16 sport, df; + int min_headroom; + __u8 tos, ttl; + __be32 saddr; + int err; + + if (!sock) + return -ESHUTDOWN; + + rt = ip_route_output_tunnel(skb, dev, bareudp->net, &saddr, info, + IPPROTO_UDP, use_cache); + + if (IS_ERR(rt)) + return PTR_ERR(rt); + + skb_tunnel_check_pmtu(skb, &rt->dst, + BAREUDP_IPV4_HLEN + info->options_len); + + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); + tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); + ttl = key->ttl; + df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + skb_scrub_packet(skb, xnet); + + err = -ENOSPC; + if (!skb_pull(skb, skb_network_offset(skb))) + goto free_dst; + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); + + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + goto free_dst; + + err = udp_tunnel_handle_offloads(skb, udp_sum); + if (err) + goto free_dst; + + skb_set_inner_protocol(skb, bareudp->ethertype); + udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst, + tos, ttl, df, sport, bareudp->port, + !net_eq(bareudp->net, dev_net(bareudp->dev)), + !(info->key.tun_flags & TUNNEL_CSUM)); + return 0; + +free_dst: + dst_release(&rt->dst); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct bareudp_dev *bareudp, + const struct ip_tunnel_info *info) +{ + bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct socket *sock = rcu_dereference(bareudp->sock); + bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + const struct ip_tunnel_key *key = &info->key; + struct dst_entry *dst = NULL; + struct in6_addr saddr, daddr; + int min_headroom; + __u8 prio, ttl; + __be16 sport; + int err; + + if (!sock) + return -ESHUTDOWN; + + dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, &saddr, info, + IPPROTO_UDP, use_cache); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len); + + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); + prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); + ttl = key->ttl; + + skb_scrub_packet(skb, xnet); + + err = -ENOSPC; + if (!skb_pull(skb, skb_network_offset(skb))) + goto free_dst; + + min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); + + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + goto free_dst; + + err = udp_tunnel_handle_offloads(skb, udp_sum); + if (err) + goto free_dst; + + daddr = info->key.u.ipv6.dst; + udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev, + &saddr, &daddr, prio, ttl, + info->key.label, sport, bareudp->port, + !(info->key.tun_flags & TUNNEL_CSUM)); + return 0; + +free_dst: + dst_release(dst); + return err; +} +#endif + +static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + struct ip_tunnel_info *info = NULL; + int err; + + if (skb->protocol != bareudp->ethertype) { + if (!bareudp->multi_proto_mode || + (skb->protocol != htons(ETH_P_MPLS_MC) && + skb->protocol != htons(ETH_P_IPV6))) { + err = -EINVAL; + goto tx_error; + } + } + + info = skb_tunnel_info(skb); + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { + err = -EINVAL; + goto tx_error; + } + + rcu_read_lock(); +#if IS_ENABLED(CONFIG_IPV6) + if (info->mode & IP_TUNNEL_INFO_IPV6) + err = bareudp6_xmit_skb(skb, dev, bareudp, info); + else +#endif + err = bareudp_xmit_skb(skb, dev, bareudp, info); + + rcu_read_unlock(); + + if (likely(!err)) + return NETDEV_TX_OK; +tx_error: + dev_kfree_skb(skb); + + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +static int bareudp_fill_metadata_dst(struct net_device *dev, + struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct bareudp_dev *bareudp = netdev_priv(dev); + bool use_cache; + + use_cache = ip_tunnel_dst_cache_usable(skb, info); + + if (ip_tunnel_info_af(info) == AF_INET) { + struct rtable *rt; + __be32 saddr; + + rt = ip_route_output_tunnel(skb, dev, bareudp->net, &saddr, + info, IPPROTO_UDP, use_cache); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = saddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (ip_tunnel_info_af(info) == AF_INET6) { + struct dst_entry *dst; + struct in6_addr saddr; + struct socket *sock = rcu_dereference(bareudp->sock); + + dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, + &saddr, info, IPPROTO_UDP, + use_cache); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + dst_release(dst); + info->key.u.ipv6.src = saddr; +#endif + } else { + return -EINVAL; + } + + info->key.tp_src = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, + USHRT_MAX, true); + info->key.tp_dst = bareudp->port; + return 0; +} + +static const struct net_device_ops bareudp_netdev_ops = { + .ndo_init = bareudp_init, + .ndo_uninit = bareudp_uninit, + .ndo_open = bareudp_open, + .ndo_stop = bareudp_stop, + .ndo_start_xmit = bareudp_xmit, + .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_fill_metadata_dst = bareudp_fill_metadata_dst, +}; + +static const struct nla_policy bareudp_policy[IFLA_BAREUDP_MAX + 1] = { + [IFLA_BAREUDP_PORT] = { .type = NLA_U16 }, + [IFLA_BAREUDP_ETHERTYPE] = { .type = NLA_U16 }, + [IFLA_BAREUDP_SRCPORT_MIN] = { .type = NLA_U16 }, + [IFLA_BAREUDP_MULTIPROTO_MODE] = { .type = NLA_FLAG }, +}; + +/* Info for udev, that this is a virtual tunnel endpoint */ +static struct device_type bareudp_type = { + .name = "bareudp", +}; + +/* Initialize the device structure. */ +static void bareudp_setup(struct net_device *dev) +{ + dev->netdev_ops = &bareudp_netdev_ops; + dev->needs_free_netdev = true; + SET_NETDEV_DEVTYPE(dev, &bareudp_type); + dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM; + dev->features |= NETIF_F_RXCSUM; + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->mtu = ETH_DATA_LEN; + dev->min_mtu = IPV4_MIN_MTU; + dev->max_mtu = IP_MAX_MTU - BAREUDP_BASE_HLEN; + dev->type = ARPHRD_NONE; + netif_keep_dst(dev); + dev->priv_flags |= IFF_NO_QUEUE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; +} + +static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (!data) { + NL_SET_ERR_MSG(extack, + "Not enough attributes provided to perform the operation"); + return -EINVAL; + } + return 0; +} + +static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf) +{ + if (!data[IFLA_BAREUDP_PORT] || !data[IFLA_BAREUDP_ETHERTYPE]) + return -EINVAL; + + if (data[IFLA_BAREUDP_PORT]) + conf->port = nla_get_u16(data[IFLA_BAREUDP_PORT]); + + if (data[IFLA_BAREUDP_ETHERTYPE]) + conf->ethertype = nla_get_u16(data[IFLA_BAREUDP_ETHERTYPE]); + + if (data[IFLA_BAREUDP_SRCPORT_MIN]) + conf->sport_min = nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]); + + return 0; +} + +static struct bareudp_dev *bareudp_find_dev(struct bareudp_net *bn, + const struct bareudp_conf *conf) +{ + struct bareudp_dev *bareudp, *t = NULL; + + list_for_each_entry(bareudp, &bn->bareudp_list, next) { + if (conf->port == bareudp->port) + t = bareudp; + } + return t; +} + +static int bareudp_configure(struct net *net, struct net_device *dev, + struct bareudp_conf *conf) +{ + struct bareudp_net *bn = net_generic(net, bareudp_net_id); + struct bareudp_dev *t, *bareudp = netdev_priv(dev); + int err; + + bareudp->net = net; + bareudp->dev = dev; + t = bareudp_find_dev(bn, conf); + if (t) + return -EBUSY; + + if (conf->multi_proto_mode && + (conf->ethertype != htons(ETH_P_MPLS_UC) && + conf->ethertype != htons(ETH_P_IP))) + return -EINVAL; + + bareudp->port = conf->port; + bareudp->ethertype = conf->ethertype; + bareudp->sport_min = conf->sport_min; + bareudp->multi_proto_mode = conf->multi_proto_mode; + err = register_netdevice(dev); + if (err) + return err; + + list_add(&bareudp->next, &bn->bareudp_list); + return 0; +} + +static int bareudp_link_config(struct net_device *dev, + struct nlattr *tb[]) +{ + int err; + + if (tb[IFLA_MTU]) { + err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + if (err) + return err; + } + return 0; +} + +static int bareudp_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct bareudp_conf conf; + int err; + + err = bareudp2info(data, &conf); + if (err) + return err; + + err = bareudp_configure(net, dev, &conf); + if (err) + return err; + + err = bareudp_link_config(dev, tb); + if (err) + return err; + + return 0; +} + +static void bareudp_dellink(struct net_device *dev, struct list_head *head) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + list_del(&bareudp->next); + unregister_netdevice_queue(dev, head); +} + +static size_t bareudp_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_PORT */ + nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_ETHERTYPE */ + nla_total_size(sizeof(__u16)) + /* IFLA_BAREUDP_SRCPORT_MIN */ + nla_total_size(0) + /* IFLA_BAREUDP_MULTIPROTO_MODE */ + 0; +} + +static int bareudp_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + if (nla_put_be16(skb, IFLA_BAREUDP_PORT, bareudp->port)) + goto nla_put_failure; + if (nla_put_be16(skb, IFLA_BAREUDP_ETHERTYPE, bareudp->ethertype)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BAREUDP_SRCPORT_MIN, bareudp->sport_min)) + goto nla_put_failure; + if (bareudp->multi_proto_mode && + nla_put_flag(skb, IFLA_BAREUDP_MULTIPROTO_MODE)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static struct rtnl_link_ops bareudp_link_ops __read_mostly = { + .kind = "bareudp", + .maxtype = IFLA_BAREUDP_MAX, + .policy = bareudp_policy, + .priv_size = sizeof(struct bareudp_dev), + .setup = bareudp_setup, + .validate = bareudp_validate, + .newlink = bareudp_newlink, + .dellink = bareudp_dellink, + .get_size = bareudp_get_size, + .fill_info = bareudp_fill_info, +}; + +struct net_device *bareudp_dev_create(struct net *net, const char *name, + u8 name_assign_type, + struct bareudp_conf *conf) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + LIST_HEAD(list_kill); + int err; + + memset(tb, 0, sizeof(tb)); + dev = rtnl_create_link(net, name, name_assign_type, + &bareudp_link_ops, tb, NULL); + if (IS_ERR(dev)) + return dev; + + err = bareudp_configure(net, dev, conf); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } + err = dev_set_mtu(dev, IP_MAX_MTU - BAREUDP_BASE_HLEN); + if (err) + goto err; + + err = rtnl_configure_link(dev, NULL); + if (err < 0) + goto err; + + return dev; +err: + bareudp_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(bareudp_dev_create); + +static __net_init int bareudp_init_net(struct net *net) +{ + struct bareudp_net *bn = net_generic(net, bareudp_net_id); + + INIT_LIST_HEAD(&bn->bareudp_list); + return 0; +} + +static void bareudp_destroy_tunnels(struct net *net, struct list_head *head) +{ + struct bareudp_net *bn = net_generic(net, bareudp_net_id); + struct bareudp_dev *bareudp, *next; + + list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next) + unregister_netdevice_queue(bareudp->dev, head); +} + +static void __net_exit bareudp_exit_batch_net(struct list_head *net_list) +{ + struct net *net; + LIST_HEAD(list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + bareudp_destroy_tunnels(net, &list); + + /* unregister the devices gathered above */ + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations bareudp_net_ops = { + .init = bareudp_init_net, + .exit_batch = bareudp_exit_batch_net, + .id = &bareudp_net_id, + .size = sizeof(struct bareudp_net), +}; + +static int __init bareudp_init_module(void) +{ + int rc; + + rc = register_pernet_subsys(&bareudp_net_ops); + if (rc) + goto out1; + + rc = rtnl_link_register(&bareudp_link_ops); + if (rc) + goto out2; + + return 0; +out2: + unregister_pernet_subsys(&bareudp_net_ops); +out1: + return rc; +} +late_initcall(bareudp_init_module); + +static void __exit bareudp_cleanup_module(void) +{ + rtnl_link_unregister(&bareudp_link_ops); + unregister_pernet_subsys(&bareudp_net_ops); +} +module_exit(bareudp_cleanup_module); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Varghese <martin.varghese@nokia.com>"); +MODULE_DESCRIPTION("Interface driver for UDP encapsulated traffic"); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c68c1d1387ee..2e70e43c5df5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4370,7 +4370,6 @@ static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, struct ethtool_drvinfo *drvinfo) { strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", BOND_ABI_VERSION); } @@ -5008,8 +5007,6 @@ static int __init bonding_init(void) int i; int res; - pr_info("%s", bond_version); - res = bond_check_params(&bonding_defaults); if (res) goto out; @@ -5064,6 +5061,5 @@ static void __exit bonding_exit(void) module_init(bonding_init); module_exit(bonding_exit); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); -MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION); +MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h index 5a4d81a9437c..45b77bc8c7b3 100644 --- a/drivers/net/bonding/bonding_priv.h +++ b/drivers/net/bonding/bonding_priv.h @@ -14,12 +14,11 @@ #ifndef _BONDING_PRIV_H #define _BONDING_PRIV_H +#include <linux/vermagic.h> -#define DRV_VERSION "3.7.1" -#define DRV_RELDATE "April 27, 2011" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" -#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" +#define bond_version DRV_DESCRIPTION ": v" UTS_RELEASE "\n" #endif diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 1a69286daa8d..ceafce446317 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1289,7 +1289,9 @@ EXPORT_SYMBOL(b53_phylink_mac_link_down); void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct b53_device *dev = ds->priv; diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 3c30f3a7eb29..3d42318bc3f1 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -338,7 +338,9 @@ void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev); + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering); int b53_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 6feaf8cb0809..368ead87e07a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -69,8 +69,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) /* Force link status for IMP port */ reg = core_readl(priv, offset); reg |= (MII_SW_OR | LINK_STS); - if (priv->type == BCM7278_DEVICE_ID) - reg |= GMII_SPEED_UP_2G; + reg &= ~GMII_SPEED_UP_2G; core_writel(priv, reg, offset); /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ @@ -616,9 +615,6 @@ force_link: if (state->duplex == DUPLEX_FULL) reg |= DUPLX_MODE; - if (priv->type == BCM7278_DEVICE_ID && dsa_is_cpu_port(ds, port)) - reg |= GMIIP_SPEED_UP_2G; - core_writel(priv, reg, offset); } @@ -652,7 +648,9 @@ static void bcm_sf2_sw_mac_link_down(struct dsa_switch *ds, int port, static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); struct ethtool_eee *p = &priv->dev->ports[port].eee; diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h index 784478176335..d8a5e6269c0e 100644 --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -178,7 +178,6 @@ enum bcm_sf2_reg_offs { #define RXFLOW_CNTL (1 << 4) #define TXFLOW_CNTL (1 << 5) #define SW_OVERRIDE (1 << 6) -#define GMIIP_SPEED_UP_2G (1 << 7) #define CORE_WATCHDOG_CTRL 0x001e4 #define SOFTWARE_RESET (1 << 7) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 0369c22fe3e1..cf6fa8fede33 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1517,7 +1517,9 @@ static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port, static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct gswip_priv *priv = ds->priv; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 022466ca1c19..86818ab3bb07 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1482,7 +1482,9 @@ static void mt7530_phylink_mac_link_down(struct dsa_switch *ds, int port, static void mt7530_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct mt7530_priv *priv = ds->priv; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 4ec09cc8dcdc..483db9d133c3 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -632,33 +632,78 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, dev_err(ds->dev, "p%d: failed to configure MAC\n", port); } -static void mv88e6xxx_mac_link_force(struct dsa_switch *ds, int port, int link) +static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) { struct mv88e6xxx_chip *chip = ds->priv; - int err; + const struct mv88e6xxx_ops *ops; + int err = 0; - mv88e6xxx_reg_lock(chip); - err = chip->info->ops->port_set_link(chip, port, link); - mv88e6xxx_reg_unlock(chip); + ops = chip->info->ops; - if (err) - dev_err(chip->dev, "p%d: failed to force MAC link\n", port); -} + /* Internal PHYs propagate their configuration directly to the MAC. + * External PHYs depend on whether the PPU is enabled for this port. + * FIXME: we should be using the PPU enable state here. What about + * an automedia port? + */ + if (!mv88e6xxx_phy_is_internal(ds, port) && ops->port_set_link) { + mv88e6xxx_reg_lock(chip); + err = ops->port_set_link(chip, port, LINK_FORCED_DOWN); + mv88e6xxx_reg_unlock(chip); -static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface) -{ - if (mode == MLO_AN_FIXED) - mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_DOWN); + if (err) + dev_err(chip->dev, + "p%d: failed to force MAC link down\n", port); + } } static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { - if (mode == MLO_AN_FIXED) - mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_UP); + struct mv88e6xxx_chip *chip = ds->priv; + const struct mv88e6xxx_ops *ops; + int err = 0; + + ops = chip->info->ops; + + /* Internal PHYs propagate their configuration directly to the MAC. + * External PHYs depend on whether the PPU is enabled for this port. + * FIXME: we should be using the PPU enable state here. What about + * an automedia port? + */ + if (!mv88e6xxx_phy_is_internal(ds, port)) { + mv88e6xxx_reg_lock(chip); + /* FIXME: for an automedia port, should we force the link + * down here - what if the link comes up due to "other" media + * while we're bringing the port up, how is the exclusivity + * handled in the Marvell hardware? E.g. port 4 on 88E6532 + * shared between internal PHY and Serdes. + */ + if (ops->port_set_speed) { + err = ops->port_set_speed(chip, port, speed); + if (err && err != -EOPNOTSUPP) + goto error; + } + + if (ops->port_set_duplex) { + err = ops->port_set_duplex(chip, port, duplex); + if (err && err != -EOPNOTSUPP) + goto error; + } + + if (ops->port_set_link) + err = ops->port_set_link(chip, port, LINK_FORCED_UP); +error: + mv88e6xxx_reg_unlock(chip); + + if (err && err != -EOPNOTSUPP) + dev_err(ds->dev, + "p%d: failed to configure MAC link up\n", port); + } } static int mv88e6xxx_stats_snapshot(struct mv88e6xxx_chip *chip, int port) @@ -1795,7 +1840,7 @@ static int mv88e6xxx_broadcast_setup(struct mv88e6xxx_chip *chip, u16 vid) } static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, - u16 vid, u8 member) + u16 vid, u8 member, bool warn) { const u8 non_member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER; struct mv88e6xxx_vtu_entry vlan; @@ -1840,7 +1885,7 @@ static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, err = mv88e6xxx_vtu_loadpurge(chip, &vlan); if (err) return err; - } else { + } else if (warn) { dev_info(chip->dev, "p%d: already a member of VLAN %d\n", port, vid); } @@ -1854,6 +1899,7 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + bool warn; u8 member; u16 vid; @@ -1867,10 +1913,15 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, else member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_TAGGED; + /* net/dsa/slave.c will call dsa_port_vlan_add() for the affected port + * and then the CPU port. Do not warn for duplicates for the CPU port. + */ + warn = !dsa_is_cpu_port(ds, port) && !dsa_is_dsa_port(ds, port); + mv88e6xxx_reg_lock(chip); for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) - if (mv88e6xxx_port_vlan_join(chip, port, vid, member)) + if (mv88e6xxx_port_vlan_join(chip, port, vid, member, warn)) dev_err(ds->dev, "p%d: failed to add VLAN %d%c\n", port, vid, untagged ? 'u' : 't'); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index b016cc205f81..ca3a7a7a73c3 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -278,13 +278,13 @@ int mv88e6095_g1_set_egress_port(struct mv88e6xxx_chip *chip, switch (direction) { case MV88E6XXX_EGRESS_DIR_INGRESS: dest_port_chip = &chip->ingress_dest_port; - reg &= MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK; + reg &= ~MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK; reg |= port << __bf_shf(MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK); break; case MV88E6XXX_EGRESS_DIR_EGRESS: dest_port_chip = &chip->egress_dest_port; - reg &= MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK; + reg &= ~MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK; reg |= port << __bf_shf(MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK); break; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3257962c147e..7e66821b05b4 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -176,8 +176,7 @@ static void felix_phylink_validate(struct dsa_switch *ds, int port, phylink_set(mask, 100baseT_Full); phylink_set(mask, 1000baseT_Full); - /* The internal ports that run at 2.5G are overclocked GMII */ - if (state->interface == PHY_INTERFACE_MODE_GMII || + if (state->interface == PHY_INTERFACE_MODE_INTERNAL || state->interface == PHY_INTERFACE_MODE_2500BASEX || state->interface == PHY_INTERFACE_MODE_USXGMII) { phylink_set(mask, 2500baseT_Full); @@ -264,7 +263,9 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int link_an_mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct ocelot *ocelot = ds->priv; struct ocelot_port *ocelot_port = ocelot->ports[port]; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 2c812b481778..93800e81cdd4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -955,8 +955,7 @@ static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port, phy_interface_t phy_mode) { switch (phy_mode) { - case PHY_INTERFACE_MODE_GMII: - /* Only supported on internal to-CPU ports */ + case PHY_INTERFACE_MODE_INTERNAL: if (port != 4 && port != 5) return -ENOTSUPP; return 0; diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index de25f99e995a..7c86056b9401 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -458,7 +458,9 @@ static void ar9331_sw_phylink_mac_link_down(struct dsa_switch *ds, int port, static void ar9331_sw_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; struct regmap *regmap = priv->regmap; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 03ba6d25f7fe..c27cc7b37440 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -786,7 +786,9 @@ static void sja1105_mac_link_down(struct dsa_switch *ds, int port, static void sja1105_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { sja1105_inhibit_tx(ds->priv, BIT(port), false); } diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 3031a5fc5427..bab3a9bb5e6f 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -42,7 +42,6 @@ #include <linux/u64_stats_sync.h> #define DRV_NAME "dummy" -#define DRV_VERSION "1.0" static int numdummies = 1; @@ -104,7 +103,6 @@ static void dummy_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops dummy_ethtool_ops = { @@ -212,4 +210,3 @@ module_init(dummy_init_module); module_exit(dummy_cleanup_module); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); -MODULE_VERSION(DRV_VERSION); diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index 8cafd06ff0c4..b762176a1406 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -60,8 +60,6 @@ */ #define DRV_NAME "3c509" -#define DRV_VERSION "1.20" -#define DRV_RELDATE "04Feb2008" /* A few values that may be tweaked. */ @@ -87,13 +85,12 @@ #include <linux/device.h> #include <linux/eisa.h> #include <linux/bitops.h> +#include <linux/vermagic.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/irq.h> -static char version[] = DRV_NAME ".c:" DRV_VERSION " " DRV_RELDATE " becker@scyld.com\n"; - #ifdef EL3_DEBUG static int el3_debug = EL3_DEBUG; #else @@ -547,8 +544,6 @@ static int el3_common_init(struct net_device *dev) dev->name, dev->base_addr, if_names[(dev->if_port & 0x03)], dev->dev_addr, dev->irq); - if (el3_debug > 0) - pr_info("%s", version); return 0; } @@ -1143,7 +1138,6 @@ el3_netdev_set_ecmd(struct net_device *dev, static void el3_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } static int el3_get_link_ksettings(struct net_device *dev, diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 1e233e2f0a5a..90312fcd6319 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -22,12 +22,8 @@ */ +#include <linux/vermagic.h> #define DRV_NAME "3c515" -#define DRV_VERSION "0.99t-ac" -#define DRV_RELDATE "28-Oct-2002" - -static char *version = -DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " becker@scyld.com and others\n"; #define CORKSCREW 1 @@ -84,7 +80,6 @@ static int max_interrupt_work = 20; MODULE_AUTHOR("Donald Becker <becker@scyld.com>"); MODULE_DESCRIPTION("3Com 3c515 Corkscrew driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); /* "Knobs" for adjusting internal parameters. */ /* Put out somewhat more debugging messages. (0 - no msg, 1 minimal msgs). */ @@ -418,8 +413,6 @@ int init_module(void) int found = 0; if (debug >= 0) corkscrew_debug = debug; - if (corkscrew_debug) - pr_debug("%s", version); while (corkscrew_scan(-1)) found++; return found ? 0 : -ENODEV; @@ -429,16 +422,10 @@ int init_module(void) struct net_device *tc515_probe(int unit) { struct net_device *dev = corkscrew_scan(unit); - static int printed; if (!dev) return ERR_PTR(-ENODEV); - if (corkscrew_debug > 0 && !printed) { - printed = 1; - pr_debug("%s", version); - } - return dev; } #endif /* not MODULE */ @@ -1540,7 +1527,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "ISA 0x%lx", dev->base_addr); } diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index d47cde6c5f08..09816e84314d 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -23,7 +23,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "3c589_cs" -#define DRV_VERSION "1.162-ac" #include <linux/module.h> #include <linux/kernel.h> @@ -482,7 +481,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "PCMCIA 0x%lx", dev->base_addr); } diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 14fce6658106..4383ee615793 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -127,7 +127,6 @@ static const int multicast_filter_limit = 32; #include "typhoon.h" MODULE_AUTHOR("David Dillow <dave@thedillows.org>"); -MODULE_VERSION("1.0"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_NAME); MODULE_DESCRIPTION("3Com Typhoon Family (3C990, 3CR990, and variants)"); diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 165d18405b0c..2db42211329f 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -27,8 +27,6 @@ */ #define DRV_NAME "starfire" -#define DRV_VERSION "2.1" -#define DRV_RELDATE "July 6, 2008" #include <linux/interrupt.h> #include <linux/module.h> @@ -47,6 +45,7 @@ #include <asm/processor.h> /* Processor type for cache alignment. */ #include <linux/uaccess.h> #include <asm/io.h> +#include <linux/vermagic.h> /* * The current frame processor firmware fails to checksum a fragment @@ -165,15 +164,9 @@ static int rx_copybreak /* = 0 */; #define FIRMWARE_RX "adaptec/starfire_rx.bin" #define FIRMWARE_TX "adaptec/starfire_tx.bin" -/* These identify the driver base version and may not be removed. */ -static const char version[] = -KERN_INFO "starfire.c:v1.03 7/26/2000 Written by Donald Becker <becker@scyld.com>\n" -" (unofficial 2.2/2.4 kernel port, version " DRV_VERSION ", " DRV_RELDATE ")\n"; - MODULE_AUTHOR("Donald Becker <becker@scyld.com>"); MODULE_DESCRIPTION("Adaptec Starfire Ethernet driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); MODULE_FIRMWARE(FIRMWARE_RX); MODULE_FIRMWARE(FIRMWARE_TX); @@ -654,13 +647,6 @@ static int starfire_init_one(struct pci_dev *pdev, int drv_flags, io_size; int boguscnt; -/* when built into the kernel, we only print version if device is found */ -#ifndef MODULE - static int printed_version; - if (!printed_version++) - printk(version); -#endif - if (pci_enable_device (pdev)) return -EIO; @@ -1853,7 +1839,6 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct netdev_private *np = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info)); } @@ -2073,8 +2058,6 @@ static int __init starfire_init (void) { /* when a module, this is printed whether or not devices are found in probe */ #ifdef MODULE - printk(version); - printk(KERN_INFO DRV_NAME ": polling (NAPI) enabled\n"); #endif diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 2a9f8643629c..bf546118dbc6 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1114,9 +1114,7 @@ static void greth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *in strlcpy(info->driver, dev_driver_string(greth->dev), sizeof(info->driver)); - strlcpy(info->version, "revision: 1.0", sizeof(info->version)); strlcpy(info->bus_info, greth->dev->bus->name, sizeof(info->bus_info)); - strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); } static void greth_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index cb6a761d5c11..1b19385ad8a9 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2958,7 +2958,6 @@ static void et131x_get_drvinfo(struct net_device *netdev, struct et131x_adapter *adapter = netdev_priv(netdev); strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); - strlcpy(info->version, DRIVER_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(adapter->pdev), sizeof(info->bus_info)); } diff --git a/drivers/net/ethernet/agere/et131x.h b/drivers/net/ethernet/agere/et131x.h index be9a11c02526..d0e922584d8a 100644 --- a/drivers/net/ethernet/agere/et131x.h +++ b/drivers/net/ethernet/agere/et131x.h @@ -46,7 +46,6 @@ */ #define DRIVER_NAME "et131x" -#define DRIVER_VERSION "v2.0" /* EEPROM registers */ diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 9daef4c8feef..6234fcd844ee 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -26,7 +26,6 @@ #include "slic.h" #define DRV_NAME "slicoss" -#define DRV_VERSION "1.0" static const struct pci_device_id slic_id_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_ALACRITECH, @@ -1533,7 +1532,6 @@ static void slic_get_drvinfo(struct net_device *dev, struct slic_device *sdev = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(sdev->pdev), sizeof(info->bus_info)); } @@ -1852,4 +1850,3 @@ module_pci_driver(slic_driver); MODULE_DESCRIPTION("Alacritech non-accelerated SLIC driver"); MODULE_AUTHOR("Lino Sanfilippo <LinoSanfilippo@gmx.de>"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 22cadfbeedfb..18d3b4340bd4 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -33,7 +33,6 @@ #include "sun4i-emac.h" #define DRV_NAME "sun4i-emac" -#define DRV_VERSION "1.02" #define EMAC_MAX_FRAME_LEN 0x0600 @@ -212,7 +211,6 @@ static void emac_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info)); } diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index f366faf88eee..5d192d551623 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -2699,9 +2699,8 @@ static void ace_get_drvinfo(struct net_device *dev, struct ace_private *ap = netdev_priv(dev); strlcpy(info->driver, "acenic", sizeof(info->driver)); - snprintf(info->version, sizeof(info->version), "%i.%i.%i", - ap->firmware_major, ap->firmware_minor, - ap->firmware_fix); + snprintf(info->fw_version, sizeof(info->version), "%i.%i.%i", + ap->firmware_major, ap->firmware_minor, ap->firmware_fix); if (ap->pdev) strlcpy(info->bus_info, pci_name(ap->pdev), diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c index 23823464f2e7..4299f1301149 100644 --- a/drivers/net/ethernet/altera/altera_tse_ethtool.c +++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c @@ -67,7 +67,6 @@ static void tse_get_drvinfo(struct net_device *dev, u32 rev = ioread32(&priv->mac_dev->megacore_revision); strcpy(info->driver, "altera_tse"); - strcpy(info->version, "v8.0"); snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "v%d.%d", rev & 0xFFFF, (rev & 0xFFFF0000) >> 16); sprintf(info->bus_info, "platform"); diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index ced1d577b62a..868265a2ec00 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -404,7 +404,6 @@ static void ena_get_drvinfo(struct net_device *dev, struct ena_adapter *adapter = netdev_priv(dev); strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(adapter->pdev), sizeof(info->bus_info)); } @@ -674,7 +673,6 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, * supports getting/setting the hash function. */ rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key); - if (rc) { if (rc == -EOPNOTSUPP) { key = NULL; @@ -685,9 +683,6 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return rc; } - if (rc) - return rc; - switch (ena_func) { case ENA_ADMIN_TOEPLITZ: func = ETH_RSS_HASH_TOP; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 0b2fd96b93d7..555c7273d712 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -49,12 +49,9 @@ #include <linux/bpf_trace.h> #include "ena_pci_id_tbl.h" -static char version[] = DEVICE_NAME " v" DRV_MODULE_VERSION "\n"; - MODULE_AUTHOR("Amazon.com, Inc. or its affiliates"); MODULE_DESCRIPTION(DEVICE_NAME); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_MODULE_VERSION); /* Time in jiffies before concluding the transmitter is hung. */ #define TX_TIMEOUT (5 * HZ) @@ -3094,9 +3091,9 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, strncpy(host_info->os_dist_str, utsname()->release, sizeof(host_info->os_dist_str) - 1); host_info->driver_version = - (DRV_MODULE_VER_MAJOR) | - (DRV_MODULE_VER_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) | - (DRV_MODULE_VER_SUBMINOR << ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT) | + (DRV_MODULE_GEN_MAJOR) | + (DRV_MODULE_GEN_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) | + (DRV_MODULE_GEN_SUBMINOR << ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT) | ("K"[0] << ENA_ADMIN_HOST_INFO_MODULE_TYPE_SHIFT); host_info->num_cpus = num_online_cpus(); @@ -3476,9 +3473,7 @@ static int ena_restore_device(struct ena_adapter *adapter) netif_carrier_on(adapter->netdev); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); - dev_err(&pdev->dev, - "Device reset completed successfully, Driver info: %s\n", - version); + dev_err(&pdev->dev, "Device reset completed successfully\n"); return rc; err_disable_msix: @@ -4116,8 +4111,6 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_dbg(&pdev->dev, "%s\n", __func__); - dev_info_once(&pdev->dev, "%s", version); - rc = pci_enable_device_mem(pdev); if (rc) { dev_err(&pdev->dev, "pci_enable_device_mem() failed!\n"); @@ -4429,8 +4422,6 @@ static struct pci_driver ena_pci_driver = { static int __init ena_init(void) { - pr_info("%s", version); - ena_wq = create_singlethread_workqueue(DRV_MODULE_NAME); if (!ena_wq) { pr_err("Failed to create workqueue\n"); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 8795e0b1dc3c..97dfd0c67e84 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,16 +45,16 @@ #include "ena_com.h" #include "ena_eth_com.h" -#define DRV_MODULE_VER_MAJOR 2 -#define DRV_MODULE_VER_MINOR 1 -#define DRV_MODULE_VER_SUBMINOR 0 +#define DRV_MODULE_GEN_MAJOR 2 +#define DRV_MODULE_GEN_MINOR 1 +#define DRV_MODULE_GEN_SUBMINOR 0 #define DRV_MODULE_NAME "ena" -#ifndef DRV_MODULE_VERSION -#define DRV_MODULE_VERSION \ - __stringify(DRV_MODULE_VER_MAJOR) "." \ - __stringify(DRV_MODULE_VER_MINOR) "." \ - __stringify(DRV_MODULE_VER_SUBMINOR) "K" +#ifndef DRV_MODULE_GENERATION +#define DRV_MODULE_GENERATION \ + __stringify(DRV_MODULE_GEN_MAJOR) "." \ + __stringify(DRV_MODULE_GEN_MINOR) "." \ + __stringify(DRV_MODULE_GEN_SUBMINOR) "K" #endif #define DEVICE_NAME "Elastic Network Adapter (ENA)" diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 0f3b743425e8..7a1286f8e983 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -84,9 +84,8 @@ Revision History: #include "amd8111e.h" #define MODULE_NAME "amd8111e" -#define MODULE_VERS "3.0.7" MODULE_AUTHOR("Advanced Micro Devices, Inc."); -MODULE_DESCRIPTION ("AMD8111 based 10/100 Ethernet Controller. Driver Version "MODULE_VERS); +MODULE_DESCRIPTION("AMD8111 based 10/100 Ethernet Controller."); MODULE_LICENSE("GPL"); module_param_array(speed_duplex, int, NULL, 0); MODULE_PARM_DESC(speed_duplex, "Set device speed and duplex modes, 0: Auto Negotiate, 1: 10Mbps Half Duplex, 2: 10Mbps Full Duplex, 3: 100Mbps Half Duplex, 4: 100Mbps Full Duplex"); @@ -1366,7 +1365,6 @@ static void amd8111e_get_drvinfo(struct net_device *dev, struct amd8111e_priv *lp = netdev_priv(dev); struct pci_dev *pci_dev = lp->pci_dev; strlcpy(info->driver, MODULE_NAME, sizeof(info->driver)); - strlcpy(info->version, MODULE_VERS, sizeof(info->version)); snprintf(info->fw_version, sizeof(info->fw_version), "%u", chip_version); strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info)); @@ -1875,7 +1873,6 @@ static int amd8111e_probe_one(struct pci_dev *pdev, /* display driver and device information */ chip_version = (readl(lp->mmio + CHIPID) & 0xf0000000)>>28; - dev_info(&pdev->dev, "AMD-8111e Driver Version: %s\n", MODULE_VERS); dev_info(&pdev->dev, "[ Rev %x ] PCI 10/100BaseT Ethernet %pM\n", chip_version, dev->dev_addr); if (lp->ext_phy_id) diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 089a4fbc61a0..9f6e3cc2ce80 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -63,14 +63,12 @@ static int au1000_debug = 3; NETIF_MSG_LINK) #define DRV_NAME "au1000_eth" -#define DRV_VERSION "1.7" #define DRV_AUTHOR "Pete Popov <ppopov@embeddedalley.com>" #define DRV_DESC "Au1xxx on-chip Ethernet driver" MODULE_AUTHOR(DRV_AUTHOR); MODULE_DESCRIPTION(DRV_DESC); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); /* AU1000 MAC registers and bits */ #define MAC_CONTROL 0x0 @@ -656,7 +654,6 @@ au1000_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) struct au1000_private *aup = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "%s %d", DRV_NAME, aup->mac_id); } @@ -1290,8 +1287,6 @@ static int au1000_probe(struct platform_device *pdev) netdev_info(dev, "Au1xx0 Ethernet found at 0x%lx, irq %d\n", (unsigned long)base->start, irq); - pr_info_once("%s version %s %s\n", DRV_NAME, DRV_VERSION, DRV_AUTHOR); - return 0; err_out: diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 023aecf6ab30..11c0b13edd30 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -114,8 +114,6 @@ Log: nmclan_cs.c,v #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "nmclan_cs" -#define DRV_VERSION "0.16" - /* ---------------------------------------------------------------------------- Conditional Compilation Options @@ -367,7 +365,7 @@ typedef struct _mace_private { char tx_free_frames; /* Number of free transmit frame buffers */ char tx_irq_disabled; /* MACE TX interrupt disabled */ - + spinlock_t bank_lock; /* Must be held if you step off bank 0 */ } mace_private; @@ -444,7 +442,7 @@ static int nmclan_probe(struct pcmcia_device *link) lp = netdev_priv(dev); lp->p_dev = link; link->priv = dev; - + spin_lock_init(&lp->bank_lock); link->resource[0]->end = 32; link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO; @@ -817,7 +815,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "PCMCIA 0x%lx", dev->base_addr); } @@ -1110,7 +1107,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) if (pkt_len & 1) *(skb_tail_pointer(skb) - 1) = inb(ioaddr + AM2150_RCV); skb->protocol = eth_type_trans(skb, dev); - + netif_rx(skb); /* Send the packet to the upper (protocol) layers. */ dev->stats.rx_packets++; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index dc7d88227e76..07e8211eea51 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -24,13 +24,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "pcnet32" -#define DRV_VERSION "1.35" #define DRV_RELDATE "21.Apr.2008" #define PFX DRV_NAME ": " -static const char *const version = - DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " tsbogend@alpha.franken.de\n"; - #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -809,7 +805,6 @@ static void pcnet32_get_drvinfo(struct net_device *dev, struct pcnet32_private *lp = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); if (lp->pci_dev) strlcpy(info->bus_info, pci_name(lp->pci_dev), sizeof(info->bus_info)); @@ -3006,8 +3001,6 @@ MODULE_LICENSE("GPL"); static int __init pcnet32_init_module(void) { - pr_info("%s", version); - pcnet32_debug = netif_msg_init(debug, PCNET32_MSG_DEFAULT); if ((tx_start_pt >= 0) && (tx_start_pt <= 3)) diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c index b00e00881253..a21b2e60157e 100644 --- a/drivers/net/ethernet/amd/sunlance.c +++ b/drivers/net/ethernet/amd/sunlance.c @@ -105,14 +105,9 @@ static char lancestr[] = "LANCE"; #include <asm/irq.h> #define DRV_NAME "sunlance" -#define DRV_VERSION "2.02" #define DRV_RELDATE "8/24/03" #define DRV_AUTHOR "Miguel de Icaza (miguel@nuclecu.unam.mx)" -static char version[] = - DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " " DRV_AUTHOR "\n"; - -MODULE_VERSION(DRV_VERSION); MODULE_AUTHOR(DRV_AUTHOR); MODULE_DESCRIPTION("Sun Lance ethernet driver"); MODULE_LICENSE("GPL"); @@ -1282,7 +1277,6 @@ static void lance_free_hwresources(struct lance_private *lp) static void sparc_lance_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, "sunlance", sizeof(info->driver)); - strlcpy(info->version, "2.02", sizeof(info->version)); } static const struct ethtool_ops sparc_lance_ethtool_ops = { @@ -1305,7 +1299,6 @@ static int sparc_lance_probe_one(struct platform_device *op, struct platform_device *lebuffer) { struct device_node *dp = op->dev.of_node; - static unsigned version_printed; struct lance_private *lp; struct net_device *dev; int i; @@ -1316,9 +1309,6 @@ static int sparc_lance_probe_one(struct platform_device *op, lp = netdev_priv(dev); - if (sparc_lance_debug && version_printed++ == 0) - printk (KERN_INFO "%s", version); - spin_lock_init(&lp->lock); /* Copy the IDPROM ethernet address to the device structure, later we diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 8083173f1a8f..b23c8ee24ee3 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -405,7 +405,6 @@ static void xgbe_get_drvinfo(struct net_device *netdev, struct xgbe_hw_features *hw_feat = &pdata->hw_feat; strlcpy(drvinfo->driver, XGBE_DRV_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, XGBE_DRV_VERSION, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, dev_name(pdata->dev), sizeof(drvinfo->bus_info)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%d", diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 7ce9c69e9c44..2a70714a791d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -127,7 +127,6 @@ MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(XGBE_DRV_VERSION); MODULE_DESCRIPTION(XGBE_DRV_DESC); static int debug = -1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 47bcbcf58048..5897e46faca5 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -135,7 +135,6 @@ #include <linux/list.h> #define XGBE_DRV_NAME "amd-xgbe" -#define XGBE_DRV_VERSION "1.0.3" #define XGBE_DRV_DESC "AMD 10 Gigabit Ethernet Driver" /* Descriptor related defines */ diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c index a58250c1b57a..b78d1a99fe81 100644 --- a/drivers/net/ethernet/apm/xgene-v2/ethtool.c +++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c @@ -89,8 +89,6 @@ static void xge_get_drvinfo(struct net_device *ndev, struct platform_device *pdev = pdata->pdev; strcpy(info->driver, "xgene-enet-v2"); - strcpy(info->version, XGENE_ENET_V2_VERSION); - snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A"); sprintf(info->bus_info, "%s", pdev->name); } diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index c48f60996761..860c18fb7aae 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -741,5 +741,4 @@ module_platform_driver(xge_driver); MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver"); MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>"); -MODULE_VERSION(XGENE_ENET_V2_VERSION); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h index d41439d2709d..b3985a7be59d 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.h +++ b/drivers/net/ethernet/apm/xgene-v2/main.h @@ -28,7 +28,6 @@ #include "ring.h" #include "ethtool.h" -#define XGENE_ENET_V2_VERSION "v1.0" #define XGENE_ENET_STD_MTU 1536 #define XGENE_ENET_MIN_FRAME 60 #define IRQ_ID_SIZE 16 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c index 246dec27140d..ada70425b48c 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c @@ -103,8 +103,6 @@ static void xgene_get_drvinfo(struct net_device *ndev, struct platform_device *pdev = pdata->pdev; strcpy(info->driver, "xgene_enet"); - strcpy(info->version, XGENE_DRV_VERSION); - snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A"); sprintf(info->bus_info, "%s", pdev->name); } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 6aee2f0fc0db..5f1fc6582d74 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -2179,7 +2179,6 @@ static struct platform_driver xgene_enet_driver = { module_platform_driver(xgene_enet_driver); MODULE_DESCRIPTION("APM X-Gene SoC Ethernet driver"); -MODULE_VERSION(XGENE_DRV_VERSION); MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>"); MODULE_AUTHOR("Keyur Chudgar <kchudgar@apm.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 18f4923b1723..d35a338120cf 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -28,7 +28,6 @@ #include "xgene_enet_ring2.h" #include "../../../phy/mdio-xgene.h" -#define XGENE_DRV_VERSION "v1.0" #define ETHER_MIN_PACKET 64 #define ETHER_STD_PACKET 1518 #define XGENE_ENET_STD_MTU 1536 diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index f0c41f7408e5..7560f5506e55 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -9,8 +9,6 @@ #ifndef AQ_CFG_H #define AQ_CFG_H -#include <generated/utsrelease.h> - #define AQ_CFG_VECS_DEF 8U #define AQ_CFG_TCS_DEF 1U @@ -85,7 +83,5 @@ #define AQ_CFG_DRV_AUTHOR "aQuantia" #define AQ_CFG_DRV_DESC "aQuantia Corporation(R) Network Driver" #define AQ_CFG_DRV_NAME "atlantic" -#define AQ_CFG_DRV_VERSION UTS_RELEASE \ - AQ_CFG_DRV_VERSION_SUFFIX #endif /* AQ_CFG_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h index 42ea8d8daa46..c8c402b013bb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h @@ -12,7 +12,6 @@ #include <linux/etherdevice.h> #include <linux/pci.h> #include <linux/if_vlan.h> -#include "ver.h" #include "aq_cfg.h" #include "aq_utils.h" diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 7b55633d2cb9..0bdaa0d785b7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -132,7 +132,6 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev, regs_count = aq_nic_get_regs_count(aq_nic); strlcat(drvinfo->driver, AQ_CFG_DRV_NAME, sizeof(drvinfo->driver)); - strlcat(drvinfo->version, AQ_CFG_DRV_VERSION, sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%u.%u.%u", firmware_version >> 24, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 538f460a3da7..9fcab646cbd5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -19,7 +19,6 @@ #include <linux/udp.h> MODULE_LICENSE("GPL v2"); -MODULE_VERSION(AQ_CFG_DRV_VERSION); MODULE_AUTHOR(AQ_CFG_DRV_AUTHOR); MODULE_DESCRIPTION(AQ_CFG_DRV_DESC); diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h deleted file mode 100644 index 597654b51e01..000000000000 --- a/drivers/net/ethernet/aquantia/atlantic/ver.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * aQuantia Corporation Network Driver - * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved - */ - -#ifndef VER_H -#define VER_H - -#define AQ_CFG_DRV_VERSION_SUFFIX "-kern" - -#endif /* VER_H */ diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h index d9efbc8d783b..d820ae03a966 100644 --- a/drivers/net/ethernet/arc/emac.h +++ b/drivers/net/ethernet/arc/emac.h @@ -130,7 +130,6 @@ struct arc_emac_mdio_bus_data { */ struct arc_emac_priv { const char *drv_name; - const char *drv_version; void (*set_mac_speed)(void *priv, unsigned int speed); /* Devices */ diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c index 539166112993..1c7736b7eaf7 100644 --- a/drivers/net/ethernet/arc/emac_arc.c +++ b/drivers/net/ethernet/arc/emac_arc.c @@ -15,7 +15,6 @@ #include "emac.h" #define DRV_NAME "emac_arc" -#define DRV_VERSION "1.0" static int emac_arc_probe(struct platform_device *pdev) { @@ -36,7 +35,6 @@ static int emac_arc_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->drv_name = DRV_NAME; - priv->drv_version = DRV_VERSION; err = of_get_phy_mode(dev->of_node, &interface); if (err) { diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 17bda4e8cc45..38cd968b6a3b 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -92,7 +92,6 @@ static void arc_emac_get_drvinfo(struct net_device *ndev, struct arc_emac_priv *priv = netdev_priv(ndev); strlcpy(info->driver, priv->drv_name, sizeof(info->driver)); - strlcpy(info->version, priv->drv_version, sizeof(info->version)); } static const struct ethtool_ops arc_emac_ethtool_ops = { diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index aae231c5224f..48ecdf15eddc 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -16,7 +16,6 @@ #include "emac.h" #define DRV_NAME "rockchip_emac" -#define DRV_VERSION "1.1" struct emac_rockchip_soc_data { unsigned int grf_offset; @@ -112,7 +111,6 @@ static int emac_rockchip_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->emac.drv_name = DRV_NAME; - priv->emac.drv_version = DRV_VERSION; priv->emac.set_mac_speed = emac_rockchip_set_mac_speed; err = of_get_phy_mode(dev->of_node, &interface); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h index 60b2febd7315..a0562a90fb6d 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c.h +++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h @@ -583,7 +583,6 @@ struct atl1c_adapter { readl(((a)->hw_addr + reg) + ((offset) << 2))) extern char atl1c_driver_name[]; -extern char atl1c_driver_version[]; void atl1c_reinit_locked(struct atl1c_adapter *adapter); s32 atl1c_reset_hw(struct atl1c_hw *hw); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c index b5a70a36fa04..e2eb7b8c63a0 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c @@ -221,8 +221,6 @@ static void atl1c_get_drvinfo(struct net_device *netdev, struct atl1c_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, atl1c_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, atl1c_driver_version, - sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 0d67b951c0b2..00bd7bd55794 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -8,9 +8,7 @@ #include "atl1c.h" -#define ATL1C_DRV_VERSION "1.0.1.1-NAPI" char atl1c_driver_name[] = "atl1c"; -char atl1c_driver_version[] = ATL1C_DRV_VERSION; /* * atl1c_pci_tbl - PCI Device ID Table @@ -37,7 +35,6 @@ MODULE_AUTHOR("Jie Yang"); MODULE_AUTHOR("Qualcomm Atheros Inc., <nic-devel@qualcomm.com>"); MODULE_DESCRIPTION("Qualcomm Atheros 100/1000M Ethernet Network Driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(ATL1C_DRV_VERSION); static int atl1c_stop_mac(struct atl1c_hw *hw); static void atl1c_disable_l0s_l1(struct atl1c_hw *hw); @@ -2642,8 +2639,6 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_register; } - if (netif_msg_probe(adapter)) - dev_info(&pdev->dev, "version %s\n", ATL1C_DRV_VERSION); cards_found++; return 0; diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e.h b/drivers/net/ethernet/atheros/atl1e/atl1e.h index e9893da50995..9fcad783c939 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e.h +++ b/drivers/net/ethernet/atheros/atl1e/atl1e.h @@ -482,7 +482,6 @@ struct atl1e_adapter { readl(((a)->hw_addr + reg) + ((offset) << 2))) extern char atl1e_driver_name[]; -extern char atl1e_driver_version[]; void atl1e_check_options(struct atl1e_adapter *adapter); int atl1e_up(struct atl1e_adapter *adapter); diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c index c6b9e7ea8e38..0cbde352d1ba 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c @@ -307,8 +307,6 @@ static void atl1e_get_drvinfo(struct net_device *netdev, struct atl1e_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, atl1e_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, atl1e_driver_version, - sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "L1e", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index e0d89942d537..223ef846123e 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -8,10 +8,7 @@ #include "atl1e.h" -#define DRV_VERSION "1.0.0.7-NAPI" - char atl1e_driver_name[] = "ATL1E"; -char atl1e_driver_version[] = DRV_VERSION; #define PCI_DEVICE_ID_ATTANSIC_L1E 0x1026 /* * atl1e_pci_tbl - PCI Device ID Table @@ -33,7 +30,6 @@ MODULE_DEVICE_TABLE(pci, atl1e_pci_tbl); MODULE_AUTHOR("Atheros Corporation, <xiong.huang@atheros.com>, Jie Yang <jie.yang@atheros.com>"); MODULE_DESCRIPTION("Atheros 1000M Ethernet Network Driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); static void atl1e_setup_mac_ctrl(struct atl1e_adapter *adapter); diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b498fd6a47d0..271e7034fa70 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -65,12 +65,10 @@ #include "atl1.h" -#define ATLX_DRIVER_VERSION "2.1.3" MODULE_AUTHOR("Xiong Huang <xiong.huang@atheros.com>, " "Chris Snook <csnook@redhat.com>, " "Jay Cliburn <jcliburn@gmail.com>"); MODULE_LICENSE("GPL"); -MODULE_VERSION(ATLX_DRIVER_VERSION); /* Temporary hack for merging atl1 and atl2 */ #include "atlx.c" @@ -2965,8 +2963,6 @@ static int atl1_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* get device revision number */ adapter->hw.dev_rev = ioread16(adapter->hw.hw_addr + (REG_MASTER_CTRL + 2)); - if (netif_msg_probe(adapter)) - dev_info(&pdev->dev, "version %s\n", ATLX_DRIVER_VERSION); /* set default ring resource counts */ adapter->rfd_ring.count = adapter->rrd_ring.count = ATL1_DEFAULT_RFD; @@ -3344,8 +3340,6 @@ static void atl1_get_drvinfo(struct net_device *netdev, struct atl1_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, ATLX_DRIVER_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, ATLX_DRIVER_VERSION, - sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index b81a4e0c5b57..7c52b92b599d 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -36,18 +36,13 @@ #include "atl2.h" -#define ATL2_DRV_VERSION "2.2.3" - static const char atl2_driver_name[] = "atl2"; static const char atl2_driver_string[] = "Atheros(R) L2 Ethernet Driver"; -static const char atl2_copyright[] = "Copyright (c) 2007 Atheros Corporation."; -static const char atl2_driver_version[] = ATL2_DRV_VERSION; static const struct ethtool_ops atl2_ethtool_ops; MODULE_AUTHOR("Atheros Corporation <xiong.huang@atheros.com>, Chris Snook <csnook@redhat.com>"); MODULE_DESCRIPTION("Atheros Fast Ethernet Network Driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(ATL2_DRV_VERSION); /* * atl2_pci_tbl - PCI Device ID Table @@ -1688,9 +1683,6 @@ static struct pci_driver atl2_driver = { */ static int __init atl2_init_module(void) { - printk(KERN_INFO "%s - version %s\n", atl2_driver_string, - atl2_driver_version); - printk(KERN_INFO "%s\n", atl2_copyright); return pci_register_driver(&atl2_driver); } module_init(atl2_init_module); @@ -2011,8 +2003,6 @@ static void atl2_get_drvinfo(struct net_device *netdev, struct atl2_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, atl2_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, atl2_driver_version, - sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "L2", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fd6e0e48cd51..f9a8151f092c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11252,7 +11252,7 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!"); + netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else @@ -11759,7 +11759,7 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[]) u32 dw; if (!pos) { - netdev_info(bp->dev, "Unable do read adapter's DSN"); + netdev_info(bp->dev, "Unable do read adapter's DSN\n"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index eec0168330b7..d3c93ccee86a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -641,14 +641,14 @@ static int bnxt_dl_params_register(struct bnxt *bp) rc = devlink_params_register(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); if (rc) { - netdev_warn(bp->dev, "devlink_params_register failed. rc=%d", + netdev_warn(bp->dev, "devlink_params_register failed. rc=%d\n", rc); return rc; } rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params, ARRAY_SIZE(bnxt_dl_port_params)); if (rc) { - netdev_err(bp->dev, "devlink_port_params_register failed"); + netdev_err(bp->dev, "devlink_port_params_register failed\n"); devlink_params_unregister(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); return rc; @@ -679,7 +679,7 @@ int bnxt_dl_register(struct bnxt *bp) else dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl)); if (!dl) { - netdev_warn(bp->dev, "devlink_alloc failed"); + netdev_warn(bp->dev, "devlink_alloc failed\n"); return -ENOMEM; } @@ -692,7 +692,7 @@ int bnxt_dl_register(struct bnxt *bp) rc = devlink_register(dl, &bp->pdev->dev); if (rc) { - netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc); + netdev_warn(bp->dev, "devlink_register failed. rc=%d\n", rc); goto err_dl_free; } @@ -704,7 +704,7 @@ int bnxt_dl_register(struct bnxt *bp) sizeof(bp->dsn)); rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id); if (rc) { - netdev_err(bp->dev, "devlink_port_register failed"); + netdev_err(bp->dev, "devlink_port_register failed\n"); goto err_dl_unreg; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6171fa8b3677..e8fc1671c581 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2028,7 +2028,7 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, } if (fw->size > item_len) { - netdev_err(dev, "PKG insufficient update area in nvram: %lu", + netdev_err(dev, "PKG insufficient update area in nvram: %lu\n", (unsigned long)fw->size); rc = -EFBIG; } else { @@ -3338,7 +3338,7 @@ err: kfree(coredump.data); *dump_len += sizeof(struct bnxt_coredump_record); if (rc == -ENOBUFS) - netdev_err(bp->dev, "Firmware returned large coredump buffer"); + netdev_err(bp->dev, "Firmware returned large coredump buffer\n"); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 0cc6ec51f45f..9bec256b0934 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -50,7 +50,7 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev) /* check if dev belongs to the same switch */ if (!netdev_port_same_parent_id(pf_bp->dev, dev)) { - netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch", + netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch\n", dev->ifindex); return BNXT_FID_INVALID; } @@ -70,7 +70,7 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, struct net_device *dev = act->dev; if (!dev) { - netdev_info(bp->dev, "no dev in mirred action"); + netdev_info(bp->dev, "no dev in mirred action\n"); return -EINVAL; } @@ -106,7 +106,7 @@ static int bnxt_tc_parse_tunnel_set(struct bnxt *bp, const struct ip_tunnel_key *tun_key = &tun_info->key; if (ip_tunnel_info_af(tun_info) != AF_INET) { - netdev_info(bp->dev, "only IPv4 tunnel-encap is supported"); + netdev_info(bp->dev, "only IPv4 tunnel-encap is supported\n"); return -EOPNOTSUPP; } @@ -295,7 +295,7 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, int i, rc; if (!flow_action_has_entries(flow_action)) { - netdev_info(bp->dev, "no actions"); + netdev_info(bp->dev, "no actions\n"); return -EINVAL; } @@ -370,7 +370,7 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) { - netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x", + netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x\n", dissector->used_keys); return -EOPNOTSUPP; } @@ -508,7 +508,7 @@ static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -841,7 +841,7 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp, resp = bnxt_get_hwrm_resp_addr(bp, &req); *decap_filter_handle = resp->decap_filter_id; } else { - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -859,7 +859,7 @@ static int hwrm_cfa_decap_filter_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -906,7 +906,7 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp, resp = bnxt_get_hwrm_resp_addr(bp, &req); *encap_record_handle = resp->encap_record_id; } else { - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -924,7 +924,7 @@ static int hwrm_cfa_encap_record_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -943,7 +943,7 @@ static int bnxt_tc_put_l2_node(struct bnxt *bp, tc_info->l2_ht_params); if (rc) netdev_err(bp->dev, - "Error: %s: rhashtable_remove_fast: %d", + "Error: %s: rhashtable_remove_fast: %d\n", __func__, rc); kfree_rcu(l2_node, rcu); } @@ -972,7 +972,7 @@ bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table, if (rc) { kfree_rcu(l2_node, rcu); netdev_err(bp->dev, - "Error: %s: rhashtable_insert_fast: %d", + "Error: %s: rhashtable_insert_fast: %d\n", __func__, rc); return NULL; } @@ -1031,7 +1031,7 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow) if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) && (flow->l4_key.ip_proto != IPPROTO_TCP && flow->l4_key.ip_proto != IPPROTO_UDP)) { - netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports", + netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports\n", flow->l4_key.ip_proto); return false; } @@ -1088,7 +1088,7 @@ static int bnxt_tc_put_tunnel_node(struct bnxt *bp, rc = rhashtable_remove_fast(tunnel_table, &tunnel_node->node, *ht_params); if (rc) { - netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc); + netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc); rc = -1; } kfree_rcu(tunnel_node, rcu); @@ -1129,7 +1129,7 @@ bnxt_tc_get_tunnel_node(struct bnxt *bp, struct rhashtable *tunnel_table, tunnel_node->refcount++; return tunnel_node; err: - netdev_info(bp->dev, "error rc=%d", rc); + netdev_info(bp->dev, "error rc=%d\n", rc); return NULL; } @@ -1187,7 +1187,7 @@ static void bnxt_tc_put_decap_l2_node(struct bnxt *bp, &decap_l2_node->node, tc_info->decap_l2_ht_params); if (rc) - netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc); + netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc); kfree_rcu(decap_l2_node, rcu); } } @@ -1227,7 +1227,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, rt = ip_route_output_key(dev_net(real_dst_dev), &flow); if (IS_ERR(rt)) { - netdev_info(bp->dev, "no route to %pI4b", &flow.daddr); + netdev_info(bp->dev, "no route to %pI4b\n", &flow.daddr); return -EOPNOTSUPP; } @@ -1241,7 +1241,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, if (vlan->real_dev != real_dst_dev) { netdev_info(bp->dev, - "dst_dev(%s) doesn't use PF-if(%s)", + "dst_dev(%s) doesn't use PF-if(%s)\n", netdev_name(dst_dev), netdev_name(real_dst_dev)); rc = -EOPNOTSUPP; @@ -1253,7 +1253,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, #endif } else if (dst_dev != real_dst_dev) { netdev_info(bp->dev, - "dst_dev(%s) for %pI4b is not PF-if(%s)", + "dst_dev(%s) for %pI4b is not PF-if(%s)\n", netdev_name(dst_dev), &flow.daddr, netdev_name(real_dst_dev)); rc = -EOPNOTSUPP; @@ -1262,7 +1262,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, nbr = dst_neigh_lookup(&rt->dst, &flow.daddr); if (!nbr) { - netdev_info(bp->dev, "can't lookup neighbor for %pI4b", + netdev_info(bp->dev, "can't lookup neighbor for %pI4b\n", &flow.daddr); rc = -EOPNOTSUPP; goto put_rt; @@ -1472,7 +1472,7 @@ static int __bnxt_tc_del_flow(struct bnxt *bp, rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node, tc_info->flow_ht_params); if (rc) - netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d", + netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d\n", __func__, rc); kfree_rcu(flow_node, rcu); @@ -1587,7 +1587,7 @@ unlock: free_node: kfree_rcu(new_node, rcu); done: - netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d", + netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d\n", __func__, tc_flow_cmd->cookie, rc); return rc; } @@ -1700,7 +1700,7 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows, le64_to_cpu(resp_bytes[i]); } } else { - netdev_info(bp->dev, "error rc=%d", rc); + netdev_info(bp->dev, "error rc=%d\n", rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -1970,7 +1970,7 @@ static int bnxt_tc_indr_block_event(struct notifier_block *nb, bp); if (rc) netdev_info(bp->dev, - "Failed to register indirect blk: dev: %s", + "Failed to register indirect blk: dev: %s\n", netdev->name); break; case NETDEV_UNREGISTER: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index b010b34cdaf8..6f2faf81c1ae 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -43,7 +43,7 @@ static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx, netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x", *tx_cfa_action, *rx_cfa_code); } else { - netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -60,7 +60,7 @@ static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx) rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); return rc; } @@ -465,7 +465,7 @@ static int bnxt_vf_reps_create(struct bnxt *bp) return 0; err: - netdev_info(bp->dev, "%s error=%d", __func__, rc); + netdev_info(bp->dev, "%s error=%d\n", __func__, rc); kfree(cfa_code_map); __bnxt_vf_reps_destroy(bp); return rc; @@ -488,7 +488,7 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, mutex_lock(&bp->sriov_lock); if (bp->eswitch_mode == mode) { - netdev_info(bp->dev, "already in %s eswitch mode", + netdev_info(bp->dev, "already in %s eswitch mode\n", mode == DEVLINK_ESWITCH_MODE_LEGACY ? "legacy" : "switchdev"); rc = -EINVAL; @@ -508,7 +508,7 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, } if (pci_num_vf(bp->pdev) == 0) { - netdev_info(bp->dev, "Enable VFs before setting switchdev mode"); + netdev_info(bp->dev, "Enable VFs before setting switchdev mode\n"); rc = -EPERM; goto done; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index e50a15397e11..80feb20a2e53 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "bcmgenet: " fmt +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> @@ -2771,6 +2772,21 @@ static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1); } +static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, + unsigned char *addr) +{ + u32 addr_tmp; + + addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC0); + addr[0] = addr_tmp >> 24; + addr[1] = (addr_tmp >> 16) & 0xff; + addr[2] = (addr_tmp >> 8) & 0xff; + addr[3] = addr_tmp & 0xff; + addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC1); + addr[4] = (addr_tmp >> 8) & 0xff; + addr[5] = addr_tmp & 0xff; +} + /* Returns a reusable dma control register value */ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) { @@ -3466,10 +3482,8 @@ static int bcmgenet_probe(struct platform_device *pdev) const struct bcmgenet_plat_data *pdata; struct bcmgenet_priv *priv; struct net_device *dev; - const void *macaddr; unsigned int i; int err = -EIO; - const char *phy_mode_str; /* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */ dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1, @@ -3498,11 +3512,6 @@ static int bcmgenet_probe(struct platform_device *pdev) } priv->wol_irq = platform_get_irq_optional(pdev, 2); - if (dn) - macaddr = of_get_mac_address(dn); - else - macaddr = pd->mac_address; - priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { err = PTR_ERR(priv->base); @@ -3513,12 +3522,6 @@ static int bcmgenet_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); dev_set_drvdata(&pdev->dev, dev); - if (IS_ERR_OR_NULL(macaddr) || !is_valid_ether_addr(macaddr)) { - dev_warn(&pdev->dev, "using random Ethernet MAC\n"); - eth_hw_addr_random(dev); - } else { - ether_addr_copy(dev->dev_addr, macaddr); - } dev->watchdog_timeo = 2 * HZ; dev->ethtool_ops = &bcmgenet_ethtool_ops; dev->netdev_ops = &bcmgenet_netdev_ops; @@ -3547,8 +3550,9 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->dev = dev; priv->pdev = pdev; - if (of_id) { - pdata = of_id->data; + + pdata = device_get_match_data(&pdev->dev); + if (pdata) { priv->version = pdata->version; priv->dma_max_burst_length = pdata->dma_max_burst_length; } else { @@ -3558,7 +3562,7 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->clk = devm_clk_get(&priv->pdev->dev, "enet"); if (IS_ERR(priv->clk)) { - dev_warn(&priv->pdev->dev, "failed to get enet clock\n"); + dev_dbg(&priv->pdev->dev, "failed to get enet clock\n"); priv->clk = NULL; } @@ -3582,23 +3586,34 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->clk_wol = devm_clk_get(&priv->pdev->dev, "enet-wol"); if (IS_ERR(priv->clk_wol)) { - dev_warn(&priv->pdev->dev, "failed to get enet-wol clock\n"); + dev_dbg(&priv->pdev->dev, "failed to get enet-wol clock\n"); priv->clk_wol = NULL; } priv->clk_eee = devm_clk_get(&priv->pdev->dev, "enet-eee"); if (IS_ERR(priv->clk_eee)) { - dev_warn(&priv->pdev->dev, "failed to get enet-eee clock\n"); + dev_dbg(&priv->pdev->dev, "failed to get enet-eee clock\n"); priv->clk_eee = NULL; } /* If this is an internal GPHY, power it on now, before UniMAC is * brought out of reset as absolutely no UniMAC activity is allowed */ - if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) && - !strcasecmp(phy_mode_str, "internal")) + if (device_get_phy_mode(&pdev->dev) == PHY_INTERFACE_MODE_INTERNAL) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + if ((pd) && (!IS_ERR_OR_NULL(pd->mac_address))) + ether_addr_copy(dev->dev_addr, pd->mac_address); + else + if (!device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) + if (has_acpi_companion(&pdev->dev)) + bcmgenet_get_hw_addr(priv, dev->dev_addr); + + if (!is_valid_ether_addr(dev->dev_addr)) { + dev_warn(&pdev->dev, "using random Ethernet MAC\n"); + eth_hw_addr_random(dev); + } + reset_umac(priv); err = bcmgenet_mii_init(dev); @@ -3771,6 +3786,12 @@ static int bcmgenet_suspend(struct device *d) static SIMPLE_DEV_PM_OPS(bcmgenet_pm_ops, bcmgenet_suspend, bcmgenet_resume); +static const struct acpi_device_id genet_acpi_match[] = { + { "BCM6E4E", (kernel_ulong_t)&bcm2711_plat_data }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, genet_acpi_match); + static struct platform_driver bcmgenet_driver = { .probe = bcmgenet_probe, .remove = bcmgenet_remove, @@ -3779,6 +3800,7 @@ static struct platform_driver bcmgenet_driver = { .name = "bcmgenet", .of_match_table = bcmgenet_match, .pm = &bcmgenet_pm_ops, + .acpi_match_table = ACPI_PTR(genet_acpi_match), }, }; module_platform_driver(bcmgenet_driver); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 6392a2530183..d3003cb1bb09 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -5,7 +5,7 @@ * Copyright (c) 2014-2017 Broadcom */ - +#include <linux/acpi.h> #include <linux/types.h> #include <linux/delay.h> #include <linux/wait.h> @@ -294,6 +294,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) */ if (priv->ext_phy) { reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~ID_MODE_DIS; reg |= id_mode_dis; if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) reg |= RGMII_MODE_EN_V123; @@ -311,7 +312,8 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) int bcmgenet_mii_probe(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *dn = priv->pdev->dev.of_node; + struct device *kdev = &priv->pdev->dev; + struct device_node *dn = kdev->of_node; struct phy_device *phydev; u32 phy_flags = 0; int ret; @@ -334,7 +336,27 @@ int bcmgenet_mii_probe(struct net_device *dev) return -ENODEV; } } else { - phydev = dev->phydev; + if (has_acpi_companion(kdev)) { + char mdio_bus_id[MII_BUS_ID_SIZE]; + struct mii_bus *unimacbus; + + snprintf(mdio_bus_id, MII_BUS_ID_SIZE, "%s-%d", + UNIMAC_MDIO_DRV_NAME, priv->pdev->id); + + unimacbus = mdio_find_bus(mdio_bus_id); + if (!unimacbus) { + pr_err("Unable to find mii\n"); + return -ENODEV; + } + phydev = phy_find_first(unimacbus); + put_device(&unimacbus->dev); + if (!phydev) { + pr_err("Unable to find PHY\n"); + return -ENODEV; + } + } else { + phydev = dev->phydev; + } phydev->dev_flags = phy_flags; ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, @@ -455,9 +477,12 @@ static int bcmgenet_mii_register(struct bcmgenet_priv *priv) /* Retain this platform_device pointer for later cleanup */ priv->mii_pdev = ppdev; ppdev->dev.parent = &pdev->dev; - ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv); - if (pdata) + if (dn) + ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv); + else if (pdata) bcmgenet_mii_pdata_init(priv, &ppd); + else + ppd.phy_mask = ~0; ret = platform_device_add_resources(ppdev, &res, 1); if (ret) @@ -477,12 +502,33 @@ out: return ret; } +static int bcmgenet_phy_interface_init(struct bcmgenet_priv *priv) +{ + struct device *kdev = &priv->pdev->dev; + int phy_mode = device_get_phy_mode(kdev); + + if (phy_mode < 0) { + dev_err(kdev, "invalid PHY mode property\n"); + return phy_mode; + } + + priv->phy_interface = phy_mode; + + /* We need to specifically look up whether this PHY interface is + * internal or not *before* we even try to probe the PHY driver + * over MDIO as we may have shut down the internal PHY for power + * saving purposes. + */ + if (priv->phy_interface == PHY_INTERFACE_MODE_INTERNAL) + priv->internal_phy = true; + + return 0; +} + static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) { struct device_node *dn = priv->pdev->dev.of_node; - struct device *kdev = &priv->pdev->dev; struct phy_device *phydev; - phy_interface_t phy_mode; int ret; /* Fetch the PHY phandle */ @@ -500,23 +546,12 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) } /* Get the link mode */ - ret = of_get_phy_mode(dn, &phy_mode); - if (ret) { - dev_err(kdev, "invalid PHY mode property\n"); + ret = bcmgenet_phy_interface_init(priv); + if (ret) return ret; - } - - priv->phy_interface = phy_mode; - - /* We need to specifically look up whether this PHY interface is internal - * or not *before* we even try to probe the PHY driver over MDIO as we - * may have shut down the internal PHY for power saving purposes. - */ - if (priv->phy_interface == PHY_INTERFACE_MODE_INTERNAL) - priv->internal_phy = true; /* Make sure we initialize MoCA PHYs with a link down */ - if (phy_mode == PHY_INTERFACE_MODE_MOCA) { + if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { phydev = of_phy_find_device(dn); if (phydev) { phydev->link = 0; @@ -581,10 +616,13 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) { - struct device_node *dn = priv->pdev->dev.of_node; + struct device *kdev = &priv->pdev->dev; + struct device_node *dn = kdev->of_node; if (dn) return bcmgenet_mii_of_init(priv); + else if (has_acpi_companion(kdev)) + return bcmgenet_phy_interface_init(priv); else return bcmgenet_mii_pd_init(priv); } diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index a3f0f27fc79a..ab827fb4b6b9 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -1200,7 +1200,6 @@ struct macb { unsigned int dma_burst_length; phy_interface_t phy_interface; - int speed; /* AT91RM9200 transmit */ struct sk_buff *skb; /* holds skb until xmit interrupt completes */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 2c28da1737fe..3a7c26b08607 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -571,37 +571,20 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); - /* Clear all the bits we might set later */ - ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE)); - if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { if (state->interface == PHY_INTERFACE_MODE_RMII) ctrl |= MACB_BIT(RM9200_RMII); } else { - ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); - - /* We do not support MLO_PAUSE_RX yet */ - if (state->pause & MLO_PAUSE_TX) - ctrl |= MACB_BIT(PAE); + ctrl &= ~(GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); if (state->interface == PHY_INTERFACE_MODE_SGMII) ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); } - if (state->speed == SPEED_1000) - ctrl |= GEM_BIT(GBE); - else if (state->speed == SPEED_100) - ctrl |= MACB_BIT(SPD); - - if (state->duplex) - ctrl |= MACB_BIT(FD); - /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); - bp->speed = state->speed; - spin_unlock_irqrestore(&bp->lock, flags); } @@ -626,16 +609,42 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, netif_tx_stop_all_queues(ndev); } -static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy) +static void macb_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct net_device *ndev = to_net_dev(config->dev); struct macb *bp = netdev_priv(ndev); struct macb_queue *queue; + unsigned long flags; unsigned int q; + u32 ctrl; + + spin_lock_irqsave(&bp->lock, flags); + + ctrl = macb_or_gem_readl(bp, NCFGR); + + ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD)); + + if (speed == SPEED_100) + ctrl |= MACB_BIT(SPD); + + if (duplex) + ctrl |= MACB_BIT(FD); if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { - macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); + ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(PAE)); + + if (speed == SPEED_1000) + ctrl |= GEM_BIT(GBE); + + /* We do not support MLO_PAUSE_RX yet */ + if (tx_pause) + ctrl |= MACB_BIT(PAE); + + macb_set_tx_clk(bp->tx_clk, speed, ndev); /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down * cleared the pipeline and control registers. @@ -648,6 +657,10 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } + macb_or_gem_writel(bp, NCFGR, ctrl); + + spin_unlock_irqrestore(&bp->lock, flags); + /* Enable Rx and Tx */ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); @@ -4429,8 +4442,6 @@ static int macb_probe(struct platform_device *pdev) else bp->phy_interface = interface; - bp->speed = SPEED_UNKNOWN; - /* IP specific init */ err = init(pdev); if (err) diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h index b19e4376ba76..401827b82aa1 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h @@ -79,7 +79,7 @@ struct ch_mem_range { uint32_t addr; uint32_t len; uint32_t version; - uint8_t buf[0]; + uint8_t buf[]; }; struct ch_qset_params { diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h b/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h index 852c399a8b0a..68bb5f39f3f1 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h +++ b/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h @@ -1448,7 +1448,7 @@ struct cpl_rdma_terminate { #endif __be32 msn; __be32 mo; - __u8 data[0]; + __u8 data[]; }; /* cpl_rdma_terminate.tid_len fields */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h index a0e0ae19649f..290c1058069a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h @@ -29,7 +29,7 @@ struct clip_tbl { atomic_t nfree; struct list_head ce_free_head; void *cl_list; - struct list_head hash_list[0]; + struct list_head hash_list[]; }; enum { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h index f5be3ee1bdb4..dcab94cc2dee 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -82,7 +82,7 @@ struct cudbg_ulprx_la { struct cudbg_tp_la { u32 size; u32 mode; - u8 data[0]; + u8 data[]; }; static const char * const cudbg_region[] = { @@ -134,7 +134,7 @@ struct cudbg_meminfo { struct cudbg_cim_pif_la { int size; - u8 data[0]; + u8 data[]; }; struct cudbg_clk_info { @@ -339,13 +339,13 @@ struct cudbg_qdesc_entry { u32 qid; u32 desc_size; u32 num_desc; - u8 data[0]; /* Must be last */ + u8 data[]; /* Must be last */ }; struct cudbg_qdesc_info { u32 qdesc_entry_size; u32 num_queues; - u8 data[0]; /* Must be last */ + u8 data[]; /* Must be last */ }; #define IREG_NUM_ELEM 4 diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index de30d61af065..fe883cb1a7af 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -984,7 +984,7 @@ static const char * const devlog_facility_strings[] = { struct devlog_info { unsigned int nentries; /* number of entries in log[] */ unsigned int first; /* first [temporal] entry in log[] */ - struct fw_devlog_e log[0]; /* Firmware Device Log */ + struct fw_devlog_e log[]; /* Firmware Device Log */ }; /* Dump a Firmaware Device Log entry. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h index ba95e13d52da..1471cf0deb58 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h @@ -49,7 +49,7 @@ struct seq_tab { unsigned int rows; /* # of entries */ unsigned char width; /* size in bytes of each entry */ unsigned char skip_first; /* whether the first line is a header */ - char data[0]; /* the table data */ + char data[]; /* the table data */ }; static inline unsigned int hex2val(char c) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h index a4b99edcc339..125868c6770a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h @@ -289,6 +289,6 @@ struct cxgb4_link { struct cxgb4_tc_u32_table { unsigned int size; /* number of entries in table */ - struct cxgb4_link table[0]; /* Jump table */ + struct cxgb4_link table[]; /* Jump table */ }; #endif /* __CXGB4_TC_U32_PARSE_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index 1a16449e9deb..12c3354172cd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -59,7 +59,7 @@ struct l2t_data { rwlock_t lock; atomic_t nfree; /* number of free entries */ struct l2t_entry *rover; /* starting point for next allocation */ - struct l2t_entry l2tab[0]; /* MUST BE LAST */ + struct l2t_entry l2tab[]; /* MUST BE LAST */ }; static inline unsigned int vlan_prio(const struct l2t_entry *e) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h index 5cc74a5a1774..5f8b871d79af 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.h +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h @@ -82,7 +82,7 @@ struct sched_class { struct sched_table { /* per port scheduling table */ u8 sched_size; - struct sched_class tab[0]; + struct sched_class tab[]; }; static inline bool can_sched(struct net_device *dev) diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h index 1268d6e93a47..541249d78914 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.h +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h @@ -66,7 +66,7 @@ struct smt_entry { struct smt_data { unsigned int smt_size; rwlock_t lock; - struct smt_entry smtab[0]; + struct smt_entry smtab[]; }; struct smt_data *t4_init_smt(void); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index 575c6abcdae7..7d874f03d6c5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -1511,7 +1511,7 @@ struct ulptx_sgl { __be32 cmd_nsge; __be32 len0; __be64 addr0; - struct ulptx_sge_pair sge[0]; + struct ulptx_sge_pair sge[]; }; struct ulptx_idata { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index accad1101ad1..703effc00a05 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -737,7 +737,7 @@ struct fw_flowc_mnemval { struct fw_flowc_wr { __be32 op_to_nparams; __be32 flowid_len16; - struct fw_flowc_mnemval mnemval[0]; + struct fw_flowc_mnemval mnemval[]; }; #define FW_FLOWC_WR_NPARAMS_S 0 diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h index 7b02c200dd1e..1b4156461ba1 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h @@ -122,7 +122,7 @@ struct cxgbi_ppm_pool { unsigned int base; /* base index */ unsigned int next; /* next possible free index */ spinlock_t lock; /* ppm pool lock */ - unsigned long bmap[0]; + unsigned long bmap[]; } ____cacheline_aligned_in_smp; struct cxgbi_ppm { @@ -145,7 +145,7 @@ struct cxgbi_ppm { unsigned int next; unsigned int max_index_in_edram; unsigned long *ppod_bmap; - struct cxgbi_ppod_data ppod_data[0]; + struct cxgbi_ppod_data ppod_data[]; }; #define DDP_THRESHOLD 512 diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h index fef5a0a0663d..fcc4a3ccdd94 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h +++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h @@ -541,7 +541,7 @@ struct vnic_devcmd_notify { struct vnic_devcmd_provinfo { u8 oui[3]; u8 type; - u8 data[0]; + u8 data[]; }; /* These are used in flags field of different filters to denote @@ -648,9 +648,9 @@ enum { #define FILTER_MAX_BUF_SIZE 100 struct filter_tlv { - u_int32_t type; - u_int32_t length; - u_int32_t val[0]; + u32 type; + u32 length; + u32 val[]; }; enum { diff --git a/drivers/net/ethernet/cisco/enic/vnic_vic.h b/drivers/net/ethernet/cisco/enic/vnic_vic.h index 9ef81f148351..057776908828 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_vic.h +++ b/drivers/net/ethernet/cisco/enic/vnic_vic.h @@ -59,7 +59,7 @@ struct vic_provinfo { u16 type; u16 length; u8 value[0]; - } tlv[0]; + } tlv[]; } __packed; #define VIC_PROVINFO_ADD_TLV(vp, tlvtype, tlvlen, data) \ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 7ff147e89426..b6c46639aa4c 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1704,10 +1704,15 @@ static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { + struct dpaa2_eth_priv *priv = netdev_priv(dev); + if (cmd == SIOCSHWTSTAMP) return dpaa2_eth_ts_ioctl(dev, rq, cmd); - return -EINVAL; + if (priv->mac) + return phylink_mii_ioctl(priv->mac->phylink, rq, cmd); + + return -EOPNOTSUPP; } static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 96676abcebd5..94347c695233 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -79,6 +79,16 @@ static void dpaa2_eth_get_drvinfo(struct net_device *net_dev, sizeof(drvinfo->bus_info)); } +static int dpaa2_eth_nway_reset(struct net_device *net_dev) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + + if (priv->mac) + return phylink_ethtool_nway_reset(priv->mac->phylink); + + return -EOPNOTSUPP; +} + static int dpaa2_eth_get_link_ksettings(struct net_device *net_dev, struct ethtool_link_ksettings *link_settings) @@ -761,6 +771,7 @@ static int dpaa2_eth_get_ts_info(struct net_device *dev, const struct ethtool_ops dpaa2_ethtool_ops = { .get_drvinfo = dpaa2_eth_get_drvinfo, + .nway_reset = dpaa2_eth_nway_reset, .get_link = ethtool_op_get_link, .get_link_ksettings = dpaa2_eth_get_link_ksettings, .set_link_ksettings = dpaa2_eth_set_link_ksettings, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 84233e467ed1..3ee236c5fc37 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -123,49 +123,60 @@ static void dpaa2_mac_config(struct phylink_config *config, unsigned int mode, struct dpmac_link_state *dpmac_state = &mac->state; int err; - if (state->speed != SPEED_UNKNOWN) - dpmac_state->rate = state->speed; - - if (state->duplex != DUPLEX_UNKNOWN) { - if (!state->duplex) - dpmac_state->options |= DPMAC_LINK_OPT_HALF_DUPLEX; - else - dpmac_state->options &= ~DPMAC_LINK_OPT_HALF_DUPLEX; - } - if (state->an_enabled) dpmac_state->options |= DPMAC_LINK_OPT_AUTONEG; else dpmac_state->options &= ~DPMAC_LINK_OPT_AUTONEG; - if (state->pause & MLO_PAUSE_RX) - dpmac_state->options |= DPMAC_LINK_OPT_PAUSE; - else - dpmac_state->options &= ~DPMAC_LINK_OPT_PAUSE; - - if (!!(state->pause & MLO_PAUSE_RX) ^ !!(state->pause & MLO_PAUSE_TX)) - dpmac_state->options |= DPMAC_LINK_OPT_ASYM_PAUSE; - else - dpmac_state->options &= ~DPMAC_LINK_OPT_ASYM_PAUSE; - err = dpmac_set_link_state(mac->mc_io, 0, mac->mc_dev->mc_handle, dpmac_state); if (err) - netdev_err(mac->net_dev, "dpmac_set_link_state() = %d\n", err); + netdev_err(mac->net_dev, "%s: dpmac_set_link_state() = %d\n", + __func__, err); } -static void dpaa2_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy) +static void dpaa2_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct dpaa2_mac *mac = phylink_to_dpaa2_mac(config); struct dpmac_link_state *dpmac_state = &mac->state; int err; dpmac_state->up = 1; + + if (mac->if_link_type == DPMAC_LINK_TYPE_PHY) { + /* If the DPMAC is configured for PHY mode, we need + * to pass the link parameters to the MC firmware. + */ + dpmac_state->rate = speed; + + if (duplex == DUPLEX_HALF) + dpmac_state->options |= DPMAC_LINK_OPT_HALF_DUPLEX; + else if (duplex == DUPLEX_FULL) + dpmac_state->options &= ~DPMAC_LINK_OPT_HALF_DUPLEX; + + /* This is lossy; the firmware really should take the pause + * enablement status rather than pause/asym pause status. + */ + if (rx_pause) + dpmac_state->options |= DPMAC_LINK_OPT_PAUSE; + else + dpmac_state->options &= ~DPMAC_LINK_OPT_PAUSE; + + if (rx_pause ^ tx_pause) + dpmac_state->options |= DPMAC_LINK_OPT_ASYM_PAUSE; + else + dpmac_state->options &= ~DPMAC_LINK_OPT_ASYM_PAUSE; + } + err = dpmac_set_link_state(mac->mc_io, 0, mac->mc_dev->mc_handle, dpmac_state); if (err) - netdev_err(mac->net_dev, "dpmac_set_link_state() = %d\n", err); + netdev_err(mac->net_dev, "%s: dpmac_set_link_state() = %d\n", + __func__, err); } static void dpaa2_mac_link_down(struct phylink_config *config, @@ -238,6 +249,8 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) goto err_close_dpmac; } + mac->if_link_type = attr.link_type; + dpmac_node = dpaa2_mac_get_node(attr.id); if (!dpmac_node) { netdev_err(net_dev, "No dpmac@%d node found.\n", attr.id); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index 4da8079b9155..2130d9c7d40e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -20,6 +20,7 @@ struct dpaa2_mac { struct phylink_config phylink_config; struct phylink *phylink; phy_interface_t if_mode; + enum dpmac_link_type if_link_type; }; bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev, diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index dd4a227ffc7a..9938f7a5fc0a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -163,7 +163,7 @@ struct enetc_int_vector { char name[ENETC_INT_NAME_MAX]; struct enetc_bdr rx_ring ____cacheline_aligned_in_smp; - struct enetc_bdr tx_ring[0]; + struct enetc_bdr tx_ring[]; }; struct enetc_cls_rule { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 62554f28ce07..da134e211c1a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -588,7 +588,7 @@ struct tgs_gcl_data { __le32 bth; __le32 ct; __le32 cte; - struct gce entry[0]; + struct gce entry[]; }; struct enetc_cbd { diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index f79e57f735b3..bd898f5b4da5 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -584,7 +584,7 @@ struct fec_enet_private { int pps_enable; unsigned int next_counter; - u64 ethtool_stats[0]; + u64 ethtool_stats[]; }; void fec_ptp_init(struct platform_device *pdev, int irq_idx); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h index 2721f1f1ab42..0f0e16f9afc0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -92,7 +92,7 @@ struct ppe_common_cb { u8 comm_index; /*ppe_common index*/ u32 ppe_num; - struct hns_ppe_cb ppe_cb[0]; + struct hns_ppe_cb ppe_cb[]; }; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 3741befb914e..a9f805925699 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -108,7 +108,7 @@ struct rcb_common_cb { u32 ring_num; u32 desc_num; /* desc num per queue*/ - struct ring_pair_cb ring_pair_cb[0]; + struct ring_pair_cb ring_pair_cb[]; }; int hns_rcb_buf_size2type(u32 buf_size); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 51399dbed77a..89d352385260 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9076,8 +9076,8 @@ init_nic_err: static int hclge_init_roce_client_instance(struct hnae3_ae_dev *ae_dev, struct hclge_vport *vport) { - struct hnae3_client *client = vport->roce.client; struct hclge_dev *hdev = ae_dev->priv; + struct hnae3_client *client; int rst_cnt; int ret; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 6f2cf569a283..79b3d53f2fbf 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -297,6 +297,7 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth, } hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif); hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT; hw_ioctxt.cmdq_depth = 0; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index b069045de416..66fd2340d447 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -151,8 +151,8 @@ struct hinic_cmd_hw_ioctxt { u8 lro_en; u8 rsvd3; + u8 ppf_idx; u8 rsvd4; - u8 rsvd5; u16 rq_depth; u16 rx_buf_sz_idx; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h index 517794509eb2..c7bb9ceca72c 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -137,6 +137,7 @@ #define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx) #define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx) #define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx) +#define HINIC_HWIF_PPF_IDX(hwif) ((hwif)->attr.ppf_idx) #define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type) #define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index f4a339b10b10..79091e131418 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -94,6 +94,7 @@ struct hinic_rq { struct hinic_wq *wq; + struct cpumask affinity_mask; u32 irq; u16 msix_entry; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 02a14f5e7fe3..13560975c103 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -356,7 +356,8 @@ static void hinic_enable_rss(struct hinic_dev *nic_dev) if (!num_cpus) num_cpus = num_online_cpus(); - nic_dev->num_qps = min_t(u16, nic_dev->max_qps, num_cpus); + nic_dev->num_qps = hinic_hwdev_num_qps(hwdev); + nic_dev->num_qps = min_t(u16, nic_dev->num_qps, num_cpus); nic_dev->rss_limit = nic_dev->num_qps; nic_dev->num_rss = nic_dev->num_qps; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 56ea6d692f1c..2695ad69fca6 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -475,7 +475,6 @@ static int rx_request_irq(struct hinic_rxq *rxq) struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_rq *rq = rxq->rq; struct hinic_qp *qp; - struct cpumask mask; int err; rx_add_napi(rxq); @@ -492,8 +491,8 @@ static int rx_request_irq(struct hinic_rxq *rxq) } qp = container_of(rq, struct hinic_qp, rq); - cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask); - return irq_set_affinity_hint(rq->irq, &mask); + cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask); + return irq_set_affinity_hint(rq->irq, &rq->affinity_mask); } static void rx_free_irq(struct hinic_rxq *rxq) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index f306084ca12c..5b78362b82ac 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -41,7 +41,7 @@ struct fm10k_l2_accel { u16 count; u16 dglort; struct rcu_head rcu; - struct net_device *macvlan[0]; + struct net_device *macvlan[]; }; enum fm10k_ring_state_t { @@ -198,7 +198,7 @@ struct fm10k_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ /* for dynamic allocation of rings associated with this q_vector */ - struct fm10k_ring ring[0] ____cacheline_internodealigned_in_smp; + struct fm10k_ring ring[] ____cacheline_internodealigned_in_smp; }; enum fm10k_ring_f_enum { @@ -218,7 +218,7 @@ struct fm10k_iov_data { unsigned int num_vfs; unsigned int next_vf_mbx; struct rcu_head rcu; - struct fm10k_vf_info vf_info[0]; + struct fm10k_vf_info vf_info[]; }; struct fm10k_udp_port { diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 4833187bd259..e95b8da45e07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -334,13 +334,13 @@ int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash); struct i40e_ddp_profile_list { u32 p_count; - struct i40e_profile_info p_info[0]; + struct i40e_profile_info p_info[]; }; struct i40e_ddp_old_profile_list { struct list_head list; size_t old_ddp_size; - u8 old_ddp_buf[0]; + u8 old_ddp_buf[]; }; /* macros related to FLX_PIT */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 62fe56ddcb6e..76361bd468db 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3061,9 +3061,6 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, struct flow_cls_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case FLOW_CLS_REPLACE: return iavf_configure_clsflower(adapter, cls_flower); @@ -3087,6 +3084,11 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + struct iavf_adapter *adapter = cb_priv; + + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) + return -EOPNOTSUPP; + switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 49b5fa9d4783..0c9282e2aaec 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -306,7 +306,7 @@ struct igb_q_vector { char name[IFNAMSIZ + 9]; /* for dynamic allocation of rings associated with this q_vector */ - struct igb_ring ring[0] ____cacheline_internodealigned_in_smp; + struct igb_ring ring[] ____cacheline_internodealigned_in_smp; }; enum e1000_ring_flags_t { diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 0014828eec46..a1f845a2aa80 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -326,7 +326,7 @@ struct igc_q_vector { struct net_device poll_dev; /* for dynamic allocation of rings associated with this q_vector */ - struct igc_ring ring[0] ____cacheline_internodealigned_in_smp; + struct igc_ring ring[] ____cacheline_internodealigned_in_smp; }; #define MAX_ETYPE_FILTER (4 - 1) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 39e73ad60352..2833e4f041ce 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -462,7 +462,7 @@ struct ixgbe_q_vector { char name[IFNAMSIZ + 9]; /* for dynamic allocation of rings associated with this q_vector */ - struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp; + struct ixgbe_ring ring[] ____cacheline_internodealigned_in_smp; }; #ifdef CONFIG_IXGBE_HWMON diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 1c391f63a26f..b22eeb5f8700 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3830,13 +3830,9 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, new_clk = gmac_clk & ~MVNETA_GMAC_1MS_CLOCK_ENABLE; new_an = gmac_an & ~(MVNETA_GMAC_INBAND_AN_ENABLE | MVNETA_GMAC_INBAND_RESTART_AN | - MVNETA_GMAC_CONFIG_MII_SPEED | - MVNETA_GMAC_CONFIG_GMII_SPEED | MVNETA_GMAC_AN_SPEED_EN | MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL | - MVNETA_GMAC_CONFIG_FLOW_CTRL | MVNETA_GMAC_AN_FLOW_CTRL_EN | - MVNETA_GMAC_CONFIG_FULL_DUPLEX | MVNETA_GMAC_AN_DUPLEX_EN); /* Even though it might look weird, when we're configured in @@ -3851,24 +3847,20 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, if (phylink_test(state->advertising, Pause)) new_an |= MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL; - if (state->pause & MLO_PAUSE_TXRX_MASK) - new_an |= MVNETA_GMAC_CONFIG_FLOW_CTRL; if (!phylink_autoneg_inband(mode)) { - /* Phy or fixed speed */ - if (state->duplex) - new_an |= MVNETA_GMAC_CONFIG_FULL_DUPLEX; - - if (state->speed == SPEED_1000 || state->speed == SPEED_2500) - new_an |= MVNETA_GMAC_CONFIG_GMII_SPEED; - else if (state->speed == SPEED_100) - new_an |= MVNETA_GMAC_CONFIG_MII_SPEED; + /* Phy or fixed speed - nothing to do, leave the + * configured speed, duplex and flow control as-is. + */ } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { /* SGMII mode receives the state from the PHY */ new_ctrl2 |= MVNETA_GMAC2_INBAND_AN_ENABLE; new_clk |= MVNETA_GMAC_1MS_CLOCK_ENABLE; new_an = (new_an & ~(MVNETA_GMAC_FORCE_LINK_DOWN | - MVNETA_GMAC_FORCE_LINK_PASS)) | + MVNETA_GMAC_FORCE_LINK_PASS | + MVNETA_GMAC_CONFIG_MII_SPEED | + MVNETA_GMAC_CONFIG_GMII_SPEED | + MVNETA_GMAC_CONFIG_FULL_DUPLEX)) | MVNETA_GMAC_INBAND_AN_ENABLE | MVNETA_GMAC_AN_SPEED_EN | MVNETA_GMAC_AN_DUPLEX_EN; @@ -3877,7 +3869,8 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, new_ctrl0 |= MVNETA_GMAC0_PORT_1000BASE_X; new_clk |= MVNETA_GMAC_1MS_CLOCK_ENABLE; new_an = (new_an & ~(MVNETA_GMAC_FORCE_LINK_DOWN | - MVNETA_GMAC_FORCE_LINK_PASS)) | + MVNETA_GMAC_FORCE_LINK_PASS | + MVNETA_GMAC_CONFIG_MII_SPEED)) | MVNETA_GMAC_INBAND_AN_ENABLE | MVNETA_GMAC_CONFIG_GMII_SPEED | /* The MAC only supports FD mode */ @@ -3965,9 +3958,11 @@ static void mvneta_mac_link_down(struct phylink_config *config, mvneta_set_eee(pp, false); } -static void mvneta_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy) +static void mvneta_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct net_device *ndev = to_net_dev(config->dev); struct mvneta_port *pp = netdev_priv(ndev); @@ -3975,8 +3970,36 @@ static void mvneta_mac_link_up(struct phylink_config *config, unsigned int mode, if (!phylink_autoneg_inband(mode)) { val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); - val &= ~MVNETA_GMAC_FORCE_LINK_DOWN; + val &= ~(MVNETA_GMAC_FORCE_LINK_DOWN | + MVNETA_GMAC_CONFIG_MII_SPEED | + MVNETA_GMAC_CONFIG_GMII_SPEED | + MVNETA_GMAC_CONFIG_FLOW_CTRL | + MVNETA_GMAC_CONFIG_FULL_DUPLEX); val |= MVNETA_GMAC_FORCE_LINK_PASS; + + if (speed == SPEED_1000 || speed == SPEED_2500) + val |= MVNETA_GMAC_CONFIG_GMII_SPEED; + else if (speed == SPEED_100) + val |= MVNETA_GMAC_CONFIG_MII_SPEED; + + if (duplex == DUPLEX_FULL) + val |= MVNETA_GMAC_CONFIG_FULL_DUPLEX; + + if (tx_pause || rx_pause) + val |= MVNETA_GMAC_CONFIG_FLOW_CTRL; + + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); + } else { + /* When inband doesn't cover flow control or flow control is + * disabled, we need to manually configure it. This bit will + * only have effect if MVNETA_GMAC_AN_FLOW_CTRL_EN is unset. + */ + val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); + val &= ~MVNETA_GMAC_CONFIG_FLOW_CTRL; + + if (tx_pause || rx_pause) + val |= MVNETA_GMAC_CONFIG_FLOW_CTRL; + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 72133cbe55d4..6b9c7ed2547e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -58,8 +58,11 @@ static struct { */ static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); -static void mvpp2_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy); +static void mvpp2_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -3473,8 +3476,9 @@ static void mvpp2_start_dev(struct mvpp2_port *port) .interface = port->phy_interface, }; mvpp2_mac_config(&port->phylink_config, MLO_AN_INBAND, &state); - mvpp2_mac_link_up(&port->phylink_config, MLO_AN_INBAND, - port->phy_interface, NULL); + mvpp2_mac_link_up(&port->phylink_config, NULL, + MLO_AN_INBAND, port->phy_interface, + SPEED_UNKNOWN, DUPLEX_UNKNOWN, false, false); } netif_tx_start_all_queues(port->dev); @@ -4972,15 +4976,13 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); - an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | + an &= ~(MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG | - MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN | - MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); + MVPP2_GMAC_AN_DUPLEX_EN | MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK; ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK); - ctrl4 &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); /* Configure port type */ if (phy_interface_mode_is_8023z(state->interface)) { @@ -5010,31 +5012,20 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, /* Configure negotiation style */ if (!phylink_autoneg_inband(mode)) { - /* Phy or fixed speed - no in-band AN */ - if (state->duplex) - an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; - - if (state->speed == SPEED_1000 || state->speed == SPEED_2500) - an |= MVPP2_GMAC_CONFIG_GMII_SPEED; - else if (state->speed == SPEED_100) - an |= MVPP2_GMAC_CONFIG_MII_SPEED; - - if (state->pause & MLO_PAUSE_TX) - ctrl4 |= MVPP22_CTRL4_TX_FC_EN; - if (state->pause & MLO_PAUSE_RX) - ctrl4 |= MVPP22_CTRL4_RX_FC_EN; + /* Phy or fixed speed - no in-band AN, nothing to do, leave the + * configured speed, duplex and flow control as-is. + */ } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { /* SGMII in-band mode receives the speed and duplex from * the PHY. Flow control information is not received. */ - an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | + MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX); an |= MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_AN_DUPLEX_EN; - - if (state->pause & MLO_PAUSE_TX) - ctrl4 |= MVPP22_CTRL4_TX_FC_EN; - if (state->pause & MLO_PAUSE_RX) - ctrl4 |= MVPP22_CTRL4_RX_FC_EN; } else if (phy_interface_mode_is_8023z(state->interface)) { /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can * they negotiate duplex: they are always operating with a fixed @@ -5042,19 +5033,17 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, * speed and full duplex here. */ ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; - an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | + MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX); an |= MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_CONFIG_GMII_SPEED | MVPP2_GMAC_CONFIG_FULL_DUPLEX; - if (state->pause & MLO_PAUSE_AN && state->an_enabled) { + if (state->pause & MLO_PAUSE_AN && state->an_enabled) an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG; - } else { - if (state->pause & MLO_PAUSE_TX) - ctrl4 |= MVPP22_CTRL4_TX_FC_EN; - if (state->pause & MLO_PAUSE_RX) - ctrl4 |= MVPP22_CTRL4_RX_FC_EN; - } } /* Some fields of the auto-negotiation register require the port to be down when @@ -5141,25 +5130,54 @@ static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, mvpp2_port_enable(port); } -static void mvpp2_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy) +static void mvpp2_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct net_device *dev = to_net_dev(config->dev); struct mvpp2_port *port = netdev_priv(dev); u32 val; - if (!phylink_autoneg_inband(mode)) { - if (mvpp2_is_xlg(interface)) { + if (mvpp2_is_xlg(interface)) { + if (!phylink_autoneg_inband(mode)) { val = readl(port->base + MVPP22_XLG_CTRL0_REG); val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_DOWN; val |= MVPP22_XLG_CTRL0_FORCE_LINK_PASS; writel(val, port->base + MVPP22_XLG_CTRL0_REG); - } else { + } + } else { + if (!phylink_autoneg_inband(mode)) { val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - val &= ~MVPP2_GMAC_FORCE_LINK_DOWN; + val &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | + MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX); val |= MVPP2_GMAC_FORCE_LINK_PASS; + + if (speed == SPEED_1000 || speed == SPEED_2500) + val |= MVPP2_GMAC_CONFIG_GMII_SPEED; + else if (speed == SPEED_100) + val |= MVPP2_GMAC_CONFIG_MII_SPEED; + + if (duplex == DUPLEX_FULL) + val |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); } + + /* We can always update the flow control enable bits; + * these will only be effective if flow control AN + * (MVPP2_GMAC_FLOW_CTRL_AUTONEG) is disabled. + */ + val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); + val &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); + if (tx_pause) + val |= MVPP22_CTRL4_TX_FC_EN; + if (rx_pause) + val |= MVPP22_CTRL4_RX_FC_EN; + writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); } mvpp2_port_enable(port); diff --git a/drivers/net/ethernet/marvell/skge.h b/drivers/net/ethernet/marvell/skge.h index 6fa7b6a34c08..a1313d57e283 100644 --- a/drivers/net/ethernet/marvell/skge.h +++ b/drivers/net/ethernet/marvell/skge.h @@ -2426,7 +2426,7 @@ struct skge_hw { spinlock_t phy_lock; struct tasklet_struct phy_task; - char irq_name[0]; /* skge@pci:000:04:00.0 */ + char irq_name[]; /* skge@pci:000:04:00.0 */ }; enum pause_control { diff --git a/drivers/net/ethernet/marvell/sky2.h b/drivers/net/ethernet/marvell/sky2.h index b02b6523083c..ada1ca60f088 100644 --- a/drivers/net/ethernet/marvell/sky2.h +++ b/drivers/net/ethernet/marvell/sky2.h @@ -2309,7 +2309,7 @@ struct sky2_hw { struct work_struct restart_work; wait_queue_head_t msi_wait; - char irq_name[0]; + char irq_name[]; }; static inline int sky2_is_copper(const struct sky2_hw *hw) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8c6cfd15481c..8d28f90acfe7 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -412,9 +412,10 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } -static void mtk_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy) +static void mtk_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) { struct mtk_mac *mac = container_of(config, struct mtk_mac, phylink_config); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index e0bb8e12356e..f3dec6b41436 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -25,7 +25,7 @@ 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/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/health.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \ - en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o + en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index ac108f1e5bd6..b7bb81b8c49b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -190,11 +190,6 @@ static int mlx5_devlink_fs_mode_get(struct devlink *devlink, u32 id, return 0; } -enum mlx5_devlink_param_id { - MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, - MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, -}; - static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, union devlink_param_value val, struct netlink_ext_ack *extack) @@ -210,14 +205,38 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, return 0; } +#ifdef CONFIG_MLX5_ESWITCH +static int mlx5_devlink_large_group_num_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + int group_num = val.vu32; + + if (group_num < 1 || group_num > 1024) { + NL_SET_ERR_MSG_MOD(extack, + "Unsupported group number, supported range is 1-1024"); + return -EOPNOTSUPP; + } + + return 0; +} +#endif + static const struct devlink_param mlx5_devlink_params[] = { - DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, + DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE, "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING, BIT(DEVLINK_PARAM_CMODE_RUNTIME), mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set, mlx5_devlink_fs_mode_validate), DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL, mlx5_devlink_enable_roce_validate), +#ifdef CONFIG_MLX5_ESWITCH + DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM, + "fdb_large_groups", DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, + mlx5_devlink_large_group_num_validate), +#endif }; static void mlx5_devlink_set_params_init_values(struct devlink *devlink) @@ -230,13 +249,20 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink) else strcpy(value.vstr, "smfs"); devlink_param_driverinit_value_set(devlink, - MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, + MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE, value); value.vbool = MLX5_CAP_GEN(dev, roce); devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, value); + +#ifdef CONFIG_MLX5_ESWITCH + value.vu32 = ESW_OFFLOADS_DEFAULT_NUM_GROUPS; + devlink_param_driverinit_value_set(devlink, + MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM, + value); +#endif } int mlx5_devlink_register(struct devlink *devlink, struct device *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index d0ba03774ddf..f0de327a59be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -6,6 +6,12 @@ #include <net/devlink.h> +enum mlx5_devlink_param_id { + MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE, + MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM, +}; + struct devlink *mlx5_devlink_alloc(void); void mlx5_devlink_free(struct devlink *devlink); int mlx5_devlink_register(struct devlink *devlink, struct device *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 94d7b69a95c7..c9c9b479bda5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -188,7 +188,7 @@ static int mlx5_fw_tracer_create_mkey(struct mlx5_fw_tracer *tracer) MLX5_SET(create_mkey_in, in, translations_octword_actual_size, DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2)); - mtt = (u64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); for (i = 0 ; i < TRACER_BUFFER_PAGE_NUM ; i++) mtt[i] = cpu_to_be64(tracer->buff.dma + i * PAGE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h index 3b7573461a45..148270073e71 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h @@ -2,7 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #ifndef __MLX5_RSC_DUMP_H -#define __MLX5_RSC_DUMP__H +#define __MLX5_RSC_DUMP_H #include <linux/mlx5/driver.h> #include "mlx5_core.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 220ef9f06f84..93ca9ea5a96e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -737,7 +737,6 @@ struct mlx5e_channel { DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; int cpu; - cpumask_var_t xps_cpumask; }; struct mlx5e_channels { @@ -813,6 +812,15 @@ struct mlx5e_xsk { bool ever_used; }; +/* Temporary storage for variables that are allocated when struct mlx5e_priv is + * initialized, and used where we can't allocate them because that functions + * must not fail. Use with care and make sure the same variable is not used + * simultaneously by multiple users. + */ +struct mlx5e_scratchpad { + cpumask_var_t cpumask; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -872,10 +880,12 @@ struct mlx5e_priv { #endif struct devlink_health_reporter *tx_reporter; struct devlink_health_reporter *rx_reporter; + struct devlink_port dl_phy_port; struct mlx5e_xsk xsk; #if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) struct mlx5e_hv_vhca_stats_agent stats_agent; #endif + struct mlx5e_scratchpad scratchpad; }; struct mlx5e_profile { @@ -1035,14 +1045,22 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs); void mlx5e_close_channels(struct mlx5e_channels *chs); -/* Function pointer to be used to modify WH settings while +/* Function pointer to be used to modify HW or kernel settings while * switching channels */ -typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv); +typedef int (*mlx5e_fp_preactivate)(struct mlx5e_priv *priv, void *context); +#define MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(fn) \ +int fn##_ctx(struct mlx5e_priv *priv, void *context) \ +{ \ + return fn(priv); \ +} int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv); int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify); + mlx5e_fp_preactivate preactivate, + void *context); +int mlx5e_num_channels_changed(struct mlx5e_priv *priv); +int mlx5e_num_channels_changed_ctx(struct mlx5e_priv *priv, void *context); void mlx5e_activate_priv_channels(struct mlx5e_priv *priv); void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); @@ -1122,10 +1140,10 @@ void mlx5e_update_ndo_stats(struct mlx5e_priv *priv); void mlx5e_queue_update_stats(struct mlx5e_priv *priv); int mlx5e_bits_invert(unsigned long a, int size); -typedef int (*change_hw_mtu_cb)(struct mlx5e_priv *priv); int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv); +int mlx5e_set_dev_port_mtu_ctx(struct mlx5e_priv *priv, void *context); int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, - change_hw_mtu_cb set_mtu_cb); + mlx5e_fp_preactivate preactivate); /* ethtool helpers */ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c new file mode 100644 index 000000000000..1a87a3fc6b44 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020, Mellanox Technologies inc. All rights reserved. */ + +#include "en/devlink.h" + +int mlx5e_devlink_phy_port_register(struct net_device *dev) +{ + struct mlx5e_priv *priv; + struct devlink *devlink; + int err; + + priv = netdev_priv(dev); + devlink = priv_to_devlink(priv->mdev); + + devlink_port_attrs_set(&priv->dl_phy_port, + DEVLINK_PORT_FLAVOUR_PHYSICAL, + PCI_FUNC(priv->mdev->pdev->devfn), + false, 0, + NULL, 0); + err = devlink_port_register(devlink, &priv->dl_phy_port, 1); + if (err) + return err; + devlink_port_type_eth_set(&priv->dl_phy_port, dev); + return 0; +} + +void mlx5e_devlink_phy_port_unregister(struct mlx5e_priv *priv) +{ + devlink_port_unregister(&priv->dl_phy_port); +} + +struct devlink_port *mlx5e_get_devlink_phy_port(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + return &priv->dl_phy_port; +} + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h new file mode 100644 index 000000000000..b8cd63b88688 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020, Mellanox Technologies inc. All rights reserved. */ + +#ifndef __MLX5E_EN_DEVLINK_H +#define __MLX5E_EN_DEVLINK_H + +#include <net/devlink.h> +#include "en.h" + +int mlx5e_devlink_phy_port_register(struct net_device *dev); +void mlx5e_devlink_phy_port_unregister(struct mlx5e_priv *priv); +struct devlink_port *mlx5e_get_devlink_phy_port(struct net_device *dev); + +#endif + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 01f2918063af..47874d34156b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1098,49 +1098,59 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) mlx5e_dcbnl_dscp_app(priv, DELETE); } -static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv, - struct mlx5e_params *params) +static void mlx5e_params_calc_trust_tx_min_inline_mode(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u8 trust_state) { - mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode); - if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP && + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); + if (trust_state == MLX5_QPTS_TRUST_DSCP && params->tx_min_inline_mode == MLX5_INLINE_MODE_L2) params->tx_min_inline_mode = MLX5_INLINE_MODE_IP; } -static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv) +static int mlx5e_update_trust_state_hw(struct mlx5e_priv *priv, void *context) +{ + u8 *trust_state = context; + int err; + + err = mlx5_set_trust_state(priv->mdev, *trust_state); + if (err) + return err; + priv->dcbx_dp.trust_state = *trust_state; + + return 0; +} + +static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) { struct mlx5e_channels new_channels = {}; + bool reset_channels = true; + int err = 0; mutex_lock(&priv->state_lock); new_channels.params = priv->channels.params; - mlx5e_trust_update_tx_min_inline_mode(priv, &new_channels.params); + mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &new_channels.params, + trust_state); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; - goto out; + reset_channels = false; } /* Skip if tx_min_inline is the same */ if (new_channels.params.tx_min_inline_mode == priv->channels.params.tx_min_inline_mode) - goto out; + reset_channels = false; - mlx5e_safe_switch_channels(priv, &new_channels, NULL); + if (reset_channels) + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_update_trust_state_hw, + &trust_state); + else + err = mlx5e_update_trust_state_hw(priv, &trust_state); -out: mutex_unlock(&priv->state_lock); -} - -static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) -{ - int err; - - err = mlx5_set_trust_state(priv->mdev, trust_state); - if (err) - return err; - priv->dcbx_dp.trust_state = trust_state; - mlx5e_trust_update_sq_inline_mode(priv); return err; } @@ -1171,7 +1181,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) if (err) return err; - mlx5e_trust_update_tx_min_inline_mode(priv, &priv->channels.params); + mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &priv->channels.params, + priv->dcbx_dp.trust_state); err = mlx5_query_dscp2prio(priv->mdev, priv->dcbx_dp.dscp2prio); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 68b520df07e4..06f6f08ff5eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -357,7 +357,7 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, goto unlock; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); unlock: mutex_unlock(&priv->state_lock); @@ -432,9 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { *cur_params = new_channels.params; - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); + mlx5e_num_channels_changed(priv); goto out; } @@ -442,12 +440,9 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (arfs_enabled) mlx5e_arfs_disable(priv); - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); - /* Switch to new channels, set new parameters and close old ones */ - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_num_channels_changed_ctx, NULL); if (arfs_enabled) { int err2 = mlx5e_arfs_enable(priv); @@ -580,7 +575,7 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); out: mutex_unlock(&priv->state_lock); @@ -1748,7 +1743,7 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable, return 0; } - return mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); } static int set_pflag_tx_cqe_based_moder(struct net_device *netdev, bool enable) @@ -1781,7 +1776,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return 0; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); if (err) return err; @@ -1838,7 +1833,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return 0; } - return mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); } static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable) @@ -1882,7 +1877,7 @@ static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable) return 0; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 966983674663..8236f655a737 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -63,6 +63,7 @@ #include "en/xsk/rx.h" #include "en/xsk/tx.h" #include "en/hv_vhca_stats.h" +#include "en/devlink.h" #include "lib/mlx5.h" @@ -1794,29 +1795,6 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) return err; } -static int mlx5e_alloc_xps_cpumask(struct mlx5e_channel *c, - struct mlx5e_params *params) -{ - int num_comp_vectors = mlx5_comp_vectors_count(c->mdev); - int irq; - - if (!zalloc_cpumask_var(&c->xps_cpumask, GFP_KERNEL)) - return -ENOMEM; - - for (irq = c->ix; irq < num_comp_vectors; irq += params->num_channels) { - int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(c->mdev, irq)); - - cpumask_set_cpu(cpu, c->xps_cpumask); - } - - return 0; -} - -static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c) -{ - free_cpumask_var(c->xps_cpumask); -} - static int mlx5e_open_queues(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1967,10 +1945,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->irq_desc = irq_to_desc(irq); c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); - err = mlx5e_alloc_xps_cpumask(c, params); - if (err) - goto err_free_channel; - netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); err = mlx5e_open_queues(c, params, cparam); @@ -1993,9 +1967,7 @@ err_close_queues: err_napi_del: netif_napi_del(&c->napi); - mlx5e_free_xps_cpumask(c); -err_free_channel: kvfree(c); return err; @@ -2009,7 +1981,6 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_icosq(&c->icosq); mlx5e_activate_rq(&c->rq); - netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix); if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) mlx5e_activate_xsk(c); @@ -2034,7 +2005,6 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) mlx5e_close_xsk(c); mlx5e_close_queues(c); netif_napi_del(&c->napi); - mlx5e_free_xps_cpumask(c); kvfree(c); } @@ -2784,6 +2754,8 @@ free_in: return err; } +static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro); + static int mlx5e_set_mtu(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u16 mtu) { @@ -2833,6 +2805,8 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv) return 0; } +MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_set_dev_port_mtu); + void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv) { struct mlx5e_params *params = &priv->channels.params; @@ -2869,6 +2843,54 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) netdev_set_tc_queue(netdev, tc, nch, 0); } +static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv, u16 count) +{ + int num_txqs = count * priv->channels.params.num_tc; + int num_rxqs = count * priv->profile->rq_groups; + struct net_device *netdev = priv->netdev; + + mlx5e_netdev_set_tcs(netdev); + netif_set_real_num_tx_queues(netdev, num_txqs); + netif_set_real_num_rx_queues(netdev, num_rxqs); +} + +static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, + struct mlx5e_params *params) +{ + struct mlx5_core_dev *mdev = priv->mdev; + int num_comp_vectors, ix, irq; + + num_comp_vectors = mlx5_comp_vectors_count(mdev); + + for (ix = 0; ix < params->num_channels; ix++) { + cpumask_clear(priv->scratchpad.cpumask); + + for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(mdev, irq)); + + cpumask_set_cpu(cpu, priv->scratchpad.cpumask); + } + + netif_set_xps_queue(priv->netdev, priv->scratchpad.cpumask, ix); + } +} + +int mlx5e_num_channels_changed(struct mlx5e_priv *priv) +{ + u16 count = priv->channels.params.num_channels; + + mlx5e_update_netdev_queues(priv, count); + mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params); + + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); + + return 0; +} + +MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_num_channels_changed); + static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) { int i, ch; @@ -2890,14 +2912,6 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { - int num_txqs = priv->channels.num * priv->channels.params.num_tc; - int num_rxqs = priv->channels.num * priv->profile->rq_groups; - struct net_device *netdev = priv->netdev; - - mlx5e_netdev_set_tcs(netdev); - netif_set_real_num_tx_queues(netdev, num_txqs); - netif_set_real_num_rx_queues(netdev, num_rxqs); - mlx5e_build_txq_maps(priv); mlx5e_activate_channels(&priv->channels); mlx5e_xdp_tx_enable(priv); @@ -2930,42 +2944,52 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) mlx5e_deactivate_channels(&priv->channels); } -static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, - struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify) +static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_preactivate preactivate, + void *context) { struct net_device *netdev = priv->netdev; - int new_num_txqs; + struct mlx5e_channels old_chs; int carrier_ok; - - new_num_txqs = new_chs->num * new_chs->params.num_tc; + int err = 0; carrier_ok = netif_carrier_ok(netdev); netif_carrier_off(netdev); - if (new_num_txqs < netdev->real_num_tx_queues) - netif_set_real_num_tx_queues(netdev, new_num_txqs); - mlx5e_deactivate_priv_channels(priv); - mlx5e_close_channels(&priv->channels); + old_chs = priv->channels; priv->channels = *new_chs; - /* New channels are ready to roll, modify HW settings if needed */ - if (hw_modify) - hw_modify(priv); + /* New channels are ready to roll, call the preactivate hook if needed + * to modify HW settings or update kernel parameters. + */ + if (preactivate) { + err = preactivate(priv, context); + if (err) { + priv->channels = old_chs; + goto out; + } + } + mlx5e_close_channels(&old_chs); priv->profile->update_rx(priv); + +out: mlx5e_activate_priv_channels(priv); /* return carrier back if needed */ if (carrier_ok) netif_carrier_on(netdev); + + return err; } int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify) + mlx5e_fp_preactivate preactivate, + void *context) { int err; @@ -2973,8 +2997,16 @@ int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, if (err) return err; - mlx5e_switch_priv_channels(priv, new_chs, hw_modify); + err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context); + if (err) + goto err_close; + return 0; + +err_close: + mlx5e_close_channels(new_chs); + + return err; } int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv) @@ -2982,7 +3014,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv) struct mlx5e_channels new_channels = {}; new_channels.params = priv->channels.params; - return mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); } void mlx5e_timestamp_init(struct mlx5e_priv *priv) @@ -3431,7 +3463,8 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_num_channels_changed_ctx, NULL); if (err) goto out; @@ -3644,7 +3677,8 @@ static int set_feature_lro(struct net_device *netdev, bool enable) goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro); + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_modify_tirs_lro_ctx, NULL); out: mutex_unlock(&priv->state_lock); return err; @@ -3863,7 +3897,7 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev, } int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, - change_hw_mtu_cb set_mtu_cb) + mlx5e_fp_preactivate preactivate) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels new_channels = {}; @@ -3912,13 +3946,13 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (!reset) { params->sw_mtu = new_mtu; - if (set_mtu_cb) - set_mtu_cb(priv); + if (preactivate) + preactivate(priv, NULL); netdev->mtu = params->sw_mtu; goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb); + err = mlx5e_safe_switch_channels(priv, &new_channels, preactivate, NULL); if (err) goto out; @@ -3931,7 +3965,7 @@ out: static int mlx5e_change_nic_mtu(struct net_device *netdev, int new_mtu) { - return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu); + return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu_ctx); } int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) @@ -4392,7 +4426,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) mlx5e_set_rq_type(priv->mdev, &new_channels.params); old_prog = priv->channels.params.xdp_prog; - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); if (err) goto unlock; } else { @@ -4572,6 +4606,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_set_vf_link_state = mlx5e_set_vf_link_state, .ndo_get_vf_stats = mlx5e_get_vf_stats, #endif + .ndo_get_devlink_port = mlx5e_get_devlink_phy_port, }; static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) @@ -4770,9 +4805,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, mlx5e_build_rq_params(mdev, params); /* HW LRO */ - - /* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */ - if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + if (MLX5_CAP_ETH(mdev, lro_cap) && + params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { /* No XSK params: checking the availability of striding RQ in general. */ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) params->lro_en = !slow_pci_heuristic(mdev); @@ -5147,7 +5181,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) static void mlx5e_nic_disable(struct mlx5e_priv *priv) { - struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; #ifdef CONFIG_MLX5_CORE_EN_DCB @@ -5168,7 +5201,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_monitor_counter_cleanup(priv); mlx5e_disable_async_events(priv); - mlx5_lag_remove(mdev, netdev); + mlx5_lag_remove(mdev); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) @@ -5214,6 +5247,9 @@ int mlx5e_netdev_init(struct net_device *netdev, priv->max_nch = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); priv->max_opened_tc = 1; + if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL)) + return -ENOMEM; + mutex_init(&priv->state_lock); INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work); INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); @@ -5222,7 +5258,7 @@ int mlx5e_netdev_init(struct net_device *netdev, priv->wq = create_singlethread_workqueue("mlx5e"); if (!priv->wq) - return -ENOMEM; + goto err_free_cpumask; /* netdev init */ netif_carrier_off(netdev); @@ -5232,11 +5268,17 @@ int mlx5e_netdev_init(struct net_device *netdev, #endif return 0; + +err_free_cpumask: + free_cpumask_var(priv->scratchpad.cpumask); + + return -ENOMEM; } void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv) { destroy_workqueue(priv->wq); + free_cpumask_var(priv->scratchpad.cpumask); } struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, @@ -5271,6 +5313,7 @@ err_free_netdev: int mlx5e_attach_netdev(struct mlx5e_priv *priv) { + const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED; const struct mlx5e_profile *profile; int max_nch; int err; @@ -5282,10 +5325,25 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) max_nch = mlx5e_get_max_num_channels(priv->mdev); if (priv->channels.params.num_channels > max_nch) { mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch); + /* Reducing the number of channels - RXFH has to be reset, and + * mlx5e_num_channels_changed below will build the RQT. + */ + priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED; priv->channels.params.num_channels = max_nch; - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, max_nch); } + /* 1. Set the real number of queues in the kernel the first time. + * 2. Set our default XPS cpumask. + * 3. Build the RQT. + * + * rtnl_lock is required by netif_set_real_num_*_queues in case the + * netdev has been registered by this point (if this function was called + * in the reload or resume flow). + */ + if (take_rtnl) + rtnl_lock(); + mlx5e_num_channels_changed(priv); + if (take_rtnl) + rtnl_unlock(); err = profile->init_tx(priv); if (err) @@ -5415,11 +5473,19 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) goto err_detach; } + err = mlx5e_devlink_phy_port_register(netdev); + if (err) { + mlx5_core_err(mdev, "mlx5e_devlink_phy_port_register failed, %d\n", err); + goto err_unregister_netdev; + } + #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_init_app(priv); #endif return priv; +err_unregister_netdev: + unregister_netdev(netdev); err_detach: mlx5e_detach(mdev, priv); err_destroy_netdev: @@ -5441,6 +5507,7 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_delete_app(priv); #endif + mlx5e_devlink_phy_port_unregister(priv); unregister_netdev(priv->netdev); mlx5e_detach(mdev, vpriv); mlx5e_destroy_netdev(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7b48ccacebe2..1a8897f80547 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -192,7 +192,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) err = mlx5_eswitch_get_vport_stats(esw, rep->vport, &vf_stats); if (err) { - pr_warn("vport %d error %d reading stats\n", rep->vport, err); + netdev_warn(priv->netdev, "vport %d error %d reading stats\n", + rep->vport, err); return; } @@ -1396,7 +1397,7 @@ static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu) static int mlx5e_uplink_rep_change_mtu(struct net_device *netdev, int new_mtu) { - return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu); + return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu_ctx); } static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr) @@ -1422,7 +1423,7 @@ static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan return 0; } -static struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) +static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1435,7 +1436,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_stop = mlx5e_rep_close, .ndo_start_xmit = mlx5e_xmit, .ndo_setup_tc = mlx5e_rep_setup_tc, - .ndo_get_devlink_port = mlx5e_get_devlink_port, + .ndo_get_devlink_port = mlx5e_rep_get_devlink_port, .ndo_get_stats64 = mlx5e_rep_get_stats, .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, @@ -1448,7 +1449,7 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { .ndo_start_xmit = mlx5e_xmit, .ndo_set_mac_address = mlx5e_uplink_rep_set_mac, .ndo_setup_tc = mlx5e_rep_setup_tc, - .ndo_get_devlink_port = mlx5e_get_devlink_port, + .ndo_get_devlink_port = mlx5e_rep_get_devlink_port, .ndo_get_stats64 = mlx5e_get_stats, .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, @@ -1464,6 +1465,11 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { .ndo_set_features = mlx5e_set_features, }; +bool mlx5e_eswitch_uplink_rep(struct net_device *netdev) +{ + return netdev->netdev_ops == &mlx5e_netdev_ops_uplink_rep; +} + bool mlx5e_eswitch_rep(struct net_device *netdev) { if (netdev->netdev_ops == &mlx5e_netdev_ops_rep || @@ -1861,7 +1867,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1870,7 +1875,7 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) #endif mlx5_notifier_unregister(mdev, &priv->events_nb); cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work); - mlx5_lag_remove(mdev, netdev); + mlx5_lag_remove(mdev); } static MLX5E_DEFINE_STATS_GRP(sw_rep, 0); @@ -2027,8 +2032,9 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) &mlx5e_uplink_rep_profile : &mlx5e_rep_profile; netdev = mlx5e_create_netdev(dev, profile, nch, rpriv); if (!netdev) { - pr_warn("Failed to create representor netdev for vport %d\n", - rep->vport); + mlx5_core_warn(dev, + "Failed to create representor netdev for vport %d\n", + rep->vport); kfree(rpriv); return -EINVAL; } @@ -2046,29 +2052,32 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) err = mlx5e_attach_netdev(netdev_priv(netdev)); if (err) { - pr_warn("Failed to attach representor netdev for vport %d\n", - rep->vport); + netdev_warn(netdev, + "Failed to attach representor netdev for vport %d\n", + rep->vport); goto err_destroy_mdev_resources; } err = mlx5e_rep_neigh_init(rpriv); if (err) { - pr_warn("Failed to initialized neighbours handling for vport %d\n", - rep->vport); + netdev_warn(netdev, + "Failed to initialized neighbours handling for vport %d\n", + rep->vport); goto err_detach_netdev; } err = register_devlink_port(dev, rpriv); if (err) { - esw_warn(dev, "Failed to register devlink port %d\n", - rep->vport); + netdev_warn(netdev, "Failed to register devlink port %d\n", + rep->vport); goto err_neigh_cleanup; } err = register_netdev(netdev); if (err) { - pr_warn("Failed to register representor netdev for vport %d\n", - rep->vport); + netdev_warn(netdev, + "Failed to register representor netdev for vport %d\n", + rep->vport); goto err_devlink_cleanup; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 3f756d51435f..8336301476a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -200,6 +200,7 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv, void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv); bool mlx5e_eswitch_rep(struct net_device *netdev); +bool mlx5e_eswitch_uplink_rep(struct net_device *netdev); #else /* CONFIG_MLX5_ESWITCH */ static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1c3ab69cbd96..065c74a2d0c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -158,7 +158,8 @@ static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, mlx5e_read_mini_arr_slot(wq, cqd, cqcc); mlx5e_decompress_cqe_no_hash(rq, wq, cqcc); - rq->handle_rx_cqe(rq, &cqd->title); + INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, rq, &cqd->title); } mlx5e_cqes_update_owner(wq, cqcc - wq->cc); wq->cc = cqcc; @@ -178,7 +179,8 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, mlx5e_read_title_slot(rq, wq, cc); mlx5e_read_mini_arr_slot(wq, cqd, cc + 1); mlx5e_decompress_cqe(rq, wq, cc); - rq->handle_rx_cqe(rq, &cqd->title); + INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, rq, &cqd->title); cqd->mini_arr_idx++; return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 74091f72c9a8..4eb2f2392d2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1076,17 +1076,17 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, static struct mlx5_flow_handle * mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, - struct mlx5_flow_spec *spec, - struct mlx5_esw_flow_attr *slow_attr) + struct mlx5_flow_spec *spec) { + struct mlx5_esw_flow_attr slow_attr; struct mlx5_flow_handle *rule; - memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr)); - slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - slow_attr->split_count = 0; - slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + memcpy(&slow_attr, flow->esw_attr, sizeof(slow_attr)); + slow_attr.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + slow_attr.split_count = 0; + slow_attr.flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; - rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); + rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, &slow_attr); if (!IS_ERR(rule)) flow_flag_set(flow, SLOW); @@ -1095,14 +1095,15 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, static void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, - struct mlx5e_tc_flow *flow, - struct mlx5_esw_flow_attr *slow_attr) + struct mlx5e_tc_flow *flow) { - memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr)); - slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - slow_attr->split_count = 0; - slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; - mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); + struct mlx5_esw_flow_attr slow_attr; + + memcpy(&slow_attr, flow->esw_attr, sizeof(slow_attr)); + slow_attr.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + slow_attr.split_count = 0; + slow_attr.flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + mlx5e_tc_unoffload_fdb_rules(esw, flow, &slow_attr); flow_flag_clear(flow, SLOW); } @@ -1173,7 +1174,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, int out_index; if (!mlx5_esw_chains_prios_supported(esw) && attr->prio != 1) { - NL_SET_ERR_MSG(extack, "E-switch priorities unsupported, upgrade FW"); + NL_SET_ERR_MSG_MOD(extack, + "E-switch priorities unsupported, upgrade FW"); return -EOPNOTSUPP; } @@ -1184,13 +1186,15 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, */ max_chain = mlx5_esw_chains_get_chain_range(esw); if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) { - NL_SET_ERR_MSG(extack, "Requested chain is out of supported range"); + NL_SET_ERR_MSG_MOD(extack, + "Requested chain is out of supported range"); return -EOPNOTSUPP; } max_prio = mlx5_esw_chains_get_prio_range(esw); if (attr->prio > max_prio) { - NL_SET_ERR_MSG(extack, "Requested priority is out of supported range"); + NL_SET_ERR_MSG_MOD(extack, + "Requested priority is out of supported range"); return -EOPNOTSUPP; } @@ -1237,14 +1241,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, * (1) there's no error * (2) there's an encap action and we don't have valid neigh */ - if (!encap_valid) { - /* continue with goto slow path rule instead */ - struct mlx5_esw_flow_attr slow_attr; - - flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec, &slow_attr); - } else { + if (!encap_valid) + flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec); + else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); - } if (IS_ERR(flow->rule[0])) return PTR_ERR(flow->rule[0]); @@ -1272,7 +1272,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->esw_attr; - struct mlx5_esw_flow_attr slow_attr; int out_index; if (flow_flag_test(flow, NOT_READY)) { @@ -1283,7 +1282,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) - mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr); + mlx5e_tc_unoffload_from_slow_path(esw, flow); else mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); } @@ -1312,7 +1311,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct list_head *flow_list) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5_esw_flow_attr slow_attr, *esw_attr; + struct mlx5_esw_flow_attr *esw_attr; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; struct mlx5e_tc_flow *flow; @@ -1365,7 +1364,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, continue; } - mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr); + mlx5e_tc_unoffload_from_slow_path(esw, flow); flow->rule[0] = rule; /* was unset when slow path rule removed */ flow_flag_set(flow, OFFLOADED); @@ -1377,7 +1376,6 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, struct list_head *flow_list) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5_esw_flow_attr slow_attr; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; struct mlx5e_tc_flow *flow; @@ -1389,7 +1387,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, spec = &flow->esw_attr->parse_attr->spec; /* update from encap rule to slow path rule */ - rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec, &slow_attr); + rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); /* mark the flow's encap dest as non-valid */ flow->esw_attr->dests[flow->tmp_efi_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; @@ -2560,7 +2558,6 @@ static const struct pedit_headers zero_masks = {}; static int parse_tc_pedit_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr, struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { @@ -2836,8 +2833,7 @@ static int add_vlan_rewrite_action(struct mlx5e_priv *priv, int namespace, return -EOPNOTSUPP; } - err = parse_tc_pedit_action(priv, &pedit_act, namespace, parse_attr, - hdrs, NULL); + err = parse_tc_pedit_action(priv, &pedit_act, namespace, hdrs, NULL); *action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; return err; @@ -2899,7 +2895,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, case FLOW_ACTION_MANGLE: case FLOW_ACTION_ADD: err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_KERNEL, - parse_attr, hdrs, extack); + hdrs, extack); if (err) return err; @@ -3343,7 +3339,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, case FLOW_ACTION_MANGLE: case FLOW_ACTION_ADD: err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB, - parse_attr, hdrs, extack); + hdrs, extack); if (err) return err; @@ -3381,8 +3377,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { NL_SET_ERR_MSG_MOD(extack, "can't support more output ports, can't offload forwarding"); - pr_err("can't support more than %d output ports, can't offload forwarding\n", - attr->out_count); + netdev_warn(priv->netdev, + "can't support more than %d output ports, can't offload forwarding\n", + attr->out_count); return -EOPNOTSUPP; } @@ -3405,6 +3402,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); struct net_device *uplink_upper; + struct mlx5e_rep_priv *rep_priv; if (is_duplicated_output_device(priv->netdev, out_dev, @@ -3440,11 +3438,29 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return err; } + /* Don't allow forwarding between uplink. + * + * Input vport was stored esw_attr->in_rep. + * In LAG case, *priv* is the private data of + * uplink which may be not the input vport. + */ + rep_priv = mlx5e_rep_to_rep_priv(attr->in_rep); + if (mlx5e_eswitch_uplink_rep(rep_priv->netdev) && + mlx5e_eswitch_uplink_rep(out_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "devices are both uplink, can't offload forwarding"); + pr_err("devices %s %s are both uplink, can't offload forwarding\n", + priv->netdev->name, out_dev->name); + return -EOPNOTSUPP; + } + if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) { NL_SET_ERR_MSG_MOD(extack, "devices are not on same switch HW, can't offload forwarding"); - pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", - priv->netdev->name, out_dev->name); + netdev_warn(priv->netdev, + "devices %s %s not on same switch HW, can't offload forwarding\n", + priv->netdev->name, + out_dev->name); return -EOPNOTSUPP; } @@ -3463,8 +3479,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, } else { NL_SET_ERR_MSG_MOD(extack, "devices are not on same switch HW, can't offload forwarding"); - pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", - priv->netdev->name, out_dev->name); + netdev_warn(priv->netdev, + "devices %s %s not on same switch HW, can't offload forwarding\n", + priv->netdev->name, + out_dev->name); return -EINVAL; } } @@ -3516,12 +3534,15 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported"); return -EOPNOTSUPP; } - if (dest_chain <= attr->chain) { - NL_SET_ERR_MSG(extack, "Goto earlier chain isn't supported"); + if (!mlx5_esw_chains_backwards_supported(esw) && + dest_chain <= attr->chain) { + NL_SET_ERR_MSG_MOD(extack, + "Goto earlier chain isn't supported"); return -EOPNOTSUPP; } if (dest_chain > max_chain) { - NL_SET_ERR_MSG(extack, "Requested destination chain is out of supported range"); + NL_SET_ERR_MSG_MOD(extack, + "Requested destination chain is out of supported range"); return -EOPNOTSUPP; } action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; @@ -3571,7 +3592,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (attr->dest_chain) { if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { - NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); + NL_SET_ERR_MSG_MOD(extack, + "Mirroring goto chain rules isn't supported"); return -EOPNOTSUPP; } attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; @@ -3579,7 +3601,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (!(attr->action & (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { - NL_SET_ERR_MSG(extack, "Rule must have at least one forward/drop action"); + NL_SET_ERR_MSG_MOD(extack, + "Rule must have at least one forward/drop action"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index ee60383adc5b..fd6b2a1898c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -72,8 +72,8 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, { int txq_ix = netdev_pick_tx(dev, skb, NULL); struct mlx5e_priv *priv = netdev_priv(dev); - u16 num_channels; int up = 0; + int ch_ix; if (!netdev_get_num_tc(dev)) return txq_ix; @@ -86,14 +86,13 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, if (skb_vlan_tag_present(skb)) up = skb_vlan_tag_get_prio(skb); - /* txq_ix can be larger than num_channels since - * dev->num_real_tx_queues = num_channels * num_tc + /* Normalize any picked txq_ix to [0, num_channels), + * So we can return a txq_ix that matches the channel and + * packet UP. */ - num_channels = priv->channels.params.num_channels; - if (txq_ix >= num_channels) - txq_ix = priv->txq2sq[txq_ix]->ch_ix; + ch_ix = priv->txq2sq[txq_ix]->ch_ix; - return priv->channel_tc2realtxq[txq_ix][up]; + return priv->channel_tc2realtxq[ch_ix][up]; } static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 257a7c9f7a14..267f4535c36b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -31,6 +31,7 @@ */ #include <linux/irq.h> +#include <linux/indirect_call_wrapper.h> #include "en.h" #include "en/xdp.h" #include "en/xsk/rx.h" @@ -99,7 +100,10 @@ static bool mlx5e_napi_xsk_post(struct mlx5e_xdpsq *xsksq, struct mlx5e_rq *xskr busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); mlx5e_xsk_update_tx_wakeup(xsksq); - xsk_rx_alloc_err = xskrq->post_wqes(xskrq); + xsk_rx_alloc_err = INDIRECT_CALL_2(xskrq->post_wqes, + mlx5e_post_rx_mpwqes, + mlx5e_post_rx_wqes, + xskrq); busy_xsk |= mlx5e_xsk_update_rx_wakeup(xskrq, xsk_rx_alloc_err); return busy_xsk; @@ -142,7 +146,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_poll_ico_cq(&c->icosq.cq); - busy |= rq->post_wqes(rq); + busy |= INDIRECT_CALL_2(rq->post_wqes, + mlx5e_post_rx_mpwqes, + mlx5e_post_rx_wqes, + rq); if (xsk_open) { mlx5e_poll_ico_cq(&c->xskicosq.cq); busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index e49acd0c5da5..25640864c375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -39,6 +39,7 @@ #include "lib/eq.h" #include "eswitch.h" #include "fs_core.h" +#include "devlink.h" #include "ecpf.h" enum { @@ -2006,6 +2007,25 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) esw_disable_vport(esw, vport); } +static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw) +{ + struct devlink *devlink = priv_to_devlink(esw->dev); + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(devlink, + MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM, + &val); + if (!err) { + esw->params.large_group_num = val.vu32; + } else { + esw_warn(esw->dev, + "Devlink can't get param fdb_large_groups, uses default (%d).\n", + ESW_OFFLOADS_DEFAULT_NUM_GROUPS); + esw->params.large_group_num = ESW_OFFLOADS_DEFAULT_NUM_GROUPS; + } +} + int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) { int err; @@ -2022,6 +2042,8 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support)) esw_warn(esw->dev, "engress ACL is not supported by FW\n"); + mlx5_eswitch_get_devlink_param(esw); + esw_create_tsar(esw); esw->mode = mode; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 4472710ccc9c..d010657ce601 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -55,6 +55,8 @@ #ifdef CONFIG_MLX5_ESWITCH +#define ESW_OFFLOADS_DEFAULT_NUM_GROUPS 15 + #define MLX5_MAX_UC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_uc_list)) @@ -183,6 +185,12 @@ struct mlx5_eswitch_fdb { int vlan_push_pop_refcount; struct mlx5_esw_chains_priv *esw_chains_priv; + struct { + DECLARE_HASHTABLE(table, 8); + /* Protects vports.table */ + struct mutex lock; + } vports; + } offloads; }; u32 flags; @@ -255,6 +263,9 @@ struct mlx5_eswitch { u16 manager_vport; u16 first_host_vport; struct mlx5_esw_functions esw_funcs; + struct { + u32 large_group_num; + } params; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -623,6 +634,9 @@ void esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +int mlx5_esw_vport_tbl_get(struct mlx5_eswitch *esw); +void mlx5_esw_vport_tbl_put(struct mlx5_eswitch *esw); + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1a57b2bd74b8..4b5b6618dff4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -50,6 +50,181 @@ #define MLX5_ESW_MISS_FLOWS (2) #define UPLINK_REP_INDEX 0 +/* Per vport tables */ + +#define MLX5_ESW_VPORT_TABLE_SIZE 128 + +/* This struct is used as a key to the hash table and we need it to be packed + * so hash result is consistent + */ +struct mlx5_vport_key { + u32 chain; + u16 prio; + u16 vport; + u16 vhca_id; +} __packed; + +struct mlx5_vport_table { + struct hlist_node hlist; + struct mlx5_flow_table *fdb; + u32 num_rules; + struct mlx5_vport_key key; +}; + +#define MLX5_ESW_VPORT_TBL_NUM_GROUPS 4 + +static struct mlx5_flow_table * +esw_vport_tbl_create(struct mlx5_eswitch *esw, struct mlx5_flow_namespace *ns) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_table *fdb; + + ft_attr.autogroup.max_num_groups = MLX5_ESW_VPORT_TBL_NUM_GROUPS; + ft_attr.max_fte = MLX5_ESW_VPORT_TABLE_SIZE; + ft_attr.prio = FDB_PER_VPORT; + fdb = mlx5_create_auto_grouped_flow_table(ns, &ft_attr); + if (IS_ERR(fdb)) { + esw_warn(esw->dev, "Failed to create per vport FDB Table err %ld\n", + PTR_ERR(fdb)); + } + + return fdb; +} + +static u32 flow_attr_to_vport_key(struct mlx5_eswitch *esw, + struct mlx5_esw_flow_attr *attr, + struct mlx5_vport_key *key) +{ + key->vport = attr->in_rep->vport; + key->chain = attr->chain; + key->prio = attr->prio; + key->vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); + return jhash(key, sizeof(*key), 0); +} + +/* caller must hold vports.lock */ +static struct mlx5_vport_table * +esw_vport_tbl_lookup(struct mlx5_eswitch *esw, struct mlx5_vport_key *skey, u32 key) +{ + struct mlx5_vport_table *e; + + hash_for_each_possible(esw->fdb_table.offloads.vports.table, e, hlist, key) + if (!memcmp(&e->key, skey, sizeof(*skey))) + return e; + + return NULL; +} + +static void +esw_vport_tbl_put(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr) +{ + struct mlx5_vport_table *e; + struct mlx5_vport_key key; + u32 hkey; + + mutex_lock(&esw->fdb_table.offloads.vports.lock); + hkey = flow_attr_to_vport_key(esw, attr, &key); + e = esw_vport_tbl_lookup(esw, &key, hkey); + if (!e || --e->num_rules) + goto out; + + hash_del(&e->hlist); + mlx5_destroy_flow_table(e->fdb); + kfree(e); +out: + mutex_unlock(&esw->fdb_table.offloads.vports.lock); +} + +static struct mlx5_flow_table * +esw_vport_tbl_get(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr) +{ + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *fdb; + struct mlx5_vport_table *e; + struct mlx5_vport_key skey; + u32 hkey; + + mutex_lock(&esw->fdb_table.offloads.vports.lock); + hkey = flow_attr_to_vport_key(esw, attr, &skey); + e = esw_vport_tbl_lookup(esw, &skey, hkey); + if (e) { + e->num_rules++; + goto out; + } + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) { + fdb = ERR_PTR(-ENOMEM); + goto err_alloc; + } + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!ns) { + esw_warn(dev, "Failed to get FDB namespace\n"); + fdb = ERR_PTR(-ENOENT); + goto err_ns; + } + + fdb = esw_vport_tbl_create(esw, ns); + if (IS_ERR(fdb)) + goto err_ns; + + e->fdb = fdb; + e->num_rules = 1; + e->key = skey; + hash_add(esw->fdb_table.offloads.vports.table, &e->hlist, hkey); +out: + mutex_unlock(&esw->fdb_table.offloads.vports.lock); + return e->fdb; + +err_ns: + kfree(e); +err_alloc: + mutex_unlock(&esw->fdb_table.offloads.vports.lock); + return fdb; +} + +int mlx5_esw_vport_tbl_get(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_flow_attr attr = {}; + struct mlx5_eswitch_rep rep = {}; + struct mlx5_flow_table *fdb; + struct mlx5_vport *vport; + int i; + + attr.prio = 1; + attr.in_rep = &rep; + mlx5_esw_for_all_vports(esw, i, vport) { + attr.in_rep->vport = vport->vport; + fdb = esw_vport_tbl_get(esw, &attr); + if (!fdb) + goto out; + } + return 0; + +out: + mlx5_esw_vport_tbl_put(esw); + return PTR_ERR(fdb); +} + +void mlx5_esw_vport_tbl_put(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_flow_attr attr = {}; + struct mlx5_eswitch_rep rep = {}; + struct mlx5_vport *vport; + int i; + + attr.prio = 1; + attr.in_rep = &rep; + mlx5_esw_for_all_vports(esw, i, vport) { + attr.in_rep->vport = vport->vport; + esw_vport_tbl_put(esw, &attr); + } +} + +/* End: Per vport tables */ + static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw, u16 vport_num) { @@ -191,8 +366,6 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, i++; } - mlx5_eswitch_set_rule_source_port(esw, spec, attr); - if (attr->outer_match_level != MLX5_MATCH_NONE) spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; if (attr->inner_match_level != MLX5_MATCH_NONE) @@ -201,8 +374,13 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_hdr = attr->modify_hdr; - fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, - !!split); + if (split) { + fdb = esw_vport_tbl_get(esw, attr); + } else { + fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, + 0); + mlx5_eswitch_set_rule_source_port(esw, spec, attr); + } if (IS_ERR(fdb)) { rule = ERR_CAST(fdb); goto err_esw_get; @@ -221,7 +399,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, return rule; err_add_rule: - mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, !!split); + if (split) + esw_vport_tbl_put(esw, attr); + else + mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0); err_esw_get: if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) && attr->dest_chain) mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0); @@ -247,7 +428,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, goto err_get_fast; } - fwd_fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, 1); + fwd_fdb = esw_vport_tbl_get(esw, attr); if (IS_ERR(fwd_fdb)) { rule = ERR_CAST(fwd_fdb); goto err_get_fwd; @@ -285,7 +466,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, return rule; add_err: - mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 1); + esw_vport_tbl_put(esw, attr); err_get_fwd: mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0); err_get_fast: @@ -312,11 +493,14 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, atomic64_dec(&esw->offloads.num_flows); if (fwd_rule) { - mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 1); + esw_vport_tbl_put(esw, attr); mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0); } else { - mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, - !!split); + if (split) + esw_vport_tbl_put(esw, attr); + else + mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, + 0); if (attr->dest_chain) mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0); } @@ -1923,6 +2107,9 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) if (err) goto create_fg_err; + mutex_init(&esw->fdb_table.offloads.vports.lock); + hash_init(esw->fdb_table.offloads.vports.table); + return 0; create_fg_err: @@ -1939,6 +2126,7 @@ create_fdb_err: static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) { + mutex_destroy(&esw->fdb_table.offloads.vports.lock); esw_destroy_vport_rx_group(esw); esw_destroy_offloads_table(esw); esw_destroy_offloads_fdb_tables(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c index 4276194b633f..d41e4f002b84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c @@ -21,8 +21,6 @@ #define fdb_ignore_flow_level_supported(esw) \ (MLX5_CAP_ESW_FLOWTABLE_FDB((esw)->dev, ignore_flow_level)) -#define ESW_OFFLOADS_NUM_GROUPS 4 - /* Firmware currently has 4 pool of 4 sizes that it supports (ESW_POOLS), * and a virtual memory region of 16M (ESW_SIZE), this region is duplicated * for each flow table pool. We can allocate up to 16M of each pool, @@ -99,6 +97,11 @@ bool mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw) return esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED; } +bool mlx5_esw_chains_backwards_supported(struct mlx5_eswitch *esw) +{ + return fdb_ignore_flow_level_supported(esw); +} + u32 mlx5_esw_chains_get_chain_range(struct mlx5_eswitch *esw) { if (!mlx5_esw_chains_prios_supported(esw)) @@ -234,7 +237,7 @@ mlx5_esw_chains_create_fdb_table(struct mlx5_eswitch *esw, } ft_attr.autogroup.num_reserved_entries = 2; - ft_attr.autogroup.max_num_groups = ESW_OFFLOADS_NUM_GROUPS; + ft_attr.autogroup.max_num_groups = esw->params.large_group_num; fdb = mlx5_create_auto_grouped_flow_table(ns, &ft_attr); if (IS_ERR(fdb)) { esw_warn(esw->dev, @@ -637,7 +640,7 @@ mlx5_esw_chains_init(struct mlx5_eswitch *esw) esw_debug(dev, "Init esw offloads chains, max counters(%d), groups(%d), max flow table size(%d)\n", - max_flow_counter, ESW_OFFLOADS_NUM_GROUPS, fdb_max); + max_flow_counter, esw->params.large_group_num, fdb_max); mlx5_esw_chains_init_sz_pool(esw); @@ -704,12 +707,9 @@ mlx5_esw_chains_open(struct mlx5_eswitch *esw) /* Open level 1 for split rules now if prios isn't supported */ if (!mlx5_esw_chains_prios_supported(esw)) { - ft = mlx5_esw_chains_get_table(esw, 0, 1, 1); - - if (IS_ERR(ft)) { - err = PTR_ERR(ft); + err = mlx5_esw_vport_tbl_get(esw); + if (err) goto level_1_err; - } } return 0; @@ -725,7 +725,7 @@ static void mlx5_esw_chains_close(struct mlx5_eswitch *esw) { if (!mlx5_esw_chains_prios_supported(esw)) - mlx5_esw_chains_put_table(esw, 0, 1, 1); + mlx5_esw_vport_tbl_put(esw); mlx5_esw_chains_put_table(esw, 0, 1, 0); mlx5_esw_chains_put_table(esw, mlx5_esw_chains_get_ft_chain(esw), 1, 0); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h index 2e13097fe348..4ae2baf2a7a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.h @@ -6,6 +6,8 @@ bool mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw); +bool +mlx5_esw_chains_backwards_supported(struct mlx5_eswitch *esw); u32 mlx5_esw_chains_get_prio_range(struct mlx5_eswitch *esw); u32 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index dc08ed9339ab..f3a925e5ba88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -181,7 +181,7 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, const struct mlx5_flow_spec *spec) { - u32 port_mask, port_value; + u16 port_mask, port_value; if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) return spec->flow_context.flow_source == @@ -191,7 +191,7 @@ static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, misc_parameters.source_port); port_value = MLX5_GET(fte_match_param, spec->match_value, misc_parameters.source_port); - return (port_mask & port_value & 0xffff) == MLX5_VPORT_UPLINK; + return (port_mask & port_value) == MLX5_VPORT_UPLINK; } bool diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9dc24241dc91..5826fd43d530 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2700,6 +2700,17 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } + /* We put this priority last, knowing that nothing will get here + * unless explicitly forwarded to. This is possible because the + * slow path tables have catch all rules and nothing gets passed + * those tables. + */ + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_PER_VPORT, 1); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + set_prio_attrs(steering->fdb_root_ns); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 56078b23f1a0..673aaa815f57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -483,7 +483,7 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu) new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index b91eabc09fbc..8e19f6ab8393 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -464,9 +464,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, struct mlx5_lag *ldev; int changed = 0; - if (!net_eq(dev_net(ndev), &init_net)) - return NOTIFY_DONE; - if ((event != NETDEV_CHANGEUPPER) && (event != NETDEV_CHANGELOWERSTATE)) return NOTIFY_DONE; @@ -586,8 +583,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) if (!ldev->nb.notifier_call) { ldev->nb.notifier_call = mlx5_lag_netdev_event; - if (register_netdevice_notifier_dev_net(netdev, &ldev->nb, - &ldev->nn)) { + if (register_netdevice_notifier_net(&init_net, &ldev->nb)) { ldev->nb.notifier_call = NULL; mlx5_core_err(dev, "Failed to register LAG netdev notifier\n"); } @@ -600,7 +596,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) } /* Must be called with intf_mutex held */ -void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev) +void mlx5_lag_remove(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; int i; @@ -620,8 +616,7 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev) if (i == MLX5_MAX_PORTS) { if (ldev->nb.notifier_call) - unregister_netdevice_notifier_dev_net(netdev, &ldev->nb, - &ldev->nn); + unregister_netdevice_notifier_net(&init_net, &ldev->nb); mlx5_lag_mp_cleanup(ldev); cancel_delayed_work_sync(&ldev->bond_work); mlx5_lag_dev_free(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 316ab09e2664..f1068aac6406 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -44,7 +44,6 @@ struct mlx5_lag { struct workqueue_struct *wq; struct delayed_work bond_work; struct notifier_block nb; - struct netdev_net_notifier nn; struct lag_mp lag_mp; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c index e065c2f68f5a..6cbccba56f70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -21,7 +21,7 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) struct mlx5_dm *dm; if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)) - return 0; + return NULL; dm = kzalloc(sizeof(*dm), GFP_KERNEL); if (!dm) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index fcce9e0fc82c..da67b28d6e23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -157,7 +157,7 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam, u8 feature_group, u8 access_reg_group); void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev); -void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev); +void mlx5_lag_remove(struct mlx5_core_dev *dev); int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 6dec2a550a10..f899da9f8488 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -672,7 +672,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, dest_action = action; if (!action->dest_tbl.is_fw_tbl) { if (action->dest_tbl.tbl->dmn != dmn) { - mlx5dr_dbg(dmn, + mlx5dr_err(dmn, "Destination table belongs to a different domain\n"); goto out_invalid_arg; } @@ -703,7 +703,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, action->dest_tbl.fw_tbl.rx_icm_addr = output.sw_owner_icm_root_0; } else { - mlx5dr_dbg(dmn, + mlx5dr_err(dmn, "Failed mlx5_cmd_query_flow_table ret: %d\n", ret); return ret; @@ -772,7 +772,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, /* Check action duplication */ if (++action_type_set[action_type] > max_actions_type) { - mlx5dr_dbg(dmn, "Action type %d supports only max %d time(s)\n", + mlx5dr_err(dmn, "Action type %d supports only max %d time(s)\n", action_type, max_actions_type); goto out_invalid_arg; } @@ -781,7 +781,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, if (dr_action_validate_and_get_next_state(action_domain, action_type, &state)) { - mlx5dr_dbg(dmn, "Invalid action sequence provided\n"); + mlx5dr_err(dmn, "Invalid action sequence provided\n"); return -EOPNOTSUPP; } } @@ -797,7 +797,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, rx_rule && recalc_cs_required && dest_action) { ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr); if (ret) { - mlx5dr_dbg(dmn, + mlx5dr_err(dmn, "Failed to handle checksum recalculation err %d\n", ret); return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index a9da961d4d2f..48b6358b6845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -59,7 +59,7 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn) ret = mlx5_core_alloc_pd(dmn->mdev, &dmn->pdn); if (ret) { - mlx5dr_dbg(dmn, "Couldn't allocate PD\n"); + mlx5dr_err(dmn, "Couldn't allocate PD, ret: %d", ret); return ret; } @@ -192,7 +192,7 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, ret = dr_domain_query_vports(dmn); if (ret) { - mlx5dr_dbg(dmn, "Failed to query vports caps\n"); + mlx5dr_err(dmn, "Failed to query vports caps (err: %d)", ret); goto free_vports_caps; } @@ -213,7 +213,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, int ret; if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) { - mlx5dr_dbg(dmn, "Failed to allocate domain, bad link type\n"); + mlx5dr_err(dmn, "Failed to allocate domain, bad link type\n"); return -EOPNOTSUPP; } @@ -257,7 +257,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0); if (!vport_cap) { - mlx5dr_dbg(dmn, "Failed to get esw manager vport\n"); + mlx5dr_err(dmn, "Failed to get esw manager vport\n"); return -ENOENT; } @@ -268,7 +268,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, dmn->info.tx.drop_icm_addr = dmn->info.caps.esw_tx_drop_address; break; default: - mlx5dr_dbg(dmn, "Invalid domain\n"); + mlx5dr_err(dmn, "Invalid domain\n"); ret = -EINVAL; break; } @@ -300,7 +300,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) mutex_init(&dmn->mutex); if (dr_domain_caps_init(mdev, dmn)) { - mlx5dr_dbg(dmn, "Failed init domain, no caps\n"); + mlx5dr_err(dmn, "Failed init domain, no caps\n"); goto free_domain; } @@ -348,8 +348,11 @@ int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags) mutex_lock(&dmn->mutex); ret = mlx5dr_send_ring_force_drain(dmn); mutex_unlock(&dmn->mutex); - if (ret) + if (ret) { + mlx5dr_err(dmn, "Force drain failed flags: %d, ret: %d\n", + flags, ret); return ret; + } } if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index d7c7467e2d53..30d2d7376f56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -468,7 +468,7 @@ mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); if (err) { dr_icm_chill_buckets_abort(pool, bucket, buckets); - mlx5dr_dbg(pool->dmn, "Sync_steering failed\n"); + mlx5dr_err(pool->dmn, "Sync_steering failed\n"); chunk = NULL; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index c6dbd856df94..a95938874798 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -388,14 +388,14 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx); if (idx == 0) { - mlx5dr_dbg(dmn, "Cannot generate any valid rules from mask\n"); + mlx5dr_err(dmn, "Cannot generate any valid rules from mask\n"); return -EINVAL; } /* Check that all mask fields were consumed */ for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) { if (((u8 *)&mask)[i] != 0) { - mlx5dr_info(dmn, "Mask contains unsupported parameters\n"); + mlx5dr_err(dmn, "Mask contains unsupported parameters\n"); return -EOPNOTSUPP; } } @@ -563,7 +563,7 @@ static int dr_matcher_set_all_ste_builders(struct mlx5dr_matcher *matcher, dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV6); if (!nic_matcher->ste_builder) { - mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n"); + mlx5dr_err(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n"); return -EINVAL; } @@ -634,13 +634,13 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, int ret; if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) { - mlx5dr_info(dmn, "Invalid match criteria attribute\n"); + mlx5dr_err(dmn, "Invalid match criteria attribute\n"); return -EINVAL; } if (mask) { if (mask->match_sz > sizeof(struct mlx5dr_match_param)) { - mlx5dr_info(dmn, "Invalid match size attribute\n"); + mlx5dr_err(dmn, "Invalid match size attribute\n"); return -EINVAL; } mlx5dr_ste_copy_param(matcher->match_criteria, @@ -671,7 +671,7 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher * mlx5dr_matcher_create(struct mlx5dr_table *tbl, - u16 priority, + u32 priority, u8 match_criteria_enable, struct mlx5dr_match_parameters *mask) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index e4cff7abb348..cce3ee7a6614 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -826,8 +826,8 @@ again: ste_location, send_ste_list); if (!new_htbl) { mlx5dr_htbl_put(cur_htbl); - mlx5dr_info(dmn, "failed creating rehash table, htbl-log_size: %d\n", - cur_htbl->chunk_size); + mlx5dr_err(dmn, "Failed creating rehash table, htbl-log_size: %d\n", + cur_htbl->chunk_size); } else { cur_htbl = new_htbl; } @@ -877,7 +877,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, if (!value_size || (value_size > sizeof(struct mlx5dr_match_param) || (value_size % sizeof(u32)))) { - mlx5dr_dbg(matcher->tbl->dmn, "Rule parameters length is incorrect\n"); + mlx5dr_err(matcher->tbl->dmn, "Rule parameters length is incorrect\n"); return false; } @@ -888,7 +888,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, e_idx = min(s_idx + sizeof(param->outer), value_size); if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { - mlx5dr_dbg(matcher->tbl->dmn, "Rule outer parameters contains a value not specified by mask\n"); + mlx5dr_err(matcher->tbl->dmn, "Rule outer parameters contains a value not specified by mask\n"); return false; } } @@ -898,7 +898,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, e_idx = min(s_idx + sizeof(param->misc), value_size); if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { - mlx5dr_dbg(matcher->tbl->dmn, "Rule misc parameters contains a value not specified by mask\n"); + mlx5dr_err(matcher->tbl->dmn, "Rule misc parameters contains a value not specified by mask\n"); return false; } } @@ -908,7 +908,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, e_idx = min(s_idx + sizeof(param->inner), value_size); if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { - mlx5dr_dbg(matcher->tbl->dmn, "Rule inner parameters contains a value not specified by mask\n"); + mlx5dr_err(matcher->tbl->dmn, "Rule inner parameters contains a value not specified by mask\n"); return false; } } @@ -918,7 +918,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, e_idx = min(s_idx + sizeof(param->misc2), value_size); if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { - mlx5dr_dbg(matcher->tbl->dmn, "Rule misc2 parameters contains a value not specified by mask\n"); + mlx5dr_err(matcher->tbl->dmn, "Rule misc2 parameters contains a value not specified by mask\n"); return false; } } @@ -928,7 +928,7 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher, e_idx = min(s_idx + sizeof(param->misc3), value_size); if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { - mlx5dr_dbg(matcher->tbl->dmn, "Rule misc3 parameters contains a value not specified by mask\n"); + mlx5dr_err(matcher->tbl->dmn, "Rule misc3 parameters contains a value not specified by mask\n"); return false; } } @@ -1221,7 +1221,7 @@ remove_action_members: dr_rule_remove_action_members(rule); free_rule: kfree(rule); - mlx5dr_info(dmn, "Failed creating rule\n"); + mlx5dr_err(dmn, "Failed creating rule\n"); return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index c7f10d4f8f8d..a93ed3c3b6c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -136,7 +136,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, err = mlx5_wq_qp_create(mdev, &wqp, temp_qpc, &dr_qp->wq, &dr_qp->wq_ctrl); if (err) { - mlx5_core_info(mdev, "Can't create QP WQ\n"); + mlx5_core_warn(mdev, "Can't create QP WQ\n"); goto err_wq; } @@ -651,8 +651,10 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) /* Init */ ret = dr_modify_qp_rst2init(dmn->mdev, dr_qp, port); - if (ret) + if (ret) { + mlx5dr_err(dmn, "Failed modify QP rst2init\n"); return ret; + } /* RTR */ ret = mlx5dr_cmd_query_gid(dmn->mdev, port, gid_index, &rtr_attr.dgid_attr); @@ -667,8 +669,10 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) rtr_attr.udp_src_port = dmn->info.caps.roce_min_src_udp; ret = dr_cmd_modify_qp_init2rtr(dmn->mdev, dr_qp, &rtr_attr); - if (ret) + if (ret) { + mlx5dr_err(dmn, "Failed modify QP init2rtr\n"); return ret; + } /* RTS */ rts_attr.timeout = 14; @@ -676,8 +680,10 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) rts_attr.rnr_retry = 7; ret = dr_cmd_modify_qp_rtr2rts(dmn->mdev, dr_qp, &rts_attr); - if (ret) + if (ret) { + mlx5dr_err(dmn, "Failed modify QP rtr2rts\n"); return ret; + } return 0; } @@ -861,6 +867,7 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) cq_size = QUEUE_SIZE + 1; dmn->send_ring->cq = dr_create_cq(dmn->mdev, dmn->uar, cq_size); if (!dmn->send_ring->cq) { + mlx5dr_err(dmn, "Failed creating CQ\n"); ret = -ENOMEM; goto free_send_ring; } @@ -872,6 +879,7 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr); if (!dmn->send_ring->qp) { + mlx5dr_err(dmn, "Failed creating QP\n"); ret = -ENOMEM; goto clean_cq; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index aade62a9ee5c..c0e3a1e7389d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -728,7 +728,7 @@ int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, { if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) { if (mask->misc.source_port && mask->misc.source_port != 0xffff) { - mlx5dr_dbg(dmn, "Partial mask source_port is not supported\n"); + mlx5dr_err(dmn, "Partial mask source_port is not supported\n"); return -EINVAL; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c index 14ce2d7dbb66..c2fe48d7b75a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c @@ -128,16 +128,20 @@ static int dr_table_init_nic(struct mlx5dr_domain *dmn, DR_CHUNK_SIZE_1, MLX5DR_STE_LU_TYPE_DONT_CARE, 0); - if (!nic_tbl->s_anchor) + if (!nic_tbl->s_anchor) { + mlx5dr_err(dmn, "Failed allocating htbl\n"); return -ENOMEM; + } info.type = CONNECT_MISS; info.miss_icm_addr = nic_dmn->default_icm_addr; ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, nic_tbl->s_anchor, &info, true); - if (ret) + if (ret) { + mlx5dr_err(dmn, "Failed int and send htbl\n"); goto free_s_anchor; + } mlx5dr_htbl_get(nic_tbl->s_anchor); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index dffe35145d19..3fa739951b34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -705,7 +705,7 @@ struct mlx5dr_matcher { struct mlx5dr_matcher_rx_tx rx; struct mlx5dr_matcher_rx_tx tx; struct list_head matcher_list; - u16 prio; + u32 prio; struct mlx5dr_match_param mask; u8 match_criteria; refcount_t refcount; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index c2027192e21e..d12d3a2d46ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -140,7 +140,7 @@ static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_group *fg) { struct mlx5dr_matcher *matcher; - u16 priority = MLX5_GET(create_flow_group_in, in, + u32 priority = MLX5_GET(create_flow_group_in, in, start_flow_index); u8 match_criteria_enable = MLX5_GET(create_flow_group_in, in, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index e1edc9c247b7..e09e4ea1b045 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -59,7 +59,7 @@ u32 mlx5dr_table_get_id(struct mlx5dr_table *table); struct mlx5dr_matcher * mlx5dr_matcher_create(struct mlx5dr_table *table, - u16 priority, + u32 priority, u8 match_criteria_enable, struct mlx5dr_match_parameters *mask); @@ -151,7 +151,7 @@ mlx5dr_table_get_id(struct mlx5dr_table *table) { return 0; } static inline struct mlx5dr_matcher * mlx5dr_matcher_create(struct mlx5dr_table *table, - u16 priority, + u32 priority, u8 match_criteria_enable, struct mlx5dr_match_parameters *mask) { return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index c7e882eb8f35..046a0cb82ed8 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -150,7 +150,7 @@ mlxfw_fsm_reactivate_err(struct mlxfw_dev *mlxfw_dev, MLXFW_REACT_ERR("device reset required", err); break; case MLXFW_FSM_REACTIVATE_STATUS_ERR_FW_PROGRAMMING_NEEDED: - MLXFW_REACT_ERR("fw progamming needed", err); + MLXFW_REACT_ERR("fw programming needed", err); break; case MLXFW_FSM_REACTIVATE_STATUS_FW_ALREADY_ACTIVATED: MLXFW_REACT_ERR("fw already activated", err); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 0d630096a28c..1078f88cff18 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -142,6 +142,7 @@ struct mlxsw_rx_listener_item { struct list_head list; struct mlxsw_rx_listener rxl; void *priv; + bool enabled; }; struct mlxsw_event_listener_item { @@ -1457,14 +1458,12 @@ static bool __is_rx_listener_equal(const struct mlxsw_rx_listener *rxl_a, static struct mlxsw_rx_listener_item * __find_rx_listener_item(struct mlxsw_core *mlxsw_core, - const struct mlxsw_rx_listener *rxl, - void *priv) + const struct mlxsw_rx_listener *rxl) { struct mlxsw_rx_listener_item *rxl_item; list_for_each_entry(rxl_item, &mlxsw_core->rx_listener_list, list) { - if (__is_rx_listener_equal(&rxl_item->rxl, rxl) && - rxl_item->priv == priv) + if (__is_rx_listener_equal(&rxl_item->rxl, rxl)) return rxl_item; } return NULL; @@ -1472,11 +1471,11 @@ __find_rx_listener_item(struct mlxsw_core *mlxsw_core, int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_rx_listener *rxl, - void *priv) + void *priv, bool enabled) { struct mlxsw_rx_listener_item *rxl_item; - rxl_item = __find_rx_listener_item(mlxsw_core, rxl, priv); + rxl_item = __find_rx_listener_item(mlxsw_core, rxl); if (rxl_item) return -EEXIST; rxl_item = kmalloc(sizeof(*rxl_item), GFP_KERNEL); @@ -1484,6 +1483,7 @@ int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, return -ENOMEM; rxl_item->rxl = *rxl; rxl_item->priv = priv; + rxl_item->enabled = enabled; list_add_rcu(&rxl_item->list, &mlxsw_core->rx_listener_list); return 0; @@ -1491,12 +1491,11 @@ int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, EXPORT_SYMBOL(mlxsw_core_rx_listener_register); void mlxsw_core_rx_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_rx_listener *rxl, - void *priv) + const struct mlxsw_rx_listener *rxl) { struct mlxsw_rx_listener_item *rxl_item; - rxl_item = __find_rx_listener_item(mlxsw_core, rxl, priv); + rxl_item = __find_rx_listener_item(mlxsw_core, rxl); if (!rxl_item) return; list_del_rcu(&rxl_item->list); @@ -1505,6 +1504,19 @@ void mlxsw_core_rx_listener_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_rx_listener_unregister); +static void +mlxsw_core_rx_listener_state_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_rx_listener *rxl, + bool enabled) +{ + struct mlxsw_rx_listener_item *rxl_item; + + rxl_item = __find_rx_listener_item(mlxsw_core, rxl); + if (WARN_ON(!rxl_item)) + return; + rxl_item->enabled = enabled; +} + static void mlxsw_core_event_listener_func(struct sk_buff *skb, u8 local_port, void *priv) { @@ -1534,14 +1546,12 @@ static bool __is_event_listener_equal(const struct mlxsw_event_listener *el_a, static struct mlxsw_event_listener_item * __find_event_listener_item(struct mlxsw_core *mlxsw_core, - const struct mlxsw_event_listener *el, - void *priv) + const struct mlxsw_event_listener *el) { struct mlxsw_event_listener_item *el_item; list_for_each_entry(el_item, &mlxsw_core->event_listener_list, list) { - if (__is_event_listener_equal(&el_item->el, el) && - el_item->priv == priv) + if (__is_event_listener_equal(&el_item->el, el)) return el_item; } return NULL; @@ -1559,7 +1569,7 @@ int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, .trap_id = el->trap_id, }; - el_item = __find_event_listener_item(mlxsw_core, el, priv); + el_item = __find_event_listener_item(mlxsw_core, el); if (el_item) return -EEXIST; el_item = kmalloc(sizeof(*el_item), GFP_KERNEL); @@ -1568,7 +1578,7 @@ int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, el_item->el = *el; el_item->priv = priv; - err = mlxsw_core_rx_listener_register(mlxsw_core, &rxl, el_item); + err = mlxsw_core_rx_listener_register(mlxsw_core, &rxl, el_item, true); if (err) goto err_rx_listener_register; @@ -1586,8 +1596,7 @@ err_rx_listener_register: EXPORT_SYMBOL(mlxsw_core_event_listener_register); void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_event_listener *el, - void *priv) + const struct mlxsw_event_listener *el) { struct mlxsw_event_listener_item *el_item; const struct mlxsw_rx_listener rxl = { @@ -1596,10 +1605,10 @@ void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core, .trap_id = el->trap_id, }; - el_item = __find_event_listener_item(mlxsw_core, el, priv); + el_item = __find_event_listener_item(mlxsw_core, el); if (!el_item) return; - mlxsw_core_rx_listener_unregister(mlxsw_core, &rxl, el_item); + mlxsw_core_rx_listener_unregister(mlxsw_core, &rxl); list_del(&el_item->list); kfree(el_item); } @@ -1607,16 +1616,18 @@ EXPORT_SYMBOL(mlxsw_core_event_listener_unregister); static int mlxsw_core_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, - void *priv) + void *priv, bool enabled) { - if (listener->is_event) + if (listener->is_event) { + WARN_ON(!enabled); return mlxsw_core_event_listener_register(mlxsw_core, - &listener->u.event_listener, + &listener->event_listener, priv); - else + } else { return mlxsw_core_rx_listener_register(mlxsw_core, - &listener->u.rx_listener, - priv); + &listener->rx_listener, + priv, enabled); + } } static void mlxsw_core_listener_unregister(struct mlxsw_core *mlxsw_core, @@ -1625,26 +1636,31 @@ static void mlxsw_core_listener_unregister(struct mlxsw_core *mlxsw_core, { if (listener->is_event) mlxsw_core_event_listener_unregister(mlxsw_core, - &listener->u.event_listener, - priv); + &listener->event_listener); else mlxsw_core_rx_listener_unregister(mlxsw_core, - &listener->u.rx_listener, - priv); + &listener->rx_listener); } int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, void *priv) { + enum mlxsw_reg_htgt_trap_group trap_group; + enum mlxsw_reg_hpkt_action action; char hpkt_pl[MLXSW_REG_HPKT_LEN]; int err; - err = mlxsw_core_listener_register(mlxsw_core, listener, priv); + err = mlxsw_core_listener_register(mlxsw_core, listener, priv, + listener->enabled_on_register); if (err) return err; - mlxsw_reg_hpkt_pack(hpkt_pl, listener->action, listener->trap_id, - listener->trap_group, listener->is_ctrl); + action = listener->enabled_on_register ? listener->en_action : + listener->dis_action; + trap_group = listener->enabled_on_register ? listener->en_trap_group : + listener->dis_trap_group; + mlxsw_reg_hpkt_pack(hpkt_pl, action, listener->trap_id, + trap_group, listener->is_ctrl); err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); if (err) goto err_trap_set; @@ -1664,8 +1680,8 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, char hpkt_pl[MLXSW_REG_HPKT_LEN]; if (!listener->is_event) { - mlxsw_reg_hpkt_pack(hpkt_pl, listener->unreg_action, - listener->trap_id, listener->trap_group, + mlxsw_reg_hpkt_pack(hpkt_pl, listener->dis_action, + listener->trap_id, listener->dis_trap_group, listener->is_ctrl); mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); } @@ -1674,17 +1690,33 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_trap_unregister); -int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core, - const struct mlxsw_listener *listener, - enum mlxsw_reg_hpkt_action action) +int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listener, + bool enabled) { + enum mlxsw_reg_htgt_trap_group trap_group; + enum mlxsw_reg_hpkt_action action; char hpkt_pl[MLXSW_REG_HPKT_LEN]; + int err; + + /* Not supported for event listener */ + if (WARN_ON(listener->is_event)) + return -EINVAL; + action = enabled ? listener->en_action : listener->dis_action; + trap_group = enabled ? listener->en_trap_group : + listener->dis_trap_group; mlxsw_reg_hpkt_pack(hpkt_pl, action, listener->trap_id, - listener->trap_group, listener->is_ctrl); - return mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); + trap_group, listener->is_ctrl); + err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); + if (err) + return err; + + mlxsw_core_rx_listener_state_set(mlxsw_core, &listener->rx_listener, + enabled); + return 0; } -EXPORT_SYMBOL(mlxsw_core_trap_action_set); +EXPORT_SYMBOL(mlxsw_core_trap_state_set); static u64 mlxsw_core_tid_get(struct mlxsw_core *mlxsw_core) { @@ -1942,7 +1974,8 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, if ((rxl->local_port == MLXSW_PORT_DONT_CARE || rxl->local_port == local_port) && rxl->trap_id == rx_info->trap_id) { - found = true; + if (rxl_item->enabled) + found = true; break; } } @@ -2168,13 +2201,22 @@ int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module) /* Here we need to get the module width according to the module type. */ switch (module_type) { + case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_OSFP: + return 8; + case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: /* fall through */ case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_QSFP: + case MLXSW_REG_PMTM_MODULE_TYPE_QSFP: return 4; - case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: + case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_DSFP: return 2; - case MLXSW_REG_PMTM_MODULE_TYPE_BP_SFP: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: + case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_SFP: return 1; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 543476a2e503..46226823c7a6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -62,7 +62,6 @@ struct mlxsw_rx_listener { void (*func)(struct sk_buff *skb, u8 local_port, void *priv); u8 local_port; u16 trap_id; - enum mlxsw_reg_hpkt_action action; }; struct mlxsw_event_listener { @@ -76,58 +75,71 @@ struct mlxsw_listener { union { struct mlxsw_rx_listener rx_listener; struct mlxsw_event_listener event_listener; - } u; - enum mlxsw_reg_hpkt_action action; - enum mlxsw_reg_hpkt_action unreg_action; - u8 trap_group; - bool is_ctrl; /* should go via control buffer or not */ - bool is_event; + }; + enum mlxsw_reg_hpkt_action en_action; /* Action when enabled */ + enum mlxsw_reg_hpkt_action dis_action; /* Action when disabled */ + u8 en_trap_group; /* Trap group when enabled */ + u8 dis_trap_group; /* Trap group when disabled */ + u8 is_ctrl:1, /* should go via control buffer or not */ + is_event:1, + enabled_on_register:1; /* Trap should be enabled when listener + * is registered. + */ }; -#define MLXSW_RXL(_func, _trap_id, _action, _is_ctrl, _trap_group, \ - _unreg_action) \ - { \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - .u.rx_listener = \ - { \ - .func = _func, \ - .local_port = MLXSW_PORT_DONT_CARE, \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - }, \ - .action = MLXSW_REG_HPKT_ACTION_##_action, \ - .unreg_action = MLXSW_REG_HPKT_ACTION_##_unreg_action, \ - .trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_trap_group, \ - .is_ctrl = _is_ctrl, \ - .is_event = false, \ +#define __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ + _dis_action, _enabled_on_register, _dis_trap_group) \ + { \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + .rx_listener = \ + { \ + .func = _func, \ + .local_port = MLXSW_PORT_DONT_CARE, \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + }, \ + .en_action = MLXSW_REG_HPKT_ACTION_##_en_action, \ + .dis_action = MLXSW_REG_HPKT_ACTION_##_dis_action, \ + .en_trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_en_trap_group, \ + .dis_trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_dis_trap_group, \ + .is_ctrl = _is_ctrl, \ + .enabled_on_register = _enabled_on_register, \ } -#define MLXSW_EVENTL(_func, _trap_id, _trap_group) \ - { \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - .u.event_listener = \ - { \ - .func = _func, \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - }, \ - .action = MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, \ - .trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_trap_group, \ - .is_ctrl = false, \ - .is_event = true, \ +#define MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _trap_group, \ + _dis_action) \ + __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _trap_group, \ + _dis_action, true, _trap_group) + +#define MLXSW_RXL_DIS(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ + _dis_action, _dis_trap_group) \ + __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ + _dis_action, false, _dis_trap_group) + +#define MLXSW_EVENTL(_func, _trap_id, _trap_group) \ + { \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + .event_listener = \ + { \ + .func = _func, \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + }, \ + .en_action = MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, \ + .en_trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_trap_group, \ + .is_event = true, \ + .enabled_on_register = true, \ } int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_rx_listener *rxl, - void *priv); + void *priv, bool enabled); void mlxsw_core_rx_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_rx_listener *rxl, - void *priv); + const struct mlxsw_rx_listener *rxl); int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_event_listener *el, void *priv); void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_event_listener *el, - void *priv); + const struct mlxsw_event_listener *el); int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, @@ -135,9 +147,9 @@ int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, void *priv); -int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core, - const struct mlxsw_listener *listener, - enum mlxsw_reg_hpkt_action action); +int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listener, + bool enabled); typedef void mlxsw_reg_trans_cb_t(struct mlxsw_core *mlxsw_core, char *payload, size_t payload_len, unsigned long cb_priv); @@ -461,7 +473,10 @@ enum mlxsw_devlink_param_id { }; struct mlxsw_skb_cb { - struct mlxsw_tx_info tx_info; + union { + struct mlxsw_tx_info tx_info; + u32 cookie_index; /* Only used during receive */ + }; }; static inline struct mlxsw_skb_cb *mlxsw_skb_cb(struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index c51b2adfc1e1..1f2e6db743e1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -7,6 +7,9 @@ #include <linux/errno.h> #include <linux/rhashtable.h> #include <linux/list.h> +#include <linux/idr.h> +#include <linux/refcount.h> +#include <net/flow_offload.h> #include "item.h" #include "trap.h" @@ -63,6 +66,8 @@ struct mlxsw_afa { void *ops_priv; struct rhashtable set_ht; struct rhashtable fwd_entry_ht; + struct rhashtable cookie_ht; + struct idr cookie_idr; }; #define MLXSW_AFA_SET_LEN 0xA8 @@ -121,6 +126,55 @@ static const struct rhashtable_params mlxsw_afa_fwd_entry_ht_params = { .automatic_shrinking = true, }; +struct mlxsw_afa_cookie { + struct rhash_head ht_node; + refcount_t ref_count; + struct rcu_head rcu; + u32 cookie_index; + struct flow_action_cookie fa_cookie; +}; + +static u32 mlxsw_afa_cookie_hash(const struct flow_action_cookie *fa_cookie, + u32 seed) +{ + return jhash2((u32 *) fa_cookie->cookie, + fa_cookie->cookie_len / sizeof(u32), seed); +} + +static u32 mlxsw_afa_cookie_key_hashfn(const void *data, u32 len, u32 seed) +{ + const struct flow_action_cookie *fa_cookie = data; + + return mlxsw_afa_cookie_hash(fa_cookie, seed); +} + +static u32 mlxsw_afa_cookie_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct mlxsw_afa_cookie *cookie = data; + + return mlxsw_afa_cookie_hash(&cookie->fa_cookie, seed); +} + +static int mlxsw_afa_cookie_obj_cmpfn(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct flow_action_cookie *fa_cookie = arg->key; + const struct mlxsw_afa_cookie *cookie = obj; + + if (cookie->fa_cookie.cookie_len == fa_cookie->cookie_len) + return memcmp(cookie->fa_cookie.cookie, fa_cookie->cookie, + fa_cookie->cookie_len); + return 1; +} + +static const struct rhashtable_params mlxsw_afa_cookie_ht_params = { + .head_offset = offsetof(struct mlxsw_afa_cookie, ht_node), + .hashfn = mlxsw_afa_cookie_key_hashfn, + .obj_hashfn = mlxsw_afa_cookie_obj_hashfn, + .obj_cmpfn = mlxsw_afa_cookie_obj_cmpfn, + .automatic_shrinking = true, +}; + struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set, const struct mlxsw_afa_ops *ops, void *ops_priv) @@ -138,11 +192,18 @@ struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set, &mlxsw_afa_fwd_entry_ht_params); if (err) goto err_fwd_entry_rhashtable_init; + err = rhashtable_init(&mlxsw_afa->cookie_ht, + &mlxsw_afa_cookie_ht_params); + if (err) + goto err_cookie_rhashtable_init; + idr_init(&mlxsw_afa->cookie_idr); mlxsw_afa->max_acts_per_set = max_acts_per_set; mlxsw_afa->ops = ops; mlxsw_afa->ops_priv = ops_priv; return mlxsw_afa; +err_cookie_rhashtable_init: + rhashtable_destroy(&mlxsw_afa->fwd_entry_ht); err_fwd_entry_rhashtable_init: rhashtable_destroy(&mlxsw_afa->set_ht); err_set_rhashtable_init: @@ -153,6 +214,9 @@ EXPORT_SYMBOL(mlxsw_afa_create); void mlxsw_afa_destroy(struct mlxsw_afa *mlxsw_afa) { + WARN_ON(!idr_is_empty(&mlxsw_afa->cookie_idr)); + idr_destroy(&mlxsw_afa->cookie_idr); + rhashtable_destroy(&mlxsw_afa->cookie_ht); rhashtable_destroy(&mlxsw_afa->fwd_entry_ht); rhashtable_destroy(&mlxsw_afa->set_ht); kfree(mlxsw_afa); @@ -627,6 +691,151 @@ err_counter_index_get: return ERR_PTR(err); } +/* 20 bits is a maximum that hardware can handle in trap with userdef action + * and carry along with the trapped packet. + */ +#define MLXSW_AFA_COOKIE_INDEX_BITS 20 +#define MLXSW_AFA_COOKIE_INDEX_MAX ((1 << MLXSW_AFA_COOKIE_INDEX_BITS) - 1) + +static struct mlxsw_afa_cookie * +mlxsw_afa_cookie_create(struct mlxsw_afa *mlxsw_afa, + const struct flow_action_cookie *fa_cookie) +{ + struct mlxsw_afa_cookie *cookie; + u32 cookie_index; + int err; + + cookie = kzalloc(sizeof(*cookie) + fa_cookie->cookie_len, GFP_KERNEL); + if (!cookie) + return ERR_PTR(-ENOMEM); + refcount_set(&cookie->ref_count, 1); + memcpy(&cookie->fa_cookie, fa_cookie, + sizeof(*fa_cookie) + fa_cookie->cookie_len); + + err = rhashtable_insert_fast(&mlxsw_afa->cookie_ht, &cookie->ht_node, + mlxsw_afa_cookie_ht_params); + if (err) + goto err_rhashtable_insert; + + /* Start cookie indexes with 1. Leave the 0 index unused. Packets + * that come from the HW which are not dropped by drop-with-cookie + * action are going to pass cookie_index 0 to lookup. + */ + cookie_index = 1; + err = idr_alloc_u32(&mlxsw_afa->cookie_idr, cookie, &cookie_index, + MLXSW_AFA_COOKIE_INDEX_MAX, GFP_KERNEL); + if (err) + goto err_idr_alloc; + cookie->cookie_index = cookie_index; + return cookie; + +err_idr_alloc: + rhashtable_remove_fast(&mlxsw_afa->cookie_ht, &cookie->ht_node, + mlxsw_afa_cookie_ht_params); +err_rhashtable_insert: + kfree(cookie); + return ERR_PTR(err); +} + +static void mlxsw_afa_cookie_destroy(struct mlxsw_afa *mlxsw_afa, + struct mlxsw_afa_cookie *cookie) +{ + idr_remove(&mlxsw_afa->cookie_idr, cookie->cookie_index); + rhashtable_remove_fast(&mlxsw_afa->cookie_ht, &cookie->ht_node, + mlxsw_afa_cookie_ht_params); + kfree_rcu(cookie, rcu); +} + +static struct mlxsw_afa_cookie * +mlxsw_afa_cookie_get(struct mlxsw_afa *mlxsw_afa, + const struct flow_action_cookie *fa_cookie) +{ + struct mlxsw_afa_cookie *cookie; + + cookie = rhashtable_lookup_fast(&mlxsw_afa->cookie_ht, fa_cookie, + mlxsw_afa_cookie_ht_params); + if (cookie) { + refcount_inc(&cookie->ref_count); + return cookie; + } + return mlxsw_afa_cookie_create(mlxsw_afa, fa_cookie); +} + +static void mlxsw_afa_cookie_put(struct mlxsw_afa *mlxsw_afa, + struct mlxsw_afa_cookie *cookie) +{ + if (!refcount_dec_and_test(&cookie->ref_count)) + return; + mlxsw_afa_cookie_destroy(mlxsw_afa, cookie); +} + +/* RCU read lock must be held */ +const struct flow_action_cookie * +mlxsw_afa_cookie_lookup(struct mlxsw_afa *mlxsw_afa, u32 cookie_index) +{ + struct mlxsw_afa_cookie *cookie; + + /* 0 index means no cookie */ + if (!cookie_index) + return NULL; + cookie = idr_find(&mlxsw_afa->cookie_idr, cookie_index); + if (!cookie) + return NULL; + return &cookie->fa_cookie; +} +EXPORT_SYMBOL(mlxsw_afa_cookie_lookup); + +struct mlxsw_afa_cookie_ref { + struct mlxsw_afa_resource resource; + struct mlxsw_afa_cookie *cookie; +}; + +static void +mlxsw_afa_cookie_ref_destroy(struct mlxsw_afa_block *block, + struct mlxsw_afa_cookie_ref *cookie_ref) +{ + mlxsw_afa_resource_del(&cookie_ref->resource); + mlxsw_afa_cookie_put(block->afa, cookie_ref->cookie); + kfree(cookie_ref); +} + +static void +mlxsw_afa_cookie_ref_destructor(struct mlxsw_afa_block *block, + struct mlxsw_afa_resource *resource) +{ + struct mlxsw_afa_cookie_ref *cookie_ref; + + cookie_ref = container_of(resource, struct mlxsw_afa_cookie_ref, + resource); + mlxsw_afa_cookie_ref_destroy(block, cookie_ref); +} + +static struct mlxsw_afa_cookie_ref * +mlxsw_afa_cookie_ref_create(struct mlxsw_afa_block *block, + const struct flow_action_cookie *fa_cookie) +{ + struct mlxsw_afa_cookie_ref *cookie_ref; + struct mlxsw_afa_cookie *cookie; + int err; + + cookie_ref = kzalloc(sizeof(*cookie_ref), GFP_KERNEL); + if (!cookie_ref) + return ERR_PTR(-ENOMEM); + cookie = mlxsw_afa_cookie_get(block->afa, fa_cookie); + if (IS_ERR(cookie)) { + err = PTR_ERR(cookie); + goto err_cookie_get; + } + cookie_ref->cookie = cookie; + cookie_ref->resource.destructor = mlxsw_afa_cookie_ref_destructor; + mlxsw_afa_resource_add(block, &cookie_ref->resource); + return cookie_ref; + +err_cookie_get: + kfree(cookie_ref); + return ERR_PTR(err); +} + #define MLXSW_AFA_ONE_ACTION_LEN 32 #define MLXSW_AFA_PAYLOAD_OFFSET 4 @@ -747,97 +956,170 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, } EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify); -/* Trap / Discard Action - * --------------------- - * The Trap / Discard action enables trapping / mirroring packets to the CPU +/* Trap Action / Trap With Userdef Action + * -------------------------------------- + * The Trap action enables trapping / mirroring packets to the CPU * as well as discarding packets. * The ACL Trap / Discard separates the forward/discard control from CPU * trap control. In addition, the Trap / Discard action enables activating * SPAN (port mirroring). + * + * The Trap with userdef action action has the same functionality as + * the Trap action with addition of user defined value that can be set + * and used by higher layer applications. */ -#define MLXSW_AFA_TRAPDISC_CODE 0x03 -#define MLXSW_AFA_TRAPDISC_SIZE 1 +#define MLXSW_AFA_TRAP_CODE 0x03 +#define MLXSW_AFA_TRAP_SIZE 1 + +#define MLXSW_AFA_TRAPWU_CODE 0x04 +#define MLXSW_AFA_TRAPWU_SIZE 2 -enum mlxsw_afa_trapdisc_trap_action { - MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP = 0, - MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP = 2, +enum mlxsw_afa_trap_trap_action { + MLXSW_AFA_TRAP_TRAP_ACTION_NOP = 0, + MLXSW_AFA_TRAP_TRAP_ACTION_TRAP = 2, }; -/* afa_trapdisc_trap_action +/* afa_trap_trap_action * Trap Action. */ -MLXSW_ITEM32(afa, trapdisc, trap_action, 0x00, 24, 4); +MLXSW_ITEM32(afa, trap, trap_action, 0x00, 24, 4); -enum mlxsw_afa_trapdisc_forward_action { - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD = 1, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD = 3, +enum mlxsw_afa_trap_forward_action { + MLXSW_AFA_TRAP_FORWARD_ACTION_FORWARD = 1, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD = 3, }; -/* afa_trapdisc_forward_action +/* afa_trap_forward_action * Forward Action. */ -MLXSW_ITEM32(afa, trapdisc, forward_action, 0x00, 0, 4); +MLXSW_ITEM32(afa, trap, forward_action, 0x00, 0, 4); -/* afa_trapdisc_trap_id +/* afa_trap_trap_id * Trap ID to configure. */ -MLXSW_ITEM32(afa, trapdisc, trap_id, 0x04, 0, 9); +MLXSW_ITEM32(afa, trap, trap_id, 0x04, 0, 9); -/* afa_trapdisc_mirror_agent +/* afa_trap_mirror_agent * Mirror agent. */ -MLXSW_ITEM32(afa, trapdisc, mirror_agent, 0x08, 29, 3); +MLXSW_ITEM32(afa, trap, mirror_agent, 0x08, 29, 3); -/* afa_trapdisc_mirror_enable +/* afa_trap_mirror_enable * Mirror enable. */ -MLXSW_ITEM32(afa, trapdisc, mirror_enable, 0x08, 24, 1); +MLXSW_ITEM32(afa, trap, mirror_enable, 0x08, 24, 1); + +/* user_def_val + * Value for the SW usage. Can be used to pass information of which + * rule has caused a trap. This may be overwritten by later traps. + * This field does a set on the packet's user_def_val only if this + * is the first trap_id or if the trap_id has replaced the previous + * packet's trap_id. + */ +MLXSW_ITEM32(afa, trap, user_def_val, 0x0C, 0, 20); static inline void -mlxsw_afa_trapdisc_pack(char *payload, - enum mlxsw_afa_trapdisc_trap_action trap_action, - enum mlxsw_afa_trapdisc_forward_action forward_action, - u16 trap_id) +mlxsw_afa_trap_pack(char *payload, + enum mlxsw_afa_trap_trap_action trap_action, + enum mlxsw_afa_trap_forward_action forward_action, + u16 trap_id) { - mlxsw_afa_trapdisc_trap_action_set(payload, trap_action); - mlxsw_afa_trapdisc_forward_action_set(payload, forward_action); - mlxsw_afa_trapdisc_trap_id_set(payload, trap_id); + mlxsw_afa_trap_trap_action_set(payload, trap_action); + mlxsw_afa_trap_forward_action_set(payload, forward_action); + mlxsw_afa_trap_trap_id_set(payload, trap_id); } static inline void -mlxsw_afa_trapdisc_mirror_pack(char *payload, bool mirror_enable, - u8 mirror_agent) +mlxsw_afa_trapwu_pack(char *payload, + enum mlxsw_afa_trap_trap_action trap_action, + enum mlxsw_afa_trap_forward_action forward_action, + u16 trap_id, u32 user_def_val) { - mlxsw_afa_trapdisc_mirror_enable_set(payload, mirror_enable); - mlxsw_afa_trapdisc_mirror_agent_set(payload, mirror_agent); + mlxsw_afa_trap_pack(payload, trap_action, forward_action, trap_id); + mlxsw_afa_trap_user_def_val_set(payload, user_def_val); } -int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block) +static inline void +mlxsw_afa_trap_mirror_pack(char *payload, bool mirror_enable, + u8 mirror_agent) { - char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + mlxsw_afa_trap_mirror_enable_set(payload, mirror_enable); + mlxsw_afa_trap_mirror_agent_set(payload, mirror_agent); +} + +static int mlxsw_afa_block_append_drop_plain(struct mlxsw_afa_block *block, + bool ingress) +{ + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD, + ingress ? MLXSW_TRAP_ID_DISCARD_INGRESS_ACL : + MLXSW_TRAP_ID_DISCARD_EGRESS_ACL); return 0; } + +static int +mlxsw_afa_block_append_drop_with_cookie(struct mlxsw_afa_block *block, + bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack) +{ + struct mlxsw_afa_cookie_ref *cookie_ref; + u32 cookie_index; + char *act; + int err; + + cookie_ref = mlxsw_afa_cookie_ref_create(block, fa_cookie); + if (IS_ERR(cookie_ref)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot create cookie for drop action"); + return PTR_ERR(cookie_ref); + } + cookie_index = cookie_ref->cookie->cookie_index; + + act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAPWU_CODE, + MLXSW_AFA_TRAPWU_SIZE); + if (IS_ERR(act)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot append drop with cookie action"); + err = PTR_ERR(act); + goto err_append_action; + } + mlxsw_afa_trapwu_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD, + ingress ? MLXSW_TRAP_ID_DISCARD_INGRESS_ACL : + MLXSW_TRAP_ID_DISCARD_EGRESS_ACL, + cookie_index); + return 0; + +err_append_action: + mlxsw_afa_cookie_ref_destroy(block, cookie_ref); + return err; +} + +int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block, bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack) +{ + return fa_cookie ? + mlxsw_afa_block_append_drop_with_cookie(block, ingress, + fa_cookie, extack) : + mlxsw_afa_block_append_drop_plain(block, ingress); +} EXPORT_SYMBOL(mlxsw_afa_block_append_drop); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id) { - char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, - trap_id); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD, trap_id); return 0; } EXPORT_SYMBOL(mlxsw_afa_block_append_trap); @@ -845,15 +1127,13 @@ EXPORT_SYMBOL(mlxsw_afa_block_append_trap); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, u16 trap_id) { - char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, - trap_id); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_FORWARD, trap_id); return 0; } EXPORT_SYMBOL(mlxsw_afa_block_append_trap_and_forward); @@ -920,13 +1200,13 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, u8 mirror_agent) { char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0); - mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_NOP, + MLXSW_AFA_TRAP_FORWARD_ACTION_FORWARD, 0); + mlxsw_afa_trap_mirror_pack(act, true, mirror_agent); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 0e3a59dda12e..5f4c1e505136 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/netdevice.h> +#include <net/flow_offload.h> struct mlxsw_afa; struct mlxsw_afa_block; @@ -42,7 +43,11 @@ int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity); int mlxsw_afa_block_continue(struct mlxsw_afa_block *block); int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block); -int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); +const struct flow_action_cookie * +mlxsw_afa_cookie_lookup(struct mlxsw_afa *mlxsw_afa, u32 cookie_index); +int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block, bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, u16 trap_id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 914c33e46fb4..67ee0da75af2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -575,6 +575,15 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe); + if (rx_info.trap_id == MLXSW_TRAP_ID_DISCARD_INGRESS_ACL || + rx_info.trap_id == MLXSW_TRAP_ID_DISCARD_EGRESS_ACL) { + u32 cookie_index = 0; + + if (mlxsw_pci->max_cqe_ver >= MLXSW_PCI_CQE_V2) + cookie_index = mlxsw_pci_cqe2_user_def_val_orig_pkt_len_get(cqe); + mlxsw_skb_cb(skb)->cookie_index = cookie_index; + } + byte_count = mlxsw_pci_cqe_byte_count_get(cqe); if (mlxsw_pci_cqe_crc_get(cqe_v, cqe)) byte_count -= ETH_FCS_LEN; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index e0d7d2d9a0c8..32c7cabfb261 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -25,10 +25,8 @@ #define MLXSW_PCI_CIR_CTRL_STATUS_SHIFT 24 #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000 -#define MLXSW_PCI_SW_RESET 0xF0010 -#define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E @@ -210,6 +208,11 @@ MLXSW_ITEM32(pci, cqe0, dqn, 0x0C, 1, 5); MLXSW_ITEM32(pci, cqe12, dqn, 0x0C, 1, 6); mlxsw_pci_cqe_item_helpers(dqn, 0, 12, 12); +/* pci_cqe_user_def_val_orig_pkt_len + * When trap_id is an ACL: User defined value from policy engine action. + */ +MLXSW_ITEM32(pci, cqe2, user_def_val_orig_pkt_len, 0x14, 0, 20); + /* pci_cqe_owner * Ownership bit. */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index dd6685156396..1bc65e597de0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -621,7 +621,7 @@ static inline void mlxsw_reg_sfn_pack(char *payload) { MLXSW_REG_ZERO(sfn, payload); mlxsw_reg_sfn_swid_set(payload, 0); - mlxsw_reg_sfn_end_set(payload, 1); + mlxsw_reg_sfn_end_set(payload, 0); mlxsw_reg_sfn_num_rec_set(payload, MLXSW_REG_SFN_REC_MAX_COUNT); } @@ -5440,15 +5440,29 @@ enum mlxsw_reg_pmtm_module_type { /* Backplane with 4 lanes */ MLXSW_REG_PMTM_MODULE_TYPE_BP_4X, /* QSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_QSFP, + MLXSW_REG_PMTM_MODULE_TYPE_QSFP, /* SFP */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_SFP, + MLXSW_REG_PMTM_MODULE_TYPE_SFP, /* Backplane with single lane */ MLXSW_REG_PMTM_MODULE_TYPE_BP_1X = 4, /* Backplane with two lane */ MLXSW_REG_PMTM_MODULE_TYPE_BP_2X = 8, - /* Chip2Chip */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C = 10, + /* Chip2Chip4x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C4X = 10, + /* Chip2Chip2x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C2X, + /* Chip2Chip1x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C1X, + /* QSFP-DD */ + MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14, + /* OSFP */ + MLXSW_REG_PMTM_MODULE_TYPE_OSFP, + /* SFP-DD */ + MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD, + /* DSFP */ + MLXSW_REG_PMTM_MODULE_TYPE_DSFP, + /* Chip2Chip8x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C8X, }; /* reg_pmtm_module_type @@ -5526,9 +5540,11 @@ enum mlxsw_reg_htgt_trap_group { enum mlxsw_reg_htgt_discard_trap_group { MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX, + MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY, MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS, }; /* reg_htgt_trap_group diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 0e399b068435..673fa2fd995c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2228,6 +2228,15 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_3635_stats[] = { #define MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN \ ARRAY_SIZE(mlxsw_sp_port_hw_rfc_3635_stats) +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_ext_stats[] = { + { + .str = "ecn_marked", + .getter = mlxsw_reg_ppcnt_ecn_marked_get, + }, +}; + +#define MLXSW_SP_PORT_HW_EXT_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_ext_stats) + static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_discard_stats[] = { { .str = "discard_ingress_general", @@ -2337,6 +2346,7 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = { MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN + \ MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \ MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN + \ + MLXSW_SP_PORT_HW_EXT_STATS_LEN + \ MLXSW_SP_PORT_HW_DISCARD_STATS_LEN + \ (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \ IEEE_8021QAZ_MAX_TCS) + \ @@ -2398,6 +2408,12 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev, p += ETH_GSTRING_LEN; } + for (i = 0; i < MLXSW_SP_PORT_HW_EXT_STATS_LEN; i++) { + memcpy(p, mlxsw_sp_port_hw_ext_stats[i].str, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < MLXSW_SP_PORT_HW_DISCARD_STATS_LEN; i++) { memcpy(p, mlxsw_sp_port_hw_discard_stats[i].str, ETH_GSTRING_LEN); @@ -2459,6 +2475,10 @@ mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats, *p_hw_stats = mlxsw_sp_port_hw_rfc_3635_stats; *p_len = MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN; break; + case MLXSW_REG_PPCNT_EXT_CNT: + *p_hw_stats = mlxsw_sp_port_hw_ext_stats; + *p_len = MLXSW_SP_PORT_HW_EXT_STATS_LEN; + break; case MLXSW_REG_PPCNT_DISCARD_CNT: *p_hw_stats = mlxsw_sp_port_hw_discard_stats; *p_len = MLXSW_SP_PORT_HW_DISCARD_STATS_LEN; @@ -2528,6 +2548,11 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev, data, data_index); data_index += MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN; + /* Extended Counters */ + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_EXT_CNT, 0, + data, data_index); + data_index += MLXSW_SP_PORT_HW_EXT_STATS_LEN; + /* Discard Counters */ __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_DISCARD_CNT, 0, data, data_index); @@ -2773,27 +2798,6 @@ static u32 mlxsw_sp1_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u8 width, return ptys_proto; } -static u32 -mlxsw_sp1_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) { - if (mlxsw_sp1_port_link_mode[i].speed <= upper_speed) - ptys_proto |= mlxsw_sp1_port_link_mode[i].mask; - } - return ptys_proto; -} - -static int -mlxsw_sp1_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u32 *base_speed) -{ - *base_speed = MLXSW_SP_PORT_BASE_SPEED_25G; - return 0; -} - static void mlxsw_sp1_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload, u8 local_port, u32 proto_admin, bool autoneg) @@ -2818,8 +2822,6 @@ mlxsw_sp1_port_type_speed_ops = { .from_ptys_speed_duplex = mlxsw_sp1_from_ptys_speed_duplex, .to_ptys_advert_link = mlxsw_sp1_to_ptys_advert_link, .to_ptys_speed = mlxsw_sp1_to_ptys_speed, - .to_ptys_upper_speed = mlxsw_sp1_to_ptys_upper_speed, - .port_speed_base = mlxsw_sp1_port_speed_base, .reg_ptys_eth_pack = mlxsw_sp1_reg_ptys_eth_pack, .reg_ptys_eth_unpack = mlxsw_sp1_reg_ptys_eth_unpack, }; @@ -3220,51 +3222,6 @@ static u32 mlxsw_sp2_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, return ptys_proto; } -static u32 -mlxsw_sp2_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { - if (mlxsw_sp2_port_link_mode[i].speed <= upper_speed) - ptys_proto |= mlxsw_sp2_port_link_mode[i].mask; - } - return ptys_proto; -} - -static int -mlxsw_sp2_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u32 *base_speed) -{ - char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 eth_proto_cap; - int err; - - /* In Spectrum-2, the speed of 1x can change from port to port, so query - * it from firmware. - */ - mlxsw_reg_ptys_ext_eth_pack(ptys_pl, local_port, 0, false); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); - if (err) - return err; - mlxsw_reg_ptys_ext_eth_unpack(ptys_pl, ð_proto_cap, NULL, NULL); - - if (eth_proto_cap & - MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR) { - *base_speed = MLXSW_SP_PORT_BASE_SPEED_50G; - return 0; - } - - if (eth_proto_cap & - MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR) { - *base_speed = MLXSW_SP_PORT_BASE_SPEED_25G; - return 0; - } - - return -EIO; -} - static void mlxsw_sp2_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload, u8 local_port, u32 proto_admin, @@ -3290,8 +3247,6 @@ mlxsw_sp2_port_type_speed_ops = { .from_ptys_speed_duplex = mlxsw_sp2_from_ptys_speed_duplex, .to_ptys_advert_link = mlxsw_sp2_to_ptys_advert_link, .to_ptys_speed = mlxsw_sp2_to_ptys_speed, - .to_ptys_upper_speed = mlxsw_sp2_to_ptys_upper_speed, - .port_speed_base = mlxsw_sp2_port_speed_base, .reg_ptys_eth_pack = mlxsw_sp2_reg_ptys_eth_pack, .reg_ptys_eth_unpack = mlxsw_sp2_reg_ptys_eth_unpack, }; @@ -3505,24 +3460,24 @@ static int mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u32 eth_proto_cap, eth_proto_admin, eth_proto_oper; const struct mlxsw_sp_port_type_speed_ops *ops; char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 eth_proto_admin; - u32 upper_speed; - u32 base_speed; int err; ops = mlxsw_sp->port_type_speed_ops; - err = ops->port_speed_base(mlxsw_sp, mlxsw_sp_port->local_port, - &base_speed); + /* Set advertised speeds to supported speeds. */ + ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port, + 0, false); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); if (err) return err; - upper_speed = base_speed * mlxsw_sp_port->mapping.width; - eth_proto_admin = ops->to_ptys_upper_speed(mlxsw_sp, upper_speed); + ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, ð_proto_cap, + ð_proto_admin, ð_proto_oper); ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port, - eth_proto_admin, mlxsw_sp_port->link.autoneg); + eth_proto_cap, mlxsw_sp_port->link.autoneg); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); } @@ -4920,16 +4875,35 @@ static const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops = { }; #define MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR 38 +#define MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR 50 + +static u32 __mlxsw_sp_span_buffsize_get(int mtu, u32 speed, u32 buffer_factor) +{ + return 3 * mtu + buffer_factor * speed / 1000; +} static u32 mlxsw_sp2_span_buffsize_get(int mtu, u32 speed) { - return 3 * mtu + MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR * speed / 1000; + int factor = MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR; + + return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); } static const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops = { .buffsize_get = mlxsw_sp2_span_buffsize_get, }; +static u32 mlxsw_sp3_span_buffsize_get(int mtu, u32 speed) +{ + int factor = MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR; + + return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); +} + +static const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops = { + .buffsize_get = mlxsw_sp3_span_buffsize_get, +}; + u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed) { u32 buffsize = mlxsw_sp->span_ops->buffsize_get(speed, mtu); @@ -5208,7 +5182,7 @@ static int mlxsw_sp3_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals; mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops; mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops; - mlxsw_sp->span_ops = &mlxsw_sp2_span_ops; + mlxsw_sp->span_ops = &mlxsw_sp3_span_ops; mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3; return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bed86f4825a8..9708156e7871 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -19,6 +19,7 @@ #include <net/pkt_cls.h> #include <net/red.h> #include <net/vxlan.h> +#include <net/flow_offload.h> #include "port.h" #include "core.h" @@ -32,9 +33,6 @@ #define MLXSW_SP_MID_MAX 7000 -#define MLXSW_SP_PORT_BASE_SPEED_25G 25000 /* Mb/s */ -#define MLXSW_SP_PORT_BASE_SPEED_50G 50000 /* Mb/s */ - #define MLXSW_SP_KVD_LINEAR_SIZE 98304 /* entries */ #define MLXSW_SP_KVD_GRANULARITY 128 @@ -309,9 +307,6 @@ struct mlxsw_sp_port_type_speed_ops { u32 (*to_ptys_advert_link)(struct mlxsw_sp *mlxsw_sp, u8 width, const struct ethtool_link_ksettings *cmd); u32 (*to_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u8 width, u32 speed); - u32 (*to_ptys_upper_speed)(struct mlxsw_sp *mlxsw_sp, u32 upper_speed); - int (*port_speed_base)(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u32 *base_speed); void (*reg_ptys_eth_pack)(struct mlxsw_sp *mlxsw_sp, char *payload, u8 local_port, u32 proto_admin, bool autoneg); void (*reg_ptys_eth_unpack)(struct mlxsw_sp *mlxsw_sp, char *payload, @@ -548,7 +543,7 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, struct netdev_notifier_changeupper_info *info); bool mlxsw_sp_netdev_is_ipip_ol(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev); -bool mlxsw_sp_netdev_is_ipip_ul(const struct mlxsw_sp *mlxsw_sp, +bool mlxsw_sp_netdev_is_ipip_ul(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev); int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp, struct net_device *l3_dev, @@ -645,6 +640,7 @@ struct mlxsw_sp_acl_rule_info { struct mlxsw_afk_element_values values; struct mlxsw_afa_block *act_block; u8 action_created:1, + ingress_bind_blocker:1, egress_bind_blocker:1; unsigned int counter_index; }; @@ -664,16 +660,20 @@ struct mlxsw_sp_acl_block { struct mlxsw_sp *mlxsw_sp; unsigned int rule_count; unsigned int disable_count; + unsigned int ingress_blocker_rule_count; unsigned int egress_blocker_rule_count; + unsigned int ingress_binding_count; + unsigned int egress_binding_count; struct net *net; }; struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl); struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block); -unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block); +unsigned int +mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block); void mlxsw_sp_acl_block_disable_inc(struct mlxsw_sp_acl_block *block); void mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block); -bool mlxsw_sp_acl_block_disabled(struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block); struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net); void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block); @@ -686,7 +686,9 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, bool ingress); -bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block); struct mlxsw_sp_acl_ruleset * mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, u32 chain_index, @@ -718,7 +720,10 @@ int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, u16 group_id); int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei); -int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); +int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei, + bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack); int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, @@ -769,6 +774,12 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp); +static inline const struct flow_action_cookie * +mlxsw_sp_acl_act_cookie_lookup(struct mlxsw_sp *mlxsw_sp, u32 cookie_index) +{ + return mlxsw_afa_cookie_lookup(mlxsw_sp->afa, cookie_index); +} + int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp); @@ -966,9 +977,6 @@ void mlxsw_sp_nve_flood_ip_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, enum mlxsw_sp_l3proto proto, union mlxsw_sp_l3addr *addr); -u32 mlxsw_sp_nve_decap_tunnel_index_get(const struct mlxsw_sp *mlxsw_sp); -bool mlxsw_sp_nve_ipv4_route_is_decap(const struct mlxsw_sp *mlxsw_sp, - u32 tb_id, __be32 addr); int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, struct mlxsw_sp_nve_params *params, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 9368b93dab38..36b264798f04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -99,7 +99,8 @@ struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block) return block->mlxsw_sp; } -unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block) +unsigned int +mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block) { return block ? block->rule_count : 0; } @@ -116,20 +117,24 @@ void mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block) block->disable_count--; } -bool mlxsw_sp_acl_block_disabled(struct mlxsw_sp_acl_block *block) +bool mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block) { return block->disable_count; } -bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block) +bool mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block) { - struct mlxsw_sp_acl_block_binding *binding; + return block->egress_binding_count; +} - list_for_each_entry(binding, &block->binding_list, list) { - if (!binding->ingress) - return true; - } - return false; +bool mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block) +{ + return block->ingress_binding_count; +} + +bool mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block) +{ + return block->ingress_binding_count && block->egress_binding_count; } static bool @@ -163,7 +168,8 @@ mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp, binding->mlxsw_sp_port, binding->ingress); } -static bool mlxsw_sp_acl_ruleset_block_bound(struct mlxsw_sp_acl_block *block) +static bool +mlxsw_sp_acl_ruleset_block_bound(const struct mlxsw_sp_acl_block *block) { return block->ruleset_zero; } @@ -250,6 +256,11 @@ int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(mlxsw_sp_acl_block_lookup(block, mlxsw_sp_port, ingress))) return -EEXIST; + if (ingress && block->ingress_blocker_rule_count) { + NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to ingress because it contains unsupported rules"); + return -EOPNOTSUPP; + } + if (!ingress && block->egress_blocker_rule_count) { NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to egress because it contains unsupported rules"); return -EOPNOTSUPP; @@ -267,6 +278,10 @@ int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, goto err_ruleset_bind; } + if (ingress) + block->ingress_binding_count++; + else + block->egress_binding_count++; list_add(&binding->list, &block->binding_list); return 0; @@ -288,6 +303,11 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp, list_del(&binding->list); + if (ingress) + block->ingress_binding_count--; + else + block->egress_binding_count--; + if (mlxsw_sp_acl_ruleset_block_bound(block)) mlxsw_sp_acl_ruleset_unbind(mlxsw_sp, block, binding); @@ -515,9 +535,13 @@ int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei) return mlxsw_afa_block_terminate(rulei->act_block); } -int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei) +int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei, + bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack) { - return mlxsw_afa_block_append_drop(rulei->act_block); + return mlxsw_afa_block_append_drop(rulei->act_block, ingress, + fa_cookie, extack); } int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei) @@ -707,6 +731,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, list_add_tail(&rule->list, &mlxsw_sp->acl->rules); mutex_unlock(&mlxsw_sp->acl->rules_lock); block->rule_count++; + block->ingress_blocker_rule_count += rule->rulei->ingress_bind_blocker; block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker; return 0; @@ -726,6 +751,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker; + block->ingress_blocker_rule_count -= rule->rulei->ingress_bind_blocker; ruleset->ht_key.block->rule_count--; mutex_lock(&mlxsw_sp->acl->rules_lock); list_del(&rule->list); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 2dc0978428e6..daf029931b5f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */ #include <linux/kernel.h> +#include <linux/mutex.h> #include <net/devlink.h> #include "spectrum.h" @@ -210,7 +211,7 @@ mlxsw_sp_dpipe_table_erif_entries_dump(void *priv, bool counters_enabled, return err; rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); i = 0; start_again: err = devlink_dpipe_entry_ctx_prepare(dump_ctx); @@ -241,14 +242,14 @@ start_again: devlink_dpipe_entry_ctx_close(dump_ctx); if (i != rif_count) goto start_again; - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); devlink_dpipe_entry_clear(&entry); return 0; err_entry_append: err_entry_get: err_ctx_prepare: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); devlink_dpipe_entry_clear(&entry); return err; } @@ -258,7 +259,7 @@ static int mlxsw_sp_dpipe_table_erif_counters_update(void *priv, bool enable) struct mlxsw_sp *mlxsw_sp = priv; int i; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); @@ -271,7 +272,7 @@ static int mlxsw_sp_dpipe_table_erif_counters_update(void *priv, bool enable) mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS); } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return 0; } @@ -546,7 +547,7 @@ mlxsw_sp_dpipe_table_host_entries_get(struct mlxsw_sp *mlxsw_sp, int i, j; int err; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); i = 0; rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); start_again: @@ -602,12 +603,12 @@ out: if (i != rif_count) goto start_again; - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return 0; err_ctx_prepare: err_entry_append: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -662,7 +663,7 @@ mlxsw_sp_dpipe_table_host_counters_update(struct mlxsw_sp *mlxsw_sp, { int i; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); struct mlxsw_sp_neigh_entry *neigh_entry; @@ -684,7 +685,7 @@ mlxsw_sp_dpipe_table_host_counters_update(struct mlxsw_sp *mlxsw_sp, enable); } } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); } static int mlxsw_sp_dpipe_table_host4_counters_update(void *priv, bool enable) @@ -701,7 +702,7 @@ mlxsw_sp_dpipe_table_host_size_get(struct mlxsw_sp *mlxsw_sp, int type) u64 size = 0; int i; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); struct mlxsw_sp_neigh_entry *neigh_entry; @@ -721,7 +722,7 @@ mlxsw_sp_dpipe_table_host_size_get(struct mlxsw_sp *mlxsw_sp, int type) size++; } } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return size; } @@ -1093,7 +1094,7 @@ mlxsw_sp_dpipe_table_adj_entries_get(struct mlxsw_sp *mlxsw_sp, int j; int err; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); nh_count_max = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp); start_again: err = devlink_dpipe_entry_ctx_prepare(dump_ctx); @@ -1130,13 +1131,13 @@ skip: devlink_dpipe_entry_ctx_close(dump_ctx); if (nh_count != nh_count_max) goto start_again; - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return 0; err_ctx_prepare: err_entry_append: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -1206,9 +1207,9 @@ mlxsw_sp_dpipe_table_adj_size_get(void *priv) struct mlxsw_sp *mlxsw_sp = priv; u64 size; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); size = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp); - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return size; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index b607919c8ad0..0011a71114e3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -41,12 +41,30 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return err; } break; - case FLOW_ACTION_DROP: - err = mlxsw_sp_acl_rulei_act_drop(rulei); + case FLOW_ACTION_DROP: { + bool ingress; + + if (mlxsw_sp_acl_block_is_mixed_bound(block)) { + NL_SET_ERR_MSG_MOD(extack, "Drop action is not supported when block is bound to ingress and egress"); + return -EOPNOTSUPP; + } + ingress = mlxsw_sp_acl_block_is_ingress_bound(block); + err = mlxsw_sp_acl_rulei_act_drop(rulei, ingress, + act->cookie, extack); if (err) { NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action"); return err; } + + /* Forbid block with this rulei to be bound + * to ingress/egress in future. Ingress rule is + * a blocker for egress and vice versa. + */ + if (ingress) + rulei->egress_bind_blocker = 1; + else + rulei->ingress_bind_blocker = 1; + } break; case FLOW_ACTION_TRAP: err = mlxsw_sp_acl_rulei_act_trap(rulei); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 423eedebcd22..085d9676e34b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */ +#include <linux/mutex.h> #include <linux/rhashtable.h> #include <net/ipv6.h> @@ -12,6 +13,7 @@ struct mlxsw_sp_mr { void *catchall_route_priv; struct delayed_work stats_update_dw; struct list_head table_list; + struct mutex table_list_lock; /* Protects table_list */ #define MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL 5000 /* ms */ unsigned long priv[0]; /* priv has to be always the last item */ @@ -66,6 +68,7 @@ struct mlxsw_sp_mr_table { u32 vr_id; struct mlxsw_sp_mr_vif vifs[MAXVIFS]; struct list_head route_list; + struct mutex route_list_lock; /* Protects route_list */ struct rhashtable route_ht; const struct mlxsw_sp_mr_table_ops *ops; char catchall_route_priv[]; @@ -370,11 +373,13 @@ static void mlxsw_sp_mr_mfc_offload_update(struct mlxsw_sp_mr_route *mr_route) static void __mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table, struct mlxsw_sp_mr_route *mr_route) { + WARN_ON_ONCE(!mutex_is_locked(&mr_table->route_list_lock)); + mlxsw_sp_mr_mfc_offload_set(mr_route, false); - mlxsw_sp_mr_route_erase(mr_table, mr_route); rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node, mlxsw_sp_mr_route_ht_params); list_del(&mr_route->node); + mlxsw_sp_mr_route_erase(mr_table, mr_route); mlxsw_sp_mr_route_destroy(mr_table, mr_route); } @@ -415,19 +420,21 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, goto err_duplicate_route; } + /* Write the route to the hardware */ + err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace); + if (err) + goto err_mr_route_write; + /* Put it in the table data-structures */ + mutex_lock(&mr_table->route_list_lock); list_add_tail(&mr_route->node, &mr_table->route_list); + mutex_unlock(&mr_table->route_list_lock); err = rhashtable_insert_fast(&mr_table->route_ht, &mr_route->ht_node, mlxsw_sp_mr_route_ht_params); if (err) goto err_rhashtable_insert; - /* Write the route to the hardware */ - err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace); - if (err) - goto err_mr_route_write; - /* Destroy the original route */ if (replace) { rhashtable_remove_fast(&mr_table->route_ht, @@ -440,11 +447,12 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, mlxsw_sp_mr_mfc_offload_update(mr_route); return 0; -err_mr_route_write: - rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node, - mlxsw_sp_mr_route_ht_params); err_rhashtable_insert: + mutex_lock(&mr_table->route_list_lock); list_del(&mr_route->node); + mutex_unlock(&mr_table->route_list_lock); + mlxsw_sp_mr_route_erase(mr_table, mr_route); +err_mr_route_write: err_no_orig_route: err_duplicate_route: mlxsw_sp_mr_route_destroy(mr_table, mr_route); @@ -460,8 +468,11 @@ void mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table, mr_table->ops->key_create(mr_table, &key, mfc); mr_route = rhashtable_lookup_fast(&mr_table->route_ht, &key, mlxsw_sp_mr_route_ht_params); - if (mr_route) + if (mr_route) { + mutex_lock(&mr_table->route_list_lock); __mlxsw_sp_mr_route_del(mr_table, mr_route); + mutex_unlock(&mr_table->route_list_lock); + } } /* Should be called after the VIF struct is updated */ @@ -910,6 +921,7 @@ struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp, mr_table->proto = proto; mr_table->ops = &mlxsw_sp_mr_table_ops_arr[proto]; INIT_LIST_HEAD(&mr_table->route_list); + mutex_init(&mr_table->route_list_lock); err = rhashtable_init(&mr_table->route_ht, &mlxsw_sp_mr_route_ht_params); @@ -927,12 +939,15 @@ struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp, &catchall_route_params); if (err) goto err_ops_route_create; + mutex_lock(&mr->table_list_lock); list_add_tail(&mr_table->node, &mr->table_list); + mutex_unlock(&mr->table_list_lock); return mr_table; err_ops_route_create: rhashtable_destroy(&mr_table->route_ht); err_route_rhashtable_init: + mutex_destroy(&mr_table->route_list_lock); kfree(mr_table); return ERR_PTR(err); } @@ -943,10 +958,13 @@ void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table) struct mlxsw_sp_mr *mr = mlxsw_sp->mr; WARN_ON(!mlxsw_sp_mr_table_empty(mr_table)); + mutex_lock(&mr->table_list_lock); list_del(&mr_table->node); + mutex_unlock(&mr->table_list_lock); mr->mr_ops->route_destroy(mlxsw_sp, mr->priv, &mr_table->catchall_route_priv); rhashtable_destroy(&mr_table->route_ht); + mutex_destroy(&mr_table->route_list_lock); kfree(mr_table); } @@ -955,8 +973,10 @@ void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table) struct mlxsw_sp_mr_route *mr_route, *tmp; int i; + mutex_lock(&mr_table->route_list_lock); list_for_each_entry_safe(mr_route, tmp, &mr_table->route_list, node) __mlxsw_sp_mr_route_del(mr_table, mr_route); + mutex_unlock(&mr_table->route_list_lock); for (i = 0; i < MAXVIFS; i++) { mr_table->vifs[i].dev = NULL; @@ -1000,12 +1020,15 @@ static void mlxsw_sp_mr_stats_update(struct work_struct *work) struct mlxsw_sp_mr_route *mr_route; unsigned long interval; - rtnl_lock(); - list_for_each_entry(mr_table, &mr->table_list, node) + mutex_lock(&mr->table_list_lock); + list_for_each_entry(mr_table, &mr->table_list, node) { + mutex_lock(&mr_table->route_list_lock); list_for_each_entry(mr_route, &mr_table->route_list, node) mlxsw_sp_mr_route_stats_update(mr_table->mlxsw_sp, mr_route); - rtnl_unlock(); + mutex_unlock(&mr_table->route_list_lock); + } + mutex_unlock(&mr->table_list_lock); interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL); mlxsw_core_schedule_dw(&mr->stats_update_dw, interval); @@ -1024,6 +1047,7 @@ int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp, mr->mr_ops = mr_ops; mlxsw_sp->mr = mr; INIT_LIST_HEAD(&mr->table_list); + mutex_init(&mr->table_list_lock); err = mr_ops->init(mlxsw_sp, mr->priv); if (err) @@ -1035,6 +1059,7 @@ int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp, mlxsw_core_schedule_dw(&mr->stats_update_dw, interval); return 0; err: + mutex_destroy(&mr->table_list_lock); kfree(mr); return err; } @@ -1045,5 +1070,6 @@ void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp) cancel_delayed_work_sync(&mr->stats_update_dw); mr->mr_ops->fini(mlxsw_sp, mr->priv); + mutex_destroy(&mr->table_list_lock); kfree(mr); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index eced553fd4ef..54d3e7dcd303 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -713,27 +713,6 @@ static void mlxsw_sp_nve_flood_ip_flush(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nve_mc_list_put(mlxsw_sp, mc_list); } -u32 mlxsw_sp_nve_decap_tunnel_index_get(const struct mlxsw_sp *mlxsw_sp) -{ - WARN_ON(mlxsw_sp->nve->num_nve_tunnels == 0); - - return mlxsw_sp->nve->tunnel_index; -} - -bool mlxsw_sp_nve_ipv4_route_is_decap(const struct mlxsw_sp *mlxsw_sp, - u32 tb_id, __be32 addr) -{ - struct mlxsw_sp_nve *nve = mlxsw_sp->nve; - struct mlxsw_sp_nve_config *config = &nve->config; - - if (nve->num_nve_tunnels && - config->ul_proto == MLXSW_SP_L3_PROTO_IPV4 && - config->ul_sip.addr4 == addr && config->ul_tb_id == tb_id) - return true; - - return false; -} - static int mlxsw_sp_nve_tunnel_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nve_config *config) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 02526c53d4f5..13a054c0ce0f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -347,7 +347,6 @@ mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->prio_bitmap, &stats_base->tx_packets, &stats_base->tx_bytes); - red_base->prob_mark = xstats->ecn; red_base->prob_drop = xstats->wred_drop[tclass_num]; red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num); @@ -453,22 +452,19 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port, u8 tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; struct red_stats *res = xstats_ptr; - int early_drops, marks, pdrops; + int early_drops, pdrops; xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop; - marks = xstats->ecn - xstats_base->prob_mark; pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) - xstats_base->pdrop; res->pdrop += pdrops; res->prob_drop += early_drops; - res->prob_mark += marks; xstats_base->pdrop += pdrops; xstats_base->prob_drop += early_drops; - xstats_base->prob_mark += marks; return 0; } @@ -486,8 +482,7 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port, stats_base = &mlxsw_sp_qdisc->stats_base; mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc, stats_ptr); - overlimits = xstats->wred_drop[tclass_num] + xstats->ecn - - stats_base->overlimits; + overlimits = xstats->wred_drop[tclass_num] - stats_base->overlimits; stats_ptr->qstats->overlimits += overlimits; stats_base->overlimits += overlimits; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 634a9a949777..b527387ccf80 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -17,6 +17,7 @@ #include <linux/refcount.h> #include <linux/jhash.h> #include <linux/net_namespace.h> +#include <linux/mutex.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> @@ -48,39 +49,6 @@ struct mlxsw_sp_vr; struct mlxsw_sp_lpm_tree; struct mlxsw_sp_rif_ops; -struct mlxsw_sp_router { - struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif **rifs; - struct mlxsw_sp_vr *vrs; - struct rhashtable neigh_ht; - struct rhashtable nexthop_group_ht; - struct rhashtable nexthop_ht; - struct list_head nexthop_list; - struct { - /* One tree for each protocol: IPv4 and IPv6 */ - struct mlxsw_sp_lpm_tree *proto_trees[2]; - struct mlxsw_sp_lpm_tree *trees; - unsigned int tree_count; - } lpm; - struct { - struct delayed_work dw; - unsigned long interval; /* ms */ - } neighs_update; - struct delayed_work nexthop_probe_dw; -#define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ - struct list_head nexthop_neighs_list; - struct list_head ipip_list; - bool aborted; - struct notifier_block fib_nb; - struct notifier_block netevent_nb; - struct notifier_block inetaddr_nb; - struct notifier_block inet6addr_nb; - const struct mlxsw_sp_rif_ops **rif_ops_arr; - const struct mlxsw_sp_ipip_ops **ipip_ops_arr; - u32 adj_discard_index; - bool adj_discard_index_valid; -}; - struct mlxsw_sp_rif { struct list_head nexthop_list; struct list_head neigh_list; @@ -763,13 +731,18 @@ int mlxsw_sp_router_tb_id_vr_id(struct mlxsw_sp *mlxsw_sp, u32 tb_id, u16 *vr_id) { struct mlxsw_sp_vr *vr; + int err = 0; + mutex_lock(&mlxsw_sp->router->lock); vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id); - if (!vr) - return -ESRCH; + if (!vr) { + err = -ESRCH; + goto out; + } *vr_id = vr->id; - - return 0; +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; } static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, @@ -1378,10 +1351,16 @@ mlxsw_sp_ipip_entry_find_by_ul_dev(const struct mlxsw_sp *mlxsw_sp, return NULL; } -bool mlxsw_sp_netdev_is_ipip_ul(const struct mlxsw_sp *mlxsw_sp, +bool mlxsw_sp_netdev_is_ipip_ul(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { - return mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, dev, NULL); + bool is_ipip_ul; + + mutex_lock(&mlxsw_sp->router->lock); + is_ipip_ul = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, dev, NULL); + mutex_unlock(&mlxsw_sp->router->lock); + + return is_ipip_ul; } static bool mlxsw_sp_netdevice_ipip_can_offload(struct mlxsw_sp *mlxsw_sp, @@ -1753,35 +1732,41 @@ int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp, { struct netdev_notifier_changeupper_info *chup; struct netlink_ext_ack *extack; + int err = 0; + mutex_lock(&mlxsw_sp->router->lock); switch (event) { case NETDEV_REGISTER: - return mlxsw_sp_netdevice_ipip_ol_reg_event(mlxsw_sp, ol_dev); + err = mlxsw_sp_netdevice_ipip_ol_reg_event(mlxsw_sp, ol_dev); + break; case NETDEV_UNREGISTER: mlxsw_sp_netdevice_ipip_ol_unreg_event(mlxsw_sp, ol_dev); - return 0; + break; case NETDEV_UP: mlxsw_sp_netdevice_ipip_ol_up_event(mlxsw_sp, ol_dev); - return 0; + break; case NETDEV_DOWN: mlxsw_sp_netdevice_ipip_ol_down_event(mlxsw_sp, ol_dev); - return 0; + break; case NETDEV_CHANGEUPPER: chup = container_of(info, typeof(*chup), info); extack = info->extack; if (netif_is_l3_master(chup->upper_dev)) - return mlxsw_sp_netdevice_ipip_ol_vrf_event(mlxsw_sp, - ol_dev, - extack); - return 0; + err = mlxsw_sp_netdevice_ipip_ol_vrf_event(mlxsw_sp, + ol_dev, + extack); + break; case NETDEV_CHANGE: extack = info->extack; - return mlxsw_sp_netdevice_ipip_ol_change_event(mlxsw_sp, - ol_dev, extack); + err = mlxsw_sp_netdevice_ipip_ol_change_event(mlxsw_sp, + ol_dev, extack); + break; case NETDEV_CHANGEMTU: - return mlxsw_sp_netdevice_ipip_ol_update_mtu(mlxsw_sp, ol_dev); + err = mlxsw_sp_netdevice_ipip_ol_update_mtu(mlxsw_sp, ol_dev); + break; } - return 0; + mutex_unlock(&mlxsw_sp->router->lock); + return err; } static int @@ -1825,8 +1810,9 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, struct netdev_notifier_info *info) { struct mlxsw_sp_ipip_entry *ipip_entry = NULL; - int err; + int err = 0; + mutex_lock(&mlxsw_sp->router->lock); while ((ipip_entry = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, ul_dev, ipip_entry))) { @@ -1839,7 +1825,7 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, if (err) { mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(mlxsw_sp, ul_dev); - return err; + break; } if (demote_this) { @@ -1856,8 +1842,9 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, ipip_entry = prev; } } + mutex_unlock(&mlxsw_sp->router->lock); - return 0; + return err; } int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, @@ -1866,8 +1853,22 @@ int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, u32 tunnel_index) { enum mlxsw_sp_fib_entry_type type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + struct mlxsw_sp_router *router = mlxsw_sp->router; struct mlxsw_sp_fib_entry *fib_entry; - int err; + int err = 0; + + mutex_lock(&mlxsw_sp->router->lock); + + if (WARN_ON_ONCE(router->nve_decap_config.valid)) { + err = -EINVAL; + goto out; + } + + router->nve_decap_config.ul_tb_id = ul_tb_id; + router->nve_decap_config.tunnel_index = tunnel_index; + router->nve_decap_config.ul_proto = ul_proto; + router->nve_decap_config.ul_sip = *ul_sip; + router->nve_decap_config.valid = true; /* It is valid to create a tunnel with a local IP and only later * assign this IP address to a local interface @@ -1876,7 +1877,7 @@ int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, ul_proto, ul_sip, type); if (!fib_entry) - return 0; + goto out; fib_entry->decap.tunnel_index = tunnel_index; fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; @@ -1885,11 +1886,13 @@ int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, if (err) goto err_fib_entry_update; - return 0; + goto out; err_fib_entry_update: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); +out: + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -1898,16 +1901,40 @@ void mlxsw_sp_router_nve_demote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, const union mlxsw_sp_l3addr *ul_sip) { enum mlxsw_sp_fib_entry_type type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; + struct mlxsw_sp_router *router = mlxsw_sp->router; struct mlxsw_sp_fib_entry *fib_entry; + mutex_lock(&mlxsw_sp->router->lock); + + if (WARN_ON_ONCE(!router->nve_decap_config.valid)) + goto out; + + router->nve_decap_config.valid = false; + fib_entry = mlxsw_sp_router_ip2me_fib_entry_find(mlxsw_sp, ul_tb_id, ul_proto, ul_sip, type); if (!fib_entry) - return; + goto out; fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); +out: + mutex_unlock(&mlxsw_sp->router->lock); +} + +static bool mlxsw_sp_router_nve_is_decap(struct mlxsw_sp *mlxsw_sp, + u32 ul_tb_id, + enum mlxsw_sp_l3proto ul_proto, + const union mlxsw_sp_l3addr *ul_sip) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + + return router->nve_decap_config.valid && + router->nve_decap_config.ul_tb_id == ul_tb_id && + router->nve_decap_config.ul_proto == ul_proto && + !memcmp(&router->nve_decap_config.ul_sip, ul_sip, + sizeof(*ul_sip)); } struct mlxsw_sp_neigh_key { @@ -2280,10 +2307,8 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp, int i, num_rec; int err; - /* Make sure the neighbour's netdev isn't removed in the - * process. - */ - rtnl_lock(); + /* Ensure the RIF we read from the device does not change mid-dump. */ + mutex_lock(&mlxsw_sp->router->lock); do { mlxsw_reg_rauhtd_pack(rauhtd_pl, type); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd), @@ -2297,7 +2322,7 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl, i); } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl)); - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -2328,15 +2353,14 @@ static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_neigh_entry *neigh_entry; - /* Take RTNL mutex here to prevent lists from changes */ - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); list_for_each_entry(neigh_entry, &mlxsw_sp->router->nexthop_neighs_list, nexthop_neighs_list_node) /* If this neigh have nexthops, make the kernel think this neigh * is active regardless of the traffic. */ neigh_event_send(neigh_entry->key.n, NULL); - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); } static void @@ -2376,15 +2400,13 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work) * the nexthop wouldn't get offloaded until the neighbor is resolved * but it wouldn't get resolved ever in case traffic is flowing in HW * using different nexthop. - * - * Take RTNL mutex here to prevent lists from changes. */ - rtnl_lock(); + mutex_lock(&router->lock); list_for_each_entry(neigh_entry, &router->nexthop_neighs_list, nexthop_neighs_list_node) if (!neigh_entry->connected) neigh_event_send(neigh_entry->key.n, NULL); - rtnl_unlock(); + mutex_unlock(&router->lock); mlxsw_core_schedule_dw(&router->nexthop_probe_dw, MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL); @@ -2522,7 +2544,7 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) dead = n->dead; read_unlock_bh(&n->lock); - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); entry_connected = nud_state & NUD_VALID && !dead; @@ -2544,7 +2566,7 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); out: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); neigh_release(n); kfree(net_work); } @@ -4499,6 +4521,7 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, { struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) }; + struct mlxsw_sp_router *router = mlxsw_sp->router; u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id); struct mlxsw_sp_ipip_entry *ipip_entry; struct fib_info *fi = fen_info->fi; @@ -4513,12 +4536,13 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry, ipip_entry); } - if (mlxsw_sp_nve_ipv4_route_is_decap(mlxsw_sp, tb_id, - dip.addr4)) { - u32 t_index; + if (mlxsw_sp_router_nve_is_decap(mlxsw_sp, tb_id, + MLXSW_SP_L3_PROTO_IPV4, + &dip)) { + u32 tunnel_index; - t_index = mlxsw_sp_nve_decap_tunnel_index_get(mlxsw_sp); - fib_entry->decap.tunnel_index = t_index; + tunnel_index = router->nve_decap_config.tunnel_index; + fib_entry->decap.tunnel_index = tunnel_index; fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; return 0; } @@ -5949,8 +5973,7 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; - /* Protect internal structures from changes */ - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); switch (fib_work->event) { @@ -5972,7 +5995,7 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) fib_info_put(fib_work->fnh_info.fib_nh->nh_parent); break; } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); kfree(fib_work); } @@ -5983,7 +6006,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); switch (fib_work->event) { @@ -6010,7 +6033,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); break; } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); kfree(fib_work); } @@ -6023,6 +6046,7 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) int err; rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_ADD: @@ -6051,6 +6075,7 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) dev_put(fib_work->ven_info.dev); break; } + mutex_unlock(&mlxsw_sp->router->lock); rtnl_unlock(); kfree(fib_work); } @@ -6276,7 +6301,13 @@ mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { - return !!mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + struct mlxsw_sp_rif *rif; + + mutex_lock(&mlxsw_sp->router->lock); + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + mutex_unlock(&mlxsw_sp->router->lock); + + return rif; } u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) @@ -6284,6 +6315,7 @@ u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) struct mlxsw_sp_rif *rif; u16 vid = 0; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!rif) goto out; @@ -6297,6 +6329,7 @@ u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) vid = mlxsw_sp_fid_8021q_vid(rif->fid); out: + mutex_unlock(&mlxsw_sp->router->lock); return vid; } @@ -6578,10 +6611,13 @@ void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_rif *rif; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!rif) - return; + goto out; mlxsw_sp_rif_destroy(rif); +out: + mutex_unlock(&mlxsw_sp->router->lock); } static void @@ -6703,7 +6739,11 @@ __mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) { + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port_vlan->mlxsw_sp_port->mlxsw_sp; + + mutex_lock(&mlxsw_sp->router->lock); __mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan); + mutex_unlock(&mlxsw_sp->router->lock); } static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, @@ -6925,7 +6965,9 @@ static void __mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, const struct net_device *macvlan_dev) { + mutex_lock(&mlxsw_sp->router->lock); __mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev); + mutex_unlock(&mlxsw_sp->router->lock); } static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp, @@ -7007,15 +7049,17 @@ static int mlxsw_sp_inetaddr_event(struct notifier_block *nb, /* NETDEV_UP event is handled by mlxsw_sp_inetaddr_valid_event */ if (event == NETDEV_UP) - goto out; + return NOTIFY_DONE; router = container_of(nb, struct mlxsw_sp_router, inetaddr_nb); + mutex_lock(&router->lock); rif = mlxsw_sp_rif_find_by_dev(router->mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, NULL); out: + mutex_unlock(&router->lock); return notifier_from_errno(err); } @@ -7030,8 +7074,9 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) - goto out; + return NOTIFY_DONE; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; @@ -7043,6 +7088,7 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack); out: + mutex_unlock(&mlxsw_sp->router->lock); return notifier_from_errno(err); } @@ -7063,6 +7109,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work) struct mlxsw_sp_rif *rif; rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) @@ -7070,6 +7117,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work) __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL); out: + mutex_unlock(&mlxsw_sp->router->lock); rtnl_unlock(); dev_put(dev); kfree(inet6addr_work); @@ -7114,8 +7162,9 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) - goto out; + return NOTIFY_DONE; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; @@ -7127,6 +7176,7 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack); out: + mutex_unlock(&mlxsw_sp->router->lock); return notifier_from_errno(err); } @@ -7213,24 +7263,30 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev, { struct mlxsw_sp *mlxsw_sp; struct mlxsw_sp_rif *rif; + int err = 0; mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) return 0; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!rif) - return 0; + goto out; switch (event) { case NETDEV_CHANGEMTU: /* fall through */ case NETDEV_CHANGEADDR: - return mlxsw_sp_router_port_change_event(mlxsw_sp, rif); + err = mlxsw_sp_router_port_change_event(mlxsw_sp, rif); + break; case NETDEV_PRE_CHANGEADDR: - return mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr); + err = mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr); + break; } - return 0; +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; } static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp, @@ -7273,9 +7329,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, if (!mlxsw_sp || netif_is_macvlan(l3_dev)) return 0; + mutex_lock(&mlxsw_sp->router->lock); switch (event) { case NETDEV_PRECHANGEUPPER: - return 0; + break; case NETDEV_CHANGEUPPER: if (info->linking) { struct netlink_ext_ack *extack; @@ -7287,6 +7344,7 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, } break; } + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -7795,28 +7853,32 @@ int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, u16 *ul_rif_index) { struct mlxsw_sp_rif *ul_rif; + int err = 0; - ASSERT_RTNL(); - + mutex_lock(&mlxsw_sp->router->lock); ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL); - if (IS_ERR(ul_rif)) - return PTR_ERR(ul_rif); + if (IS_ERR(ul_rif)) { + err = PTR_ERR(ul_rif); + goto out; + } *ul_rif_index = ul_rif->rif_index; - - return 0; +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; } void mlxsw_sp_router_ul_rif_put(struct mlxsw_sp *mlxsw_sp, u16 ul_rif_index) { struct mlxsw_sp_rif *ul_rif; - ASSERT_RTNL(); - + mutex_lock(&mlxsw_sp->router->lock); ul_rif = mlxsw_sp->router->rifs[ul_rif_index]; if (WARN_ON(!ul_rif)) - return; + goto out; mlxsw_sp_ul_rif_put(ul_rif); +out: + mutex_unlock(&mlxsw_sp->router->lock); } static int @@ -8066,6 +8128,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, router = kzalloc(sizeof(*mlxsw_sp->router), GFP_KERNEL); if (!router) return -ENOMEM; + mutex_init(&router->lock); mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; @@ -8169,6 +8232,7 @@ err_router_init: err_register_inet6addr_notifier: unregister_inetaddr_notifier(&router->inetaddr_nb); err_register_inetaddr_notifier: + mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); return err; } @@ -8189,5 +8253,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) __mlxsw_sp_router_fini(mlxsw_sp); unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); + mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index c9b94f435cdd..8418dc3ae967 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -7,6 +7,49 @@ #include "spectrum.h" #include "reg.h" +struct mlxsw_sp_router_nve_decap { + u32 ul_tb_id; + u32 tunnel_index; + enum mlxsw_sp_l3proto ul_proto; + union mlxsw_sp_l3addr ul_sip; + u8 valid:1; +}; + +struct mlxsw_sp_router { + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif **rifs; + struct mlxsw_sp_vr *vrs; + struct rhashtable neigh_ht; + struct rhashtable nexthop_group_ht; + struct rhashtable nexthop_ht; + struct list_head nexthop_list; + struct { + /* One tree for each protocol: IPv4 and IPv6 */ + struct mlxsw_sp_lpm_tree *proto_trees[2]; + struct mlxsw_sp_lpm_tree *trees; + unsigned int tree_count; + } lpm; + struct { + struct delayed_work dw; + unsigned long interval; /* ms */ + } neighs_update; + struct delayed_work nexthop_probe_dw; +#define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ + struct list_head nexthop_neighs_list; + struct list_head ipip_list; + bool aborted; + struct notifier_block fib_nb; + struct notifier_block netevent_nb; + struct notifier_block inetaddr_nb; + struct notifier_block inet6addr_nb; + const struct mlxsw_sp_rif_ops **rif_ops_arr; + const struct mlxsw_sp_ipip_ops **ipip_ops_arr; + u32 adj_discard_index; + bool adj_discard_index_valid; + struct mlxsw_sp_router_nve_decap nve_decap_config; + struct mutex lock; /* Protects shared router resources */ +}; + struct mlxsw_sp_rif_ipip_lb; struct mlxsw_sp_rif_ipip_lb_config { enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 339c69da83b2..a26162b08b7d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2674,19 +2674,24 @@ static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp, } } -static void mlxsw_sp_fdb_notify_work_schedule(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_fdb_notify_work_schedule(struct mlxsw_sp *mlxsw_sp, + bool no_delay) { struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge; + unsigned int interval = no_delay ? 0 : bridge->fdb_notify.interval; mlxsw_core_schedule_dw(&bridge->fdb_notify.dw, - msecs_to_jiffies(bridge->fdb_notify.interval)); + msecs_to_jiffies(interval)); } +#define MLXSW_SP_FDB_SFN_QUERIES_PER_SESSION 10 + static void mlxsw_sp_fdb_notify_work(struct work_struct *work) { struct mlxsw_sp_bridge *bridge; struct mlxsw_sp *mlxsw_sp; char *sfn_pl; + int queries; u8 num_rec; int i; int err; @@ -2699,20 +2704,26 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp = bridge->mlxsw_sp; rtnl_lock(); - mlxsw_reg_sfn_pack(sfn_pl); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); - if (err) { - dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get FDB notifications\n"); - goto out; + queries = MLXSW_SP_FDB_SFN_QUERIES_PER_SESSION; + while (queries > 0) { + mlxsw_reg_sfn_pack(sfn_pl); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); + if (err) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get FDB notifications\n"); + goto out; + } + num_rec = mlxsw_reg_sfn_num_rec_get(sfn_pl); + for (i = 0; i < num_rec; i++) + mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); + if (num_rec != MLXSW_REG_SFN_REC_MAX_COUNT) + goto out; + queries--; } - num_rec = mlxsw_reg_sfn_num_rec_get(sfn_pl); - for (i = 0; i < num_rec; i++) - mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); out: rtnl_unlock(); kfree(sfn_pl); - mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); + mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp, !queries); } struct mlxsw_sp_switchdev_event_work { @@ -3458,7 +3469,7 @@ static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) INIT_DELAYED_WORK(&bridge->fdb_notify.dw, mlxsw_sp_fdb_notify_work); bridge->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL; - mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); + mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp, false); return 0; err_register_switchdev_blocking_notifier: diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 60205aa3f6a5..9c300d625e04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -25,16 +25,121 @@ enum { #define MLXSW_SP_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT +static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, + u8 local_port, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + + if (unlikely(!mlxsw_sp_port)) { + dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n", + local_port); + kfree_skb(skb); + return -EINVAL; + } + + skb->dev = mlxsw_sp_port->dev; + + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += skb->len; + u64_stats_update_end(&pcpu_stats->syncp); + + skb->protocol = eth_type_trans(skb, skb->dev); + + return 0; +} + static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, - void *priv); + void *trap_ctx) +{ + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + int err; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port); + if (err) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, NULL); + consume_skb(skb); +} + +static void mlxsw_sp_rx_acl_drop_listener(struct sk_buff *skb, u8 local_port, + void *trap_ctx) +{ + u32 cookie_index = mlxsw_skb_cb(skb)->cookie_index; + const struct flow_action_cookie *fa_cookie; + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + int err; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port); + if (err) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + rcu_read_lock(); + fa_cookie = mlxsw_sp_acl_act_cookie_lookup(mlxsw_sp, cookie_index); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, fa_cookie); + rcu_read_unlock(); + consume_skb(skb); +} + static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, - void *trap_ctx); + void *trap_ctx) +{ + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + int err; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port); + if (err) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, NULL); + skb_pull(skb, ETH_HLEN); + skb->offload_fwd_mark = 1; + netif_receive_skb(skb); +} #define MLXSW_SP_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ MLXSW_SP_TRAP_METADATA) +#define MLXSW_SP_TRAP_DROP_EXT(_id, _group_id, _metadata) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + MLXSW_SP_TRAP_METADATA | (_metadata)) + #define MLXSW_SP_TRAP_DRIVER_DROP(_id, _group_id) \ DEVLINK_TRAP_DRIVER(DROP, DROP, DEVLINK_MLXSW_TRAP_ID_##_id, \ DEVLINK_MLXSW_TRAP_NAME_##_id, \ @@ -47,14 +152,20 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, MLXSW_SP_TRAP_METADATA) #define MLXSW_SP_RXL_DISCARD(_id, _group_id) \ - MLXSW_RXL(mlxsw_sp_rx_drop_listener, DISCARD_##_id, SET_FW_DEFAULT, \ - false, SP_##_group_id, DISCARD) + MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, DISCARD_##_id, \ + TRAP_EXCEPTION_TO_CPU, false, SP_##_group_id, \ + SET_FW_DEFAULT, SP_##_group_id) + +#define MLXSW_SP_RXL_ACL_DISCARD(_id, _en_group_id, _dis_group_id) \ + MLXSW_RXL_DIS(mlxsw_sp_rx_acl_drop_listener, DISCARD_##_id, \ + TRAP_EXCEPTION_TO_CPU, false, SP_##_en_group_id, \ + SET_FW_DEFAULT, SP_##_dis_group_id) #define MLXSW_SP_RXL_EXCEPTION(_id, _group_id, _action) \ MLXSW_RXL(mlxsw_sp_rx_exception_listener, _id, \ - _action, false, SP_##_group_id, DISCARD) + _action, false, SP_##_group_id, SET_FW_DEFAULT) -static struct devlink_trap mlxsw_sp_traps_arr[] = { +static const struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS), MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), MLXSW_SP_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS), @@ -83,9 +194,13 @@ static struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(NON_ROUTABLE, L3_DROPS), MLXSW_SP_TRAP_EXCEPTION(DECAP_ERROR, TUNNEL_DROPS), MLXSW_SP_TRAP_DROP(OVERLAY_SMAC_MC, TUNNEL_DROPS), + MLXSW_SP_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), + MLXSW_SP_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), }; -static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { +static const struct mlxsw_listener mlxsw_sp_listeners_arr[] = { MLXSW_SP_RXL_DISCARD(ING_PACKET_SMAC_MC, L2_DISCARDS), MLXSW_SP_RXL_DISCARD(ING_SWITCH_VTAG_ALLOW, L2_DISCARDS), MLXSW_SP_RXL_DISCARD(ING_SWITCH_VLAN, L2_DISCARDS), @@ -124,13 +239,15 @@ static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { MLXSW_SP_RXL_EXCEPTION(DISCARD_DEC_PKT, TUNNEL_DISCARDS, TRAP_EXCEPTION_TO_CPU), MLXSW_SP_RXL_DISCARD(OVERLAY_SMAC_MC, TUNNEL_DISCARDS), + MLXSW_SP_RXL_ACL_DISCARD(INGRESS_ACL, ACL_DISCARDS, DUMMY), + MLXSW_SP_RXL_ACL_DISCARD(EGRESS_ACL, ACL_DISCARDS, DUMMY), }; /* Mapping between hardware trap and devlink trap. Multiple hardware traps can * be mapped to the same devlink trap. Order is according to * 'mlxsw_sp_listeners_arr'. */ -static u16 mlxsw_sp_listener_devlink_map[] = { +static const u16 mlxsw_sp_listener_devlink_map[] = { DEVLINK_TRAP_GENERIC_ID_SMAC_MC, DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH, DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER, @@ -164,83 +281,53 @@ static u16 mlxsw_sp_listener_devlink_map[] = { DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR, DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR, DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP, + DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP, }; -static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, - u8 local_port, - struct mlxsw_sp_port *mlxsw_sp_port) -{ - struct mlxsw_sp_port_pcpu_stats *pcpu_stats; - - if (unlikely(!mlxsw_sp_port)) { - dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n", - local_port); - kfree_skb(skb); - return -EINVAL; - } - - skb->dev = mlxsw_sp_port->dev; - - pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); - u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += skb->len; - u64_stats_update_end(&pcpu_stats->syncp); - - skb->protocol = eth_type_trans(skb, skb->dev); - - return 0; -} +#define MLXSW_SP_DISCARD_POLICER_ID (MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1) +#define MLXSW_SP_THIN_POLICER_ID (MLXSW_SP_DISCARD_POLICER_ID + 1) -static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, - void *trap_ctx) +static int mlxsw_sp_trap_cpu_policers_set(struct mlxsw_sp *mlxsw_sp) { - struct devlink_port *in_devlink_port; - struct mlxsw_sp_port *mlxsw_sp_port; - struct mlxsw_sp *mlxsw_sp; - struct devlink *devlink; - - mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); - mlxsw_sp_port = mlxsw_sp->ports[local_port]; + char qpcr_pl[MLXSW_REG_QPCR_LEN]; + int err; - if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port)) - return; + mlxsw_reg_qpcr_pack(qpcr_pl, MLXSW_SP_DISCARD_POLICER_ID, + MLXSW_REG_QPCR_IR_UNITS_M, false, 10 * 1024, 7); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); + if (err) + return err; - devlink = priv_to_devlink(mlxsw_sp->core); - in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - local_port); - skb_push(skb, ETH_HLEN); - devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); - consume_skb(skb); + /* The purpose of "thin" policer is to drop as many packets + * as possible. The dummy group is using it. + */ + mlxsw_reg_qpcr_pack(qpcr_pl, MLXSW_SP_THIN_POLICER_ID, + MLXSW_REG_QPCR_IR_UNITS_M, false, 1, 4); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); } -static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, - void *trap_ctx) +static int mlxsw_sp_trap_dummy_group_init(struct mlxsw_sp *mlxsw_sp) { - struct devlink_port *in_devlink_port; - struct mlxsw_sp_port *mlxsw_sp_port; - struct mlxsw_sp *mlxsw_sp; - struct devlink *devlink; - - mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); - mlxsw_sp_port = mlxsw_sp->ports[local_port]; - - if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port)) - return; + char htgt_pl[MLXSW_REG_HTGT_LEN]; - devlink = priv_to_devlink(mlxsw_sp->core); - in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - local_port); - skb_push(skb, ETH_HLEN); - devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); - skb_pull(skb, ETH_HLEN); - skb->offload_fwd_mark = 1; - netif_receive_skb(skb); + mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY, + MLXSW_SP_THIN_POLICER_ID, 0, 1); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); } int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + int err; + + err = mlxsw_sp_trap_cpu_policers_set(mlxsw_sp); + if (err) + return err; + + err = mlxsw_sp_trap_dummy_group_init(mlxsw_sp); + if (err) + return err; if (WARN_ON(ARRAY_SIZE(mlxsw_sp_listener_devlink_map) != ARRAY_SIZE(mlxsw_sp_listeners_arr))) @@ -265,7 +352,7 @@ int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core, int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { - struct mlxsw_listener *listener; + const struct mlxsw_listener *listener; int err; if (mlxsw_sp_listener_devlink_map[i] != trap->id) @@ -286,7 +373,7 @@ void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core, int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { - struct mlxsw_listener *listener; + const struct mlxsw_listener *listener; if (mlxsw_sp_listener_devlink_map[i] != trap->id) continue; @@ -303,27 +390,24 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { - enum mlxsw_reg_hpkt_action hw_action; - struct mlxsw_listener *listener; + const struct mlxsw_listener *listener; + bool enabled; int err; if (mlxsw_sp_listener_devlink_map[i] != trap->id) continue; listener = &mlxsw_sp_listeners_arr[i]; - switch (action) { case DEVLINK_TRAP_ACTION_DROP: - hw_action = MLXSW_REG_HPKT_ACTION_SET_FW_DEFAULT; + enabled = false; break; case DEVLINK_TRAP_ACTION_TRAP: - hw_action = MLXSW_REG_HPKT_ACTION_TRAP_EXCEPTION_TO_CPU; + enabled = true; break; default: return -EINVAL; } - - err = mlxsw_core_trap_action_set(mlxsw_core, listener, - hw_action); + err = mlxsw_core_trap_state_set(mlxsw_core, listener, enabled); if (err) return err; } @@ -331,41 +415,8 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, return 0; } -#define MLXSW_SP_DISCARD_POLICER_ID (MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1) - -static int -mlxsw_sp_trap_group_policer_init(struct mlxsw_sp *mlxsw_sp, - const struct devlink_trap_group *group) -{ - enum mlxsw_reg_qpcr_ir_units ir_units; - char qpcr_pl[MLXSW_REG_QPCR_LEN]; - u16 policer_id; - u8 burst_size; - bool is_bytes; - u32 rate; - - switch (group->id) { - case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS: /* fall through */ - case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS: /* fall through */ - case DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS: - policer_id = MLXSW_SP_DISCARD_POLICER_ID; - ir_units = MLXSW_REG_QPCR_IR_UNITS_M; - is_bytes = false; - rate = 10 * 1024; /* 10Kpps */ - burst_size = 7; - break; - default: - return -EINVAL; - } - - mlxsw_reg_qpcr_pack(qpcr_pl, policer_id, ir_units, is_bytes, rate, - burst_size); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); -} - -static int -__mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp, - const struct devlink_trap_group *group) +int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, + const struct devlink_trap_group *group) { char htgt_pl[MLXSW_REG_HTGT_LEN]; u8 priority, tc, group_id; @@ -390,27 +441,16 @@ __mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp, priority = 0; tc = 1; break; + case DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS: + group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS; + policer_id = MLXSW_SP_DISCARD_POLICER_ID; + priority = 0; + tc = 1; + break; default: return -EINVAL; } mlxsw_reg_htgt_pack(htgt_pl, group_id, policer_id, priority, tc); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); -} - -int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, - const struct devlink_trap_group *group) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - int err; - - err = mlxsw_sp_trap_group_policer_init(mlxsw_sp, group); - if (err) - return err; - - err = __mlxsw_sp_trap_group_init(mlxsw_sp, group); - if (err) - return err; - - return 0; + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 12e1fa998d42..eaa521b7561b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -102,6 +102,8 @@ enum { MLXSW_TRAP_ID_ACL1 = 0x1C1, /* Multicast trap used for routes with trap-and-forward action */ MLXSW_TRAP_ID_ACL2 = 0x1C2, + MLXSW_TRAP_ID_DISCARD_INGRESS_ACL = 0x1C3, + MLXSW_TRAP_ID_DISCARD_EGRESS_ACL = 0x1C4, MLXSW_TRAP_ID_MAX = 0x1FF }; diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 1c9e70c8cc30..58579baf3f7a 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -513,14 +513,17 @@ static irqreturn_t ks_irq(int irq, void *pw) { struct net_device *netdev = pw; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; u16 status; + spin_lock_irqsave(&ks->statelock, flags); /*this should be the first in IRQ handler */ ks_save_cmd_reg(ks); status = ks_rdreg16(ks, KS_ISR); if (unlikely(!status)) { ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_NONE; } @@ -546,6 +549,7 @@ static irqreturn_t ks_irq(int irq, void *pw) ks->netdev->stats.rx_over_errors++; /* this should be the last in IRQ handler*/ ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_HANDLED; } @@ -615,6 +619,7 @@ static int ks_net_stop(struct net_device *netdev) /* shutdown RX/TX QMU */ ks_disable_qmu(ks); + ks_disable_int(ks); /* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -671,10 +676,9 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) { netdev_tx_t retv = NETDEV_TX_OK; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; - disable_irq(netdev->irq); - ks_disable_int(ks); - spin_lock(&ks->statelock); + spin_lock_irqsave(&ks->statelock, flags); /* Extra space are required: * 4 byte for alignment, 4 for status/length, 4 for CRC @@ -688,9 +692,7 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) dev_kfree_skb(skb); } else retv = NETDEV_TX_BUSY; - spin_unlock(&ks->statelock); - ks_enable_int(ks); - enable_irq(netdev->irq); + spin_unlock_irqrestore(&ks->statelock, flags); return retv; } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h index a83a0ad5e27d..4268a7e0f344 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h @@ -104,14 +104,14 @@ struct cmsg_req_map_op { __be32 tid; __be32 count; __be32 flags; - u8 data[0]; + u8 data[]; }; struct cmsg_reply_map_op { struct cmsg_reply_map_simple reply_hdr; __be32 count; __be32 resv; - u8 data[0]; + u8 data[]; }; struct cmsg_bpf_event { @@ -120,6 +120,6 @@ struct cmsg_bpf_event { __be64 map_ptr; __be32 data_size; __be32 pkt_size; - u8 data[0]; + u8 data[]; }; #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 9b50d76bbc09..bf516285510f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -587,7 +587,7 @@ struct nfp_flower_cmsg_mac_repr { u8 info; u8 nbi_port; u8 phys_port; - } ports[0]; + } ports[]; }; #define NFP_FLOWER_CMSG_MAC_REPR_NBI GENMASK(1, 0) @@ -619,7 +619,7 @@ struct nfp_flower_cmsg_merge_hint { struct { __be32 host_ctx; __be64 host_cookie; - } __packed flow[0]; + } __packed flow[]; }; enum nfp_flower_cmsg_port_type { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index 5d5812fd9317..fa6b13a05941 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -42,7 +42,7 @@ struct nfp_shared_buf; */ struct nfp_dumpspec { u32 size; - u8 data[0]; + u8 data[]; }; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c index 769ceef09756..a614df095b08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c @@ -36,7 +36,7 @@ enum nfp_dumpspec_type { struct nfp_dump_tl { __be32 type; __be32 length; /* chunk length to follow, aligned to 8 bytes */ - char data[0]; + char data[]; }; /* NFP CPP parameters */ @@ -62,7 +62,7 @@ struct nfp_dumpspec_csr { struct nfp_dumpspec_rtsym { struct nfp_dump_tl tl; - char rtsym[0]; + char rtsym[]; }; /* header for register dumpable */ @@ -79,7 +79,7 @@ struct nfp_dump_rtsym { struct nfp_dump_common_cpp cpp; __be32 error; /* error code encountered while reading */ u8 padded_name_length; /* pad so data starts at 8 byte boundary */ - char rtsym[0]; + char rtsym[]; /* after padded_name_length, there is dump_length data */ }; @@ -92,7 +92,7 @@ struct nfp_dump_error { struct nfp_dump_tl tl; __be32 error; char padding[4]; - char spec[0]; + char spec[]; }; /* to track state through debug size calculation TLV traversal */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h index e0f13dfe1f39..48a74accbbd3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h @@ -18,7 +18,7 @@ struct nfp_port; */ struct nfp_reprs { unsigned int num_reprs; - struct net_device __rcu *reprs[0]; + struct net_device __rcu *reprs[]; }; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index 1531c1870020..f5360bae6f75 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -183,7 +183,7 @@ struct nfp_eth_table { bool is_split; unsigned int fec_modes_supported; - } ports[0]; + } ports[]; }; struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h index 3dce769d83a1..86153660d245 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h @@ -1316,7 +1316,7 @@ struct netxen_minidump_template_hdr { u32 driver_info_word4; u32 saved_state_array[NX_DUMP_STATE_ARRAY_LEN]; u32 capture_size_array[NX_DUMP_CAP_SIZE_ARRAY_LEN]; - u32 rsvd[0]; + u32 rsvd[]; }; /* Common Entry Header: Common to All Entry Types */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 374a4d4371f9..134611aa2c9a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -418,7 +418,7 @@ struct qlcnic_83xx_dump_template_hdr { u32 saved_state[16]; u32 cap_sizes[8]; u32 ocm_wnd_reg[16]; - u32 rsvd[0]; + u32 rsvd[]; }; struct qlcnic_82xx_dump_template_hdr { @@ -436,7 +436,7 @@ struct qlcnic_82xx_dump_template_hdr { u32 cap_sizes[8]; u32 rsvd[7]; u32 capabilities; - u32 rsvd1[0]; + u32 rsvd1[]; }; #define QLC_PEX_DMA_READ_SIZE (PAGE_SIZE * 16) @@ -740,7 +740,7 @@ struct qlcnic_hostrq_rx_ctx { The following is packed: - N hostrq_rds_rings - N hostrq_sds_rings */ - char data[0]; + char data[]; } __packed; struct qlcnic_cardrsp_rds_ring{ @@ -769,7 +769,7 @@ struct qlcnic_cardrsp_rx_ctx { The following is packed: - N cardrsp_rds_rings - N cardrs_sds_rings */ - char data[0]; + char data[]; } __packed; #define SIZEOF_HOSTRQ_RX(HOSTRQ_RX, rds_rings, sds_rings) \ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 06de59521fc4..fbf4cbcf1a65 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -13,25 +13,6 @@ #include "rmnet_vnd.h" #include "rmnet_private.h" -/* Locking scheme - - * The shared resource which needs to be protected is realdev->rx_handler_data. - * For the writer path, this is using rtnl_lock(). The writer paths are - * rmnet_newlink(), rmnet_dellink() and rmnet_force_unassociate_device(). These - * paths are already called with rtnl_lock() acquired in. There is also an - * ASSERT_RTNL() to ensure that we are calling with rtnl acquired. For - * dereference here, we will need to use rtnl_dereference(). Dev list writing - * needs to happen with rtnl_lock() acquired for netdev_master_upper_dev_link(). - * For the reader path, the real_dev->rx_handler_data is called in the TX / RX - * path. We only need rcu_read_lock() for these scenarios. In these cases, - * the rcu_read_lock() is held in __dev_queue_xmit() and - * netif_receive_skb_internal(), so readers need to use rcu_dereference_rtnl() - * to get the relevant information. For dev list reading, we again acquire - * rcu_read_lock() in rmnet_dellink() for netdev_master_upper_dev_get_rcu(). - * We also use unregister_netdevice_many() to free all rmnet devices in - * rmnet_force_unassociate_device() so we dont lose the rtnl_lock() and free in - * same context. - */ - /* Local Definitions and Declarations */ static const struct nla_policy rmnet_policy[IFLA_RMNET_MAX + 1] = { @@ -51,9 +32,10 @@ rmnet_get_port_rtnl(const struct net_device *real_dev) return rtnl_dereference(real_dev->rx_handler_data); } -static int rmnet_unregister_real_device(struct net_device *real_dev, - struct rmnet_port *port) +static int rmnet_unregister_real_device(struct net_device *real_dev) { + struct rmnet_port *port = rmnet_get_port_rtnl(real_dev); + if (port->nr_rmnet_devs) return -EINVAL; @@ -61,9 +43,6 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, kfree(port); - /* release reference on real_dev */ - dev_put(real_dev); - netdev_dbg(real_dev, "Removed from rmnet\n"); return 0; } @@ -89,9 +68,6 @@ static int rmnet_register_real_device(struct net_device *real_dev) return -EBUSY; } - /* hold on to real dev for MAP data */ - dev_hold(real_dev); - for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++) INIT_HLIST_HEAD(&port->muxed_ep[entry]); @@ -99,28 +75,33 @@ static int rmnet_register_real_device(struct net_device *real_dev) return 0; } -static void rmnet_unregister_bridge(struct net_device *dev, - struct rmnet_port *port) +static void rmnet_unregister_bridge(struct rmnet_port *port) { - struct rmnet_port *bridge_port; - struct net_device *bridge_dev; + struct net_device *bridge_dev, *real_dev, *rmnet_dev; + struct rmnet_port *real_port; if (port->rmnet_mode != RMNET_EPMODE_BRIDGE) return; - /* bridge slave handling */ + rmnet_dev = port->rmnet_dev; if (!port->nr_rmnet_devs) { - bridge_dev = port->bridge_ep; + /* bridge device */ + real_dev = port->bridge_ep; + bridge_dev = port->dev; - bridge_port = rmnet_get_port_rtnl(bridge_dev); - bridge_port->bridge_ep = NULL; - bridge_port->rmnet_mode = RMNET_EPMODE_VND; + real_port = rmnet_get_port_rtnl(real_dev); + real_port->bridge_ep = NULL; + real_port->rmnet_mode = RMNET_EPMODE_VND; } else { + /* real device */ bridge_dev = port->bridge_ep; - bridge_port = rmnet_get_port_rtnl(bridge_dev); - rmnet_unregister_real_device(bridge_dev, bridge_port); + port->bridge_ep = NULL; + port->rmnet_mode = RMNET_EPMODE_VND; } + + netdev_upper_dev_unlink(bridge_dev, rmnet_dev); + rmnet_unregister_real_device(bridge_dev); } static int rmnet_newlink(struct net *src_net, struct net_device *dev, @@ -135,6 +116,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, int err = 0; u16 mux_id; + if (!tb[IFLA_LINK]) { + NL_SET_ERR_MSG_MOD(extack, "link not specified"); + return -EINVAL; + } + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev || !dev) return -ENODEV; @@ -157,7 +143,12 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (err) goto err1; + err = netdev_upper_dev_link(real_dev, dev, extack); + if (err < 0) + goto err2; + port->rmnet_mode = mode; + port->rmnet_dev = dev; hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]); @@ -173,8 +164,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, return 0; +err2: + unregister_netdevice(dev); + rmnet_vnd_dellink(mux_id, port, ep); err1: - rmnet_unregister_real_device(real_dev, port); + rmnet_unregister_real_device(real_dev); err0: kfree(ep); return err; @@ -183,77 +177,74 @@ err0: static void rmnet_dellink(struct net_device *dev, struct list_head *head) { struct rmnet_priv *priv = netdev_priv(dev); - struct net_device *real_dev; + struct net_device *real_dev, *bridge_dev; + struct rmnet_port *real_port, *bridge_port; struct rmnet_endpoint *ep; - struct rmnet_port *port; - u8 mux_id; + u8 mux_id = priv->mux_id; real_dev = priv->real_dev; - if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + if (!rmnet_is_real_dev_registered(real_dev)) return; - port = rmnet_get_port_rtnl(real_dev); - - mux_id = rmnet_vnd_get_mux(dev); + real_port = rmnet_get_port_rtnl(real_dev); + bridge_dev = real_port->bridge_ep; + if (bridge_dev) { + bridge_port = rmnet_get_port_rtnl(bridge_dev); + rmnet_unregister_bridge(bridge_port); + } - ep = rmnet_get_endpoint(port, mux_id); + ep = rmnet_get_endpoint(real_port, mux_id); if (ep) { hlist_del_init_rcu(&ep->hlnode); - rmnet_unregister_bridge(dev, port); - rmnet_vnd_dellink(mux_id, port, ep); + rmnet_vnd_dellink(mux_id, real_port, ep); kfree(ep); } - rmnet_unregister_real_device(real_dev, port); + netdev_upper_dev_unlink(real_dev, dev); + rmnet_unregister_real_device(real_dev); unregister_netdevice_queue(dev, head); } -static void rmnet_force_unassociate_device(struct net_device *dev) +static void rmnet_force_unassociate_device(struct net_device *real_dev) { - struct net_device *real_dev = dev; struct hlist_node *tmp_ep; struct rmnet_endpoint *ep; struct rmnet_port *port; unsigned long bkt_ep; LIST_HEAD(list); - if (!rmnet_is_real_dev_registered(real_dev)) - return; - - ASSERT_RTNL(); - - port = rmnet_get_port_rtnl(dev); - - rcu_read_lock(); - rmnet_unregister_bridge(dev, port); - - hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { - unregister_netdevice_queue(ep->egress_dev, &list); - rmnet_vnd_dellink(ep->mux_id, port, ep); + port = rmnet_get_port_rtnl(real_dev); - hlist_del_init_rcu(&ep->hlnode); - kfree(ep); + if (port->nr_rmnet_devs) { + /* real device */ + rmnet_unregister_bridge(port); + hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { + unregister_netdevice_queue(ep->egress_dev, &list); + netdev_upper_dev_unlink(real_dev, ep->egress_dev); + rmnet_vnd_dellink(ep->mux_id, port, ep); + hlist_del_init_rcu(&ep->hlnode); + kfree(ep); + } + rmnet_unregister_real_device(real_dev); + unregister_netdevice_many(&list); + } else { + rmnet_unregister_bridge(port); } - - rcu_read_unlock(); - unregister_netdevice_many(&list); - - rmnet_unregister_real_device(real_dev, port); } static int rmnet_config_notify_cb(struct notifier_block *nb, unsigned long event, void *data) { - struct net_device *dev = netdev_notifier_info_to_dev(data); + struct net_device *real_dev = netdev_notifier_info_to_dev(data); - if (!dev) + if (!rmnet_is_real_dev_registered(real_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: - netdev_dbg(dev, "Kernel unregister\n"); - rmnet_force_unassociate_device(dev); + netdev_dbg(real_dev, "Kernel unregister\n"); + rmnet_force_unassociate_device(real_dev); break; default: @@ -295,16 +286,18 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[], if (!dev) return -ENODEV; - real_dev = __dev_get_by_index(dev_net(dev), - nla_get_u32(tb[IFLA_LINK])); - - if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + real_dev = priv->real_dev; + if (!rmnet_is_real_dev_registered(real_dev)) return -ENODEV; port = rmnet_get_port_rtnl(real_dev); if (data[IFLA_RMNET_MUX_ID]) { mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]); + if (rmnet_get_endpoint(port, mux_id)) { + NL_SET_ERR_MSG_MOD(extack, "MUX ID already exists"); + return -EINVAL; + } ep = rmnet_get_endpoint(port, priv->mux_id); if (!ep) return -ENODEV; @@ -379,11 +372,10 @@ struct rtnl_link_ops rmnet_link_ops __read_mostly = { .fill_info = rmnet_fill_info, }; -/* Needs either rcu_read_lock() or rtnl lock */ -struct rmnet_port *rmnet_get_port(struct net_device *real_dev) +struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev) { if (rmnet_is_real_dev_registered(real_dev)) - return rcu_dereference_rtnl(real_dev->rx_handler_data); + return rcu_dereference_bh(real_dev->rx_handler_data); else return NULL; } @@ -409,7 +401,7 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, struct rmnet_port *port, *slave_port; int err; - port = rmnet_get_port(real_dev); + port = rmnet_get_port_rtnl(real_dev); /* If there is more than one rmnet dev attached, its probably being * used for muxing. Skip the briding in that case @@ -417,6 +409,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (port->nr_rmnet_devs > 1) return -EINVAL; + if (port->rmnet_mode != RMNET_EPMODE_VND) + return -EINVAL; + if (rmnet_is_real_dev_registered(slave_dev)) return -EBUSY; @@ -424,9 +419,17 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (err) return -EBUSY; - slave_port = rmnet_get_port(slave_dev); + err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL, + extack); + if (err) { + rmnet_unregister_real_device(slave_dev); + return err; + } + + slave_port = rmnet_get_port_rtnl(slave_dev); slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE; slave_port->bridge_ep = real_dev; + slave_port->rmnet_dev = rmnet_dev; port->rmnet_mode = RMNET_EPMODE_BRIDGE; port->bridge_ep = slave_dev; @@ -438,16 +441,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, int rmnet_del_bridge(struct net_device *rmnet_dev, struct net_device *slave_dev) { - struct rmnet_priv *priv = netdev_priv(rmnet_dev); - struct net_device *real_dev = priv->real_dev; - struct rmnet_port *port, *slave_port; + struct rmnet_port *port = rmnet_get_port_rtnl(slave_dev); - port = rmnet_get_port(real_dev); - port->rmnet_mode = RMNET_EPMODE_VND; - port->bridge_ep = NULL; - - slave_port = rmnet_get_port(slave_dev); - rmnet_unregister_real_device(slave_dev, slave_port); + rmnet_unregister_bridge(port); netdev_dbg(slave_dev, "removed from rmnet as slave\n"); return 0; @@ -473,8 +469,8 @@ static int __init rmnet_init(void) static void __exit rmnet_exit(void) { - unregister_netdevice_notifier(&rmnet_dev_notifier); rtnl_link_unregister(&rmnet_link_ops); + unregister_netdevice_notifier(&rmnet_dev_notifier); } module_init(rmnet_init) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index cd0a6bcbe74a..be515982d628 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -28,6 +28,7 @@ struct rmnet_port { u8 rmnet_mode; struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; struct net_device *bridge_ep; + struct net_device *rmnet_dev; }; extern struct rtnl_link_ops rmnet_link_ops; @@ -65,7 +66,7 @@ struct rmnet_priv { struct rmnet_priv_stats stats; }; -struct rmnet_port *rmnet_get_port(struct net_device *real_dev); +struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev); struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id); int rmnet_add_bridge(struct net_device *rmnet_dev, struct net_device *slave_dev, diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 1b74bc160402..29a7bfa2584d 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -159,6 +159,9 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, static void rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev) { + if (skb_mac_header_was_set(skb)) + skb_push(skb, skb->mac_len); + if (bridge_dev) { skb->dev = bridge_dev; dev_queue_xmit(skb); @@ -184,7 +187,7 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) return RX_HANDLER_PASS; dev = skb->dev; - port = rmnet_get_port(dev); + port = rmnet_get_port_rcu(dev); switch (port->rmnet_mode) { case RMNET_EPMODE_VND: @@ -217,7 +220,7 @@ void rmnet_egress_handler(struct sk_buff *skb) skb->dev = priv->real_dev; mux_id = priv->mux_id; - port = rmnet_get_port(skb->dev); + port = rmnet_get_port_rcu(skb->dev); if (!port) goto drop; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 509dfc895a33..26ad40f19c64 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -266,14 +266,6 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, return 0; } -u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev) -{ - struct rmnet_priv *priv; - - priv = netdev_priv(rmnet_dev); - return priv->mux_id; -} - int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable) { netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index 54cbaf3c3bc4..14d77c709d4a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -16,6 +16,5 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, struct rmnet_endpoint *ep); void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); -u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev); void rmnet_vnd_setup(struct net_device *dev); #endif /* _RMNET_VND_H_ */ diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 267b7ae05e23..f081007a245b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1308,10 +1308,6 @@ static void rtl_irq_disable(struct rtl8169_private *tp) tp->irq_enabled = 0; } -#define RTL_EVENT_NAPI_RX (RxOK | RxErr) -#define RTL_EVENT_NAPI_TX (TxOK | TxErr) -#define RTL_EVENT_NAPI (RTL_EVENT_NAPI_RX | RTL_EVENT_NAPI_TX) - static void rtl_irq_enable(struct rtl8169_private *tp) { tp->irq_enabled = 1; @@ -4091,12 +4087,10 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb, tp->tx_skb[entry].len = len; } - if (cur_frag) { - tp->tx_skb[entry].skb = skb; - txd->opts1 |= cpu_to_le32(LastFrag); - } + tp->tx_skb[entry].skb = skb; + txd->opts1 |= cpu_to_le32(LastFrag); - return cur_frag; + return 0; err_out: rtl8169_tx_clear_range(tp, tp->cur_tx + 1, cur_frag); @@ -4221,6 +4215,7 @@ static void rtl8169_doorbell(struct rtl8169_private *tp) static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev) { + unsigned int frags = skb_shinfo(skb)->nr_frags; struct rtl8169_private *tp = netdev_priv(dev); unsigned int entry = tp->cur_tx % NUM_TX_DESC; struct TxDesc *txd = tp->TxDescArray + entry; @@ -4229,9 +4224,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, u32 opts[2], len; bool stop_queue; bool door_bell; - int frags; - if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { + if (unlikely(!rtl_tx_slots_avail(tp, frags))) { netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n"); goto err_stop_0; } @@ -4260,14 +4254,13 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->tx_skb[entry].len = len; txd->addr = cpu_to_le64(mapping); - frags = rtl8169_xmit_frags(tp, skb, opts); - if (frags < 0) - goto err_dma_1; - else if (frags) - opts[0] |= FirstFrag; - else { + if (!frags) { opts[0] |= FirstFrag | LastFrag; tp->tx_skb[entry].skb = skb; + } else { + if (rtl8169_xmit_frags(tp, skb, opts)) + goto err_dma_1; + opts[0] |= FirstFrag; } txd->opts2 = cpu_to_le32(opts[1]); @@ -5113,7 +5106,7 @@ static const struct net_device_ops rtl_netdev_ops = { static void rtl_set_irq_mask(struct rtl8169_private *tp) { - tp->irq_mask = RTL_EVENT_NAPI | LinkChg; + tp->irq_mask = RxOK | RxErr | TxOK | TxErr | LinkChg; if (tp->mac_version <= RTL_GIGA_MAC_VER_06) tp->irq_mask |= SYSErr | RxOverflow | RxFIFOOver; diff --git a/drivers/net/ethernet/sfc/falcon/net_driver.h b/drivers/net/ethernet/sfc/falcon/net_driver.h index a49ea2e719b6..a529ff395ead 100644 --- a/drivers/net/ethernet/sfc/falcon/net_driver.h +++ b/drivers/net/ethernet/sfc/falcon/net_driver.h @@ -288,7 +288,7 @@ struct ef4_rx_buffer { struct ef4_rx_page_state { dma_addr_t dma_addr; - unsigned int __pad[0] ____cacheline_aligned; + unsigned int __pad[] ____cacheline_aligned; }; /** diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 9f9886f222c8..392bd5b7017e 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -336,7 +336,7 @@ struct efx_rx_buffer { struct efx_rx_page_state { dma_addr_t dma_addr; - unsigned int __pad[0] ____cacheline_aligned; + unsigned int __pad[] ____cacheline_aligned; }; /** diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index af15a737c675..59b4f16896a8 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -560,13 +560,45 @@ efx_ptp_mac_nic_to_ktime_correction(struct efx_nic *efx, u32 nic_major, u32 nic_minor, s32 correction) { + u32 sync_timestamp; ktime_t kt = { 0 }; + s16 delta; if (!(nic_major & 0x80000000)) { WARN_ON_ONCE(nic_major >> 16); - /* Use the top bits from the latest sync event. */ - nic_major &= 0xffff; - nic_major |= (last_sync_timestamp_major(efx) & 0xffff0000); + + /* Medford provides 48 bits of timestamp, so we must get the top + * 16 bits from the timesync event state. + * + * We only have the lower 16 bits of the time now, but we do + * have a full resolution timestamp at some point in past. As + * long as the difference between the (real) now and the sync + * is less than 2^15, then we can reconstruct the difference + * between those two numbers using only the lower 16 bits of + * each. + * + * Put another way + * + * a - b = ((a mod k) - b) mod k + * + * when -k/2 < (a-b) < k/2. In our case k is 2^16. We know + * (a mod k) and b, so can calculate the delta, a - b. + * + */ + sync_timestamp = last_sync_timestamp_major(efx); + + /* Because delta is s16 this does an implicit mask down to + * 16 bits which is what we need, assuming + * MEDFORD_TX_SECS_EVENT_BITS is 16. delta is signed so that + * we can deal with the (unlikely) case of sync timestamps + * arriving from the future. + */ + delta = nic_major - sync_timestamp; + + /* Recover the fully specified time now, by applying the offset + * to the (fully specified) sync time. + */ + nic_major = sync_timestamp + delta; kt = ptp->nic_to_kernel_time(nic_major, nic_minor, correction); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 9b7be996d07b..b2dc99289687 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -304,7 +304,7 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, /* Get ETH_CLK clocks */ dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck"); if (IS_ERR(dwmac->clk_eth_ck)) { - dev_warn(dev, "No phy clock provided...\n"); + dev_info(dev, "No phy clock provided...\n"); dwmac->clk_eth_ck = NULL; } @@ -324,7 +324,7 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, /* Get IRQ information early to have an ability to ask for deferred * probe if needed before we went too far with resource allocation. */ - dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev, + dwmac->irq_pwr_wakeup = platform_get_irq_byname_optional(pdev, "stm32_pwr_wakeup"); if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER) return -EPROBE_DEFER; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 37920b4da091..cb7a5bad4cfe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -950,8 +950,10 @@ static void stmmac_mac_link_down(struct phylink_config *config, } static void stmmac_mac_link_up(struct phylink_config *config, + struct phy_device *phy, unsigned int mode, phy_interface_t interface, - struct phy_device *phy) + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); @@ -4405,6 +4407,8 @@ static void stmmac_init_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + rtnl_lock(); + /* Create per netdev entries */ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); @@ -4416,14 +4420,13 @@ static void stmmac_init_fs(struct net_device *dev) debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev, &stmmac_dma_cap_fops); - register_netdevice_notifier(&stmmac_notifier); + rtnl_unlock(); } static void stmmac_exit_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - unregister_netdevice_notifier(&stmmac_notifier); debugfs_remove_recursive(priv->dbgfs_dir); } #endif /* CONFIG_DEBUG_FS */ @@ -4940,14 +4943,14 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); -#ifdef CONFIG_DEBUG_FS - stmmac_exit_fs(ndev); -#endif stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); +#ifdef CONFIG_DEBUG_FS + stmmac_exit_fs(ndev); +#endif phylink_destroy(priv->phylink); if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); @@ -5166,6 +5169,7 @@ static int __init stmmac_init(void) /* Create debugfs main directory if it doesn't exist yet */ if (!stmmac_fs_dir) stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); + register_netdevice_notifier(&stmmac_notifier); #endif return 0; @@ -5174,6 +5178,7 @@ static int __init stmmac_init(void) static void __exit stmmac_exit(void) { #ifdef CONFIG_DEBUG_FS + unregister_netdevice_notifier(&stmmac_notifier); debugfs_remove_recursive(stmmac_fs_dir); #endif } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index d10ac54bf385..165958c9f069 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -588,7 +588,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) if (IS_ERR(plat->clk_ptp_ref)) { plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk); plat->clk_ptp_ref = NULL; - dev_warn(&pdev->dev, "PTP uses main clock\n"); + dev_info(&pdev->dev, "PTP uses main clock\n"); } else { plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref); dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate); diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index 805903dbddcc..68f324ed4eaf 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -308,7 +308,7 @@ struct gelic_port { struct gelic_card *card; struct net_device *netdev; enum gelic_port_type type; - long priv[0]; /* long for alignment */ + long priv[]; /* long for alignment */ }; static inline struct gelic_card *port_to_card(struct gelic_port *p) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h index 4041d946b649..1f203d1ae8db 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h @@ -158,7 +158,7 @@ struct gelic_eurus_scan_info { __be32 reserved2; __be32 reserved3; __be32 reserved4; - u8 elements[0]; /* ie */ + u8 elements[]; /* ie */ } __packed; /* the hypervisor returns bbs up to 16 */ diff --git a/drivers/net/ethernet/toshiba/spider_net.h b/drivers/net/ethernet/toshiba/spider_net.h index c0c68cbc898c..05b1a0736835 100644 --- a/drivers/net/ethernet/toshiba/spider_net.h +++ b/drivers/net/ethernet/toshiba/spider_net.h @@ -470,7 +470,7 @@ struct spider_net_card { struct spider_net_extra_stats spider_stats; /* Must be last item in struct */ - struct spider_net_descr darray[0]; + struct spider_net_descr darray[]; }; #endif diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 3fd43d30b20d..b50c3ec3495b 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -367,7 +367,7 @@ struct TxFD { struct RxFD { struct FDesc fd; - struct BDesc bd[0]; /* variable length */ + struct BDesc bd[]; /* variable length */ }; struct FrFD { diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index 276292bca334..53fb8141f1a6 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -375,10 +375,14 @@ struct temac_local { int tx_bd_next; int tx_bd_tail; int rx_bd_ci; + int rx_bd_tail; /* DMA channel control setup */ u32 tx_chnl_ctrl; u32 rx_chnl_ctrl; + u8 coalesce_count_rx; + + struct delayed_work restart_work; }; /* Wrappers for temac_ior()/temac_iow() function pointers above */ diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 6f11f52c9a9e..9461acec6f70 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -51,6 +51,7 @@ #include <linux/ip.h> #include <linux/slab.h> #include <linux/interrupt.h> +#include <linux/workqueue.h> #include <linux/dma-mapping.h> #include <linux/processor.h> #include <linux/platform_data/xilinx-ll-temac.h> @@ -367,6 +368,8 @@ static int temac_dma_bd_init(struct net_device *ndev) skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) + goto out; lp->rx_bd_v[i].phys = cpu_to_be32(skb_dma_addr); lp->rx_bd_v[i].len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); @@ -387,12 +390,13 @@ static int temac_dma_bd_init(struct net_device *ndev) lp->tx_bd_next = 0; lp->tx_bd_tail = 0; lp->rx_bd_ci = 0; + lp->rx_bd_tail = RX_BD_NUM - 1; /* Enable RX DMA transfers */ wmb(); lp->dma_out(lp, RX_CURDESC_PTR, lp->rx_bd_p); lp->dma_out(lp, RX_TAILDESC_PTR, - lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1))); + lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * lp->rx_bd_tail)); /* Prepare for TX DMA transfer */ lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p); @@ -788,6 +792,9 @@ static void temac_start_xmit_done(struct net_device *ndev) stat = be32_to_cpu(cur_p->app0); } + /* Matches barrier in temac_start_xmit */ + smp_mb(); + netif_wake_queue(ndev); } @@ -830,9 +837,19 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; if (temac_check_tx_bd_space(lp, num_frag + 1)) { - if (!netif_queue_stopped(ndev)) - netif_stop_queue(ndev); - return NETDEV_TX_BUSY; + if (netif_queue_stopped(ndev)) + return NETDEV_TX_BUSY; + + netif_stop_queue(ndev); + + /* Matches barrier in temac_start_xmit_done */ + smp_mb(); + + /* Space might have just been freed - check again */ + if (temac_check_tx_bd_space(lp, num_frag)) + return NETDEV_TX_BUSY; + + netif_wake_queue(ndev); } cur_p->app0 = 0; @@ -850,12 +867,16 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb_headlen(skb), DMA_TO_DEVICE); cur_p->len = cpu_to_be32(skb_headlen(skb)); + if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, skb_dma_addr))) { + dev_kfree_skb_any(skb); + ndev->stats.tx_dropped++; + return NETDEV_TX_OK; + } cur_p->phys = cpu_to_be32(skb_dma_addr); ptr_to_txbd((void *)skb, cur_p); for (ii = 0; ii < num_frag; ii++) { - lp->tx_bd_tail++; - if (lp->tx_bd_tail >= TX_BD_NUM) + if (++lp->tx_bd_tail >= TX_BD_NUM) lp->tx_bd_tail = 0; cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; @@ -863,6 +884,27 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_frag_address(frag), skb_frag_size(frag), DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) { + if (--lp->tx_bd_tail < 0) + lp->tx_bd_tail = TX_BD_NUM - 1; + cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; + while (--ii >= 0) { + --frag; + dma_unmap_single(ndev->dev.parent, + be32_to_cpu(cur_p->phys), + skb_frag_size(frag), + DMA_TO_DEVICE); + if (--lp->tx_bd_tail < 0) + lp->tx_bd_tail = TX_BD_NUM - 1; + cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; + } + dma_unmap_single(ndev->dev.parent, + be32_to_cpu(cur_p->phys), + skb_headlen(skb), DMA_TO_DEVICE); + dev_kfree_skb_any(skb); + ndev->stats.tx_dropped++; + return NETDEV_TX_OK; + } cur_p->phys = cpu_to_be32(skb_dma_addr); cur_p->len = cpu_to_be32(skb_frag_size(frag)); cur_p->app0 = 0; @@ -884,31 +926,56 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +static int ll_temac_recv_buffers_available(struct temac_local *lp) +{ + int available; + + if (!lp->rx_skb[lp->rx_bd_ci]) + return 0; + available = 1 + lp->rx_bd_tail - lp->rx_bd_ci; + if (available <= 0) + available += RX_BD_NUM; + return available; +} static void ll_temac_recv(struct net_device *ndev) { struct temac_local *lp = netdev_priv(ndev); - struct sk_buff *skb, *new_skb; - unsigned int bdstat; - struct cdmac_bd *cur_p; - dma_addr_t tail_p, skb_dma_addr; - int length; unsigned long flags; + int rx_bd; + bool update_tail = false; spin_lock_irqsave(&lp->rx_lock, flags); - tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci; - cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; - - bdstat = be32_to_cpu(cur_p->app0); - while ((bdstat & STS_CTRL_APP0_CMPLT)) { + /* Process all received buffers, passing them on network + * stack. After this, the buffer descriptors will be in an + * un-allocated stage, where no skb is allocated for it, and + * they are therefore not available for TEMAC/DMA. + */ + do { + struct cdmac_bd *bd = &lp->rx_bd_v[lp->rx_bd_ci]; + struct sk_buff *skb = lp->rx_skb[lp->rx_bd_ci]; + unsigned int bdstat = be32_to_cpu(bd->app0); + int length; + + /* While this should not normally happen, we can end + * here when GFP_ATOMIC allocations fail, and we + * therefore have un-allocated buffers. + */ + if (!skb) + break; - skb = lp->rx_skb[lp->rx_bd_ci]; - length = be32_to_cpu(cur_p->app4) & 0x3FFF; + /* Loop over all completed buffer descriptors */ + if (!(bdstat & STS_CTRL_APP0_CMPLT)) + break; - dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), + dma_unmap_single(ndev->dev.parent, be32_to_cpu(bd->phys), XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); + /* The buffer is not valid for DMA anymore */ + bd->phys = 0; + bd->len = 0; + length = be32_to_cpu(bd->app4) & 0x3FFF; skb_put(skb, length); skb->protocol = eth_type_trans(skb, ndev); skb_checksum_none_assert(skb); @@ -923,43 +990,102 @@ static void ll_temac_recv(struct net_device *ndev) * (back) for proper IP checksum byte order * (be16). */ - skb->csum = htons(be32_to_cpu(cur_p->app3) & 0xFFFF); + skb->csum = htons(be32_to_cpu(bd->app3) & 0xFFFF); skb->ip_summed = CHECKSUM_COMPLETE; } if (!skb_defer_rx_timestamp(skb)) netif_rx(skb); + /* The skb buffer is now owned by network stack above */ + lp->rx_skb[lp->rx_bd_ci] = NULL; ndev->stats.rx_packets++; ndev->stats.rx_bytes += length; - new_skb = netdev_alloc_skb_ip_align(ndev, - XTE_MAX_JUMBO_FRAME_SIZE); - if (!new_skb) { - spin_unlock_irqrestore(&lp->rx_lock, flags); - return; + rx_bd = lp->rx_bd_ci; + if (++lp->rx_bd_ci >= RX_BD_NUM) + lp->rx_bd_ci = 0; + } while (rx_bd != lp->rx_bd_tail); + + /* DMA operations will halt when the last buffer descriptor is + * processed (ie. the one pointed to by RX_TAILDESC_PTR). + * When that happens, no more interrupt events will be + * generated. No IRQ_COAL or IRQ_DLY, and not even an + * IRQ_ERR. To avoid stalling, we schedule a delayed work + * when there is a potential risk of that happening. The work + * will call this function, and thus re-schedule itself until + * enough buffers are available again. + */ + if (ll_temac_recv_buffers_available(lp) < lp->coalesce_count_rx) + schedule_delayed_work(&lp->restart_work, HZ / 1000); + + /* Allocate new buffers for those buffer descriptors that were + * passed to network stack. Note that GFP_ATOMIC allocations + * can fail (e.g. when a larger burst of GFP_ATOMIC + * allocations occurs), so while we try to allocate all + * buffers in the same interrupt where they were processed, we + * continue with what we could get in case of allocation + * failure. Allocation of remaining buffers will be retried + * in following calls. + */ + while (1) { + struct sk_buff *skb; + struct cdmac_bd *bd; + dma_addr_t skb_dma_addr; + + rx_bd = lp->rx_bd_tail + 1; + if (rx_bd >= RX_BD_NUM) + rx_bd = 0; + bd = &lp->rx_bd_v[rx_bd]; + + if (bd->phys) + break; /* All skb's allocated */ + + skb = netdev_alloc_skb_ip_align(ndev, XTE_MAX_JUMBO_FRAME_SIZE); + if (!skb) { + dev_warn(&ndev->dev, "skb alloc failed\n"); + break; } - cur_p->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); - skb_dma_addr = dma_map_single(ndev->dev.parent, new_skb->data, + skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); - cur_p->phys = cpu_to_be32(skb_dma_addr); - cur_p->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); - lp->rx_skb[lp->rx_bd_ci] = new_skb; + if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, + skb_dma_addr))) { + dev_kfree_skb_any(skb); + break; + } - lp->rx_bd_ci++; - if (lp->rx_bd_ci >= RX_BD_NUM) - lp->rx_bd_ci = 0; + bd->phys = cpu_to_be32(skb_dma_addr); + bd->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); + bd->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); + lp->rx_skb[rx_bd] = skb; - cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; - bdstat = be32_to_cpu(cur_p->app0); + lp->rx_bd_tail = rx_bd; + update_tail = true; + } + + /* Move tail pointer when buffers have been allocated */ + if (update_tail) { + lp->dma_out(lp, RX_TAILDESC_PTR, + lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_tail); } - lp->dma_out(lp, RX_TAILDESC_PTR, tail_p); spin_unlock_irqrestore(&lp->rx_lock, flags); } +/* Function scheduled to ensure a restart in case of DMA halt + * condition caused by running out of buffer descriptors. + */ +static void ll_temac_restart_work_func(struct work_struct *work) +{ + struct temac_local *lp = container_of(work, struct temac_local, + restart_work.work); + struct net_device *ndev = lp->ndev; + + ll_temac_recv(ndev); +} + static irqreturn_t ll_temac_tx_irq(int irq, void *_ndev) { struct net_device *ndev = _ndev; @@ -1052,6 +1178,8 @@ static int temac_stop(struct net_device *ndev) dev_dbg(&ndev->dev, "temac_close()\n"); + cancel_delayed_work_sync(&lp->restart_work); + free_irq(lp->tx_irq, ndev); free_irq(lp->rx_irq, ndev); @@ -1173,6 +1301,7 @@ static int temac_probe(struct platform_device *pdev) lp->dev = &pdev->dev; lp->options = XTE_OPTION_DEFAULTS; spin_lock_init(&lp->rx_lock); + INIT_DELAYED_WORK(&lp->restart_work, ll_temac_restart_work_func); /* Setup mutex for synchronization of indirect register access */ if (pdata) { @@ -1279,6 +1408,7 @@ static int temac_probe(struct platform_device *pdev) */ lp->tx_chnl_ctrl = 0x10220000; lp->rx_chnl_ctrl = 0xff070000; + lp->coalesce_count_rx = 0x07; /* Finished with the DMA node; drop the reference */ of_node_put(dma_np); @@ -1310,11 +1440,14 @@ static int temac_probe(struct platform_device *pdev) (pdata->tx_irq_count << 16); else lp->tx_chnl_ctrl = 0x10220000; - if (pdata->rx_irq_timeout || pdata->rx_irq_count) + if (pdata->rx_irq_timeout || pdata->rx_irq_count) { lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) | (pdata->rx_irq_count << 16); - else + lp->coalesce_count_rx = pdata->rx_irq_count; + } else { lp->rx_chnl_ctrl = 0xff070000; + lp->coalesce_count_rx = 0x07; + } } /* Error handle returned DMA RX and TX interrupts */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 20746b801959..c2f4c5ca2e80 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1441,6 +1441,22 @@ static void axienet_mac_an_restart(struct phylink_config *config) static void axienet_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { + /* nothing meaningful to do */ +} + +static void axienet_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + /* nothing meaningful to do */ +} + +static void axienet_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) +{ struct net_device *ndev = to_net_dev(config->dev); struct axienet_local *lp = netdev_priv(ndev); u32 emmc_reg, fcc_reg; @@ -1448,7 +1464,7 @@ static void axienet_mac_config(struct phylink_config *config, unsigned int mode, emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET); emmc_reg &= ~XAE_EMMC_LINKSPEED_MASK; - switch (state->speed) { + switch (speed) { case SPEED_1000: emmc_reg |= XAE_EMMC_LINKSPD_1000; break; @@ -1467,32 +1483,17 @@ static void axienet_mac_config(struct phylink_config *config, unsigned int mode, axienet_iow(lp, XAE_EMMC_OFFSET, emmc_reg); fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET); - if (state->pause & MLO_PAUSE_TX) + if (tx_pause) fcc_reg |= XAE_FCC_FCTX_MASK; else fcc_reg &= ~XAE_FCC_FCTX_MASK; - if (state->pause & MLO_PAUSE_RX) + if (rx_pause) fcc_reg |= XAE_FCC_FCRX_MASK; else fcc_reg &= ~XAE_FCC_FCRX_MASK; axienet_iow(lp, XAE_FCC_OFFSET, fcc_reg); } -static void axienet_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - /* nothing meaningful to do */ -} - -static void axienet_mac_link_up(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phy) -{ - /* nothing meaningful to do */ -} - static const struct phylink_mac_ops axienet_phylink_ops = { .validate = axienet_validate, .mac_pcs_get_state = axienet_mac_pcs_get_state, diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index ae3f3084c2ed..1b320bcf150a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -99,7 +99,7 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; - net_device->tx_disable = false; + net_device->tx_disable = true; net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 5ee282b20ecb..245ce2374035 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1065,6 +1065,7 @@ static int netvsc_attach(struct net_device *ndev, } /* In any case device is now ready */ + nvdev->tx_disable = false; netif_device_attach(ndev); /* Note: enable and attach happen when sub-channels setup */ @@ -2473,6 +2474,8 @@ static int netvsc_probe(struct hv_device *dev, else net->max_mtu = ETH_DATA_LEN; + nvdev->tx_disable = false; + ret = register_netdevice(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d7706a0346f2..f81c47377f32 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -28,6 +28,7 @@ #include <linux/workqueue.h> #include <net/devlink.h> #include <net/ip.h> +#include <net/flow_offload.h> #include <uapi/linux/devlink.h> #include <uapi/linux/ip.h> #include <uapi/linux/udp.h> @@ -71,6 +72,98 @@ static const struct file_operations nsim_dev_take_snapshot_fops = { .llseek = generic_file_llseek, }; +static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file, + char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + struct flow_action_cookie *fa_cookie; + unsigned int buf_len; + ssize_t ret; + char *buf; + + spin_lock(&nsim_dev->fa_cookie_lock); + fa_cookie = nsim_dev->fa_cookie; + if (!fa_cookie) { + ret = -EINVAL; + goto errout; + } + buf_len = fa_cookie->cookie_len * 2; + buf = kmalloc(buf_len, GFP_ATOMIC); + if (!buf) { + ret = -ENOMEM; + goto errout; + } + bin2hex(buf, fa_cookie->cookie, fa_cookie->cookie_len); + spin_unlock(&nsim_dev->fa_cookie_lock); + + ret = simple_read_from_buffer(data, count, ppos, buf, buf_len); + + kfree(buf); + return ret; + +errout: + spin_unlock(&nsim_dev->fa_cookie_lock); + return ret; +} + +static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + struct flow_action_cookie *fa_cookie; + size_t cookie_len; + ssize_t ret; + char *buf; + + if (*ppos != 0) + return -EINVAL; + cookie_len = (count - 1) / 2; + if ((count - 1) % 2) + return -EINVAL; + buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); + if (!buf) + return -ENOMEM; + + ret = simple_write_to_buffer(buf, count, ppos, data, count); + if (ret < 0) + goto free_buf; + + fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len, + GFP_KERNEL | __GFP_NOWARN); + if (!fa_cookie) { + ret = -ENOMEM; + goto free_buf; + } + + fa_cookie->cookie_len = cookie_len; + ret = hex2bin(fa_cookie->cookie, buf, cookie_len); + if (ret) + goto free_fa_cookie; + kfree(buf); + + spin_lock(&nsim_dev->fa_cookie_lock); + kfree(nsim_dev->fa_cookie); + nsim_dev->fa_cookie = fa_cookie; + spin_unlock(&nsim_dev->fa_cookie_lock); + + return count; + +free_fa_cookie: + kfree(fa_cookie); +free_buf: + kfree(buf); + return ret; +} + +static const struct file_operations nsim_dev_trap_fa_cookie_fops = { + .open = simple_open, + .read = nsim_dev_trap_fa_cookie_read, + .write = nsim_dev_trap_fa_cookie_write, + .llseek = generic_file_llseek, +}; + static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) { char dev_ddir_name[sizeof(DRV_NAME) + 10]; @@ -97,6 +190,8 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) &nsim_dev->dont_allow_reload); debugfs_create_bool("fail_reload", 0600, nsim_dev->ddir, &nsim_dev->fail_reload); + debugfs_create_file("trap_flow_action_cookie", 0600, nsim_dev->ddir, + nsim_dev, &nsim_dev_trap_fa_cookie_fops); return 0; } @@ -288,6 +383,10 @@ enum { DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ NSIM_TRAP_METADATA) +#define NSIM_TRAP_DROP_EXT(_id, _group_id, _metadata) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + NSIM_TRAP_METADATA | (_metadata)) #define NSIM_TRAP_EXCEPTION(_id, _group_id) \ DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ @@ -309,6 +408,10 @@ static const struct devlink_trap nsim_traps_arr[] = { NSIM_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS), NSIM_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS), NSIM_TRAP_DROP(TAIL_DROP, BUFFER_DROPS), + NSIM_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), + NSIM_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), }; #define NSIM_TRAP_L4_DATA_LEN 100 @@ -366,8 +469,13 @@ static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) spin_lock(&nsim_trap_data->trap_lock); for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + struct flow_action_cookie *fa_cookie = NULL; struct nsim_trap_item *nsim_trap_item; struct sk_buff *skb; + bool has_fa_cookie; + + has_fa_cookie = nsim_traps_arr[i].metadata_cap & + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE; nsim_trap_item = &nsim_trap_data->trap_items_arr[i]; if (nsim_trap_item->action == DEVLINK_TRAP_ACTION_DROP) @@ -383,10 +491,12 @@ static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) * softIRQs to prevent lockdep from complaining about * "incosistent lock state". */ - local_bh_disable(); + + spin_lock_bh(&nsim_dev->fa_cookie_lock); + fa_cookie = has_fa_cookie ? nsim_dev->fa_cookie : NULL; devlink_trap_report(devlink, skb, nsim_trap_item->trap_ctx, - &nsim_dev_port->devlink_port); - local_bh_enable(); + &nsim_dev_port->devlink_port, fa_cookie); + spin_unlock_bh(&nsim_dev->fa_cookie_lock); consume_skb(skb); } spin_unlock(&nsim_trap_data->trap_lock); @@ -780,6 +890,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->fw_update_status = true; nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; + spin_lock_init(&nsim_dev->fa_cookie_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 2eb7b0dc1594..e46fc565b981 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -178,6 +178,8 @@ struct nsim_dev { bool fail_reload; struct devlink_region *dummy_region; struct nsim_dev_health health; + struct flow_action_cookie *fa_cookie; + spinlock_t fa_cookie_lock; /* protects fa_cookie */ }; static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 28e33ece4ce1..9a8badafea8a 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1306,6 +1306,9 @@ static int marvell_read_status_page_an(struct phy_device *phydev, } } + if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) + return 0; + if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) phydev->duplex = DUPLEX_FULL; else @@ -1365,6 +1368,8 @@ static int marvell_read_status_page(struct phy_device *phydev, int page) linkmode_zero(phydev->lp_advertising); phydev->pause = 0; phydev->asym_pause = 0; + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; if (phydev->autoneg == AUTONEG_ENABLE) err = marvell_read_status_page_an(phydev, fiber, status); diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 64c9f3bba2cd..9a4e12a2af07 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -39,10 +39,19 @@ enum { MV_PCS_BASE_R = 0x1000, MV_PCS_1000BASEX = 0x2000, - MV_PCS_PAIRSWAP = 0x8182, - MV_PCS_PAIRSWAP_MASK = 0x0003, - MV_PCS_PAIRSWAP_AB = 0x0002, - MV_PCS_PAIRSWAP_NONE = 0x0003, + MV_PCS_CSSR1 = 0x8008, + MV_PCS_CSSR1_SPD1_MASK = 0xc000, + MV_PCS_CSSR1_SPD1_SPD2 = 0xc000, + MV_PCS_CSSR1_SPD1_1000 = 0x8000, + MV_PCS_CSSR1_SPD1_100 = 0x4000, + MV_PCS_CSSR1_SPD1_10 = 0x0000, + MV_PCS_CSSR1_DUPLEX_FULL= BIT(13), + MV_PCS_CSSR1_RESOLVED = BIT(11), + MV_PCS_CSSR1_MDIX = BIT(6), + MV_PCS_CSSR1_SPD2_MASK = 0x000c, + MV_PCS_CSSR1_SPD2_5000 = 0x0008, + MV_PCS_CSSR1_SPD2_2500 = 0x0004, + MV_PCS_CSSR1_SPD2_10000 = 0x0000, /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is @@ -413,35 +422,18 @@ static void mv3310_update_interface(struct phy_device *phydev) } /* 10GBASE-ER,LR,LRM,SR do not support autonegotiation. */ -static int mv3310_read_10gbr_status(struct phy_device *phydev) +static int mv3310_read_status_10gbaser(struct phy_device *phydev) { phydev->link = 1; phydev->speed = SPEED_10000; phydev->duplex = DUPLEX_FULL; - mv3310_update_interface(phydev); - return 0; } -static int mv3310_read_status(struct phy_device *phydev) +static int mv3310_read_status_copper(struct phy_device *phydev) { - int val; - - phydev->speed = SPEED_UNKNOWN; - phydev->duplex = DUPLEX_UNKNOWN; - linkmode_zero(phydev->lp_advertising); - phydev->link = 0; - phydev->pause = 0; - phydev->asym_pause = 0; - phydev->mdix = 0; - - val = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_BASE_R + MDIO_STAT1); - if (val < 0) - return val; - - if (val & MDIO_STAT1_LSTATUS) - return mv3310_read_10gbr_status(phydev); + int cssr1, speed, val; val = genphy_c45_read_link(phydev); if (val < 0) @@ -451,6 +443,52 @@ static int mv3310_read_status(struct phy_device *phydev) if (val < 0) return val; + cssr1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_CSSR1); + if (cssr1 < 0) + return val; + + /* If the link settings are not resolved, mark the link down */ + if (!(cssr1 & MV_PCS_CSSR1_RESOLVED)) { + phydev->link = 0; + return 0; + } + + /* Read the copper link settings */ + speed = cssr1 & MV_PCS_CSSR1_SPD1_MASK; + if (speed == MV_PCS_CSSR1_SPD1_SPD2) + speed |= cssr1 & MV_PCS_CSSR1_SPD2_MASK; + + switch (speed) { + case MV_PCS_CSSR1_SPD1_SPD2 | MV_PCS_CSSR1_SPD2_10000: + phydev->speed = SPEED_10000; + break; + + case MV_PCS_CSSR1_SPD1_SPD2 | MV_PCS_CSSR1_SPD2_5000: + phydev->speed = SPEED_5000; + break; + + case MV_PCS_CSSR1_SPD1_SPD2 | MV_PCS_CSSR1_SPD2_2500: + phydev->speed = SPEED_2500; + break; + + case MV_PCS_CSSR1_SPD1_1000: + phydev->speed = SPEED_1000; + break; + + case MV_PCS_CSSR1_SPD1_100: + phydev->speed = SPEED_100; + break; + + case MV_PCS_CSSR1_SPD1_10: + phydev->speed = SPEED_10; + break; + } + + phydev->duplex = cssr1 & MV_PCS_CSSR1_DUPLEX_FULL ? + DUPLEX_FULL : DUPLEX_HALF; + phydev->mdix = cssr1 & MV_PCS_CSSR1_MDIX ? + ETH_TP_MDI_X : ETH_TP_MDI; + if (val & MDIO_AN_STAT1_COMPLETE) { val = genphy_c45_read_lpa(phydev); if (val < 0) @@ -463,39 +501,38 @@ static int mv3310_read_status(struct phy_device *phydev) mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val); - if (phydev->autoneg == AUTONEG_ENABLE) - phy_resolve_aneg_linkmode(phydev); + /* Update the pause status */ + phy_resolve_aneg_pause(phydev); } - if (phydev->autoneg != AUTONEG_ENABLE) { - val = genphy_c45_read_pma(phydev); - if (val < 0) - return val; - } + return 0; +} - if (phydev->speed == SPEED_10000) { - val = genphy_c45_read_mdix(phydev); - if (val < 0) - return val; - } else { - val = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PAIRSWAP); - if (val < 0) - return val; +static int mv3310_read_status(struct phy_device *phydev) +{ + int err, val; - switch (val & MV_PCS_PAIRSWAP_MASK) { - case MV_PCS_PAIRSWAP_AB: - phydev->mdix = ETH_TP_MDI_X; - break; - case MV_PCS_PAIRSWAP_NONE: - phydev->mdix = ETH_TP_MDI; - break; - default: - phydev->mdix = ETH_TP_MDI_INVALID; - break; - } - } + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + linkmode_zero(phydev->lp_advertising); + phydev->link = 0; + phydev->pause = 0; + phydev->asym_pause = 0; + phydev->mdix = ETH_TP_MDI_INVALID; - mv3310_update_interface(phydev); + val = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_BASE_R + MDIO_STAT1); + if (val < 0) + return val; + + if (val & MDIO_STAT1_LSTATUS) + err = mv3310_read_status_10gbaser(phydev); + else + err = mv3310_read_status_copper(phydev); + if (err < 0) + return err; + + if (phydev->link) + mv3310_update_interface(phydev); return 0; } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 9bb9f37f21dc..3ab9ca7614d1 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -462,6 +462,23 @@ static struct class mdio_bus_class = { .dev_groups = mdio_bus_groups, }; +/** + * mdio_find_bus - Given the name of a mdiobus, find the mii_bus. + * @mdio_bus_np: Pointer to the mii_bus. + * + * Returns a reference to the mii_bus, or NULL if none found. The + * embedded struct device will have its reference count incremented, + * and this must be put_deviced'ed once the bus is finished with. + */ +struct mii_bus *mdio_find_bus(const char *mdio_name) +{ + struct device *d; + + d = class_find_device_by_name(&mdio_bus_class, mdio_name); + return d ? to_mii_bus(d) : NULL; +} +EXPORT_SYMBOL(mdio_find_bus); + #if IS_ENABLED(CONFIG_OF_MDIO) /** * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 937ac7da2789..d24577de0775 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -345,11 +345,11 @@ enum macsec_bank { BIT(VSC8531_FORCE_LED_OFF) | \ BIT(VSC8531_FORCE_LED_ON)) -#define MSCC_VSC8584_REVB_INT8051_FW "mscc_vsc8584_revb_int8051_fb48.bin" +#define MSCC_VSC8584_REVB_INT8051_FW "microchip/mscc_vsc8584_revb_int8051_fb48.bin" #define MSCC_VSC8584_REVB_INT8051_FW_START_ADDR 0xe800 #define MSCC_VSC8584_REVB_INT8051_FW_CRC 0xfb48 -#define MSCC_VSC8574_REVB_INT8051_FW "mscc_vsc8574_revb_int8051_29e8.bin" +#define MSCC_VSC8574_REVB_INT8051_FW "microchip/mscc_vsc8574_revb_int8051_29e8.bin" #define MSCC_VSC8574_REVB_INT8051_FW_START_ADDR 0x4000 #define MSCC_VSC8574_REVB_INT8051_FW_CRC 0x29e8 @@ -2813,8 +2813,8 @@ static int vsc8584_config_init(struct phy_device *phydev) val = phy_read(phydev, MSCC_PHY_EXT_PHY_CNTL_1); val &= ~(MEDIA_OP_MODE_MASK | VSC8584_MAC_IF_SELECTION_MASK); - val |= MEDIA_OP_MODE_COPPER | (VSC8584_MAC_IF_SELECTION_SGMII << - VSC8584_MAC_IF_SELECTION_POS); + val |= (MEDIA_OP_MODE_COPPER << MEDIA_OP_MODE_POS) | + (VSC8584_MAC_IF_SELECTION_SGMII << VSC8584_MAC_IF_SELECTION_POS); ret = phy_write(phydev, MSCC_PHY_EXT_PHY_CNTL_1, val); ret = genphy_soft_reset(phydev); @@ -3276,7 +3276,7 @@ static int vsc8514_config_init(struct phy_device *phydev) return ret; ret = phy_modify(phydev, MSCC_PHY_EXT_PHY_CNTL_1, MEDIA_OP_MODE_MASK, - MEDIA_OP_MODE_COPPER); + MEDIA_OP_MODE_COPPER << MEDIA_OP_MODE_POS); if (ret) return ret; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index bceb0dcdecbd..67ba47ae5284 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -167,7 +167,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg); */ int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) { - int ret = 0; + int ret; if (!restart) { /* Configure and restart aneg if it wasn't set before */ @@ -180,9 +180,9 @@ int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) } if (restart) - ret = genphy_c45_restart_aneg(phydev); + return genphy_c45_restart_aneg(phydev); - return ret; + return 0; } EXPORT_SYMBOL_GPL(genphy_c45_check_and_restart_aneg); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index be0129231c2a..7c00b029ebfb 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -247,7 +247,7 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) * MDIO bus driver and clock gated at this point. */ if (!netdev) - return !phydev->suspended; + goto out; if (netdev->wol_enabled) return false; @@ -267,7 +267,8 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) if (device_may_wakeup(&netdev->dev)) return false; - return true; +out: + return !phydev->suspended; } static int mdio_bus_phy_suspend(struct device *dev) @@ -1792,7 +1793,7 @@ EXPORT_SYMBOL(genphy_restart_aneg); */ int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart) { - int ret = 0; + int ret; if (!restart) { /* Advertisement hasn't changed, but maybe aneg was never on to @@ -1807,9 +1808,9 @@ int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart) } if (restart) - ret = genphy_restart_aneg(phydev); + return genphy_restart_aneg(phydev); - return ret; + return 0; } EXPORT_SYMBOL(genphy_check_and_restart_aneg); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 2899fbe699ab..b4367fab7899 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -480,8 +480,11 @@ static void phylink_mac_link_up(struct phylink *pl, struct net_device *ndev = pl->netdev; pl->cur_interface = link_state.interface; - pl->ops->mac_link_up(pl->config, pl->cur_link_an_mode, - pl->cur_interface, pl->phydev); + pl->ops->mac_link_up(pl->config, pl->phydev, + pl->cur_link_an_mode, pl->cur_interface, + link_state.speed, link_state.duplex, + !!(link_state.pause & MLO_PAUSE_TX), + !!(link_state.pause & MLO_PAUSE_RX)); if (ndev) netif_carrier_on(ndev); @@ -547,6 +550,8 @@ static void phylink_resolve(struct work_struct *w) link_state.pause = pl->phy_state.pause; phylink_apply_manual_flow(pl, &link_state); phylink_mac_config(pl, &link_state); + } else { + phylink_apply_manual_flow(pl, &link_state); } break; } diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 6f4d7ba8b109..babb01888b78 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -863,7 +863,10 @@ err_free_chan: tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); sl_free_netdev(sl->dev); + /* do not call free_netdev before rtnl_unlock */ + rtnl_unlock(); free_netdev(sl->dev); + return err; err_exit: rtnl_unlock(); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 650c937ed56b..79f248cb282d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1078,8 +1078,6 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len); - BUG_ON(!tfile); - /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3b7a3b8a5e06..5754bb6ca0ee 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -337,6 +337,9 @@ static void qmi_wwan_netdev_setup(struct net_device *net) netdev_dbg(net, "mode: raw IP\n"); } else if (!net->header_ops) { /* don't bother if already set */ ether_setup(net); + /* Restoring min/max mtu values set originally by usbnet */ + net->min_mtu = 0; + net->max_mtu = ETH_MAX_MTU; clear_bit(EVENT_NO_IP_ALIGN, &dev->flags); netdev_dbg(net, "mode: Ethernet\n"); } diff --git a/drivers/net/wan/farsync.h b/drivers/net/wan/farsync.h index 47b8e36f97ab..5f43568a9715 100644 --- a/drivers/net/wan/farsync.h +++ b/drivers/net/wan/farsync.h @@ -65,7 +65,7 @@ struct fstioc_write { unsigned int size; unsigned int offset; - unsigned char data[0]; + unsigned char data[]; }; diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index 23f93f1c815d..499f7cd19a4a 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -78,7 +78,7 @@ struct card { struct sk_buff *rx_skbs[RX_QUEUE_LENGTH]; struct card_status *status; /* shared between host and card */ dma_addr_t status_address; - struct port ports[0]; /* 1 - 4 port structures follow */ + struct port ports[]; /* 1 - 4 port structures follow */ }; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 05464b5629d5..da0a6b6c4771 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2947,6 +2947,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, NL80211_FEATURE_DYNAMIC_SMPS | NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_VHT_IBSS); + wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION); hw->wiphy->interface_modes = param->iftypes; diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index 0cc9ac856fe2..7c0b1e6b80ff 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -76,7 +76,7 @@ static u8 nci_core_get_config_otp_ram_version[5] = { struct nci_core_get_config_rsp { u8 status; u8 count; - u8 data[0]; + u8 data[]; }; static int fdp_nci_create_conn(struct nci_dev *ndev) diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index 60acdfd1cb8c..a1d69f9b2d4a 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -66,7 +66,7 @@ struct st21nfca_atr_req { u8 bsi; u8 bri; u8 ppi; - u8 gbi[0]; + u8 gbi[]; } __packed; struct st21nfca_atr_res { @@ -79,7 +79,7 @@ struct st21nfca_atr_res { u8 bri; u8 to; u8 ppi; - u8 gbi[0]; + u8 gbi[]; } __packed; struct st21nfca_psl_req { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ada59df642d2..a4d8c90ee7cc 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1165,8 +1165,8 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result) { + union nvme_result res = { 0 }; struct nvme_command c; - union nvme_result res; int ret; memset(&c, 0, sizeof(c)); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 797c18337d96..a11900cf3a36 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -715,6 +715,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) } INIT_WORK(&ctrl->ana_work, nvme_ana_work); + kfree(ctrl->ana_log_buf); ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL); if (!ctrl->ana_log_buf) { error = -ENOMEM; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9c80f9f08149..ace4dd9e953c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2747,6 +2747,18 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) (dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") || dmi_match(DMI_BOARD_NAME, "PRIME Z370-A"))) return NVME_QUIRK_NO_APST; + } else if ((pdev->vendor == 0x144d && (pdev->device == 0xa801 || + pdev->device == 0xa808 || pdev->device == 0xa809)) || + (pdev->vendor == 0x1e0f && pdev->device == 0x0001)) { + /* + * Forcing to use host managed nvme power settings for + * lowest idle power with quick resume latency on + * Samsung and Toshiba SSDs based on suspend behavior + * on Coffee Lake board for LENOVO C640 + */ + if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) && + dmi_match(DMI_BOARD_NAME, "LNVNB161216")) + return NVME_QUIRK_SIMPLE_SUSPEND; } return 0; @@ -3109,7 +3121,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, - { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, + { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), + .driver_data = NVME_QUIRK_SINGLE_VECTOR }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005), .driver_data = NVME_QUIRK_SINGLE_VECTOR | diff --git a/drivers/platform/chrome/wilco_ec/properties.c b/drivers/platform/chrome/wilco_ec/properties.c index e69682c95ea2..62f27610dd33 100644 --- a/drivers/platform/chrome/wilco_ec/properties.c +++ b/drivers/platform/chrome/wilco_ec/properties.c @@ -5,7 +5,7 @@ #include <linux/platform_data/wilco-ec.h> #include <linux/string.h> -#include <linux/unaligned/le_memmove.h> +#include <asm/unaligned.h> /* Operation code; what the EC should do with the property */ enum ec_property_op { diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 475c60dccaa4..3b424ffceb83 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -115,6 +115,18 @@ config PTP_1588_CLOCK_KVM To compile this driver as a module, choose M here: the module will be called ptp_kvm. +config PTP_1588_CLOCK_IDT82P33 + tristate "IDT 82P33xxx PTP clock" + depends on PTP_1588_CLOCK && I2C + default n + help + This driver adds support for using the IDT 82P33xxx as a PTP + clock. This clock is only useful if your time stamping MAC + is connected to the IDT chip. + + To compile this driver as a module, choose M here: the module + will be called ptp_idt82p33. + config PTP_1588_CLOCK_IDTCM tristate "IDT CLOCKMATRIX as PTP clock" depends on PTP_1588_CLOCK && I2C diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 8c830336f178..01ff7fc3e820 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -13,3 +13,4 @@ obj-$(CONFIG_PTP_1588_CLOCK_QORIQ) += ptp-qoriq.o ptp-qoriq-y += ptp_qoriq.o ptp-qoriq-$(CONFIG_DEBUG_FS) += ptp_qoriq_debugfs.o obj-$(CONFIG_PTP_1588_CLOCK_IDTCM) += ptp_clockmatrix.o +obj-$(CONFIG_PTP_1588_CLOCK_IDT82P33) += ptp_idt82p33.o diff --git a/drivers/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c new file mode 100644 index 000000000000..b63ac240308b --- /dev/null +++ b/drivers/ptp/ptp_idt82p33.c @@ -0,0 +1,1008 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright (C) 2018 Integrated Device Technology, Inc +// + +#define pr_fmt(fmt) "IDT_82p33xxx: " fmt + +#include <linux/firmware.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/timekeeping.h> +#include <linux/bitops.h> + +#include "ptp_private.h" +#include "ptp_idt82p33.h" + +MODULE_DESCRIPTION("Driver for IDT 82p33xxx clock devices"); +MODULE_AUTHOR("IDT support-1588 <IDT-support-1588@lm.renesas.com>"); +MODULE_VERSION("1.0"); +MODULE_LICENSE("GPL"); + +/* Module Parameters */ +u32 sync_tod_timeout = SYNC_TOD_TIMEOUT_SEC; +module_param(sync_tod_timeout, uint, 0); +MODULE_PARM_DESC(sync_tod_timeout, +"duration in second to keep SYNC_TOD on (set to 0 to keep it always on)"); + +u32 phase_snap_threshold = SNAP_THRESHOLD_NS; +module_param(phase_snap_threshold, uint, 0); +MODULE_PARM_DESC(phase_snap_threshold, +"threshold (150000ns by default) below which adjtime would ignore"); + +static void idt82p33_byte_array_to_timespec(struct timespec64 *ts, + u8 buf[TOD_BYTE_COUNT]) +{ + time64_t sec; + s32 nsec; + u8 i; + + nsec = buf[3]; + for (i = 0; i < 3; i++) { + nsec <<= 8; + nsec |= buf[2 - i]; + } + + sec = buf[9]; + for (i = 0; i < 5; i++) { + sec <<= 8; + sec |= buf[8 - i]; + } + + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} + +static void idt82p33_timespec_to_byte_array(struct timespec64 const *ts, + u8 buf[TOD_BYTE_COUNT]) +{ + time64_t sec; + s32 nsec; + u8 i; + + nsec = ts->tv_nsec; + sec = ts->tv_sec; + + for (i = 0; i < 4; i++) { + buf[i] = nsec & 0xff; + nsec >>= 8; + } + + for (i = 4; i < TOD_BYTE_COUNT; i++) { + buf[i] = sec & 0xff; + sec >>= 8; + } +} + +static int idt82p33_xfer(struct idt82p33 *idt82p33, + unsigned char regaddr, + unsigned char *buf, + unsigned int count, + int write) +{ + struct i2c_client *client = idt82p33->client; + struct i2c_msg msg[2]; + int cnt; + + msg[0].addr = client->addr; + msg[0].flags = 0; + msg[0].len = 1; + msg[0].buf = ®addr; + + msg[1].addr = client->addr; + msg[1].flags = write ? 0 : I2C_M_RD; + msg[1].len = count; + msg[1].buf = buf; + + cnt = i2c_transfer(client->adapter, msg, 2); + if (cnt < 0) { + dev_err(&client->dev, "i2c_transfer returned %d\n", cnt); + return cnt; + } else if (cnt != 2) { + dev_err(&client->dev, + "i2c_transfer sent only %d of %d messages\n", cnt, 2); + return -EIO; + } + return 0; +} + +static int idt82p33_page_offset(struct idt82p33 *idt82p33, unsigned char val) +{ + int err; + + if (idt82p33->page_offset == val) + return 0; + + err = idt82p33_xfer(idt82p33, PAGE_ADDR, &val, sizeof(val), 1); + if (err) + dev_err(&idt82p33->client->dev, + "failed to set page offset %d\n", val); + else + idt82p33->page_offset = val; + + return err; +} + +static int idt82p33_rdwr(struct idt82p33 *idt82p33, unsigned int regaddr, + unsigned char *buf, unsigned int count, bool write) +{ + u8 offset, page; + int err; + + page = _PAGE(regaddr); + offset = _OFFSET(regaddr); + + err = idt82p33_page_offset(idt82p33, page); + if (err) + goto out; + + err = idt82p33_xfer(idt82p33, offset, buf, count, write); +out: + return err; +} + +static int idt82p33_read(struct idt82p33 *idt82p33, unsigned int regaddr, + unsigned char *buf, unsigned int count) +{ + return idt82p33_rdwr(idt82p33, regaddr, buf, count, false); +} + +static int idt82p33_write(struct idt82p33 *idt82p33, unsigned int regaddr, + unsigned char *buf, unsigned int count) +{ + return idt82p33_rdwr(idt82p33, regaddr, buf, count, true); +} + +static int idt82p33_dpll_set_mode(struct idt82p33_channel *channel, + enum pll_mode mode) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 dpll_mode; + int err; + + if (channel->pll_mode == mode) + return 0; + + err = idt82p33_read(idt82p33, channel->dpll_mode_cnfg, + &dpll_mode, sizeof(dpll_mode)); + if (err) + return err; + + dpll_mode &= ~(PLL_MODE_MASK << PLL_MODE_SHIFT); + + dpll_mode |= (mode << PLL_MODE_SHIFT); + + err = idt82p33_write(idt82p33, channel->dpll_mode_cnfg, + &dpll_mode, sizeof(dpll_mode)); + if (err) + return err; + + channel->pll_mode = dpll_mode; + + return 0; +} + +static int _idt82p33_gettime(struct idt82p33_channel *channel, + struct timespec64 *ts) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 buf[TOD_BYTE_COUNT]; + u8 trigger; + int err; + + trigger = TOD_TRIGGER(HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS); + + + err = idt82p33_write(idt82p33, channel->dpll_tod_trigger, + &trigger, sizeof(trigger)); + + if (err) + return err; + + if (idt82p33->calculate_overhead_flag) + idt82p33->start_time = ktime_get_raw(); + + err = idt82p33_read(idt82p33, channel->dpll_tod_sts, buf, sizeof(buf)); + + if (err) + return err; + + idt82p33_byte_array_to_timespec(ts, buf); + + return 0; +} + +/* + * TOD Trigger: + * Bits[7:4] Write 0x9, MSB write + * Bits[3:0] Read 0x9, LSB read + */ + +static int _idt82p33_settime(struct idt82p33_channel *channel, + struct timespec64 const *ts) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + struct timespec64 local_ts = *ts; + char buf[TOD_BYTE_COUNT]; + s64 dynamic_overhead_ns; + unsigned char trigger; + int err; + u8 i; + + trigger = TOD_TRIGGER(HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS); + + err = idt82p33_write(idt82p33, channel->dpll_tod_trigger, + &trigger, sizeof(trigger)); + + if (err) + return err; + + if (idt82p33->calculate_overhead_flag) { + dynamic_overhead_ns = ktime_to_ns(ktime_get_raw()) + - ktime_to_ns(idt82p33->start_time); + + timespec64_add_ns(&local_ts, dynamic_overhead_ns); + + idt82p33->calculate_overhead_flag = 0; + } + + idt82p33_timespec_to_byte_array(&local_ts, buf); + + /* + * Store the new time value. + */ + for (i = 0; i < TOD_BYTE_COUNT; i++) { + err = idt82p33_write(idt82p33, channel->dpll_tod_cnfg + i, + &buf[i], sizeof(buf[i])); + if (err) + return err; + } + + return err; +} + +static int _idt82p33_adjtime(struct idt82p33_channel *channel, s64 delta_ns) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + struct timespec64 ts; + s64 now_ns; + int err; + + idt82p33->calculate_overhead_flag = 1; + + err = _idt82p33_gettime(channel, &ts); + + if (err) + return err; + + now_ns = timespec64_to_ns(&ts); + now_ns += delta_ns + idt82p33->tod_write_overhead_ns; + + ts = ns_to_timespec64(now_ns); + + err = _idt82p33_settime(channel, &ts); + + return err; +} + +static int _idt82p33_adjfine(struct idt82p33_channel *channel, long scaled_ppm) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + unsigned char buf[5] = {0}; + int neg_adj = 0; + int err, i; + s64 fcw; + + if (scaled_ppm == channel->current_freq_ppb) + return 0; + + /* + * Frequency Control Word unit is: 1.68 * 10^-10 ppm + * + * adjfreq: + * ppb * 10^9 + * FCW = ---------- + * 168 + * + * adjfine: + * scaled_ppm * 5^12 + * FCW = ------------- + * 168 * 2^4 + */ + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + + fcw = scaled_ppm * 244140625ULL; + fcw = div_u64(fcw, 2688); + + if (neg_adj) + fcw = -fcw; + + for (i = 0; i < 5; i++) { + buf[i] = fcw & 0xff; + fcw >>= 8; + } + + err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO); + + if (err) + return err; + + err = idt82p33_write(idt82p33, channel->dpll_freq_cnfg, + buf, sizeof(buf)); + + if (err == 0) + channel->current_freq_ppb = scaled_ppm; + + return err; +} + +static int idt82p33_measure_one_byte_write_overhead( + struct idt82p33_channel *channel, s64 *overhead_ns) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + ktime_t start, stop; + s64 total_ns; + u8 trigger; + int err; + u8 i; + + total_ns = 0; + *overhead_ns = 0; + trigger = TOD_TRIGGER(HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS); + + for (i = 0; i < MAX_MEASURMENT_COUNT; i++) { + + start = ktime_get_raw(); + + err = idt82p33_write(idt82p33, channel->dpll_tod_trigger, + &trigger, sizeof(trigger)); + + stop = ktime_get_raw(); + + if (err) + return err; + + total_ns += ktime_to_ns(stop) - ktime_to_ns(start); + } + + *overhead_ns = div_s64(total_ns, MAX_MEASURMENT_COUNT); + + return err; +} + +static int idt82p33_measure_tod_write_9_byte_overhead( + struct idt82p33_channel *channel) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 buf[TOD_BYTE_COUNT]; + ktime_t start, stop; + s64 total_ns; + int err = 0; + u8 i, j; + + total_ns = 0; + idt82p33->tod_write_overhead_ns = 0; + + for (i = 0; i < MAX_MEASURMENT_COUNT; i++) { + + start = ktime_get_raw(); + + /* Need one less byte for applicable overhead */ + for (j = 0; j < (TOD_BYTE_COUNT - 1); j++) { + err = idt82p33_write(idt82p33, + channel->dpll_tod_cnfg + i, + &buf[i], sizeof(buf[i])); + if (err) + return err; + } + + stop = ktime_get_raw(); + + total_ns += ktime_to_ns(stop) - ktime_to_ns(start); + } + + idt82p33->tod_write_overhead_ns = div_s64(total_ns, + MAX_MEASURMENT_COUNT); + + return err; +} + +static int idt82p33_measure_settime_gettime_gap_overhead( + struct idt82p33_channel *channel, s64 *overhead_ns) +{ + struct timespec64 ts1 = {0, 0}; + struct timespec64 ts2; + int err; + + *overhead_ns = 0; + + err = _idt82p33_settime(channel, &ts1); + + if (err) + return err; + + err = _idt82p33_gettime(channel, &ts2); + + if (!err) + *overhead_ns = timespec64_to_ns(&ts2) - timespec64_to_ns(&ts1); + + return err; +} + +static int idt82p33_measure_tod_write_overhead(struct idt82p33_channel *channel) +{ + s64 trailing_overhead_ns, one_byte_write_ns, gap_ns; + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + idt82p33->tod_write_overhead_ns = 0; + + err = idt82p33_measure_settime_gettime_gap_overhead(channel, &gap_ns); + + if (err) + return err; + + err = idt82p33_measure_one_byte_write_overhead(channel, + &one_byte_write_ns); + + if (err) + return err; + + err = idt82p33_measure_tod_write_9_byte_overhead(channel); + + if (err) + return err; + + trailing_overhead_ns = gap_ns - (2 * one_byte_write_ns); + + idt82p33->tod_write_overhead_ns -= trailing_overhead_ns; + + return err; +} + +static int idt82p33_check_and_set_masks(struct idt82p33 *idt82p33, + u8 page, + u8 offset, + u8 val) +{ + int err = 0; + + if (page == PLLMASK_ADDR_HI && offset == PLLMASK_ADDR_LO) { + if ((val & 0xfc) || !(val & 0x3)) { + dev_err(&idt82p33->client->dev, + "Invalid PLL mask 0x%hhx\n", val); + err = -EINVAL; + } else { + idt82p33->pll_mask = val; + } + } else if (page == PLL0_OUTMASK_ADDR_HI && + offset == PLL0_OUTMASK_ADDR_LO) { + idt82p33->channel[0].output_mask = val; + } else if (page == PLL1_OUTMASK_ADDR_HI && + offset == PLL1_OUTMASK_ADDR_LO) { + idt82p33->channel[1].output_mask = val; + } + + return err; +} + +static void idt82p33_display_masks(struct idt82p33 *idt82p33) +{ + u8 mask, i; + + dev_info(&idt82p33->client->dev, + "pllmask = 0x%02x\n", idt82p33->pll_mask); + + for (i = 0; i < MAX_PHC_PLL; i++) { + mask = 1 << i; + + if (mask & idt82p33->pll_mask) + dev_info(&idt82p33->client->dev, + "PLL%d output_mask = 0x%04x\n", + i, idt82p33->channel[i].output_mask); + } +} + +static int idt82p33_sync_tod(struct idt82p33_channel *channel, bool enable) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 sync_cnfg; + int err; + + if (enable == channel->sync_tod_on) { + if (enable && sync_tod_timeout) { + mod_delayed_work(system_wq, &channel->sync_tod_work, + sync_tod_timeout * HZ); + } + return 0; + } + + err = idt82p33_read(idt82p33, channel->dpll_sync_cnfg, + &sync_cnfg, sizeof(sync_cnfg)); + if (err) + return err; + + sync_cnfg &= ~SYNC_TOD; + + if (enable) + sync_cnfg |= SYNC_TOD; + + err = idt82p33_write(idt82p33, channel->dpll_sync_cnfg, + &sync_cnfg, sizeof(sync_cnfg)); + if (err) + return err; + + channel->sync_tod_on = enable; + + if (enable && sync_tod_timeout) { + mod_delayed_work(system_wq, &channel->sync_tod_work, + sync_tod_timeout * HZ); + } + + return 0; +} + +static void idt82p33_sync_tod_work_handler(struct work_struct *work) +{ + struct idt82p33_channel *channel = + container_of(work, struct idt82p33_channel, sync_tod_work.work); + struct idt82p33 *idt82p33 = channel->idt82p33; + + mutex_lock(&idt82p33->reg_lock); + + (void)idt82p33_sync_tod(channel, false); + + mutex_unlock(&idt82p33->reg_lock); +} + +static int idt82p33_pps_enable(struct idt82p33_channel *channel, bool enable) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 mask, outn, val; + int err; + + mask = channel->output_mask; + outn = 0; + + while (mask) { + if (mask & 0x1) { + err = idt82p33_read(idt82p33, OUT_MUX_CNFG(outn), + &val, sizeof(val)); + if (err) + return err; + + if (enable) + val &= ~SQUELCH_ENABLE; + else + val |= SQUELCH_ENABLE; + + err = idt82p33_write(idt82p33, OUT_MUX_CNFG(outn), + &val, sizeof(val)); + + if (err) + return err; + } + mask >>= 0x1; + outn++; + } + + return 0; +} + +static int idt82p33_enable_tod(struct idt82p33_channel *channel) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + struct timespec64 ts = {0, 0}; + int err; + u8 val; + + val = 0; + err = idt82p33_write(idt82p33, channel->dpll_input_mode_cnfg, + &val, sizeof(val)); + if (err) + return err; + + err = idt82p33_pps_enable(channel, false); + + if (err) + return err; + + err = idt82p33_measure_tod_write_overhead(channel); + + if (err) + return err; + + err = _idt82p33_settime(channel, &ts); + + if (err) + return err; + + return idt82p33_sync_tod(channel, true); +} + +static void idt82p33_ptp_clock_unregister_all(struct idt82p33 *idt82p33) +{ + struct idt82p33_channel *channel; + u8 i; + + for (i = 0; i < MAX_PHC_PLL; i++) { + + channel = &idt82p33->channel[i]; + + if (channel->ptp_clock) { + ptp_clock_unregister(channel->ptp_clock); + cancel_delayed_work_sync(&channel->sync_tod_work); + } + } +} + +static int idt82p33_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + err = -EOPNOTSUPP; + + mutex_lock(&idt82p33->reg_lock); + + if (rq->type == PTP_CLK_REQ_PEROUT) { + if (!on) + err = idt82p33_pps_enable(channel, false); + + /* Only accept a 1-PPS aligned to the second. */ + else if (rq->perout.start.nsec || rq->perout.period.sec != 1 || + rq->perout.period.nsec) { + err = -ERANGE; + } else + err = idt82p33_pps_enable(channel, true); + } + + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + err = _idt82p33_adjfine(channel, scaled_ppm); + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_adjtime(struct ptp_clock_info *ptp, s64 delta_ns) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + + if (abs(delta_ns) < phase_snap_threshold) { + mutex_unlock(&idt82p33->reg_lock); + return 0; + } + + err = _idt82p33_adjtime(channel, delta_ns); + + if (err) { + mutex_unlock(&idt82p33->reg_lock); + return err; + } + + err = idt82p33_sync_tod(channel, true); + + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + err = _idt82p33_gettime(channel, ts); + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + err = _idt82p33_settime(channel, ts); + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_channel_init(struct idt82p33_channel *channel, int index) +{ + switch (index) { + case 0: + channel->dpll_tod_cnfg = DPLL1_TOD_CNFG; + channel->dpll_tod_trigger = DPLL1_TOD_TRIGGER; + channel->dpll_tod_sts = DPLL1_TOD_STS; + channel->dpll_mode_cnfg = DPLL1_OPERATING_MODE_CNFG; + channel->dpll_freq_cnfg = DPLL1_HOLDOVER_FREQ_CNFG; + channel->dpll_phase_cnfg = DPLL1_PHASE_OFFSET_CNFG; + channel->dpll_sync_cnfg = DPLL1_SYNC_EDGE_CNFG; + channel->dpll_input_mode_cnfg = DPLL1_INPUT_MODE_CNFG; + break; + case 1: + channel->dpll_tod_cnfg = DPLL2_TOD_CNFG; + channel->dpll_tod_trigger = DPLL2_TOD_TRIGGER; + channel->dpll_tod_sts = DPLL2_TOD_STS; + channel->dpll_mode_cnfg = DPLL2_OPERATING_MODE_CNFG; + channel->dpll_freq_cnfg = DPLL2_HOLDOVER_FREQ_CNFG; + channel->dpll_phase_cnfg = DPLL2_PHASE_OFFSET_CNFG; + channel->dpll_sync_cnfg = DPLL2_SYNC_EDGE_CNFG; + channel->dpll_input_mode_cnfg = DPLL2_INPUT_MODE_CNFG; + break; + default: + return -EINVAL; + } + + INIT_DELAYED_WORK(&channel->sync_tod_work, + idt82p33_sync_tod_work_handler); + channel->sync_tod_on = false; + channel->current_freq_ppb = 0; + + return 0; +} + +static void idt82p33_caps_init(struct ptp_clock_info *caps) +{ + caps->owner = THIS_MODULE; + caps->max_adj = 92000; + caps->adjfine = idt82p33_adjfine; + caps->adjtime = idt82p33_adjtime; + caps->gettime64 = idt82p33_gettime; + caps->settime64 = idt82p33_settime; + caps->enable = idt82p33_enable; +} + +static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index) +{ + struct idt82p33_channel *channel; + int err; + + if (!(index < MAX_PHC_PLL)) + return -EINVAL; + + channel = &idt82p33->channel[index]; + + err = idt82p33_channel_init(channel, index); + if (err) + return err; + + channel->idt82p33 = idt82p33; + + idt82p33_caps_init(&channel->caps); + snprintf(channel->caps.name, sizeof(channel->caps.name), + "IDT 82P33 PLL%u", index); + channel->caps.n_per_out = hweight8(channel->output_mask); + + err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO); + if (err) + return err; + + err = idt82p33_enable_tod(channel); + if (err) + return err; + + channel->ptp_clock = ptp_clock_register(&channel->caps, NULL); + + if (IS_ERR(channel->ptp_clock)) { + err = PTR_ERR(channel->ptp_clock); + channel->ptp_clock = NULL; + return err; + } + + if (!channel->ptp_clock) + return -ENOTSUPP; + + dev_info(&idt82p33->client->dev, "PLL%d registered as ptp%d\n", + index, channel->ptp_clock->index); + + return 0; +} + +static int idt82p33_load_firmware(struct idt82p33 *idt82p33) +{ + const struct firmware *fw; + struct idt82p33_fwrc *rec; + u8 loaddr, page, val; + int err; + s32 len; + + dev_dbg(&idt82p33->client->dev, + "requesting firmware '%s'\n", FW_FILENAME); + + err = request_firmware(&fw, FW_FILENAME, &idt82p33->client->dev); + + if (err) + return err; + + dev_dbg(&idt82p33->client->dev, "firmware size %zu bytes\n", fw->size); + + rec = (struct idt82p33_fwrc *) fw->data; + + for (len = fw->size; len > 0; len -= sizeof(*rec)) { + + if (rec->reserved) { + dev_err(&idt82p33->client->dev, + "bad firmware, reserved field non-zero\n"); + err = -EINVAL; + } else { + val = rec->value; + loaddr = rec->loaddr; + page = rec->hiaddr; + + rec++; + + err = idt82p33_check_and_set_masks(idt82p33, page, + loaddr, val); + } + + if (err == 0) { + /* maximum 8 pages */ + if (page >= PAGE_NUM) + continue; + + /* Page size 128, last 4 bytes of page skipped */ + if (((loaddr > 0x7b) && (loaddr <= 0x7f)) + || ((loaddr > 0xfb) && (loaddr <= 0xff))) + continue; + + err = idt82p33_write(idt82p33, _ADDR(page, loaddr), + &val, sizeof(val)); + } + + if (err) + goto out; + } + + idt82p33_display_masks(idt82p33); +out: + release_firmware(fw); + return err; +} + + +static int idt82p33_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct idt82p33 *idt82p33; + int err; + u8 i; + + (void)id; + + idt82p33 = devm_kzalloc(&client->dev, + sizeof(struct idt82p33), GFP_KERNEL); + if (!idt82p33) + return -ENOMEM; + + mutex_init(&idt82p33->reg_lock); + + idt82p33->client = client; + idt82p33->page_offset = 0xff; + idt82p33->tod_write_overhead_ns = 0; + idt82p33->calculate_overhead_flag = 0; + idt82p33->pll_mask = DEFAULT_PLL_MASK; + idt82p33->channel[0].output_mask = DEFAULT_OUTPUT_MASK_PLL0; + idt82p33->channel[1].output_mask = DEFAULT_OUTPUT_MASK_PLL1; + + mutex_lock(&idt82p33->reg_lock); + + err = idt82p33_load_firmware(idt82p33); + + if (err) + dev_warn(&idt82p33->client->dev, + "loading firmware failed with %d\n", err); + + if (idt82p33->pll_mask) { + for (i = 0; i < MAX_PHC_PLL; i++) { + if (idt82p33->pll_mask & (1 << i)) { + err = idt82p33_enable_channel(idt82p33, i); + if (err) + break; + } + } + } else { + dev_err(&idt82p33->client->dev, + "no PLLs flagged as PHCs, nothing to do\n"); + err = -ENODEV; + } + + mutex_unlock(&idt82p33->reg_lock); + + if (err) { + idt82p33_ptp_clock_unregister_all(idt82p33); + return err; + } + + i2c_set_clientdata(client, idt82p33); + + return 0; +} + +static int idt82p33_remove(struct i2c_client *client) +{ + struct idt82p33 *idt82p33 = i2c_get_clientdata(client); + + idt82p33_ptp_clock_unregister_all(idt82p33); + mutex_destroy(&idt82p33->reg_lock); + + return 0; +} + +#ifdef CONFIG_OF +static const struct of_device_id idt82p33_dt_id[] = { + { .compatible = "idt,82p33810" }, + { .compatible = "idt,82p33813" }, + { .compatible = "idt,82p33814" }, + { .compatible = "idt,82p33831" }, + { .compatible = "idt,82p33910" }, + { .compatible = "idt,82p33913" }, + { .compatible = "idt,82p33914" }, + { .compatible = "idt,82p33931" }, + {}, +}; +MODULE_DEVICE_TABLE(of, idt82p33_dt_id); +#endif + +static const struct i2c_device_id idt82p33_i2c_id[] = { + { "idt82p33810", }, + { "idt82p33813", }, + { "idt82p33814", }, + { "idt82p33831", }, + { "idt82p33910", }, + { "idt82p33913", }, + { "idt82p33914", }, + { "idt82p33931", }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, idt82p33_i2c_id); + +static struct i2c_driver idt82p33_driver = { + .driver = { + .of_match_table = of_match_ptr(idt82p33_dt_id), + .name = "idt82p33", + }, + .probe = idt82p33_probe, + .remove = idt82p33_remove, + .id_table = idt82p33_i2c_id, +}; + +module_i2c_driver(idt82p33_driver); diff --git a/drivers/ptp/ptp_idt82p33.h b/drivers/ptp/ptp_idt82p33.h new file mode 100644 index 000000000000..9d46966d25f1 --- /dev/null +++ b/drivers/ptp/ptp_idt82p33.h @@ -0,0 +1,171 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * PTP hardware clock driver for the IDT 82P33XXX family of clocks. + * + * Copyright (C) 2019 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef PTP_IDT82P33_H +#define PTP_IDT82P33_H + +#include <linux/ktime.h> +#include <linux/workqueue.h> + + +/* Register Map - AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf */ +#define PAGE_NUM (8) +#define _ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) +#define _PAGE(addr) (((addr) >> 0x7) & 0x7) +#define _OFFSET(addr) ((addr) & 0x7f) + +#define DPLL1_TOD_CNFG 0x134 +#define DPLL2_TOD_CNFG 0x1B4 + +#define DPLL1_TOD_STS 0x10B +#define DPLL2_TOD_STS 0x18B + +#define DPLL1_TOD_TRIGGER 0x115 +#define DPLL2_TOD_TRIGGER 0x195 + +#define DPLL1_OPERATING_MODE_CNFG 0x120 +#define DPLL2_OPERATING_MODE_CNFG 0x1A0 + +#define DPLL1_HOLDOVER_FREQ_CNFG 0x12C +#define DPLL2_HOLDOVER_FREQ_CNFG 0x1AC + +#define DPLL1_PHASE_OFFSET_CNFG 0x143 +#define DPLL2_PHASE_OFFSET_CNFG 0x1C3 + +#define DPLL1_SYNC_EDGE_CNFG 0X140 +#define DPLL2_SYNC_EDGE_CNFG 0X1C0 + +#define DPLL1_INPUT_MODE_CNFG 0X116 +#define DPLL2_INPUT_MODE_CNFG 0X196 + +#define OUT_MUX_CNFG(outn) _ADDR(0x6, (0xC * (outn))) + +#define PAGE_ADDR 0x7F +/* Register Map end */ + +/* Register definitions - AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf*/ +#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) +#define SYNC_TOD BIT(1) +#define PH_OFFSET_EN BIT(7) +#define SQUELCH_ENABLE BIT(5) + +/* Bit definitions for the DPLL_MODE register */ +#define PLL_MODE_SHIFT (0) +#define PLL_MODE_MASK (0x1F) + +enum pll_mode { + PLL_MODE_MIN = 0, + PLL_MODE_AUTOMATIC = PLL_MODE_MIN, + PLL_MODE_FORCE_FREERUN = 1, + PLL_MODE_FORCE_HOLDOVER = 2, + PLL_MODE_FORCE_LOCKED = 4, + PLL_MODE_FORCE_PRE_LOCKED2 = 5, + PLL_MODE_FORCE_PRE_LOCKED = 6, + PLL_MODE_FORCE_LOST_PHASE = 7, + PLL_MODE_DCO = 10, + PLL_MODE_WPH = 18, + PLL_MODE_MAX = PLL_MODE_WPH, +}; + +enum hw_tod_trig_sel { + HW_TOD_TRIG_SEL_MIN = 0, + HW_TOD_TRIG_SEL_NO_WRITE = HW_TOD_TRIG_SEL_MIN, + HW_TOD_TRIG_SEL_SYNC_SEL = 1, + HW_TOD_TRIG_SEL_IN12 = 2, + HW_TOD_TRIG_SEL_IN13 = 3, + HW_TOD_TRIG_SEL_IN14 = 4, + HW_TOD_TRIG_SEL_TOD_PPS = 5, + HW_TOD_TRIG_SEL_TIMER_INTERVAL = 6, + HW_TOD_TRIG_SEL_MSB_PHASE_OFFSET_CNFG = 7, + HW_TOD_TRIG_SEL_MSB_HOLDOVER_FREQ_CNFG = 8, + HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG = 9, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, +}; + +/* Register bit definitions end */ +#define FW_FILENAME "idt82p33xxx.bin" +#define MAX_PHC_PLL (2) +#define TOD_BYTE_COUNT (10) +#define MAX_MEASURMENT_COUNT (5) +#define SNAP_THRESHOLD_NS (150000) +#define SYNC_TOD_TIMEOUT_SEC (5) + +#define PLLMASK_ADDR_HI 0xFF +#define PLLMASK_ADDR_LO 0xA5 + +#define PLL0_OUTMASK_ADDR_HI 0xFF +#define PLL0_OUTMASK_ADDR_LO 0xB0 + +#define PLL1_OUTMASK_ADDR_HI 0xFF +#define PLL1_OUTMASK_ADDR_LO 0xB2 + +#define PLL2_OUTMASK_ADDR_HI 0xFF +#define PLL2_OUTMASK_ADDR_LO 0xB4 + +#define PLL3_OUTMASK_ADDR_HI 0xFF +#define PLL3_OUTMASK_ADDR_LO 0xB6 + +#define DEFAULT_PLL_MASK (0x01) +#define DEFAULT_OUTPUT_MASK_PLL0 (0xc0) +#define DEFAULT_OUTPUT_MASK_PLL1 DEFAULT_OUTPUT_MASK_PLL0 + +/* PTP Hardware Clock interface */ +struct idt82p33_channel { + struct ptp_clock_info caps; + struct ptp_clock *ptp_clock; + struct idt82p33 *idt82p33; + enum pll_mode pll_mode; + /* task to turn off SYNC_TOD bit after pps sync */ + struct delayed_work sync_tod_work; + bool sync_tod_on; + s32 current_freq_ppb; + u8 output_mask; + u16 dpll_tod_cnfg; + u16 dpll_tod_trigger; + u16 dpll_tod_sts; + u16 dpll_mode_cnfg; + u16 dpll_freq_cnfg; + u16 dpll_phase_cnfg; + u16 dpll_sync_cnfg; + u16 dpll_input_mode_cnfg; +}; + +struct idt82p33 { + struct idt82p33_channel channel[MAX_PHC_PLL]; + struct i2c_client *client; + u8 page_offset; + u8 pll_mask; + ktime_t start_time; + int calculate_overhead_flag; + s64 tod_write_overhead_ns; + /* Protects I2C read/modify/write registers from concurrent access */ + struct mutex reg_lock; +}; + +/* firmware interface */ +struct idt82p33_fwrc { + u8 hiaddr; + u8 loaddr; + u8 value; + u8 reserved; +} __packed; + +/** + * @brief Maximum absolute value for write phase offset in femtoseconds + */ +#define WRITE_PHASE_OFFSET_LIMIT (20000052084ll) + +/** @brief Phase offset resolution + * + * DPLL phase offset = 10^15 fs / ( System Clock * 2^13) + * = 10^15 fs / ( 1638400000 * 2^23) + * = 74.5058059692382 fs + */ +#define IDT_T0DPLL_PHASE_RESOL 74506 + + +#endif /* PTP_IDT82P33_H */ diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index da642e811f7f..4dd2eb634856 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -303,8 +303,10 @@ static void * cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) { struct ccwdev_iter *iter; + loff_t p = *offset; - if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) + (*offset)++; + if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) return NULL; iter = it; if (iter->devno == __MAX_SUBCHANNEL) { @@ -314,7 +316,6 @@ cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) return NULL; } else iter->devno++; - (*offset)++; return iter; } diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 51038ec309c1..dfcbe54591fb 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -135,7 +135,7 @@ static ssize_t chp_measurement_chars_read(struct file *filp, struct channel_path *chp; struct device *device; - device = container_of(kobj, struct device, kobj); + device = kobj_to_dev(kobj); chp = to_channelpath(device); if (chp->cmg == -1) return 0; @@ -184,7 +184,7 @@ static ssize_t chp_measurement_read(struct file *filp, struct kobject *kobj, struct device *device; unsigned int size; - device = container_of(kobj, struct device, kobj); + device = kobj_to_dev(kobj); chp = to_channelpath(device); css = to_css(chp->dev.parent); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 3ab8e80d7bbc..e115623b86b2 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/io.h> #include <asm/qdio.h> #include "cio.h" @@ -205,7 +206,7 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr, /* fill in sl */ for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++) - q->sl->element[j].sbal = (unsigned long)q->sbal[j]; + q->sl->element[j].sbal = virt_to_phys(q->sbal[j]); } static void setup_queues(struct qdio_irq *irq_ptr, diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index d4caf46ff9df..2afe2153b34e 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -887,7 +887,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, /* empty pin tag */ *p++ = 0x04; *p++ = 0; - /* encrytped key value tag and bytes */ + /* encrypted key value tag and bytes */ p += asn1tag_write(p, 0x04, enckey, enckeysize); /* reply cprb and payload */ @@ -1095,7 +1095,7 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, /* Step 1: generate AES 256 bit random kek key */ rc = ep11_genaeskey(card, domain, 256, - 0x00006c00, /* EN/DECRYTP, WRAP/UNWRAP */ + 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ kek, &keklen); if (rc) { DEBUG_ERR( diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 9575a627a1e1..b7d64690ea38 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -189,6 +189,8 @@ struct qeth_vnicc_info { #define QETH_IQD_MIN_TXQ 2 /* One for ucast, one for mcast. */ #define QETH_IQD_MCAST_TXQ 0 #define QETH_IQD_MIN_UCAST_TXQ 1 + +#define QETH_RX_COPYBREAK (PAGE_SIZE >> 1) #define QETH_IN_BUF_SIZE_DEFAULT 65536 #define QETH_IN_BUF_COUNT_DEFAULT 64 #define QETH_IN_BUF_COUNT_HSDEFAULT 128 @@ -219,9 +221,6 @@ struct qeth_vnicc_info { #define QETH_HIGH_WATERMARK_PACK 5 #define QETH_WATERMARK_PACK_FUZZ 1 -/* large receive scatter gather copy break */ -#define QETH_RX_SG_CB (PAGE_SIZE >> 1) - struct qeth_hdr_layer3 { __u8 id; __u8 flags; @@ -711,7 +710,6 @@ struct qeth_card_options { struct qeth_vnicc_info vnicc; /* VNICC options */ int fake_broadcast; enum qeth_discipline_id layer; - int rx_sg_cb; enum qeth_ipa_isolation_modes isolation; enum qeth_ipa_isolation_modes prev_isolation; int sniffer; @@ -770,6 +768,10 @@ struct qeth_switch_info { __u32 settings; }; +struct qeth_priv { + unsigned int rx_copybreak; +}; + #define QETH_NAPI_WEIGHT NAPI_POLL_WEIGHT struct qeth_card { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 5efcaa43615b..fdc50543ce9a 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -742,7 +742,7 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, /* fall through */ default: qeth_clear_ipacmd_list(card); - goto out; + goto err_idx; } cmd = __ipa_reply(iob); @@ -795,8 +795,9 @@ out: memcpy(&card->seqno.pdu_hdr_ack, QETH_PDU_HEADER_SEQ_NO(iob->data), QETH_SEQ_NO_LENGTH); - qeth_put_cmd(iob); __qeth_issue_next_read(card); +err_idx: + qeth_put_cmd(iob); } static int qeth_set_thread_start_bit(struct qeth_card *card, @@ -1128,9 +1129,10 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, qeth_tx_complete_buf(buf, error, budget); for (i = 0; i < queue->max_elements; ++i) { - if (buf->buffer->element[i].addr && buf->is_header[i]) - kmem_cache_free(qeth_core_header_cache, - buf->buffer->element[i].addr); + void *data = phys_to_virt(buf->buffer->element[i].addr); + + if (data && buf->is_header[i]) + kmem_cache_free(qeth_core_header_cache, data); buf->is_header[i] = 0; } @@ -1256,7 +1258,6 @@ static void qeth_set_initial_options(struct qeth_card *card) { card->options.route4.type = NO_ROUTER; card->options.route6.type = NO_ROUTER; - card->options.rx_sg_cb = QETH_RX_SG_CB; card->options.isolation = ISOLATION_MODE_NONE; card->options.cq = QETH_CQ_DISABLED; card->options.layer = QETH_DISCIPLINE_UNDETERMINED; @@ -1624,17 +1625,16 @@ static void qeth_set_blkt_defaults(struct qeth_card *card) } } -static void qeth_init_tokens(struct qeth_card *card) +static void qeth_idx_init(struct qeth_card *card) { + memset(&card->seqno, 0, sizeof(card->seqno)); + card->token.issuer_rm_w = 0x00010103UL; card->token.cm_filter_w = 0x00010108UL; card->token.cm_connection_w = 0x0001010aUL; card->token.ulp_filter_w = 0x0001010bUL; card->token.ulp_connection_w = 0x0001010dUL; -} -static void qeth_init_func_level(struct qeth_card *card) -{ switch (card->info.type) { case QETH_CARD_TYPE_IQD: card->info.func_level = QETH_IDX_FUNC_LEVEL_IQD; @@ -2641,7 +2641,8 @@ static int qeth_init_input_buffer(struct qeth_card *card, buf->pool_entry = pool_entry; for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { buf->buffer->element[i].length = PAGE_SIZE; - buf->buffer->element[i].addr = pool_entry->elements[i]; + buf->buffer->element[i].addr = + virt_to_phys(pool_entry->elements[i]); if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1) buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY; else @@ -3405,8 +3406,7 @@ static void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue, { struct qeth_card *card = (struct qeth_card *)card_ptr; - if (card->dev->flags & IFF_UP) - napi_schedule_irqoff(&card->napi); + napi_schedule_irqoff(&card->napi); } int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) @@ -3459,9 +3459,8 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) && buffer->element[e].addr) { - unsigned long phys_aob_addr; + unsigned long phys_aob_addr = buffer->element[e].addr; - phys_aob_addr = (unsigned long) buffer->element[e].addr; qeth_qdio_handle_aob(card, phys_aob_addr); ++e; } @@ -3750,7 +3749,7 @@ static unsigned int __qeth_fill_buffer(struct sk_buff *skb, elem_length = min_t(unsigned int, length, PAGE_SIZE - offset_in_page(data)); - buffer->element[element].addr = data; + buffer->element[element].addr = virt_to_phys(data); buffer->element[element].length = elem_length; length -= elem_length; if (is_first_elem) { @@ -3780,7 +3779,7 @@ static unsigned int __qeth_fill_buffer(struct sk_buff *skb, elem_length = min_t(unsigned int, length, PAGE_SIZE - offset_in_page(data)); - buffer->element[element].addr = data; + buffer->element[element].addr = virt_to_phys(data); buffer->element[element].length = elem_length; buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG; @@ -3820,7 +3819,7 @@ static unsigned int qeth_fill_buffer(struct qeth_qdio_out_buffer *buf, int element = buf->next_element_to_fill; is_first_elem = false; - buffer->element[element].addr = hdr; + buffer->element[element].addr = virt_to_phys(hdr); buffer->element[element].length = hd_len; buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG; /* remember to free cache-allocated qeth_hdr: */ @@ -4746,10 +4745,10 @@ static void qeth_qdio_establish_cq(struct qeth_card *card, if (card->options.cq == QETH_CQ_ENABLED) { int offset = QDIO_MAX_BUFFERS_PER_Q * (card->qdio.no_in_queues - 1); - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) { - in_sbal_ptrs[offset + i] = (struct qdio_buffer *) - virt_to_phys(card->qdio.c_q->bufs[i].buffer); - } + + for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) + in_sbal_ptrs[offset + i] = + card->qdio.c_q->bufs[i].buffer; queue_start_poll[card->qdio.no_in_queues - 1] = NULL; } @@ -4783,10 +4782,9 @@ static int qeth_qdio_establish(struct qeth_card *card) rc = -ENOMEM; goto out_free_qib_param; } - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) { - in_sbal_ptrs[i] = (struct qdio_buffer *) - virt_to_phys(card->qdio.in_q->bufs[i].buffer); - } + + for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) + in_sbal_ptrs[i] = card->qdio.in_q->bufs[i].buffer; queue_start_poll = kcalloc(card->qdio.no_in_queues, sizeof(void *), GFP_KERNEL); @@ -4807,11 +4805,11 @@ static int qeth_qdio_establish(struct qeth_card *card) rc = -ENOMEM; goto out_free_queue_start_poll; } + for (i = 0, k = 0; i < card->qdio.no_out_queues; ++i) - for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j, ++k) { - out_sbal_ptrs[k] = (struct qdio_buffer *)virt_to_phys( - card->qdio.out_qs[i]->bufs[j]->buffer); - } + for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++, k++) + out_sbal_ptrs[k] = + card->qdio.out_qs[i]->bufs[j]->buffer; memset(&init_data, 0, sizeof(struct qdio_initialize)); init_data.cdev = CARD_DDEV(card); @@ -4952,9 +4950,9 @@ retriable: else goto retry; } + qeth_determine_capabilities(card); - qeth_init_tokens(card); - qeth_init_func_level(card); + qeth_idx_init(card); rc = qeth_idx_activate_read_channel(card); if (rc == -EINTR) { @@ -5269,6 +5267,7 @@ static int qeth_extract_skb(struct qeth_card *card, int *__offset) { struct qdio_buffer_element *element = *__element; + struct qeth_priv *priv = netdev_priv(card->dev); struct qdio_buffer *buffer = qethbuffer->buffer; struct napi_struct *napi = &card->napi; unsigned int linear_len = 0; @@ -5289,7 +5288,7 @@ next_packet: offset = 0; } - hdr = element->addr + offset; + hdr = phys_to_virt(element->addr) + offset; offset += sizeof(*hdr); skb = NULL; @@ -5344,7 +5343,7 @@ next_packet: } use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) || - (skb_len > card->options.rx_sg_cb && + (skb_len > READ_ONCE(priv->rx_copybreak) && !atomic_read(&card->force_alloc_skb) && !IS_OSN(card)); @@ -5388,7 +5387,7 @@ use_skb: walk_packet: while (skb_len) { int data_len = min(skb_len, (int)(element->length - offset)); - char *data = element->addr + offset; + char *data = phys_to_virt(element->addr) + offset; skb_len -= data_len; offset += data_len; @@ -5893,25 +5892,30 @@ static void qeth_clear_dbf_list(void) static struct net_device *qeth_alloc_netdev(struct qeth_card *card) { struct net_device *dev; + struct qeth_priv *priv; switch (card->info.type) { case QETH_CARD_TYPE_IQD: - dev = alloc_netdev_mqs(0, "hsi%d", NET_NAME_UNKNOWN, + dev = alloc_netdev_mqs(sizeof(*priv), "hsi%d", NET_NAME_UNKNOWN, ether_setup, QETH_MAX_QUEUES, 1); break; case QETH_CARD_TYPE_OSM: - dev = alloc_etherdev(0); + dev = alloc_etherdev(sizeof(*priv)); break; case QETH_CARD_TYPE_OSN: - dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup); + dev = alloc_netdev(sizeof(*priv), "osn%d", NET_NAME_UNKNOWN, + ether_setup); break; default: - dev = alloc_etherdev_mqs(0, QETH_MAX_QUEUES, 1); + dev = alloc_etherdev_mqs(sizeof(*priv), QETH_MAX_QUEUES, 1); } if (!dev) return NULL; + priv = netdev_priv(dev); + priv->rx_copybreak = QETH_RX_COPYBREAK; + dev->ml_priv = card; dev->watchdog_timeo = QETH_TX_TIMEOUT; dev->min_mtu = IS_OSN(card) ? 64 : 576; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 3865f7258449..6f304fdbb073 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -93,10 +93,6 @@ enum qeth_link_types { QETH_LINK_TYPE_LANE = 0x88, }; -/* - * Routing stuff - */ -#define RESET_ROUTING_FLAG 0x10 /* indicate that routing type shall be set */ enum qeth_routing_types { /* TODO: set to bit flag used in IPA Command */ NO_ROUTER = 0, @@ -427,7 +423,6 @@ struct qeth_ipacmd_setassparms { struct qeth_arp_cache_entry arp_entry; struct qeth_arp_query_data query_arp; struct qeth_tso_start_data tso; - __u8 ip[16]; } data; } __attribute__ ((packed)); @@ -550,8 +545,9 @@ struct qeth_ipacmd_setadpparms { /* CREATE_ADDR IPA Command: ***********************************************/ struct qeth_create_destroy_address { - __u8 unique_id[8]; -} __attribute__ ((packed)); + u8 mac_addr[ETH_ALEN]; + u16 uid; +}; /* SET DIAGNOSTIC ASSIST IPA Command: *************************************/ diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index ab59bc975719..9052c72d5b8f 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -175,6 +175,35 @@ static void qeth_get_channels(struct net_device *dev, channels->combined_count = 0; } +static int qeth_get_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, void *data) +{ + struct qeth_priv *priv = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = priv->rx_copybreak; + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int qeth_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct qeth_priv *priv = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + WRITE_ONCE(priv->rx_copybreak, *(u32 *)data); + return 0; + default: + return -EOPNOTSUPP; + } +} + /* Helper function to fill 'advertising' and 'supported' which are the same. */ /* Autoneg and full-duplex are supported and advertised unconditionally. */ /* Always advertise and support all speeds up to specified, and only one */ @@ -381,6 +410,8 @@ const struct ethtool_ops qeth_ethtool_ops = { .get_sset_count = qeth_get_sset_count, .get_drvinfo = qeth_get_drvinfo, .get_channels = qeth_get_channels, + .get_tunable = qeth_get_tunable, + .set_tunable = qeth_set_tunable, .get_link_ksettings = qeth_get_link_ksettings, }; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 317d56647a4a..1000e18c1090 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -920,9 +920,11 @@ static int qeth_l3_iqd_read_initial_mac_cb(struct qeth_card *card, if (cmd->hdr.return_code) return -EIO; + if (!is_valid_ether_addr(cmd->data.create_destroy_addr.mac_addr)) + return -EADDRNOTAVAIL; ether_addr_copy(card->dev->dev_addr, - cmd->data.create_destroy_addr.unique_id); + cmd->data.create_destroy_addr.mac_addr); return 0; } @@ -930,7 +932,6 @@ static int qeth_l3_iqd_read_initial_mac(struct qeth_card *card) { int rc = 0; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; QETH_CARD_TEXT(card, 2, "hsrmac"); @@ -938,9 +939,6 @@ static int qeth_l3_iqd_read_initial_mac(struct qeth_card *card) IPA_DATA_SIZEOF(create_destroy_addr)); if (!iob) return -ENOMEM; - cmd = __ipa_cmd(iob); - *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) = - card->info.unique_id; rc = qeth_send_ipa_cmd(card, iob, qeth_l3_iqd_read_initial_mac_cb, NULL); @@ -953,8 +951,7 @@ static int qeth_l3_get_unique_id_cb(struct qeth_card *card, struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; if (cmd->hdr.return_code == 0) { - card->info.unique_id = *((__u16 *) - &cmd->data.create_destroy_addr.unique_id[6]); + card->info.unique_id = cmd->data.create_destroy_addr.uid; return 0; } @@ -968,7 +965,6 @@ static int qeth_l3_get_unique_id(struct qeth_card *card) { int rc = 0; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; QETH_CARD_TEXT(card, 2, "guniqeid"); @@ -982,10 +978,8 @@ static int qeth_l3_get_unique_id(struct qeth_card *card) IPA_DATA_SIZEOF(create_destroy_addr)); if (!iob) return -ENOMEM; - cmd = __ipa_cmd(iob); - *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) = - card->info.unique_id; + __ipa_cmd(iob)->data.create_destroy_addr.uid = card->info.unique_id; rc = qeth_send_ipa_cmd(card, iob, qeth_l3_get_unique_id_cb, NULL); return rc; } diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 223a805f0b0b..cae9b7ff79b0 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -2510,7 +2510,7 @@ void zfcp_fsf_reqid_check(struct zfcp_qdio *qdio, int sbal_idx) for (idx = 0; idx < QDIO_MAX_ELEMENTS_PER_BUFFER; idx++) { sbale = &sbal->element[idx]; - req_id = (unsigned long) sbale->addr; + req_id = sbale->addr; fsf_req = zfcp_reqlist_find_rm(adapter->req_list, req_id); if (!fsf_req) { diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index 661436a92f8e..f0d6296e673b 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -98,7 +98,7 @@ static void zfcp_qdio_int_resp(struct ccw_device *cdev, unsigned int qdio_err, memset(pl, 0, ZFCP_QDIO_MAX_SBALS_PER_REQ * sizeof(void *)); sbale = qdio->res_q[idx]->element; - req_id = (u64) sbale->addr; + req_id = sbale->addr; scount = min(sbale->scount + 1, ZFCP_QDIO_MAX_SBALS_PER_REQ + 1); /* incl. signaling SBAL */ @@ -199,7 +199,7 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, q_req->sbal_number); return -EINVAL; } - sbale->addr = sg_virt(sg); + sbale->addr = sg_phys(sg); sbale->length = sg->length; } return 0; @@ -418,7 +418,7 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio) sbale->length = 0; sbale->eflags = SBAL_EFLAGS_LAST_ENTRY; sbale->sflags = 0; - sbale->addr = NULL; + sbale->addr = 0; } if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, 0, QDIO_MAX_BUFFERS_PER_Q)) diff --git a/drivers/s390/scsi/zfcp_qdio.h b/drivers/s390/scsi/zfcp_qdio.h index 2a816a37b3c0..6b43d6b254be 100644 --- a/drivers/s390/scsi/zfcp_qdio.h +++ b/drivers/s390/scsi/zfcp_qdio.h @@ -122,14 +122,14 @@ void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, % QDIO_MAX_BUFFERS_PER_Q; sbale = zfcp_qdio_sbale_req(qdio, q_req); - sbale->addr = (void *) req_id; + sbale->addr = req_id; sbale->eflags = 0; sbale->sflags = SBAL_SFLAGS0_COMMAND | sbtype; if (unlikely(!data)) return; sbale++; - sbale->addr = data; + sbale->addr = virt_to_phys(data); sbale->length = len; } @@ -152,7 +152,7 @@ void zfcp_qdio_fill_next(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, BUG_ON(q_req->sbale_curr == qdio->max_sbale_per_sbal - 1); q_req->sbale_curr++; sbale = zfcp_qdio_sbale_curr(qdio, q_req); - sbale->addr = data; + sbale->addr = virt_to_phys(data); sbale->length = len; } diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index f3b36fd0a0eb..b2ad96564484 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -623,7 +623,8 @@ retry_alloc: fusion->io_request_frames = dma_pool_alloc(fusion->io_request_frames_pool, - GFP_KERNEL, &fusion->io_request_frames_phys); + GFP_KERNEL | __GFP_NOWARN, + &fusion->io_request_frames_phys); if (!fusion->io_request_frames) { if (instance->max_fw_cmds >= (MEGASAS_REDUCE_QD_COUNT * 2)) { instance->max_fw_cmds -= MEGASAS_REDUCE_QD_COUNT; @@ -661,7 +662,7 @@ retry_alloc: fusion->io_request_frames = dma_pool_alloc(fusion->io_request_frames_pool, - GFP_KERNEL, + GFP_KERNEL | __GFP_NOWARN, &fusion->io_request_frames_phys); if (!fusion->io_request_frames) { diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index b94ed4e30770..09e55ea0bf5d 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1165,9 +1165,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -2004,9 +2002,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); /* * TASK_REASSIGN for ERL=2 / connection stays inside of @@ -4149,6 +4145,9 @@ int iscsit_close_connection( iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4231,11 +4230,6 @@ int iscsit_close_connection( * must wait until they have completed. */ iscsit_check_conn_usage_count(conn); - target_sess_cmd_list_set_waiting(sess->se_sess); - target_wait_for_sess_cmds(sess->se_sess); - - if (conn->conn_transport->iscsit_wait_conn) - conn->conn_transport->iscsit_wait_conn(conn); ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ea482d4b1f00..0ae9e60fc4d5 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -666,6 +666,11 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) target_remove_from_state_list(cmd); + /* + * Clear struct se_cmd->se_lun before the handoff to FE. + */ + cmd->se_lun = NULL; + spin_lock_irqsave(&cmd->t_state_lock, flags); /* * Determine if frontend context caller is requesting the stopping of @@ -693,6 +698,17 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) return cmd->se_tfo->check_stop_free(cmd); } +static void transport_lun_remove_cmd(struct se_cmd *cmd) +{ + struct se_lun *lun = cmd->se_lun; + + if (!lun) + return; + + if (cmpxchg(&cmd->lun_ref_active, true, false)) + percpu_ref_put(&lun->lun_ref); +} + static void target_complete_failure_work(struct work_struct *work) { struct se_cmd *cmd = container_of(work, struct se_cmd, work); @@ -783,6 +799,8 @@ static void target_handle_abort(struct se_cmd *cmd) WARN_ON_ONCE(kref_read(&cmd->cmd_kref) == 0); + transport_lun_remove_cmd(cmd); + transport_cmd_check_stop_to_fabric(cmd); } @@ -1708,6 +1726,7 @@ static void target_complete_tmr_failure(struct work_struct *work) se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST; se_cmd->se_tfo->queue_tm_rsp(se_cmd); + transport_lun_remove_cmd(se_cmd); transport_cmd_check_stop_to_fabric(se_cmd); } @@ -1898,6 +1917,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, goto queue_full; check_stop: + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; @@ -2195,6 +2215,7 @@ queue_status: transport_handle_queue_full(cmd, cmd->se_dev, ret, false); return; } + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); } @@ -2289,6 +2310,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2314,6 +2336,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2349,6 +2372,7 @@ queue_rsp: if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2384,6 +2408,7 @@ queue_status: break; } + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; @@ -2710,6 +2735,9 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) */ if (cmd->state_active) target_remove_from_state_list(cmd); + + if (cmd->se_lun) + transport_lun_remove_cmd(cmd); } if (aborted) cmd->free_compl = &compl; @@ -2781,9 +2809,6 @@ static void target_release_cmd_kref(struct kref *kref) struct completion *abrt_compl = se_cmd->abrt_compl; unsigned long flags; - if (se_cmd->lun_ref_active) - percpu_ref_put(&se_cmd->se_lun->lun_ref); - if (se_sess) { spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_del_init(&se_cmd->se_cmd_list); diff --git a/drivers/tee/amdtee/Kconfig b/drivers/tee/amdtee/Kconfig index 4e32b6413b41..191f9715fa9a 100644 --- a/drivers/tee/amdtee/Kconfig +++ b/drivers/tee/amdtee/Kconfig @@ -3,6 +3,6 @@ config AMDTEE tristate "AMD-TEE" default m - depends on CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && CRYPTO_DEV_CCP_DD help This implements AMD's Trusted Execution Environment (TEE) driver. diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e158159671fa..18e205eeb9af 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1414,10 +1414,6 @@ static int vhost_net_release(struct inode *inode, struct file *f) static struct socket *get_raw_socket(int fd) { - struct { - struct sockaddr_ll sa; - char buf[MAX_ADDR_LEN]; - } uaddr; int r; struct socket *sock = sockfd_lookup(fd, &r); @@ -1430,11 +1426,7 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); - if (r < 0) - goto err; - - if (uaddr.sa.sll_family != AF_PACKET) { + if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c index 70650b248de5..17240c5325a3 100644 --- a/drivers/xen/preempt.c +++ b/drivers/xen/preempt.c @@ -33,7 +33,9 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void) * cpu. */ __this_cpu_write(xen_in_preemptible_hcall, false); - _cond_resched(); + local_irq_enable(); + cond_resched(); + local_irq_disable(); __this_cpu_write(xen_in_preemptible_hcall, true); } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 89422aa8e9d1..c6c9a6a8e6c8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3200,6 +3200,7 @@ int __cold open_ctree(struct super_block *sb, if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); btrfs_warn(fs_info, "failed to read fs tree: %d", err); + fs_info->fs_root = NULL; goto fail_qgroup; } @@ -4276,6 +4277,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, cond_resched(); spin_lock(&delayed_refs->lock); } + btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); @@ -4501,7 +4503,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, wake_up(&fs_info->transaction_wait); btrfs_destroy_delayed_inodes(fs_info); - btrfs_assert_delayed_root_empty(fs_info); btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages, EXTENT_DIRTY); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0163fdd59f8f..a7bc66121330 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4430,6 +4430,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner, offset, ins, 1); + if (ret) + btrfs_pin_extent(fs_info, ins->objectid, ins->offset, 1); btrfs_put_block_group(block_group); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 36deef69f847..1ccb3f8d528d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4103,8 +4103,9 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->reada = READA_BACK; - lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, - &cached_state); + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) + lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, + &cached_state); /* * We want to drop from the next block forward in case this new size is @@ -4368,11 +4369,10 @@ out: if (!ret && last_size > new_size) last_size = new_size; btrfs_ordered_update_i_size(inode, last_size, NULL); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, + (u64)-1, &cached_state); } - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, - &cached_state); - btrfs_free_path(path); return ret; } @@ -9824,6 +9824,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_key ins; u64 cur_offset = start; + u64 clear_offset = start; u64 i_size; u64 cur_bytes; u64 last_alloc = (u64)-1; @@ -9858,6 +9859,15 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, btrfs_end_transaction(trans); break; } + + /* + * We've reserved this space, and thus converted it from + * ->bytes_may_use to ->bytes_reserved. Any error that happens + * from here on out we will only need to clear our reservation + * for the remaining unreserved area, so advance our + * clear_offset by our extent size. + */ + clear_offset += ins.offset; btrfs_dec_block_group_reservations(fs_info, ins.objectid); last_alloc = ins.offset; @@ -9937,9 +9947,9 @@ next: if (own_trans) btrfs_end_transaction(trans); } - if (cur_offset < end) - btrfs_free_reserved_data_space(inode, NULL, cur_offset, - end - cur_offset + 1); + if (clear_offset < end) + btrfs_free_reserved_data_space(inode, NULL, clear_offset, + end - clear_offset + 1); return ret; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index ecb9fb6a6fe0..a65f189a5b94 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -679,10 +679,15 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) } btrfs_start_ordered_extent(inode, ordered, 1); end = ordered->file_offset; + /* + * If the ordered extent had an error save the error but don't + * exit without waiting first for all other ordered extents in + * the range to complete. + */ if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) ret = -EIO; btrfs_put_ordered_extent(ordered); - if (ret || end == 0 || end == start) + if (end == 0 || end == start) break; end--; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 98d9a50352d6..ff1870ff3474 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4002,3 +4002,16 @@ out: } return ret; } + +void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) +{ + struct btrfs_qgroup_extent_record *entry; + struct btrfs_qgroup_extent_record *next; + struct rb_root *root; + + root = &trans->delayed_refs.dirty_extent_root; + rbtree_postorder_for_each_entry_safe(entry, next, root, node) { + ulist_free(entry->old_roots); + kfree(entry); + } +} diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 236f12224d52..1bc654459469 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -414,5 +414,6 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, u64 last_snapshot); int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb); +void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans); #endif diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 33dcc88b428a..beb6c69cd1e5 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -121,6 +121,8 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) BUG_ON(!list_empty(&transaction->list)); WARN_ON(!RB_EMPTY_ROOT( &transaction->delayed_refs.href_root.rb_root)); + WARN_ON(!RB_EMPTY_ROOT( + &transaction->delayed_refs.dirty_extent_root)); if (transaction->delayed_refs.pending_csums) btrfs_err(transaction->fs_info, "pending csums is %llu", diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 5f993a411251..8fd0b3cdab4c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -270,6 +270,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bh_p; if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," @@ -280,7 +281,14 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); - if (!sbi->s_group_desc[group_desc]) { + bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc); + /* + * sbi_array_rcu_deref returns with rcu unlocked, this is ok since + * the pointer being dereferenced won't be dereferenced again. By + * looking at the usage in add_new_gdb() the value isn't modified, + * just the pointer, and so it remains valid. + */ + if (!bh_p) { ext4_error(sb, "Group descriptor not loaded - " "block_group = %u, group_desc = %u, desc = %u", block_group, group_desc, offset); @@ -288,10 +296,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, } desc = (struct ext4_group_desc *)( - (__u8 *)sbi->s_group_desc[group_desc]->b_data + + (__u8 *)bh_p->b_data + offset * EXT4_DESC_SIZE(sb)); if (bh) - *bh = sbi->s_group_desc[group_desc]; + *bh = bh_p; return desc; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4441331d06cc..61b37a052052 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1400,7 +1400,7 @@ struct ext4_sb_info { loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; + struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; unsigned int s_mount_flags; @@ -1462,7 +1462,7 @@ struct ext4_sb_info { #endif /* for buddy allocator */ - struct ext4_group_info ***s_group_info; + struct ext4_group_info ** __rcu *s_group_info; struct inode *s_buddy_cache; spinlock_t s_md_lock; unsigned short *s_mb_offsets; @@ -1512,7 +1512,7 @@ struct ext4_sb_info { unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; + struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; /* workqueue for reserved extent conversions (buffered io) */ @@ -1552,8 +1552,11 @@ struct ext4_sb_info { struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; - /* Barrier between changing inodes' journal flags and writepages ops. */ - struct percpu_rw_semaphore s_journal_flag_rwsem; + /* + * Barrier between writepages ops and changing any inode's JOURNAL_DATA + * or EXTENTS flag. + */ + struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; @@ -1577,6 +1580,23 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) } /* + * Returns: sbi->field[index] + * Used to access an array element from the following sbi fields which require + * rcu protection to avoid dereferencing an invalid pointer due to reassignment + * - s_group_desc + * - s_group_info + * - s_flex_group + */ +#define sbi_array_rcu_deref(sbi, field, index) \ +({ \ + typeof(*((sbi)->field)) _v; \ + rcu_read_lock(); \ + _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \ + rcu_read_unlock(); \ + _v; \ +}) + +/* * Simulate_fail codes */ #define EXT4_SIM_BBITMAP_EIO 1 @@ -2730,6 +2750,7 @@ extern int ext4_generic_delete_entry(handle_t *handle, extern bool ext4_empty_dir(struct inode *inode); /* resize.c */ +extern void ext4_kvfree_array_rcu(void *to_free); extern int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input); extern int ext4_group_extend(struct super_block *sb, @@ -2976,13 +2997,13 @@ static inline struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info ***grp_info; + struct ext4_group_info **grp_info; long indexv, indexh; BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - grp_info = EXT4_SB(sb)->s_group_info; indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - return grp_info[indexv][indexh]; + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; } /* @@ -3032,7 +3053,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) !inode_is_locked(inode)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = newsize; + WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index c66e8f9451a2..f95ee99091e4 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -328,11 +328,13 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { - ext4_group_t f = ext4_flex_group(sbi, block_group); + struct flex_groups *fg; - atomic_inc(&sbi->s_flex_groups[f].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, + ext4_flex_group(sbi, block_group)); + atomic_inc(&fg->free_inodes); if (is_directory) - atomic_dec(&sbi->s_flex_groups[f].used_dirs); + atomic_dec(&fg->used_dirs); } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); fatal = ext4_handle_dirty_metadata(handle, NULL, bh2); @@ -368,12 +370,13 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, int flex_size, struct orlov_stats *stats) { struct ext4_group_desc *desc; - struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups; if (flex_size > 1) { - stats->free_inodes = atomic_read(&flex_group[g].free_inodes); - stats->free_clusters = atomic64_read(&flex_group[g].free_clusters); - stats->used_dirs = atomic_read(&flex_group[g].used_dirs); + struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb), + s_flex_groups, g); + stats->free_inodes = atomic_read(&fg->free_inodes); + stats->free_clusters = atomic64_read(&fg->free_clusters); + stats->used_dirs = atomic_read(&fg->used_dirs); return; } @@ -1054,7 +1057,8 @@ got: if (sbi->s_log_groups_per_flex) { ext4_group_t f = ext4_flex_group(sbi, group); - atomic_inc(&sbi->s_flex_groups[f].used_dirs); + atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups, + f)->used_dirs); } } if (ext4_has_group_desc_csum(sb)) { @@ -1077,7 +1081,8 @@ got: if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); - atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); + atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_inodes); } inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e60aca791d3f..fa0ff78dc033 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2465,7 +2465,7 @@ update_disksize: * truncate are avoided by checking i_size under i_data_sem. */ disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT; - if (disksize > EXT4_I(inode)->i_disksize) { + if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) { int err2; loff_t i_size; @@ -2628,7 +2628,7 @@ static int ext4_writepages(struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_journal_flag_rwsem); + percpu_down_read(&sbi->s_writepages_rwsem); trace_ext4_writepages(inode, wbc); /* @@ -2849,7 +2849,7 @@ unplug: out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_journal_flag_rwsem); + percpu_up_read(&sbi->s_writepages_rwsem); return ret; } @@ -2864,13 +2864,13 @@ static int ext4_dax_writepages(struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_journal_flag_rwsem); + percpu_down_read(&sbi->s_writepages_rwsem); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_journal_flag_rwsem); + percpu_up_read(&sbi->s_writepages_rwsem); return ret; } @@ -5861,7 +5861,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_journal_flag_rwsem); + percpu_down_write(&sbi->s_writepages_rwsem); jbd2_journal_lock_updates(journal); /* @@ -5878,7 +5878,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_journal_flag_rwsem); + percpu_up_write(&sbi->s_writepages_rwsem); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); @@ -5886,7 +5886,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_journal_flag_rwsem); + percpu_up_write(&sbi->s_writepages_rwsem); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f64838187559..51a78eb65f3c 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2356,7 +2356,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; - struct ext4_group_info ***new_groupinfo; + struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); @@ -2369,13 +2369,16 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } - if (sbi->s_group_info) { - memcpy(new_groupinfo, sbi->s_group_info, + rcu_read_lock(); + old_groupinfo = rcu_dereference(sbi->s_group_info); + if (old_groupinfo) + memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); - kvfree(sbi->s_group_info); - } - sbi->s_group_info = new_groupinfo; + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); + if (old_groupinfo) + ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; @@ -2387,6 +2390,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, { int i; int metalen = 0; + int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2405,12 +2409,12 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, "for a buddy group"); goto exit_meta_group_info; } - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = - meta_group_info; + rcu_read_lock(); + rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; + rcu_read_unlock(); } - meta_group_info = - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; + meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); @@ -2458,8 +2462,13 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { - kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]); - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL; + struct ext4_group_info ***group_info; + + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); + kfree(group_info[idx]); + group_info[idx] = NULL; + rcu_read_unlock(); } exit_meta_group_info: return -ENOMEM; @@ -2472,6 +2481,7 @@ static int ext4_mb_init_backend(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; + struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); @@ -2507,11 +2517,16 @@ err_freebuddy: while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = sbi->s_group_info_size; + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) - kfree(sbi->s_group_info[i]); + kfree(group_info[i]); + rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: - kvfree(sbi->s_group_info); + rcu_read_lock(); + kvfree(rcu_dereference(sbi->s_group_info)); + rcu_read_unlock(); return -ENOMEM; } @@ -2700,7 +2715,7 @@ int ext4_mb_release(struct super_block *sb) ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; - struct ext4_group_info *grinfo; + struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2719,9 +2734,12 @@ int ext4_mb_release(struct super_block *sb) num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) - kfree(sbi->s_group_info[i]); - kvfree(sbi->s_group_info); + kfree(group_info[i]); + kvfree(group_info); + rcu_read_unlock(); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); @@ -3020,7 +3038,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic64_sub(ac->ac_b_ex.fe_len, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4918,7 +4937,8 @@ do_more: if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(count_clusters, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } /* @@ -5075,7 +5095,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(clusters_freed, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 89725fa42573..fb6520f37135 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -407,6 +407,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -431,6 +432,8 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; + percpu_down_write(&sbi->s_writepages_rwsem); + /* * Worst case we can touch the allocation bitmaps, a bgd * block, and a block to link in the orphan list. We do need @@ -441,7 +444,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(handle)) { retval = PTR_ERR(handle); - return retval; + goto out_unlock; } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; @@ -452,7 +455,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); - return retval; + goto out_unlock; } i_size_write(tmp_inode, i_size_read(inode)); /* @@ -494,7 +497,7 @@ int ext4_ext_migrate(struct inode *inode) */ ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); - goto out; + goto out_tmp_inode; } ei = EXT4_I(inode); @@ -576,10 +579,11 @@ err_out: ext4_ext_tree_init(handle, tmp_inode); out_stop: ext4_journal_stop(handle); -out: +out_tmp_inode: unlock_new_inode(tmp_inode); iput(tmp_inode); - +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return retval; } @@ -589,7 +593,8 @@ out: int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_super_block *es = sbi->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; @@ -613,9 +618,13 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); + percpu_down_write(&sbi->s_writepages_rwsem); + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_unlock; + } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); @@ -650,5 +659,7 @@ int ext4_ind_migrate(struct inode *inode) errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return ret; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ceff4b4b1877..b05ea72f38fd 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1511,6 +1511,7 @@ restart: /* * We deal with the read-ahead logic here. */ + cond_resched(); if (ra_ptr >= ra_max) { /* Refill the readahead buffer */ ra_ptr = 0; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 86a2500ed292..a50b51270ea9 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -17,6 +17,33 @@ #include "ext4_jbd2.h" +struct ext4_rcu_ptr { + struct rcu_head rcu; + void *ptr; +}; + +static void ext4_rcu_ptr_callback(struct rcu_head *head) +{ + struct ext4_rcu_ptr *ptr; + + ptr = container_of(head, struct ext4_rcu_ptr, rcu); + kvfree(ptr->ptr); + kfree(ptr); +} + +void ext4_kvfree_array_rcu(void *to_free) +{ + struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); + + if (ptr) { + ptr->ptr = to_free; + call_rcu(&ptr->rcu, ext4_rcu_ptr_callback); + return; + } + synchronize_rcu(); + kvfree(to_free); +} + int ext4_resize_begin(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -542,8 +569,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, brelse(gdb); goto out; } - memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data, - gdb->b_size); + memcpy(gdb->b_data, sbi_array_rcu_deref(sbi, + s_group_desc, j)->b_data, gdb->b_size); set_buffer_uptodate(gdb); err = ext4_handle_dirty_metadata(handle, NULL, gdb); @@ -860,13 +887,15 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, } brelse(dind); - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); err = ext4_handle_dirty_super(handle, sb); @@ -909,9 +938,11 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; BUFFER_TRACE(gdb_bh, "get_write_access"); @@ -922,9 +953,9 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); return err; } @@ -1188,7 +1219,8 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, * use non-sparse filesystems anymore. This is already checked above. */ if (gdb_off) { - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); @@ -1270,7 +1302,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, /* * get_write_access() has been called on gdb_bh by ext4_add_new_desc(). */ - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); /* Update group descriptor block for new group */ gdp = (struct ext4_group_desc *)(gdb_bh->b_data + gdb_off * EXT4_DESC_SIZE(sb)); @@ -1398,11 +1430,14 @@ static void ext4_update_super(struct super_block *sb, percpu_counter_read(&sbi->s_freeclusters_counter)); if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { ext4_group_t flex_group; + struct flex_groups *fg; + flex_group = ext4_flex_group(sbi, group_data[0].group); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic64_add(EXT4_NUM_B2C(sbi, free_blocks), - &sbi->s_flex_groups[flex_group].free_clusters); + &fg->free_clusters); atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count, - &sbi->s_flex_groups[flex_group].free_inodes); + &fg->free_inodes); } /* @@ -1497,7 +1532,8 @@ exit_journal: for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f464dff09774..ff1b764b0c0e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1014,6 +1014,8 @@ static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; + struct buffer_head **group_desc; + struct flex_groups **flex_groups; int aborted = 0; int i, err; @@ -1046,15 +1048,23 @@ static void ext4_put_super(struct super_block *sb) if (!sb_rdonly(sb)) ext4_commit_super(sb, 1); + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); - kvfree(sbi->s_flex_groups); + brelse(group_desc[i]); + kvfree(group_desc); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); - percpu_free_rwsem(&sbi->s_journal_flag_rwsem); + percpu_free_rwsem(&sbi->s_writepages_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); @@ -2380,8 +2390,8 @@ done: int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct flex_groups *new_groups; - int size; + struct flex_groups **old_groups, **new_groups; + int size, i; if (!sbi->s_log_groups_per_flex) return 0; @@ -2390,22 +2400,37 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) if (size <= sbi->s_flex_groups_allocated) return 0; - size = roundup_pow_of_two(size * sizeof(struct flex_groups)); - new_groups = kvzalloc(size, GFP_KERNEL); + new_groups = kvzalloc(roundup_pow_of_two(size * + sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { - ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", - size / (int) sizeof(struct flex_groups)); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex group pointers", size); return -ENOMEM; } - - if (sbi->s_flex_groups) { - memcpy(new_groups, sbi->s_flex_groups, - (sbi->s_flex_groups_allocated * - sizeof(struct flex_groups))); - kvfree(sbi->s_flex_groups); + for (i = sbi->s_flex_groups_allocated; i < size; i++) { + new_groups[i] = kvzalloc(roundup_pow_of_two( + sizeof(struct flex_groups)), + GFP_KERNEL); + if (!new_groups[i]) { + for (i--; i >= sbi->s_flex_groups_allocated; i--) + kvfree(new_groups[i]); + kvfree(new_groups); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex groups", size); + return -ENOMEM; + } } - sbi->s_flex_groups = new_groups; - sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); + rcu_read_lock(); + old_groups = rcu_dereference(sbi->s_flex_groups); + if (old_groups) + memcpy(new_groups, old_groups, + (sbi->s_flex_groups_allocated * + sizeof(struct flex_groups *))); + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_flex_groups, new_groups); + sbi->s_flex_groups_allocated = size; + if (old_groups) + ext4_kvfree_array_rcu(old_groups); return 0; } @@ -2413,6 +2438,7 @@ static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; + struct flex_groups *fg; ext4_group_t flex_group; int i, err; @@ -2430,12 +2456,11 @@ static int ext4_fill_flex_info(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); - atomic_add(ext4_free_inodes_count(sb, gdp), - &sbi->s_flex_groups[flex_group].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); + atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), - &sbi->s_flex_groups[flex_group].free_clusters); - atomic_add(ext4_used_dirs_count(sb, gdp), - &sbi->s_flex_groups[flex_group].used_dirs); + &fg->free_clusters); + atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; @@ -3009,7 +3034,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2) +#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, @@ -3634,9 +3659,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) { struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); char *orig_data = kstrdup(data, GFP_KERNEL); - struct buffer_head *bh; + struct buffer_head *bh, **group_desc; struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + struct flex_groups **flex_groups; ext4_fsblk_t block; ext4_fsblk_t sb_block = get_sb_block(&data); ext4_fsblk_t logical_sb_block; @@ -4290,9 +4316,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } } - sbi->s_group_desc = kvmalloc_array(db_count, - sizeof(struct buffer_head *), - GFP_KERNEL); + rcu_assign_pointer(sbi->s_group_desc, + kvmalloc_array(db_count, + sizeof(struct buffer_head *), + GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); ret = -ENOMEM; @@ -4308,14 +4335,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } for (i = 0; i < db_count; i++) { + struct buffer_head *bh; + block = descriptor_loc(sb, logical_sb_block, i); - sbi->s_group_desc[i] = sb_bread_unmovable(sb, block); - if (!sbi->s_group_desc[i]) { + bh = sb_bread_unmovable(sb, block); + if (!bh) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); db_count = i; goto failed_mount2; } + rcu_read_lock(); + rcu_dereference(sbi->s_group_desc)[i] = bh; + rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { @@ -4594,7 +4626,7 @@ no_journal: err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) - err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem); + err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); @@ -4682,13 +4714,19 @@ failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); - if (sbi->s_flex_groups) - kvfree(sbi->s_flex_groups); + rcu_read_lock(); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); - percpu_free_rwsem(&sbi->s_journal_flag_rwsem); + percpu_free_rwsem(&sbi->s_writepages_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); @@ -4717,9 +4755,12 @@ failed_mount3: if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < db_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); + brelse(group_desc[i]); + kvfree(group_desc); + rcu_read_unlock(); failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); diff --git a/fs/io_uring.c b/fs/io_uring.c index 5a826017ebb8..de650df9ac53 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1260,6 +1260,9 @@ static void __io_req_aux_free(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + if (req->flags & REQ_F_NEED_CLEANUP) + io_cleanup_req(req); + kfree(req->io); if (req->file) { if (req->flags & REQ_F_FIXED_FILE) @@ -1275,9 +1278,6 @@ static void __io_free_req(struct io_kiocb *req) { __io_req_aux_free(req); - if (req->flags & REQ_F_NEED_CLEANUP) - io_cleanup_req(req); - if (req->flags & REQ_F_INFLIGHT) { struct io_ring_ctx *ctx = req->ctx; unsigned long flags; @@ -1672,11 +1672,17 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) +static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) { int iters = 0, ret = 0; + /* + * We disallow the app entering submit/complete with polling, but we + * still need to lock the ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); do { int tmin = 0; @@ -1712,21 +1718,6 @@ static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, ret = 0; } while (min && !*nr_events && !need_resched()); - return ret; -} - -static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) -{ - int ret; - - /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); - ret = __io_iopoll_check(ctx, nr_events, min); mutex_unlock(&ctx->uring_lock); return ret; } @@ -2517,6 +2508,9 @@ static void io_fallocate_finish(struct io_wq_work **workptr) struct io_kiocb *nxt = NULL; int ret; + if (io_req_cancelled(req)) + return; + ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); if (ret < 0) @@ -2904,6 +2898,7 @@ static void io_close_finish(struct io_wq_work **workptr) struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); struct io_kiocb *nxt = NULL; + /* not cancellable, don't do io_req_cancelled() */ __io_close_finish(req, &nxt); if (nxt) io_wq_assign_next(workptr, nxt); @@ -3071,7 +3066,7 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, if (req->io) return -EAGAIN; if (io_alloc_async_ctx(req)) { - if (kmsg && kmsg->iov != kmsg->fast_iov) + if (kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); return -ENOMEM; } @@ -3225,7 +3220,7 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, if (req->io) return -EAGAIN; if (io_alloc_async_ctx(req)) { - if (kmsg && kmsg->iov != kmsg->fast_iov) + if (kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); return -ENOMEM; } @@ -5114,7 +5109,7 @@ static int io_sq_thread(void *data) */ mutex_lock(&ctx->uring_lock); if (!list_empty(&ctx->poll_list)) - __io_iopoll_check(ctx, &nr_events, 0); + io_iopoll_getevents(ctx, &nr_events, 0); else inflight = 0; mutex_unlock(&ctx->uring_lock); @@ -5139,6 +5134,18 @@ static int io_sq_thread(void *data) */ if (!to_submit || ret == -EBUSY) { /* + * Drop cur_mm before scheduling, we can't hold it for + * long periods (or over schedule()). Do this before + * adding ourselves to the waitqueue, as the unuse/drop + * may sleep. + */ + if (cur_mm) { + unuse_mm(cur_mm); + mmput(cur_mm); + cur_mm = NULL; + } + + /* * We're polling. If we're within the defined idle * period, then let us spin without work before going * to sleep. The exception is if we got EBUSY doing @@ -5152,18 +5159,6 @@ static int io_sq_thread(void *data) continue; } - /* - * Drop cur_mm before scheduling, we can't hold it for - * long periods (or over schedule()). Do this before - * adding ourselves to the waitqueue, as the unuse/drop - * may sleep. - */ - if (cur_mm) { - unuse_mm(cur_mm); - mmput(cur_mm); - cur_mm = NULL; - } - prepare_to_wait(&ctx->sqo_wait, &wait, TASK_INTERRUPTIBLE); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 2dd848a743ed..d181948c0390 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -936,8 +936,6 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, char *frozen_buffer = NULL; unsigned long start_lock, time_lock; - if (is_handle_aborted(handle)) - return -EROFS; journal = transaction->t_journal; jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); @@ -1189,6 +1187,9 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int rc; + if (is_handle_aborted(handle)) + return -EROFS; + if (jbd2_write_access_granted(handle, bh, false)) return 0; @@ -1326,6 +1327,9 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; char *committed_data = NULL; + if (is_handle_aborted(handle)) + return -EROFS; + if (jbd2_write_access_granted(handle, bh, true)) return 0; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 130fc6fbcc03..26bbf960e2a2 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -558,3 +558,151 @@ void sysfs_remove_bin_file(struct kobject *kobj, kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); + +static int internal_change_owner(struct kernfs_node *kn, kuid_t kuid, + kgid_t kgid) +{ + struct iattr newattrs = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = kuid, + .ia_gid = kgid, + }; + return kernfs_setattr(kn, &newattrs); +} + +/** + * sysfs_link_change_owner - change owner of a sysfs file. + * @kobj: object of the kernfs_node the symlink is located in. + * @targ: object of the kernfs_node the symlink points to. + * @name: name of the link. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * This function looks up the sysfs symlink entry @name under @kobj and changes + * the ownership to @kuid/@kgid. The symlink is looked up in the namespace of + * @targ. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, + const char *name, kuid_t kuid, kgid_t kgid) +{ + struct kernfs_node *kn = NULL; + int error; + + if (!name || !kobj->state_in_sysfs || !targ->state_in_sysfs) + return -EINVAL; + + error = -ENOENT; + kn = kernfs_find_and_get_ns(kobj->sd, name, targ->sd->ns); + if (!kn) + goto out; + + error = -EINVAL; + if (kernfs_type(kn) != KERNFS_LINK) + goto out; + if (kn->symlink.target_kn->priv != targ) + goto out; + + error = internal_change_owner(kn, kuid, kgid); + +out: + kernfs_put(kn); + return error; +} + +/** + * sysfs_file_change_owner - change owner of a sysfs file. + * @kobj: object. + * @name: name of the file to change. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * This function looks up the sysfs entry @name under @kobj and changes the + * ownership to @kuid/@kgid. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, + kgid_t kgid) +{ + struct kernfs_node *kn; + int error; + + if (!name) + return -EINVAL; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + kn = kernfs_find_and_get(kobj->sd, name); + if (!kn) + return -ENOENT; + + error = internal_change_owner(kn, kuid, kgid); + + kernfs_put(kn); + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_file_change_owner); + +/** + * sysfs_change_owner - change owner of the given object. + * @kobj: object. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Change the owner of the default directory, files, groups, and attributes of + * @kobj to @kuid/@kgid. Note that sysfs_change_owner mirrors how the sysfs + * entries for a kobject are added by driver core. In summary, + * sysfs_change_owner() takes care of the default directory entry for @kobj, + * the default attributes associated with the ktype of @kobj and the default + * attributes associated with the ktype of @kobj. + * Additional properties not added by driver core have to be changed by the + * driver or subsystem which created them. This is similar to how + * driver/subsystem specific entries are removed. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) +{ + int error; + const struct kobj_type *ktype; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + /* Change the owner of the kobject itself. */ + error = internal_change_owner(kobj->sd, kuid, kgid); + if (error) + return error; + + ktype = get_ktype(kobj); + if (ktype) { + struct attribute **kattr; + + /* + * Change owner of the default attributes associated with the + * ktype of @kobj. + */ + for (kattr = ktype->default_attrs; kattr && *kattr; kattr++) { + error = sysfs_file_change_owner(kobj, (*kattr)->name, + kuid, kgid); + if (error) + return error; + } + + /* + * Change owner of the default groups associated with the + * ktype of @kobj. + */ + error = sysfs_groups_change_owner(kobj, ktype->default_groups, + kuid, kgid); + if (error) + return error; + } + + return 0; +} +EXPORT_SYMBOL_GPL(sysfs_change_owner); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index c4ab045926b7..5afe0e7ff7cd 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -13,6 +13,7 @@ #include <linux/dcache.h> #include <linux/namei.h> #include <linux/err.h> +#include <linux/fs.h> #include "sysfs.h" @@ -457,3 +458,117 @@ int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, return PTR_ERR_OR_ZERO(link); } EXPORT_SYMBOL_GPL(__compat_only_sysfs_link_entry_to_kobj); + +static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, + const struct attribute_group *grp, + struct iattr *newattrs) +{ + struct kernfs_node *kn; + int error; + + if (grp->attrs) { + struct attribute *const *attr; + + for (attr = grp->attrs; *attr; attr++) { + kn = kernfs_find_and_get(grp_kn, (*attr)->name); + if (!kn) + return -ENOENT; + + error = kernfs_setattr(kn, newattrs); + kernfs_put(kn); + if (error) + return error; + } + } + + if (grp->bin_attrs) { + struct bin_attribute *const *bin_attr; + + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); + if (!kn) + return -ENOENT; + + error = kernfs_setattr(kn, newattrs); + kernfs_put(kn); + if (error) + return error; + } + } + + return 0; +} + +/** + * sysfs_group_change_owner - change owner of an attribute group. + * @kobj: The kobject containing the group. + * @grp: The attribute group. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Returns 0 on success or error code on failure. + */ +int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *grp, kuid_t kuid, + kgid_t kgid) +{ + struct kernfs_node *grp_kn; + int error; + struct iattr newattrs = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = kuid, + .ia_gid = kgid, + }; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + if (grp->name) { + grp_kn = kernfs_find_and_get(kobj->sd, grp->name); + } else { + kernfs_get(kobj->sd); + grp_kn = kobj->sd; + } + if (!grp_kn) + return -ENOENT; + + error = kernfs_setattr(grp_kn, &newattrs); + if (!error) + error = sysfs_group_attrs_change_owner(grp_kn, grp, &newattrs); + + kernfs_put(grp_kn); + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_group_change_owner); + +/** + * sysfs_groups_change_owner - change owner of a set of attribute groups. + * @kobj: The kobject containing the groups. + * @groups: The attribute groups. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Returns 0 on success or error code on failure. + */ +int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + int error = 0, i; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = sysfs_group_change_owner(kobj, groups[i], kuid, kgid); + if (error) + break; + } + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_groups_change_owner); diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 7e18c939663e..d11e183fcb54 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,9 @@ #include <linux/kernel.h> #include <linux/types.h> +#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" +#define BOOTCONFIG_MAGIC_LEN 12 + /* XBC tree node */ struct xbc_node { u16 next; diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 6b64b6cc2175..07e547c02fd8 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -198,7 +198,7 @@ enum dccp_role { struct dccp_service_list { __u32 dccpsl_nr; - __be32 dccpsl_list[0]; + __be32 dccpsl_list[]; }; #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) diff --git a/include/linux/device.h b/include/linux/device.h index 0cd7c647c16c..3e40533d2037 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -817,6 +817,7 @@ extern struct device *device_find_child_by_name(struct device *parent, extern int device_rename(struct device *dev, const char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); +extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); extern const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); diff --git a/include/linux/hid.h b/include/linux/hid.h index cd41f209043f..875f71132b14 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -492,7 +492,7 @@ struct hid_report_enum { }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ -#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 93338fd54af8..33d379602314 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -22,19 +22,23 @@ extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); +#if IS_ENABLED(CONFIG_NF_NAT) +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); +#else +#define icmpv6_ndo_send icmpv6_send +#endif + #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { - } -#endif -#if IS_ENABLED(CONFIG_NF_NAT) -void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); -#else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) +{ +} #endif extern int icmpv6_init(void); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b2d47571ab67..8d062e86d954 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -192,7 +192,7 @@ enum { IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), /* Irq domain name was allocated in __irq_domain_add() */ - IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6), + IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1), /* Irq domain is an IPI domain with virq per cpu */ IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2), diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e89eb67356cb..7944ad6ac10b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -889,6 +889,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); +int kvm_arch_post_init_vm(struct kvm *kvm); +void kvm_arch_pre_destroy_vm(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 4cae16016b2b..a5cf5c76f348 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -84,6 +84,7 @@ enum { FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, FDB_SLOW_PATH, + FDB_PER_VPORT, }; struct mlx5_pkt_reformat; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 908d38dbcb91..5448c8b443db 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -121,6 +121,7 @@ struct ip_set_ext { u32 timeout; u8 packets_op; u8 bytes_op; + bool target; }; struct ip_set; @@ -187,6 +188,14 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Region-locking is used */ + bool region_lock; +}; + +struct ip_set_region { + spinlock_t lock; /* Region lock */ + size_t ext_size; /* Size of the dynamic extensions */ + u32 elements; /* Number of elements vs timeout */ }; /* The core set type structure */ @@ -501,7 +510,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } #define IP_SET_INIT_KEXT(skb, opt, set) \ - { .bytes = (skb)->len, .packets = 1, \ + { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ diff --git a/include/linux/phy.h b/include/linux/phy.h index 80f8b2158271..e72dbd0d2d6a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -289,6 +289,7 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) return devm_mdiobus_alloc_size(dev, 0); } +struct mii_bus *mdio_find_bus(const char *mdio_name); void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 812357c03df4..2180eb1aa254 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -91,9 +91,10 @@ struct phylink_mac_ops { void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); - void (*mac_link_up)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy); + void (*mac_link_up)(struct phylink_config *config, + struct phy_device *phy, unsigned int mode, + phy_interface_t interface, int speed, int duplex, + bool tx_pause, bool rx_pause); }; #if 0 /* For kernel-doc purposes only. */ @@ -152,6 +153,9 @@ void mac_pcs_get_state(struct phylink_config *config, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * (this requires a rewrite - please refer to mac_link_up() for situations + * where the PCS and MAC are not tightly integrated.) + * * In all negotiation modes, as defined by @mode, @state->pause indicates the * pause settings which should be applied as follows. If %MLO_PAUSE_AN is not * set, %MLO_PAUSE_TX and %MLO_PAUSE_RX indicate whether the MAC should send @@ -162,12 +166,20 @@ void mac_pcs_get_state(struct phylink_config *config, * The action performed depends on the currently selected mode: * * %MLO_AN_FIXED, %MLO_AN_PHY: - * Configure the specified @state->speed and @state->duplex over a link - * specified by @state->interface. @state->advertising may be used, but - * is not required. Pause modes as above. Other members of @state must - * be ignored. + * Configure for non-inband negotiation mode, where the link settings + * are completely communicated via mac_link_up(). The physical link + * protocol from the MAC is specified by @state->interface. + * + * @state->advertising may be used, but is not required. + * + * Older drivers (prior to the mac_link_up() change) may use @state->speed, + * @state->duplex and @state->pause to configure the MAC, but this is + * deprecated; such drivers should be converted to use mac_link_up(). * - * Valid state members: interface, speed, duplex, pause, advertising. + * Other members of @state must be ignored. + * + * Valid state members: interface, advertising. + * Deprecated state members: speed, duplex, pause. * * %MLO_AN_INBAND: * place the link in an inband negotiation mode (such as 802.3z @@ -228,19 +240,34 @@ void mac_link_down(struct phylink_config *config, unsigned int mode, /** * mac_link_up() - allow the link to come up * @config: a pointer to a &struct phylink_config. + * @phy: any attached phy * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode - * @phy: any attached phy + * @speed: link speed + * @duplex: link duplex + * @tx_pause: link transmit pause enablement status + * @rx_pause: link receive pause enablement status * - * If @mode is not an in-band negotiation mode (as defined by - * phylink_autoneg_inband()), allow the link to come up. If @phy - * is non-%NULL, configure Energy Efficient Ethernet by calling + * Configure the MAC for an established link. + * + * @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link + * settings, and should be used to configure the MAC block appropriately + * where these settings are not automatically conveyed from the PCS block, + * or if in-band negotiation (as defined by phylink_autoneg_inband(@mode)) + * is disabled. + * + * Note that when 802.3z in-band negotiation is in use, it is possible + * that the user wishes to override the pause settings, and this should + * be allowed when considering the implementation of this method. + * + * If in-band negotiation mode is disabled, allow the link to come up. If + * @phy is non-%NULL, configure Energy Efficient Ethernet by calling * phy_init_eee() and perform appropriate MAC configuration for EEE. * Interface type selection must be done in mac_config(). */ -void mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy); +void mac_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause); #endif struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5b50278c4bc8..21749b2cdc9b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3514,23 +3514,15 @@ int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err, + unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err); + unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index fa7ee503fb76..9e531ec76274 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -310,6 +310,18 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) return kernfs_enable_ns(kn); } +int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, + kgid_t kgid); +int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid); +int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, + const char *name, kuid_t kuid, kgid_t kgid); +int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid); +int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *groups, kuid_t kuid, + kgid_t kgid); + #else /* CONFIG_SYSFS */ static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) @@ -522,6 +534,40 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) { } +static inline int sysfs_file_change_owner(struct kobject *kobj, + const char *name, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_link_change_owner(struct kobject *kobj, + struct kobject *targ, + const char *name, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + return 0; +} + #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 17e10fba2152..f42fdddecd41 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -27,7 +27,7 @@ struct unix_address { refcount_t refcnt; int len; unsigned int hash; - struct sockaddr_un name[0]; + struct sockaddr_un name[]; }; struct unix_skb_parms { @@ -42,7 +42,7 @@ struct unix_skb_parms { } __randomize_layout; struct scm_stat { - u32 nr_fds; + atomic_t nr_fds; }; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) diff --git a/include/net/bareudp.h b/include/net/bareudp.h new file mode 100644 index 000000000000..cb03f6f15956 --- /dev/null +++ b/include/net/bareudp.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NET_BAREUDP_H +#define __NET_BAREUDP_H + +#include <linux/types.h> +#include <linux/skbuff.h> + +struct bareudp_conf { + __be16 ethertype; + __be16 port; + u16 sport_min; + bool multi_proto_mode; +}; + +struct net_device *bareudp_dev_create(struct net *net, const char *name, + u8 name_assign_type, + struct bareudp_conf *info); + +#endif diff --git a/include/net/bonding.h b/include/net/bonding.h index 3d56b026bb9e..dc2ce31a1f52 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -183,7 +183,7 @@ struct slave { struct bond_up_slave { unsigned int count; struct rcu_head rcu; - struct slave *arr[0]; + struct slave *arr[]; }; /* diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7709b92f5b6b..f7c84c32ba39 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -72,12 +72,12 @@ struct wiphy; * * @IEEE80211_CHAN_DISABLED: This channel is disabled. * @IEEE80211_CHAN_NO_IR: do not initiate radiation, this includes - * sending probe requests or beaconing. + * sending probe requests or beaconing. * @IEEE80211_CHAN_RADAR: Radar detection is required on this channel. * @IEEE80211_CHAN_NO_HT40PLUS: extension channel above this channel - * is not permitted. + * is not permitted. * @IEEE80211_CHAN_NO_HT40MINUS: extension channel below this channel - * is not permitted. + * is not permitted. * @IEEE80211_CHAN_NO_OFDM: OFDM is not allowed on this channel. * @IEEE80211_CHAN_NO_80MHZ: If the driver supports 80 MHz on the band, * this flag indicates that an 80 MHz channel cannot use this @@ -627,6 +627,41 @@ struct cfg80211_chan_def { }; /** + * struct cfg80211_tid_cfg - TID specific configuration + * @config_override: Flag to notify driver to reset TID configuration + * of the peer. + * @tids: bitmap of TIDs to modify + * @mask: bitmap of attributes indicating which parameter changed, + * similar to &nl80211_tid_config_supp. + * @noack: noack configuration value for the TID + * @retry_long: retry count value + * @retry_short: retry count value + * @ampdu: Enable/Disable aggregation + * @rtscts: Enable/Disable RTS/CTS + */ +struct cfg80211_tid_cfg { + bool config_override; + u8 tids; + u32 mask; + enum nl80211_tid_config noack; + u8 retry_long, retry_short; + enum nl80211_tid_config ampdu; + enum nl80211_tid_config rtscts; +}; + +/** + * struct cfg80211_tid_config - TID configuration + * @peer: Station's MAC address + * @n_tid_conf: Number of TID specific configurations to be applied + * @tid_conf: Configuration change info + */ +struct cfg80211_tid_config { + const u8 *peer; + u32 n_tid_conf; + struct cfg80211_tid_cfg tid_conf[]; +}; + +/** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition * @@ -1686,7 +1721,7 @@ struct mpath_info { * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations * @ht_opmode: HT Operation mode - * (u16 = opmode, -1 = do not change) + * (u16 = opmode, -1 = do not change) * @p2p_ctwindow: P2P CT Window (-1 = no change) * @p2p_opp_ps: P2P opportunistic PS (-1 = no change) */ @@ -2062,8 +2097,8 @@ struct cfg80211_bss_select_adjust { * @ie_len: length of ie in octets * @flags: bit field of flags controlling operation * @match_sets: sets of parameters to be matched for a scan result - * entry to be considered valid and to be passed to the host - * (others are filtered out). + * entry to be considered valid and to be passed to the host + * (others are filtered out). * If ommited, all results are passed. * @n_match_sets: number of match sets * @report_results: indicates that results were reported for this request @@ -2456,7 +2491,7 @@ struct cfg80211_disassoc_request { * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. * @wep_keys: static WEP keys, if not NULL points to an array of - * CFG80211_MAX_WEP_KEYS WEP keys + * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key */ struct cfg80211_ibss_params { @@ -3369,6 +3404,8 @@ struct cfg80211_update_owe_info { * @set_default_key: set the default key on an interface * * @set_default_mgmt_key: set the default management frame key on an interface + + * @set_default_beacon_key: set the default Beacon frame key on an interface * * @set_rekey_data: give the data necessary for GTK rekeying to the driver * @@ -3669,6 +3706,10 @@ struct cfg80211_update_owe_info { * * @probe_mesh_link: Probe direct Mesh peer's link quality by sending data frame * and overrule HWMP path selection algorithm. + * @set_tid_config: TID specific configuration, this can be peer or BSS specific + * This callback may sleep. + * @reset_tid_config: Reset TID specific configuration for the peer, for the + * given TIDs. This callback may sleep. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3702,6 +3743,9 @@ struct cfg80211_ops { int (*set_default_mgmt_key)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index); + int (*set_default_beacon_key)(struct wiphy *wiphy, + struct net_device *netdev, + u8 key_index); int (*start_ap)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *settings); @@ -3974,8 +4018,7 @@ struct cfg80211_ops { int (*tx_control_port)(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len, - const u8 *dest, const u8 *src, - const __be16 proto, + const u8 *dest, const __be16 proto, const bool noencrypt); int (*get_ftm_responder_stats)(struct wiphy *wiphy, @@ -3990,6 +4033,10 @@ struct cfg80211_ops { struct cfg80211_update_owe_info *owe_info); int (*probe_mesh_link)(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); + int (*set_tid_config)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_tid_config *tid_conf); + int (*reset_tid_config)(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 tids); }; /* @@ -4427,7 +4474,7 @@ struct wiphy_iftype_akm_suites { * note that if your driver uses wiphy_apply_custom_regulatory() * the reg_notifier's request can be passed as NULL * @regd: the driver's regulatory domain, if one was requested via - * the regulatory_hint() API. This can be used by the driver + * the regulatory_hint() API. This can be used by the driver * on the reg_notifier() if it chooses to ignore future * regulatory domain changes caused by other drivers. * @signal_type: signal type reported in &struct cfg80211_bss. @@ -4463,10 +4510,11 @@ struct wiphy_iftype_akm_suites { * the same number of arbitrary MAC addresses. * @registered: protects ->resume and ->suspend sysfs callbacks against * unregister hardware - * @debugfsdir: debugfs directory used for this wiphy, will be renamed - * automatically on wiphy renames - * @dev: (virtual) struct device for this wiphy - * @registered: helps synchronize suspend/resume with wiphy unregister + * @debugfsdir: debugfs directory used for this wiphy (ieee80211/<wiphyname>). + * It will be renamed automatically on wiphy renames + * @dev: (virtual) struct device for this wiphy. The item in + * /sys/class/ieee80211/ points to this. You need use set_wiphy_dev() + * (see below). * @wext: wireless extension handlers * @priv: driver private data (sized according to wiphy_new() parameter) * @interface_modes: bitmask of interfaces types valid for this wiphy, @@ -4577,12 +4625,6 @@ struct wiphy_iftype_akm_suites { * and probe responses. This value should be set if the driver * wishes to limit the number of csa counters. Default (0) means * infinite. - * @max_adj_channel_rssi_comp: max offset of between the channel on which the - * frame was sent and the channel on which the frame was heard for which - * the reported rssi is still valid. If a driver is able to compensate the - * low rssi when a frame is heard on different channel, then it should set - * this variable to the maximal offset for which it can compensate. - * This value should be set in MHz. * @bss_select_support: bitmask indicating the BSS selection criteria supported * by the driver in the .connect() callback. The bit position maps to the * attribute indices defined in &enum nl80211_bss_select_attr. @@ -4602,11 +4644,19 @@ struct wiphy_iftype_akm_suites { * @support_mbssid must be set for this to have any effect. * * @pmsr_capa: peer measurement capabilities + * + * @tid_config_support: describes the per-TID config support that the + * device has + * @tid_config_support.vif: bitmap of attributes (configurations) + * supported by the driver for each vif + * @tid_config_support.peer: bitmap of attributes (configurations) + * supported by the driver for each peer + * @tid_config_support.max_retry: maximum supported retry count for + * long/short retry configuration */ struct wiphy { /* assign these fields before you register the wiphy */ - /* permanent MAC address(es) */ u8 perm_addr[ETH_ALEN]; u8 addr_mask[ETH_ALEN]; @@ -4673,11 +4723,6 @@ struct wiphy { u32 available_antennas_tx; u32 available_antennas_rx; - /* - * Bitmap of supported protocols for probe response offloading - * see &enum nl80211_probe_resp_offload_support_attr. Only valid - * when the wiphy flag @WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD is set. - */ u32 probe_resp_offload; const u8 *extended_capabilities, *extended_capabilities_mask; @@ -4686,16 +4731,10 @@ struct wiphy { const struct wiphy_iftype_ext_capab *iftype_ext_capab; unsigned int num_iftype_ext_capab; - /* If multiple wiphys are registered and you're handed e.g. - * a regular netdev with assigned ieee80211_ptr, you won't - * know whether it points to a wiphy your driver has registered - * or not. Assign this to something global to your driver to - * help determine whether you own this wiphy or not. */ const void *privid; struct ieee80211_supported_band *bands[NUM_NL80211_BANDS]; - /* Lets us get back the wiphy on the callback */ void (*reg_notifier)(struct wiphy *wiphy, struct regulatory_request *request); @@ -4703,14 +4742,10 @@ struct wiphy { const struct ieee80211_regdomain __rcu *regd; - /* the item in /sys/class/ieee80211/ points to this, - * you need use set_wiphy_dev() (see below) */ struct device dev; - /* protects ->resume, ->suspend sysfs callbacks against unregister hw */ bool registered; - /* dir in debugfs: ieee80211/<wiphyname> */ struct dentry *debugfsdir; const struct ieee80211_ht_cap *ht_capa_mod_mask; @@ -4718,7 +4753,6 @@ struct wiphy { struct list_head wdev_list; - /* the network namespace this phy lives in currently */ possible_net_t _net; #ifdef CONFIG_CFG80211_WEXT @@ -4734,7 +4768,6 @@ struct wiphy { u16 max_ap_assoc_sta; u8 max_num_csa_counters; - u8 max_adj_channel_rssi_comp; u32 bss_select_support; @@ -4751,6 +4784,13 @@ struct wiphy { const struct cfg80211_pmsr_capabilities *pmsr_capa; + struct { + u64 peer, vif; + u8 max_retry; + } tid_config_support; + + u8 max_data_retry_count; + char priv[0] __aligned(NETDEV_ALIGN); }; @@ -5526,9 +5566,9 @@ void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr); * @wiphy: the wireless device giving the hint (used only for reporting * conflicts) * @alpha2: the ISO/IEC 3166 alpha2 the driver claims its regulatory domain - * should be in. If @rd is set this should be NULL. Note that if you - * set this to NULL you should still set rd->alpha2 to some accepted - * alpha2. + * should be in. If @rd is set this should be NULL. Note that if you + * set this to NULL you should still set rd->alpha2 to some accepted + * alpha2. * * Wireless drivers can use this function to hint to the wireless core * what it believes should be the current regulatory domain by diff --git a/include/net/devlink.h b/include/net/devlink.h index 149c108be66f..c9ca86b054bc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -16,6 +16,7 @@ #include <linux/workqueue.h> #include <linux/refcount.h> #include <net/net_namespace.h> +#include <net/flow_offload.h> #include <uapi/linux/devlink.h> struct devlink_ops; @@ -541,6 +542,7 @@ struct devlink_trap_group { }; #define DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT BIT(0) +#define DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE BIT(1) /** * struct devlink_trap - Immutable packet trap attributes. @@ -596,6 +598,8 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_NON_ROUTABLE, DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR, DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP, + DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -610,6 +614,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -671,6 +676,10 @@ enum devlink_trap_group_generic_id { "decap_error" #define DEVLINK_TRAP_GENERIC_NAME_OVERLAY_SMAC_MC \ "overlay_smac_is_mc" +#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_FLOW_ACTION_DROP \ + "ingress_flow_action_drop" +#define DEVLINK_TRAP_GENERIC_NAME_EGRESS_FLOW_ACTION_DROP \ + "egress_flow_action_drop" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -680,6 +689,8 @@ enum devlink_trap_group_generic_id { "buffer_drops" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_TUNNEL_DROPS \ "tunnel_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_DROPS \ + "acl_drops" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \ { \ @@ -1040,9 +1051,9 @@ int devlink_traps_register(struct devlink *devlink, void devlink_traps_unregister(struct devlink *devlink, const struct devlink_trap *traps, size_t traps_count); -void devlink_trap_report(struct devlink *devlink, - struct sk_buff *skb, void *trap_ctx, - struct devlink_port *in_devlink_port); +void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, + void *trap_ctx, struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie); void *devlink_trap_ctx_priv(void *trap_ctx); #if IS_ENABLED(CONFIG_NET_DEVLINK) diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h index 2ab668461463..ddd441a60e03 100644 --- a/include/net/drop_monitor.h +++ b/include/net/drop_monitor.h @@ -6,17 +6,20 @@ #include <linux/ktime.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/flow_offload.h> /** * struct net_dm_hw_metadata - Hardware-supplied packet metadata. * @trap_group_name: Hardware trap group name. * @trap_name: Hardware trap name. * @input_dev: Input netdevice. + * @fa_cookie: Flow action user cookie. */ struct net_dm_hw_metadata { const char *trap_group_name; const char *trap_name; struct net_device *input_dev; + const struct flow_action_cookie *fa_cookie; }; #if IS_ENABLED(CONFIG_NET_DROP_MONITOR) diff --git a/include/net/dsa.h b/include/net/dsa.h index 63495e3443ac..7d3d84f0ef42 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -420,7 +420,9 @@ struct dsa_switch_ops { void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev); + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index c6f7bd22db60..4e864c34a1b0 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -156,6 +156,16 @@ enum flow_action_mangle_base { typedef void (*action_destr)(void *priv); +struct flow_action_cookie { + u32 cookie_len; + u8 cookie[]; +}; + +struct flow_action_cookie *flow_action_cookie_create(void *data, + unsigned int len, + gfp_t gfp); +void flow_action_cookie_destroy(struct flow_action_cookie *cookie); + struct flow_action_entry { enum flow_action_id id; action_destr destructor; @@ -214,6 +224,7 @@ struct flow_action_entry { u8 ttl; } mpls_mangle; }; + struct flow_action_cookie *cookie; /* user defined action cookie */ }; struct flow_action { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index cec1a54401f2..1bf8065fe871 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1027,6 +1027,12 @@ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, st struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); +struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, struct socket *sock, + struct in6_addr *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ce80773dfeb2..5ef34a2ba3c7 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3776,6 +3776,9 @@ enum ieee80211_reconfig_type { * * @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep) * @abort_pmsr: abort peer measurement (this call can sleep) + * @set_tid_config: Apply TID specific configurations. This callback may sleep. + * @reset_tid_config: Reset TID specific configuration for the peer. + * This callback may sleep. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4080,6 +4083,13 @@ struct ieee80211_ops { struct cfg80211_pmsr_request *request); void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request); + int (*set_tid_config)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct cfg80211_tid_config *tid_conf); + int (*reset_tid_config)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, u8 tids); }; /** diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h index 6b4759eae158..9deb3a3735da 100644 --- a/include/net/mpls_iptunnel.h +++ b/include/net/mpls_iptunnel.h @@ -11,7 +11,7 @@ struct mpls_iptunnel_encap { u8 ttl_propagate; u8 default_ttl; u8 reserved1; - u32 label[0]; + u32 label[]; }; static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate) diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index 6ab5a83f597c..0550e0380b8d 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -244,13 +244,13 @@ struct dest_spec_params { struct core_conn_create_dest_spec_params { __u8 type; __u8 length; - __u8 value[0]; + __u8 value[]; } __packed; struct nci_core_conn_create_cmd { __u8 destination_type; __u8 number_destination_params; - struct core_conn_create_dest_spec_params params[0]; + struct core_conn_create_dest_spec_params params[]; } __packed; #define NCI_OP_CORE_CONN_CLOSE_CMD nci_opcode_pack(NCI_GID_CORE, 0x05) @@ -321,7 +321,7 @@ struct nci_core_init_rsp_1 { __u8 status; __le32 nfcc_features; __u8 num_supported_rf_interfaces; - __u8 supported_rf_interfaces[0]; /* variable size array */ + __u8 supported_rf_interfaces[]; /* variable size array */ /* continuted in nci_core_init_rsp_2 */ } __packed; @@ -338,7 +338,7 @@ struct nci_core_init_rsp_2 { struct nci_core_set_config_rsp { __u8 status; __u8 num_params; - __u8 params_id[0]; /* variable size array */ + __u8 params_id[]; /* variable size array */ } __packed; #define NCI_OP_CORE_CONN_CREATE_RSP nci_opcode_pack(NCI_GID_CORE, 0x04) @@ -501,18 +501,18 @@ struct nci_rf_nfcee_action_ntf { __u8 nfcee_id; __u8 trigger; __u8 supported_data_length; - __u8 supported_data[0]; + __u8 supported_data[]; } __packed; #define NCI_OP_NFCEE_DISCOVER_NTF nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00) struct nci_nfcee_supported_protocol { __u8 num_protocol; - __u8 supported_protocol[0]; + __u8 supported_protocol[]; } __packed; struct nci_nfcee_information_tlv { __u8 num_tlv; - __u8 information_tlv[0]; + __u8 information_tlv[]; } __packed; struct nci_nfcee_discover_ntf { diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 5d277d68fd8d..2cd3a261bcbc 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -146,7 +146,7 @@ struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; - u8 params[0]; + u8 params[]; } __packed; struct nfc_genl_data { diff --git a/include/net/route.h b/include/net/route.h index a9c60fc68e36..81750ae50833 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -128,6 +128,12 @@ static inline struct rtable *__ip_route_output_key(struct net *net, struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); +struct rtable *ip_route_output_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, __be32 *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache); + struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index 533f56733ba8..b71b5c4f418c 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -627,7 +627,6 @@ struct iscsi_reject { #define ISCSI_REASON_BOOKMARK_INVALID 9 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10 #define ISCSI_REASON_NEGOTIATION_RESET 11 -#define ISCSI_REASON_WAITING_FOR_LOGOUT 12 /* Max. number of Key=Value pairs in a text message */ #define MAX_KEY_VALUE_PAIRS 8192 diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ae37fd4d194a..be2a2948f452 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -252,6 +252,8 @@ enum devlink_trap_type { enum { /* Trap can report input port as metadata */ DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT, + /* Trap can report flow action cookie as metadata */ + DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE, }; enum devlink_attr { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 024af2d1d0af..61e0801c82df 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -590,6 +590,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 8bf79a9eb234..66048cc5d7b3 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -92,6 +92,7 @@ enum net_dm_attr { NET_DM_ATTR_HW_TRAP_COUNT, /* u32 */ NET_DM_ATTR_SW_DROPS, /* flag */ NET_DM_ATTR_HW_DROPS, /* flag */ + NET_DM_ATTR_FLOW_ACTION_COOKIE, /* binary */ __NET_DM_ATTR_MAX, NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 158bccb4a47b..b002ef2060fa 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -265,6 +265,29 @@ */ /** + * DOC: TID configuration + * + * TID config support can be checked in the %NL80211_ATTR_TID_CONFIG + * attribute given in wiphy capabilities. + * + * The necessary configuration parameters are mentioned in + * &enum nl80211_tid_config_attr and it will be passed to the + * %NL80211_CMD_SET_TID_CONFIG command in %NL80211_ATTR_TID_CONFIG. + * + * If the configuration needs to be applied for specific peer then the MAC + * address of the peer needs to be passed in %NL80211_ATTR_MAC, otherwise the + * configuration will be applied for all the connected peers in the vif except + * any peers that have peer specific configuration for the TID by default; if + * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer specific values + * will be overwritten. + * + * All this configuration is valid only for STA's current connection + * i.e. the configuration will be reset to default when the STA connects back + * after disconnection/roaming, and this configuration will be cleared when + * the interface goes down. + */ + +/** * enum nl80211_commands - supported nl80211 commands * * @NL80211_CMD_UNSPEC: unspecified command to catch errors @@ -1039,14 +1062,11 @@ * a control port frame and as a notification that a control port frame * has been received. %NL80211_ATTR_FRAME is used to specify the * frame contents. The frame is the raw EAPoL data, without ethernet or - * 802.11 headers. An optional %NL80211_ATTR_SRC_MAC can be used to send - * pre-auth frames to STAs on behalf of other APs. + * 802.11 headers. * When used as an event indication %NL80211_ATTR_CONTROL_PORT_ETHERTYPE, * %NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT and %NL80211_ATTR_MAC are added * indicating the protocol type of the received frame; whether the frame * was received unencrypted and the MAC address of the peer respectively. - * %NL80211_ATTR_DST_MAC can be used to forward pre-auth frames in - * userspace while using AP mode. * * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded. * @@ -1128,6 +1148,9 @@ * peer MAC address and %NL80211_ATTR_FRAME is used to specify the frame * content. The frame is ethernet data. * + * @NL80211_CMD_SET_TID_CONFIG: Data frame TID specific configuration + * is passed using %NL80211_ATTR_TID_CONFIG attribute. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1352,6 +1375,8 @@ enum nl80211_commands { NL80211_CMD_PROBE_MESH_LINK, + NL80211_CMD_SET_TID_CONFIG, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2412,8 +2437,10 @@ enum nl80211_commands { * %NL80211_ATTR_AKM_SUITES are default capabilities if AKM suites not * advertised for a specific interface type. * - * @NL80211_ATTR_SRC_MAC: MAC address used in control port over nl80211 transmit - * @NL80211_ATTR_DST_MAC: MAC address used in control port over nl80211 receive + * @NL80211_ATTR_TID_CONFIG: TID specific configuration in a + * nested attribute with &enum nl80211_tid_config_attr sub-attributes; + * on output (in wiphy attributes) it contains only the feature sub- + * attributes. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2883,8 +2910,7 @@ enum nl80211_attrs { NL80211_ATTR_IFTYPE_AKM_SUITES, - NL80211_ATTR_SRC_MAC, - NL80211_ATTR_DST_MAC, + NL80211_ATTR_TID_CONFIG, /* add attributes here, update the policy in nl80211.c */ @@ -4559,6 +4585,7 @@ enum nl80211_key_default_types { * See &enum nl80211_key_default_types. * @NL80211_KEY_MODE: the mode from enum nl80211_key_mode. * Defaults to @NL80211_KEY_RX_TX. + * @NL80211_KEY_DEFAULT_BEACON: flag indicating default Beacon frame key * * @__NL80211_KEY_AFTER_LAST: internal * @NL80211_KEY_MAX: highest key attribute @@ -4574,6 +4601,7 @@ enum nl80211_key_attributes { NL80211_KEY_TYPE, NL80211_KEY_DEFAULT_TYPES, NL80211_KEY_MODE, + NL80211_KEY_DEFAULT_BEACON, /* keep last */ __NL80211_KEY_AFTER_LAST, @@ -4730,6 +4758,69 @@ enum nl80211_tx_power_setting { }; /** + * enum nl80211_tid_config - TID config state + * @NL80211_TID_CONFIG_ENABLE: Enable config for the TID + * @NL80211_TID_CONFIG_DISABLE: Disable config for the TID + */ +enum nl80211_tid_config { + NL80211_TID_CONFIG_ENABLE, + NL80211_TID_CONFIG_DISABLE, +}; + +/* enum nl80211_tid_config_attr - TID specific configuration. + * @NL80211_TID_CONFIG_ATTR_PAD: pad attribute for 64-bit values + * @NL80211_TID_CONFIG_ATTR_VIF_SUPP: a bitmap (u64) of attributes supported + * for per-vif configuration; doesn't list the ones that are generic + * (%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE). + * @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but + * per peer instead. + * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if no peer + * is selected, if set indicates that the new configuration overrides + * all previous peer configurations, otherwise previous peer specific + * configurations should be left untouched. If peer is selected then + * it will reset particular TID configuration of that peer and it will + * not accept other TID config attributes along with peer. + * @NL80211_TID_CONFIG_ATTR_TIDS: a bitmask value of TIDs (bit 0 to 7) + * Its type is u16. + * @NL80211_TID_CONFIG_ATTR_NOACK: Configure ack policy for the TID. + * specified in %NL80211_TID_CONFIG_ATTR_TID. see %enum nl80211_tid_config. + * Its type is u8. + * @NL80211_TID_CONFIG_ATTR_RETRY_SHORT: Number of retries used with data frame + * transmission, user-space sets this configuration in + * &NL80211_CMD_SET_TID_CONFIG. It is u8 type, min value is 1 and + * the max value is advertised by the driver in this attribute on + * output in wiphy capabilities. + * @NL80211_TID_CONFIG_ATTR_RETRY_LONG: Number of retries used with data frame + * transmission, user-space sets this configuration in + * &NL80211_CMD_SET_TID_CONFIG. Its type is u8, min value is 1 and + * the max value is advertised by the driver in this attribute on + * output in wiphy capabilities. + * @NL80211_TID_CONFIG_ATTR_AMPDU_CTRL: Enable/Disable aggregation for the TIDs + * specified in %NL80211_TID_CONFIG_ATTR_TIDS. Its type is u8, using + * the values from &nl80211_tid_config. + * @NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL: Enable/Disable RTS_CTS for the TIDs + * specified in %NL80211_TID_CONFIG_ATTR_TIDS. It is u8 type, using + * the values from &nl80211_tid_config. + */ +enum nl80211_tid_config_attr { + __NL80211_TID_CONFIG_ATTR_INVALID, + NL80211_TID_CONFIG_ATTR_PAD, + NL80211_TID_CONFIG_ATTR_VIF_SUPP, + NL80211_TID_CONFIG_ATTR_PEER_SUPP, + NL80211_TID_CONFIG_ATTR_OVERRIDE, + NL80211_TID_CONFIG_ATTR_TIDS, + NL80211_TID_CONFIG_ATTR_NOACK, + NL80211_TID_CONFIG_ATTR_RETRY_SHORT, + NL80211_TID_CONFIG_ATTR_RETRY_LONG, + NL80211_TID_CONFIG_ATTR_AMPDU_CTRL, + NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL, + + /* keep last */ + __NL80211_TID_CONFIG_ATTR_AFTER_LAST, + NL80211_TID_CONFIG_ATTR_MAX = __NL80211_TID_CONFIG_ATTR_AFTER_LAST - 1 +}; + +/** * enum nl80211_packet_pattern_attr - packet pattern attribute * @__NL80211_PKTPAT_INVALID: invalid number for nested attribute * @NL80211_PKTPAT_PATTERN: the pattern, values where the mask has @@ -5548,9 +5639,8 @@ enum nl80211_feature_flags { * feature, which prevents bufferbloat by using the expected transmission * time to limit the amount of data buffered in the hardware. * - * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_MAC_ADDRS: The driver - * can use src and dst MAC addresses with control port over nl80211 rx - * and tx operations. + * @NL80211_EXT_FEATURE_BEACON_PROTECTION: The driver supports Beacon protection + * and can receive key configuration for BIGTK using key indexes 6 and 7. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -5599,7 +5689,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SAE_OFFLOAD, NL80211_EXT_FEATURE_VLAN_OFFLOAD, NL80211_EXT_FEATURE_AQL, - NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_MAC_ADDRS, + NL80211_EXT_FEATURE_BEACON_PROTECTION, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/init/Kconfig b/init/Kconfig index 452bc1835cd4..20a6ac33761c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1226,13 +1226,12 @@ endif config BOOT_CONFIG bool "Boot config support" - depends on BLK_DEV_INITRD - default y + select BLK_DEV_INITRD help Extra boot config allows system admin to pass a config file as complemental extension of kernel cmdline when booting. The boot config file must be attached at the end of initramfs - with checksum and size. + with checksum, size and magic word. See <file:Documentation/admin-guide/bootconfig.rst> for details. If unsure, say Y. diff --git a/init/main.c b/init/main.c index f95b014a5479..ee4947af823f 100644 --- a/init/main.c +++ b/init/main.c @@ -268,7 +268,6 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, { struct xbc_node *knode, *vnode; char *end = buf + size; - char c = '\"'; const char *val; int ret; @@ -279,25 +278,20 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, return ret; vnode = xbc_node_get_child(knode); - ret = snprintf(buf, rest(buf, end), "%s%c", xbc_namebuf, - vnode ? '=' : ' '); - if (ret < 0) - return ret; - buf += ret; - if (!vnode) + if (!vnode) { + ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf); + if (ret < 0) + return ret; + buf += ret; continue; - - c = '\"'; + } xbc_array_for_each_value(vnode, val) { - ret = snprintf(buf, rest(buf, end), "%c%s", c, val); + ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ", + xbc_namebuf, val); if (ret < 0) return ret; buf += ret; - c = ','; } - if (rest(buf, end) > 2) - strcpy(buf, "\" "); - buf += 2; } return buf - (end - size); @@ -335,7 +329,7 @@ static char * __init xbc_make_cmdline(const char *key) return new_cmdline; } -u32 boot_config_checksum(unsigned char *p, u32 size) +static u32 boot_config_checksum(unsigned char *p, u32 size) { u32 ret = 0; @@ -374,7 +368,11 @@ static void __init setup_boot_config(const char *cmdline) if (!initrd_end) goto not_found; - hdr = (u32 *)(initrd_end - 8); + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + goto not_found; + + hdr = (u32 *)(data - 8); size = hdr[0]; csum = hdr[1]; @@ -418,6 +416,14 @@ not_found: } #else #define setup_boot_config(cmdline) do { } while (0) + +static int __init warn_bootconfig(char *str) +{ + pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOTCONFIG is not set.\n"); + return 0; +} +early_param("bootconfig", warn_bootconfig); + #endif /* Change NUL term back to "=", to make "param" the whole string. */ diff --git a/kernel/audit.c b/kernel/audit.c index 17b0d523afb3..9ddfe2aa6671 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1101,13 +1101,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature audit_log_end(ab); } -static int audit_set_feature(struct sk_buff *skb) +static int audit_set_feature(struct audit_features *uaf) { - struct audit_features *uaf; int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); - uaf = nlmsg_data(nlmsg_hdr(skb)); /* if there is ever a version 2 we should handle that here */ @@ -1175,6 +1173,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; void *data; + int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; @@ -1188,6 +1187,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); + data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { @@ -1211,7 +1211,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) @@ -1315,7 +1315,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; break; case AUDIT_SET_FEATURE: - err = audit_set_feature(skb); + if (data_len < sizeof(struct audit_features)) + return -EINVAL; + err = audit_set_feature(data); if (err) return err; break; @@ -1327,6 +1329,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ + char *str = data; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); @@ -1334,26 +1338,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; } audit_log_user_recv_msg(&ab, msg_type); - if (msg_type != AUDIT_USER_TTY) + if (msg_type != AUDIT_USER_TTY) { + /* ensure NULL termination */ + str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, - (char *)data); - else { - int size; - + str); + } else { audit_log_format(ab, " data="); - size = nlmsg_len(nlh); - if (size > 0 && - ((unsigned char *)data)[size - 1] == '\0') - size--; - audit_log_n_untrustedstring(ab, data, size); + if (data_len > 0 && str[data_len - 1] == '\0') + data_len--; + audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: - if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, @@ -1365,7 +1367,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_log_end(ab); return -EPERM; } - err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh)); + err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); @@ -1380,7 +1382,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; - size_t msglen = nlmsg_len(nlh); + size_t msglen = data_len; char *old, *new; err = -EINVAL; @@ -1456,7 +1458,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b0126e9c0743..026e34da4ace 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -456,6 +456,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 f_val; err = -EINVAL; @@ -464,12 +465,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; f->type = data->fields[i]; - f->val = data->values[i]; + f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; - f->val = 0; + f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } @@ -485,7 +486,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: - f->uid = make_kuid(current_user_ns(), f->val); + f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; @@ -494,11 +495,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: - f->gid = make_kgid(current_user_ns(), f->val); + f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: + f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: @@ -511,11 +513,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } + entry->rule.buflen += f_val; + f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they @@ -524,68 +528,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; - } - if (err) { - kfree(str); + } else if (err) goto exit_free; - } else - f->lsm_str = str; break; case AUDIT_WATCH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - - err = audit_to_watch(&entry->rule, str, f->val, f->op); + } + err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } + entry->rule.buflen += f_val; break; case AUDIT_DIR: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; + entry->rule.buflen += f_val; break; case AUDIT_INODE: + f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: - if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; + } + entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: - if (entry->rule.exe || f->val > PATH_MAX) + if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); + str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } - entry->rule.buflen += f->val; - - audit_mark = audit_alloc_mark(&entry->rule, str, f->val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } + entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; + default: + f->val = f_val; + break; } } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 3924fbe829d4..c9d8eb7f5c02 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -128,8 +128,6 @@ static inline void unregister_handler_proc(unsigned int irq, extern bool irq_can_set_affinity_usr(unsigned int irq); -extern int irq_select_affinity_usr(unsigned int irq); - extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3089a60ea8f9..7eee98c38f25 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -481,23 +481,9 @@ int irq_setup_affinity(struct irq_desc *desc) { return irq_select_affinity(irq_desc_get_irq(desc)); } -#endif +#endif /* CONFIG_AUTO_IRQ_AFFINITY */ +#endif /* CONFIG_SMP */ -/* - * Called when a bogus affinity is set via /proc/irq - */ -int irq_select_affinity_usr(unsigned int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&desc->lock, flags); - ret = irq_setup_affinity(desc); - raw_spin_unlock_irqrestore(&desc->lock, flags); - return ret; -} -#endif /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 9e5783d98033..32c071d7bc03 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -111,6 +111,28 @@ static int irq_affinity_list_proc_show(struct seq_file *m, void *v) return show_irq_affinity(AFFINITY_LIST, m); } +#ifndef CONFIG_AUTO_IRQ_AFFINITY +static inline int irq_select_affinity_usr(unsigned int irq) +{ + /* + * If the interrupt is started up already then this fails. The + * interrupt is assigned to an online CPU already. There is no + * point to move it around randomly. Tell user space that the + * selected mask is bogus. + * + * If not then any change to the affinity is pointless because the + * startup code invokes irq_setup_affinity() which will select + * a online CPU anyway. + */ + return -EINVAL; +} +#else +/* ALPHA magic affinity auto selector. Keep it for historical reasons. */ +static inline int irq_select_affinity_usr(unsigned int irq) +{ + return irq_select_affinity(irq); +} +#endif static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) diff --git a/kernel/signal.c b/kernel/signal.c index 9ad8dea93dbb..5b2396350dd1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -413,27 +413,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi { struct sigqueue *q = NULL; struct user_struct *user; + int sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. + * + * NOTE! A pending signal will hold on to the user refcount, + * and we get/put the refcount only when the sigpending count + * changes from/to zero. */ rcu_read_lock(); - user = get_uid(__task_cred(t)->user); - atomic_inc(&user->sigpending); + user = __task_cred(t)->user; + sigpending = atomic_inc_return(&user->sigpending); + if (sigpending == 1) + get_uid(user); rcu_read_unlock(); - if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { - atomic_dec(&user->sigpending); - free_uid(user); + if (atomic_dec_and_test(&user->sigpending)) + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; @@ -447,8 +452,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - atomic_dec(&q->user->sigpending); - free_uid(q->user); + if (atomic_dec_and_test(&q->user->sigpending)) + free_uid(q->user); kmem_cache_free(sigqueue_cachep, q); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d396aaaf19a3..ad5b88a53c5a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -805,15 +805,6 @@ static struct ctl_table kern_table[] = { .extra2 = &maxolduid, }, #ifdef CONFIG_S390 -#ifdef CONFIG_MATHEMU - { - .procname = "ieee_emulation_warnings", - .data = &sysctl_ieee_emulation_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif { .procname = "userprocess_debug", .data = &show_unhandled_signals, diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 91e885194dbc..402eef84c859 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -143,8 +143,8 @@ if FTRACE config BOOTTIME_TRACING bool "Boot-time Tracing support" - depends on BOOT_CONFIG && TRACING - default y + depends on TRACING + select BOOT_CONFIG help Enable developer to setup ftrace subsystem via supplemental kernel cmdline at boot time for debugging (tracing) driver diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 4aefe003cb7c..7d56d621ffea 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -111,11 +111,11 @@ static int __init test_gen_synth_cmd(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"hula hoops"; /* next_comm_field */ + vals[1] = (u64)(long)"hula hoops"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed"; /* my_string_field */ vals[6] = 598; /* my_int_field */ /* Now generate a gen_synth_test event */ @@ -218,11 +218,11 @@ static int __init test_empty_synth_event(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed_2.0"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed_2.0"; /* my_string_field */ vals[6] = 399; /* my_int_field */ /* Now trace an empty_synth_test event */ @@ -290,11 +290,11 @@ static int __init test_create_synth_event(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed"; /* my_string_field */ vals[6] = 398; /* my_int_field */ /* Now generate a create_synth_test event */ @@ -330,7 +330,7 @@ static int __init test_add_next_synth_val(void) goto out; /* next_comm_field */ - ret = synth_event_add_next_val((u64)"slinky", &trace_state); + ret = synth_event_add_next_val((u64)(long)"slinky", &trace_state); if (ret) goto out; @@ -345,12 +345,12 @@ static int __init test_add_next_synth_val(void) goto out; /* cpu */ - ret = synth_event_add_next_val(smp_processor_id(), &trace_state); + ret = synth_event_add_next_val(raw_smp_processor_id(), &trace_state); if (ret) goto out; /* my_string_field */ - ret = synth_event_add_next_val((u64)"thneed_2.01", &trace_state); + ret = synth_event_add_next_val((u64)(long)"thneed_2.01", &trace_state); if (ret) goto out; @@ -388,7 +388,7 @@ static int __init test_add_synth_val(void) if (ret) goto out; - ret = synth_event_add_val("cpu", smp_processor_id(), &trace_state); + ret = synth_event_add_val("cpu", raw_smp_processor_id(), &trace_state); if (ret) goto out; @@ -396,12 +396,12 @@ static int __init test_add_synth_val(void) if (ret) goto out; - ret = synth_event_add_val("next_comm_field", (u64)"silly putty", + ret = synth_event_add_val("next_comm_field", (u64)(long)"silly putty", &trace_state); if (ret) goto out; - ret = synth_event_add_val("my_string_field", (u64)"thneed_9", + ret = synth_event_add_val("my_string_field", (u64)(long)"thneed_9", &trace_state); if (ret) goto out; @@ -423,13 +423,13 @@ static int __init test_trace_synth_event(void) /* Trace some bogus values just for testing */ ret = synth_event_trace(create_synth_test, 7, /* number of values */ - 444, /* next_pid_field */ - (u64)"clackers", /* next_comm_field */ - 1000000, /* ts_ns */ - 1000, /* ts_ms */ - smp_processor_id(), /* cpu */ - (u64)"Thneed", /* my_string_field */ - 999); /* my_int_field */ + (u64)444, /* next_pid_field */ + (u64)(long)"clackers", /* next_comm_field */ + (u64)1000000, /* ts_ns */ + (u64)1000, /* ts_ms */ + (u64)raw_smp_processor_id(), /* cpu */ + (u64)(long)"Thneed", /* my_string_field */ + (u64)999); /* my_int_field */ return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c797a15a1fc7..6b11e4e2150c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1837,6 +1837,7 @@ static __init int init_trace_selftests(void) pr_info("Running postponed tracer tests:\n"); + tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { /* This loop can take minutes when sanitizers are enabled, so * lets make sure we allow RCU processing. @@ -1859,6 +1860,7 @@ static __init int init_trace_selftests(void) list_del(&p->list); kfree(p); } + tracing_selftest_running = false; out: mutex_unlock(&trace_types_lock); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 483b3fd1094f..5f6834a2bf41 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -821,6 +821,29 @@ static const char *synth_field_fmt(char *type) return fmt; } +static void print_synth_event_num_val(struct trace_seq *s, + char *print_fmt, char *name, + int size, u64 val, char *space) +{ + switch (size) { + case 1: + trace_seq_printf(s, print_fmt, name, (u8)val, space); + break; + + case 2: + trace_seq_printf(s, print_fmt, name, (u16)val, space); + break; + + case 4: + trace_seq_printf(s, print_fmt, name, (u32)val, space); + break; + + default: + trace_seq_printf(s, print_fmt, name, val, space); + break; + } +} + static enum print_line_t print_synth_event(struct trace_iterator *iter, int flags, struct trace_event *event) @@ -859,10 +882,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, } else { struct trace_print_flags __flags[] = { __def_gfpflag_names, {-1, NULL} }; + char *space = (i == se->n_fields - 1 ? "" : " "); - trace_seq_printf(s, print_fmt, se->fields[i]->name, - entry->fields[n_u64], - i == se->n_fields - 1 ? "" : " "); + print_synth_event_num_val(s, print_fmt, + se->fields[i]->name, + se->fields[i]->size, + entry->fields[n_u64], + space); if (strcmp(se->fields[i]->type, "gfp_t") == 0) { trace_seq_puts(s, " ("); @@ -1805,6 +1831,8 @@ __synth_event_trace_start(struct trace_event_file *file, int entry_size, fields_size = 0; int ret = 0; + memset(trace_state, '\0', sizeof(*trace_state)); + /* * Normal event tracing doesn't get called at all unless the * ENABLED bit is set (which attaches the probe thus allowing @@ -1885,6 +1913,11 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) return ret; } + if (n_vals != state.event->n_fields) { + ret = -EINVAL; + goto out; + } + va_start(args, n_vals); for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { u64 val; @@ -1898,12 +1931,30 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - state.entry->fields[n_u64] = val; + struct synth_field *field = state.event->fields[i]; + + switch (field->size) { + case 1: + *(u8 *)&state.entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&state.entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&state.entry->fields[n_u64] = (u32)val; + break; + + default: + state.entry->fields[n_u64] = val; + break; + } n_u64++; } } va_end(args); - +out: __synth_event_trace_end(&state); return ret; @@ -1942,6 +1993,11 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals, return ret; } + if (n_vals != state.event->n_fields) { + ret = -EINVAL; + goto out; + } + for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { if (state.event->fields[i]->is_string) { char *str_val = (char *)(long)vals[i]; @@ -1950,11 +2006,30 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals, strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - state.entry->fields[n_u64] = vals[i]; + struct synth_field *field = state.event->fields[i]; + u64 val = vals[i]; + + switch (field->size) { + case 1: + *(u8 *)&state.entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&state.entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&state.entry->fields[n_u64] = (u32)val; + break; + + default: + state.entry->fields[n_u64] = val; + break; + } n_u64++; } } - +out: __synth_event_trace_end(&state); return ret; @@ -1997,8 +2072,6 @@ int synth_event_trace_start(struct trace_event_file *file, if (!trace_state) return -EINVAL; - memset(trace_state, '\0', sizeof(*trace_state)); - ret = __synth_event_trace_start(file, trace_state); if (ret == -ENOENT) ret = 0; /* just disabled, not really an error */ @@ -2069,8 +2142,25 @@ static int __synth_event_add_val(const char *field_name, u64 val, str_field = (char *)&entry->fields[field->offset]; strscpy(str_field, str_val, STR_VAR_LEN_MAX); - } else - entry->fields[field->offset] = val; + } else { + switch (field->size) { + case 1: + *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val; + break; + + case 2: + *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val; + break; + + case 4: + *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val; + break; + + default: + trace_state->entry->fields[field->offset] = val; + break; + } + } out: return ret; } diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 3ea601a2eba5..ec3ce7fd299f 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -533,7 +533,7 @@ struct xbc_node *find_match_node(struct xbc_node *node, char *k) static int __init __xbc_add_key(char *k) { - struct xbc_node *node; + struct xbc_node *node, *child; if (!xbc_valid_keyword(k)) return xbc_parse_error("Invalid keyword", k); @@ -543,8 +543,12 @@ static int __init __xbc_add_key(char *k) if (!last_parent) /* the first level */ node = find_match_node(xbc_nodes, k); - else - node = find_match_node(xbc_node_get_child(last_parent), k); + else { + child = xbc_node_get_child(last_parent); + if (child && xbc_node_is_value(child)) + return xbc_parse_error("Subkey is mixed with value", k); + node = find_match_node(child, k); + } if (node) last_parent = node; @@ -574,10 +578,10 @@ static int __init __xbc_parse_keys(char *k) return __xbc_add_key(k); } -static int __init xbc_parse_kv(char **k, char *v) +static int __init xbc_parse_kv(char **k, char *v, int op) { struct xbc_node *prev_parent = last_parent; - struct xbc_node *node; + struct xbc_node *child; char *next; int c, ret; @@ -585,12 +589,19 @@ static int __init xbc_parse_kv(char **k, char *v) if (ret) return ret; + child = xbc_node_get_child(last_parent); + if (child) { + if (xbc_node_is_key(child)) + return xbc_parse_error("Value is mixed with subkey", v); + else if (op == '=') + return xbc_parse_error("Value is redefined", v); + } + c = __xbc_parse_value(&v, &next); if (c < 0) return c; - node = xbc_add_sibling(v, XBC_VALUE); - if (!node) + if (!xbc_add_sibling(v, XBC_VALUE)) return -ENOMEM; if (c == ',') { /* Array */ @@ -763,7 +774,7 @@ int __init xbc_init(char *buf) p = buf; do { - q = strpbrk(p, "{}=;\n#"); + q = strpbrk(p, "{}=+;\n#"); if (!q) { p = skip_spaces(p); if (*p != '\0') @@ -774,8 +785,15 @@ int __init xbc_init(char *buf) c = *q; *q++ = '\0'; switch (c) { + case '+': + if (*q++ != '=') { + ret = xbc_parse_error("Wrong '+' operator", + q - 2); + break; + } + /* Fall through */ case '=': - ret = xbc_parse_kv(&p, q); + ret = xbc_parse_kv(&p, q, c); break; case '{': ret = xbc_open_brace(&p, q); diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c index 6d83cafebc69..ad0699ce702f 100644 --- a/lib/crypto/chacha20poly1305.c +++ b/lib/crypto/chacha20poly1305.c @@ -235,6 +235,9 @@ bool chacha20poly1305_crypt_sg_inplace(struct scatterlist *src, __le64 lens[2]; } b __aligned(16); + if (WARN_ON(src_len > INT_MAX)) + return false; + chacha_load_key(b.k, key); b.iv[0] = 0; diff --git a/mm/mmap.c b/mm/mmap.c index 6756b8bb0033..d681a20eb4ea 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -195,8 +195,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) bool downgraded = false; LIST_HEAD(uf); - brk = untagged_addr(brk); - if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -1557,8 +1555,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, struct file *file = NULL; unsigned long retval; - addr = untagged_addr(addr); - if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); diff --git a/mm/mremap.c b/mm/mremap.c index 122938dcec15..af363063ea23 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -607,7 +607,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, LIST_HEAD(uf_unmap); addr = untagged_addr(addr); - new_addr = untagged_addr(new_addr); if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; diff --git a/mm/shmem.c b/mm/shmem.c index c8f7540ef048..aad3ba74b0e9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3386,8 +3386,6 @@ static const struct constant_table shmem_param_enums_huge[] = { {"always", SHMEM_HUGE_ALWAYS }, {"within_size", SHMEM_HUGE_WITHIN_SIZE }, {"advise", SHMEM_HUGE_ADVISE }, - {"deny", SHMEM_HUGE_DENY }, - {"force", SHMEM_HUGE_FORCE }, {} }; diff --git a/net/802/psnap.c b/net/802/psnap.c index 40ab2aea7b31..4492e8d7ad20 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -30,7 +30,7 @@ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; - list_for_each_entry_rcu(p, &snap_list, node) { + list_for_each_entry_rcu(p, &snap_list, node, lockdep_is_held(&snap_lock)) { if (!memcmp(p->type, desc, 5)) { proto = p; break; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index dc3d2c1dd9d5..0e3dbc5f3c34 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,7 +34,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const struct nf_br_ops *nf_ops; u8 state = BR_STATE_FORWARDING; const unsigned char *dest; - struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -54,15 +53,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->frag_max_size = 0; skb_reset_mac_header(skb); - eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state)) goto out; if (IS_ENABLED(CONFIG_INET) && - (eth->h_proto == htons(ETH_P_ARP) || - eth->h_proto == htons(ETH_P_RARP)) && + (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) || + eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); } else if (IS_ENABLED(CONFIG_IPV6) && diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 3415a4896c59..756b63b6f7b3 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -61,7 +61,7 @@ struct bpf_sk_storage_data { * the number of cachelines access during the cache hit case. */ struct bpf_sk_storage_map __rcu *smap; - u8 data[0] __aligned(8); + u8 data[] __aligned(8); }; /* Linked to bpf_sk_storage and bpf_sk_storage_map */ diff --git a/net/core/datagram.c b/net/core/datagram.c index a78e7f864c1e..4213081c6ed3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -166,8 +166,6 @@ done: struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), int *off, int *err, struct sk_buff **last) { @@ -198,8 +196,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, refcount_inc(&skb->users); } else { __skb_unlink(skb, queue); - if (destructor) - destructor(sk, skb); } *off = _off; return skb; @@ -212,7 +208,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, * @sk: socket * @queue: socket queue from which to receive * @flags: MSG\_ flags - * @destructor: invoked under the receive lock on successful dequeue * @off: an offset in bytes to peek skb from. Returns an offset * within an skb where data actually starts * @err: error code returned @@ -245,10 +240,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, */ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err, + unsigned int flags, int *off, int *err, struct sk_buff **last) { struct sk_buff *skb; @@ -269,8 +261,8 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, * However, this function was correct in any case. 8) */ spin_lock_irqsave(&queue->lock, cpu_flags); - skb = __skb_try_recv_from_queue(sk, queue, flags, destructor, - off, &error, last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, &error, + last); spin_unlock_irqrestore(&queue->lock, cpu_flags); if (error) goto no_packet; @@ -293,10 +285,7 @@ EXPORT_SYMBOL(__skb_try_recv_datagram); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err) + unsigned int flags, int *off, int *err) { struct sk_buff *skb, *last; long timeo; @@ -304,8 +293,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - skb = __skb_try_recv_datagram(sk, sk_queue, flags, destructor, - off, err, &last); + skb = __skb_try_recv_datagram(sk, sk_queue, flags, off, err, + &last); if (skb) return skb; @@ -326,7 +315,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, return __skb_recv_datagram(sk, &sk->sk_receive_queue, flags | (noblock ? MSG_DONTWAIT : 0), - NULL, &off, err); + &off, err); } EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index e10bd680dc03..25dab1598803 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3076,6 +3076,8 @@ static u16 skb_tx_hash(const struct net_device *dev, if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); + if (hash >= qoffset) + hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; @@ -4636,7 +4638,6 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) kfree_skb(skb); } } -EXPORT_SYMBOL_GPL(generic_xdp_tx); static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); @@ -10004,6 +10005,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { + struct net *net_old = dev_net(dev); int err, new_nsid, new_ifindex; ASSERT_RTNL(); @@ -10019,7 +10021,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Get out if there is nothing todo */ err = 0; - if (net_eq(dev_net(dev), net)) + if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure @@ -10095,6 +10097,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char err = device_rename(&dev->dev, dev->name); WARN_ON(err); + /* Adapt owner in case owning user namespace of target network + * namespace is different from the original one. + */ + err = netdev_change_owner(dev, net_old, net); + WARN_ON(err); + /* Add the device back in the hashes */ list_netdevice(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 216bdd25ce39..295d761cbfb1 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2103,11 +2103,11 @@ err_action_values_put: static struct devlink_dpipe_table * devlink_dpipe_table_find(struct list_head *dpipe_tables, - const char *table_name) + const char *table_name, struct devlink *devlink) { struct devlink_dpipe_table *table; - - list_for_each_entry_rcu(table, dpipe_tables, list) { + list_for_each_entry_rcu(table, dpipe_tables, list, + lockdep_is_held(&devlink->lock)) { if (!strcmp(table->name, table_name)) return table; } @@ -2226,7 +2226,7 @@ static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -2382,7 +2382,7 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink, struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -4232,7 +4232,7 @@ struct devlink_fmsg_item { int attrtype; u8 nla_type; u16 len; - int value[0]; + int value[]; }; struct devlink_fmsg { @@ -5540,6 +5540,9 @@ static int devlink_trap_metadata_put(struct sk_buff *msg, if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) goto nla_put_failure; + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE)) + goto nla_put_failure; nla_nest_end(msg, attr); @@ -6932,7 +6935,7 @@ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, rcu_read_lock(); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); enabled = false; if (table) enabled = table->counters_enabled; @@ -6956,26 +6959,34 @@ int devlink_dpipe_table_register(struct devlink *devlink, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; - - if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name)) - return -EEXIST; + int err = 0; if (WARN_ON(!table_ops->size_get)) return -EINVAL; + mutex_lock(&devlink->lock); + + if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, + devlink)) { + err = -EEXIST; + goto unlock; + } + table = kzalloc(sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; + if (!table) { + err = -ENOMEM; + goto unlock; + } table->name = table_name; table->table_ops = table_ops; table->priv = priv; table->counter_control_extern = counter_control_extern; - mutex_lock(&devlink->lock); list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); +unlock: mutex_unlock(&devlink->lock); - return 0; + return err; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_register); @@ -6992,7 +7003,7 @@ void devlink_dpipe_table_unregister(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) goto unlock; list_del_rcu(&table->list); @@ -7149,7 +7160,7 @@ int devlink_dpipe_table_resource_set(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) { err = -EINVAL; goto out; @@ -7795,6 +7806,8 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(NON_ROUTABLE, DROP), DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), + DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP), + DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -7808,6 +7821,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(L3_DROPS), DEVLINK_TRAP_GROUP(BUFFER_DROPS), DEVLINK_TRAP_GROUP(TUNNEL_DROPS), + DEVLINK_TRAP_GROUP(ACL_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -8199,12 +8213,14 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, static void devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, const struct devlink_trap_item *trap_item, - struct devlink_port *in_devlink_port) + struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) { struct devlink_trap_group_item *group_item = trap_item->group_item; hw_metadata->trap_group_name = group_item->group->name; hw_metadata->trap_name = trap_item->trap->name; + hw_metadata->fa_cookie = fa_cookie; spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) @@ -8218,9 +8234,12 @@ devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, * @skb: Trapped packet. * @trap_ctx: Trap context. * @in_devlink_port: Input devlink port. + * @fa_cookie: Flow action cookie. Could be NULL. */ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, - void *trap_ctx, struct devlink_port *in_devlink_port) + void *trap_ctx, struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) + { struct devlink_trap_item *trap_item = trap_ctx; struct net_dm_hw_metadata hw_metadata = {}; @@ -8229,7 +8248,7 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, devlink_trap_stats_update(trap_item->group_item->stats, skb->len); devlink_trap_report_metadata_fill(&hw_metadata, trap_item, - in_devlink_port); + in_devlink_port, fa_cookie); net_dm_hw_report(skb, &hw_metadata); } EXPORT_SYMBOL_GPL(devlink_trap_report); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 31700e0c3928..8e33cec9fc4e 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -29,6 +29,7 @@ #include <net/drop_monitor.h> #include <net/genetlink.h> #include <net/netevent.h> +#include <net/flow_offload.h> #include <trace/events/skb.h> #include <trace/events/napi.h> @@ -67,7 +68,7 @@ struct net_dm_hw_entry { struct net_dm_hw_entries { u32 num_entries; - struct net_dm_hw_entry entries[0]; + struct net_dm_hw_entry entries[]; }; struct per_cpu_dm_data { @@ -701,6 +702,13 @@ static void net_dm_packet_work(struct work_struct *work) } static size_t +net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) +{ + return hw_metadata->fa_cookie ? + nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; +} + +static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct net_dm_hw_metadata *hw_metadata) { @@ -717,6 +725,8 @@ net_dm_hw_packet_report_size(size_t payload_len, nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ + net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ @@ -762,6 +772,12 @@ static int net_dm_hw_packet_report_fill(struct sk_buff *msg, goto nla_put_failure; } + if (hw_metadata->fa_cookie && + nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, + hw_metadata->fa_cookie->cookie_len, + hw_metadata->fa_cookie->cookie)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; @@ -794,11 +810,12 @@ nla_put_failure: static struct net_dm_hw_metadata * net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) { + const struct flow_action_cookie *fa_cookie; struct net_dm_hw_metadata *n_hw_metadata; const char *trap_group_name; const char *trap_name; - n_hw_metadata = kmalloc(sizeof(*hw_metadata), GFP_ATOMIC); + n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); if (!n_hw_metadata) return NULL; @@ -812,12 +829,25 @@ net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) goto free_trap_group; n_hw_metadata->trap_name = trap_name; + if (hw_metadata->fa_cookie) { + size_t cookie_size = sizeof(*fa_cookie) + + hw_metadata->fa_cookie->cookie_len; + + fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size, + GFP_ATOMIC); + if (!fa_cookie) + goto free_trap_name; + n_hw_metadata->fa_cookie = fa_cookie; + } + n_hw_metadata->input_dev = hw_metadata->input_dev; if (n_hw_metadata->input_dev) dev_hold(n_hw_metadata->input_dev); return n_hw_metadata; +free_trap_name: + kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: @@ -830,6 +860,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) { if (hw_metadata->input_dev) dev_put(hw_metadata->input_dev); + kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); diff --git a/net/core/filter.c b/net/core/filter.c index 925b23de218b..4a08c9fb2be7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3626,7 +3626,6 @@ err: _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } -EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 45b6a59ac124..d21348202ba6 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -167,6 +167,27 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_enc_opts); +struct flow_action_cookie *flow_action_cookie_create(void *data, + unsigned int len, + gfp_t gfp) +{ + struct flow_action_cookie *cookie; + + cookie = kmalloc(sizeof(*cookie) + len, gfp); + if (!cookie) + return NULL; + cookie->cookie_len = len; + memcpy(cookie->cookie, data, len); + return cookie; +} +EXPORT_SYMBOL(flow_action_cookie_create); + +void flow_action_cookie_destroy(struct flow_action_cookie *cookie) +{ + kfree(cookie); +} +EXPORT_SYMBOL(flow_action_cookie_destroy); + struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4c826b8bf9b1..cf0215734ceb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -944,6 +944,24 @@ err: kobject_put(kobj); return error; } + +static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, + kgid_t kgid) +{ + struct netdev_rx_queue *queue = dev->_rx + index; + struct kobject *kobj = &queue->kobj; + int error; + + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + return error; + + if (dev->sysfs_rx_queue_group) + error = sysfs_group_change_owner( + kobj, dev->sysfs_rx_queue_group, kuid, kgid); + + return error; +} #endif /* CONFIG_SYSFS */ int @@ -981,6 +999,29 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) #endif } +static int net_rx_queue_change_owner(struct net_device *dev, int num, + kuid_t kuid, kgid_t kgid) +{ +#ifdef CONFIG_SYSFS + int error = 0; + int i; + +#ifndef CONFIG_RPS + if (!dev->sysfs_rx_queue_group) + return 0; +#endif + for (i = 0; i < num; i++) { + error = rx_queue_change_owner(dev, i, kuid, kgid); + if (error) + break; + } + + return error; +#else + return 0; +#endif +} + #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. @@ -1486,6 +1527,23 @@ err: kobject_put(kobj); return error; } + +static int tx_queue_change_owner(struct net_device *ndev, int index, + kuid_t kuid, kgid_t kgid) +{ + struct netdev_queue *queue = ndev->_tx + index; + struct kobject *kobj = &queue->kobj; + int error; + + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + return error; + +#ifdef CONFIG_BQL + error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); +#endif + return error; +} #endif /* CONFIG_SYSFS */ int @@ -1520,6 +1578,25 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) #endif /* CONFIG_SYSFS */ } +static int net_tx_queue_change_owner(struct net_device *dev, int num, + kuid_t kuid, kgid_t kgid) +{ +#ifdef CONFIG_SYSFS + int error = 0; + int i; + + for (i = 0; i < num; i++) { + error = tx_queue_change_owner(dev, i, kuid, kgid); + if (error) + break; + } + + return error; +#else + return 0; +#endif /* CONFIG_SYSFS */ +} + static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; @@ -1554,6 +1631,31 @@ error: return error; } +static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) +{ + int error = 0, real_rx = 0, real_tx = 0; + +#ifdef CONFIG_SYSFS + if (ndev->queues_kset) { + error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); + if (error) + return error; + } + real_rx = ndev->real_num_rx_queues; +#endif + real_tx = ndev->real_num_tx_queues; + + error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); + if (error) + return error; + + error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); + if (error) + return error; + + return 0; +} + static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; @@ -1767,6 +1869,37 @@ int netdev_register_kobject(struct net_device *ndev) return error; } +/* Change owner for sysfs entries when moving network devices across network + * namespaces owned by different user namespaces. + */ +int netdev_change_owner(struct net_device *ndev, const struct net *net_old, + const struct net *net_new) +{ + struct device *dev = &ndev->dev; + kuid_t old_uid, new_uid; + kgid_t old_gid, new_gid; + int error; + + net_ns_get_ownership(net_old, &old_uid, &old_gid); + net_ns_get_ownership(net_new, &new_uid, &new_gid); + + /* The network namespace was changed but the owning user namespace is + * identical so there's no need to change the owner of sysfs entries. + */ + if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) + return 0; + + error = device_change_owner(dev, new_uid, new_gid); + if (error) + return error; + + error = queue_change_owner(ndev, new_uid, new_gid); + if (error) + return error; + + return 0; +} + int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 006876c7b78d..8a5b04c2699a 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -8,5 +8,7 @@ void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num); +int netdev_change_owner(struct net_device *, const struct net *net_old, + const struct net *net_new); #endif diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 70f88f2b4456..105f3734dadb 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -95,7 +95,7 @@ void ccid_cleanup_builtins(void); struct ccid { struct ccid_operations *ccid_ops; - char ccid_priv[0]; + char ccid_priv[]; }; static inline void *ccid_priv(const struct ccid *ccid) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 25187528c308..c5c74a34d139 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -216,6 +216,7 @@ EXPORT_SYMBOL_GPL(dccp_check_req); */ int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb) + __releases(child) { int ret = 0; const int state = child->sk_state; diff --git a/net/dsa/port.c b/net/dsa/port.c index 774facb8d547..d4450a454249 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -489,9 +489,11 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, } static void dsa_port_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -502,7 +504,8 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, return; } - ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); + ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev, + speed, duplex, tx_pause, rx_pause); } const struct phylink_mac_ops dsa_port_phylink_mac_ops = { diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 8977fe1f3946..ef9197541cb3 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -305,7 +305,8 @@ nla_put_failure: static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { [ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT }, [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, - [ETHTOOL_A_BITSET_SIZE] = { .type = NLA_U32 }, + [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, + ETHNL_MAX_BITSET_SIZE), [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h index b8247e34109d..b849f9d19676 100644 --- a/net/ethtool/bitset.h +++ b/net/ethtool/bitset.h @@ -3,6 +3,8 @@ #ifndef _NET_ETHTOOL_BITSET_H #define _NET_ETHTOOL_BITSET_H +#define ETHNL_MAX_BITSET_SIZE S16_MAX + typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN]; int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 376882215919..0bd10a1f477f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1724,6 +1724,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1735,7 +1736,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3b9c7a2725a9..47f0502b2101 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,8 +107,6 @@ #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) -#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ebe7060d0fc9..042599cc691d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2774,6 +2774,54 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); +struct rtable *ip_route_output_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, __be32 *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache) +{ +#ifdef CONFIG_DST_CACHE + struct dst_cache *dst_cache; +#endif + struct rtable *rt = NULL; + struct flowi4 fl4; + __u8 tos; + +#ifdef CONFIG_DST_CACHE + dst_cache = (struct dst_cache *)&info->dst_cache; + if (use_cache) { + rt = dst_cache_get_ip4(dst_cache, saddr); + if (rt) + return rt; + } +#endif + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = protocol; + fl4.daddr = info->key.u.ipv4.dst; + fl4.saddr = info->key.u.ipv4.src; + tos = info->key.tos; + fl4.flowi4_tos = RT_TOS(tos); + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) { + netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (rt->dst.dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); + ip_rt_put(rt); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (use_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); +#endif + *saddr = fl4.saddr; + return rt; +} +EXPORT_SYMBOL_GPL(ip_route_output_tunnel); + /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1b685485a5b5..48aa457a9516 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3669,8 +3669,11 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; if (len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; - if (len > sizeof(zc)) + if (len > sizeof(zc)) { len = sizeof(zc); + if (put_user(len, optlen)) + return -EFAULT; + } if (copy_from_user(&zc, optval, len)) return -EFAULT; lock_sock(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 316ebdf8151d..6b6b57000dad 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6124,7 +6124,11 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { struct request_sock *req; - tcp_try_undo_loss(sk, false); + /* If we are still handling the SYNACK RTO, see if timestamp ECR allows + * undo. If peer SACKs triggered fast recovery, we can't undo here. + */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ tcp_sk(sk)->retrans_stamp = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index df1166b76126..52acf0bc2ee5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1019,7 +1019,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, if (!md5sig) return NULL; - hlist_for_each_entry_rcu(key, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) @@ -1064,7 +1065,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 6c43fa189195..2703f24c5d1a 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -22,7 +22,8 @@ static struct tcp_ulp_ops *tcp_ulp_find(const char *name) { struct tcp_ulp_ops *e; - list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + list_for_each_entry_rcu(e, &tcp_ulp_list, list, + lockdep_is_held(&tcp_ulp_list_lock)) { if (strcmp(e->name, name) == 0) return e; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 08a41f1e1cd2..a68e2ac37f26 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1671,10 +1671,11 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, error = -EAGAIN; do { spin_lock_bh(&queue->lock); - skb = __skb_try_recv_from_queue(sk, queue, flags, - udp_skb_destructor, - off, err, &last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, + err, &last); if (skb) { + if (!(flags & MSG_PEEK)) + udp_skb_destructor(sk, skb); spin_unlock_bh(&queue->lock); return skb; } @@ -1692,9 +1693,10 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, queue); - skb = __skb_try_recv_from_queue(sk, queue, flags, - udp_skb_dtor_locked, - off, err, &last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, + err, &last); + if (skb && !(flags & MSG_PEEK)) + udp_skb_dtor_locked(sk, skb); spin_unlock(&sk_queue->lock); spin_unlock_bh(&queue->lock); if (skb) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 95835e8d99aa..871d6e52ec67 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -36,7 +36,7 @@ struct tmp_ext { struct in6_addr saddr; #endif struct in6_addr daddr; - char hdrs[0]; + char hdrs[]; }; struct ah_skb_cb { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 087304427bbb..8a8c2d0cfcc8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -54,6 +54,7 @@ #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> +#include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -1196,6 +1197,75 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); +/** + * ip6_dst_lookup_tunnel - perform route lookup on tunnel + * @skb: Packet for which lookup is done + * @dev: Tunnel device + * @net: Network namespace of tunnel device + * @sk: Socket which provides route info + * @saddr: Memory to store the src ip address + * @info: Tunnel information + * @protocol: IP protocol + * @use_cahce: Flag to enable cache usage + * This function performs a route lookup on a tunnel + * + * It returns a valid dst pointer and stores src address to be used in + * tunnel in param saddr on success, else a pointer encoded error code. + */ + +struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, + struct socket *sock, + struct in6_addr *saddr, + const struct ip_tunnel_info *info, + u8 protocol, + bool use_cache) +{ + struct dst_entry *dst = NULL; +#ifdef CONFIG_DST_CACHE + struct dst_cache *dst_cache; +#endif + struct flowi6 fl6; + __u8 prio; + +#ifdef CONFIG_DST_CACHE + dst_cache = (struct dst_cache *)&info->dst_cache; + if (use_cache) { + dst = dst_cache_get_ip6(dst_cache, saddr); + if (dst) + return dst; + } +#endif + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = protocol; + fl6.daddr = info->key.u.ipv6.dst; + fl6.saddr = info->key.u.ipv6.src; + prio = info->key.tos; + fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio), + info->key.label); + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, + NULL); + if (IS_ERR(dst)) { + netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (use_cache) + dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); +#endif + *saddr = fl6.saddr; + return dst; +} +EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel); + static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index bfa49ff70531..d6483926f449 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -97,7 +97,8 @@ static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \ + lockdep_rtnl_is_held()) static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 79fc012dd2ca..debdaeba5d8c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,9 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol != IPPROTO_TCP) + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } break; - + } else { + break; + } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index ab7f124ff5d7..d8afe7290de8 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -29,7 +29,7 @@ struct seg6_lwt { struct dst_cache cache; - struct seg6_iptunnel_encap tuninfo[0]; + struct seg6_iptunnel_encap tuninfo[]; }; static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt) diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 2db3d50d10a4..10cf7c3dcbb3 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -116,7 +116,7 @@ struct l2tp_session { void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len); void (*session_close)(struct l2tp_session *session); void (*show)(struct seq_file *m, void *priv); - uint8_t priv[0]; /* private data */ + u8 priv[]; /* private data */ }; /* Describes the tunnel. It contains info to track all the associated diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2922d4150d88..54fb8d452a7b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -47,7 +47,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else -#define dprintk(args...) +#define dprintk(args...) do {} while (0) #endif /* Maybe we'll add some more in the future. */ diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index f3a36c16a5e7..a4eccb98220a 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -56,7 +56,7 @@ found: return sk; } -static void *llc_seq_start(struct seq_file *seq, loff_t *pos) +static void *llc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { loff_t l = *pos; diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 57748cab0e28..b31f1021ad9c 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -26,12 +26,20 @@ void ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, { SHASH_DESC_ON_STACK(desc, tfm); u8 out[AES_BLOCK_SIZE]; + const __le16 *fc; desc->tfm = tfm; crypto_shash_init(desc); crypto_shash_update(desc, aad, AAD_LEN); - crypto_shash_update(desc, data, data_len - CMAC_TLEN); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + crypto_shash_update(desc, zero, 8); + crypto_shash_update(desc, data + 8, data_len - 8 - CMAC_TLEN); + } else { + crypto_shash_update(desc, data, data_len - CMAC_TLEN); + } crypto_shash_finup(desc, zero, CMAC_TLEN, out); memcpy(mic, out, CMAC_TLEN); @@ -41,12 +49,21 @@ void ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic) { SHASH_DESC_ON_STACK(desc, tfm); + const __le16 *fc; desc->tfm = tfm; crypto_shash_init(desc); crypto_shash_update(desc, aad, AAD_LEN); - crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + crypto_shash_update(desc, zero, 8); + crypto_shash_update(desc, data + 8, + data_len - 8 - CMAC_TLEN_256); + } else { + crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + } crypto_shash_finup(desc, zero, CMAC_TLEN_256, mic); } diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c index 363ad1c1dc0c..16ba09cb5def 100644 --- a/net/mac80211/aes_gmac.c +++ b/net/mac80211/aes_gmac.c @@ -17,10 +17,11 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, const u8 *data, size_t data_len, u8 *mic) { - struct scatterlist sg[4]; + struct scatterlist sg[5]; u8 *zero, *__aad, iv[AES_BLOCK_SIZE]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); + const __le16 *fc; if (data_len < GMAC_MIC_LEN) return -EINVAL; @@ -33,11 +34,22 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, __aad = zero + GMAC_MIC_LEN; memcpy(__aad, aad, GMAC_AAD_LEN); - sg_init_table(sg, 4); - sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); - sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); - sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); - sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + sg_init_table(sg, 5); + sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); + sg_set_buf(&sg[1], zero, 8); + sg_set_buf(&sg[2], data + 8, data_len - 8 - GMAC_MIC_LEN); + sg_set_buf(&sg[3], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[4], mic, GMAC_MIC_LEN); + } else { + sg_init_table(sg, 4); + sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); + sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); + sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); + } memcpy(iv, nonce, GMAC_NONCE_LEN); memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index a66eff1ee26a..7b654d2b8bb2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -568,7 +568,8 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, if (pairwise && key_idx < NUM_DEFAULT_KEYS) key = rcu_dereference(sta->ptk[key_idx]); else if (!pairwise && - key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) + key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) key = rcu_dereference(sta->gtk[key_idx]); } else key = rcu_dereference(sdata->keys[key_idx]); @@ -680,6 +681,17 @@ static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, return 0; } +static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, + struct net_device *dev, + u8 key_idx) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + ieee80211_set_default_beacon_key(sdata, key_idx); + + return 0; +} + void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) @@ -3874,6 +3886,60 @@ ieee80211_abort_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, return drv_abort_pmsr(local, sdata, request); } +static int ieee80211_set_tid_config(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_tid_config *tid_conf) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + int ret; + + if (!sdata->local->ops->set_tid_config) + return -EOPNOTSUPP; + + if (!tid_conf->peer) + return drv_set_tid_config(sdata->local, sdata, NULL, tid_conf); + + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get_bss(sdata, tid_conf->peer); + if (!sta) { + mutex_unlock(&sdata->local->sta_mtx); + return -ENOENT; + } + + ret = drv_set_tid_config(sdata->local, sdata, &sta->sta, tid_conf); + mutex_unlock(&sdata->local->sta_mtx); + + return ret; +} + +static int ieee80211_reset_tid_config(struct wiphy *wiphy, + struct net_device *dev, + const u8 *peer, u8 tid) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + int ret; + + if (!sdata->local->ops->reset_tid_config) + return -EOPNOTSUPP; + + if (!peer) + return drv_reset_tid_config(sdata->local, sdata, NULL, tid); + + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get_bss(sdata, peer); + if (!sta) { + mutex_unlock(&sdata->local->sta_mtx); + return -ENOENT; + } + + ret = drv_reset_tid_config(sdata->local, sdata, &sta->sta, tid); + mutex_unlock(&sdata->local->sta_mtx); + + return ret; +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -3885,6 +3951,7 @@ const struct cfg80211_ops mac80211_config_ops = { .get_key = ieee80211_get_key, .set_default_key = ieee80211_config_default_key, .set_default_mgmt_key = ieee80211_config_default_mgmt_key, + .set_default_beacon_key = ieee80211_config_default_beacon_key, .start_ap = ieee80211_start_ap, .change_beacon = ieee80211_change_beacon, .stop_ap = ieee80211_stop_ap, @@ -3973,4 +4040,6 @@ const struct cfg80211_ops mac80211_config_ops = { .start_pmsr = ieee80211_start_pmsr, .abort_pmsr = ieee80211_abort_pmsr, .probe_mesh_link = ieee80211_probe_mesh_link, + .set_tid_config = ieee80211_set_tid_config, + .reset_tid_config = ieee80211_reset_tid_config, }; diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 7b8735ced2a1..98a713475e0f 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -433,6 +433,37 @@ void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sda sdata->debugfs.default_mgmt_key = NULL; } +void +ieee80211_debugfs_key_add_beacon_default(struct ieee80211_sub_if_data *sdata) +{ + char buf[50]; + struct ieee80211_key *key; + + if (!sdata->vif.debugfs_dir) + return; + + key = key_mtx_dereference(sdata->local, + sdata->default_beacon_key); + if (key) { + sprintf(buf, "../keys/%d", key->debugfs.cnt); + sdata->debugfs.default_beacon_key = + debugfs_create_symlink("default_beacon_key", + sdata->vif.debugfs_dir, buf); + } else { + ieee80211_debugfs_key_remove_beacon_default(sdata); + } +} + +void +ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) +{ + if (!sdata) + return; + + debugfs_remove(sdata->debugfs.default_beacon_key); + sdata->debugfs.default_beacon_key = NULL; +} + void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) { diff --git a/net/mac80211/debugfs_key.h b/net/mac80211/debugfs_key.h index 1cd7b8bff56c..af7cf495f8d1 100644 --- a/net/mac80211/debugfs_key.h +++ b/net/mac80211/debugfs_key.h @@ -10,6 +10,10 @@ void ieee80211_debugfs_key_add_mgmt_default( struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata); +void ieee80211_debugfs_key_add_beacon_default( + struct ieee80211_sub_if_data *sdata); +void ieee80211_debugfs_key_remove_beacon_default( + struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta); #else @@ -26,6 +30,12 @@ static inline void ieee80211_debugfs_key_add_mgmt_default( static inline void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata) {} +static inline void ieee80211_debugfs_key_add_beacon_default( + struct ieee80211_sub_if_data *sdata) +{} +static inline void ieee80211_debugfs_key_remove_beacon_default( + struct ieee80211_sub_if_data *sdata) +{} static inline void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) {} diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 2c9b3eb8b652..3877710e3b48 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1358,4 +1358,31 @@ static inline void drv_del_nan_func(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline int drv_set_tid_config(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct cfg80211_tid_config *tid_conf) +{ + int ret; + + might_sleep(); + ret = local->ops->set_tid_config(&local->hw, &sdata->vif, sta, + tid_conf); + trace_drv_return_int(local, ret); + + return ret; +} + +static inline int drv_reset_tid_config(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, u8 tid) +{ + int ret; + + might_sleep(); + ret = local->ops->reset_tid_config(&local->hw, &sdata->vif, sta, tid); + trace_drv_return_int(local, ret); + + return ret; +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index da9eaa9ee37e..de39f9ca9935 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -901,10 +901,13 @@ struct ieee80211_sub_if_data { /* bit field of ACM bits (BIT(802.1D tag)) */ u8 wmm_acm; - struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_key __rcu *default_unicast_key; struct ieee80211_key __rcu *default_multicast_key; struct ieee80211_key __rcu *default_mgmt_key; + struct ieee80211_key __rcu *default_beacon_key; u16 sequence_number; __be16 control_port_protocol; @@ -978,6 +981,7 @@ struct ieee80211_sub_if_data { struct dentry *default_unicast_key; struct dentry *default_multicast_key; struct dentry *default_mgmt_key; + struct dentry *default_beacon_key; } debugfs; #endif @@ -1792,8 +1796,7 @@ void ieee80211_check_fast_xmit_iface(struct ieee80211_sub_if_data *sdata); void ieee80211_clear_fast_xmit(struct sta_info *sta); int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len, - const u8 *dest, const u8 *src, __be16 proto, - bool unencrypted); + const u8 *dest, __be16 proto, bool unencrypted); int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 54934eff4ac1..6354491c5a09 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -407,6 +407,31 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, mutex_unlock(&sdata->local->key_mtx); } +static void +__ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, int idx) +{ + struct ieee80211_key *key = NULL; + + assert_key_lock(sdata->local); + + if (idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS && + idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + key = key_mtx_dereference(sdata->local, sdata->keys[idx]); + + rcu_assign_pointer(sdata->default_beacon_key, key); + + ieee80211_debugfs_key_update_default(sdata); +} + +void ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, + int idx) +{ + mutex_lock(&sdata->local->key_mtx); + __ieee80211_set_default_beacon_key(sdata, idx); + mutex_unlock(&sdata->local->key_mtx); +} + static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, bool pairwise, @@ -415,7 +440,7 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, { int idx; int ret = 0; - bool defunikey, defmultikey, defmgmtkey; + bool defunikey, defmultikey, defmgmtkey, defbeaconkey; /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) @@ -480,6 +505,9 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, defmgmtkey = old && old == key_mtx_dereference(sdata->local, sdata->default_mgmt_key); + defbeaconkey = old && + old == key_mtx_dereference(sdata->local, + sdata->default_beacon_key); if (defunikey && !new) __ieee80211_set_default_key(sdata, -1, true, false); @@ -487,6 +515,8 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, __ieee80211_set_default_key(sdata, -1, false, true); if (defmgmtkey && !new) __ieee80211_set_default_mgmt_key(sdata, -1); + if (defbeaconkey && !new) + __ieee80211_set_default_beacon_key(sdata, -1); rcu_assign_pointer(sdata->keys[idx], new); if (defunikey && new) @@ -498,6 +528,9 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (defmgmtkey && new) __ieee80211_set_default_mgmt_key(sdata, new->conf.keyidx); + if (defbeaconkey && new) + __ieee80211_set_default_beacon_key(sdata, + new->conf.keyidx); } if (old) @@ -515,7 +548,9 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, struct ieee80211_key *key; int i, j, err; - if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS)) + if (WARN_ON(idx < 0 || + idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS)) return ERR_PTR(-EINVAL); key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL); @@ -978,6 +1013,7 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); + ieee80211_debugfs_key_remove_beacon_default(sdata); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { ieee80211_key_replace(key->sdata, key->sta, diff --git a/net/mac80211/key.h b/net/mac80211/key.h index d6d6e89cf7dd..7ad72e9b4991 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -17,6 +17,7 @@ #define NUM_DEFAULT_KEYS 4 #define NUM_DEFAULT_MGMT_KEYS 2 +#define NUM_DEFAULT_BEACON_KEYS 2 #define INVALID_PTK_KEYIDX 2 /* Keyidx always pointing to a NULL key for PTK */ struct ieee80211_local; @@ -153,6 +154,8 @@ void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx, bool uni, bool multi); void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, int idx); +void ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, + int idx); void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, bool force_synchronize); void ieee80211_free_sta_keys(struct ieee80211_local *local, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index cae3a34d3503..944e86da5c65 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -589,8 +589,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_FILS_STA); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211); - wiphy_ext_feature_set(wiphy, - NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_MAC_ADDRS); if (!ops->hw_scan) { wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN | diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9ab0842a7c37..8a2f2fa21916 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2986,7 +2986,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 2 && ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata, bssid)) - goto out_err; + return; /* ignore frame -- wait for timeout */ } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -2994,10 +2994,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); - return; - out_err: - mutex_unlock(&sdata->local->sta_mtx); - /* ignore frame -- wait for timeout */ } #define case_WLAN(type) \ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index ec3a04a1db20..2ffb4ee467e1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -983,7 +983,8 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da)) return -1; - if (!ieee80211_is_robust_mgmt_frame(skb)) + if (!ieee80211_is_robust_mgmt_frame(skb) && + !ieee80211_is_beacon(hdr->frame_control)) return -1; /* not a robust management frame */ mmie = (struct ieee80211_mmie *) @@ -1868,6 +1869,41 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) return RX_CONTINUE; } /* ieee80211_rx_h_sta_process */ +static struct ieee80211_key * +ieee80211_rx_get_bigtk(struct ieee80211_rx_data *rx, int idx) +{ + struct ieee80211_key *key = NULL; + struct ieee80211_sub_if_data *sdata = rx->sdata; + int idx2; + + /* Make sure key gets set if either BIGTK key index is set so that + * ieee80211_drop_unencrypted_mgmt() can properly drop both unprotected + * Beacon frames and Beacon frames that claim to use another BIGTK key + * index (i.e., a key that we do not have). + */ + + if (idx < 0) { + idx = NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS; + idx2 = idx + 1; + } else { + if (idx == NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) + idx2 = idx + 1; + else + idx2 = idx - 1; + } + + if (rx->sta) + key = rcu_dereference(rx->sta->gtk[idx]); + if (!key) + key = rcu_dereference(sdata->keys[idx]); + if (!key && rx->sta) + key = rcu_dereference(rx->sta->gtk[idx2]); + if (!key) + key = rcu_dereference(sdata->keys[idx2]); + + return key; +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) { @@ -1885,17 +1921,18 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* * Key selection 101 * - * There are four types of keys: + * There are five types of keys: * - GTK (group keys) * - IGTK (group keys for management frames) + * - BIGTK (group keys for Beacon frames) * - PTK (pairwise keys) * - STK (station-to-station pairwise keys) * * When selecting a key, we have to distinguish between multicast * (including broadcast) and unicast frames, the latter can only - * use PTKs and STKs while the former always use GTKs and IGTKs. - * Unless, of course, actual WEP keys ("pre-RSNA") are used, then - * unicast frames can also use key indices like GTKs. Hence, if we + * use PTKs and STKs while the former always use GTKs, IGTKs, and + * BIGTKs. Unless, of course, actual WEP keys ("pre-RSNA") are used, + * then unicast frames can also use key indices like GTKs. Hence, if we * don't have a PTK/STK we check the key index for a WEP key. * * Note that in a regular BSS, multicast frames are sent by the @@ -1939,6 +1976,20 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* Skip decryption if the frame is not protected. */ if (!ieee80211_has_protected(fc)) return RX_CONTINUE; + } else if (mmie_keyidx >= 0 && ieee80211_is_beacon(fc)) { + /* Broadcast/multicast robust management frame / BIP */ + if ((status->flag & RX_FLAG_DECRYPTED) && + (status->flag & RX_FLAG_IV_STRIPPED)) + return RX_CONTINUE; + + if (mmie_keyidx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS || + mmie_keyidx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + return RX_DROP_MONITOR; /* unexpected BIP keyidx */ + + rx->key = ieee80211_rx_get_bigtk(rx, mmie_keyidx); + if (!rx->key) + return RX_CONTINUE; /* Beacon protection not in use */ } else if (mmie_keyidx >= 0) { /* Broadcast/multicast robust management frame / BIP */ if ((status->flag & RX_FLAG_DECRYPTED) && @@ -1968,11 +2019,12 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; int i; - if (ieee80211_is_mgmt(fc) && - is_multicast_ether_addr(hdr->addr1) && - (key = rcu_dereference(rx->sdata->default_mgmt_key))) - rx->key = key; - else { + if (ieee80211_is_beacon(fc)) { + key = ieee80211_rx_get_bigtk(rx, -1); + } else if (ieee80211_is_mgmt(fc) && + is_multicast_ether_addr(hdr->addr1)) { + key = rcu_dereference(rx->sdata->default_mgmt_key); + } else { if (rx->sta) { for (i = 0; i < NUM_DEFAULT_KEYS; i++) { key = rcu_dereference(rx->sta->gtk[i]); @@ -1987,9 +2039,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) break; } } - if (key) - rx->key = key; } + if (key) + rx->key = key; return RX_CONTINUE; } else { /* @@ -2358,6 +2410,9 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) rx->skb->len); return -EACCES; } + if (unlikely(ieee80211_is_beacon(fc) && rx->key && + ieee80211_get_mmie_keyidx(rx->skb) < 0)) + return -EACCES; /* * When using MFP, Action frames are not allowed prior to * having configured keys. @@ -4116,7 +4171,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&local->sta_mtx); - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata && (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) continue; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 4d31d9688dc2..fdac8192a519 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -201,8 +201,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, mgmt->bssid, cbss->bssid); /* In case the signal is invalid update the status */ - signal_valid = abs(channel->center_freq - cbss->channel->center_freq) - <= local->hw.wiphy->max_adj_channel_rssi_comp; + signal_valid = channel == cbss->channel; if (!signal_valid) rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index c00e28585f9d..364a35414d05 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -533,7 +533,9 @@ struct sta_info { u8 addr[ETH_ALEN]; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; - struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_key __rcu *ptk[NUM_DEFAULT_KEYS]; u8 ptk_idx; struct rate_control_ref *rate_ctrl; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 38f20a370f2a..83147385c200 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation * * Transmit and frame generation functions. */ @@ -3682,7 +3682,8 @@ begin: encap_out: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { + if (vif && + wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -4663,6 +4664,28 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) } EXPORT_SYMBOL(ieee80211_csa_is_complete); +static int ieee80211_beacon_protect(struct sk_buff *skb, + struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + ieee80211_tx_result res; + struct ieee80211_tx_data tx; + + memset(&tx, 0, sizeof(tx)); + tx.key = rcu_dereference(sdata->default_beacon_key); + if (!tx.key) + return 0; + tx.local = local; + tx.sdata = sdata; + __skb_queue_head_init(&tx.skbs); + __skb_queue_tail(&tx.skbs, skb); + res = ieee80211_tx_h_encrypt(&tx); + if (WARN_ON_ONCE(res != TX_CONTINUE)) + return -1; + + return 0; +} + static struct sk_buff * __ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -4730,6 +4753,9 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (beacon->tail) skb_put_data(skb, beacon->tail, beacon->tail_len); + + if (ieee80211_beacon_protect(skb, local, sdata) < 0) + goto out; } else goto out; } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { @@ -5282,8 +5308,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len, - const u8 *dest, const u8 *src, __be16 proto, - bool unencrypted) + const u8 *dest, __be16 proto, bool unencrypted) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -5314,7 +5339,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, ehdr = skb_push(skb, sizeof(struct ethhdr)); memcpy(ehdr->h_dest, dest, ETH_ALEN); - memcpy(ehdr->h_source, src, ETH_ALEN); + memcpy(ehdr->h_source, sdata->vif.addr, ETH_ALEN); ehdr->h_proto = proto; skb->dev = dev; diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 768a302879b4..0e9aa94adc07 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -98,7 +98,7 @@ struct mpls_nh { /* next hop label forwarding entry */ u8 nh_via_table; u8 nh_reserved1; - u32 nh_label[0]; + u32 nh_label[]; }; /* offset of via from beginning of mpls_nh */ @@ -154,7 +154,7 @@ struct mpls_route { /* next hop label forwarding entry */ u8 rt_nh_size; u8 rt_via_offset; u8 rt_reserved1; - struct mpls_nh rt_nh[0]; + struct mpls_nh rt_nh[]; }; #define for_nexthops(rt) { \ diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e9aa6807b5be..a8445407d25a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -31,6 +31,12 @@ struct mptcp6_sock { }; #endif +struct mptcp_skb_cb { + u32 offset; +}; + +#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) + /* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not * completed yet or has failed, return the subflow socket. * Otherwise return NULL. @@ -111,6 +117,141 @@ static struct sock *mptcp_subflow_get(const struct mptcp_sock *msk) return NULL; } +static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb, + unsigned int offset, size_t copy_len) +{ + struct sock *sk = (struct sock *)msk; + + __skb_unlink(skb, &ssk->sk_receive_queue); + skb_set_owner_r(skb, sk); + __skb_queue_tail(&sk->sk_receive_queue, skb); + + msk->ack_seq += copy_len; + MPTCP_SKB_CB(skb)->offset = offset; +} + +static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, + struct sock *ssk, + unsigned int *bytes) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = (struct sock *)msk; + unsigned int moved = 0; + bool more_data_avail; + struct tcp_sock *tp; + bool done = false; + int rcvbuf; + + rcvbuf = max(ssk->sk_rcvbuf, sk->sk_rcvbuf); + if (rcvbuf > sk->sk_rcvbuf) + sk->sk_rcvbuf = rcvbuf; + + tp = tcp_sk(ssk); + do { + u32 map_remaining, offset; + u32 seq = tp->copied_seq; + struct sk_buff *skb; + bool fin; + + /* try to move as much data as available */ + map_remaining = subflow->map_data_len - + mptcp_subflow_get_map_offset(subflow); + + skb = skb_peek(&ssk->sk_receive_queue); + if (!skb) + break; + + offset = seq - TCP_SKB_CB(skb)->seq; + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; + if (fin) { + done = true; + seq++; + } + + if (offset < skb->len) { + size_t len = skb->len - offset; + + if (tp->urg_data) + done = true; + + __mptcp_move_skb(msk, ssk, skb, offset, len); + seq += len; + moved += len; + + if (WARN_ON_ONCE(map_remaining < len)) + break; + } else { + WARN_ON_ONCE(!fin); + sk_eat_skb(ssk, skb); + done = true; + } + + WRITE_ONCE(tp->copied_seq, seq); + more_data_avail = mptcp_subflow_data_available(ssk); + + if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) { + done = true; + break; + } + } while (more_data_avail); + + *bytes = moved; + + return done; +} + +/* In most cases we will be able to lock the mptcp socket. If its already + * owned, we need to defer to the work queue to avoid ABBA deadlock. + */ +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +{ + struct sock *sk = (struct sock *)msk; + unsigned int moved = 0; + + if (READ_ONCE(sk->sk_lock.owned)) + return false; + + if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock))) + return false; + + /* must re-check after taking the lock */ + if (!READ_ONCE(sk->sk_lock.owned)) + __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + + spin_unlock_bh(&sk->sk_lock.slock); + + return moved > 0; +} + +void mptcp_data_ready(struct sock *sk, struct sock *ssk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + set_bit(MPTCP_DATA_READY, &msk->flags); + + if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) && + move_skbs_to_msk(msk, ssk)) + goto wake; + + /* don't schedule if mptcp sk is (still) over limit */ + if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) + goto wake; + + /* mptcp socket is owned, release_cb should retry */ + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, + &sk->sk_tsq_flags)) { + sock_hold(sk); + + /* need to try again, its possible release_cb() has already + * been called after the test_and_set_bit() above. + */ + move_skbs_to_msk(msk, ssk); + } +wake: + sk->sk_data_ready(sk); +} + static bool mptcp_ext_cache_refill(struct mptcp_sock *msk) { if (!msk->cached_ext) @@ -323,61 +464,83 @@ fallback: return ret; } -int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, - unsigned int offset, size_t len) +static void mptcp_wait_data(struct sock *sk, long *timeo) { - struct mptcp_read_arg *arg = desc->arg.data; - size_t copy_len; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct mptcp_sock *msk = mptcp_sk(sk); + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + + sk_wait_event(sk, timeo, + test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); - copy_len = min(desc->count, len); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); +} + +static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, + struct msghdr *msg, + size_t len) +{ + struct sock *sk = (struct sock *)msk; + struct sk_buff *skb; + int copied = 0; - if (likely(arg->msg)) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { + u32 offset = MPTCP_SKB_CB(skb)->offset; + u32 data_len = skb->len - offset; + u32 count = min_t(size_t, len - copied, data_len); int err; - err = skb_copy_datagram_msg(skb, offset, arg->msg, copy_len); - if (err) { - pr_debug("error path"); - desc->error = err; - return err; + err = skb_copy_datagram_msg(skb, offset, msg, count); + if (unlikely(err < 0)) { + if (!copied) + return err; + break; } - } else { - pr_debug("Flushing skb payload"); - } - desc->count -= copy_len; + copied += count; + + if (count < data_len) { + MPTCP_SKB_CB(skb)->offset += count; + break; + } + + __skb_unlink(skb, &sk->sk_receive_queue); + __kfree_skb(skb); + + if (copied >= len) + break; + } - pr_debug("consumed %zu bytes, %zu left", copy_len, desc->count); - return copy_len; + return copied; } -static void mptcp_wait_data(struct sock *sk, long *timeo) +static bool __mptcp_move_skbs(struct mptcp_sock *msk) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct mptcp_sock *msk = mptcp_sk(sk); + unsigned int moved = 0; + bool done; - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + do { + struct sock *ssk = mptcp_subflow_recv_lookup(msk); - sk_wait_event(sk, timeo, - test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + if (!ssk) + break; - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); + lock_sock(ssk); + done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + release_sock(ssk); + } while (!done); + + return moved > 0; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); - struct mptcp_subflow_context *subflow; - bool more_data_avail = false; - struct mptcp_read_arg arg; - read_descriptor_t desc; - bool wait_data = false; struct socket *ssock; - struct tcp_sock *tp; - bool done = false; - struct sock *ssk; int copied = 0; int target; long timeo; @@ -395,65 +558,26 @@ fallback: return copied; } - arg.msg = msg; - desc.arg.data = &arg; - desc.error = 0; - timeo = sock_rcvtimeo(sk, nonblock); len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - while (!done) { - u32 map_remaining; + while (len > (size_t)copied) { int bytes_read; - ssk = mptcp_subflow_recv_lookup(msk); - pr_debug("msk=%p ssk=%p", msk, ssk); - if (!ssk) - goto wait_for_data; - - subflow = mptcp_subflow_ctx(ssk); - tp = tcp_sk(ssk); - - lock_sock(ssk); - do { - /* try to read as much data as available */ - map_remaining = subflow->map_data_len - - mptcp_subflow_get_map_offset(subflow); - desc.count = min_t(size_t, len - copied, map_remaining); - pr_debug("reading %zu bytes, copied %d", desc.count, - copied); - bytes_read = tcp_read_sock(ssk, &desc, - mptcp_read_actor); - if (bytes_read < 0) { - if (!copied) - copied = bytes_read; - done = true; - goto next; - } + bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied); + if (unlikely(bytes_read < 0)) { + if (!copied) + copied = bytes_read; + goto out_err; + } - pr_debug("msk ack_seq=%llx -> %llx", msk->ack_seq, - msk->ack_seq + bytes_read); - msk->ack_seq += bytes_read; - copied += bytes_read; - if (copied >= len) { - done = true; - goto next; - } - if (tp->urg_data && tp->urg_seq == tp->copied_seq) { - pr_err("Urgent data present, cannot proceed"); - done = true; - goto next; - } -next: - more_data_avail = mptcp_subflow_data_available(ssk); - } while (more_data_avail && !done); - release_sock(ssk); - continue; + copied += bytes_read; -wait_for_data: - more_data_avail = false; + if (skb_queue_empty(&sk->sk_receive_queue) && + __mptcp_move_skbs(msk)) + continue; /* only the master socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() @@ -494,26 +618,25 @@ wait_for_data: } pr_debug("block timeout %ld", timeo); - wait_data = true; mptcp_wait_data(sk, &timeo); if (unlikely(__mptcp_tcp_fallback(msk))) goto fallback; } - if (more_data_avail) { - if (!test_bit(MPTCP_DATA_READY, &msk->flags)) - set_bit(MPTCP_DATA_READY, &msk->flags); - } else if (!wait_data) { + if (skb_queue_empty(&sk->sk_receive_queue)) { + /* entire backlog drained, clear DATA_READY. */ clear_bit(MPTCP_DATA_READY, &msk->flags); - /* .. race-breaker: ssk might get new data after last - * data_available() returns false. + /* .. race-breaker: ssk might have gotten new data + * after last __mptcp_move_skbs() returned false. */ - ssk = mptcp_subflow_recv_lookup(msk); - if (unlikely(ssk)) + if (unlikely(__mptcp_move_skbs(msk))) set_bit(MPTCP_DATA_READY, &msk->flags); + } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) { + /* data to read but mptcp_wait_data() cleared DATA_READY */ + set_bit(MPTCP_DATA_READY, &msk->flags); } - +out_err: release_sock(sk); return copied; } @@ -543,14 +666,32 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } } +static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) +{ + return 0; +} + +static void mptcp_worker(struct work_struct *work) +{ + struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); + struct sock *sk = &msk->sk.icsk_inet.sk; + + lock_sock(sk); + __mptcp_move_skbs(msk); + release_sock(sk); + sock_put(sk); +} + static int __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); INIT_LIST_HEAD(&msk->conn_list); __set_bit(MPTCP_SEND_SPACE, &msk->flags); + INIT_WORK(&msk->work, mptcp_worker); msk->first = NULL; + inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; return 0; } @@ -563,6 +704,14 @@ static int mptcp_init_sock(struct sock *sk) return __mptcp_init_sock(sk); } +static void mptcp_cancel_work(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (cancel_work_sync(&msk->work)) + sock_put(sk); +} + static void mptcp_subflow_shutdown(struct sock *ssk, int how) { lock_sock(ssk); @@ -608,6 +757,10 @@ static void mptcp_close(struct sock *sk, long timeout) __mptcp_close_ssk(sk, ssk, subflow, timeout); } + mptcp_cancel_work(sk); + + __skb_queue_purge(&sk->sk_receive_queue); + sk_common_release(sk); } @@ -801,6 +954,32 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; } +#define MPTCP_DEFERRED_ALL TCPF_DELACK_TIMER_DEFERRED + +/* this is very alike tcp_release_cb() but we must handle differently a + * different set of events + */ +static void mptcp_release_cb(struct sock *sk) +{ + unsigned long flags, nflags; + + do { + flags = sk->sk_tsq_flags; + if (!(flags & MPTCP_DEFERRED_ALL)) + return; + nflags = flags & ~MPTCP_DEFERRED_ALL; + } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); + + if (flags & TCPF_DELACK_TIMER_DEFERRED) { + struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk; + + ssk = mptcp_subflow_recv_lookup(msk); + if (!ssk || !schedule_work(&msk->work)) + __sock_put(sk); + } +} + static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -876,6 +1055,7 @@ static struct proto mptcp_prot = { .destroy = mptcp_destroy, .sendmsg = mptcp_sendmsg, .recvmsg = mptcp_recvmsg, + .release_cb = mptcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = mptcp_get_port, @@ -1174,6 +1354,8 @@ void mptcp_proto_init(void) panic("Failed to register MPTCP proto.\n"); inet_register_protosw(&mptcp_protosw); + + BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb)); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9f8663b30456..6c0b2c8ab674 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -70,6 +70,7 @@ struct mptcp_sock { u32 token; unsigned long flags; bool can_ack; + struct work_struct work; struct list_head conn_list; struct skb_ext *cached_ext; /* for the next sendmsg */ struct socket *subflow; /* outgoing connect/listener/!mp_capable */ @@ -190,17 +191,11 @@ void mptcp_proto_init(void); int mptcp_proto_v6_init(void); #endif -struct mptcp_read_arg { - struct msghdr *msg; -}; - -int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, - unsigned int offset, size_t len); - void mptcp_get_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx); void mptcp_finish_connect(struct sock *sk); +void mptcp_data_ready(struct sock *sk, struct sock *ssk); int mptcp_token_new_request(struct request_sock *req); void mptcp_token_destroy_request(u32 token); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 65122edf60aa..0de2a44bdaa0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,6 +408,18 @@ validate_seq: return MAPPING_OK; } +static int subflow_read_actor(read_descriptor_t *desc, + struct sk_buff *skb, + unsigned int offset, size_t len) +{ + size_t copy_len = min(desc->count, len); + + desc->count -= copy_len; + + pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count); + return copy_len; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -482,16 +494,12 @@ static bool subflow_check_data_avail(struct sock *ssk) pr_debug("discarding %zu bytes, current map len=%d", delta, map_remaining); if (delta) { - struct mptcp_read_arg arg = { - .msg = NULL, - }; read_descriptor_t desc = { .count = delta, - .arg.data = &arg, }; int ret; - ret = tcp_read_sock(ssk, &desc, mptcp_read_actor); + ret = tcp_read_sock(ssk, &desc, subflow_read_actor); if (ret < 0) { ssk->sk_err = -ret; goto fatal; @@ -554,11 +562,8 @@ static void subflow_data_ready(struct sock *sk) return; } - if (mptcp_subflow_data_available(sk)) { - set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); - - parent->sk_data_ready(parent); - } + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); } static void subflow_write_space(struct sock *sk) @@ -690,11 +695,8 @@ static void subflow_state_change(struct sock *sk) * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. */ - if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) { - set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); - - parent->sk_data_ready(parent); - } + if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) && !subflow->rx_eof && subflow_is_done(sk)) { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69c107f9ba8d..8dd17589217d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -723,6 +723,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index) return set; } +static inline void +ip_set_lock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_lock_bh(&set->lock); +} + +static inline void +ip_set_unlock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_unlock_bh(&set->lock); +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) @@ -744,9 +758,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -775,9 +789,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -797,9 +811,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -1264,9 +1278,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->flush(set); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); } static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, @@ -1713,9 +1727,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); retried = true; } while (ret == -EAGAIN && set->variant->resize && diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7480ce55b5c8..e52d7b7597a0 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,13 +7,21 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> #include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set.h> -#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) -#define ipset_dereference_protected(p, set) \ - __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock)) - -#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) +#define __ipset_dereference(p) \ + rcu_dereference_protected(p, 1) +#define ipset_dereference_nfnl(p) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) +#define ipset_dereference_set(p, set) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&(set)->lock)) +#define ipset_dereference_bh_nfnl(p) \ + rcu_dereference_bh_check(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. @@ -72,11 +80,35 @@ struct hbucket { __aligned(__alignof__(u64)); }; +/* Region size for locking == 2^HTABLE_REGION_BITS */ +#define HTABLE_REGION_BITS 10 +#define ahash_numof_locks(htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 1 \ + : jhash_size((htable_bits) - HTABLE_REGION_BITS)) +#define ahash_sizeof_regions(htable_bits) \ + (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) +#define ahash_region(n, htable_bits) \ + ((n) % ahash_numof_locks(htable_bits)) +#define ahash_bucket_start(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 0 \ + : (h) * jhash_size(HTABLE_REGION_BITS)) +#define ahash_bucket_end(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ + : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) + +struct htable_gc { + struct delayed_work dwork; + struct ip_set *set; /* Set the gc belongs to */ + u32 region; /* Last gc run position */ +}; + /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ - atomic_t uref; /* References for dumping */ + atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ + u32 maxelem; /* Maxelem per region */ + struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; @@ -162,6 +194,10 @@ htable_bits(u32 hashsize) #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ +#define SET_ELEM_EXPIRED(set, d) \ + (SET_WITH_TIMEOUT(set) && \ + ip_set_timeout_expired(ext_timeout(d, set))) + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -205,10 +241,12 @@ htable_bits(u32 hashsize) #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref -#undef mtype_expire #undef mtype_resize +#undef mtype_ext_size +#undef mtype_resize_ad #undef mtype_head #undef mtype_list +#undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_variant @@ -247,10 +285,12 @@ htable_bits(u32 hashsize) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) -#define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) +#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) +#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) +#define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) @@ -275,8 +315,7 @@ htable_bits(u32 hashsize) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct ip_set *set; /* attached to this ip_set */ + struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -288,21 +327,33 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif + struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; +/* ADD|DEL entries saved during resize */ +struct mtype_resize_ad { + struct list_head list; + enum ipset_adt ad; /* ADD|DEL element */ + struct mtype_elem d; /* Element value */ + struct ip_set_ext ext; /* Extensions for ADD */ + struct ip_set_ext mext; /* Target extensions for ADD */ + u32 flags; /* Flags for ADD */ +}; + #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void -mtype_add_cidr(struct htype *h, u8 cidr, u8 n) +mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; + spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { @@ -311,7 +362,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; - return; + goto unlock; } } if (j != -1) { @@ -320,24 +371,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; +unlock: + spin_unlock_bh(&set->lock); } static void -mtype_del_cidr(struct htype *h, u8 cidr, u8 n) +mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; + spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - return; + goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + goto unlock; } +unlock: + spin_unlock_bh(&set->lock); } #endif @@ -345,7 +401,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n) static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { - return sizeof(*h) + sizeof(*t); + return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ @@ -369,24 +425,29 @@ mtype_flush(struct ip_set *set) struct htype *h = set->data; struct htable *t; struct hbucket *n; - u32 i; - - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); - if (!n) - continue; - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - rcu_assign_pointer(hbucket(t, i), NULL); - kfree_rcu(n, rcu); + u32 r, i; + + t = ipset_dereference_nfnl(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + } + t->hregion[r].ext_size = 0; + t->hregion[r].elements = 0; + spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif - set->elements = 0; - set->ext_size = 0; } /* Destroy the hashtable part of the set */ @@ -397,7 +458,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -406,6 +467,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } + ip_set_free(t->hregion); ip_set_free(t); } @@ -414,28 +476,21 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct list_head *l, *lt; if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&h->gc); + cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, - __ipset_dereference_protected(h->table, 1), true); + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); + kfree(l); + } kfree(h); set->data = NULL; } -static void -mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) -{ - struct htype *h = set->data; - - timer_setup(&h->gc, gc, 0); - mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(set->timeout)); -} - static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { @@ -454,11 +509,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } -/* Delete expired elements from the hashtable */ static void -mtype_expire(struct ip_set *set, struct htype *h) +mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { - struct htable *t; struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; @@ -466,10 +519,12 @@ mtype_expire(struct ip_set *set, struct htype *h) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif + u8 htable_bits = t->htable_bits; - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, htable_bits); + i < ahash_bucket_end(r, htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { @@ -485,58 +540,100 @@ mtype_expire(struct ip_set *set, struct htype *h) smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif + t->hregion[r].elements--; ip_set_ext_destroy(set, data); - set->elements--; d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { + t->hregion[r].ext_size -= + ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) - /* Still try to delete expired elements */ + /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); - memcpy(tmp->value + d * dsize, data, dsize); + memcpy(tmp->value + d * dsize, + data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } + spin_unlock_bh(&t->hregion[r].lock); } static void -mtype_gc(struct timer_list *t) +mtype_gc(struct work_struct *work) { - struct htype *h = from_timer(h, t, gc); - struct ip_set *set = h->set; + struct htable_gc *gc; + struct ip_set *set; + struct htype *h; + struct htable *t; + u32 r, numof_locks; + unsigned int next_run; + + gc = container_of(work, struct htable_gc, dwork.work); + set = gc->set; + h = set->data; - pr_debug("called\n"); spin_lock_bh(&set->lock); - mtype_expire(set, h); + t = ipset_dereference_set(h->table, set); + atomic_inc(&t->uref); + numof_locks = ahash_numof_locks(t->htable_bits); + r = gc->region++; + if (r >= numof_locks) { + r = gc->region = 0; + } + next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; + if (next_run < HZ/10) + next_run = HZ/10; spin_unlock_bh(&set->lock); - h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; - add_timer(&h->gc); + mtype_gc_do(set, h, t, r); + + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by expire: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + + queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); + +} + +static void +mtype_gc_init(struct htable_gc *gc) +{ + INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static int +mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +static int +mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); + /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. @@ -547,7 +644,7 @@ mtype_resize(struct ip_set *set, bool retried) struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; - size_t extsize, dsize = set->dsize; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; @@ -555,7 +652,9 @@ mtype_resize(struct ip_set *set, bool retried) struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j, key; + struct list_head *l, *lt; + struct mtype_resize_ad *x; + u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS @@ -563,10 +662,8 @@ mtype_resize(struct ip_set *set, bool retried) if (!tmp) return -ENOMEM; #endif - rcu_read_lock_bh(); - orig = rcu_dereference_bh_nfnl(h->table); + orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; - rcu_read_unlock_bh(); retry: ret = 0; @@ -583,88 +680,124 @@ retry: ret = -ENOMEM; goto out; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); + if (!t->hregion) { + kfree(t); + ret = -ENOMEM; + goto out; + } t->htable_bits = htable_bits; + t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + for (i = 0; i < ahash_numof_locks(htable_bits); i++) + spin_lock_init(&t->hregion[i].lock); - spin_lock_bh(&set->lock); - orig = __ipset_dereference_protected(h->table, 1); - /* There can't be another parallel resizing, but dumping is possible */ + /* There can't be another parallel resizing, + * but dumping, gc, kernel side add/del are possible + */ + orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); - extsize = 0; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(orig, i), 1); - if (!n) - continue; - for (j = 0; j < n->pos; j++) { - if (!test_bit(j, n->used)) + for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { + /* Expire may replace a hbucket with another one */ + rcu_read_lock_bh(); + for (i = ahash_bucket_start(r, orig->htable_bits); + i < ahash_bucket_end(r, orig->htable_bits); i++) { + n = __ipset_dereference(hbucket(orig, i)); + if (!n) continue; - data = ahash_data(n, j, dsize); + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + if (SET_ELEM_EXPIRED(set, data)) + continue; #ifdef IP_SET_HASH_WITH_NETS - /* We have readers running parallel with us, - * so the live data cannot be modified. - */ - flags = 0; - memcpy(tmp, data, dsize); - data = tmp; - mtype_data_reset_flags(data, &flags); + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ + flags = 0; + memcpy(tmp, data, dsize); + data = tmp; + mtype_data_reset_flags(data, &flags); #endif - key = HKEY(data, h->initval, htable_bits); - m = __ipset_dereference_protected(hbucket(t, key), 1); - if (!m) { - m = kzalloc(sizeof(*m) + + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference(hbucket(t, key)); + nr = ahash_region(key, htable_bits); + if (!m) { + m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); - if (!m) { - ret = -ENOMEM; - goto cleanup; - } - m->size = AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - RCU_INIT_POINTER(hbucket(t, key), m); - } else if (m->pos >= m->size) { - struct hbucket *ht; - - if (m->size >= AHASH_MAX(h)) { - ret = -EAGAIN; - } else { - ht = kzalloc(sizeof(*ht) + + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); - if (!ht) - ret = -ENOMEM; + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - if (ret < 0) - goto cleanup; - memcpy(ht, m, sizeof(struct hbucket) + - m->size * dsize); - ht->size = m->size + AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - kfree(m); - m = ht; - RCU_INIT_POINTER(hbucket(t, key), ht); - } - d = ahash_data(m, m->pos, dsize); - memcpy(d, data, dsize); - set_bit(m->pos++, m->used); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); + t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(d, &flags); + mtype_data_reset_flags(d, &flags); #endif + } } + rcu_read_unlock_bh(); } - rcu_assign_pointer(h->table, t); - set->ext_size = extsize; - spin_unlock_bh(&set->lock); + /* There can't be any other writer. */ + rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - /* If there's nobody else dumping the table, destroy it */ + /* Add/delete elements processed by the SET target during resize. + * Kernel-side add cannot trigger a resize and userspace actions + * are serialized by the mutex. + */ + list_for_each_safe(l, lt, &h->ad) { + x = list_entry(l, struct mtype_resize_ad, list); + if (x->ad == IPSET_ADD) { + mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); + } else { + mtype_del(set, &x->d, NULL, NULL, 0); + } + list_del(l); + kfree(l); + } + /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); @@ -677,15 +810,44 @@ out: return ret; cleanup: + rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); - spin_unlock_bh(&set->lock); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; } +/* Get the current number of elements and ext_size in the set */ +static void +mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) +{ + struct htype *h = set->data; + const struct htable *t; + u32 i, j, r; + struct hbucket *n; + struct mtype_elem *data; + + t = rcu_dereference_bh(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, set->dsize); + if (!SET_ELEM_EXPIRED(set, data)) + (*elements)++; + } + } + *ext_size += t->hregion[r].ext_size; + } +} + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ @@ -698,32 +860,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); - int i, j = -1; + int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; - u32 key, multi = 0; + u32 r, key, multi = 0, elements, maxelem; - if (set->elements >= h->maxelem) { - if (SET_WITH_TIMEOUT(set)) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h); - if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + elements = t->hregion[r].elements; + maxelem = t->maxelem; + if (elements >= maxelem) { + u32 e; + if (SET_WITH_TIMEOUT(set)) { + rcu_read_unlock_bh(); + mtype_gc_do(set, h, t, r); + rcu_read_lock_bh(); + } + maxelem = h->maxelem; + elements = 0; + for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) + elements += t->hregion[e].elements; + if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } + rcu_read_unlock_bh(); - t = ipset_dereference_protected(h->table, set); - key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) { - if (forceadd || set->elements >= h->maxelem) + if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } n->size = AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { @@ -737,38 +916,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { - if (flag_exist || - (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)))) { + if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } - return -IPSET_ERR_EXIST; + ret = -IPSET_ERR_EXIST; + goto unlock; } /* Reuse first timed out entry */ - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)) && - j == -1) { + if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { + if (j == -1) + j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); - set->elements--; + t->hregion[r].elements--; } goto copy_data; } - if (set->elements >= h->maxelem) + if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { @@ -776,28 +954,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); - return -EAGAIN; + ret = -EAGAIN; + goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: - set->elements++; + t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -820,13 +1002,41 @@ overwrite_extensions: if (old) kfree_rcu(old, rcu); } + ret = 0; +resize: + spin_unlock_bh(&t->hregion[r].lock); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side add, save values */ + struct mtype_resize_ad *x; + + x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); + if (!x) + /* Don't bother */ + goto out; + x->ad = IPSET_ADD; + memcpy(&x->d, value, sizeof(struct mtype_elem)); + memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); + memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); + x->flags = flags; + spin_lock_bh(&set->lock); + list_add_tail(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + goto out; - return 0; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; + set->name, maxelem); + ret = -IPSET_ERR_HASH_FULL; +unlock: + spin_unlock_bh(&t->hregion[r].lock); +out: + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by add: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + return ret; } /* Delete an element from the hash and free up space if possible. @@ -840,13 +1050,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, j, k, ret = -IPSET_ERR_EXIST; + struct mtype_resize_ad *x = NULL; + int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; - t = ipset_dereference_protected(h->table, set); + /* Userspace add and resize is excluded by the mutex. + * Kernespace add does not trigger resize. + */ + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + rcu_read_unlock_bh(); + + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { @@ -857,8 +1077,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set))) + if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; @@ -866,20 +1085,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; - set->elements--; + t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), - j); + mtype_del_cidr(set, h, + NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side del, + * save values + */ + x = kzalloc(sizeof(struct mtype_resize_ad), + GFP_ATOMIC); + if (x) { + x->ad = IPSET_DEL; + memcpy(&x->d, value, + sizeof(struct mtype_elem)); + x->flags = flags; + } + } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { - set->ext_size -= ext_size(n->size, dsize); + t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { @@ -898,7 +1130,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, k++; } tmp->pos = k; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } @@ -906,6 +1139,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, } out: + spin_unlock_bh(&t->hregion[r].lock); + if (x) { + spin_lock_bh(&set->lock); + list_add(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by del: %p\n", t); + mtype_ahash_destroy(set, t, false); + } return ret; } @@ -991,6 +1234,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; + rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -1022,6 +1266,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto out; } out: + rcu_read_unlock_bh(); return ret; } @@ -1033,23 +1278,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u32 elements = 0; + size_t ext_size = 0; u8 htable_bits; - /* If any members have expired, set->elements will be wrong - * mytype_expire function will update it with the right count. - * we do not hold set->lock here, so grab it first. - * set->elements can still be incorrect in the case of a huge set, - * because elements might time out during the listing. - */ - if (SET_WITH_TIMEOUT(set)) { - spin_lock_bh(&set->lock); - mtype_expire(set, h); - spin_unlock_bh(&set->lock); - } - rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); - memsize = mtype_ahash_memsize(h, t) + set->ext_size; + t = rcu_dereference_bh(h->table); + mtype_ext_size(set, &elements, &ext_size); + memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); @@ -1071,7 +1307,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) #endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) + nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -1091,15 +1327,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) if (start) { rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { - /* Resizing didn't destroy the hash table */ - pr_debug("Table destroy by dump: %p\n", t); + pr_debug("Table destroy after resize " + " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; @@ -1141,8 +1377,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); @@ -1208,6 +1443,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE @@ -1226,6 +1462,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, size_t hsize; struct htype *h; struct htable *t; + u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); @@ -1294,6 +1531,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, kfree(h); return -ENOMEM; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); + if (!t->hregion) { + kfree(t); + kfree(h); + return -ENOMEM; + } + h->gc.set = set; + for (i = 0; i < ahash_numof_locks(hbits); i++) + spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; @@ -1304,9 +1550,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, get_random_bytes(&h->initval, sizeof(h->initval)); t->htable_bits = hbits; + t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); - h->set = set; + INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { @@ -1329,12 +1576,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif - IPSET_TOKEN(HTYPE, 4_gc_init)(set, - IPSET_TOKEN(HTYPE, 4_gc)); + IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else - IPSET_TOKEN(HTYPE, 6_gc_init)(set, - IPSET_TOKEN(HTYPE, 6_gc)); + IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index feac8553f6d9..4fc0c924ed5d 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1766,11 +1766,13 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { - const u8 *data = (const u8 *)elem->key.val.data; struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; + struct nft_pipapo_elem *e = elem->priv; int rules_f0, first_rule = 0; - struct nft_pipapo_elem *e; + const u8 *data; + + data = (const u8 *)nft_set_ext_key(&e->ext); e = pipapo_get(net, set, data, 0); if (IS_ERR(e)) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 7a2c4b8408c4..8c835ad63729 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -402,15 +402,6 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) remove_proc_entry(hinfo->name, parent); } -static void htable_destroy(struct xt_hashlimit_htable *hinfo) -{ - cancel_delayed_work_sync(&hinfo->gc_work); - htable_remove_proc_entry(hinfo); - htable_selective_cleanup(hinfo, true); - kfree(hinfo->name); - vfree(hinfo); -} - static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) @@ -432,8 +423,13 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) { if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); + htable_remove_proc_entry(hinfo); mutex_unlock(&hashlimit_mutex); - htable_destroy(hinfo); + + cancel_delayed_work_sync(&hinfo->gc_work); + htable_selective_cleanup(hinfo, true); + kfree(hinfo->name); + vfree(hinfo); } } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0522b2b1fd95..9f357aa22b94 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -497,8 +497,9 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); - if (err && parallel) { - kfree(attrbuf); + if (err) { + if (parallel) + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 58d5373c513c..7b1a74f74aad 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1230,6 +1230,7 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #ifdef CONFIG_PROC_FS static void *nr_info_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_list_lock) { spin_lock_bh(&nr_list_lock); return seq_hlist_start_head(&nr_list, *pos); @@ -1241,6 +1242,7 @@ static void *nr_info_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_info_stop(struct seq_file *seq, void *v) + __releases(&nr_list_lock) { spin_unlock_bh(&nr_list_lock); } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index d41335bad1f8..79f12d8c7b86 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -838,6 +838,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) #ifdef CONFIG_PROC_FS static void *nr_node_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_node_list_lock) { spin_lock_bh(&nr_node_list_lock); return seq_hlist_start_head(&nr_node_list, *pos); @@ -849,6 +850,7 @@ static void *nr_node_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_node_stop(struct seq_file *seq, void *v) + __releases(&nr_node_list_lock) { spin_unlock_bh(&nr_node_list_lock); } @@ -893,6 +895,7 @@ const struct seq_operations nr_node_seqops = { }; static void *nr_neigh_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_neigh_list_lock) { spin_lock_bh(&nr_neigh_list_lock); return seq_hlist_start_head(&nr_neigh_list, *pos); @@ -904,6 +907,7 @@ static void *nr_neigh_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_neigh_stop(struct seq_file *seq, void *v) + __releases(&nr_neigh_list_lock) { spin_unlock_bh(&nr_neigh_list_lock); } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 67a4e59cdf4d..413228c4520e 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -76,7 +76,7 @@ static struct qrtr_node *node_get(unsigned int node_id) /* If node didn't exist, allocate and insert it to the tree */ node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) - return ERR_PTR(-ENOMEM); + return NULL; node->id = node_id; @@ -150,7 +150,7 @@ static int service_announce_del(struct sockaddr_qrtr *dest, ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); if (ret < 0) - pr_err("failed to announce del serivce\n"); + pr_err("failed to announce del service\n"); return ret; } @@ -224,7 +224,7 @@ static struct qrtr_server *server_add(unsigned int service, srv = kzalloc(sizeof(*srv), GFP_KERNEL); if (!srv) - return ERR_PTR(-ENOMEM); + return NULL; srv->service = service; srv->instance = instance; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 90a31b15585f..8c466a712cda 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -186,6 +186,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) /* TCA_STATS_PKT64 */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 13c33eaf1ca1..4e766c5ab77a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3382,14 +3382,40 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, } EXPORT_SYMBOL(tc_setup_cb_reoffload); +static int tcf_act_get_cookie(struct flow_action_entry *entry, + const struct tc_action *act) +{ + struct tc_cookie *cookie; + int err = 0; + + rcu_read_lock(); + cookie = rcu_dereference(act->act_cookie); + if (cookie) { + entry->cookie = flow_action_cookie_create(cookie->data, + cookie->len, + GFP_ATOMIC); + if (!entry->cookie) + err = -ENOMEM; + } + rcu_read_unlock(); + return err; +} + +static void tcf_act_put_cookie(struct flow_action_entry *entry) +{ + flow_action_cookie_destroy(entry->cookie); +} + void tc_cleanup_flow_action(struct flow_action *flow_action) { struct flow_action_entry *entry; int i; - flow_action_for_each(i, entry, flow_action) + flow_action_for_each(i, entry, flow_action) { + tcf_act_put_cookie(entry); if (entry->destructor) entry->destructor(entry->destructor_priv); + } } EXPORT_SYMBOL(tc_cleanup_flow_action); @@ -3447,6 +3473,9 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry = &flow_action->entries[j]; spin_lock_bh(&act->tcfa_lock); + err = tcf_act_get_cookie(entry, act); + if (err) + goto err_out_locked; if (is_tcf_gact_ok(act)) { entry->id = FLOW_ACTION_ACCEPT; } else if (is_tcf_gact_shot(act)) { diff --git a/net/sctp/input.c b/net/sctp/input.c index efaaefc3bb1c..55d4fc6f371d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -548,6 +548,7 @@ out: /* Common cleanup code for icmp/icmpv6 error handler. */ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) + __releases(&((__sk)->sk_lock.slock)) { bh_unlock_sock(sk); sctp_transport_put(t); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1b56fc440606..fed26a1e9518 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5333,14 +5333,14 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, EXPORT_SYMBOL_GPL(sctp_get_sctp_info); /* use callback to avoid exporting the core structure */ -void sctp_transport_walk_start(struct rhashtable_iter *iter) +void sctp_transport_walk_start(struct rhashtable_iter *iter) __acquires(RCU) { rhltable_walk_enter(&sctp_transport_hashtable, iter); rhashtable_walk_start(iter); } -void sctp_transport_walk_stop(struct rhashtable_iter *iter) +void sctp_transport_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { rhashtable_walk_stop(iter); rhashtable_walk_exit(iter); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 90988a511cd5..6fd44bdb0fc3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -512,15 +512,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_abort(struct smc_sock *smc, int reason_code, int local_contact) { + bool is_smcd = smc->conn.lgr->is_smcd; + if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(smc->conn.lgr); - if (smc->conn.lgr->is_smcd) + smc_lgr_cleanup_early(&smc->conn); + else + smc_conn_free(&smc->conn); + if (is_smcd) /* there is only one lgr role for SMC-D; use server lock */ mutex_unlock(&smc_server_lgr_pending); else mutex_unlock(&smc_client_lgr_pending); - smc_conn_free(&smc->conn); smc->connect_nonblock = 0; return reason_code; } @@ -1091,7 +1094,6 @@ static void smc_listen_out_err(struct smc_sock *new_smc) if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; - smc_conn_free(&new_smc->conn); smc_listen_out(new_smc); } @@ -1102,12 +1104,13 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, { /* RDMA setup failed, switch back to TCP */ if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); if (reason_code < 0) { /* error, no fallback possible */ smc_listen_out_err(new_smc); return; } - smc_conn_free(&new_smc->conn); smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { @@ -1170,16 +1173,18 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, new_smc->conn.lgr->vlan_id, new_smc->conn.lgr->smcd)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_SMCDNOTALK; } /* Create send and receive buffers */ if (smc_buf_create(new_smc, true)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_MEM; } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 3e16b887cfcf..ea0068f0173c 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -372,7 +372,8 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; - if (smc->conn.lgr && !smc->conn.lgr->is_smcd) + if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) && + smc_ib_is_valid_local_systemid()) memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 1bbce5531014..824c5211b027 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -163,6 +163,18 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) conn->lgr = NULL; } +void smc_lgr_cleanup_early(struct smc_connection *conn) +{ + struct smc_link_group *lgr = conn->lgr; + + if (!lgr) + return; + + smc_conn_free(conn); + smc_lgr_forget(lgr); + smc_lgr_schedule_free_work_fast(lgr); +} + /* Send delete link, either as client to request the initiation * of the DELETE LINK sequence from server; or as server to * initiate the delete processing. See smc_llc_rx_delete_link(). diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 5695c7bc639e..8041db20c753 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -290,6 +290,7 @@ struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_forget(struct smc_link_group *lgr); +void smc_lgr_cleanup_early(struct smc_connection *conn); void smc_lgr_terminate_sched(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, @@ -310,7 +311,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); -void smcd_conn_free(struct smc_connection *conn); void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr); int smc_core_init(void); void smc_core_exit(void); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 6756bd5a3fe4..9239cf881f21 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -37,11 +37,7 @@ struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */ .list = LIST_HEAD_INIT(smc_ib_devices.list), }; -#define SMC_LOCAL_SYSTEMID_RESET "%%%%%%%" - -u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET; /* unique system - * identifier - */ +u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */ static int smc_ib_modify_qp_init(struct smc_link *lnk) { @@ -168,6 +164,15 @@ static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev, { memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1], sizeof(smcibdev->mac[ibport - 1])); +} + +bool smc_ib_is_valid_local_systemid(void) +{ + return !is_zero_ether_addr(&local_systemid[2]); +} + +static void smc_ib_init_local_systemid(void) +{ get_random_bytes(&local_systemid[0], 2); } @@ -224,8 +229,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) rc = smc_ib_fill_mac(smcibdev, ibport); if (rc) goto out; - if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET, - sizeof(local_systemid)) && + if (!smc_ib_is_valid_local_systemid() && smc_ib_port_active(smcibdev, ibport)) /* create unique system identifier */ smc_ib_define_local_systemid(smcibdev, ibport); @@ -587,6 +591,8 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) struct smc_ib_device *smcibdev; smcibdev = ib_get_client_data(ibdev, &smc_ib_client); + if (!smcibdev || smcibdev->ibdev != ibdev) + return; ib_set_client_data(ibdev, &smc_ib_client, NULL); spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ @@ -605,6 +611,7 @@ static struct ib_client smc_ib_client = { int __init smc_ib_register_client(void) { + smc_ib_init_local_systemid(); return ib_register_client(&smc_ib_client); } diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 255db87547d3..5c2b115d36da 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -84,4 +84,5 @@ void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev, enum dma_data_direction data_direction); int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index); +bool smc_ib_is_valid_local_systemid(void); #endif diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 60630762a748..f25604d68337 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -475,6 +475,9 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info, check_cb, add_cb); if (err && err != -EOPNOTSUPP) @@ -526,6 +529,9 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info, check_cb, del_cb); if (err && err != -EOPNOTSUPP) @@ -576,6 +582,9 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info, check_cb, set_cb); if (err && err != -EOPNOTSUPP) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 62c12cb5763e..3385a7a0b231 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -682,6 +682,7 @@ static int unix_set_peek_off(struct sock *sk, int val) return 0; } +#ifdef CONFIG_PROC_FS static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; @@ -689,9 +690,13 @@ static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) if (sk) { u = unix_sk(sock->sk); - seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); + seq_printf(m, "scm_fds: %u\n", + atomic_read(&u->scm_stat.nr_fds)); } } +#else +#define unix_show_fdinfo NULL +#endif static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, @@ -1207,6 +1212,7 @@ out: } static long unix_wait_for_peer(struct sock *other, long timeo) + __releases(&unix_sk(other)->lock) { struct unix_sock *u = unix_sk(other); int sched; @@ -1597,10 +1603,8 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - lockdep_assert_held(&sk->sk_receive_queue.lock); - if (unlikely(fp && fp->count)) - u->scm_stat.nr_fds += fp->count; + atomic_add(fp->count, &u->scm_stat.nr_fds); } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1608,10 +1612,8 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - lockdep_assert_held(&sk->sk_receive_queue.lock); - if (unlikely(fp && fp->count)) - u->scm_stat.nr_fds -= fp->count; + atomic_sub(fp->count, &u->scm_stat.nr_fds); } /* @@ -1800,10 +1802,8 @@ restart_locked: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); - spin_lock(&other->sk_receive_queue.lock); scm_stat_add(other, skb); - __skb_queue_tail(&other->sk_receive_queue, skb); - spin_unlock(&other->sk_receive_queue.lock); + skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); other->sk_data_ready(other); sock_put(other); @@ -1905,10 +1905,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto pipe_err_free; maybe_add_creds(skb, sock, other); - spin_lock(&other->sk_receive_queue.lock); scm_stat_add(other, skb); - __skb_queue_tail(&other->sk_receive_queue, skb); - spin_unlock(&other->sk_receive_queue.lock); + skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); other->sk_data_ready(other); sent += size; @@ -2108,9 +2106,12 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, skip = sk_peek_offset(sk, flags); skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags, - scm_stat_del, &skip, &err, &last); - if (skb) + &skip, &err, &last); + if (skb) { + if (!(flags & MSG_PEEK)) + scm_stat_del(sk, skb); break; + } mutex_unlock(&u->iolock); @@ -2404,9 +2405,7 @@ unlock: sk_peek_offset_bwd(sk, chunk); if (UNIXCB(skb).fp) { - spin_lock(&sk->sk_receive_queue.lock); scm_stat_del(sk, skb); - spin_unlock(&sk->sk_receive_queue.lock); unix_detach_fds(&scm, skb); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9c5b2a91baad..a5f28708e0e7 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -451,6 +451,12 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (vsk->transport == new_transport) return 0; + /* transport->release() must be called with sock lock acquired. + * This path can only be taken during vsock_stream_connect(), + * where we have already held the sock lock. + * In the other cases, this function is called on a new socket + * which is not assigned to any transport. + */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); } @@ -753,20 +759,18 @@ static void __vsock_release(struct sock *sk, int level) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ - /* The release call is supposed to use lock_sock_nested() - * rather than lock_sock(), if a sock lock should be acquired. - */ - if (vsk->transport) - vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) - vsock_remove_sock(vsk); - /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); + + if (vsk->transport) + vsk->transport->release(vsk); + else if (sk->sk_type == SOCK_STREAM) + vsock_remove_sock(vsk); + sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 3492c021925f..630b851f8150 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -526,12 +526,9 @@ static bool hvs_close_lock_held(struct vsock_sock *vsk) static void hvs_release(struct vsock_sock *vsk) { - struct sock *sk = sk_vsock(vsk); bool remove_sock; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); remove_sock = hvs_close_lock_held(vsk); - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 2f696124bab6..709038a4783e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -829,7 +829,6 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); @@ -837,7 +836,6 @@ void virtio_transport_release(struct vsock_sock *vsk) list_del(&pkt->list); virtio_transport_free_pkt(pkt); } - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8c2a246099ef..15000275b32d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -20,6 +20,7 @@ #include <linux/netlink.h> #include <linux/nospec.h> #include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <net/net_namespace.h> #include <net/genetlink.h> #include <net/cfg80211.h> @@ -328,6 +329,22 @@ he_bss_color_policy[NL80211_HE_BSS_COLOR_ATTR_MAX + 1] = { [NL80211_HE_BSS_COLOR_ATTR_PARTIAL] = { .type = NLA_FLAG }, }; +static const struct nla_policy +nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { + [NL80211_TID_CONFIG_ATTR_VIF_SUPP] = { .type = NLA_U64 }, + [NL80211_TID_CONFIG_ATTR_PEER_SUPP] = { .type = NLA_U64 }, + [NL80211_TID_CONFIG_ATTR_OVERRIDE] = { .type = NLA_FLAG }, + [NL80211_TID_CONFIG_ATTR_TIDS] = NLA_POLICY_RANGE(NLA_U16, 1, 0xff), + [NL80211_TID_CONFIG_ATTR_NOACK] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_RETRY_SHORT] = NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_TID_CONFIG_ATTR_RETRY_LONG] = NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_TID_CONFIG_ATTR_AMPDU_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), +}; + const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -368,7 +385,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, - [NL80211_ATTR_KEY_IDX] = NLA_POLICY_MAX(NLA_U8, 5), + [NL80211_ATTR_KEY_IDX] = NLA_POLICY_MAX(NLA_U8, 7), [NL80211_ATTR_KEY_CIPHER] = { .type = NLA_U32 }, [NL80211_ATTR_KEY_DEFAULT] = { .type = NLA_FLAG }, [NL80211_ATTR_KEY_SEQ] = { .type = NLA_BINARY, .len = 16 }, @@ -634,8 +651,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HE_OBSS_PD] = NLA_POLICY_NESTED(he_obss_pd_policy), [NL80211_ATTR_VLAN_ID] = NLA_POLICY_RANGE(NLA_U16, 1, VLAN_N_VID - 2), [NL80211_ATTR_HE_BSS_COLOR] = NLA_POLICY_NESTED(he_bss_color_policy), - [NL80211_ATTR_SRC_MAC] = NLA_POLICY_ETH_ADDR, - [NL80211_ATTR_DST_MAC] = NLA_POLICY_ETH_ADDR, + [NL80211_ATTR_TID_CONFIG] = + NLA_POLICY_NESTED_ARRAY(nl80211_tid_config_attr_policy), }; /* policy for the key attributes */ @@ -1039,7 +1056,7 @@ struct key_parse { struct key_params p; int idx; int type; - bool def, defmgmt; + bool def, defmgmt, defbeacon; bool def_uni, def_multi; }; @@ -1055,12 +1072,13 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key, k->def = !!tb[NL80211_KEY_DEFAULT]; k->defmgmt = !!tb[NL80211_KEY_DEFAULT_MGMT]; + k->defbeacon = !!tb[NL80211_KEY_DEFAULT_BEACON]; if (k->def) { k->def_uni = true; k->def_multi = true; } - if (k->defmgmt) + if (k->defmgmt || k->defbeacon) k->def_multi = true; if (tb[NL80211_KEY_IDX]) @@ -1167,14 +1185,17 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) if (err) return err; - if (k->def && k->defmgmt) { - GENL_SET_ERR_MSG(info, "key with def && defmgmt is invalid"); + if ((k->def ? 1 : 0) + (k->defmgmt ? 1 : 0) + + (k->defbeacon ? 1 : 0) > 1) { + GENL_SET_ERR_MSG(info, + "key with multiple default flags is invalid"); return -EINVAL; } - if (k->defmgmt) { + if (k->defmgmt || k->defbeacon) { if (k->def_uni || !k->def_multi) { - GENL_SET_ERR_MSG(info, "defmgmt key must be mcast"); + GENL_SET_ERR_MSG(info, + "defmgmt/defbeacon key must be mcast"); return -EINVAL; } } @@ -1186,14 +1207,20 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) "defmgmt key idx not 4 or 5"); return -EINVAL; } + } else if (k->defbeacon) { + if (k->idx < 6 || k->idx > 7) { + GENL_SET_ERR_MSG(info, + "defbeacon key idx not 6 or 7"); + return -EINVAL; + } } else if (k->def) { if (k->idx < 0 || k->idx > 3) { GENL_SET_ERR_MSG(info, "def key idx not 0-3"); return -EINVAL; } } else { - if (k->idx < 0 || k->idx > 5) { - GENL_SET_ERR_MSG(info, "key idx not 0-5"); + if (k->idx < 0 || k->idx > 7) { + GENL_SET_ERR_MSG(info, "key idx not 0-7"); return -EINVAL; } } @@ -1939,6 +1966,48 @@ nl80211_put_iftype_akm_suites(struct cfg80211_registered_device *rdev, return 0; } +static int +nl80211_put_tid_config_support(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) +{ + struct nlattr *supp; + + if (!rdev->wiphy.tid_config_support.vif && + !rdev->wiphy.tid_config_support.peer) + return 0; + + supp = nla_nest_start(msg, NL80211_ATTR_TID_CONFIG); + if (!supp) + return -ENOSPC; + + if (rdev->wiphy.tid_config_support.vif && + nla_put_u64_64bit(msg, NL80211_TID_CONFIG_ATTR_VIF_SUPP, + rdev->wiphy.tid_config_support.vif, + NL80211_TID_CONFIG_ATTR_PAD)) + goto fail; + + if (rdev->wiphy.tid_config_support.peer && + nla_put_u64_64bit(msg, NL80211_TID_CONFIG_ATTR_PEER_SUPP, + rdev->wiphy.tid_config_support.peer, + NL80211_TID_CONFIG_ATTR_PAD)) + goto fail; + + /* for now we just use the same value ... makes more sense */ + if (nla_put_u8(msg, NL80211_TID_CONFIG_ATTR_RETRY_SHORT, + rdev->wiphy.tid_config_support.max_retry)) + goto fail; + if (nla_put_u8(msg, NL80211_TID_CONFIG_ATTR_RETRY_LONG, + rdev->wiphy.tid_config_support.max_retry)) + goto fail; + + nla_nest_end(msg, supp); + + return 0; +fail: + nla_nest_cancel(msg, supp); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2500,6 +2569,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_put_iftype_akm_suites(rdev, msg)) goto nla_put_failure; + if (nl80211_put_tid_config_support(rdev, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -3819,8 +3891,14 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) void *hdr; struct sk_buff *msg; - if (info->attrs[NL80211_ATTR_KEY_IDX]) + if (info->attrs[NL80211_ATTR_KEY_IDX]) { key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); + if (key_idx > 5 && + !wiphy_ext_feature_isset( + &rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + return -EINVAL; + } if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3896,7 +3974,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) /* Only support setting default key and * Extended Key ID action NL80211_KEY_SET_TX. */ - if (!key.def && !key.defmgmt && + if (!key.def && !key.defmgmt && !key.defbeacon && !(key.p.mode == NL80211_KEY_SET_TX)) return -EINVAL; @@ -3943,6 +4021,24 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_CFG80211_WEXT dev->ieee80211_ptr->wext.default_mgmt_key = key.idx; #endif + } else if (key.defbeacon) { + if (key.def_uni || !key.def_multi) { + err = -EINVAL; + goto out; + } + + if (!rdev->ops->set_default_beacon_key) { + err = -EOPNOTSUPP; + goto out; + } + + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (err) + goto out; + + err = rdev_set_default_beacon_key(rdev, dev, key.idx); + if (err) + goto out; } else if (key.p.mode == NL80211_KEY_SET_TX && wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) { @@ -3980,8 +4076,10 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (!key.p.key) + if (!key.p.key) { + GENL_SET_ERR_MSG(info, "no key"); return -EINVAL; + } if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3995,8 +4093,10 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) /* for now */ if (key.type != NL80211_KEYTYPE_PAIRWISE && - key.type != NL80211_KEYTYPE_GROUP) + key.type != NL80211_KEYTYPE_GROUP) { + GENL_SET_ERR_MSG(info, "key type not pairwise or group"); return -EINVAL; + } if (key.type == NL80211_KEYTYPE_GROUP && info->attrs[NL80211_ATTR_VLAN_ID]) @@ -4007,15 +4107,22 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (cfg80211_validate_key_settings(rdev, &key.p, key.idx, key.type == NL80211_KEYTYPE_PAIRWISE, - mac_addr)) + mac_addr)) { + GENL_SET_ERR_MSG(info, "key setting validation failed"); return -EINVAL; + } wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); - if (!err) + if (err) + GENL_SET_ERR_MSG(info, "key not allowed"); + if (!err) { err = rdev_add_key(rdev, dev, key.idx, key.type == NL80211_KEYTYPE_PAIRWISE, mac_addr, &key.p); + if (err) + GENL_SET_ERR_MSG(info, "key addition failed"); + } wdev_unlock(dev->ieee80211_ptr); return err; @@ -4880,8 +4987,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - if (err) - return err; + goto out; } if (info->attrs[NL80211_ATTR_HE_BSS_COLOR]) { @@ -4911,6 +5017,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) } wdev_unlock(wdev); +out: kfree(params.acl); return err; @@ -13698,7 +13805,6 @@ static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) const u8 *buf; size_t len; u8 *dest; - u8 src[ETH_ALEN]; u16 proto; bool noencrypt; int err; @@ -13736,13 +13842,6 @@ static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) goto out; } - /* copy src address under wdev_lock, as we may copy wdev_address */ - if (info->attrs[NL80211_ATTR_SRC_MAC]) - ether_addr_copy(src, - nla_data(info->attrs[NL80211_ATTR_SRC_MAC])); - else - ether_addr_copy(src, wdev_address(wdev)); - wdev_unlock(wdev); buf = nla_data(info->attrs[NL80211_ATTR_FRAME]); @@ -13753,7 +13852,7 @@ static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info) nla_get_flag(info->attrs[NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT]); return rdev_tx_control_port(rdev, dev, buf, len, - dest, src, cpu_to_be16(proto), noencrypt); + dest, cpu_to_be16(proto), noencrypt); out: wdev_unlock(wdev); @@ -13899,6 +13998,141 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info) return rdev_probe_mesh_link(rdev, dev, dest, buf, len); } +static int parse_tid_conf(struct cfg80211_registered_device *rdev, + struct nlattr *attrs[], struct net_device *dev, + struct cfg80211_tid_cfg *tid_conf, + struct genl_info *info, const u8 *peer) +{ + struct netlink_ext_ack *extack = info->extack; + u64 mask; + int err; + + if (!attrs[NL80211_TID_CONFIG_ATTR_TIDS]) + return -EINVAL; + + tid_conf->config_override = + nla_get_flag(attrs[NL80211_TID_CONFIG_ATTR_OVERRIDE]); + tid_conf->tids = nla_get_u16(attrs[NL80211_TID_CONFIG_ATTR_TIDS]); + + if (tid_conf->config_override) { + if (rdev->ops->reset_tid_config) { + err = rdev_reset_tid_config(rdev, dev, peer, + tid_conf->tids); + /* If peer is there no other configuration will be + * allowed + */ + if (err || peer) + return err; + } else { + return -EINVAL; + } + } + + if (attrs[NL80211_TID_CONFIG_ATTR_NOACK]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_NOACK); + tid_conf->noack = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_NOACK]); + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RETRY_SHORT]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RETRY_SHORT); + tid_conf->retry_short = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RETRY_SHORT]); + + if (tid_conf->retry_short > rdev->wiphy.max_data_retry_count) + return -EINVAL; + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RETRY_LONG]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RETRY_LONG); + tid_conf->retry_long = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RETRY_LONG]); + + if (tid_conf->retry_long > rdev->wiphy.max_data_retry_count) + return -EINVAL; + } + + if (attrs[NL80211_TID_CONFIG_ATTR_AMPDU_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_AMPDU_CTRL); + tid_conf->ampdu = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_AMPDU_CTRL]); + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL); + tid_conf->rtscts = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]); + } + + if (peer) + mask = rdev->wiphy.tid_config_support.peer; + else + mask = rdev->wiphy.tid_config_support.vif; + + if (tid_conf->mask & ~mask) { + NL_SET_ERR_MSG(extack, "unsupported TID configuration"); + return -ENOTSUPP; + } + + return 0; +} + +static int nl80211_set_tid_config(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct nlattr *attrs[NL80211_TID_CONFIG_ATTR_MAX + 1]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_tid_config *tid_config; + struct nlattr *tid; + int conf_idx = 0, rem_conf; + int ret = -EINVAL; + u32 num_conf = 0; + + if (!info->attrs[NL80211_ATTR_TID_CONFIG]) + return -EINVAL; + + if (!rdev->ops->set_tid_config) + return -EOPNOTSUPP; + + nla_for_each_nested(tid, info->attrs[NL80211_ATTR_TID_CONFIG], + rem_conf) + num_conf++; + + tid_config = kzalloc(struct_size(tid_config, tid_conf, num_conf), + GFP_KERNEL); + if (!tid_config) + return -ENOMEM; + + tid_config->n_tid_conf = num_conf; + + if (info->attrs[NL80211_ATTR_MAC]) + tid_config->peer = nla_data(info->attrs[NL80211_ATTR_MAC]); + + nla_for_each_nested(tid, info->attrs[NL80211_ATTR_TID_CONFIG], + rem_conf) { + ret = nla_parse_nested(attrs, NL80211_TID_CONFIG_ATTR_MAX, + tid, NULL, NULL); + + if (ret) + goto bad_tid_conf; + + ret = parse_tid_conf(rdev, attrs, dev, + &tid_config->tid_conf[conf_idx], + info, tid_config->peer); + if (ret) + goto bad_tid_conf; + + conf_idx++; + } + + ret = rdev_set_tid_config(rdev, dev, tid_config); + +bad_tid_conf: + kfree(tid_config); + return ret; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -14853,6 +15087,13 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_TID_CONFIG, + .doit = nl80211_set_tid_config, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_family nl80211_fam __ro_after_init = { @@ -16010,8 +16251,7 @@ static int __nl80211_rx_control_port(struct net_device *dev, struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct ethhdr *ehdr = eth_hdr(skb); - const u8 *daddr = ehdr->h_dest; - const u8 *saddr = ehdr->h_source; + const u8 *addr = ehdr->h_source; u16 proto = be16_to_cpu(skb->protocol); struct sk_buff *msg; void *hdr; @@ -16036,8 +16276,7 @@ static int __nl80211_rx_control_port(struct net_device *dev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || - nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, saddr) || - nla_put(msg, NL80211_ATTR_DST_MAC, ETH_ALEN, daddr) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) || (unencrypted && nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT))) diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 5ea34c1b60fe..99462f0c4e08 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -136,6 +136,19 @@ rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_default_beacon_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index) +{ + int ret; + + trace_rdev_set_default_beacon_key(&rdev->wiphy, netdev, key_index); + ret = rdev->ops->set_default_beacon_key(&rdev->wiphy, netdev, + key_index); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_settings *settings) @@ -734,14 +747,14 @@ static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev, static inline int rdev_tx_control_port(struct cfg80211_registered_device *rdev, struct net_device *dev, const void *buf, size_t len, - const u8 *dest, const u8 *src, - __be16 proto, const bool noencrypt) + const u8 *dest, __be16 proto, + const bool noencrypt) { int ret; trace_rdev_tx_control_port(&rdev->wiphy, dev, buf, len, - dest, src, proto, noencrypt); + dest, proto, noencrypt); ret = rdev->ops->tx_control_port(&rdev->wiphy, dev, buf, len, - dest, src, proto, noencrypt); + dest, proto, noencrypt); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -1313,4 +1326,28 @@ rdev_probe_mesh_link(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_set_tid_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_tid_config *tid_conf) +{ + int ret; + + trace_rdev_set_tid_config(&rdev->wiphy, dev, tid_conf); + ret = rdev->ops->set_tid_config(&rdev->wiphy, dev, tid_conf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *peer, + u8 tids) +{ + int ret; + + trace_rdev_reset_tid_config(&rdev->wiphy, dev, peer, tids); + ret = rdev->ops->reset_tid_config(&rdev->wiphy, dev, peer, tids); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 173a7d7a7003..d476d4da0d09 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2278,7 +2278,7 @@ static void handle_channel_custom(struct wiphy *wiphy, break; } - if (IS_ERR(reg_rule)) { + if (IS_ERR_OR_NULL(reg_rule)) { pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { diff --git a/net/wireless/scan.c b/net/wireless/scan.c index aef240fdf8df..dd41e41f9d26 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -556,9 +556,8 @@ cfg80211_find_sched_scan_req(struct cfg80211_registered_device *rdev, u64 reqid) { struct cfg80211_sched_scan_request *pos; - WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - - list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list) { + list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list, + lockdep_rtnl_is_held()) { if (pos->reqid == reqid) return pos; } @@ -1434,8 +1433,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, } rcu_assign_pointer(tmp.pub.ies, ies); - signal_valid = abs(data->chan->center_freq - channel->center_freq) <= - wiphy->max_adj_channel_rssi_comp; + signal_valid = data->chan == channel; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, ts); if (!res) return NULL; @@ -1852,8 +1850,7 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); ether_addr_copy(tmp.parent_bssid, data->parent_bssid); - signal_valid = abs(data->chan->center_freq - channel->center_freq) <= - wiphy->max_adj_channel_rssi_comp; + signal_valid = data->chan == channel; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, jiffies); if (!res) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d32a2ec4d96a..ac3e60aa1fc8 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1111,9 +1111,16 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ - if (rdev->ops->del_key) - for (i = 0; i < 6; i++) + if (rdev->ops->del_key) { + int max_key_idx = 5; + + if (wiphy_ext_feature_isset( + wdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + max_key_idx = 7; + for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, i, false, NULL); + } rdev_set_qos_map(rdev, dev, NULL); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index b6b60e3aea41..839df54cee21 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -510,6 +510,23 @@ TRACE_EVENT(rdev_set_default_mgmt_key, WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) ); +TRACE_EVENT(rdev_set_default_beacon_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index), + TP_ARGS(wiphy, netdev, key_index), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u8, key_index) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->key_index = key_index; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key index: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) +); + TRACE_EVENT(rdev_start_ap, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_ap_settings *settings), @@ -1928,31 +1945,27 @@ TRACE_EVENT(rdev_mgmt_tx, TRACE_EVENT(rdev_tx_control_port, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, - const u8 *buf, size_t len, - const u8 *dest, const u8 *src, __be16 proto, + const u8 *buf, size_t len, const u8 *dest, __be16 proto, bool unencrypted), - TP_ARGS(wiphy, netdev, buf, len, dest, src, proto, unencrypted), + TP_ARGS(wiphy, netdev, buf, len, dest, proto, unencrypted), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY MAC_ENTRY(dest) - MAC_ENTRY(src) - __field(u16, proto) + __field(__be16, proto) __field(bool, unencrypted) ), TP_fast_assign( WIPHY_ASSIGN; NETDEV_ASSIGN; MAC_ASSIGN(dest, dest); - MAC_ASSIGN(src, src); - __entry->proto = be16_to_cpu(proto); + __entry->proto = proto; __entry->unencrypted = unencrypted; ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", dest: " MAC_PR_FMT - ", src: " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", - WIPHY_PR_ARG, NETDEV_PR_ARG, - MAC_PR_ARG(dest), MAC_PR_ARG(src), - __entry->proto, + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT "," + " proto: 0x%x, unencrypted: %s", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dest), + be16_to_cpu(__entry->proto), BOOL_TO_STR(__entry->unencrypted)) ); @@ -2844,7 +2857,6 @@ TRACE_EVENT(cfg80211_rx_control_port, TP_STRUCT__entry( NETDEV_ENTRY __field(int, len) - MAC_ENTRY(to) MAC_ENTRY(from) __field(u16, proto) __field(bool, unencrypted) @@ -2852,14 +2864,12 @@ TRACE_EVENT(cfg80211_rx_control_port, TP_fast_assign( NETDEV_ASSIGN; __entry->len = skb->len; - MAC_ASSIGN(to, eth_hdr(skb)->h_dest); MAC_ASSIGN(from, eth_hdr(skb)->h_source); __entry->proto = be16_to_cpu(skb->protocol); __entry->unencrypted = unencrypted; ), - TP_printk(NETDEV_PR_FMT ", len=%d, dest: " MAC_PR_FMT - ", src: " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", - NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(to), MAC_PR_ARG(from), + TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", + NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from), __entry->proto, BOOL_TO_STR(__entry->unencrypted)) ); @@ -3470,6 +3480,43 @@ TRACE_EVENT(rdev_probe_mesh_link, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dest)) ); +TRACE_EVENT(rdev_set_tid_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_tid_config *tid_conf), + TP_ARGS(wiphy, netdev, tid_conf), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, tid_conf->peer); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer)) +); + +TRACE_EVENT(rdev_reset_tid_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const u8 *peer, u8 tids), + TP_ARGS(wiphy, netdev, peer, tids), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(u8, tids) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->tids = tids; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", tids: 0x%x", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tids) +); #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index 80fb47c43bdd..6590efbbcbb9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -231,7 +231,12 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - if (key_idx < 0 || key_idx > 5) + int max_key_idx = 5; + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + max_key_idx = 7; + if (key_idx < 0 || key_idx > max_key_idx) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 89a01ac4e079..b50bb5c76da5 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -19,13 +19,13 @@ struct xdp_ring { /* Used for the RX and TX queues for packets */ struct xdp_rxtx_ring { struct xdp_ring ptrs; - struct xdp_desc desc[0] ____cacheline_aligned_in_smp; + struct xdp_desc desc[] ____cacheline_aligned_in_smp; }; /* Used for the fill and completion queues for buffers */ struct xdp_umem_ring { struct xdp_ring ptrs; - u64 desc[0] ____cacheline_aligned_in_smp; + u64 desc[] ____cacheline_aligned_in_smp; }; struct xsk_queue { diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index f15d6a564b0e..037ea156d2f9 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -100,7 +100,7 @@ static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, flags |= nonblock ? MSG_DONTWAIT : 0; - skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, NULL, &off, &err); + skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err); if (!skb) return err; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index bae62549e3d2..752ff0a225a9 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -300,15 +300,15 @@ DT_BINDING_DIR := Documentation/devicetree/bindings DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.yaml quiet_cmd_dtb_check = CHECK $@ - cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ ; + cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ -define rule_dtc_dt_yaml +define rule_dtc $(call cmd_and_fixdep,dtc,yaml) $(call cmd,dtb_check) endef $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_rule,dtc_dt_yaml) + $(call if_changed_rule,dtc) dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp) diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h index e978a63d3222..036e667596eb 100644 --- a/tools/bootconfig/include/linux/printk.h +++ b/tools/bootconfig/include/linux/printk.h @@ -4,10 +4,7 @@ #include <stdio.h> -/* controllable printf */ -extern int pr_output; -#define printk(fmt, ...) \ - (pr_output ? printf(fmt, ##__VA_ARGS__) : 0) +#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__) #define pr_err printk #define pr_warn printk diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index e18eeb070562..a9b97814d1a9 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -14,8 +14,6 @@ #include <linux/kernel.h> #include <linux/bootconfig.h> -int pr_output = 1; - static int xbc_show_array(struct xbc_node *node) { const char *val; @@ -131,15 +129,26 @@ int load_xbc_from_initrd(int fd, char **buf) struct stat stat; int ret; u32 size = 0, csum = 0, rcsum; + char magic[BOOTCONFIG_MAGIC_LEN]; ret = fstat(fd, &stat); if (ret < 0) return -errno; - if (stat.st_size < 8) + if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN) + return 0; + + if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) { + pr_err("Failed to lseek: %d\n", -errno); + return -errno; + } + if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) + return -errno; + /* Check the bootconfig magic bytes */ + if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -8, SEEK_END) < 0) { + if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) { pr_err("Failed to lseek: %d\n", -errno); return -errno; } @@ -150,11 +159,14 @@ int load_xbc_from_initrd(int fd, char **buf) if (read(fd, &csum, sizeof(u32)) < 0) return -errno; - /* Wrong size, maybe no boot config here */ - if (stat.st_size < size + 8) - return 0; + /* Wrong size error */ + if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { + pr_err("bootconfig size is too big\n"); + return -E2BIG; + } - if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) { + if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN), + SEEK_SET) < 0) { pr_err("Failed to lseek: %d\n", -errno); return -errno; } @@ -163,17 +175,17 @@ int load_xbc_from_initrd(int fd, char **buf) if (ret < 0) return ret; - /* Wrong Checksum, maybe no boot config here */ + /* Wrong Checksum */ rcsum = checksum((unsigned char *)*buf, size); if (csum != rcsum) { pr_err("checksum error: %d != %d\n", csum, rcsum); - return 0; + return -EINVAL; } ret = xbc_init(*buf); - /* Wrong data, maybe no boot config here */ + /* Wrong data */ if (ret < 0) - return 0; + return ret; return size; } @@ -213,20 +225,15 @@ int delete_xbc(const char *path) return -errno; } - /* - * Suppress error messages in xbc_init() because it can be just a - * data which concidentally matches the size and checksum footer. - */ - pr_output = 0; size = load_xbc_from_initrd(fd, &buf); - pr_output = 1; if (size < 0) { ret = size; pr_err("Failed to load a boot config from initrd: %d\n", ret); } else if (size > 0) { ret = fstat(fd, &stat); if (!ret) - ret = ftruncate(fd, stat.st_size - size - 8); + ret = ftruncate(fd, stat.st_size + - size - 8 - BOOTCONFIG_MAGIC_LEN); if (ret) ret = -errno; } /* Ignore if there is no boot config in initrd */ @@ -295,6 +302,12 @@ int apply_xbc(const char *path, const char *xbc_path) pr_err("Failed to apply a boot config: %d\n", ret); return ret; } + /* Write a magic word of the bootconfig */ + ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); + if (ret < 0) { + pr_err("Failed to apply a boot config magic: %d\n", ret); + return ret; + } close(fd); free(data); diff --git a/tools/bootconfig/samples/bad-mixed-kv1.bconf b/tools/bootconfig/samples/bad-mixed-kv1.bconf new file mode 100644 index 000000000000..1761547dd05c --- /dev/null +++ b/tools/bootconfig/samples/bad-mixed-kv1.bconf @@ -0,0 +1,3 @@ +# value -> subkey pattern +key = value +key.subkey = another-value diff --git a/tools/bootconfig/samples/bad-mixed-kv2.bconf b/tools/bootconfig/samples/bad-mixed-kv2.bconf new file mode 100644 index 000000000000..6b32e0c3878c --- /dev/null +++ b/tools/bootconfig/samples/bad-mixed-kv2.bconf @@ -0,0 +1,3 @@ +# subkey -> value pattern +key.subkey = value +key = another-value diff --git a/tools/bootconfig/samples/bad-samekey.bconf b/tools/bootconfig/samples/bad-samekey.bconf new file mode 100644 index 000000000000..e8d983a4563c --- /dev/null +++ b/tools/bootconfig/samples/bad-samekey.bconf @@ -0,0 +1,6 @@ +# Same key value is not allowed +key { + foo = value + bar = value2 +} +key.foo = value diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index 1de06de328e2..1411f4c3454f 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -9,7 +9,7 @@ TEMPCONF=`mktemp temp-XXXX.bconf` NG=0 cleanup() { - rm -f $INITRD $TEMPCONF + rm -f $INITRD $TEMPCONF $OUTFILE exit $NG } @@ -49,7 +49,7 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD new_size=$(stat -c %s $INITRD) echo "File size check" -xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9) +xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12) echo "Apply command repeat test" xpass $BOOTCONF -a $TEMPCONF $INITRD @@ -71,7 +71,6 @@ printf " \0\0\0 \0\0\0" >> $INITRD $BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1 xfail grep -i "failed" $OUTFILE xfail grep -i "error" $OUTFILE -rm $OUTFILE echo "Max node number check" @@ -96,6 +95,19 @@ truncate -s 32764 $TEMPCONF echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0') xpass $BOOTCONF -a $TEMPCONF $INITRD +echo "Adding same-key values" +cat > $TEMPCONF << EOF +key = bar, baz +key += qux +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xpass grep -q "bar" $OUTFILE +xpass grep -q "baz" $OUTFILE +xpass grep -q "qux" $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index e59eb9e7f923..180ad1e1b04f 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -24,6 +24,8 @@ KunitResult = namedtuple('KunitResult', ['status','result']) KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig']) +KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0] + class KunitStatus(Enum): SUCCESS = auto() CONFIG_FAILURE = auto() @@ -35,6 +37,13 @@ def create_default_kunitconfig(): shutil.copyfile('arch/um/configs/kunit_defconfig', kunit_kernel.kunitconfig_path) +def get_kernel_root_path(): + parts = sys.argv[0] if not __file__ else __file__ + parts = os.path.realpath(parts).split('tools/testing/kunit') + if len(parts) != 2: + sys.exit(1) + return parts[0] + def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: config_start = time.time() @@ -114,6 +123,9 @@ def main(argv, linux=None): cli_args = parser.parse_args(argv) if cli_args.subcommand == 'run': + if get_kernel_root_path(): + os.chdir(get_kernel_root_path()) + if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index cc5d844ecca1..d99ae75ef72f 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -93,6 +93,20 @@ class LinuxSourceTree(object): return False return True + def validate_config(self, build_dir): + kconfig_path = get_kconfig_path(build_dir) + validated_kconfig = kunit_config.Kconfig() + validated_kconfig.read_from_file(kconfig_path) + if not self._kconfig.is_subset_of(validated_kconfig): + invalid = self._kconfig.entries() - validated_kconfig.entries() + message = 'Provided Kconfig is not contained in validated .config. Following fields found in kunitconfig, ' \ + 'but not in .config: %s' % ( + ', '.join([str(e) for e in invalid]) + ) + logging.error(message) + return False + return True + def build_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) if build_dir and not os.path.exists(build_dir): @@ -103,12 +117,7 @@ class LinuxSourceTree(object): except ConfigError as e: logging.error(e) return False - validated_kconfig = kunit_config.Kconfig() - validated_kconfig.read_from_file(kconfig_path) - if not self._kconfig.is_subset_of(validated_kconfig): - logging.error('Provided Kconfig is not contained in validated .config!') - return False - return True + return self.validate_config(build_dir) def build_reconfig(self, build_dir): """Creates a new .config if it is not a subset of the .kunitconfig.""" @@ -133,12 +142,7 @@ class LinuxSourceTree(object): except (ConfigError, BuildError) as e: logging.error(e) return False - used_kconfig = kunit_config.Kconfig() - used_kconfig.read_from_file(get_kconfig_path(build_dir)) - if not self._kconfig.is_subset_of(used_kconfig): - logging.error('Provided Kconfig is not contained in final config!') - return False - return True + return self.validate_config(build_dir) def run_kernel(self, args=[], timeout=None, build_dir=''): args.extend(['mem=256M']) diff --git a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh index 5ba5bef44d5b..bdffe698e1d1 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh @@ -45,6 +45,7 @@ ALL_TESTS=" blackhole_ipv6 " NUM_NETIFS=4 +: ${TIMEOUT:=20000} # ms source $lib_dir/tc_common.sh source $lib_dir/lib.sh @@ -123,7 +124,7 @@ blackhole_ipv4() skip_hw dst_ip 198.51.100.1 src_ip 192.0.2.1 ip_proto icmp \ action pass - ip -4 route show 198.51.100.0/30 | grep -q offload + busywait "$TIMEOUT" wait_for_offload ip -4 route show 198.51.100.0/30 check_err $? "route not marked as offloaded when should" ping_do $h1 198.51.100.1 @@ -147,7 +148,7 @@ blackhole_ipv6() skip_hw dst_ip 2001:db8:2::1 src_ip 2001:db8:1::1 \ ip_proto icmpv6 action pass - ip -6 route show 2001:db8:2::/120 | grep -q offload + busywait "$TIMEOUT" wait_for_offload ip -6 route show 2001:db8:2::/120 check_err $? "route not marked as offloaded when should" ping6_do $h1 2001:db8:2::1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh new file mode 100755 index 000000000000..26044e397157 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh @@ -0,0 +1,151 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap ACL drops functionality over mlxsw. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ingress_flow_action_drop_test + egress_flow_action_drop_test +" +NUM_NETIFS=4 +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 +} + +h2_destroy() +{ + simple_if_fini $h2 +} + +switch_create() +{ + ip link add dev br0 type bridge vlan_filtering 1 mcast_snooping 0 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ingress_flow_action_drop_test() +{ + local mz_pid + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower src_mac $h1mac action pass + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \ + flower dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 0 -p 100 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -d 1msec -q & + mz_pid=$! + + RET=0 + + devlink_trap_drop_test ingress_flow_action_drop acl_drops $swp2 101 + + log_test "ingress_flow_action_drop" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 +} + +egress_flow_action_drop_test() +{ + local mz_pid + + tc filter add dev $swp2 egress protocol ip pref 2 handle 102 \ + flower src_mac $h1mac action pass + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 0 -p 100 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -d 1msec -q & + mz_pid=$! + + RET=0 + + devlink_trap_drop_test egress_flow_action_drop acl_drops $swp2 102 + + log_test "egress_flow_action_drop" + + tc filter del dev $swp2 egress protocol ip pref 1 handle 101 flower + + devlink_trap_drop_cleanup $mz_pid $swp2 ip 2 102 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh index 58cdbfb608e9..e7aecb065409 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh @@ -107,11 +107,11 @@ source_mac_is_multicast_test() RET=0 - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 log_test "Source MAC is multicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 } __vlan_tag_mismatch_test() @@ -132,7 +132,7 @@ __vlan_tag_mismatch_test() $MZ $h1 "$opt" -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Add PVID and make sure packets are no longer dropped. bridge vlan add vid 1 dev $swp1 pvid untagged master @@ -148,7 +148,7 @@ __vlan_tag_mismatch_test() devlink_trap_action_set $trap_name "drop" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 } vlan_tag_mismatch_untagged_test() @@ -193,7 +193,7 @@ ingress_vlan_filter_test() $MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Add the VLAN on the bridge port and make sure packets are no longer # dropped. @@ -212,7 +212,7 @@ ingress_vlan_filter_test() log_test "Ingress VLAN filter" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 bridge vlan del vid $vid dev $swp1 master bridge vlan del vid $vid dev $swp2 master @@ -237,7 +237,7 @@ __ingress_stp_filter_test() $MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Change STP state to forwarding and make sure packets are no longer # dropped. @@ -254,7 +254,7 @@ __ingress_stp_filter_test() devlink_trap_action_set $trap_name "drop" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 bridge vlan del vid $vid dev $swp1 master bridge vlan del vid $vid dev $swp2 master @@ -308,7 +308,7 @@ port_list_is_empty_uc_test() $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Allow packets to be flooded to one port. ip link set dev $swp2 type bridge_slave flood on @@ -326,7 +326,7 @@ port_list_is_empty_uc_test() log_test "Port list is empty - unicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 ip link set dev $swp1 type bridge_slave flood on } @@ -354,7 +354,7 @@ port_list_is_empty_mc_test() $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Allow packets to be flooded to one port. ip link set dev $swp2 type bridge_slave mcast_flood on @@ -372,7 +372,7 @@ port_list_is_empty_mc_test() log_test "Port list is empty - multicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 ip link set dev $swp1 type bridge_slave mcast_flood on } @@ -401,7 +401,7 @@ port_loopback_filter_uc_test() $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Allow packets to be flooded. ip link set dev $swp2 type bridge_slave flood on @@ -419,7 +419,7 @@ port_loopback_filter_uc_test() log_test "Port loopback filter - unicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 } port_loopback_filter_test() diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index d88d8e47d11b..616f47d86a61 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -176,11 +176,11 @@ non_ip_test() 00:00 de:ad:be:ef" & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Non IP" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } __uc_dip_over_mc_dmac_test() @@ -206,11 +206,11 @@ __uc_dip_over_mc_dmac_test() -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Unicast destination IP over multicast destination MAC: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } uc_dip_over_mc_dmac_test() @@ -242,11 +242,11 @@ __sip_is_loopback_test() -b $rp1mac -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Source IP is loopback address: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } sip_is_loopback_test() @@ -277,11 +277,11 @@ __dip_is_loopback_test() -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Destination IP is loopback address: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } dip_is_loopback_test() @@ -313,11 +313,11 @@ __sip_is_mc_test() -b $rp1mac -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Source IP is multicast: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } sip_is_mc_test() @@ -345,11 +345,11 @@ ipv4_sip_is_limited_bc_test() -B $h2_ipv4 -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IPv4 source IP is limited broadcast" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } ipv4_payload_get() @@ -399,11 +399,11 @@ __ipv4_header_corrupted_test() $MZ $h1 -c 0 -d 1msec -a $h1mac -b $rp1mac -q p=$payload & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IP header corrupted: $desc: IPv4" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } ipv6_payload_get() @@ -446,11 +446,11 @@ __ipv6_header_corrupted_test() $MZ $h1 -c 0 -d 1msec -a $h1mac -b $rp1mac -q p=$payload & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IP header corrupted: $desc: IPv6" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } ip_header_corrupted_test() @@ -485,11 +485,11 @@ ipv6_mc_dip_reserved_scope_test() "33:33:00:00:00:00" -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IPv6 multicast destination IP reserved scope" - devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" + devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" 1 101 } ipv6_mc_dip_interface_local_scope_test() @@ -511,11 +511,11 @@ ipv6_mc_dip_interface_local_scope_test() "33:33:00:00:00:00" -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IPv6 multicast destination IP interface-local scope" - devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" + devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" 1 101 } __blackhole_route_test() @@ -542,10 +542,10 @@ __blackhole_route_test() -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Blackhole route: IPv$flags" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 ip -$flags route del blackhole $subnet } @@ -641,13 +641,9 @@ erif_disabled_test() mz_pid=$! sleep 5 - # In order to see this trap we need a route that points to disabled RIF. - # When ipv6 address is flushed, there is a delay and the routes are - # deleted before the RIF and we cannot get state that we have route - # to disabled RIF. - # Delete IPv6 address first and then check this trap with flushing IPv4. - ip -6 add flush dev br0 - ip -4 add flush dev br0 + # Unlinking the port from the bridge will disable the RIF associated + # with br0 as it is no longer an upper of any mlxsw port. + ip link set dev $rp1 nomaster t1_packets=$(devlink_trap_rx_packets_get $trap_name) t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) @@ -659,7 +655,6 @@ erif_disabled_test() log_test "Egress RIF disabled" kill $mz_pid && wait $mz_pid &> /dev/null - ip link set dev $rp1 nomaster __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge devlink_trap_action_set $trap_name "drop" diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh index fd19161dd4ec..e11a416323cf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -314,11 +314,11 @@ overlay_smac_is_mc_test() -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp1 + devlink_trap_drop_test $trap_name $group_name $swp1 101 log_test "Overlay source MAC is multicast" - devlink_trap_drop_cleanup $mz_pid $swp1 "ip" + devlink_trap_drop_cleanup $mz_pid $swp1 "ip" 1 101 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh new file mode 100644 index 000000000000..cbe50f260a40 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh @@ -0,0 +1,13 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +############################################################################## +# Defines + +if [[ ! -v MLXSW_CHIP ]]; then + MLXSW_CHIP=$(devlink -j dev info $DEVLINK_DEV | jq -r '.[][]["driver"]') + if [ -z "$MLXSW_CHIP" ]; then + echo "SKIP: Device $DEVLINK_DEV doesn't support devlink info command" + exit 1 + fi +fi diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh index d231649b4f01..e93878d42596 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh @@ -2,16 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 ROUTER_NUM_NETIFS=4 +: ${TIMEOUT:=20000} # ms 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 } @@ -64,13 +63,15 @@ router_setup_prepare() router_create } -router_offload_validate() +wait_for_routes() { - local route_count=$1 - local offloaded_count + local t0=$1; shift + local route_count=$1; shift - offloaded_count=$(ip route | grep -o 'offload' | wc -l) - [[ $offloaded_count -ge $route_count ]] + local t1=$(ip route | grep -o 'offload' | wc -l) + local delta=$((t1 - t0)) + echo $delta + [[ $delta -ge $route_count ]] } router_routes_create() @@ -90,8 +91,8 @@ router_routes_create() break 3 fi - echo route add 193.${i}.${j}.${k}/32 via \ - 192.0.2.1 dev $rp2 >> $ROUTE_FILE + echo route add 193.${i}.${j}.${k}/32 dev $rp2 \ + >> $ROUTE_FILE ((count++)) done done @@ -111,45 +112,19 @@ router_test() { local route_count=$1 local should_fail=$2 - local count=0 + local delta RET=0 + local t0=$(ip route | grep -o 'offload' | wc -l) router_routes_create $route_count + delta=$(busywait "$TIMEOUT" wait_for_routes $t0 $route_count) - router_offload_validate $route_count - check_err_fail $should_fail $? "Offload of $route_count routes" + check_err_fail $should_fail $? "Offload routes: Expected $route_count, got $delta." 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 } diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index 5c39e5f6a480..f4031002d5e9 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -32,6 +32,7 @@ ALL_TESTS=" devlink_reload_test " NUM_NETIFS=2 +: ${TIMEOUT:=20000} # ms source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh @@ -360,20 +361,24 @@ vlan_rif_refcount_test() ip link add link br0 name br0.10 up type vlan id 10 ip -6 address add 2001:db8:1::1/64 dev br0.10 - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 check_err $? "vlan rif was not created before adding port to vlan" bridge vlan add vid 10 dev $swp1 - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 check_err $? "vlan rif was destroyed after adding port to vlan" bridge vlan del vid 10 dev $swp1 - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 check_err $? "vlan rif was destroyed after removing port from vlan" ip link set dev $swp1 nomaster - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload - check_fail $? "vlan rif was not destroyed after unlinking port from bridge" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 + check_err $? "vlan rif was not destroyed after unlinking port from bridge" log_test "vlan rif refcount" @@ -401,22 +406,28 @@ subport_rif_refcount_test() ip -6 address add 2001:db8:1::1/64 dev bond1 ip -6 address add 2001:db8:2::1/64 dev bond1.10 - ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev bond1 check_err $? "subport rif was not created on lag device" - ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 check_err $? "subport rif was not created on vlan device" ip link set dev $swp1 nomaster - ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev bond1 check_err $? "subport rif of lag device was destroyed when should not" - ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 check_err $? "subport rif of vlan device was destroyed when should not" ip link set dev $swp2 nomaster - ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload - check_fail $? "subport rif of lag device was not destroyed when should" - ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload - check_fail $? "subport rif of vlan device was not destroyed when should" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev bond1 + check_err $? "subport rif of lag device was not destroyed when should" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 + check_err $? "subport rif of vlan device was not destroyed when should" log_test "subport rif refcount" @@ -575,7 +586,8 @@ bridge_extern_learn_test() bridge fdb add de:ad:be:ef:13:37 dev $swp1 master extern_learn - bridge fdb show brport $swp1 | grep de:ad:be:ef:13:37 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + bridge fdb show brport $swp1 de:ad:be:ef:13:37 check_err $? "fdb entry not marked as offloaded when should" log_test "externally learned fdb entry" @@ -595,9 +607,11 @@ neigh_offload_test() ip -6 neigh add 2001:db8:1::2 lladdr de:ad:be:ef:13:37 nud perm \ dev $swp1 - ip -4 neigh show dev $swp1 | grep 192.0.2.2 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -4 neigh show dev $swp1 192.0.2.2 check_err $? "ipv4 neigh entry not marked as offloaded when should" - ip -6 neigh show dev $swp1 | grep 2001:db8:1::2 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 neigh show dev $swp1 2001:db8:1::2 check_err $? "ipv6 neigh entry not marked as offloaded when should" log_test "neighbour offload indication" @@ -623,25 +637,31 @@ nexthop_offload_test() ip -6 route add 2001:db8:2::/64 vrf v$swp1 \ nexthop via 2001:db8:1::2 dev $swp1 - ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -4 route show 198.51.100.0/24 vrf v$swp1 check_err $? "ipv4 nexthop not marked as offloaded when should" - ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route show 2001:db8:2::/64 vrf v$swp1 check_err $? "ipv6 nexthop not marked as offloaded when should" ip link set dev $swp2 down sleep 1 - ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload - check_fail $? "ipv4 nexthop marked as offloaded when should not" - ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload - check_fail $? "ipv6 nexthop marked as offloaded when should not" + busywait "$TIMEOUT" not wait_for_offload \ + ip -4 route show 198.51.100.0/24 vrf v$swp1 + check_err $? "ipv4 nexthop marked as offloaded when should not" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route show 2001:db8:2::/64 vrf v$swp1 + check_err $? "ipv6 nexthop marked as offloaded when should not" ip link set dev $swp2 up setup_wait - ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -4 route show 198.51.100.0/24 vrf v$swp1 check_err $? "ipv4 nexthop not marked as offloaded after neigh add" - ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route show 2001:db8:2::/64 vrf v$swp1 check_err $? "ipv6 nexthop not marked as offloaded after neigh add" log_test "nexthop offload indication" diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh new file mode 100644 index 000000000000..ebf7752f6d93 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -0,0 +1,499 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends a >1Gbps stream of traffic from H1, to the switch, which +# forwards it to a 1Gbps port. This 1Gbps stream is then looped back to the +# switch and forwarded to the port under test $swp3, which is also 1Gbps. +# +# This way, $swp3 should be 100% filled with traffic without any of it spilling +# to the backlog. Any extra packets sent should almost 1:1 go to backlog. That +# is what H2 is used for--it sends the extra traffic to create backlog. +# +# A RED Qdisc is installed on $swp3. The configuration is such that the minimum +# and maximum size are 1 byte apart, so there is a very clear border under which +# no marking or dropping takes place, and above which everything is marked or +# dropped. +# +# The test uses the buffer build-up behavior to test the installed RED. +# +# In order to test WRED, $swp3 actually contains RED under PRIO, with two +# different configurations. Traffic is prioritized using 802.1p and relies on +# the implicit mlxsw configuration, where packet priority is taken 1:1 from the +# 802.1p marking. +# +# +--------------------------+ +--------------------------+ +# | H1 | | H2 | +# | + $h1.10 | | + $h2.10 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | | | | | +# | | $h1.11 + | | | $h2.11 + | +# | | 192.0.2.17/28 | | | | 192.0.2.18/28 | | +# | | | | | | | | +# | \______ ______/ | | \______ ______/ | +# | \ / | | \ / | +# | + $h1 | | + $h2 | +# +-------------|------------+ +-------------|------------+ +# | >1Gbps | +# +-------------|------------------------------------------------|------------+ +# | SW + $swp1 + $swp2 | +# | _______/ \___________ ___________/ \_______ | +# | / \ / \ | +# | +-|-----------------+ | +-|-----------------+ | | +# | | + $swp1.10 | | | + $swp2.10 | | | +# | | | | .-------------+ $swp5.10 | | | +# | | BR1_10 | | | | | | | +# | | | | | | BR2_10 | | | +# | | + $swp2.10 | | | | | | | +# | +-|-----------------+ | | | + $swp3.10 | | | +# | | | | +-|-----------------+ | | +# | | +-----------------|-+ | | +-----------------|-+ | +# | | | $swp1.11 + | | | | $swp2.11 + | | +# | | | | | .-----------------+ $swp5.11 | | +# | | | BR1_11 | | | | | | | +# | | | | | | | | BR2_11 | | +# | | | $swp2.11 + | | | | | | | +# | | +-----------------|-+ | | | | $swp3.11 + | | +# | | | | | | +-----------------|-+ | +# | \_______ ___________/ | | \___________ _______/ | +# | \ / \ / \ / | +# | + $swp4 + $swp5 + $swp3 | +# +-------------|----------------------|-------------------------|------------+ +# | | | 1Gbps +# \________1Gbps_________/ | +# +----------------------------|------------+ +# | H3 + $h3 | +# | _____________________/ \_______ | +# | / \ | +# | | | | +# | + $h3.10 $h3.11 + | +# | 192.0.2.3/28 192.0.2.19/28 | +# +-----------------------------------------+ + +NUM_NETIFS=8 +CHECK_TC="yes" +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source qos_lib.sh + +ipaddr() +{ + local host=$1; shift + local vlan=$1; shift + + echo 192.0.2.$((16 * (vlan - 10) + host)) +} + +host_create() +{ + local dev=$1; shift + local host=$1; shift + + simple_if_init $dev + mtu_set $dev 10000 + + vlan_create $dev 10 v$dev $(ipaddr $host 10)/28 + ip link set dev $dev.10 type vlan egress 0:0 + + vlan_create $dev 11 v$dev $(ipaddr $host 11)/28 + ip link set dev $dev.11 type vlan egress 0:1 +} + +host_destroy() +{ + local dev=$1; shift + + vlan_destroy $dev 11 + vlan_destroy $dev 10 + mtu_restore $dev + simple_if_fini $dev +} + +h1_create() +{ + host_create $h1 1 +} + +h1_destroy() +{ + host_destroy $h1 +} + +h2_create() +{ + host_create $h2 2 + + # Some of the tests in this suite use multicast traffic. As this traffic + # enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus + # e.g. traffic ingressing through $swp2 is flooded to $swp3 (the + # intended destination) and $swp5 (which is intended as ingress for + # another stream of traffic). + # + # This is generally not a problem, but if the $swp5 throughput is lower + # than $swp2 throughput, there will be a build-up at $swp5. That may + # cause packets to fail to queue up at $swp3 due to shared buffer + # quotas, and the test to spuriously fail. + # + # Prevent this by setting the speed of $h2 to 1Gbps. + + ethtool -s $h2 speed 1000 autoneg off +} + +h2_destroy() +{ + ethtool -s $h2 autoneg on + host_destroy $h2 +} + +h3_create() +{ + host_create $h3 3 + ethtool -s $h3 speed 1000 autoneg off +} + +h3_destroy() +{ + ethtool -s $h3 autoneg on + host_destroy $h3 +} + +switch_create() +{ + local intf + local vlan + + ip link add dev br1_10 type bridge + ip link add dev br1_11 type bridge + + ip link add dev br2_10 type bridge + ip link add dev br2_11 type bridge + + for intf in $swp1 $swp2 $swp3 $swp4 $swp5; do + ip link set dev $intf up + mtu_set $intf 10000 + done + + for intf in $swp1 $swp4; do + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br1_$vlan + ip link set dev $intf.$vlan up + done + done + + for intf in $swp2 $swp3 $swp5; do + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br2_$vlan + ip link set dev $intf.$vlan up + done + done + + ip link set dev $swp4.10 type vlan egress 0:0 + ip link set dev $swp4.11 type vlan egress 0:1 + for intf in $swp1 $swp2 $swp5; do + for vlan in 10 11; do + ip link set dev $intf.$vlan type vlan ingress 0:0 1:1 + done + done + + for intf in $swp2 $swp3 $swp4 $swp5; do + ethtool -s $intf speed 1000 autoneg off + done + + ip link set dev br1_10 up + ip link set dev br1_11 up + ip link set dev br2_10 up + ip link set dev br2_11 up + + local size=$(devlink_pool_size_thtype 0 | cut -d' ' -f 1) + devlink_port_pool_th_set $swp3 8 $size +} + +switch_destroy() +{ + local intf + local vlan + + devlink_port_pool_th_restore $swp3 8 + + tc qdisc del dev $swp3 root 2>/dev/null + + ip link set dev br2_11 down + ip link set dev br2_10 down + ip link set dev br1_11 down + ip link set dev br1_10 down + + for intf in $swp5 $swp4 $swp3 $swp2; do + ethtool -s $intf autoneg on + done + + for intf in $swp5 $swp3 $swp2 $swp4 $swp1; do + for vlan in 11 10; do + ip link set dev $intf.$vlan down + ip link set dev $intf.$vlan nomaster + vlan_destroy $intf $vlan + done + + mtu_restore $intf + ip link set dev $intf down + done + + ip link del dev br2_11 + ip link del dev br2_10 + ip link del dev br1_11 + ip link del dev br1_10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + swp4=${NETIFS[p7]} + swp5=${NETIFS[p8]} + + h3_mac=$(mac_get $h3) + + vrf_prepare + + h1_create + h2_create + h3_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(ipaddr 3 10) " from host 1, vlan 10" + ping_test $h1.11 $(ipaddr 3 11) " from host 1, vlan 11" + ping_test $h2.10 $(ipaddr 3 10) " from host 2, vlan 10" + ping_test $h2.11 $(ipaddr 3 11) " from host 2, vlan 11" +} + +get_tc() +{ + local vlan=$1; shift + + echo $((vlan - 10)) +} + +get_qdisc_handle() +{ + local vlan=$1; shift + + local tc=$(get_tc $vlan) + local band=$((8 - tc)) + + # Handle is 107: for TC1, 108: for TC0. + echo "10$band:" +} + +get_qdisc_backlog() +{ + local vlan=$1; shift + + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .backlog +} + +get_mc_transmit_queue() +{ + local vlan=$1; shift + + local tc=$(($(get_tc $vlan) + 8)) + ethtool_stats_get $swp3 tc_transmit_queue_tc_$tc +} + +get_nmarked() +{ + local vlan=$1; shift + + ethtool_stats_get $swp3 ecn_marked +} + +get_qdisc_npackets() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets +} + +# This sends traffic in an attempt to build a backlog of $size. Returns 0 on +# success. After 10 failed attempts it bails out and returns 1. It dumps the +# backlog size to stdout. +build_backlog() +{ + local vlan=$1; shift + local size=$1; shift + local proto=$1; shift + + local tc=$((vlan - 10)) + local band=$((8 - tc)) + local cur=-1 + local i=0 + + while :; do + local cur=$(busywait 1100 until_counter_is $((cur + 1)) \ + get_qdisc_backlog $vlan) + local diff=$((size - cur)) + local pkts=$(((diff + 7999) / 8000)) + + if ((cur >= size)); then + echo $cur + return 0 + elif ((i++ > 10)); then + echo $cur + return 1 + fi + + $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ + -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ + -t $proto -q -c $pkts "$@" + done +} + +check_marking() +{ + local vlan=$1; shift + local cond=$1; shift + + local npackets_0=$(get_qdisc_npackets $vlan) + local nmarked_0=$(get_nmarked $vlan) + sleep 5 + local npackets_1=$(get_qdisc_npackets $vlan) + local nmarked_1=$(get_nmarked $vlan) + + local nmarked_d=$((nmarked_1 - nmarked_0)) + local npackets_d=$((npackets_1 - npackets_0)) + local pct=$((100 * nmarked_d / npackets_d)) + + echo $pct + ((pct $cond)) +} + +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + local backlog + local pct + + # Main stream. + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Build the below-the-limit backlog using UDP. We could use TCP just + # fine, but this way we get a proof that UDP is accepted when queue + # length is below the limit. The main stream is using TCP, and if the + # limit is misconfigured, we would see this traffic being ECN marked. + RET=0 + backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) + check_err $? "Could not build the requested backlog" + pct=$(check_marking $vlan "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "TC $((vlan - 10)): ECN backlog < limit" + + # Now push TCP, because non-TCP traffic would be early-dropped after the + # backlog crosses the limit, and we want to make sure that the backlog + # is above the limit. + RET=0 + backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking $vlan ">= 95") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." + log_test "TC $((vlan - 10)): ECN backlog > limit" + + # Up there we saw that UDP gets accepted when backlog is below the + # limit. Now that it is above, it should all get dropped, and backlog + # building should fail. + RET=0 + build_backlog $vlan $((2 * limit)) udp >/dev/null + check_fail $? "UDP traffic went into backlog instead of being early-dropped" + log_test "TC $((vlan - 10)): ECN backlog > limit: UDP early-dropped" + + stop_traffic + sleep 1 +} + +do_red_test() +{ + local vlan=$1; shift + local limit=$1; shift + local backlog + local pct + + # Use ECN-capable TCP to verify there's no marking even though the queue + # is above limit. + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Pushing below the queue limit should work. + RET=0 + backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking $vlan "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "TC $((vlan - 10)): RED backlog < limit" + + # Pushing above should not. + RET=0 + backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) + check_fail $? "Traffic went into backlog instead of being early-dropped" + pct=$(check_marking $vlan "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + local diff=$((limit - backlog)) + pct=$((100 * diff / limit)) + ((0 <= pct && pct <= 5)) + check_err $? "backlog $backlog / $limit expected <= 5% distance" + log_test "TC $((vlan - 10)): RED backlog > limit" + + stop_traffic + sleep 1 +} + +do_mc_backlog_test() +{ + local vlan=$1; shift + local limit=$1; shift + local backlog + local pct + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) bc + start_tcp_traffic $h2.$vlan $(ipaddr 2 $vlan) $(ipaddr 3 $vlan) bc + + qbl=$(busywait 5000 until_counter_is 500000 \ + get_qdisc_backlog $vlan) + check_err $? "Could not build MC backlog" + + # Verify that we actually see the backlog on BUM TC. Do a busywait as + # well, performance blips might cause false fail. + local ebl + ebl=$(busywait 5000 until_counter_is 500000 \ + get_mc_transmit_queue $vlan) + check_err $? "MC backlog reported by qdisc not visible in ethtool" + + stop_traffic + stop_traffic + + log_test "TC $((vlan - 10)): Qdisc reports MC backlog" +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh new file mode 100755 index 000000000000..af83efe9ccf1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ecn_test + red_test + mc_backlog_test +" +: ${QDISC:=ets} +source sch_red_core.sh + +# do_ecn_test first build 2/3 of the requested backlog and expects no marking, +# and then builds 3/2 of it and does expect marking. The values of $BACKLOG1 and +# $BACKLOG2 are far enough not to overlap, so that we can assume that if we do +# see (do not see) marking, it is actually due to the configuration of that one +# TC, and not due to configuration of the other TC leaking over. +BACKLOG1=200000 +BACKLOG2=500000 + +install_qdisc() +{ + local -a args=("$@") + + tc qdisc add dev $swp3 root handle 10: $QDISC \ + bands 8 priomap 7 6 5 4 3 2 1 0 + tc qdisc add dev $swp3 parent 10:8 handle 108: red \ + limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ + probability 1.0 avpkt 8000 burst 38 "${args[@]}" + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ + limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ + probability 1.0 avpkt 8000 burst 63 "${args[@]}" + sleep 1 +} + +uninstall_qdisc() +{ + tc qdisc del dev $swp3 parent 10:7 + tc qdisc del dev $swp3 parent 10:8 + tc qdisc del dev $swp3 root +} + +ecn_test() +{ + install_qdisc ecn + + do_ecn_test 10 $BACKLOG1 + do_ecn_test 11 $BACKLOG2 + + uninstall_qdisc +} + +red_test() +{ + install_qdisc + + do_red_test 10 $BACKLOG1 + do_red_test 11 $BACKLOG2 + + uninstall_qdisc +} + +mc_backlog_test() +{ + install_qdisc + + # Note that the backlog numbers here do not correspond to RED + # configuration, but are arbitrary. + do_mc_backlog_test 10 $BACKLOG1 + do_mc_backlog_test 11 $BACKLOG2 + + uninstall_qdisc +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +bail_on_lldpad +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh new file mode 100755 index 000000000000..76820a0e9a1b --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC=prio +source sch_red_ets.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh new file mode 100755 index 000000000000..b2217493a88e --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -0,0 +1,60 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ecn_test + red_test + mc_backlog_test +" +source sch_red_core.sh + +BACKLOG=300000 + +install_qdisc() +{ + local -a args=("$@") + + tc qdisc add dev $swp3 root handle 108: red \ + limit 1000000 min $BACKLOG max $((BACKLOG + 1)) \ + probability 1.0 avpkt 8000 burst 38 "${args[@]}" + sleep 1 +} + +uninstall_qdisc() +{ + tc qdisc del dev $swp3 root +} + +ecn_test() +{ + install_qdisc ecn + do_ecn_test 10 $BACKLOG + uninstall_qdisc +} + +red_test() +{ + install_qdisc + do_red_test 10 $BACKLOG + uninstall_qdisc +} + +mc_backlog_test() +{ + install_qdisc + # Note that the backlog value here does not correspond to RED + # configuration, but is arbitrary. + do_mc_backlog_test 10 $BACKLOG + uninstall_qdisc +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +bail_on_lldpad +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh new file mode 100755 index 000000000000..58f3a05f08af --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -0,0 +1,222 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + port_pool_test + port_tc_ip_test + port_tc_arp_test +" + +NUM_NETIFS=2 +source ../../../net/forwarding/lib.sh +source ../../../net/forwarding/devlink_lib.sh +source mlxsw_lib.sh + +SB_POOL_ING=0 +SB_POOL_EGR_CPU=10 + +SB_ITC_CPU_IP=3 +SB_ITC_CPU_ARP=2 +SB_ITC=0 + +h1_create() +{ + simple_if_init $h1 192.0.1.1/24 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.1.1/24 +} + +h2_create() +{ + simple_if_init $h2 192.0.1.2/24 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.1.2/24 +} + +sb_occ_pool_check() +{ + local dl_port=$1; shift + local pool=$1; shift + local exp_max_occ=$1 + local max_occ + local err=0 + + max_occ=$(devlink sb -j occupancy show $dl_port \ + | jq -e ".[][][\"pool\"][\"$pool\"][\"max\"]") + + if [[ "$max_occ" -ne "$exp_max_occ" ]]; then + err=1 + fi + + echo $max_occ + return $err +} + +sb_occ_itc_check() +{ + local dl_port=$1; shift + local itc=$1; shift + local exp_max_occ=$1 + local max_occ + local err=0 + + max_occ=$(devlink sb -j occupancy show $dl_port \ + | jq -e ".[][][\"itc\"][\"$itc\"][\"max\"]") + + if [[ "$max_occ" -ne "$exp_max_occ" ]]; then + err=1 + fi + + echo $max_occ + return $err +} + +sb_occ_etc_check() +{ + local dl_port=$1; shift + local etc=$1; shift + local exp_max_occ=$1; shift + local max_occ + local err=0 + + max_occ=$(devlink sb -j occupancy show $dl_port \ + | jq -e ".[][][\"etc\"][\"$etc\"][\"max\"]") + + if [[ "$max_occ" -ne "$exp_max_occ" ]]; then + err=1 + fi + + echo $max_occ + return $err +} + +port_pool_test() +{ + local exp_max_occ=288 + local max_occ + + devlink sb occupancy clearmax $DEVLINK_DEV + + $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + -t ip -q + + devlink sb occupancy snapshot $DEVLINK_DEV + + RET=0 + max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ) + check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h1) ingress pool" + + RET=0 + max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ) + check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h2) ingress pool" + + RET=0 + max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ) + check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "CPU port's egress pool" +} + +port_tc_ip_test() +{ + local exp_max_occ=288 + local max_occ + + devlink sb occupancy clearmax $DEVLINK_DEV + + $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + -t ip -q + + devlink sb occupancy snapshot $DEVLINK_DEV + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h1) ingress TC - IP packet" + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h2) ingress TC - IP packet" + + RET=0 + max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ) + check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "CPU port's egress TC - IP packet" +} + +port_tc_arp_test() +{ + local exp_max_occ=96 + local max_occ + + if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then + exp_max_occ=144 + fi + + devlink sb occupancy clearmax $DEVLINK_DEV + + $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q + + devlink sb occupancy snapshot $DEVLINK_DEV + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h1) ingress TC - ARP packet" + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h2) ingress TC - ARP packet" + + RET=0 + max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ) + check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "CPU port's egress TC - ARP packet" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + dl_port1=$(devlink_port_by_netdev $h1) + dl_port2=$(devlink_port_by_netdev $h2) + + cpu_dl_port=$(devlink_cpu_port_get) + + vrf_prepare + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py new file mode 100755 index 000000000000..0d4b9327c9b3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py @@ -0,0 +1,416 @@ +#!/usr/bin/python +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +import json as j +import random + + +class SkipTest(Exception): + pass + + +class RandomValuePicker: + """ + Class for storing shared buffer configuration. Can handle 3 different + objects, pool, tcbind and portpool. Provide an interface to get random + values for a specific object type as the follow: + 1. Pool: + - random size + + 2. TcBind: + - random pool number + - random threshold + + 3. PortPool: + - random threshold + """ + def __init__(self, pools): + self._pools = [] + for pool in pools: + self._pools.append(pool) + + def _cell_size(self): + return self._pools[0]["cell_size"] + + def _get_static_size(self, th): + # For threshold of 16, this works out to be about 12MB on Spectrum-1, + # and about 17MB on Spectrum-2. + return th * 8000 * self._cell_size() + + def _get_size(self): + return self._get_static_size(16) + + def _get_thtype(self): + return "static" + + def _get_th(self, pool): + # Threshold value could be any integer between 3 to 16 + th = random.randint(3, 16) + if pool["thtype"] == "dynamic": + return th + else: + return self._get_static_size(th) + + def _get_pool(self, direction): + ing_pools = [] + egr_pools = [] + for pool in self._pools: + if pool["type"] == "ingress": + ing_pools.append(pool) + else: + egr_pools.append(pool) + if direction == "ingress": + arr = ing_pools + else: + arr = egr_pools + return arr[random.randint(0, len(arr) - 1)] + + def get_value(self, objid): + if isinstance(objid, Pool): + if objid["pool"] in [4, 8, 9, 10]: + # The threshold type of pools 4, 8, 9 and 10 cannot be changed + raise SkipTest() + else: + return (self._get_size(), self._get_thtype()) + if isinstance(objid, TcBind): + if objid["tc"] >= 8: + # Multicast TCs cannot be changed + raise SkipTest() + else: + pool = self._get_pool(objid["type"]) + th = self._get_th(pool) + pool_n = pool["pool"] + return (pool_n, th) + if isinstance(objid, PortPool): + pool_n = objid["pool"] + pool = self._pools[pool_n] + assert pool["pool"] == pool_n + th = self._get_th(pool) + return (th,) + + +class RecordValuePickerException(Exception): + pass + + +class RecordValuePicker: + """ + Class for storing shared buffer configuration. Can handle 2 different + objects, pool and tcbind. Provide an interface to get the stored values per + object type. + """ + def __init__(self, objlist): + self._recs = [] + for item in objlist: + self._recs.append({"objid": item, "value": item.var_tuple()}) + + def get_value(self, objid): + if isinstance(objid, Pool) and objid["pool"] in [4, 8, 9, 10]: + # The threshold type of pools 4, 8, 9 and 10 cannot be changed + raise SkipTest() + if isinstance(objid, TcBind) and objid["tc"] >= 8: + # Multicast TCs cannot be changed + raise SkipTest() + for rec in self._recs: + if rec["objid"].weak_eq(objid): + return rec["value"] + raise RecordValuePickerException() + + +def run_cmd(cmd, json=False): + out = subprocess.check_output(cmd, shell=True) + if json: + return j.loads(out) + return out + + +def run_json_cmd(cmd): + return run_cmd(cmd, json=True) + + +def log_test(test_name, err_msg=None): + if err_msg: + print("\t%s" % err_msg) + print("TEST: %-80s [FAIL]" % test_name) + else: + print("TEST: %-80s [ OK ]" % test_name) + + +class CommonItem(dict): + varitems = [] + + def var_tuple(self): + ret = [] + self.varitems.sort() + for key in self.varitems: + ret.append(self[key]) + return tuple(ret) + + def weak_eq(self, other): + for key in self: + if key in self.varitems: + continue + if self[key] != other[key]: + return False + return True + + +class CommonList(list): + def get_by(self, by_obj): + for item in self: + if item.weak_eq(by_obj): + return item + return None + + def del_by(self, by_obj): + for item in self: + if item.weak_eq(by_obj): + self.remove(item) + + +class Pool(CommonItem): + varitems = ["size", "thtype"] + + def dl_set(self, dlname, size, thtype): + run_cmd("devlink sb pool set {} sb {} pool {} size {} thtype {}".format(dlname, self["sb"], + self["pool"], + size, thtype)) + + +class PoolList(CommonList): + pass + + +def get_pools(dlname, direction=None): + d = run_json_cmd("devlink sb pool show -j") + pools = PoolList() + for pooldict in d["pool"][dlname]: + if not direction or direction == pooldict["type"]: + pools.append(Pool(pooldict)) + return pools + + +def do_check_pools(dlname, pools, vp): + for pool in pools: + pre_pools = get_pools(dlname) + try: + (size, thtype) = vp.get_value(pool) + except SkipTest: + continue + pool.dl_set(dlname, size, thtype) + post_pools = get_pools(dlname) + pool = post_pools.get_by(pool) + + err_msg = None + if pool["size"] != size: + err_msg = "Incorrect pool size (got {}, expected {})".format(pool["size"], size) + if pool["thtype"] != thtype: + err_msg = "Incorrect pool threshold type (got {}, expected {})".format(pool["thtype"], thtype) + + pre_pools.del_by(pool) + post_pools.del_by(pool) + if pre_pools != post_pools: + err_msg = "Other pool setup changed as well" + log_test("pool {} of sb {} set verification".format(pool["pool"], + pool["sb"]), err_msg) + + +def check_pools(dlname, pools): + # Save defaults + record_vp = RecordValuePicker(pools) + + # For each pool, set random size and static threshold type + do_check_pools(dlname, pools, RandomValuePicker(pools)) + + # Restore defaults + do_check_pools(dlname, pools, record_vp) + + +class TcBind(CommonItem): + varitems = ["pool", "threshold"] + + def __init__(self, port, d): + super(TcBind, self).__init__(d) + self["dlportname"] = port.name + + def dl_set(self, pool, th): + run_cmd("devlink sb tc bind set {} sb {} tc {} type {} pool {} th {}".format(self["dlportname"], + self["sb"], + self["tc"], + self["type"], + pool, th)) + + +class TcBindList(CommonList): + pass + + +def get_tcbinds(ports, verify_existence=False): + d = run_json_cmd("devlink sb tc bind show -j -n") + tcbinds = TcBindList() + for port in ports: + err_msg = None + if port.name not in d["tc_bind"] or len(d["tc_bind"][port.name]) == 0: + err_msg = "No tc bind for port" + else: + for tcbinddict in d["tc_bind"][port.name]: + tcbinds.append(TcBind(port, tcbinddict)) + if verify_existence: + log_test("tc bind existence for port {} verification".format(port.name), err_msg) + return tcbinds + + +def do_check_tcbind(ports, tcbinds, vp): + for tcbind in tcbinds: + pre_tcbinds = get_tcbinds(ports) + try: + (pool, th) = vp.get_value(tcbind) + except SkipTest: + continue + tcbind.dl_set(pool, th) + post_tcbinds = get_tcbinds(ports) + tcbind = post_tcbinds.get_by(tcbind) + + err_msg = None + if tcbind["pool"] != pool: + err_msg = "Incorrect pool (got {}, expected {})".format(tcbind["pool"], pool) + if tcbind["threshold"] != th: + err_msg = "Incorrect threshold (got {}, expected {})".format(tcbind["threshold"], th) + + pre_tcbinds.del_by(tcbind) + post_tcbinds.del_by(tcbind) + if pre_tcbinds != post_tcbinds: + err_msg = "Other tc bind setup changed as well" + log_test("tc bind {}-{} of sb {} set verification".format(tcbind["dlportname"], + tcbind["tc"], + tcbind["sb"]), err_msg) + + +def check_tcbind(dlname, ports, pools): + tcbinds = get_tcbinds(ports, verify_existence=True) + + # Save defaults + record_vp = RecordValuePicker(tcbinds) + + # Bind each port and unicast TC (TCs < 8) to a random pool and a random + # threshold + do_check_tcbind(ports, tcbinds, RandomValuePicker(pools)) + + # Restore defaults + do_check_tcbind(ports, tcbinds, record_vp) + + +class PortPool(CommonItem): + varitems = ["threshold"] + + def __init__(self, port, d): + super(PortPool, self).__init__(d) + self["dlportname"] = port.name + + def dl_set(self, th): + run_cmd("devlink sb port pool set {} sb {} pool {} th {}".format(self["dlportname"], + self["sb"], + self["pool"], th)) + + +class PortPoolList(CommonList): + pass + + +def get_portpools(ports, verify_existence=False): + d = run_json_cmd("devlink sb port pool -j -n") + portpools = PortPoolList() + for port in ports: + err_msg = None + if port.name not in d["port_pool"] or len(d["port_pool"][port.name]) == 0: + err_msg = "No port pool for port" + else: + for portpooldict in d["port_pool"][port.name]: + portpools.append(PortPool(port, portpooldict)) + if verify_existence: + log_test("port pool existence for port {} verification".format(port.name), err_msg) + return portpools + + +def do_check_portpool(ports, portpools, vp): + for portpool in portpools: + pre_portpools = get_portpools(ports) + (th,) = vp.get_value(portpool) + portpool.dl_set(th) + post_portpools = get_portpools(ports) + portpool = post_portpools.get_by(portpool) + + err_msg = None + if portpool["threshold"] != th: + err_msg = "Incorrect threshold (got {}, expected {})".format(portpool["threshold"], th) + + pre_portpools.del_by(portpool) + post_portpools.del_by(portpool) + if pre_portpools != post_portpools: + err_msg = "Other port pool setup changed as well" + log_test("port pool {}-{} of sb {} set verification".format(portpool["dlportname"], + portpool["pool"], + portpool["sb"]), err_msg) + + +def check_portpool(dlname, ports, pools): + portpools = get_portpools(ports, verify_existence=True) + + # Save defaults + record_vp = RecordValuePicker(portpools) + + # For each port pool, set a random threshold + do_check_portpool(ports, portpools, RandomValuePicker(pools)) + + # Restore defaults + do_check_portpool(ports, portpools, record_vp) + + +class Port: + def __init__(self, name): + self.name = name + + +class PortList(list): + pass + + +def get_ports(dlname): + d = run_json_cmd("devlink port show -j") + ports = PortList() + for name in d["port"]: + if name.find(dlname) == 0 and d["port"][name]["flavour"] == "physical": + ports.append(Port(name)) + return ports + + +def get_device(): + devices_info = run_json_cmd("devlink -j dev info")["info"] + for d in devices_info: + if "mlxsw_spectrum" in devices_info[d]["driver"]: + return d + return None + + +class UnavailableDevlinkNameException(Exception): + pass + + +def test_sb_configuration(): + # Use static seed + random.seed(0) + + dlname = get_device() + if not dlname: + raise UnavailableDevlinkNameException() + + ports = get_ports(dlname) + pools = get_pools(dlname) + + check_pools(dlname, pools) + check_tcbind(dlname, ports, pools) + check_portpool(dlname, ports, pools) + + +test_sb_configuration() diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 7b2acba82a49..fd583a171db7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -8,8 +8,9 @@ source $lib_dir/lib.sh source $lib_dir/tc_common.sh source $lib_dir/devlink_lib.sh -if [ "$DEVLINK_VIDDID" != "15b3:cf6c" ]; then - echo "SKIP: test is tailored for Mellanox Spectrum-2" +if [[ "$DEVLINK_VIDDID" != "15b3:cf6c" && \ + "$DEVLINK_VIDDID" != "15b3:cf70" ]]; then + echo "SKIP: test is tailored for Mellanox Spectrum-2 and Spectrum-3" exit 1 fi diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh new file mode 100755 index 000000000000..68c80d0ec1ec --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh @@ -0,0 +1,186 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + shared_block_drop_test + egress_redirect_test + multi_mirror_test +" +NUM_NETIFS=2 + +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh + +switch_create() +{ + simple_if_init $swp1 192.0.2.1/24 + simple_if_init $swp2 192.0.2.2/24 +} + +switch_destroy() +{ + simple_if_fini $swp2 192.0.2.2/24 + simple_if_fini $swp1 192.0.2.1/24 +} + +shared_block_drop_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have mixed-bound + # shared block with a drop rule. + + tc qdisc add dev $swp1 ingress_block 22 clsact + check_err $? "Failed to create clsact with ingress block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_err $? "Failed to add drop rule to ingress bound block" + + tc qdisc add dev $swp2 ingress_block 22 clsact + check_err $? "Failed to create another clsact with ingress shared block" + + tc qdisc del dev $swp2 clsact + + tc qdisc add dev $swp2 egress_block 22 clsact + check_fail $? "Incorrect success to create another clsact with egress shared block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + tc qdisc add dev $swp2 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block after blocker drop rule removed" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_fail $? "Incorrect success to add drop rule to mixed bound block" + + tc qdisc del dev $swp1 clsact + + tc qdisc add dev $swp1 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_err $? "Failed to add drop rule to egress bound shared block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + log_test "shared block drop" +} + +egress_redirect_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have mirred redirect on + # egress-bound block. + + tc qdisc add dev $swp1 ingress_block 22 clsact + check_err $? "Failed to create clsact with ingress block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_err $? "Failed to add redirect rule to ingress bound block" + + tc qdisc add dev $swp2 ingress_block 22 clsact + check_err $? "Failed to create another clsact with ingress shared block" + + tc qdisc del dev $swp2 clsact + + tc qdisc add dev $swp2 egress_block 22 clsact + check_fail $? "Incorrect success to create another clsact with egress shared block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + tc qdisc add dev $swp2 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block after blocker redirect rule removed" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_fail $? "Incorrect success to add redirect rule to mixed bound block" + + tc qdisc del dev $swp1 clsact + + tc qdisc add dev $swp1 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_fail $? "Incorrect success to add redirect rule to egress bound shared block" + + tc qdisc del dev $swp2 clsact + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_fail $? "Incorrect success to add redirect rule to egress bound block" + + tc qdisc del dev $swp1 clsact + + log_test "shared block drop" +} + +multi_mirror_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have multiple mirror + # actions in a single rule. + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress mirror dev $swp2 + check_err $? "Failed to add rule with single mirror action" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress mirror dev $swp2 \ + action mirred egress mirror dev $swp1 + check_fail $? "Incorrect success to add rule with two mirror actions" + + tc qdisc del dev $swp1 clsact + + log_test "multi mirror" +} + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + + vrf_prepare + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + vrf_cleanup +} + +check_tc_shblock_support + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh index a6d733d2a4b4..cc0f07e72cf2 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh @@ -2,9 +2,9 @@ # 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 +# number of flower matches for different IPv6 addresses, then check the offload +# indication for all of the tc flower rules. 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 @@ -94,22 +94,15 @@ __tc_flower_test() 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 $MISMATCHES" + offload_count=$(tc -j -s filter show dev $h2 ingress | + jq -r '[ .[] | select(.kind == "flower") | + .options | .in_hw ]' | jq .[] | wc -l) + [[ $((offload_count - 1)) -eq $count ]] + if [[ $should_fail -eq 0 ]]; then + check_err $? "Offload mismatch" + else + check_err_fail $should_fail $? "Offload more than expacted" + fi } tc_flower_test() diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index 15eb0dc9a685..729a86cc4ede 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -9,6 +9,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS="sanitization_test offload_indication_test \ sanitization_vlan_aware_test offload_indication_vlan_aware_test" NUM_NETIFS=2 +: ${TIMEOUT:=20000} # ms source $lib_dir/lib.sh setup_prepare() @@ -470,8 +471,8 @@ offload_indication_fdb_flood_test() bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2 - bridge fdb show brport vxlan0 | grep 00:00:00:00:00:00 \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb 00:00:00:00:00:00 \ + bridge fdb show brport vxlan0 check_err $? bridge fdb del 00:00:00:00:00:00 dev vxlan0 self @@ -486,11 +487,11 @@ offload_indication_fdb_bridge_test() bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \ dst 198.51.100.2 - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 check_err $? log_test "vxlan entry offload indication - initial state" @@ -500,9 +501,9 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan0 master - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 + check_err $? log_test "vxlan entry offload indication - after removal from bridge" @@ -511,11 +512,11 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan0 master static - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 check_err $? log_test "vxlan entry offload indication - after re-add to bridge" @@ -525,9 +526,9 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 + check_err $? log_test "vxlan entry offload indication - after removal from vxlan" @@ -536,11 +537,11 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2 - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 check_err $? log_test "vxlan entry offload indication - after re-add to vxlan" @@ -558,27 +559,32 @@ offload_indication_decap_route_test() { RET=0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev vxlan0 down - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev vxlan1 down - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vxlan decap route - vxlan device down" RET=0 ip link set dev vxlan1 up - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev vxlan0 up - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - vxlan device up" @@ -586,11 +592,13 @@ offload_indication_decap_route_test() RET=0 ip address delete 198.51.100.1/32 dev lo - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? ip address add 198.51.100.1/32 dev lo - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - add local route" @@ -598,16 +606,19 @@ offload_indication_decap_route_test() RET=0 ip link set dev $swp1 nomaster - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev $swp2 nomaster - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - local ports enslavement" @@ -615,12 +626,14 @@ offload_indication_decap_route_test() RET=0 ip link del dev br0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link del dev br1 - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vxlan decap route - bridge device deletion" @@ -632,16 +645,19 @@ offload_indication_decap_route_test() ip link set dev $swp2 master br1 ip link set dev vxlan0 master br0 ip link set dev vxlan1 master br1 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link del dev vxlan0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link del dev vxlan1 - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vxlan decap route - vxlan device deletion" @@ -656,12 +672,15 @@ check_fdb_offloaded() local mac=00:11:22:33:44:55 local zmac=00:00:00:00:00:00 - bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $mac self \ + bridge fdb show dev vxlan0 check_err $? - bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $mac master \ + bridge fdb show dev vxlan0 check_err $? - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 check_err $? } @@ -672,13 +691,15 @@ check_vxlan_fdb_not_offloaded() bridge fdb show dev vxlan0 | grep $mac | grep -q self check_err $? - bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $mac self \ + bridge fdb show dev vxlan0 + check_err $? bridge fdb show dev vxlan0 | grep $zmac | grep -q self check_err $? - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 + check_err $? } check_bridge_fdb_not_offloaded() @@ -688,8 +709,9 @@ check_bridge_fdb_not_offloaded() bridge fdb show dev vxlan0 | grep $mac | grep -q master check_err $? - bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $mac master \ + bridge fdb show dev vxlan0 + check_err $? } __offload_indication_join_vxlan_first() @@ -771,12 +793,14 @@ __offload_indication_join_vxlan_last() ip link set dev $swp1 master br0 - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 + check_err $? ip link set dev vxlan0 master br0 - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 check_err $? log_test "offload indication - attach vxlan last" @@ -866,8 +890,9 @@ sanitization_vlan_aware_test() ip link set dev $swp1 master br0 &> /dev/null check_fail $? - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vlan-aware - failed enslavement to bridge due to conflict" @@ -929,11 +954,11 @@ offload_indication_vlan_aware_fdb_test() bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self master static \ dst 198.51.100.2 vlan 10 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 check_err $? log_test "vxlan entry offload indication - initial state" @@ -943,9 +968,9 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan10 master vlan 10 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 + check_err $? log_test "vxlan entry offload indication - after removal from bridge" @@ -954,11 +979,11 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan10 master static vlan 10 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 check_err $? log_test "vxlan entry offload indication - after re-add to bridge" @@ -968,9 +993,9 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 + check_err $? log_test "vxlan entry offload indication - after removal from vxlan" @@ -979,11 +1004,11 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst 198.51.100.2 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 check_err $? log_test "vxlan entry offload indication - after re-add to vxlan" @@ -995,28 +1020,31 @@ offload_indication_vlan_aware_decap_route_test() { RET=0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? # Toggle PVID flag on one VxLAN device and make sure route is still # marked as offloaded bridge vlan add vid 10 dev vxlan10 untagged - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? # Toggle PVID flag on second VxLAN device and make sure route is no # longer marked as offloaded bridge vlan add vid 20 dev vxlan20 untagged - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? # Toggle PVID flag back and make sure route is marked as offloaded bridge vlan add vid 10 dev vxlan10 pvid untagged bridge vlan add vid 20 dev vxlan20 pvid untagged - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - vni map/unmap" @@ -1069,33 +1097,33 @@ offload_indication_vlan_aware_l3vni_test() ip link set dev vxlan0 master br0 bridge vlan add dev vxlan0 vid 10 pvid untagged - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 check_err $? "vxlan tunnel not offloaded when should" # Configure a VLAN interface and make sure tunnel is offloaded ip link add link br0 name br10 up type vlan id 10 sysctl_set net.ipv6.conf.br10.disable_ipv6 0 ip -6 address add 2001:db8:1::1/64 dev br10 - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 check_err $? "vxlan tunnel not offloaded when should" # Unlink the VXLAN device, make sure tunnel is no longer offloaded, # then add it back to the bridge and make sure it is offloaded ip link set dev vxlan0 nomaster - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload - check_fail $? "vxlan tunnel offloaded after unlinked from bridge" + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 + check_err $? "vxlan tunnel offloaded after unlinked from bridge" ip link set dev vxlan0 master br0 - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload - check_fail $? "vxlan tunnel offloaded despite no matching vid" + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 + check_err $? "vxlan tunnel offloaded despite no matching vid" bridge vlan add dev vxlan0 vid 10 pvid untagged - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 check_err $? "vxlan tunnel not offloaded after adding vid" log_test "vxlan - l3 vni" diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh index f101ab9441e2..437d32bd4cfd 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh @@ -103,6 +103,11 @@ trap_metadata_test() for trap_name in $(devlink_traps_get); do devlink_trap_metadata_test $trap_name "input_port" check_err $? "Input port not reported as metadata of trap $trap_name" + if [ $trap_name == "ingress_flow_action_drop" ] || + [ $trap_name == "egress_flow_action_drop" ]; then + devlink_trap_metadata_test $trap_name "flow_action_cookie" + check_err $? "Flow action cookie not reported as metadata of trap $trap_name" + fi done log_test "Trap metadata" diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index cd1f5b3a7774..d6e106fbce11 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -2,7 +2,7 @@ all: TEST_PROGS := ftracetest -TEST_FILES := test.d +TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* include ../lib.mk diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile index 3876d8d62494..1acc9e1fa3fb 100644 --- a/tools/testing/selftests/livepatch/Makefile +++ b/tools/testing/selftests/livepatch/Makefile @@ -8,4 +8,6 @@ TEST_PROGS := \ test-state.sh \ test-ftrace.sh +TEST_FILES := settings + include ../lib.mk diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 40b076983239..0df6d8942721 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -35,6 +35,12 @@ if [ $? -ne 0 ]; then exit 1 fi +devlink dev help 2>&1 | grep info &> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing devlink dev info support" + exit 1 +fi + ############################################################################## # Devlink helpers @@ -373,6 +379,7 @@ devlink_trap_drop_test() local trap_name=$1; shift local group_name=$1; shift local dev=$1; shift + local handle=$1; shift # This is the common part of all the tests. It checks that stats are # initially idle, then non-idle after changing the trap action and @@ -397,7 +404,7 @@ devlink_trap_drop_test() devlink_trap_group_stats_idle_test $group_name check_err $? "Trap group stats not idle after setting action to drop" - tc_check_packets "dev $dev egress" 101 0 + tc_check_packets "dev $dev egress" $handle 0 check_err $? "Packets were not dropped" } @@ -406,7 +413,25 @@ devlink_trap_drop_cleanup() local mz_pid=$1; shift local dev=$1; shift local proto=$1; shift + local pref=$1; shift + local handle=$1; shift kill $mz_pid && wait $mz_pid &> /dev/null - tc filter del dev $dev egress protocol $proto pref 1 handle 101 flower + tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower +} + +devlink_port_by_netdev() +{ + local if_name=$1 + + devlink -j port show $if_name | jq -e '.[] | keys' | jq -r '.[]' +} + +devlink_cpu_port_get() +{ + local cpu_dl_port_num=$(devlink port list | grep "$DEVLINK_DEV" | + grep cpu | cut -d/ -f3 | cut -d: -f1 | + sed -n '1p') + + echo "$DEVLINK_DEV/$cpu_dl_port_num" } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 2f5da414aaa7..83fd15e3e545 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -248,6 +248,33 @@ busywait() done } +not() +{ + "$@" + [[ $? != 0 ]] +} + +grep_bridge_fdb() +{ + local addr=$1; shift + local word + local flag + + if [ "$1" == "self" ] || [ "$1" == "master" ]; then + word=$1; shift + if [ "$1" == "-v" ]; then + flag=$1; shift + fi + fi + + $@ | grep $addr | grep $flag "$word" +} + +wait_for_offload() +{ + "$@" | grep -q offload +} + until_counter_is() { local value=$1; shift @@ -607,6 +634,16 @@ ethtool_stats_get() ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 } +qdisc_stats_get() +{ + local dev=$1; shift + local handle=$1; shift + local selector=$1; shift + + tc -j -s qdisc show dev "$dev" \ + | jq '.[] | select(.handle == "'"$handle"'") | '"$selector" +} + humanize() { local speed=$1; shift @@ -1132,18 +1169,29 @@ flood_test() flood_multicast_test $br_port $host1_if $host2_if } -start_traffic() +__start_traffic() { + local proto=$1; shift local h_in=$1; shift # Where the traffic egresses the host local sip=$1; shift local dip=$1; shift local dmac=$1; shift $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ - -a own -b $dmac -t udp -q & + -a own -b $dmac -t "$proto" -q "$@" & sleep 1 } +start_traffic() +{ + __start_traffic udp "$@" +} + +start_tcp_traffic() +{ + __start_traffic tcp "$@" +} + stop_traffic() { # Suppress noise from killing mausezahn. diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 93de52016dde..ba450e62dc5b 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,6 +8,8 @@ TEST_PROGS := mptcp_connect.sh TEST_GEN_FILES = mptcp_connect +TEST_FILES := settings + EXTRA_CLEAN := *.pcap include ../../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index aca21dde102a..5a4938d6dcf2 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -13,11 +13,12 @@ KSELFTEST_SKIP=4 # Available test groups: +# - reported_issues: check for issues that were reported in the past # - correctness: check that packets match given entries, and only those # - concurrency: attempt races between insertion, deletion and lookup # - timeout: check that packets match entries until they expire # - performance: estimate matching rate, compare with rbtree and hash baselines -TESTS="correctness concurrency timeout" +TESTS="reported_issues correctness concurrency timeout" [ "${quicktest}" != "1" ] && TESTS="${TESTS} performance" # Set types, defined by TYPE_ variables below @@ -25,6 +26,9 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port net_port_mac_proto_net" +# Reported bugs, also described by TYPE_ variables below +BUGS="flush_remove_add" + # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh @@ -327,6 +331,12 @@ flood_spec ip daddr . tcp dport . meta l4proto . ip saddr perf_duration 0 " +# Definition of tests for bugs reported in the past: +# display display text for test report +TYPE_flush_remove_add=" +display Add two elements, flush, re-add +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -440,6 +450,8 @@ setup_set() { # Check that at least one of the needed tools is available check_tools() { + [ -z "${tools}" ] && return 0 + __tools= for tool in ${tools}; do if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \ @@ -1025,7 +1037,7 @@ format_noconcat() { add() { if ! nft add element inet filter test "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1045,7 +1057,7 @@ add_perf() { add_perf_norange() { if ! nft add element netdev perf norange "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1054,7 +1066,7 @@ add_perf_norange() { add_perf_noconcat() { if ! nft add element netdev perf noconcat "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1063,7 +1075,7 @@ add_perf_noconcat() { del() { if ! nft delete element inet filter test "${1}"; then err "Failed to delete ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1134,7 +1146,7 @@ send_match() { err " $(for f in ${src}; do eval format_\$f "${2}"; printf ' '; done)" err "should have matched ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi nft reset counter inet filter test >/dev/null @@ -1160,7 +1172,7 @@ send_nomatch() { err " $(for f in ${src}; do eval format_\$f "${2}"; printf ' '; done)" err "should not have matched ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1430,6 +1442,23 @@ test_performance() { kill "${perf_pid}" } +test_bug_flush_remove_add() { + set_cmd='{ set s { type ipv4_addr . inet_service; flags interval; }; }' + elem1='{ 10.0.0.1 . 22-25, 10.0.0.1 . 10-20 }' + elem2='{ 10.0.0.1 . 10-20, 10.0.0.1 . 22-25 }' + for i in `seq 1 100`; do + nft add table t ${set_cmd} || return ${KSELFTEST_SKIP} + nft add element t s ${elem1} 2>/dev/null || return 1 + nft flush set t s 2>/dev/null || return 1 + nft add element t s ${elem2} 2>/dev/null || return 1 + done + nft flush ruleset +} + +test_reported_issues() { + eval test_bug_"${subtest}" +} + # Run everything in a separate network namespace [ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } tmp="$(mktemp)" @@ -1438,9 +1467,15 @@ trap cleanup EXIT # Entry point for test runs passed=0 for name in ${TESTS}; do - printf "TEST: %s\n" "${name}" - for type in ${TYPES}; do - eval desc=\$TYPE_"${type}" + printf "TEST: %s\n" "$(echo ${name} | tr '_' ' ')" + if [ "${name}" = "reported_issues" ]; then + SUBTESTS="${BUGS}" + else + SUBTESTS="${TYPES}" + fi + + for subtest in ${SUBTESTS}; do + eval desc=\$TYPE_"${subtest}" IFS=' ' for __line in ${desc}; do diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index d6469535630a..2af9d39a9716 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif -CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \ +CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) LDLIBS += -lpthread @@ -19,6 +19,8 @@ TEST_GEN_PROGS_EXTENDED = librseq.so TEST_PROGS = run_param_test.sh +TEST_FILES := settings + include ../lib.mk $(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index 2d93d65723c9..55198ecc04db 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -6,4 +6,6 @@ TEST_GEN_PROGS = rtctest TEST_GEN_PROGS_EXTENDED = setdate +TEST_FILES := settings + include ../lib.mk diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index 222174a2de01..afb9187b46a7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -856,5 +856,203 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "47a0", + "name": "Add basic filter with u32 ematch u32/zero offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xffffffff at 0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabbccdd/ffffffff at 0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "849f", + "name": "Add basic filter with u32 ematch u32/positive offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11227788 0x1ffff0f0 at 12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11227080/1ffff0f0 at 12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "d288", + "name": "Add basic filter with u32 ematch u32/missing offset", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11227788 0xffffffff at)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11227788/ffffffff at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "4998", + "name": "Add basic filter with u32 ematch u32/missing AT keyword", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x77889900 0xfffff0f0 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77889900/fffff0f0 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1f0a", + "name": "Add basic filter with u32 ematch u32/missing value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 at 12)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "848e", + "name": "Add basic filter with u32 ematch u32/non-numeric value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 zero 0xffff at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ffff0000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "f748", + "name": "Add basic filter with u32 ematch u32/non-numeric mask", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11223344 mask at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11223344/00000000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "55a6", + "name": "Add basic filter with u32 ematch u32/negative offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xff00ff00 at -12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aa00cc00/ff00ff00 at -12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "7282", + "name": "Add basic filter with u32 ematch u32/nexthdr+ offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xffffffff at nexthdr+0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabbccdd/ffffffff at nexthdr\\+0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] } ] |